sizhkhy commited on
Commit
cb0bd09
·
verified ·
1 Parent(s): 5cdb702

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-410/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: unsloth/Llama-3.2-3B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - unsloth
9
+ - generated_from_trainer
10
+ model-index:
11
+ - name: llm3br256
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # llm3br256
19
+
20
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the brasingh_publicis_f5f dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0205
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 4
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 32
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 5.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.1038 | 0.0606 | 5 | 0.0979 |
57
+ | 0.0759 | 0.1212 | 10 | 0.0765 |
58
+ | 0.069 | 0.1818 | 15 | 0.0683 |
59
+ | 0.0729 | 0.2424 | 20 | 0.0620 |
60
+ | 0.0545 | 0.3030 | 25 | 0.0571 |
61
+ | 0.0589 | 0.3636 | 30 | 0.0528 |
62
+ | 0.0461 | 0.4242 | 35 | 0.0501 |
63
+ | 0.0522 | 0.4848 | 40 | 0.0493 |
64
+ | 0.052 | 0.5455 | 45 | 0.0483 |
65
+ | 0.0459 | 0.6061 | 50 | 0.0458 |
66
+ | 0.0363 | 0.6667 | 55 | 0.0434 |
67
+ | 0.0553 | 0.7273 | 60 | 0.0418 |
68
+ | 0.0444 | 0.7879 | 65 | 0.0403 |
69
+ | 0.0469 | 0.8485 | 70 | 0.0397 |
70
+ | 0.0417 | 0.9091 | 75 | 0.0386 |
71
+ | 0.0388 | 0.9697 | 80 | 0.0372 |
72
+ | 0.0309 | 1.0303 | 85 | 0.0358 |
73
+ | 0.0487 | 1.0909 | 90 | 0.0354 |
74
+ | 0.0348 | 1.1515 | 95 | 0.0340 |
75
+ | 0.0308 | 1.2121 | 100 | 0.0334 |
76
+ | 0.0318 | 1.2727 | 105 | 0.0330 |
77
+ | 0.028 | 1.3333 | 110 | 0.0322 |
78
+ | 0.0311 | 1.3939 | 115 | 0.0321 |
79
+ | 0.0382 | 1.4545 | 120 | 0.0315 |
80
+ | 0.0316 | 1.5152 | 125 | 0.0304 |
81
+ | 0.0278 | 1.5758 | 130 | 0.0299 |
82
+ | 0.0285 | 1.6364 | 135 | 0.0292 |
83
+ | 0.0257 | 1.6970 | 140 | 0.0285 |
84
+ | 0.0244 | 1.7576 | 145 | 0.0281 |
85
+ | 0.0256 | 1.8182 | 150 | 0.0278 |
86
+ | 0.0338 | 1.8788 | 155 | 0.0270 |
87
+ | 0.0309 | 1.9394 | 160 | 0.0262 |
88
+ | 0.0378 | 2.0 | 165 | 0.0261 |
89
+ | 0.0275 | 2.0606 | 170 | 0.0263 |
90
+ | 0.0225 | 2.1212 | 175 | 0.0259 |
91
+ | 0.0232 | 2.1818 | 180 | 0.0256 |
92
+ | 0.0193 | 2.2424 | 185 | 0.0255 |
93
+ | 0.0251 | 2.3030 | 190 | 0.0253 |
94
+ | 0.0228 | 2.3636 | 195 | 0.0249 |
95
+ | 0.0195 | 2.4242 | 200 | 0.0249 |
96
+ | 0.0219 | 2.4848 | 205 | 0.0241 |
97
+ | 0.0184 | 2.5455 | 210 | 0.0238 |
98
+ | 0.0199 | 2.6061 | 215 | 0.0236 |
99
+ | 0.023 | 2.6667 | 220 | 0.0232 |
100
+ | 0.0227 | 2.7273 | 225 | 0.0234 |
101
+ | 0.0206 | 2.7879 | 230 | 0.0230 |
102
+ | 0.0217 | 2.8485 | 235 | 0.0225 |
103
+ | 0.0186 | 2.9091 | 240 | 0.0224 |
104
+ | 0.0201 | 2.9697 | 245 | 0.0220 |
105
+ | 0.0147 | 3.0303 | 250 | 0.0220 |
106
+ | 0.0142 | 3.0909 | 255 | 0.0226 |
107
+ | 0.0149 | 3.1515 | 260 | 0.0218 |
108
+ | 0.0151 | 3.2121 | 265 | 0.0215 |
109
+ | 0.0174 | 3.2727 | 270 | 0.0217 |
110
+ | 0.0172 | 3.3333 | 275 | 0.0213 |
111
+ | 0.017 | 3.3939 | 280 | 0.0211 |
112
+ | 0.0223 | 3.4545 | 285 | 0.0212 |
113
+ | 0.0144 | 3.5152 | 290 | 0.0211 |
114
+ | 0.0125 | 3.5758 | 295 | 0.0208 |
115
+ | 0.0163 | 3.6364 | 300 | 0.0207 |
116
+ | 0.015 | 3.6970 | 305 | 0.0207 |
117
+ | 0.0154 | 3.7576 | 310 | 0.0206 |
118
+ | 0.0186 | 3.8182 | 315 | 0.0203 |
119
+ | 0.0135 | 3.8788 | 320 | 0.0202 |
120
+ | 0.0159 | 3.9394 | 325 | 0.0201 |
121
+ | 0.0211 | 4.0 | 330 | 0.0200 |
122
+ | 0.0134 | 4.0606 | 335 | 0.0202 |
123
+ | 0.0113 | 4.1212 | 340 | 0.0206 |
124
+ | 0.0117 | 4.1818 | 345 | 0.0208 |
125
+ | 0.0108 | 4.2424 | 350 | 0.0209 |
126
+ | 0.012 | 4.3030 | 355 | 0.0207 |
127
+ | 0.0111 | 4.3636 | 360 | 0.0206 |
128
+ | 0.0118 | 4.4242 | 365 | 0.0205 |
129
+ | 0.0099 | 4.4848 | 370 | 0.0206 |
130
+ | 0.0118 | 4.5455 | 375 | 0.0206 |
131
+ | 0.0119 | 4.6061 | 380 | 0.0206 |
132
+ | 0.0114 | 4.6667 | 385 | 0.0206 |
133
+ | 0.0109 | 4.7273 | 390 | 0.0206 |
134
+ | 0.0124 | 4.7879 | 395 | 0.0205 |
135
+ | 0.0111 | 4.8485 | 400 | 0.0206 |
136
+ | 0.012 | 4.9091 | 405 | 0.0206 |
137
+ | 0.0104 | 4.9697 | 410 | 0.0205 |
138
+
139
+
140
+ ### Framework versions
141
+
142
+ - PEFT 0.12.0
143
+ - Transformers 4.46.1
144
+ - Pytorch 2.4.0+cu121
145
+ - Datasets 3.1.0
146
+ - Tokenizers 0.20.3
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 256,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 256,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9e21e8d743b135412f1e3ec2c11e1ffaf214421bd6cbe51c4d8c4f604bffaa
3
+ size 1556140392
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.96969696969697,
3
+ "eval_loss": 0.020535212010145187,
4
+ "eval_runtime": 6.2115,
5
+ "eval_samples_per_second": 8.05,
6
+ "eval_steps_per_second": 2.093,
7
+ "total_flos": 6.27193584892674e+17,
8
+ "train_loss": 0.027697906577278202,
9
+ "train_runtime": 5078.5288,
10
+ "train_samples_per_second": 2.598,
11
+ "train_steps_per_second": 0.081
12
+ }
checkpoint-410/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Llama-3.2-3B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-410/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 256,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 256,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-410/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9e21e8d743b135412f1e3ec2c11e1ffaf214421bd6cbe51c4d8c4f604bffaa
3
+ size 1556140392
checkpoint-410/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:346857d06a4d50f2d5090eaf9df3a8a9ced5250a6f4fd409939bc36397535c81
3
+ size 3112505578
checkpoint-410/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0a87f49f383525426454159a1127d3d94dd9fb46840bf4641d6f309437aff2
3
+ size 14308
checkpoint-410/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354ed2e29ea4b7ad4203450764e631ed60090962c2c9d8b07ecf401ed84bd36f
3
+ size 1064
checkpoint-410/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
checkpoint-410/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-410/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-410/trainer_state.json ADDED
@@ -0,0 +1,3559 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.020535213872790337,
3
+ "best_model_checkpoint": "/home/paperspace/Data/models/brasingh_publicis_f5f/llm3br256/checkpoint-410",
4
+ "epoch": 4.96969696969697,
5
+ "eval_steps": 5,
6
+ "global_step": 410,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.012121212121212121,
13
+ "grad_norm": 0.17719489336013794,
14
+ "learning_rate": 2.4390243902439027e-06,
15
+ "loss": 0.103,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.024242424242424242,
20
+ "grad_norm": 0.1567779779434204,
21
+ "learning_rate": 4.8780487804878055e-06,
22
+ "loss": 0.11,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03636363636363636,
27
+ "grad_norm": 0.1601039469242096,
28
+ "learning_rate": 7.317073170731707e-06,
29
+ "loss": 0.1104,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.048484848484848485,
34
+ "grad_norm": 0.16313816606998444,
35
+ "learning_rate": 9.756097560975611e-06,
36
+ "loss": 0.1076,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.06060606060606061,
41
+ "grad_norm": 0.15266162157058716,
42
+ "learning_rate": 1.2195121951219513e-05,
43
+ "loss": 0.1038,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.06060606060606061,
48
+ "eval_loss": 0.09789121896028519,
49
+ "eval_runtime": 8.116,
50
+ "eval_samples_per_second": 6.161,
51
+ "eval_steps_per_second": 1.602,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.07272727272727272,
56
+ "grad_norm": 0.1329907476902008,
57
+ "learning_rate": 1.4634146341463415e-05,
58
+ "loss": 0.0995,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.08484848484848485,
63
+ "grad_norm": 0.09588994085788727,
64
+ "learning_rate": 1.707317073170732e-05,
65
+ "loss": 0.0833,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.09696969696969697,
70
+ "grad_norm": 0.07421080023050308,
71
+ "learning_rate": 1.9512195121951222e-05,
72
+ "loss": 0.0756,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.10909090909090909,
77
+ "grad_norm": 0.0636032298207283,
78
+ "learning_rate": 2.1951219512195124e-05,
79
+ "loss": 0.0681,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.12121212121212122,
84
+ "grad_norm": 0.07186830043792725,
85
+ "learning_rate": 2.4390243902439026e-05,
86
+ "loss": 0.0759,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.12121212121212122,
91
+ "eval_loss": 0.07647334039211273,
92
+ "eval_runtime": 6.2195,
93
+ "eval_samples_per_second": 8.039,
94
+ "eval_steps_per_second": 2.09,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.13333333333333333,
99
+ "grad_norm": 0.07592587172985077,
100
+ "learning_rate": 2.682926829268293e-05,
101
+ "loss": 0.0757,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.14545454545454545,
106
+ "grad_norm": 0.057555243372917175,
107
+ "learning_rate": 2.926829268292683e-05,
108
+ "loss": 0.0733,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.15757575757575756,
113
+ "grad_norm": 0.04685232415795326,
114
+ "learning_rate": 3.170731707317073e-05,
115
+ "loss": 0.0751,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.1696969696969697,
120
+ "grad_norm": 0.04220229387283325,
121
+ "learning_rate": 3.414634146341464e-05,
122
+ "loss": 0.0784,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.18181818181818182,
127
+ "grad_norm": 0.050287775695323944,
128
+ "learning_rate": 3.6585365853658535e-05,
129
+ "loss": 0.069,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.18181818181818182,
134
+ "eval_loss": 0.06831522285938263,
135
+ "eval_runtime": 6.1929,
136
+ "eval_samples_per_second": 8.074,
137
+ "eval_steps_per_second": 2.099,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.19393939393939394,
142
+ "grad_norm": 0.04325024411082268,
143
+ "learning_rate": 3.9024390243902444e-05,
144
+ "loss": 0.0691,
145
+ "step": 16
146
+ },
147
+ {
148
+ "epoch": 0.20606060606060606,
149
+ "grad_norm": 0.037937626242637634,
150
+ "learning_rate": 4.146341463414634e-05,
151
+ "loss": 0.0813,
152
+ "step": 17
153
+ },
154
+ {
155
+ "epoch": 0.21818181818181817,
156
+ "grad_norm": 0.03867847099900246,
157
+ "learning_rate": 4.390243902439025e-05,
158
+ "loss": 0.065,
159
+ "step": 18
160
+ },
161
+ {
162
+ "epoch": 0.23030303030303031,
163
+ "grad_norm": 0.03792285919189453,
164
+ "learning_rate": 4.634146341463415e-05,
165
+ "loss": 0.0617,
166
+ "step": 19
167
+ },
168
+ {
169
+ "epoch": 0.24242424242424243,
170
+ "grad_norm": 0.03528020903468132,
171
+ "learning_rate": 4.878048780487805e-05,
172
+ "loss": 0.0729,
173
+ "step": 20
174
+ },
175
+ {
176
+ "epoch": 0.24242424242424243,
177
+ "eval_loss": 0.062009546905756,
178
+ "eval_runtime": 6.1891,
179
+ "eval_samples_per_second": 8.079,
180
+ "eval_steps_per_second": 2.1,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.2545454545454545,
185
+ "grad_norm": 0.031467072665691376,
186
+ "learning_rate": 5.121951219512195e-05,
187
+ "loss": 0.0602,
188
+ "step": 21
189
+ },
190
+ {
191
+ "epoch": 0.26666666666666666,
192
+ "grad_norm": 0.03714953735470772,
193
+ "learning_rate": 5.365853658536586e-05,
194
+ "loss": 0.0772,
195
+ "step": 22
196
+ },
197
+ {
198
+ "epoch": 0.2787878787878788,
199
+ "grad_norm": 0.03779144585132599,
200
+ "learning_rate": 5.6097560975609764e-05,
201
+ "loss": 0.0584,
202
+ "step": 23
203
+ },
204
+ {
205
+ "epoch": 0.2909090909090909,
206
+ "grad_norm": 0.030055589973926544,
207
+ "learning_rate": 5.853658536585366e-05,
208
+ "loss": 0.0568,
209
+ "step": 24
210
+ },
211
+ {
212
+ "epoch": 0.30303030303030304,
213
+ "grad_norm": 0.029797468334436417,
214
+ "learning_rate": 6.097560975609756e-05,
215
+ "loss": 0.0545,
216
+ "step": 25
217
+ },
218
+ {
219
+ "epoch": 0.30303030303030304,
220
+ "eval_loss": 0.057142239063978195,
221
+ "eval_runtime": 6.2052,
222
+ "eval_samples_per_second": 8.058,
223
+ "eval_steps_per_second": 2.095,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 0.3151515151515151,
228
+ "grad_norm": 0.029303744435310364,
229
+ "learning_rate": 6.341463414634146e-05,
230
+ "loss": 0.0591,
231
+ "step": 26
232
+ },
233
+ {
234
+ "epoch": 0.32727272727272727,
235
+ "grad_norm": 0.03735222667455673,
236
+ "learning_rate": 6.585365853658538e-05,
237
+ "loss": 0.0836,
238
+ "step": 27
239
+ },
240
+ {
241
+ "epoch": 0.3393939393939394,
242
+ "grad_norm": 0.02950606681406498,
243
+ "learning_rate": 6.829268292682928e-05,
244
+ "loss": 0.0574,
245
+ "step": 28
246
+ },
247
+ {
248
+ "epoch": 0.3515151515151515,
249
+ "grad_norm": 0.02479255013167858,
250
+ "learning_rate": 7.073170731707317e-05,
251
+ "loss": 0.0506,
252
+ "step": 29
253
+ },
254
+ {
255
+ "epoch": 0.36363636363636365,
256
+ "grad_norm": 0.030447915196418762,
257
+ "learning_rate": 7.317073170731707e-05,
258
+ "loss": 0.0589,
259
+ "step": 30
260
+ },
261
+ {
262
+ "epoch": 0.36363636363636365,
263
+ "eval_loss": 0.05275052413344383,
264
+ "eval_runtime": 6.1946,
265
+ "eval_samples_per_second": 8.072,
266
+ "eval_steps_per_second": 2.099,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.37575757575757573,
271
+ "grad_norm": 0.029138660058379173,
272
+ "learning_rate": 7.560975609756099e-05,
273
+ "loss": 0.0536,
274
+ "step": 31
275
+ },
276
+ {
277
+ "epoch": 0.3878787878787879,
278
+ "grad_norm": 0.029026566073298454,
279
+ "learning_rate": 7.804878048780489e-05,
280
+ "loss": 0.0454,
281
+ "step": 32
282
+ },
283
+ {
284
+ "epoch": 0.4,
285
+ "grad_norm": 0.03538930043578148,
286
+ "learning_rate": 8.048780487804879e-05,
287
+ "loss": 0.0727,
288
+ "step": 33
289
+ },
290
+ {
291
+ "epoch": 0.4121212121212121,
292
+ "grad_norm": 0.028354594483971596,
293
+ "learning_rate": 8.292682926829268e-05,
294
+ "loss": 0.0557,
295
+ "step": 34
296
+ },
297
+ {
298
+ "epoch": 0.42424242424242425,
299
+ "grad_norm": 0.02743169106543064,
300
+ "learning_rate": 8.53658536585366e-05,
301
+ "loss": 0.0461,
302
+ "step": 35
303
+ },
304
+ {
305
+ "epoch": 0.42424242424242425,
306
+ "eval_loss": 0.05005570873618126,
307
+ "eval_runtime": 6.192,
308
+ "eval_samples_per_second": 8.075,
309
+ "eval_steps_per_second": 2.099,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.43636363636363634,
314
+ "grad_norm": 0.03530753031373024,
315
+ "learning_rate": 8.78048780487805e-05,
316
+ "loss": 0.0627,
317
+ "step": 36
318
+ },
319
+ {
320
+ "epoch": 0.4484848484848485,
321
+ "grad_norm": 0.02797996811568737,
322
+ "learning_rate": 9.02439024390244e-05,
323
+ "loss": 0.0527,
324
+ "step": 37
325
+ },
326
+ {
327
+ "epoch": 0.46060606060606063,
328
+ "grad_norm": 0.022809529677033424,
329
+ "learning_rate": 9.26829268292683e-05,
330
+ "loss": 0.0509,
331
+ "step": 38
332
+ },
333
+ {
334
+ "epoch": 0.4727272727272727,
335
+ "grad_norm": 0.02468150481581688,
336
+ "learning_rate": 9.51219512195122e-05,
337
+ "loss": 0.0488,
338
+ "step": 39
339
+ },
340
+ {
341
+ "epoch": 0.48484848484848486,
342
+ "grad_norm": 0.030917035415768623,
343
+ "learning_rate": 9.75609756097561e-05,
344
+ "loss": 0.0522,
345
+ "step": 40
346
+ },
347
+ {
348
+ "epoch": 0.48484848484848486,
349
+ "eval_loss": 0.049276672303676605,
350
+ "eval_runtime": 6.1874,
351
+ "eval_samples_per_second": 8.081,
352
+ "eval_steps_per_second": 2.101,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.49696969696969695,
357
+ "grad_norm": 0.026523206382989883,
358
+ "learning_rate": 0.0001,
359
+ "loss": 0.0463,
360
+ "step": 41
361
+ },
362
+ {
363
+ "epoch": 0.509090909090909,
364
+ "grad_norm": 0.028745442628860474,
365
+ "learning_rate": 9.999818789066165e-05,
366
+ "loss": 0.0433,
367
+ "step": 42
368
+ },
369
+ {
370
+ "epoch": 0.5212121212121212,
371
+ "grad_norm": 0.026402153074741364,
372
+ "learning_rate": 9.999275169399614e-05,
373
+ "loss": 0.0393,
374
+ "step": 43
375
+ },
376
+ {
377
+ "epoch": 0.5333333333333333,
378
+ "grad_norm": 0.02671145275235176,
379
+ "learning_rate": 9.998369180404283e-05,
380
+ "loss": 0.044,
381
+ "step": 44
382
+ },
383
+ {
384
+ "epoch": 0.5454545454545454,
385
+ "grad_norm": 0.034986190497875214,
386
+ "learning_rate": 9.997100887750215e-05,
387
+ "loss": 0.052,
388
+ "step": 45
389
+ },
390
+ {
391
+ "epoch": 0.5454545454545454,
392
+ "eval_loss": 0.04825693741440773,
393
+ "eval_runtime": 6.1973,
394
+ "eval_samples_per_second": 8.068,
395
+ "eval_steps_per_second": 2.098,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.5575757575757576,
400
+ "grad_norm": 0.029590139165520668,
401
+ "learning_rate": 9.995470383368808e-05,
402
+ "loss": 0.0436,
403
+ "step": 46
404
+ },
405
+ {
406
+ "epoch": 0.5696969696969697,
407
+ "grad_norm": 0.03095312975347042,
408
+ "learning_rate": 9.99347778544615e-05,
409
+ "loss": 0.0431,
410
+ "step": 47
411
+ },
412
+ {
413
+ "epoch": 0.5818181818181818,
414
+ "grad_norm": 0.030565602704882622,
415
+ "learning_rate": 9.991123238414455e-05,
416
+ "loss": 0.0526,
417
+ "step": 48
418
+ },
419
+ {
420
+ "epoch": 0.593939393939394,
421
+ "grad_norm": 0.027898119762539864,
422
+ "learning_rate": 9.98840691294159e-05,
423
+ "loss": 0.0447,
424
+ "step": 49
425
+ },
426
+ {
427
+ "epoch": 0.6060606060606061,
428
+ "grad_norm": 0.03219461813569069,
429
+ "learning_rate": 9.985329005918702e-05,
430
+ "loss": 0.0459,
431
+ "step": 50
432
+ },
433
+ {
434
+ "epoch": 0.6060606060606061,
435
+ "eval_loss": 0.045825447887182236,
436
+ "eval_runtime": 6.1916,
437
+ "eval_samples_per_second": 8.075,
438
+ "eval_steps_per_second": 2.1,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.6181818181818182,
443
+ "grad_norm": 0.02641221322119236,
444
+ "learning_rate": 9.981889740445958e-05,
445
+ "loss": 0.0417,
446
+ "step": 51
447
+ },
448
+ {
449
+ "epoch": 0.6303030303030303,
450
+ "grad_norm": 0.028501464053988457,
451
+ "learning_rate": 9.978089365816357e-05,
452
+ "loss": 0.0446,
453
+ "step": 52
454
+ },
455
+ {
456
+ "epoch": 0.6424242424242425,
457
+ "grad_norm": 0.0260939784348011,
458
+ "learning_rate": 9.973928157497674e-05,
459
+ "loss": 0.0451,
460
+ "step": 53
461
+ },
462
+ {
463
+ "epoch": 0.6545454545454545,
464
+ "grad_norm": 0.029564740136265755,
465
+ "learning_rate": 9.969406417112489e-05,
466
+ "loss": 0.0416,
467
+ "step": 54
468
+ },
469
+ {
470
+ "epoch": 0.6666666666666666,
471
+ "grad_norm": 0.027353042736649513,
472
+ "learning_rate": 9.964524472416319e-05,
473
+ "loss": 0.0363,
474
+ "step": 55
475
+ },
476
+ {
477
+ "epoch": 0.6666666666666666,
478
+ "eval_loss": 0.0433911457657814,
479
+ "eval_runtime": 6.2376,
480
+ "eval_samples_per_second": 8.016,
481
+ "eval_steps_per_second": 2.084,
482
+ "step": 55
483
+ },
484
+ {
485
+ "epoch": 0.6787878787878788,
486
+ "grad_norm": 0.03154386952519417,
487
+ "learning_rate": 9.95928267727387e-05,
488
+ "loss": 0.0457,
489
+ "step": 56
490
+ },
491
+ {
492
+ "epoch": 0.6909090909090909,
493
+ "grad_norm": 0.0249126385897398,
494
+ "learning_rate": 9.953681411633376e-05,
495
+ "loss": 0.0367,
496
+ "step": 57
497
+ },
498
+ {
499
+ "epoch": 0.703030303030303,
500
+ "grad_norm": 0.02522316575050354,
501
+ "learning_rate": 9.947721081499068e-05,
502
+ "loss": 0.0428,
503
+ "step": 58
504
+ },
505
+ {
506
+ "epoch": 0.7151515151515152,
507
+ "grad_norm": 0.028446340933442116,
508
+ "learning_rate": 9.941402118901744e-05,
509
+ "loss": 0.0456,
510
+ "step": 59
511
+ },
512
+ {
513
+ "epoch": 0.7272727272727273,
514
+ "grad_norm": 0.0324234701693058,
515
+ "learning_rate": 9.934724981867446e-05,
516
+ "loss": 0.0553,
517
+ "step": 60
518
+ },
519
+ {
520
+ "epoch": 0.7272727272727273,
521
+ "eval_loss": 0.04182567819952965,
522
+ "eval_runtime": 6.2053,
523
+ "eval_samples_per_second": 8.058,
524
+ "eval_steps_per_second": 2.095,
525
+ "step": 60
526
+ },
527
+ {
528
+ "epoch": 0.7393939393939394,
529
+ "grad_norm": 0.027509605512022972,
530
+ "learning_rate": 9.927690154384273e-05,
531
+ "loss": 0.0443,
532
+ "step": 61
533
+ },
534
+ {
535
+ "epoch": 0.7515151515151515,
536
+ "grad_norm": 0.025798741728067398,
537
+ "learning_rate": 9.920298146367286e-05,
538
+ "loss": 0.0423,
539
+ "step": 62
540
+ },
541
+ {
542
+ "epoch": 0.7636363636363637,
543
+ "grad_norm": 0.029940692707896233,
544
+ "learning_rate": 9.912549493621554e-05,
545
+ "loss": 0.0469,
546
+ "step": 63
547
+ },
548
+ {
549
+ "epoch": 0.7757575757575758,
550
+ "grad_norm": 0.032555170357227325,
551
+ "learning_rate": 9.904444757803321e-05,
552
+ "loss": 0.0428,
553
+ "step": 64
554
+ },
555
+ {
556
+ "epoch": 0.7878787878787878,
557
+ "grad_norm": 0.03051156736910343,
558
+ "learning_rate": 9.895984526379281e-05,
559
+ "loss": 0.0444,
560
+ "step": 65
561
+ },
562
+ {
563
+ "epoch": 0.7878787878787878,
564
+ "eval_loss": 0.0403163880109787,
565
+ "eval_runtime": 6.1935,
566
+ "eval_samples_per_second": 8.073,
567
+ "eval_steps_per_second": 2.099,
568
+ "step": 65
569
+ },
570
+ {
571
+ "epoch": 0.8,
572
+ "grad_norm": 0.02734997309744358,
573
+ "learning_rate": 9.887169412584011e-05,
574
+ "loss": 0.0389,
575
+ "step": 66
576
+ },
577
+ {
578
+ "epoch": 0.8121212121212121,
579
+ "grad_norm": 0.026902060955762863,
580
+ "learning_rate": 9.878000055375512e-05,
581
+ "loss": 0.0397,
582
+ "step": 67
583
+ },
584
+ {
585
+ "epoch": 0.8242424242424242,
586
+ "grad_norm": 0.03240904584527016,
587
+ "learning_rate": 9.868477119388896e-05,
588
+ "loss": 0.0387,
589
+ "step": 68
590
+ },
591
+ {
592
+ "epoch": 0.8363636363636363,
593
+ "grad_norm": 0.02606021985411644,
594
+ "learning_rate": 9.858601294888213e-05,
595
+ "loss": 0.0344,
596
+ "step": 69
597
+ },
598
+ {
599
+ "epoch": 0.8484848484848485,
600
+ "grad_norm": 0.029814746230840683,
601
+ "learning_rate": 9.848373297716414e-05,
602
+ "loss": 0.0469,
603
+ "step": 70
604
+ },
605
+ {
606
+ "epoch": 0.8484848484848485,
607
+ "eval_loss": 0.03973233327269554,
608
+ "eval_runtime": 6.2308,
609
+ "eval_samples_per_second": 8.025,
610
+ "eval_steps_per_second": 2.086,
611
+ "step": 70
612
+ },
613
+ {
614
+ "epoch": 0.8606060606060606,
615
+ "grad_norm": 0.025392569601535797,
616
+ "learning_rate": 9.837793869243468e-05,
617
+ "loss": 0.0388,
618
+ "step": 71
619
+ },
620
+ {
621
+ "epoch": 0.8727272727272727,
622
+ "grad_norm": 0.03046100027859211,
623
+ "learning_rate": 9.82686377631262e-05,
624
+ "loss": 0.0415,
625
+ "step": 72
626
+ },
627
+ {
628
+ "epoch": 0.8848484848484849,
629
+ "grad_norm": 0.02428356185555458,
630
+ "learning_rate": 9.815583811184808e-05,
631
+ "loss": 0.037,
632
+ "step": 73
633
+ },
634
+ {
635
+ "epoch": 0.896969696969697,
636
+ "grad_norm": 0.029197214171290398,
637
+ "learning_rate": 9.803954791481239e-05,
638
+ "loss": 0.0408,
639
+ "step": 74
640
+ },
641
+ {
642
+ "epoch": 0.9090909090909091,
643
+ "grad_norm": 0.027502721175551414,
644
+ "learning_rate": 9.791977560124119e-05,
645
+ "loss": 0.0417,
646
+ "step": 75
647
+ },
648
+ {
649
+ "epoch": 0.9090909090909091,
650
+ "eval_loss": 0.038558006286621094,
651
+ "eval_runtime": 6.2,
652
+ "eval_samples_per_second": 8.065,
653
+ "eval_steps_per_second": 2.097,
654
+ "step": 75
655
+ },
656
+ {
657
+ "epoch": 0.9212121212121213,
658
+ "grad_norm": 0.030016757547855377,
659
+ "learning_rate": 9.779652985275562e-05,
660
+ "loss": 0.0427,
661
+ "step": 76
662
+ },
663
+ {
664
+ "epoch": 0.9333333333333333,
665
+ "grad_norm": 0.029366502538323402,
666
+ "learning_rate": 9.766981960274653e-05,
667
+ "loss": 0.0312,
668
+ "step": 77
669
+ },
670
+ {
671
+ "epoch": 0.9454545454545454,
672
+ "grad_norm": 0.02805924229323864,
673
+ "learning_rate": 9.753965403572703e-05,
674
+ "loss": 0.0424,
675
+ "step": 78
676
+ },
677
+ {
678
+ "epoch": 0.9575757575757575,
679
+ "grad_norm": 0.027496378868818283,
680
+ "learning_rate": 9.740604258666668e-05,
681
+ "loss": 0.0368,
682
+ "step": 79
683
+ },
684
+ {
685
+ "epoch": 0.9696969696969697,
686
+ "grad_norm": 0.02711924910545349,
687
+ "learning_rate": 9.726899494030768e-05,
688
+ "loss": 0.0388,
689
+ "step": 80
690
+ },
691
+ {
692
+ "epoch": 0.9696969696969697,
693
+ "eval_loss": 0.037164073437452316,
694
+ "eval_runtime": 6.2151,
695
+ "eval_samples_per_second": 8.045,
696
+ "eval_steps_per_second": 2.092,
697
+ "step": 80
698
+ },
699
+ {
700
+ "epoch": 0.9818181818181818,
701
+ "grad_norm": 0.02877042628824711,
702
+ "learning_rate": 9.71285210304628e-05,
703
+ "loss": 0.0367,
704
+ "step": 81
705
+ },
706
+ {
707
+ "epoch": 0.9939393939393939,
708
+ "grad_norm": 0.029804140329360962,
709
+ "learning_rate": 9.698463103929542e-05,
710
+ "loss": 0.0399,
711
+ "step": 82
712
+ },
713
+ {
714
+ "epoch": 1.006060606060606,
715
+ "grad_norm": 0.04405470937490463,
716
+ "learning_rate": 9.683733539658139e-05,
717
+ "loss": 0.0545,
718
+ "step": 83
719
+ },
720
+ {
721
+ "epoch": 1.018181818181818,
722
+ "grad_norm": 0.0315798744559288,
723
+ "learning_rate": 9.66866447789531e-05,
724
+ "loss": 0.048,
725
+ "step": 84
726
+ },
727
+ {
728
+ "epoch": 1.0303030303030303,
729
+ "grad_norm": 0.02551027573645115,
730
+ "learning_rate": 9.653257010912559e-05,
731
+ "loss": 0.0309,
732
+ "step": 85
733
+ },
734
+ {
735
+ "epoch": 1.0303030303030303,
736
+ "eval_loss": 0.03581343591213226,
737
+ "eval_runtime": 6.2558,
738
+ "eval_samples_per_second": 7.993,
739
+ "eval_steps_per_second": 2.078,
740
+ "step": 85
741
+ },
742
+ {
743
+ "epoch": 1.0424242424242425,
744
+ "grad_norm": 0.03550685569643974,
745
+ "learning_rate": 9.637512255510475e-05,
746
+ "loss": 0.0659,
747
+ "step": 86
748
+ },
749
+ {
750
+ "epoch": 1.0545454545454545,
751
+ "grad_norm": 0.03085348755121231,
752
+ "learning_rate": 9.621431352937789e-05,
753
+ "loss": 0.0502,
754
+ "step": 87
755
+ },
756
+ {
757
+ "epoch": 1.0666666666666667,
758
+ "grad_norm": 0.02470513805747032,
759
+ "learning_rate": 9.605015468808651e-05,
760
+ "loss": 0.0318,
761
+ "step": 88
762
+ },
763
+ {
764
+ "epoch": 1.0787878787878789,
765
+ "grad_norm": 0.02803831174969673,
766
+ "learning_rate": 9.58826579301814e-05,
767
+ "loss": 0.0446,
768
+ "step": 89
769
+ },
770
+ {
771
+ "epoch": 1.0909090909090908,
772
+ "grad_norm": 0.03941066190600395,
773
+ "learning_rate": 9.571183539656011e-05,
774
+ "loss": 0.0487,
775
+ "step": 90
776
+ },
777
+ {
778
+ "epoch": 1.0909090909090908,
779
+ "eval_loss": 0.0354202575981617,
780
+ "eval_runtime": 6.1921,
781
+ "eval_samples_per_second": 8.075,
782
+ "eval_steps_per_second": 2.099,
783
+ "step": 90
784
+ },
785
+ {
786
+ "epoch": 1.103030303030303,
787
+ "grad_norm": 0.029008885845541954,
788
+ "learning_rate": 9.553769946918697e-05,
789
+ "loss": 0.0403,
790
+ "step": 91
791
+ },
792
+ {
793
+ "epoch": 1.1151515151515152,
794
+ "grad_norm": 0.025633882731199265,
795
+ "learning_rate": 9.536026277019561e-05,
796
+ "loss": 0.032,
797
+ "step": 92
798
+ },
799
+ {
800
+ "epoch": 1.1272727272727272,
801
+ "grad_norm": 0.02955947443842888,
802
+ "learning_rate": 9.517953816097396e-05,
803
+ "loss": 0.0366,
804
+ "step": 93
805
+ },
806
+ {
807
+ "epoch": 1.1393939393939394,
808
+ "grad_norm": 0.029836708679795265,
809
+ "learning_rate": 9.499553874123212e-05,
810
+ "loss": 0.0383,
811
+ "step": 94
812
+ },
813
+ {
814
+ "epoch": 1.1515151515151516,
815
+ "grad_norm": 0.030258659273386,
816
+ "learning_rate": 9.480827784805278e-05,
817
+ "loss": 0.0348,
818
+ "step": 95
819
+ },
820
+ {
821
+ "epoch": 1.1515151515151516,
822
+ "eval_loss": 0.034031517803668976,
823
+ "eval_runtime": 6.1911,
824
+ "eval_samples_per_second": 8.076,
825
+ "eval_steps_per_second": 2.1,
826
+ "step": 95
827
+ },
828
+ {
829
+ "epoch": 1.1636363636363636,
830
+ "grad_norm": 0.02571636624634266,
831
+ "learning_rate": 9.461776905492446e-05,
832
+ "loss": 0.0322,
833
+ "step": 96
834
+ },
835
+ {
836
+ "epoch": 1.1757575757575758,
837
+ "grad_norm": 0.025425300002098083,
838
+ "learning_rate": 9.442402617075765e-05,
839
+ "loss": 0.0302,
840
+ "step": 97
841
+ },
842
+ {
843
+ "epoch": 1.187878787878788,
844
+ "grad_norm": 0.02790471538901329,
845
+ "learning_rate": 9.422706323888397e-05,
846
+ "loss": 0.0305,
847
+ "step": 98
848
+ },
849
+ {
850
+ "epoch": 1.2,
851
+ "grad_norm": 0.031999390572309494,
852
+ "learning_rate": 9.402689453603815e-05,
853
+ "loss": 0.0384,
854
+ "step": 99
855
+ },
856
+ {
857
+ "epoch": 1.2121212121212122,
858
+ "grad_norm": 0.02810075506567955,
859
+ "learning_rate": 9.382353457132317e-05,
860
+ "loss": 0.0308,
861
+ "step": 100
862
+ },
863
+ {
864
+ "epoch": 1.2121212121212122,
865
+ "eval_loss": 0.03338392823934555,
866
+ "eval_runtime": 6.1917,
867
+ "eval_samples_per_second": 8.075,
868
+ "eval_steps_per_second": 2.1,
869
+ "step": 100
870
+ },
871
+ {
872
+ "epoch": 1.2242424242424241,
873
+ "grad_norm": 0.0302734412252903,
874
+ "learning_rate": 9.361699808515876e-05,
875
+ "loss": 0.0341,
876
+ "step": 101
877
+ },
878
+ {
879
+ "epoch": 1.2363636363636363,
880
+ "grad_norm": 0.033730726689100266,
881
+ "learning_rate": 9.340730004821266e-05,
882
+ "loss": 0.0346,
883
+ "step": 102
884
+ },
885
+ {
886
+ "epoch": 1.2484848484848485,
887
+ "grad_norm": 0.03323773667216301,
888
+ "learning_rate": 9.31944556603157e-05,
889
+ "loss": 0.0408,
890
+ "step": 103
891
+ },
892
+ {
893
+ "epoch": 1.2606060606060607,
894
+ "grad_norm": 0.027124911546707153,
895
+ "learning_rate": 9.297848034936006e-05,
896
+ "loss": 0.0332,
897
+ "step": 104
898
+ },
899
+ {
900
+ "epoch": 1.2727272727272727,
901
+ "grad_norm": 0.026853900402784348,
902
+ "learning_rate": 9.275938977018081e-05,
903
+ "loss": 0.0318,
904
+ "step": 105
905
+ },
906
+ {
907
+ "epoch": 1.2727272727272727,
908
+ "eval_loss": 0.03301350772380829,
909
+ "eval_runtime": 6.1968,
910
+ "eval_samples_per_second": 8.069,
911
+ "eval_steps_per_second": 2.098,
912
+ "step": 105
913
+ },
914
+ {
915
+ "epoch": 1.284848484848485,
916
+ "grad_norm": 0.027320127934217453,
917
+ "learning_rate": 9.253719980342135e-05,
918
+ "loss": 0.0339,
919
+ "step": 106
920
+ },
921
+ {
922
+ "epoch": 1.2969696969696969,
923
+ "grad_norm": 0.0313449464738369,
924
+ "learning_rate": 9.231192655438221e-05,
925
+ "loss": 0.0336,
926
+ "step": 107
927
+ },
928
+ {
929
+ "epoch": 1.309090909090909,
930
+ "grad_norm": 0.029063764959573746,
931
+ "learning_rate": 9.208358635185373e-05,
932
+ "loss": 0.0324,
933
+ "step": 108
934
+ },
935
+ {
936
+ "epoch": 1.3212121212121213,
937
+ "grad_norm": 0.03135693818330765,
938
+ "learning_rate": 9.185219574693242e-05,
939
+ "loss": 0.0332,
940
+ "step": 109
941
+ },
942
+ {
943
+ "epoch": 1.3333333333333333,
944
+ "grad_norm": 0.0317191518843174,
945
+ "learning_rate": 9.161777151182136e-05,
946
+ "loss": 0.028,
947
+ "step": 110
948
+ },
949
+ {
950
+ "epoch": 1.3333333333333333,
951
+ "eval_loss": 0.03218723088502884,
952
+ "eval_runtime": 6.2118,
953
+ "eval_samples_per_second": 8.049,
954
+ "eval_steps_per_second": 2.093,
955
+ "step": 110
956
+ },
957
+ {
958
+ "epoch": 1.3454545454545455,
959
+ "grad_norm": 0.031457044184207916,
960
+ "learning_rate": 9.138033063861436e-05,
961
+ "loss": 0.0346,
962
+ "step": 111
963
+ },
964
+ {
965
+ "epoch": 1.3575757575757577,
966
+ "grad_norm": 0.031810589134693146,
967
+ "learning_rate": 9.113989033806434e-05,
968
+ "loss": 0.0283,
969
+ "step": 112
970
+ },
971
+ {
972
+ "epoch": 1.3696969696969696,
973
+ "grad_norm": 0.030629124492406845,
974
+ "learning_rate": 9.089646803833589e-05,
975
+ "loss": 0.0246,
976
+ "step": 113
977
+ },
978
+ {
979
+ "epoch": 1.3818181818181818,
980
+ "grad_norm": 0.030411459505558014,
981
+ "learning_rate": 9.065008138374189e-05,
982
+ "loss": 0.0317,
983
+ "step": 114
984
+ },
985
+ {
986
+ "epoch": 1.393939393939394,
987
+ "grad_norm": 0.029815878719091415,
988
+ "learning_rate": 9.040074823346465e-05,
989
+ "loss": 0.0311,
990
+ "step": 115
991
+ },
992
+ {
993
+ "epoch": 1.393939393939394,
994
+ "eval_loss": 0.032092493027448654,
995
+ "eval_runtime": 6.1885,
996
+ "eval_samples_per_second": 8.08,
997
+ "eval_steps_per_second": 2.101,
998
+ "step": 115
999
+ },
1000
+ {
1001
+ "epoch": 1.406060606060606,
1002
+ "grad_norm": 0.030812319368124008,
1003
+ "learning_rate": 9.014848666026138e-05,
1004
+ "loss": 0.0389,
1005
+ "step": 116
1006
+ },
1007
+ {
1008
+ "epoch": 1.4181818181818182,
1009
+ "grad_norm": 0.02588343806564808,
1010
+ "learning_rate": 8.989331494915417e-05,
1011
+ "loss": 0.0287,
1012
+ "step": 117
1013
+ },
1014
+ {
1015
+ "epoch": 1.4303030303030302,
1016
+ "grad_norm": 0.02780727669596672,
1017
+ "learning_rate": 8.963525159610465e-05,
1018
+ "loss": 0.0265,
1019
+ "step": 118
1020
+ },
1021
+ {
1022
+ "epoch": 1.4424242424242424,
1023
+ "grad_norm": 0.026163380593061447,
1024
+ "learning_rate": 8.937431530667328e-05,
1025
+ "loss": 0.0262,
1026
+ "step": 119
1027
+ },
1028
+ {
1029
+ "epoch": 1.4545454545454546,
1030
+ "grad_norm": 0.0316736213862896,
1031
+ "learning_rate": 8.911052499466357e-05,
1032
+ "loss": 0.0382,
1033
+ "step": 120
1034
+ },
1035
+ {
1036
+ "epoch": 1.4545454545454546,
1037
+ "eval_loss": 0.031465690582990646,
1038
+ "eval_runtime": 6.1922,
1039
+ "eval_samples_per_second": 8.075,
1040
+ "eval_steps_per_second": 2.099,
1041
+ "step": 120
1042
+ },
1043
+ {
1044
+ "epoch": 1.4666666666666668,
1045
+ "grad_norm": 0.03706022724509239,
1046
+ "learning_rate": 8.884389978075098e-05,
1047
+ "loss": 0.0336,
1048
+ "step": 121
1049
+ },
1050
+ {
1051
+ "epoch": 1.4787878787878788,
1052
+ "grad_norm": 0.027684392407536507,
1053
+ "learning_rate": 8.857445899109715e-05,
1054
+ "loss": 0.0267,
1055
+ "step": 122
1056
+ },
1057
+ {
1058
+ "epoch": 1.490909090909091,
1059
+ "grad_norm": 0.02498454973101616,
1060
+ "learning_rate": 8.83022221559489e-05,
1061
+ "loss": 0.0258,
1062
+ "step": 123
1063
+ },
1064
+ {
1065
+ "epoch": 1.503030303030303,
1066
+ "grad_norm": 0.03206618130207062,
1067
+ "learning_rate": 8.80272090082227e-05,
1068
+ "loss": 0.0344,
1069
+ "step": 124
1070
+ },
1071
+ {
1072
+ "epoch": 1.5151515151515151,
1073
+ "grad_norm": 0.03329097852110863,
1074
+ "learning_rate": 8.774943948207426e-05,
1075
+ "loss": 0.0316,
1076
+ "step": 125
1077
+ },
1078
+ {
1079
+ "epoch": 1.5151515151515151,
1080
+ "eval_loss": 0.030392121523618698,
1081
+ "eval_runtime": 6.2076,
1082
+ "eval_samples_per_second": 8.055,
1083
+ "eval_steps_per_second": 2.094,
1084
+ "step": 125
1085
+ },
1086
+ {
1087
+ "epoch": 1.5272727272727273,
1088
+ "grad_norm": 0.029471345245838165,
1089
+ "learning_rate": 8.746893371145366e-05,
1090
+ "loss": 0.0279,
1091
+ "step": 126
1092
+ },
1093
+ {
1094
+ "epoch": 1.5393939393939395,
1095
+ "grad_norm": 0.030292104929685593,
1096
+ "learning_rate": 8.718571202864598e-05,
1097
+ "loss": 0.0292,
1098
+ "step": 127
1099
+ },
1100
+ {
1101
+ "epoch": 1.5515151515151515,
1102
+ "grad_norm": 0.028025031089782715,
1103
+ "learning_rate": 8.689979496279746e-05,
1104
+ "loss": 0.0296,
1105
+ "step": 128
1106
+ },
1107
+ {
1108
+ "epoch": 1.5636363636363635,
1109
+ "grad_norm": 0.027177123352885246,
1110
+ "learning_rate": 8.661120323842751e-05,
1111
+ "loss": 0.0286,
1112
+ "step": 129
1113
+ },
1114
+ {
1115
+ "epoch": 1.5757575757575757,
1116
+ "grad_norm": 0.03291260078549385,
1117
+ "learning_rate": 8.631995777392645e-05,
1118
+ "loss": 0.0278,
1119
+ "step": 130
1120
+ },
1121
+ {
1122
+ "epoch": 1.5757575757575757,
1123
+ "eval_loss": 0.029901880770921707,
1124
+ "eval_runtime": 6.1931,
1125
+ "eval_samples_per_second": 8.073,
1126
+ "eval_steps_per_second": 2.099,
1127
+ "step": 130
1128
+ },
1129
+ {
1130
+ "epoch": 1.587878787878788,
1131
+ "grad_norm": 0.027456866577267647,
1132
+ "learning_rate": 8.602607968003935e-05,
1133
+ "loss": 0.0277,
1134
+ "step": 131
1135
+ },
1136
+ {
1137
+ "epoch": 1.6,
1138
+ "grad_norm": 0.02367628738284111,
1139
+ "learning_rate": 8.572959025833573e-05,
1140
+ "loss": 0.023,
1141
+ "step": 132
1142
+ },
1143
+ {
1144
+ "epoch": 1.612121212121212,
1145
+ "grad_norm": 0.030250705778598785,
1146
+ "learning_rate": 8.543051099966558e-05,
1147
+ "loss": 0.0253,
1148
+ "step": 133
1149
+ },
1150
+ {
1151
+ "epoch": 1.6242424242424243,
1152
+ "grad_norm": 0.02687668427824974,
1153
+ "learning_rate": 8.512886358260162e-05,
1154
+ "loss": 0.0249,
1155
+ "step": 134
1156
+ },
1157
+ {
1158
+ "epoch": 1.6363636363636362,
1159
+ "grad_norm": 0.032938696444034576,
1160
+ "learning_rate": 8.482466987186785e-05,
1161
+ "loss": 0.0285,
1162
+ "step": 135
1163
+ },
1164
+ {
1165
+ "epoch": 1.6363636363636362,
1166
+ "eval_loss": 0.029229959473013878,
1167
+ "eval_runtime": 6.1897,
1168
+ "eval_samples_per_second": 8.078,
1169
+ "eval_steps_per_second": 2.1,
1170
+ "step": 135
1171
+ },
1172
+ {
1173
+ "epoch": 1.6484848484848484,
1174
+ "grad_norm": 0.02894946001470089,
1175
+ "learning_rate": 8.451795191675488e-05,
1176
+ "loss": 0.0268,
1177
+ "step": 136
1178
+ },
1179
+ {
1180
+ "epoch": 1.6606060606060606,
1181
+ "grad_norm": 0.03599061071872711,
1182
+ "learning_rate": 8.420873194952152e-05,
1183
+ "loss": 0.0351,
1184
+ "step": 137
1185
+ },
1186
+ {
1187
+ "epoch": 1.6727272727272728,
1188
+ "grad_norm": 0.031365521252155304,
1189
+ "learning_rate": 8.389703238378339e-05,
1190
+ "loss": 0.0309,
1191
+ "step": 138
1192
+ },
1193
+ {
1194
+ "epoch": 1.6848484848484848,
1195
+ "grad_norm": 0.024763284251093864,
1196
+ "learning_rate": 8.358287581288822e-05,
1197
+ "loss": 0.0244,
1198
+ "step": 139
1199
+ },
1200
+ {
1201
+ "epoch": 1.696969696969697,
1202
+ "grad_norm": 0.026635024696588516,
1203
+ "learning_rate": 8.326628500827826e-05,
1204
+ "loss": 0.0257,
1205
+ "step": 140
1206
+ },
1207
+ {
1208
+ "epoch": 1.696969696969697,
1209
+ "eval_loss": 0.02854442596435547,
1210
+ "eval_runtime": 6.2016,
1211
+ "eval_samples_per_second": 8.062,
1212
+ "eval_steps_per_second": 2.096,
1213
+ "step": 140
1214
+ },
1215
+ {
1216
+ "epoch": 1.709090909090909,
1217
+ "grad_norm": 0.03084694594144821,
1218
+ "learning_rate": 8.294728291783966e-05,
1219
+ "loss": 0.0301,
1220
+ "step": 141
1221
+ },
1222
+ {
1223
+ "epoch": 1.7212121212121212,
1224
+ "grad_norm": 0.024888882413506508,
1225
+ "learning_rate": 8.262589266423908e-05,
1226
+ "loss": 0.0254,
1227
+ "step": 142
1228
+ },
1229
+ {
1230
+ "epoch": 1.7333333333333334,
1231
+ "grad_norm": 0.02867315709590912,
1232
+ "learning_rate": 8.230213754324773e-05,
1233
+ "loss": 0.0338,
1234
+ "step": 143
1235
+ },
1236
+ {
1237
+ "epoch": 1.7454545454545456,
1238
+ "grad_norm": 0.030578091740608215,
1239
+ "learning_rate": 8.197604102205271e-05,
1240
+ "loss": 0.0265,
1241
+ "step": 144
1242
+ },
1243
+ {
1244
+ "epoch": 1.7575757575757576,
1245
+ "grad_norm": 0.025194313377141953,
1246
+ "learning_rate": 8.16476267375561e-05,
1247
+ "loss": 0.0244,
1248
+ "step": 145
1249
+ },
1250
+ {
1251
+ "epoch": 1.7575757575757576,
1252
+ "eval_loss": 0.028112677857279778,
1253
+ "eval_runtime": 6.1903,
1254
+ "eval_samples_per_second": 8.077,
1255
+ "eval_steps_per_second": 2.1,
1256
+ "step": 145
1257
+ },
1258
+ {
1259
+ "epoch": 1.7696969696969695,
1260
+ "grad_norm": 0.03511481732130051,
1261
+ "learning_rate": 8.131691849466153e-05,
1262
+ "loss": 0.0351,
1263
+ "step": 146
1264
+ },
1265
+ {
1266
+ "epoch": 1.7818181818181817,
1267
+ "grad_norm": 0.034265320748090744,
1268
+ "learning_rate": 8.098394026454885e-05,
1269
+ "loss": 0.0318,
1270
+ "step": 147
1271
+ },
1272
+ {
1273
+ "epoch": 1.793939393939394,
1274
+ "grad_norm": 0.02798490971326828,
1275
+ "learning_rate": 8.064871618293646e-05,
1276
+ "loss": 0.0258,
1277
+ "step": 148
1278
+ },
1279
+ {
1280
+ "epoch": 1.8060606060606061,
1281
+ "grad_norm": 0.031277846544981,
1282
+ "learning_rate": 8.03112705483319e-05,
1283
+ "loss": 0.0322,
1284
+ "step": 149
1285
+ },
1286
+ {
1287
+ "epoch": 1.8181818181818183,
1288
+ "grad_norm": 0.025352105498313904,
1289
+ "learning_rate": 7.997162782027061e-05,
1290
+ "loss": 0.0256,
1291
+ "step": 150
1292
+ },
1293
+ {
1294
+ "epoch": 1.8181818181818183,
1295
+ "eval_loss": 0.027805332094430923,
1296
+ "eval_runtime": 6.1948,
1297
+ "eval_samples_per_second": 8.071,
1298
+ "eval_steps_per_second": 2.099,
1299
+ "step": 150
1300
+ },
1301
+ {
1302
+ "epoch": 1.8303030303030303,
1303
+ "grad_norm": 0.03179726377129555,
1304
+ "learning_rate": 7.962981261754294e-05,
1305
+ "loss": 0.0265,
1306
+ "step": 151
1307
+ },
1308
+ {
1309
+ "epoch": 1.8424242424242423,
1310
+ "grad_norm": 0.02985468879342079,
1311
+ "learning_rate": 7.928584971640974e-05,
1312
+ "loss": 0.0302,
1313
+ "step": 152
1314
+ },
1315
+ {
1316
+ "epoch": 1.8545454545454545,
1317
+ "grad_norm": 0.031871821731328964,
1318
+ "learning_rate": 7.893976404880643e-05,
1319
+ "loss": 0.0331,
1320
+ "step": 153
1321
+ },
1322
+ {
1323
+ "epoch": 1.8666666666666667,
1324
+ "grad_norm": 0.028416186571121216,
1325
+ "learning_rate": 7.859158070053577e-05,
1326
+ "loss": 0.0245,
1327
+ "step": 154
1328
+ },
1329
+ {
1330
+ "epoch": 1.878787878787879,
1331
+ "grad_norm": 0.03054559975862503,
1332
+ "learning_rate": 7.824132490944967e-05,
1333
+ "loss": 0.0338,
1334
+ "step": 155
1335
+ },
1336
+ {
1337
+ "epoch": 1.878787878787879,
1338
+ "eval_loss": 0.027029650285840034,
1339
+ "eval_runtime": 6.235,
1340
+ "eval_samples_per_second": 8.019,
1341
+ "eval_steps_per_second": 2.085,
1342
+ "step": 155
1343
+ },
1344
+ {
1345
+ "epoch": 1.8909090909090909,
1346
+ "grad_norm": 0.028330031782388687,
1347
+ "learning_rate": 7.788902206361973e-05,
1348
+ "loss": 0.0241,
1349
+ "step": 156
1350
+ },
1351
+ {
1352
+ "epoch": 1.903030303030303,
1353
+ "grad_norm": 0.031616389751434326,
1354
+ "learning_rate": 7.7534697699497e-05,
1355
+ "loss": 0.0301,
1356
+ "step": 157
1357
+ },
1358
+ {
1359
+ "epoch": 1.915151515151515,
1360
+ "grad_norm": 0.027048081159591675,
1361
+ "learning_rate": 7.717837750006106e-05,
1362
+ "loss": 0.0274,
1363
+ "step": 158
1364
+ },
1365
+ {
1366
+ "epoch": 1.9272727272727272,
1367
+ "grad_norm": 0.028316281735897064,
1368
+ "learning_rate": 7.682008729295833e-05,
1369
+ "loss": 0.026,
1370
+ "step": 159
1371
+ },
1372
+ {
1373
+ "epoch": 1.9393939393939394,
1374
+ "grad_norm": 0.02987455017864704,
1375
+ "learning_rate": 7.645985304863003e-05,
1376
+ "loss": 0.0309,
1377
+ "step": 160
1378
+ },
1379
+ {
1380
+ "epoch": 1.9393939393939394,
1381
+ "eval_loss": 0.02624826692044735,
1382
+ "eval_runtime": 6.1867,
1383
+ "eval_samples_per_second": 8.082,
1384
+ "eval_steps_per_second": 2.101,
1385
+ "step": 160
1386
+ },
1387
+ {
1388
+ "epoch": 1.9515151515151516,
1389
+ "grad_norm": 0.02562532387673855,
1390
+ "learning_rate": 7.609770087842969e-05,
1391
+ "loss": 0.0275,
1392
+ "step": 161
1393
+ },
1394
+ {
1395
+ "epoch": 1.9636363636363636,
1396
+ "grad_norm": 0.026776108890771866,
1397
+ "learning_rate": 7.573365703273046e-05,
1398
+ "loss": 0.0263,
1399
+ "step": 162
1400
+ },
1401
+ {
1402
+ "epoch": 1.9757575757575756,
1403
+ "grad_norm": 0.031301844865083694,
1404
+ "learning_rate": 7.536774789902246e-05,
1405
+ "loss": 0.0293,
1406
+ "step": 163
1407
+ },
1408
+ {
1409
+ "epoch": 1.9878787878787878,
1410
+ "grad_norm": 0.02761393040418625,
1411
+ "learning_rate": 7.500000000000001e-05,
1412
+ "loss": 0.0292,
1413
+ "step": 164
1414
+ },
1415
+ {
1416
+ "epoch": 2.0,
1417
+ "grad_norm": 0.04325617477297783,
1418
+ "learning_rate": 7.463043999163919e-05,
1419
+ "loss": 0.0378,
1420
+ "step": 165
1421
+ },
1422
+ {
1423
+ "epoch": 2.0,
1424
+ "eval_loss": 0.02608395926654339,
1425
+ "eval_runtime": 6.2208,
1426
+ "eval_samples_per_second": 8.038,
1427
+ "eval_steps_per_second": 2.09,
1428
+ "step": 165
1429
+ },
1430
+ {
1431
+ "epoch": 2.012121212121212,
1432
+ "grad_norm": 0.026866400614380836,
1433
+ "learning_rate": 7.425909466126568e-05,
1434
+ "loss": 0.024,
1435
+ "step": 166
1436
+ },
1437
+ {
1438
+ "epoch": 2.0242424242424244,
1439
+ "grad_norm": 0.026734622195363045,
1440
+ "learning_rate": 7.388599092561315e-05,
1441
+ "loss": 0.0238,
1442
+ "step": 167
1443
+ },
1444
+ {
1445
+ "epoch": 2.036363636363636,
1446
+ "grad_norm": 0.02514388971030712,
1447
+ "learning_rate": 7.351115582887211e-05,
1448
+ "loss": 0.0218,
1449
+ "step": 168
1450
+ },
1451
+ {
1452
+ "epoch": 2.0484848484848484,
1453
+ "grad_norm": 0.02405986562371254,
1454
+ "learning_rate": 7.313461654072973e-05,
1455
+ "loss": 0.0199,
1456
+ "step": 169
1457
+ },
1458
+ {
1459
+ "epoch": 2.0606060606060606,
1460
+ "grad_norm": 0.030505580827593803,
1461
+ "learning_rate": 7.275640035440045e-05,
1462
+ "loss": 0.0275,
1463
+ "step": 170
1464
+ },
1465
+ {
1466
+ "epoch": 2.0606060606060606,
1467
+ "eval_loss": 0.026318900287151337,
1468
+ "eval_runtime": 6.2393,
1469
+ "eval_samples_per_second": 8.014,
1470
+ "eval_steps_per_second": 2.084,
1471
+ "step": 170
1472
+ },
1473
+ {
1474
+ "epoch": 2.0727272727272728,
1475
+ "grad_norm": 0.03722088038921356,
1476
+ "learning_rate": 7.237653468464756e-05,
1477
+ "loss": 0.0256,
1478
+ "step": 171
1479
+ },
1480
+ {
1481
+ "epoch": 2.084848484848485,
1482
+ "grad_norm": 0.03724412992596626,
1483
+ "learning_rate": 7.199504706579617e-05,
1484
+ "loss": 0.0226,
1485
+ "step": 172
1486
+ },
1487
+ {
1488
+ "epoch": 2.096969696969697,
1489
+ "grad_norm": 0.030355574563145638,
1490
+ "learning_rate": 7.161196514973734e-05,
1491
+ "loss": 0.0188,
1492
+ "step": 173
1493
+ },
1494
+ {
1495
+ "epoch": 2.109090909090909,
1496
+ "grad_norm": 0.03693992272019386,
1497
+ "learning_rate": 7.12273167039238e-05,
1498
+ "loss": 0.0232,
1499
+ "step": 174
1500
+ },
1501
+ {
1502
+ "epoch": 2.121212121212121,
1503
+ "grad_norm": 0.03164402395486832,
1504
+ "learning_rate": 7.084112960935716e-05,
1505
+ "loss": 0.0225,
1506
+ "step": 175
1507
+ },
1508
+ {
1509
+ "epoch": 2.121212121212121,
1510
+ "eval_loss": 0.025883661583065987,
1511
+ "eval_runtime": 6.2414,
1512
+ "eval_samples_per_second": 8.011,
1513
+ "eval_steps_per_second": 2.083,
1514
+ "step": 175
1515
+ },
1516
+ {
1517
+ "epoch": 2.1333333333333333,
1518
+ "grad_norm": 0.031605158001184464,
1519
+ "learning_rate": 7.045343185856701e-05,
1520
+ "loss": 0.0248,
1521
+ "step": 176
1522
+ },
1523
+ {
1524
+ "epoch": 2.1454545454545455,
1525
+ "grad_norm": 0.0310862734913826,
1526
+ "learning_rate": 7.006425155358195e-05,
1527
+ "loss": 0.0244,
1528
+ "step": 177
1529
+ },
1530
+ {
1531
+ "epoch": 2.1575757575757577,
1532
+ "grad_norm": 0.031485848128795624,
1533
+ "learning_rate": 6.967361690389258e-05,
1534
+ "loss": 0.0242,
1535
+ "step": 178
1536
+ },
1537
+ {
1538
+ "epoch": 2.16969696969697,
1539
+ "grad_norm": 0.03367177024483681,
1540
+ "learning_rate": 6.92815562244068e-05,
1541
+ "loss": 0.0246,
1542
+ "step": 179
1543
+ },
1544
+ {
1545
+ "epoch": 2.1818181818181817,
1546
+ "grad_norm": 0.028202077373862267,
1547
+ "learning_rate": 6.88880979333973e-05,
1548
+ "loss": 0.0232,
1549
+ "step": 180
1550
+ },
1551
+ {
1552
+ "epoch": 2.1818181818181817,
1553
+ "eval_loss": 0.025616060942411423,
1554
+ "eval_runtime": 6.1872,
1555
+ "eval_samples_per_second": 8.081,
1556
+ "eval_steps_per_second": 2.101,
1557
+ "step": 180
1558
+ },
1559
+ {
1560
+ "epoch": 2.193939393939394,
1561
+ "grad_norm": 0.03502137213945389,
1562
+ "learning_rate": 6.849327055044183e-05,
1563
+ "loss": 0.0251,
1564
+ "step": 181
1565
+ },
1566
+ {
1567
+ "epoch": 2.206060606060606,
1568
+ "grad_norm": 0.029362250119447708,
1569
+ "learning_rate": 6.809710269435589e-05,
1570
+ "loss": 0.022,
1571
+ "step": 182
1572
+ },
1573
+ {
1574
+ "epoch": 2.2181818181818183,
1575
+ "grad_norm": 0.033701106905937195,
1576
+ "learning_rate": 6.769962308111839e-05,
1577
+ "loss": 0.0234,
1578
+ "step": 183
1579
+ },
1580
+ {
1581
+ "epoch": 2.2303030303030305,
1582
+ "grad_norm": 0.03379302844405174,
1583
+ "learning_rate": 6.730086052179004e-05,
1584
+ "loss": 0.0221,
1585
+ "step": 184
1586
+ },
1587
+ {
1588
+ "epoch": 2.242424242424242,
1589
+ "grad_norm": 0.027100039646029472,
1590
+ "learning_rate": 6.690084392042513e-05,
1591
+ "loss": 0.0193,
1592
+ "step": 185
1593
+ },
1594
+ {
1595
+ "epoch": 2.242424242424242,
1596
+ "eval_loss": 0.025547849014401436,
1597
+ "eval_runtime": 6.2367,
1598
+ "eval_samples_per_second": 8.017,
1599
+ "eval_steps_per_second": 2.084,
1600
+ "step": 185
1601
+ },
1602
+ {
1603
+ "epoch": 2.2545454545454544,
1604
+ "grad_norm": 0.03181413188576698,
1605
+ "learning_rate": 6.649960227197647e-05,
1606
+ "loss": 0.0217,
1607
+ "step": 186
1608
+ },
1609
+ {
1610
+ "epoch": 2.2666666666666666,
1611
+ "grad_norm": 0.03648809716105461,
1612
+ "learning_rate": 6.609716466019356e-05,
1613
+ "loss": 0.0239,
1614
+ "step": 187
1615
+ },
1616
+ {
1617
+ "epoch": 2.278787878787879,
1618
+ "grad_norm": 0.0302013847976923,
1619
+ "learning_rate": 6.569356025551454e-05,
1620
+ "loss": 0.0232,
1621
+ "step": 188
1622
+ },
1623
+ {
1624
+ "epoch": 2.290909090909091,
1625
+ "grad_norm": 0.028094977140426636,
1626
+ "learning_rate": 6.528881831295188e-05,
1627
+ "loss": 0.02,
1628
+ "step": 189
1629
+ },
1630
+ {
1631
+ "epoch": 2.303030303030303,
1632
+ "grad_norm": 0.03214862942695618,
1633
+ "learning_rate": 6.488296816997173e-05,
1634
+ "loss": 0.0251,
1635
+ "step": 190
1636
+ },
1637
+ {
1638
+ "epoch": 2.303030303030303,
1639
+ "eval_loss": 0.02527759224176407,
1640
+ "eval_runtime": 6.19,
1641
+ "eval_samples_per_second": 8.078,
1642
+ "eval_steps_per_second": 2.1,
1643
+ "step": 190
1644
+ },
1645
+ {
1646
+ "epoch": 2.315151515151515,
1647
+ "grad_norm": 0.033984988927841187,
1648
+ "learning_rate": 6.447603924436744e-05,
1649
+ "loss": 0.0243,
1650
+ "step": 191
1651
+ },
1652
+ {
1653
+ "epoch": 2.327272727272727,
1654
+ "grad_norm": 0.027719179168343544,
1655
+ "learning_rate": 6.406806103212725e-05,
1656
+ "loss": 0.0204,
1657
+ "step": 192
1658
+ },
1659
+ {
1660
+ "epoch": 2.3393939393939394,
1661
+ "grad_norm": 0.029257657006382942,
1662
+ "learning_rate": 6.36590631052963e-05,
1663
+ "loss": 0.0232,
1664
+ "step": 193
1665
+ },
1666
+ {
1667
+ "epoch": 2.3515151515151516,
1668
+ "grad_norm": 0.050508007407188416,
1669
+ "learning_rate": 6.32490751098331e-05,
1670
+ "loss": 0.0324,
1671
+ "step": 194
1672
+ },
1673
+ {
1674
+ "epoch": 2.3636363636363638,
1675
+ "grad_norm": 0.029407154768705368,
1676
+ "learning_rate": 6.283812676346063e-05,
1677
+ "loss": 0.0228,
1678
+ "step": 195
1679
+ },
1680
+ {
1681
+ "epoch": 2.3636363636363638,
1682
+ "eval_loss": 0.024870626628398895,
1683
+ "eval_runtime": 6.191,
1684
+ "eval_samples_per_second": 8.076,
1685
+ "eval_steps_per_second": 2.1,
1686
+ "step": 195
1687
+ },
1688
+ {
1689
+ "epoch": 2.375757575757576,
1690
+ "grad_norm": 0.0258539617061615,
1691
+ "learning_rate": 6.242624785351236e-05,
1692
+ "loss": 0.0231,
1693
+ "step": 196
1694
+ },
1695
+ {
1696
+ "epoch": 2.3878787878787877,
1697
+ "grad_norm": 0.02586168795824051,
1698
+ "learning_rate": 6.201346823477303e-05,
1699
+ "loss": 0.0193,
1700
+ "step": 197
1701
+ },
1702
+ {
1703
+ "epoch": 2.4,
1704
+ "grad_norm": 0.029741084203124046,
1705
+ "learning_rate": 6.159981782731474e-05,
1706
+ "loss": 0.0227,
1707
+ "step": 198
1708
+ },
1709
+ {
1710
+ "epoch": 2.412121212121212,
1711
+ "grad_norm": 0.029881663620471954,
1712
+ "learning_rate": 6.118532661432812e-05,
1713
+ "loss": 0.0224,
1714
+ "step": 199
1715
+ },
1716
+ {
1717
+ "epoch": 2.4242424242424243,
1718
+ "grad_norm": 0.027224918827414513,
1719
+ "learning_rate": 6.0770024639949074e-05,
1720
+ "loss": 0.0195,
1721
+ "step": 200
1722
+ },
1723
+ {
1724
+ "epoch": 2.4242424242424243,
1725
+ "eval_loss": 0.024939175695180893,
1726
+ "eval_runtime": 6.1942,
1727
+ "eval_samples_per_second": 8.072,
1728
+ "eval_steps_per_second": 2.099,
1729
+ "step": 200
1730
+ },
1731
+ {
1732
+ "epoch": 2.4363636363636365,
1733
+ "grad_norm": 0.028513159602880478,
1734
+ "learning_rate": 6.0353942007081046e-05,
1735
+ "loss": 0.0198,
1736
+ "step": 201
1737
+ },
1738
+ {
1739
+ "epoch": 2.4484848484848483,
1740
+ "grad_norm": 0.028778916224837303,
1741
+ "learning_rate": 5.993710887521302e-05,
1742
+ "loss": 0.0184,
1743
+ "step": 202
1744
+ },
1745
+ {
1746
+ "epoch": 2.4606060606060605,
1747
+ "grad_norm": 0.03407447412610054,
1748
+ "learning_rate": 5.951955545823342e-05,
1749
+ "loss": 0.0207,
1750
+ "step": 203
1751
+ },
1752
+ {
1753
+ "epoch": 2.4727272727272727,
1754
+ "grad_norm": 0.033413201570510864,
1755
+ "learning_rate": 5.9101312022240106e-05,
1756
+ "loss": 0.0217,
1757
+ "step": 204
1758
+ },
1759
+ {
1760
+ "epoch": 2.484848484848485,
1761
+ "grad_norm": 0.031220227479934692,
1762
+ "learning_rate": 5.868240888334653e-05,
1763
+ "loss": 0.0219,
1764
+ "step": 205
1765
+ },
1766
+ {
1767
+ "epoch": 2.484848484848485,
1768
+ "eval_loss": 0.024136777967214584,
1769
+ "eval_runtime": 6.2,
1770
+ "eval_samples_per_second": 8.065,
1771
+ "eval_steps_per_second": 2.097,
1772
+ "step": 205
1773
+ },
1774
+ {
1775
+ "epoch": 2.496969696969697,
1776
+ "grad_norm": 0.0299720149487257,
1777
+ "learning_rate": 5.826287640548425e-05,
1778
+ "loss": 0.0231,
1779
+ "step": 206
1780
+ },
1781
+ {
1782
+ "epoch": 2.509090909090909,
1783
+ "grad_norm": 0.030199084430933,
1784
+ "learning_rate": 5.784274499820214e-05,
1785
+ "loss": 0.0243,
1786
+ "step": 207
1787
+ },
1788
+ {
1789
+ "epoch": 2.5212121212121215,
1790
+ "grad_norm": 0.03225167095661163,
1791
+ "learning_rate": 5.742204511446203e-05,
1792
+ "loss": 0.0241,
1793
+ "step": 208
1794
+ },
1795
+ {
1796
+ "epoch": 2.533333333333333,
1797
+ "grad_norm": 0.02794428914785385,
1798
+ "learning_rate": 5.700080724843147e-05,
1799
+ "loss": 0.0217,
1800
+ "step": 209
1801
+ },
1802
+ {
1803
+ "epoch": 2.5454545454545454,
1804
+ "grad_norm": 0.026055919006466866,
1805
+ "learning_rate": 5.657906193327325e-05,
1806
+ "loss": 0.0184,
1807
+ "step": 210
1808
+ },
1809
+ {
1810
+ "epoch": 2.5454545454545454,
1811
+ "eval_loss": 0.023839673027396202,
1812
+ "eval_runtime": 6.1855,
1813
+ "eval_samples_per_second": 8.083,
1814
+ "eval_steps_per_second": 2.102,
1815
+ "step": 210
1816
+ },
1817
+ {
1818
+ "epoch": 2.5575757575757576,
1819
+ "grad_norm": 0.03009297326207161,
1820
+ "learning_rate": 5.6156839738932343e-05,
1821
+ "loss": 0.0233,
1822
+ "step": 211
1823
+ },
1824
+ {
1825
+ "epoch": 2.56969696969697,
1826
+ "grad_norm": 0.038690801709890366,
1827
+ "learning_rate": 5.573417126992003e-05,
1828
+ "loss": 0.0419,
1829
+ "step": 212
1830
+ },
1831
+ {
1832
+ "epoch": 2.581818181818182,
1833
+ "grad_norm": 0.03184739127755165,
1834
+ "learning_rate": 5.531108716309547e-05,
1835
+ "loss": 0.0208,
1836
+ "step": 213
1837
+ },
1838
+ {
1839
+ "epoch": 2.5939393939393938,
1840
+ "grad_norm": 0.04226066172122955,
1841
+ "learning_rate": 5.4887618085445094e-05,
1842
+ "loss": 0.0356,
1843
+ "step": 214
1844
+ },
1845
+ {
1846
+ "epoch": 2.606060606060606,
1847
+ "grad_norm": 0.02787015587091446,
1848
+ "learning_rate": 5.446379473185972e-05,
1849
+ "loss": 0.0199,
1850
+ "step": 215
1851
+ },
1852
+ {
1853
+ "epoch": 2.606060606060606,
1854
+ "eval_loss": 0.023647097870707512,
1855
+ "eval_runtime": 6.1981,
1856
+ "eval_samples_per_second": 8.067,
1857
+ "eval_steps_per_second": 2.097,
1858
+ "step": 215
1859
+ },
1860
+ {
1861
+ "epoch": 2.618181818181818,
1862
+ "grad_norm": 0.028222182765603065,
1863
+ "learning_rate": 5.4039647822909624e-05,
1864
+ "loss": 0.0185,
1865
+ "step": 216
1866
+ },
1867
+ {
1868
+ "epoch": 2.6303030303030304,
1869
+ "grad_norm": 0.03137464076280594,
1870
+ "learning_rate": 5.361520810261779e-05,
1871
+ "loss": 0.0212,
1872
+ "step": 217
1873
+ },
1874
+ {
1875
+ "epoch": 2.6424242424242426,
1876
+ "grad_norm": 0.028826339170336723,
1877
+ "learning_rate": 5.319050633623142e-05,
1878
+ "loss": 0.0208,
1879
+ "step": 218
1880
+ },
1881
+ {
1882
+ "epoch": 2.6545454545454543,
1883
+ "grad_norm": 0.048953138291835785,
1884
+ "learning_rate": 5.2765573307992036e-05,
1885
+ "loss": 0.0343,
1886
+ "step": 219
1887
+ },
1888
+ {
1889
+ "epoch": 2.6666666666666665,
1890
+ "grad_norm": 0.03138812631368637,
1891
+ "learning_rate": 5.234043981890394e-05,
1892
+ "loss": 0.023,
1893
+ "step": 220
1894
+ },
1895
+ {
1896
+ "epoch": 2.6666666666666665,
1897
+ "eval_loss": 0.02315612882375717,
1898
+ "eval_runtime": 6.1852,
1899
+ "eval_samples_per_second": 8.084,
1900
+ "eval_steps_per_second": 2.102,
1901
+ "step": 220
1902
+ },
1903
+ {
1904
+ "epoch": 2.6787878787878787,
1905
+ "grad_norm": 0.03604348748922348,
1906
+ "learning_rate": 5.191513668450178e-05,
1907
+ "loss": 0.0208,
1908
+ "step": 221
1909
+ },
1910
+ {
1911
+ "epoch": 2.690909090909091,
1912
+ "grad_norm": 0.028721556067466736,
1913
+ "learning_rate": 5.14896947326168e-05,
1914
+ "loss": 0.0178,
1915
+ "step": 222
1916
+ },
1917
+ {
1918
+ "epoch": 2.703030303030303,
1919
+ "grad_norm": 0.02585718221962452,
1920
+ "learning_rate": 5.1064144801142374e-05,
1921
+ "loss": 0.019,
1922
+ "step": 223
1923
+ },
1924
+ {
1925
+ "epoch": 2.7151515151515153,
1926
+ "grad_norm": 0.02729875221848488,
1927
+ "learning_rate": 5.0638517735798696e-05,
1928
+ "loss": 0.0184,
1929
+ "step": 224
1930
+ },
1931
+ {
1932
+ "epoch": 2.7272727272727275,
1933
+ "grad_norm": 0.029812021180987358,
1934
+ "learning_rate": 5.021284438789694e-05,
1935
+ "loss": 0.0227,
1936
+ "step": 225
1937
+ },
1938
+ {
1939
+ "epoch": 2.7272727272727275,
1940
+ "eval_loss": 0.023449590429663658,
1941
+ "eval_runtime": 6.1841,
1942
+ "eval_samples_per_second": 8.085,
1943
+ "eval_steps_per_second": 2.102,
1944
+ "step": 225
1945
+ },
1946
+ {
1947
+ "epoch": 2.7393939393939393,
1948
+ "grad_norm": 0.02997618354856968,
1949
+ "learning_rate": 4.9787155612103074e-05,
1950
+ "loss": 0.0205,
1951
+ "step": 226
1952
+ },
1953
+ {
1954
+ "epoch": 2.7515151515151515,
1955
+ "grad_norm": 0.028398435562849045,
1956
+ "learning_rate": 4.936148226420132e-05,
1957
+ "loss": 0.0171,
1958
+ "step": 227
1959
+ },
1960
+ {
1961
+ "epoch": 2.7636363636363637,
1962
+ "grad_norm": 0.030046509578824043,
1963
+ "learning_rate": 4.893585519885764e-05,
1964
+ "loss": 0.0197,
1965
+ "step": 228
1966
+ },
1967
+ {
1968
+ "epoch": 2.775757575757576,
1969
+ "grad_norm": 0.029226917773485184,
1970
+ "learning_rate": 4.851030526738321e-05,
1971
+ "loss": 0.0204,
1972
+ "step": 229
1973
+ },
1974
+ {
1975
+ "epoch": 2.787878787878788,
1976
+ "grad_norm": 0.03432171046733856,
1977
+ "learning_rate": 4.8084863315498234e-05,
1978
+ "loss": 0.0206,
1979
+ "step": 230
1980
+ },
1981
+ {
1982
+ "epoch": 2.787878787878788,
1983
+ "eval_loss": 0.022967081516981125,
1984
+ "eval_runtime": 6.1905,
1985
+ "eval_samples_per_second": 8.077,
1986
+ "eval_steps_per_second": 2.1,
1987
+ "step": 230
1988
+ },
1989
+ {
1990
+ "epoch": 2.8,
1991
+ "grad_norm": 0.029804987832903862,
1992
+ "learning_rate": 4.765956018109607e-05,
1993
+ "loss": 0.0197,
1994
+ "step": 231
1995
+ },
1996
+ {
1997
+ "epoch": 2.812121212121212,
1998
+ "grad_norm": 0.029483767226338387,
1999
+ "learning_rate": 4.723442669200798e-05,
2000
+ "loss": 0.0213,
2001
+ "step": 232
2002
+ },
2003
+ {
2004
+ "epoch": 2.824242424242424,
2005
+ "grad_norm": 0.03142073005437851,
2006
+ "learning_rate": 4.680949366376858e-05,
2007
+ "loss": 0.0237,
2008
+ "step": 233
2009
+ },
2010
+ {
2011
+ "epoch": 2.8363636363636364,
2012
+ "grad_norm": 0.029062366113066673,
2013
+ "learning_rate": 4.638479189738224e-05,
2014
+ "loss": 0.0235,
2015
+ "step": 234
2016
+ },
2017
+ {
2018
+ "epoch": 2.8484848484848486,
2019
+ "grad_norm": 0.03055807389318943,
2020
+ "learning_rate": 4.5960352177090395e-05,
2021
+ "loss": 0.0217,
2022
+ "step": 235
2023
+ },
2024
+ {
2025
+ "epoch": 2.8484848484848486,
2026
+ "eval_loss": 0.022518714889883995,
2027
+ "eval_runtime": 6.1918,
2028
+ "eval_samples_per_second": 8.075,
2029
+ "eval_steps_per_second": 2.1,
2030
+ "step": 235
2031
+ },
2032
+ {
2033
+ "epoch": 2.8606060606060604,
2034
+ "grad_norm": 0.027205798774957657,
2035
+ "learning_rate": 4.5536205268140294e-05,
2036
+ "loss": 0.0189,
2037
+ "step": 236
2038
+ },
2039
+ {
2040
+ "epoch": 2.8727272727272726,
2041
+ "grad_norm": 0.025477448478341103,
2042
+ "learning_rate": 4.511238191455491e-05,
2043
+ "loss": 0.0166,
2044
+ "step": 237
2045
+ },
2046
+ {
2047
+ "epoch": 2.8848484848484848,
2048
+ "grad_norm": 0.025487707927823067,
2049
+ "learning_rate": 4.468891283690454e-05,
2050
+ "loss": 0.0183,
2051
+ "step": 238
2052
+ },
2053
+ {
2054
+ "epoch": 2.896969696969697,
2055
+ "grad_norm": 0.0332886204123497,
2056
+ "learning_rate": 4.4265828730079987e-05,
2057
+ "loss": 0.0221,
2058
+ "step": 239
2059
+ },
2060
+ {
2061
+ "epoch": 2.909090909090909,
2062
+ "grad_norm": 0.029150154441595078,
2063
+ "learning_rate": 4.3843160261067655e-05,
2064
+ "loss": 0.0186,
2065
+ "step": 240
2066
+ },
2067
+ {
2068
+ "epoch": 2.909090909090909,
2069
+ "eval_loss": 0.022352781146764755,
2070
+ "eval_runtime": 6.1961,
2071
+ "eval_samples_per_second": 8.07,
2072
+ "eval_steps_per_second": 2.098,
2073
+ "step": 240
2074
+ },
2075
+ {
2076
+ "epoch": 2.9212121212121214,
2077
+ "grad_norm": 0.029591498896479607,
2078
+ "learning_rate": 4.342093806672678e-05,
2079
+ "loss": 0.0181,
2080
+ "step": 241
2081
+ },
2082
+ {
2083
+ "epoch": 2.9333333333333336,
2084
+ "grad_norm": 0.03216252475976944,
2085
+ "learning_rate": 4.2999192751568564e-05,
2086
+ "loss": 0.0203,
2087
+ "step": 242
2088
+ },
2089
+ {
2090
+ "epoch": 2.9454545454545453,
2091
+ "grad_norm": 0.02891668863594532,
2092
+ "learning_rate": 4.2577954885537986e-05,
2093
+ "loss": 0.0181,
2094
+ "step": 243
2095
+ },
2096
+ {
2097
+ "epoch": 2.9575757575757575,
2098
+ "grad_norm": 0.028023086488246918,
2099
+ "learning_rate": 4.215725500179787e-05,
2100
+ "loss": 0.0191,
2101
+ "step": 244
2102
+ },
2103
+ {
2104
+ "epoch": 2.9696969696969697,
2105
+ "grad_norm": 0.03082926571369171,
2106
+ "learning_rate": 4.1737123594515756e-05,
2107
+ "loss": 0.0201,
2108
+ "step": 245
2109
+ },
2110
+ {
2111
+ "epoch": 2.9696969696969697,
2112
+ "eval_loss": 0.02198323793709278,
2113
+ "eval_runtime": 6.1948,
2114
+ "eval_samples_per_second": 8.071,
2115
+ "eval_steps_per_second": 2.099,
2116
+ "step": 245
2117
+ },
2118
+ {
2119
+ "epoch": 2.981818181818182,
2120
+ "grad_norm": 0.0321161188185215,
2121
+ "learning_rate": 4.131759111665349e-05,
2122
+ "loss": 0.0191,
2123
+ "step": 246
2124
+ },
2125
+ {
2126
+ "epoch": 2.993939393939394,
2127
+ "grad_norm": 0.026935642585158348,
2128
+ "learning_rate": 4.089868797775989e-05,
2129
+ "loss": 0.0185,
2130
+ "step": 247
2131
+ },
2132
+ {
2133
+ "epoch": 3.006060606060606,
2134
+ "grad_norm": 0.05411810800433159,
2135
+ "learning_rate": 4.0480444541766576e-05,
2136
+ "loss": 0.0301,
2137
+ "step": 248
2138
+ },
2139
+ {
2140
+ "epoch": 3.018181818181818,
2141
+ "grad_norm": 0.027184097096323967,
2142
+ "learning_rate": 4.0062891124787e-05,
2143
+ "loss": 0.0188,
2144
+ "step": 249
2145
+ },
2146
+ {
2147
+ "epoch": 3.0303030303030303,
2148
+ "grad_norm": 0.022542983293533325,
2149
+ "learning_rate": 3.964605799291897e-05,
2150
+ "loss": 0.0147,
2151
+ "step": 250
2152
+ },
2153
+ {
2154
+ "epoch": 3.0303030303030303,
2155
+ "eval_loss": 0.021969465538859367,
2156
+ "eval_runtime": 6.1917,
2157
+ "eval_samples_per_second": 8.075,
2158
+ "eval_steps_per_second": 2.1,
2159
+ "step": 250
2160
+ },
2161
+ {
2162
+ "epoch": 3.0424242424242425,
2163
+ "grad_norm": 0.03472661226987839,
2164
+ "learning_rate": 3.922997536005094e-05,
2165
+ "loss": 0.0178,
2166
+ "step": 251
2167
+ },
2168
+ {
2169
+ "epoch": 3.0545454545454547,
2170
+ "grad_norm": 0.028128741309046745,
2171
+ "learning_rate": 3.8814673385671894e-05,
2172
+ "loss": 0.0157,
2173
+ "step": 252
2174
+ },
2175
+ {
2176
+ "epoch": 3.066666666666667,
2177
+ "grad_norm": 0.03135592117905617,
2178
+ "learning_rate": 3.840018217268527e-05,
2179
+ "loss": 0.0161,
2180
+ "step": 253
2181
+ },
2182
+ {
2183
+ "epoch": 3.0787878787878786,
2184
+ "grad_norm": 0.03661385551095009,
2185
+ "learning_rate": 3.7986531765226964e-05,
2186
+ "loss": 0.0161,
2187
+ "step": 254
2188
+ },
2189
+ {
2190
+ "epoch": 3.090909090909091,
2191
+ "grad_norm": 0.03205974027514458,
2192
+ "learning_rate": 3.757375214648764e-05,
2193
+ "loss": 0.0142,
2194
+ "step": 255
2195
+ },
2196
+ {
2197
+ "epoch": 3.090909090909091,
2198
+ "eval_loss": 0.022621195763349533,
2199
+ "eval_runtime": 6.2467,
2200
+ "eval_samples_per_second": 8.004,
2201
+ "eval_steps_per_second": 2.081,
2202
+ "step": 255
2203
+ },
2204
+ {
2205
+ "epoch": 3.103030303030303,
2206
+ "grad_norm": 0.037527382373809814,
2207
+ "learning_rate": 3.716187323653939e-05,
2208
+ "loss": 0.0167,
2209
+ "step": 256
2210
+ },
2211
+ {
2212
+ "epoch": 3.1151515151515152,
2213
+ "grad_norm": 0.03540443629026413,
2214
+ "learning_rate": 3.675092489016693e-05,
2215
+ "loss": 0.0168,
2216
+ "step": 257
2217
+ },
2218
+ {
2219
+ "epoch": 3.1272727272727274,
2220
+ "grad_norm": 0.034389954060316086,
2221
+ "learning_rate": 3.634093689470371e-05,
2222
+ "loss": 0.017,
2223
+ "step": 258
2224
+ },
2225
+ {
2226
+ "epoch": 3.1393939393939396,
2227
+ "grad_norm": 0.033294420689344406,
2228
+ "learning_rate": 3.5931938967872766e-05,
2229
+ "loss": 0.016,
2230
+ "step": 259
2231
+ },
2232
+ {
2233
+ "epoch": 3.1515151515151514,
2234
+ "grad_norm": 0.028759747743606567,
2235
+ "learning_rate": 3.5523960755632574e-05,
2236
+ "loss": 0.0149,
2237
+ "step": 260
2238
+ },
2239
+ {
2240
+ "epoch": 3.1515151515151514,
2241
+ "eval_loss": 0.021824924275279045,
2242
+ "eval_runtime": 6.1966,
2243
+ "eval_samples_per_second": 8.069,
2244
+ "eval_steps_per_second": 2.098,
2245
+ "step": 260
2246
+ },
2247
+ {
2248
+ "epoch": 3.1636363636363636,
2249
+ "grad_norm": 0.02833370864391327,
2250
+ "learning_rate": 3.5117031830028274e-05,
2251
+ "loss": 0.0127,
2252
+ "step": 261
2253
+ },
2254
+ {
2255
+ "epoch": 3.175757575757576,
2256
+ "grad_norm": 0.0286524910479784,
2257
+ "learning_rate": 3.471118168704811e-05,
2258
+ "loss": 0.015,
2259
+ "step": 262
2260
+ },
2261
+ {
2262
+ "epoch": 3.187878787878788,
2263
+ "grad_norm": 0.02769540622830391,
2264
+ "learning_rate": 3.4306439744485454e-05,
2265
+ "loss": 0.0154,
2266
+ "step": 263
2267
+ },
2268
+ {
2269
+ "epoch": 3.2,
2270
+ "grad_norm": 0.03221355006098747,
2271
+ "learning_rate": 3.390283533980646e-05,
2272
+ "loss": 0.0167,
2273
+ "step": 264
2274
+ },
2275
+ {
2276
+ "epoch": 3.212121212121212,
2277
+ "grad_norm": 0.026392612606287003,
2278
+ "learning_rate": 3.350039772802354e-05,
2279
+ "loss": 0.0151,
2280
+ "step": 265
2281
+ },
2282
+ {
2283
+ "epoch": 3.212121212121212,
2284
+ "eval_loss": 0.02153392694890499,
2285
+ "eval_runtime": 6.1848,
2286
+ "eval_samples_per_second": 8.084,
2287
+ "eval_steps_per_second": 2.102,
2288
+ "step": 265
2289
+ },
2290
+ {
2291
+ "epoch": 3.224242424242424,
2292
+ "grad_norm": 0.03104759193956852,
2293
+ "learning_rate": 3.309915607957487e-05,
2294
+ "loss": 0.0171,
2295
+ "step": 266
2296
+ },
2297
+ {
2298
+ "epoch": 3.2363636363636363,
2299
+ "grad_norm": 0.028836429119110107,
2300
+ "learning_rate": 3.269913947820998e-05,
2301
+ "loss": 0.0158,
2302
+ "step": 267
2303
+ },
2304
+ {
2305
+ "epoch": 3.2484848484848485,
2306
+ "grad_norm": 0.032903432846069336,
2307
+ "learning_rate": 3.2300376918881624e-05,
2308
+ "loss": 0.0156,
2309
+ "step": 268
2310
+ },
2311
+ {
2312
+ "epoch": 3.2606060606060607,
2313
+ "grad_norm": 0.030551951378583908,
2314
+ "learning_rate": 3.1902897305644095e-05,
2315
+ "loss": 0.0134,
2316
+ "step": 269
2317
+ },
2318
+ {
2319
+ "epoch": 3.2727272727272725,
2320
+ "grad_norm": 0.030059080570936203,
2321
+ "learning_rate": 3.1506729449558184e-05,
2322
+ "loss": 0.0174,
2323
+ "step": 270
2324
+ },
2325
+ {
2326
+ "epoch": 3.2727272727272725,
2327
+ "eval_loss": 0.021679332479834557,
2328
+ "eval_runtime": 6.1964,
2329
+ "eval_samples_per_second": 8.069,
2330
+ "eval_steps_per_second": 2.098,
2331
+ "step": 270
2332
+ },
2333
+ {
2334
+ "epoch": 3.2848484848484847,
2335
+ "grad_norm": 0.030379703268408775,
2336
+ "learning_rate": 3.1111902066602724e-05,
2337
+ "loss": 0.018,
2338
+ "step": 271
2339
+ },
2340
+ {
2341
+ "epoch": 3.296969696969697,
2342
+ "grad_norm": 0.02761555276811123,
2343
+ "learning_rate": 3.071844377559323e-05,
2344
+ "loss": 0.016,
2345
+ "step": 272
2346
+ },
2347
+ {
2348
+ "epoch": 3.309090909090909,
2349
+ "grad_norm": 0.026775086298584938,
2350
+ "learning_rate": 3.0326383096107426e-05,
2351
+ "loss": 0.014,
2352
+ "step": 273
2353
+ },
2354
+ {
2355
+ "epoch": 3.3212121212121213,
2356
+ "grad_norm": 0.03328753635287285,
2357
+ "learning_rate": 2.9935748446418066e-05,
2358
+ "loss": 0.0169,
2359
+ "step": 274
2360
+ },
2361
+ {
2362
+ "epoch": 3.3333333333333335,
2363
+ "grad_norm": 0.03564237430691719,
2364
+ "learning_rate": 2.9546568141433006e-05,
2365
+ "loss": 0.0172,
2366
+ "step": 275
2367
+ },
2368
+ {
2369
+ "epoch": 3.3333333333333335,
2370
+ "eval_loss": 0.021324800327420235,
2371
+ "eval_runtime": 6.1942,
2372
+ "eval_samples_per_second": 8.072,
2373
+ "eval_steps_per_second": 2.099,
2374
+ "step": 275
2375
+ },
2376
+ {
2377
+ "epoch": 3.3454545454545457,
2378
+ "grad_norm": 0.028079047799110413,
2379
+ "learning_rate": 2.915887039064287e-05,
2380
+ "loss": 0.0141,
2381
+ "step": 276
2382
+ },
2383
+ {
2384
+ "epoch": 3.3575757575757574,
2385
+ "grad_norm": 0.02460673451423645,
2386
+ "learning_rate": 2.8772683296076196e-05,
2387
+ "loss": 0.0126,
2388
+ "step": 277
2389
+ },
2390
+ {
2391
+ "epoch": 3.3696969696969696,
2392
+ "grad_norm": 0.04345537722110748,
2393
+ "learning_rate": 2.8388034850262646e-05,
2394
+ "loss": 0.0376,
2395
+ "step": 278
2396
+ },
2397
+ {
2398
+ "epoch": 3.381818181818182,
2399
+ "grad_norm": 0.0306687094271183,
2400
+ "learning_rate": 2.8004952934203838e-05,
2401
+ "loss": 0.017,
2402
+ "step": 279
2403
+ },
2404
+ {
2405
+ "epoch": 3.393939393939394,
2406
+ "grad_norm": 0.033993735909461975,
2407
+ "learning_rate": 2.762346531535246e-05,
2408
+ "loss": 0.017,
2409
+ "step": 280
2410
+ },
2411
+ {
2412
+ "epoch": 3.393939393939394,
2413
+ "eval_loss": 0.02108747698366642,
2414
+ "eval_runtime": 6.2236,
2415
+ "eval_samples_per_second": 8.034,
2416
+ "eval_steps_per_second": 2.089,
2417
+ "step": 280
2418
+ },
2419
+ {
2420
+ "epoch": 3.4060606060606062,
2421
+ "grad_norm": 0.02444186620414257,
2422
+ "learning_rate": 2.7243599645599576e-05,
2423
+ "loss": 0.014,
2424
+ "step": 281
2425
+ },
2426
+ {
2427
+ "epoch": 3.418181818181818,
2428
+ "grad_norm": 0.028384167701005936,
2429
+ "learning_rate": 2.6865383459270265e-05,
2430
+ "loss": 0.0158,
2431
+ "step": 282
2432
+ },
2433
+ {
2434
+ "epoch": 3.43030303030303,
2435
+ "grad_norm": 0.03162846714258194,
2436
+ "learning_rate": 2.6488844171127903e-05,
2437
+ "loss": 0.017,
2438
+ "step": 283
2439
+ },
2440
+ {
2441
+ "epoch": 3.4424242424242424,
2442
+ "grad_norm": 0.027297567576169968,
2443
+ "learning_rate": 2.6114009074386846e-05,
2444
+ "loss": 0.0124,
2445
+ "step": 284
2446
+ },
2447
+ {
2448
+ "epoch": 3.4545454545454546,
2449
+ "grad_norm": 0.03545952960848808,
2450
+ "learning_rate": 2.574090533873431e-05,
2451
+ "loss": 0.0223,
2452
+ "step": 285
2453
+ },
2454
+ {
2455
+ "epoch": 3.4545454545454546,
2456
+ "eval_loss": 0.021236957982182503,
2457
+ "eval_runtime": 6.1899,
2458
+ "eval_samples_per_second": 8.078,
2459
+ "eval_steps_per_second": 2.1,
2460
+ "step": 285
2461
+ },
2462
+ {
2463
+ "epoch": 3.466666666666667,
2464
+ "grad_norm": 0.024587715044617653,
2465
+ "learning_rate": 2.5369560008360828e-05,
2466
+ "loss": 0.0132,
2467
+ "step": 286
2468
+ },
2469
+ {
2470
+ "epoch": 3.4787878787878785,
2471
+ "grad_norm": 0.025963526219129562,
2472
+ "learning_rate": 2.500000000000001e-05,
2473
+ "loss": 0.0132,
2474
+ "step": 287
2475
+ },
2476
+ {
2477
+ "epoch": 3.4909090909090907,
2478
+ "grad_norm": 0.03487967699766159,
2479
+ "learning_rate": 2.4632252100977566e-05,
2480
+ "loss": 0.0136,
2481
+ "step": 288
2482
+ },
2483
+ {
2484
+ "epoch": 3.503030303030303,
2485
+ "grad_norm": 0.030390363186597824,
2486
+ "learning_rate": 2.4266342967269552e-05,
2487
+ "loss": 0.0157,
2488
+ "step": 289
2489
+ },
2490
+ {
2491
+ "epoch": 3.515151515151515,
2492
+ "grad_norm": 0.030459538102149963,
2493
+ "learning_rate": 2.3902299121570333e-05,
2494
+ "loss": 0.0144,
2495
+ "step": 290
2496
+ },
2497
+ {
2498
+ "epoch": 3.515151515151515,
2499
+ "eval_loss": 0.02107882872223854,
2500
+ "eval_runtime": 6.2006,
2501
+ "eval_samples_per_second": 8.064,
2502
+ "eval_steps_per_second": 2.097,
2503
+ "step": 290
2504
+ },
2505
+ {
2506
+ "epoch": 3.5272727272727273,
2507
+ "grad_norm": 0.02951274998486042,
2508
+ "learning_rate": 2.354014695136997e-05,
2509
+ "loss": 0.0131,
2510
+ "step": 291
2511
+ },
2512
+ {
2513
+ "epoch": 3.5393939393939395,
2514
+ "grad_norm": 0.029193086549639702,
2515
+ "learning_rate": 2.317991270704167e-05,
2516
+ "loss": 0.0151,
2517
+ "step": 292
2518
+ },
2519
+ {
2520
+ "epoch": 3.5515151515151517,
2521
+ "grad_norm": 0.02726319245994091,
2522
+ "learning_rate": 2.282162249993895e-05,
2523
+ "loss": 0.0125,
2524
+ "step": 293
2525
+ },
2526
+ {
2527
+ "epoch": 3.5636363636363635,
2528
+ "grad_norm": 0.03212954103946686,
2529
+ "learning_rate": 2.246530230050301e-05,
2530
+ "loss": 0.0162,
2531
+ "step": 294
2532
+ },
2533
+ {
2534
+ "epoch": 3.5757575757575757,
2535
+ "grad_norm": 0.024175025522708893,
2536
+ "learning_rate": 2.211097793638029e-05,
2537
+ "loss": 0.0125,
2538
+ "step": 295
2539
+ },
2540
+ {
2541
+ "epoch": 3.5757575757575757,
2542
+ "eval_loss": 0.020796656608581543,
2543
+ "eval_runtime": 6.1933,
2544
+ "eval_samples_per_second": 8.073,
2545
+ "eval_steps_per_second": 2.099,
2546
+ "step": 295
2547
+ },
2548
+ {
2549
+ "epoch": 3.587878787878788,
2550
+ "grad_norm": 0.02679980918765068,
2551
+ "learning_rate": 2.175867509055033e-05,
2552
+ "loss": 0.0111,
2553
+ "step": 296
2554
+ },
2555
+ {
2556
+ "epoch": 3.6,
2557
+ "grad_norm": 0.031121132895350456,
2558
+ "learning_rate": 2.1408419299464245e-05,
2559
+ "loss": 0.0165,
2560
+ "step": 297
2561
+ },
2562
+ {
2563
+ "epoch": 3.6121212121212123,
2564
+ "grad_norm": 0.030764909461140633,
2565
+ "learning_rate": 2.106023595119358e-05,
2566
+ "loss": 0.0139,
2567
+ "step": 298
2568
+ },
2569
+ {
2570
+ "epoch": 3.624242424242424,
2571
+ "grad_norm": 0.0302122812718153,
2572
+ "learning_rate": 2.071415028359026e-05,
2573
+ "loss": 0.0148,
2574
+ "step": 299
2575
+ },
2576
+ {
2577
+ "epoch": 3.6363636363636362,
2578
+ "grad_norm": 0.029834948480129242,
2579
+ "learning_rate": 2.0370187382457068e-05,
2580
+ "loss": 0.0163,
2581
+ "step": 300
2582
+ },
2583
+ {
2584
+ "epoch": 3.6363636363636362,
2585
+ "eval_loss": 0.02069205790758133,
2586
+ "eval_runtime": 6.2054,
2587
+ "eval_samples_per_second": 8.057,
2588
+ "eval_steps_per_second": 2.095,
2589
+ "step": 300
2590
+ },
2591
+ {
2592
+ "epoch": 3.6484848484848484,
2593
+ "grad_norm": 0.03009135089814663,
2594
+ "learning_rate": 2.0028372179729403e-05,
2595
+ "loss": 0.0143,
2596
+ "step": 301
2597
+ },
2598
+ {
2599
+ "epoch": 3.6606060606060606,
2600
+ "grad_norm": 0.029639270156621933,
2601
+ "learning_rate": 1.9688729451668114e-05,
2602
+ "loss": 0.0168,
2603
+ "step": 302
2604
+ },
2605
+ {
2606
+ "epoch": 3.672727272727273,
2607
+ "grad_norm": 0.026824606582522392,
2608
+ "learning_rate": 1.935128381706355e-05,
2609
+ "loss": 0.0129,
2610
+ "step": 303
2611
+ },
2612
+ {
2613
+ "epoch": 3.6848484848484846,
2614
+ "grad_norm": 0.03427920117974281,
2615
+ "learning_rate": 1.901605973545116e-05,
2616
+ "loss": 0.0194,
2617
+ "step": 304
2618
+ },
2619
+ {
2620
+ "epoch": 3.6969696969696972,
2621
+ "grad_norm": 0.031160475686192513,
2622
+ "learning_rate": 1.868308150533847e-05,
2623
+ "loss": 0.015,
2624
+ "step": 305
2625
+ },
2626
+ {
2627
+ "epoch": 3.6969696969696972,
2628
+ "eval_loss": 0.020683376118540764,
2629
+ "eval_runtime": 6.1876,
2630
+ "eval_samples_per_second": 8.081,
2631
+ "eval_steps_per_second": 2.101,
2632
+ "step": 305
2633
+ },
2634
+ {
2635
+ "epoch": 3.709090909090909,
2636
+ "grad_norm": 0.033249229192733765,
2637
+ "learning_rate": 1.8352373262443916e-05,
2638
+ "loss": 0.0147,
2639
+ "step": 306
2640
+ },
2641
+ {
2642
+ "epoch": 3.721212121212121,
2643
+ "grad_norm": 0.029073260724544525,
2644
+ "learning_rate": 1.8023958977947304e-05,
2645
+ "loss": 0.0157,
2646
+ "step": 307
2647
+ },
2648
+ {
2649
+ "epoch": 3.7333333333333334,
2650
+ "grad_norm": 0.030520522966980934,
2651
+ "learning_rate": 1.7697862456752273e-05,
2652
+ "loss": 0.0152,
2653
+ "step": 308
2654
+ },
2655
+ {
2656
+ "epoch": 3.7454545454545456,
2657
+ "grad_norm": 0.029693983495235443,
2658
+ "learning_rate": 1.7374107335760936e-05,
2659
+ "loss": 0.0172,
2660
+ "step": 309
2661
+ },
2662
+ {
2663
+ "epoch": 3.757575757575758,
2664
+ "grad_norm": 0.03103681467473507,
2665
+ "learning_rate": 1.7052717082160346e-05,
2666
+ "loss": 0.0154,
2667
+ "step": 310
2668
+ },
2669
+ {
2670
+ "epoch": 3.757575757575758,
2671
+ "eval_loss": 0.02056981809437275,
2672
+ "eval_runtime": 6.1896,
2673
+ "eval_samples_per_second": 8.078,
2674
+ "eval_steps_per_second": 2.1,
2675
+ "step": 310
2676
+ },
2677
+ {
2678
+ "epoch": 3.7696969696969695,
2679
+ "grad_norm": 0.030047744512557983,
2680
+ "learning_rate": 1.673371499172174e-05,
2681
+ "loss": 0.015,
2682
+ "step": 311
2683
+ },
2684
+ {
2685
+ "epoch": 3.7818181818181817,
2686
+ "grad_norm": 0.03367823734879494,
2687
+ "learning_rate": 1.6417124187111775e-05,
2688
+ "loss": 0.017,
2689
+ "step": 312
2690
+ },
2691
+ {
2692
+ "epoch": 3.793939393939394,
2693
+ "grad_norm": 0.027037424966692924,
2694
+ "learning_rate": 1.610296761621662e-05,
2695
+ "loss": 0.0145,
2696
+ "step": 313
2697
+ },
2698
+ {
2699
+ "epoch": 3.806060606060606,
2700
+ "grad_norm": 0.030140092596411705,
2701
+ "learning_rate": 1.5791268050478486e-05,
2702
+ "loss": 0.0228,
2703
+ "step": 314
2704
+ },
2705
+ {
2706
+ "epoch": 3.8181818181818183,
2707
+ "grad_norm": 0.031016338616609573,
2708
+ "learning_rate": 1.5482048083245114e-05,
2709
+ "loss": 0.0186,
2710
+ "step": 315
2711
+ },
2712
+ {
2713
+ "epoch": 3.8181818181818183,
2714
+ "eval_loss": 0.02028246596455574,
2715
+ "eval_runtime": 6.1869,
2716
+ "eval_samples_per_second": 8.082,
2717
+ "eval_steps_per_second": 2.101,
2718
+ "step": 315
2719
+ },
2720
+ {
2721
+ "epoch": 3.83030303030303,
2722
+ "grad_norm": 0.02848219871520996,
2723
+ "learning_rate": 1.517533012813217e-05,
2724
+ "loss": 0.0159,
2725
+ "step": 316
2726
+ },
2727
+ {
2728
+ "epoch": 3.8424242424242423,
2729
+ "grad_norm": 0.024206412956118584,
2730
+ "learning_rate": 1.4871136417398406e-05,
2731
+ "loss": 0.0123,
2732
+ "step": 317
2733
+ },
2734
+ {
2735
+ "epoch": 3.8545454545454545,
2736
+ "grad_norm": 0.03030635416507721,
2737
+ "learning_rate": 1.4569489000334436e-05,
2738
+ "loss": 0.0137,
2739
+ "step": 318
2740
+ },
2741
+ {
2742
+ "epoch": 3.8666666666666667,
2743
+ "grad_norm": 0.03156241029500961,
2744
+ "learning_rate": 1.427040974166427e-05,
2745
+ "loss": 0.0159,
2746
+ "step": 319
2747
+ },
2748
+ {
2749
+ "epoch": 3.878787878787879,
2750
+ "grad_norm": 0.028942270204424858,
2751
+ "learning_rate": 1.3973920319960655e-05,
2752
+ "loss": 0.0135,
2753
+ "step": 320
2754
+ },
2755
+ {
2756
+ "epoch": 3.878787878787879,
2757
+ "eval_loss": 0.020162392407655716,
2758
+ "eval_runtime": 6.1914,
2759
+ "eval_samples_per_second": 8.076,
2760
+ "eval_steps_per_second": 2.1,
2761
+ "step": 320
2762
+ },
2763
+ {
2764
+ "epoch": 3.8909090909090907,
2765
+ "grad_norm": 0.03344618156552315,
2766
+ "learning_rate": 1.3680042226073552e-05,
2767
+ "loss": 0.0148,
2768
+ "step": 321
2769
+ },
2770
+ {
2771
+ "epoch": 3.9030303030303033,
2772
+ "grad_norm": 0.02961633913218975,
2773
+ "learning_rate": 1.3388796761572492e-05,
2774
+ "loss": 0.0141,
2775
+ "step": 322
2776
+ },
2777
+ {
2778
+ "epoch": 3.915151515151515,
2779
+ "grad_norm": 0.030708983540534973,
2780
+ "learning_rate": 1.310020503720254e-05,
2781
+ "loss": 0.0132,
2782
+ "step": 323
2783
+ },
2784
+ {
2785
+ "epoch": 3.9272727272727272,
2786
+ "grad_norm": 0.030072160065174103,
2787
+ "learning_rate": 1.2814287971354022e-05,
2788
+ "loss": 0.0161,
2789
+ "step": 324
2790
+ },
2791
+ {
2792
+ "epoch": 3.9393939393939394,
2793
+ "grad_norm": 0.03028644621372223,
2794
+ "learning_rate": 1.253106628854635e-05,
2795
+ "loss": 0.0159,
2796
+ "step": 325
2797
+ },
2798
+ {
2799
+ "epoch": 3.9393939393939394,
2800
+ "eval_loss": 0.020128030329942703,
2801
+ "eval_runtime": 6.1885,
2802
+ "eval_samples_per_second": 8.08,
2803
+ "eval_steps_per_second": 2.101,
2804
+ "step": 325
2805
+ },
2806
+ {
2807
+ "epoch": 3.9515151515151516,
2808
+ "grad_norm": 0.02972756326198578,
2809
+ "learning_rate": 1.2250560517925746e-05,
2810
+ "loss": 0.0142,
2811
+ "step": 326
2812
+ },
2813
+ {
2814
+ "epoch": 3.963636363636364,
2815
+ "grad_norm": 0.02873014286160469,
2816
+ "learning_rate": 1.1972790991777311e-05,
2817
+ "loss": 0.0155,
2818
+ "step": 327
2819
+ },
2820
+ {
2821
+ "epoch": 3.9757575757575756,
2822
+ "grad_norm": 0.028870223090052605,
2823
+ "learning_rate": 1.1697777844051105e-05,
2824
+ "loss": 0.0142,
2825
+ "step": 328
2826
+ },
2827
+ {
2828
+ "epoch": 3.987878787878788,
2829
+ "grad_norm": 0.02774449624121189,
2830
+ "learning_rate": 1.1425541008902851e-05,
2831
+ "loss": 0.0147,
2832
+ "step": 329
2833
+ },
2834
+ {
2835
+ "epoch": 4.0,
2836
+ "grad_norm": 0.04664117470383644,
2837
+ "learning_rate": 1.1156100219249022e-05,
2838
+ "loss": 0.0211,
2839
+ "step": 330
2840
+ },
2841
+ {
2842
+ "epoch": 4.0,
2843
+ "eval_loss": 0.01995450258255005,
2844
+ "eval_runtime": 6.191,
2845
+ "eval_samples_per_second": 8.076,
2846
+ "eval_steps_per_second": 2.1,
2847
+ "step": 330
2848
+ },
2849
+ {
2850
+ "epoch": 4.012121212121212,
2851
+ "grad_norm": 0.024339957162737846,
2852
+ "learning_rate": 1.0889475005336446e-05,
2853
+ "loss": 0.0133,
2854
+ "step": 331
2855
+ },
2856
+ {
2857
+ "epoch": 4.024242424242424,
2858
+ "grad_norm": 0.023921139538288116,
2859
+ "learning_rate": 1.0625684693326727e-05,
2860
+ "loss": 0.013,
2861
+ "step": 332
2862
+ },
2863
+ {
2864
+ "epoch": 4.036363636363636,
2865
+ "grad_norm": 0.02364080585539341,
2866
+ "learning_rate": 1.036474840389537e-05,
2867
+ "loss": 0.0132,
2868
+ "step": 333
2869
+ },
2870
+ {
2871
+ "epoch": 4.048484848484849,
2872
+ "grad_norm": 0.02356121875345707,
2873
+ "learning_rate": 1.0106685050845838e-05,
2874
+ "loss": 0.0121,
2875
+ "step": 334
2876
+ },
2877
+ {
2878
+ "epoch": 4.0606060606060606,
2879
+ "grad_norm": 0.025879928842186928,
2880
+ "learning_rate": 9.851513339738628e-06,
2881
+ "loss": 0.0134,
2882
+ "step": 335
2883
+ },
2884
+ {
2885
+ "epoch": 4.0606060606060606,
2886
+ "eval_loss": 0.0202109944075346,
2887
+ "eval_runtime": 6.1925,
2888
+ "eval_samples_per_second": 8.074,
2889
+ "eval_steps_per_second": 2.099,
2890
+ "step": 335
2891
+ },
2892
+ {
2893
+ "epoch": 4.072727272727272,
2894
+ "grad_norm": 0.02288251556456089,
2895
+ "learning_rate": 9.599251766535345e-06,
2896
+ "loss": 0.0121,
2897
+ "step": 336
2898
+ },
2899
+ {
2900
+ "epoch": 4.084848484848485,
2901
+ "grad_norm": 0.02703404612839222,
2902
+ "learning_rate": 9.349918616258114e-06,
2903
+ "loss": 0.0126,
2904
+ "step": 337
2905
+ },
2906
+ {
2907
+ "epoch": 4.096969696969697,
2908
+ "grad_norm": 0.025494417175650597,
2909
+ "learning_rate": 9.103531961664118e-06,
2910
+ "loss": 0.0122,
2911
+ "step": 338
2912
+ },
2913
+ {
2914
+ "epoch": 4.109090909090909,
2915
+ "grad_norm": 0.02807869389653206,
2916
+ "learning_rate": 8.860109661935674e-06,
2917
+ "loss": 0.0155,
2918
+ "step": 339
2919
+ },
2920
+ {
2921
+ "epoch": 4.121212121212121,
2922
+ "grad_norm": 0.027642810717225075,
2923
+ "learning_rate": 8.619669361385663e-06,
2924
+ "loss": 0.0113,
2925
+ "step": 340
2926
+ },
2927
+ {
2928
+ "epoch": 4.121212121212121,
2929
+ "eval_loss": 0.020561667159199715,
2930
+ "eval_runtime": 6.1965,
2931
+ "eval_samples_per_second": 8.069,
2932
+ "eval_steps_per_second": 2.098,
2933
+ "step": 340
2934
+ },
2935
+ {
2936
+ "epoch": 4.133333333333334,
2937
+ "grad_norm": 0.030346019193530083,
2938
+ "learning_rate": 8.38222848817864e-06,
2939
+ "loss": 0.0127,
2940
+ "step": 341
2941
+ },
2942
+ {
2943
+ "epoch": 4.1454545454545455,
2944
+ "grad_norm": 0.024746423587203026,
2945
+ "learning_rate": 8.14780425306758e-06,
2946
+ "loss": 0.0121,
2947
+ "step": 342
2948
+ },
2949
+ {
2950
+ "epoch": 4.157575757575757,
2951
+ "grad_norm": 0.026435259729623795,
2952
+ "learning_rate": 7.91641364814628e-06,
2953
+ "loss": 0.0109,
2954
+ "step": 343
2955
+ },
2956
+ {
2957
+ "epoch": 4.16969696969697,
2958
+ "grad_norm": 0.02962976135313511,
2959
+ "learning_rate": 7.688073445617799e-06,
2960
+ "loss": 0.0108,
2961
+ "step": 344
2962
+ },
2963
+ {
2964
+ "epoch": 4.181818181818182,
2965
+ "grad_norm": 0.02813326194882393,
2966
+ "learning_rate": 7.462800196578662e-06,
2967
+ "loss": 0.0117,
2968
+ "step": 345
2969
+ },
2970
+ {
2971
+ "epoch": 4.181818181818182,
2972
+ "eval_loss": 0.0208114180713892,
2973
+ "eval_runtime": 6.1943,
2974
+ "eval_samples_per_second": 8.072,
2975
+ "eval_steps_per_second": 2.099,
2976
+ "step": 345
2977
+ },
2978
+ {
2979
+ "epoch": 4.193939393939394,
2980
+ "grad_norm": 0.03237050771713257,
2981
+ "learning_rate": 7.240610229819195e-06,
2982
+ "loss": 0.013,
2983
+ "step": 346
2984
+ },
2985
+ {
2986
+ "epoch": 4.206060606060606,
2987
+ "grad_norm": 0.026286713778972626,
2988
+ "learning_rate": 7.0215196506399515e-06,
2989
+ "loss": 0.0108,
2990
+ "step": 347
2991
+ },
2992
+ {
2993
+ "epoch": 4.218181818181818,
2994
+ "grad_norm": 0.026608100160956383,
2995
+ "learning_rate": 6.8055443396842945e-06,
2996
+ "loss": 0.0103,
2997
+ "step": 348
2998
+ },
2999
+ {
3000
+ "epoch": 4.2303030303030305,
3001
+ "grad_norm": 0.03118029236793518,
3002
+ "learning_rate": 6.592699951787362e-06,
3003
+ "loss": 0.0138,
3004
+ "step": 349
3005
+ },
3006
+ {
3007
+ "epoch": 4.242424242424242,
3008
+ "grad_norm": 0.030633771792054176,
3009
+ "learning_rate": 6.3830019148412525e-06,
3010
+ "loss": 0.0108,
3011
+ "step": 350
3012
+ },
3013
+ {
3014
+ "epoch": 4.242424242424242,
3015
+ "eval_loss": 0.020906535908579826,
3016
+ "eval_runtime": 6.1873,
3017
+ "eval_samples_per_second": 8.081,
3018
+ "eval_steps_per_second": 2.101,
3019
+ "step": 350
3020
+ },
3021
+ {
3022
+ "epoch": 4.254545454545455,
3023
+ "grad_norm": 0.03377068042755127,
3024
+ "learning_rate": 6.17646542867682e-06,
3025
+ "loss": 0.0144,
3026
+ "step": 351
3027
+ },
3028
+ {
3029
+ "epoch": 4.266666666666667,
3030
+ "grad_norm": 0.027513034641742706,
3031
+ "learning_rate": 5.973105463961865e-06,
3032
+ "loss": 0.0107,
3033
+ "step": 352
3034
+ },
3035
+ {
3036
+ "epoch": 4.278787878787879,
3037
+ "grad_norm": 0.03077622503042221,
3038
+ "learning_rate": 5.772936761116027e-06,
3039
+ "loss": 0.0139,
3040
+ "step": 353
3041
+ },
3042
+ {
3043
+ "epoch": 4.290909090909091,
3044
+ "grad_norm": 0.026948513463139534,
3045
+ "learning_rate": 5.575973829242364e-06,
3046
+ "loss": 0.0126,
3047
+ "step": 354
3048
+ },
3049
+ {
3050
+ "epoch": 4.303030303030303,
3051
+ "grad_norm": 0.02911302261054516,
3052
+ "learning_rate": 5.382230945075556e-06,
3053
+ "loss": 0.012,
3054
+ "step": 355
3055
+ },
3056
+ {
3057
+ "epoch": 4.303030303030303,
3058
+ "eval_loss": 0.020746439695358276,
3059
+ "eval_runtime": 6.1873,
3060
+ "eval_samples_per_second": 8.081,
3061
+ "eval_steps_per_second": 2.101,
3062
+ "step": 355
3063
+ },
3064
+ {
3065
+ "epoch": 4.315151515151515,
3066
+ "grad_norm": 0.02364683710038662,
3067
+ "learning_rate": 5.191722151947226e-06,
3068
+ "loss": 0.0099,
3069
+ "step": 356
3070
+ },
3071
+ {
3072
+ "epoch": 4.327272727272727,
3073
+ "grad_norm": 0.031056983396410942,
3074
+ "learning_rate": 5.004461258767873e-06,
3075
+ "loss": 0.0143,
3076
+ "step": 357
3077
+ },
3078
+ {
3079
+ "epoch": 4.33939393939394,
3080
+ "grad_norm": 0.02985430881381035,
3081
+ "learning_rate": 4.820461839026047e-06,
3082
+ "loss": 0.0126,
3083
+ "step": 358
3084
+ },
3085
+ {
3086
+ "epoch": 4.351515151515152,
3087
+ "grad_norm": 0.02651560679078102,
3088
+ "learning_rate": 4.639737229804403e-06,
3089
+ "loss": 0.0115,
3090
+ "step": 359
3091
+ },
3092
+ {
3093
+ "epoch": 4.363636363636363,
3094
+ "grad_norm": 0.026479771360754967,
3095
+ "learning_rate": 4.462300530813024e-06,
3096
+ "loss": 0.0111,
3097
+ "step": 360
3098
+ },
3099
+ {
3100
+ "epoch": 4.363636363636363,
3101
+ "eval_loss": 0.020565090700984,
3102
+ "eval_runtime": 6.2012,
3103
+ "eval_samples_per_second": 8.063,
3104
+ "eval_steps_per_second": 2.096,
3105
+ "step": 360
3106
+ },
3107
+ {
3108
+ "epoch": 4.375757575757576,
3109
+ "grad_norm": 0.02071288600564003,
3110
+ "learning_rate": 4.2881646034398925e-06,
3111
+ "loss": 0.0114,
3112
+ "step": 361
3113
+ },
3114
+ {
3115
+ "epoch": 4.387878787878788,
3116
+ "grad_norm": 0.02533382549881935,
3117
+ "learning_rate": 4.117342069818603e-06,
3118
+ "loss": 0.0113,
3119
+ "step": 362
3120
+ },
3121
+ {
3122
+ "epoch": 4.4,
3123
+ "grad_norm": 0.021412553265690804,
3124
+ "learning_rate": 3.949845311913492e-06,
3125
+ "loss": 0.0115,
3126
+ "step": 363
3127
+ },
3128
+ {
3129
+ "epoch": 4.412121212121212,
3130
+ "grad_norm": 0.024555562064051628,
3131
+ "learning_rate": 3.7856864706221185e-06,
3132
+ "loss": 0.0098,
3133
+ "step": 364
3134
+ },
3135
+ {
3136
+ "epoch": 4.424242424242424,
3137
+ "grad_norm": 0.027632344514131546,
3138
+ "learning_rate": 3.6248774448952695e-06,
3139
+ "loss": 0.0118,
3140
+ "step": 365
3141
+ },
3142
+ {
3143
+ "epoch": 4.424242424242424,
3144
+ "eval_loss": 0.02050224132835865,
3145
+ "eval_runtime": 6.1859,
3146
+ "eval_samples_per_second": 8.083,
3147
+ "eval_steps_per_second": 2.102,
3148
+ "step": 365
3149
+ },
3150
+ {
3151
+ "epoch": 4.4363636363636365,
3152
+ "grad_norm": 0.028998758643865585,
3153
+ "learning_rate": 3.467429890874424e-06,
3154
+ "loss": 0.0111,
3155
+ "step": 366
3156
+ },
3157
+ {
3158
+ "epoch": 4.448484848484848,
3159
+ "grad_norm": 0.027949200943112373,
3160
+ "learning_rate": 3.3133552210468875e-06,
3161
+ "loss": 0.0122,
3162
+ "step": 367
3163
+ },
3164
+ {
3165
+ "epoch": 4.460606060606061,
3166
+ "grad_norm": 0.029877539724111557,
3167
+ "learning_rate": 3.162664603418608e-06,
3168
+ "loss": 0.0136,
3169
+ "step": 368
3170
+ },
3171
+ {
3172
+ "epoch": 4.472727272727273,
3173
+ "grad_norm": 0.02742207795381546,
3174
+ "learning_rate": 3.0153689607045845e-06,
3175
+ "loss": 0.0116,
3176
+ "step": 369
3177
+ },
3178
+ {
3179
+ "epoch": 4.484848484848484,
3180
+ "grad_norm": 0.02200300246477127,
3181
+ "learning_rate": 2.871478969537206e-06,
3182
+ "loss": 0.0099,
3183
+ "step": 370
3184
+ },
3185
+ {
3186
+ "epoch": 4.484848484848484,
3187
+ "eval_loss": 0.02058413252234459,
3188
+ "eval_runtime": 6.1924,
3189
+ "eval_samples_per_second": 8.074,
3190
+ "eval_steps_per_second": 2.099,
3191
+ "step": 370
3192
+ },
3193
+ {
3194
+ "epoch": 4.496969696969697,
3195
+ "grad_norm": 0.029120702296495438,
3196
+ "learning_rate": 2.731005059692332e-06,
3197
+ "loss": 0.0212,
3198
+ "step": 371
3199
+ },
3200
+ {
3201
+ "epoch": 4.509090909090909,
3202
+ "grad_norm": 0.030737141147255898,
3203
+ "learning_rate": 2.5939574133333312e-06,
3204
+ "loss": 0.0275,
3205
+ "step": 372
3206
+ },
3207
+ {
3208
+ "epoch": 4.5212121212121215,
3209
+ "grad_norm": 0.02619299292564392,
3210
+ "learning_rate": 2.4603459642729863e-06,
3211
+ "loss": 0.0104,
3212
+ "step": 373
3213
+ },
3214
+ {
3215
+ "epoch": 4.533333333333333,
3216
+ "grad_norm": 0.02171757072210312,
3217
+ "learning_rate": 2.330180397253473e-06,
3218
+ "loss": 0.0099,
3219
+ "step": 374
3220
+ },
3221
+ {
3222
+ "epoch": 4.545454545454545,
3223
+ "grad_norm": 0.022865932434797287,
3224
+ "learning_rate": 2.203470147244385e-06,
3225
+ "loss": 0.0118,
3226
+ "step": 375
3227
+ },
3228
+ {
3229
+ "epoch": 4.545454545454545,
3230
+ "eval_loss": 0.020584262907505035,
3231
+ "eval_runtime": 6.193,
3232
+ "eval_samples_per_second": 8.074,
3233
+ "eval_steps_per_second": 2.099,
3234
+ "step": 375
3235
+ },
3236
+ {
3237
+ "epoch": 4.557575757575758,
3238
+ "grad_norm": 0.02180948108434677,
3239
+ "learning_rate": 2.0802243987588066e-06,
3240
+ "loss": 0.0104,
3241
+ "step": 376
3242
+ },
3243
+ {
3244
+ "epoch": 4.569696969696969,
3245
+ "grad_norm": 0.027300819754600525,
3246
+ "learning_rate": 1.9604520851876198e-06,
3247
+ "loss": 0.0121,
3248
+ "step": 377
3249
+ },
3250
+ {
3251
+ "epoch": 4.581818181818182,
3252
+ "grad_norm": 0.027127033099532127,
3253
+ "learning_rate": 1.8441618881519184e-06,
3254
+ "loss": 0.0113,
3255
+ "step": 378
3256
+ },
3257
+ {
3258
+ "epoch": 4.593939393939394,
3259
+ "grad_norm": 0.026878971606492996,
3260
+ "learning_rate": 1.7313622368738014e-06,
3261
+ "loss": 0.0105,
3262
+ "step": 379
3263
+ },
3264
+ {
3265
+ "epoch": 4.606060606060606,
3266
+ "grad_norm": 0.02648119069635868,
3267
+ "learning_rate": 1.6220613075653202e-06,
3268
+ "loss": 0.0119,
3269
+ "step": 380
3270
+ },
3271
+ {
3272
+ "epoch": 4.606060606060606,
3273
+ "eval_loss": 0.02056843228638172,
3274
+ "eval_runtime": 6.1957,
3275
+ "eval_samples_per_second": 8.07,
3276
+ "eval_steps_per_second": 2.098,
3277
+ "step": 380
3278
+ },
3279
+ {
3280
+ "epoch": 4.618181818181818,
3281
+ "grad_norm": 0.026216818019747734,
3282
+ "learning_rate": 1.51626702283586e-06,
3283
+ "loss": 0.0098,
3284
+ "step": 381
3285
+ },
3286
+ {
3287
+ "epoch": 4.63030303030303,
3288
+ "grad_norm": 0.02351340465247631,
3289
+ "learning_rate": 1.4139870511178766e-06,
3290
+ "loss": 0.0116,
3291
+ "step": 382
3292
+ },
3293
+ {
3294
+ "epoch": 4.642424242424243,
3295
+ "grad_norm": 0.030724933370947838,
3296
+ "learning_rate": 1.3152288061110518e-06,
3297
+ "loss": 0.0101,
3298
+ "step": 383
3299
+ },
3300
+ {
3301
+ "epoch": 4.654545454545454,
3302
+ "grad_norm": 0.02688099816441536,
3303
+ "learning_rate": 1.2199994462448904e-06,
3304
+ "loss": 0.0113,
3305
+ "step": 384
3306
+ },
3307
+ {
3308
+ "epoch": 4.666666666666667,
3309
+ "grad_norm": 0.02722257934510708,
3310
+ "learning_rate": 1.128305874159896e-06,
3311
+ "loss": 0.0114,
3312
+ "step": 385
3313
+ },
3314
+ {
3315
+ "epoch": 4.666666666666667,
3316
+ "eval_loss": 0.02059413306415081,
3317
+ "eval_runtime": 6.2059,
3318
+ "eval_samples_per_second": 8.057,
3319
+ "eval_steps_per_second": 2.095,
3320
+ "step": 385
3321
+ },
3322
+ {
3323
+ "epoch": 4.678787878787879,
3324
+ "grad_norm": 0.02383565530180931,
3325
+ "learning_rate": 1.040154736207194e-06,
3326
+ "loss": 0.0106,
3327
+ "step": 386
3328
+ },
3329
+ {
3330
+ "epoch": 4.690909090909091,
3331
+ "grad_norm": 0.028037432581186295,
3332
+ "learning_rate": 9.555524219667989e-07,
3333
+ "loss": 0.0122,
3334
+ "step": 387
3335
+ },
3336
+ {
3337
+ "epoch": 4.703030303030303,
3338
+ "grad_norm": 0.021838784217834473,
3339
+ "learning_rate": 8.745050637844532e-07,
3340
+ "loss": 0.0097,
3341
+ "step": 388
3342
+ },
3343
+ {
3344
+ "epoch": 4.715151515151515,
3345
+ "grad_norm": 0.030912073329091072,
3346
+ "learning_rate": 7.970185363271431e-07,
3347
+ "loss": 0.0121,
3348
+ "step": 389
3349
+ },
3350
+ {
3351
+ "epoch": 4.7272727272727275,
3352
+ "grad_norm": 0.02470664493739605,
3353
+ "learning_rate": 7.230984561572729e-07,
3354
+ "loss": 0.0109,
3355
+ "step": 390
3356
+ },
3357
+ {
3358
+ "epoch": 4.7272727272727275,
3359
+ "eval_loss": 0.020591916516423225,
3360
+ "eval_runtime": 6.1901,
3361
+ "eval_samples_per_second": 8.077,
3362
+ "eval_steps_per_second": 2.1,
3363
+ "step": 390
3364
+ },
3365
+ {
3366
+ "epoch": 4.739393939393939,
3367
+ "grad_norm": 0.030810924246907234,
3368
+ "learning_rate": 6.527501813255344e-07,
3369
+ "loss": 0.0165,
3370
+ "step": 391
3371
+ },
3372
+ {
3373
+ "epoch": 4.751515151515152,
3374
+ "grad_norm": 0.025043383240699768,
3375
+ "learning_rate": 5.859788109825793e-07,
3376
+ "loss": 0.0096,
3377
+ "step": 392
3378
+ },
3379
+ {
3380
+ "epoch": 4.763636363636364,
3381
+ "grad_norm": 0.028706299141049385,
3382
+ "learning_rate": 5.227891850093314e-07,
3383
+ "loss": 0.0129,
3384
+ "step": 393
3385
+ },
3386
+ {
3387
+ "epoch": 4.775757575757575,
3388
+ "grad_norm": 0.0277020912617445,
3389
+ "learning_rate": 4.6318588366625616e-07,
3390
+ "loss": 0.0122,
3391
+ "step": 394
3392
+ },
3393
+ {
3394
+ "epoch": 4.787878787878788,
3395
+ "grad_norm": 0.02909735217690468,
3396
+ "learning_rate": 4.071732272613149e-07,
3397
+ "loss": 0.0124,
3398
+ "step": 395
3399
+ },
3400
+ {
3401
+ "epoch": 4.787878787878788,
3402
+ "eval_loss": 0.020531287416815758,
3403
+ "eval_runtime": 6.1957,
3404
+ "eval_samples_per_second": 8.07,
3405
+ "eval_steps_per_second": 2.098,
3406
+ "step": 395
3407
+ },
3408
+ {
3409
+ "epoch": 4.8,
3410
+ "grad_norm": 0.024658478796482086,
3411
+ "learning_rate": 3.5475527583681e-07,
3412
+ "loss": 0.0112,
3413
+ "step": 396
3414
+ },
3415
+ {
3416
+ "epoch": 4.8121212121212125,
3417
+ "grad_norm": 0.023081207647919655,
3418
+ "learning_rate": 3.059358288751202e-07,
3419
+ "loss": 0.0102,
3420
+ "step": 397
3421
+ },
3422
+ {
3423
+ "epoch": 4.824242424242424,
3424
+ "grad_norm": 0.03320831060409546,
3425
+ "learning_rate": 2.6071842502326527e-07,
3426
+ "loss": 0.0119,
3427
+ "step": 398
3428
+ },
3429
+ {
3430
+ "epoch": 4.836363636363636,
3431
+ "grad_norm": 0.025276964530348778,
3432
+ "learning_rate": 2.1910634183644474e-07,
3433
+ "loss": 0.0117,
3434
+ "step": 399
3435
+ },
3436
+ {
3437
+ "epoch": 4.848484848484849,
3438
+ "grad_norm": 0.02636777050793171,
3439
+ "learning_rate": 1.811025955404333e-07,
3440
+ "loss": 0.0111,
3441
+ "step": 400
3442
+ },
3443
+ {
3444
+ "epoch": 4.848484848484849,
3445
+ "eval_loss": 0.020571600645780563,
3446
+ "eval_runtime": 6.1951,
3447
+ "eval_samples_per_second": 8.071,
3448
+ "eval_steps_per_second": 2.098,
3449
+ "step": 400
3450
+ },
3451
+ {
3452
+ "epoch": 4.86060606060606,
3453
+ "grad_norm": 0.0283295139670372,
3454
+ "learning_rate": 1.4670994081297795e-07,
3455
+ "loss": 0.0141,
3456
+ "step": 401
3457
+ },
3458
+ {
3459
+ "epoch": 4.872727272727273,
3460
+ "grad_norm": 0.025880116969347,
3461
+ "learning_rate": 1.1593087058410779e-07,
3462
+ "loss": 0.0113,
3463
+ "step": 402
3464
+ },
3465
+ {
3466
+ "epoch": 4.884848484848485,
3467
+ "grad_norm": 0.02684679627418518,
3468
+ "learning_rate": 8.876761585545068e-08,
3469
+ "loss": 0.0104,
3470
+ "step": 403
3471
+ },
3472
+ {
3473
+ "epoch": 4.8969696969696965,
3474
+ "grad_norm": 0.027327047660946846,
3475
+ "learning_rate": 6.522214553850159e-08,
3476
+ "loss": 0.0122,
3477
+ "step": 404
3478
+ },
3479
+ {
3480
+ "epoch": 4.909090909090909,
3481
+ "grad_norm": 0.033394601196050644,
3482
+ "learning_rate": 4.529616631193112e-08,
3483
+ "loss": 0.012,
3484
+ "step": 405
3485
+ },
3486
+ {
3487
+ "epoch": 4.909090909090909,
3488
+ "eval_loss": 0.020557112991809845,
3489
+ "eval_runtime": 6.1866,
3490
+ "eval_samples_per_second": 8.082,
3491
+ "eval_steps_per_second": 2.101,
3492
+ "step": 405
3493
+ },
3494
+ {
3495
+ "epoch": 4.921212121212121,
3496
+ "grad_norm": 0.02917388454079628,
3497
+ "learning_rate": 2.899112249786229e-08,
3498
+ "loss": 0.0115,
3499
+ "step": 406
3500
+ },
3501
+ {
3502
+ "epoch": 4.933333333333334,
3503
+ "grad_norm": 0.032552849501371384,
3504
+ "learning_rate": 1.6308195957182027e-08,
3505
+ "loss": 0.0125,
3506
+ "step": 407
3507
+ },
3508
+ {
3509
+ "epoch": 4.945454545454545,
3510
+ "grad_norm": 0.026771927252411842,
3511
+ "learning_rate": 7.248306003865279e-09,
3512
+ "loss": 0.0123,
3513
+ "step": 408
3514
+ },
3515
+ {
3516
+ "epoch": 4.957575757575757,
3517
+ "grad_norm": 0.024449503049254417,
3518
+ "learning_rate": 1.8121093383671738e-09,
3519
+ "loss": 0.0117,
3520
+ "step": 409
3521
+ },
3522
+ {
3523
+ "epoch": 4.96969696969697,
3524
+ "grad_norm": 0.02603001333773136,
3525
+ "learning_rate": 0.0,
3526
+ "loss": 0.0104,
3527
+ "step": 410
3528
+ },
3529
+ {
3530
+ "epoch": 4.96969696969697,
3531
+ "eval_loss": 0.020535213872790337,
3532
+ "eval_runtime": 6.2062,
3533
+ "eval_samples_per_second": 8.056,
3534
+ "eval_steps_per_second": 2.095,
3535
+ "step": 410
3536
+ }
3537
+ ],
3538
+ "logging_steps": 1,
3539
+ "max_steps": 410,
3540
+ "num_input_tokens_seen": 0,
3541
+ "num_train_epochs": 5,
3542
+ "save_steps": 50,
3543
+ "stateful_callbacks": {
3544
+ "TrainerControl": {
3545
+ "args": {
3546
+ "should_epoch_stop": false,
3547
+ "should_evaluate": false,
3548
+ "should_log": false,
3549
+ "should_save": true,
3550
+ "should_training_stop": true
3551
+ },
3552
+ "attributes": {}
3553
+ }
3554
+ },
3555
+ "total_flos": 6.27193584892674e+17,
3556
+ "train_batch_size": 4,
3557
+ "trial_name": null,
3558
+ "trial_params": null
3559
+ }
checkpoint-410/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96aa9d85c0c8aaa8150b6566c50c34edbca6adae21b4dd043144f9d0462346e
3
+ size 5496
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.96969696969697,
3
+ "eval_loss": 0.020535212010145187,
4
+ "eval_runtime": 6.2115,
5
+ "eval_samples_per_second": 8.05,
6
+ "eval_steps_per_second": 2.093
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.96969696969697,
3
+ "total_flos": 6.27193584892674e+17,
4
+ "train_loss": 0.027697906577278202,
5
+ "train_runtime": 5078.5288,
6
+ "train_samples_per_second": 2.598,
7
+ "train_steps_per_second": 0.081
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 410, "loss": 0.103, "lr": 2.4390243902439027e-06, "epoch": 0.012121212121212121, "percentage": 0.24, "elapsed_time": "0:00:21", "remaining_time": "2:27:24"}
2
+ {"current_steps": 2, "total_steps": 410, "loss": 0.11, "lr": 4.8780487804878055e-06, "epoch": 0.024242424242424242, "percentage": 0.49, "elapsed_time": "0:00:39", "remaining_time": "2:15:54"}
3
+ {"current_steps": 3, "total_steps": 410, "loss": 0.1104, "lr": 7.317073170731707e-06, "epoch": 0.03636363636363636, "percentage": 0.73, "elapsed_time": "0:00:55", "remaining_time": "2:05:28"}
4
+ {"current_steps": 4, "total_steps": 410, "loss": 0.1076, "lr": 9.756097560975611e-06, "epoch": 0.048484848484848485, "percentage": 0.98, "elapsed_time": "0:01:06", "remaining_time": "1:51:59"}
5
+ {"current_steps": 5, "total_steps": 410, "loss": 0.1038, "lr": 1.2195121951219513e-05, "epoch": 0.06060606060606061, "percentage": 1.22, "elapsed_time": "0:01:17", "remaining_time": "1:44:23"}
6
+ {"current_steps": 5, "total_steps": 410, "eval_loss": 0.09789121896028519, "epoch": 0.06060606060606061, "percentage": 1.22, "elapsed_time": "0:01:25", "remaining_time": "1:55:20"}
7
+ {"current_steps": 6, "total_steps": 410, "loss": 0.0995, "lr": 1.4634146341463415e-05, "epoch": 0.07272727272727272, "percentage": 1.46, "elapsed_time": "0:01:35", "remaining_time": "1:47:37"}
8
+ {"current_steps": 7, "total_steps": 410, "loss": 0.0833, "lr": 1.707317073170732e-05, "epoch": 0.08484848484848485, "percentage": 1.71, "elapsed_time": "0:01:47", "remaining_time": "1:42:40"}
9
+ {"current_steps": 8, "total_steps": 410, "loss": 0.0756, "lr": 1.9512195121951222e-05, "epoch": 0.09696969696969697, "percentage": 1.95, "elapsed_time": "0:01:58", "remaining_time": "1:39:19"}
10
+ {"current_steps": 9, "total_steps": 410, "loss": 0.0681, "lr": 2.1951219512195124e-05, "epoch": 0.10909090909090909, "percentage": 2.2, "elapsed_time": "0:02:08", "remaining_time": "1:35:14"}
11
+ {"current_steps": 10, "total_steps": 410, "loss": 0.0759, "lr": 2.4390243902439026e-05, "epoch": 0.12121212121212122, "percentage": 2.44, "elapsed_time": "0:02:18", "remaining_time": "1:32:15"}
12
+ {"current_steps": 10, "total_steps": 410, "eval_loss": 0.07647334039211273, "epoch": 0.12121212121212122, "percentage": 2.44, "elapsed_time": "0:02:24", "remaining_time": "1:36:24"}
13
+ {"current_steps": 11, "total_steps": 410, "loss": 0.0757, "lr": 2.682926829268293e-05, "epoch": 0.13333333333333333, "percentage": 2.68, "elapsed_time": "0:02:35", "remaining_time": "1:33:43"}
14
+ {"current_steps": 12, "total_steps": 410, "loss": 0.0733, "lr": 2.926829268292683e-05, "epoch": 0.14545454545454545, "percentage": 2.93, "elapsed_time": "0:02:45", "remaining_time": "1:31:37"}
15
+ {"current_steps": 13, "total_steps": 410, "loss": 0.0751, "lr": 3.170731707317073e-05, "epoch": 0.15757575757575756, "percentage": 3.17, "elapsed_time": "0:02:57", "remaining_time": "1:30:10"}
16
+ {"current_steps": 14, "total_steps": 410, "loss": 0.0784, "lr": 3.414634146341464e-05, "epoch": 0.1696969696969697, "percentage": 3.41, "elapsed_time": "0:03:08", "remaining_time": "1:28:59"}
17
+ {"current_steps": 15, "total_steps": 410, "loss": 0.069, "lr": 3.6585365853658535e-05, "epoch": 0.18181818181818182, "percentage": 3.66, "elapsed_time": "0:03:19", "remaining_time": "1:27:29"}
18
+ {"current_steps": 15, "total_steps": 410, "eval_loss": 0.06831522285938263, "epoch": 0.18181818181818182, "percentage": 3.66, "elapsed_time": "0:03:25", "remaining_time": "1:30:12"}
19
+ {"current_steps": 16, "total_steps": 410, "loss": 0.0691, "lr": 3.9024390243902444e-05, "epoch": 0.19393939393939394, "percentage": 3.9, "elapsed_time": "0:03:37", "remaining_time": "1:29:16"}
20
+ {"current_steps": 17, "total_steps": 410, "loss": 0.0813, "lr": 4.146341463414634e-05, "epoch": 0.20606060606060606, "percentage": 4.15, "elapsed_time": "0:03:47", "remaining_time": "1:27:40"}
21
+ {"current_steps": 18, "total_steps": 410, "loss": 0.065, "lr": 4.390243902439025e-05, "epoch": 0.21818181818181817, "percentage": 4.39, "elapsed_time": "0:03:57", "remaining_time": "1:26:13"}
22
+ {"current_steps": 19, "total_steps": 410, "loss": 0.0617, "lr": 4.634146341463415e-05, "epoch": 0.23030303030303031, "percentage": 4.63, "elapsed_time": "0:04:08", "remaining_time": "1:25:15"}
23
+ {"current_steps": 20, "total_steps": 410, "loss": 0.0729, "lr": 4.878048780487805e-05, "epoch": 0.24242424242424243, "percentage": 4.88, "elapsed_time": "0:04:19", "remaining_time": "1:24:16"}
24
+ {"current_steps": 20, "total_steps": 410, "eval_loss": 0.062009546905756, "epoch": 0.24242424242424243, "percentage": 4.88, "elapsed_time": "0:04:25", "remaining_time": "1:26:18"}
25
+ {"current_steps": 21, "total_steps": 410, "loss": 0.0602, "lr": 5.121951219512195e-05, "epoch": 0.2545454545454545, "percentage": 5.12, "elapsed_time": "0:04:35", "remaining_time": "1:25:06"}
26
+ {"current_steps": 22, "total_steps": 410, "loss": 0.0772, "lr": 5.365853658536586e-05, "epoch": 0.26666666666666666, "percentage": 5.37, "elapsed_time": "0:04:49", "remaining_time": "1:25:14"}
27
+ {"current_steps": 23, "total_steps": 410, "loss": 0.0584, "lr": 5.6097560975609764e-05, "epoch": 0.2787878787878788, "percentage": 5.61, "elapsed_time": "0:05:02", "remaining_time": "1:24:58"}
28
+ {"current_steps": 24, "total_steps": 410, "loss": 0.0568, "lr": 5.853658536585366e-05, "epoch": 0.2909090909090909, "percentage": 5.85, "elapsed_time": "0:05:13", "remaining_time": "1:24:07"}
29
+ {"current_steps": 25, "total_steps": 410, "loss": 0.0545, "lr": 6.097560975609756e-05, "epoch": 0.30303030303030304, "percentage": 6.1, "elapsed_time": "0:05:26", "remaining_time": "1:23:51"}
30
+ {"current_steps": 25, "total_steps": 410, "eval_loss": 0.057142239063978195, "epoch": 0.30303030303030304, "percentage": 6.1, "elapsed_time": "0:05:32", "remaining_time": "1:25:27"}
31
+ {"current_steps": 26, "total_steps": 410, "loss": 0.0591, "lr": 6.341463414634146e-05, "epoch": 0.3151515151515151, "percentage": 6.34, "elapsed_time": "0:05:44", "remaining_time": "1:24:54"}
32
+ {"current_steps": 27, "total_steps": 410, "loss": 0.0836, "lr": 6.585365853658538e-05, "epoch": 0.32727272727272727, "percentage": 6.59, "elapsed_time": "0:05:55", "remaining_time": "1:23:56"}
33
+ {"current_steps": 28, "total_steps": 410, "loss": 0.0574, "lr": 6.829268292682928e-05, "epoch": 0.3393939393939394, "percentage": 6.83, "elapsed_time": "0:06:06", "remaining_time": "1:23:15"}
34
+ {"current_steps": 29, "total_steps": 410, "loss": 0.0506, "lr": 7.073170731707317e-05, "epoch": 0.3515151515151515, "percentage": 7.07, "elapsed_time": "0:06:19", "remaining_time": "1:23:09"}
35
+ {"current_steps": 30, "total_steps": 410, "loss": 0.0589, "lr": 7.317073170731707e-05, "epoch": 0.36363636363636365, "percentage": 7.32, "elapsed_time": "0:06:31", "remaining_time": "1:22:33"}
36
+ {"current_steps": 30, "total_steps": 410, "eval_loss": 0.05275052413344383, "epoch": 0.36363636363636365, "percentage": 7.32, "elapsed_time": "0:06:37", "remaining_time": "1:23:51"}
37
+ {"current_steps": 31, "total_steps": 410, "loss": 0.0536, "lr": 7.560975609756099e-05, "epoch": 0.37575757575757573, "percentage": 7.56, "elapsed_time": "0:06:45", "remaining_time": "1:22:41"}
38
+ {"current_steps": 32, "total_steps": 410, "loss": 0.0454, "lr": 7.804878048780489e-05, "epoch": 0.3878787878787879, "percentage": 7.8, "elapsed_time": "0:06:56", "remaining_time": "1:22:00"}
39
+ {"current_steps": 33, "total_steps": 410, "loss": 0.0727, "lr": 8.048780487804879e-05, "epoch": 0.4, "percentage": 8.05, "elapsed_time": "0:07:07", "remaining_time": "1:21:23"}
40
+ {"current_steps": 34, "total_steps": 410, "loss": 0.0557, "lr": 8.292682926829268e-05, "epoch": 0.4121212121212121, "percentage": 8.29, "elapsed_time": "0:07:19", "remaining_time": "1:20:57"}
41
+ {"current_steps": 35, "total_steps": 410, "loss": 0.0461, "lr": 8.53658536585366e-05, "epoch": 0.42424242424242425, "percentage": 8.54, "elapsed_time": "0:07:30", "remaining_time": "1:20:29"}
42
+ {"current_steps": 35, "total_steps": 410, "eval_loss": 0.05005570873618126, "epoch": 0.42424242424242425, "percentage": 8.54, "elapsed_time": "0:07:36", "remaining_time": "1:21:36"}
43
+ {"current_steps": 36, "total_steps": 410, "loss": 0.0627, "lr": 8.78048780487805e-05, "epoch": 0.43636363636363634, "percentage": 8.78, "elapsed_time": "0:07:46", "remaining_time": "1:20:42"}
44
+ {"current_steps": 37, "total_steps": 410, "loss": 0.0527, "lr": 9.02439024390244e-05, "epoch": 0.4484848484848485, "percentage": 9.02, "elapsed_time": "0:07:57", "remaining_time": "1:20:14"}
45
+ {"current_steps": 38, "total_steps": 410, "loss": 0.0509, "lr": 9.26829268292683e-05, "epoch": 0.46060606060606063, "percentage": 9.27, "elapsed_time": "0:08:07", "remaining_time": "1:19:33"}
46
+ {"current_steps": 39, "total_steps": 410, "loss": 0.0488, "lr": 9.51219512195122e-05, "epoch": 0.4727272727272727, "percentage": 9.51, "elapsed_time": "0:08:19", "remaining_time": "1:19:15"}
47
+ {"current_steps": 40, "total_steps": 410, "loss": 0.0522, "lr": 9.75609756097561e-05, "epoch": 0.48484848484848486, "percentage": 9.76, "elapsed_time": "0:08:30", "remaining_time": "1:18:44"}
48
+ {"current_steps": 40, "total_steps": 410, "eval_loss": 0.049276672303676605, "epoch": 0.48484848484848486, "percentage": 9.76, "elapsed_time": "0:08:37", "remaining_time": "1:19:42"}
49
+ {"current_steps": 41, "total_steps": 410, "loss": 0.0463, "lr": 0.0001, "epoch": 0.49696969696969695, "percentage": 10.0, "elapsed_time": "0:08:48", "remaining_time": "1:19:18"}
50
+ {"current_steps": 42, "total_steps": 410, "loss": 0.0433, "lr": 9.999818789066165e-05, "epoch": 0.509090909090909, "percentage": 10.24, "elapsed_time": "0:08:59", "remaining_time": "1:18:43"}
51
+ {"current_steps": 43, "total_steps": 410, "loss": 0.0393, "lr": 9.999275169399614e-05, "epoch": 0.5212121212121212, "percentage": 10.49, "elapsed_time": "0:09:09", "remaining_time": "1:18:08"}
52
+ {"current_steps": 44, "total_steps": 410, "loss": 0.044, "lr": 9.998369180404283e-05, "epoch": 0.5333333333333333, "percentage": 10.73, "elapsed_time": "0:09:19", "remaining_time": "1:17:33"}
53
+ {"current_steps": 45, "total_steps": 410, "loss": 0.052, "lr": 9.997100887750215e-05, "epoch": 0.5454545454545454, "percentage": 10.98, "elapsed_time": "0:09:30", "remaining_time": "1:17:05"}
54
+ {"current_steps": 45, "total_steps": 410, "eval_loss": 0.04825693741440773, "epoch": 0.5454545454545454, "percentage": 10.98, "elapsed_time": "0:09:36", "remaining_time": "1:17:55"}
55
+ {"current_steps": 46, "total_steps": 410, "loss": 0.0436, "lr": 9.995470383368808e-05, "epoch": 0.5575757575757576, "percentage": 11.22, "elapsed_time": "0:09:46", "remaining_time": "1:17:24"}
56
+ {"current_steps": 47, "total_steps": 410, "loss": 0.0431, "lr": 9.99347778544615e-05, "epoch": 0.5696969696969697, "percentage": 11.46, "elapsed_time": "0:09:57", "remaining_time": "1:16:55"}
57
+ {"current_steps": 48, "total_steps": 410, "loss": 0.0526, "lr": 9.991123238414455e-05, "epoch": 0.5818181818181818, "percentage": 11.71, "elapsed_time": "0:10:08", "remaining_time": "1:16:31"}
58
+ {"current_steps": 49, "total_steps": 410, "loss": 0.0447, "lr": 9.98840691294159e-05, "epoch": 0.593939393939394, "percentage": 11.95, "elapsed_time": "0:10:19", "remaining_time": "1:16:06"}
59
+ {"current_steps": 50, "total_steps": 410, "loss": 0.0459, "lr": 9.985329005918702e-05, "epoch": 0.6060606060606061, "percentage": 12.2, "elapsed_time": "0:10:32", "remaining_time": "1:15:55"}
60
+ {"current_steps": 50, "total_steps": 410, "eval_loss": 0.045825447887182236, "epoch": 0.6060606060606061, "percentage": 12.2, "elapsed_time": "0:10:38", "remaining_time": "1:16:39"}
61
+ {"current_steps": 51, "total_steps": 410, "loss": 0.0417, "lr": 9.981889740445958e-05, "epoch": 0.6181818181818182, "percentage": 12.44, "elapsed_time": "0:10:55", "remaining_time": "1:16:55"}
62
+ {"current_steps": 52, "total_steps": 410, "loss": 0.0446, "lr": 9.978089365816357e-05, "epoch": 0.6303030303030303, "percentage": 12.68, "elapsed_time": "0:11:06", "remaining_time": "1:16:25"}
63
+ {"current_steps": 53, "total_steps": 410, "loss": 0.0451, "lr": 9.973928157497674e-05, "epoch": 0.6424242424242425, "percentage": 12.93, "elapsed_time": "0:11:18", "remaining_time": "1:16:07"}
64
+ {"current_steps": 54, "total_steps": 410, "loss": 0.0416, "lr": 9.969406417112489e-05, "epoch": 0.6545454545454545, "percentage": 13.17, "elapsed_time": "0:11:27", "remaining_time": "1:15:29"}
65
+ {"current_steps": 55, "total_steps": 410, "loss": 0.0363, "lr": 9.964524472416319e-05, "epoch": 0.6666666666666666, "percentage": 13.41, "elapsed_time": "0:11:37", "remaining_time": "1:15:05"}
66
+ {"current_steps": 55, "total_steps": 410, "eval_loss": 0.0433911457657814, "epoch": 0.6666666666666666, "percentage": 13.41, "elapsed_time": "0:11:44", "remaining_time": "1:15:45"}
67
+ {"current_steps": 56, "total_steps": 410, "loss": 0.0457, "lr": 9.95928267727387e-05, "epoch": 0.6787878787878788, "percentage": 13.66, "elapsed_time": "0:11:54", "remaining_time": "1:15:18"}
68
+ {"current_steps": 57, "total_steps": 410, "loss": 0.0367, "lr": 9.953681411633376e-05, "epoch": 0.6909090909090909, "percentage": 13.9, "elapsed_time": "0:12:04", "remaining_time": "1:14:49"}
69
+ {"current_steps": 58, "total_steps": 410, "loss": 0.0428, "lr": 9.947721081499068e-05, "epoch": 0.703030303030303, "percentage": 14.15, "elapsed_time": "0:12:16", "remaining_time": "1:14:30"}
70
+ {"current_steps": 59, "total_steps": 410, "loss": 0.0456, "lr": 9.941402118901744e-05, "epoch": 0.7151515151515152, "percentage": 14.39, "elapsed_time": "0:12:27", "remaining_time": "1:14:04"}
71
+ {"current_steps": 60, "total_steps": 410, "loss": 0.0553, "lr": 9.934724981867446e-05, "epoch": 0.7272727272727273, "percentage": 14.63, "elapsed_time": "0:12:37", "remaining_time": "1:13:37"}
72
+ {"current_steps": 60, "total_steps": 410, "eval_loss": 0.04182567819952965, "epoch": 0.7272727272727273, "percentage": 14.63, "elapsed_time": "0:12:43", "remaining_time": "1:14:14"}
73
+ {"current_steps": 61, "total_steps": 410, "loss": 0.0443, "lr": 9.927690154384273e-05, "epoch": 0.7393939393939394, "percentage": 14.88, "elapsed_time": "0:12:52", "remaining_time": "1:13:40"}
74
+ {"current_steps": 62, "total_steps": 410, "loss": 0.0423, "lr": 9.920298146367286e-05, "epoch": 0.7515151515151515, "percentage": 15.12, "elapsed_time": "0:13:01", "remaining_time": "1:13:07"}
75
+ {"current_steps": 63, "total_steps": 410, "loss": 0.0469, "lr": 9.912549493621554e-05, "epoch": 0.7636363636363637, "percentage": 15.37, "elapsed_time": "0:13:12", "remaining_time": "1:12:44"}
76
+ {"current_steps": 64, "total_steps": 410, "loss": 0.0428, "lr": 9.904444757803321e-05, "epoch": 0.7757575757575758, "percentage": 15.61, "elapsed_time": "0:13:24", "remaining_time": "1:12:29"}
77
+ {"current_steps": 65, "total_steps": 410, "loss": 0.0444, "lr": 9.895984526379281e-05, "epoch": 0.7878787878787878, "percentage": 15.85, "elapsed_time": "0:13:36", "remaining_time": "1:12:16"}
78
+ {"current_steps": 65, "total_steps": 410, "eval_loss": 0.0403163880109787, "epoch": 0.7878787878787878, "percentage": 15.85, "elapsed_time": "0:13:43", "remaining_time": "1:12:49"}
79
+ {"current_steps": 66, "total_steps": 410, "loss": 0.0389, "lr": 9.887169412584011e-05, "epoch": 0.8, "percentage": 16.1, "elapsed_time": "0:13:55", "remaining_time": "1:12:36"}
80
+ {"current_steps": 67, "total_steps": 410, "loss": 0.0397, "lr": 9.878000055375512e-05, "epoch": 0.8121212121212121, "percentage": 16.34, "elapsed_time": "0:14:07", "remaining_time": "1:12:16"}
81
+ {"current_steps": 68, "total_steps": 410, "loss": 0.0387, "lr": 9.868477119388896e-05, "epoch": 0.8242424242424242, "percentage": 16.59, "elapsed_time": "0:14:18", "remaining_time": "1:11:55"}
82
+ {"current_steps": 69, "total_steps": 410, "loss": 0.0344, "lr": 9.858601294888213e-05, "epoch": 0.8363636363636363, "percentage": 16.83, "elapsed_time": "0:14:29", "remaining_time": "1:11:36"}
83
+ {"current_steps": 70, "total_steps": 410, "loss": 0.0469, "lr": 9.848373297716414e-05, "epoch": 0.8484848484848485, "percentage": 17.07, "elapsed_time": "0:14:40", "remaining_time": "1:11:16"}
84
+ {"current_steps": 70, "total_steps": 410, "eval_loss": 0.03973233327269554, "epoch": 0.8484848484848485, "percentage": 17.07, "elapsed_time": "0:14:46", "remaining_time": "1:11:46"}
85
+ {"current_steps": 71, "total_steps": 410, "loss": 0.0388, "lr": 9.837793869243468e-05, "epoch": 0.8606060606060606, "percentage": 17.32, "elapsed_time": "0:14:55", "remaining_time": "1:11:15"}
86
+ {"current_steps": 72, "total_steps": 410, "loss": 0.0415, "lr": 9.82686377631262e-05, "epoch": 0.8727272727272727, "percentage": 17.56, "elapsed_time": "0:15:06", "remaining_time": "1:10:55"}
87
+ {"current_steps": 73, "total_steps": 410, "loss": 0.037, "lr": 9.815583811184808e-05, "epoch": 0.8848484848484849, "percentage": 17.8, "elapsed_time": "0:15:16", "remaining_time": "1:10:30"}
88
+ {"current_steps": 74, "total_steps": 410, "loss": 0.0408, "lr": 9.803954791481239e-05, "epoch": 0.896969696969697, "percentage": 18.05, "elapsed_time": "0:15:26", "remaining_time": "1:10:07"}
89
+ {"current_steps": 75, "total_steps": 410, "loss": 0.0417, "lr": 9.791977560124119e-05, "epoch": 0.9090909090909091, "percentage": 18.29, "elapsed_time": "0:15:37", "remaining_time": "1:09:45"}
90
+ {"current_steps": 75, "total_steps": 410, "eval_loss": 0.038558006286621094, "epoch": 0.9090909090909091, "percentage": 18.29, "elapsed_time": "0:15:43", "remaining_time": "1:10:13"}
91
+ {"current_steps": 76, "total_steps": 410, "loss": 0.0427, "lr": 9.779652985275562e-05, "epoch": 0.9212121212121213, "percentage": 18.54, "elapsed_time": "0:15:53", "remaining_time": "1:09:49"}
92
+ {"current_steps": 77, "total_steps": 410, "loss": 0.0312, "lr": 9.766981960274653e-05, "epoch": 0.9333333333333333, "percentage": 18.78, "elapsed_time": "0:16:05", "remaining_time": "1:09:36"}
93
+ {"current_steps": 78, "total_steps": 410, "loss": 0.0424, "lr": 9.753965403572703e-05, "epoch": 0.9454545454545454, "percentage": 19.02, "elapsed_time": "0:16:17", "remaining_time": "1:09:20"}
94
+ {"current_steps": 79, "total_steps": 410, "loss": 0.0368, "lr": 9.740604258666668e-05, "epoch": 0.9575757575757575, "percentage": 19.27, "elapsed_time": "0:16:29", "remaining_time": "1:09:04"}
95
+ {"current_steps": 80, "total_steps": 410, "loss": 0.0388, "lr": 9.726899494030768e-05, "epoch": 0.9696969696969697, "percentage": 19.51, "elapsed_time": "0:16:40", "remaining_time": "1:08:45"}
96
+ {"current_steps": 80, "total_steps": 410, "eval_loss": 0.037164073437452316, "epoch": 0.9696969696969697, "percentage": 19.51, "elapsed_time": "0:16:46", "remaining_time": "1:09:11"}
97
+ {"current_steps": 81, "total_steps": 410, "loss": 0.0367, "lr": 9.71285210304628e-05, "epoch": 0.9818181818181818, "percentage": 19.76, "elapsed_time": "0:16:59", "remaining_time": "1:09:02"}
98
+ {"current_steps": 82, "total_steps": 410, "loss": 0.0399, "lr": 9.698463103929542e-05, "epoch": 0.9939393939393939, "percentage": 20.0, "elapsed_time": "0:17:09", "remaining_time": "1:08:36"}
99
+ {"current_steps": 83, "total_steps": 410, "loss": 0.0545, "lr": 9.683733539658139e-05, "epoch": 1.006060606060606, "percentage": 20.24, "elapsed_time": "0:17:19", "remaining_time": "1:08:14"}
100
+ {"current_steps": 84, "total_steps": 410, "loss": 0.048, "lr": 9.66866447789531e-05, "epoch": 1.018181818181818, "percentage": 20.49, "elapsed_time": "0:17:29", "remaining_time": "1:07:53"}
101
+ {"current_steps": 85, "total_steps": 410, "loss": 0.0309, "lr": 9.653257010912559e-05, "epoch": 1.0303030303030303, "percentage": 20.73, "elapsed_time": "0:17:39", "remaining_time": "1:07:29"}
102
+ {"current_steps": 85, "total_steps": 410, "eval_loss": 0.03581343591213226, "epoch": 1.0303030303030303, "percentage": 20.73, "elapsed_time": "0:17:45", "remaining_time": "1:07:53"}
103
+ {"current_steps": 86, "total_steps": 410, "loss": 0.0659, "lr": 9.637512255510475e-05, "epoch": 1.0424242424242425, "percentage": 20.98, "elapsed_time": "0:17:54", "remaining_time": "1:07:27"}
104
+ {"current_steps": 87, "total_steps": 410, "loss": 0.0502, "lr": 9.621431352937789e-05, "epoch": 1.0545454545454545, "percentage": 21.22, "elapsed_time": "0:18:04", "remaining_time": "1:07:05"}
105
+ {"current_steps": 88, "total_steps": 410, "loss": 0.0318, "lr": 9.605015468808651e-05, "epoch": 1.0666666666666667, "percentage": 21.46, "elapsed_time": "0:18:14", "remaining_time": "1:06:43"}
106
+ {"current_steps": 89, "total_steps": 410, "loss": 0.0446, "lr": 9.58826579301814e-05, "epoch": 1.0787878787878789, "percentage": 21.71, "elapsed_time": "0:18:26", "remaining_time": "1:06:29"}
107
+ {"current_steps": 90, "total_steps": 410, "loss": 0.0487, "lr": 9.571183539656011e-05, "epoch": 1.0909090909090908, "percentage": 21.95, "elapsed_time": "0:18:38", "remaining_time": "1:06:16"}
108
+ {"current_steps": 90, "total_steps": 410, "eval_loss": 0.0354202575981617, "epoch": 1.0909090909090908, "percentage": 21.95, "elapsed_time": "0:18:44", "remaining_time": "1:06:38"}
109
+ {"current_steps": 91, "total_steps": 410, "loss": 0.0403, "lr": 9.553769946918697e-05, "epoch": 1.103030303030303, "percentage": 22.2, "elapsed_time": "0:18:54", "remaining_time": "1:06:16"}
110
+ {"current_steps": 92, "total_steps": 410, "loss": 0.032, "lr": 9.536026277019561e-05, "epoch": 1.1151515151515152, "percentage": 22.44, "elapsed_time": "0:19:05", "remaining_time": "1:05:59"}
111
+ {"current_steps": 93, "total_steps": 410, "loss": 0.0366, "lr": 9.517953816097396e-05, "epoch": 1.1272727272727272, "percentage": 22.68, "elapsed_time": "0:19:13", "remaining_time": "1:05:33"}
112
+ {"current_steps": 94, "total_steps": 410, "loss": 0.0383, "lr": 9.499553874123212e-05, "epoch": 1.1393939393939394, "percentage": 22.93, "elapsed_time": "0:19:25", "remaining_time": "1:05:19"}
113
+ {"current_steps": 95, "total_steps": 410, "loss": 0.0348, "lr": 9.480827784805278e-05, "epoch": 1.1515151515151516, "percentage": 23.17, "elapsed_time": "0:19:34", "remaining_time": "1:04:55"}
114
+ {"current_steps": 95, "total_steps": 410, "eval_loss": 0.034031517803668976, "epoch": 1.1515151515151516, "percentage": 23.17, "elapsed_time": "0:19:41", "remaining_time": "1:05:16"}
115
+ {"current_steps": 96, "total_steps": 410, "loss": 0.0322, "lr": 9.461776905492446e-05, "epoch": 1.1636363636363636, "percentage": 23.41, "elapsed_time": "0:19:53", "remaining_time": "1:05:03"}
116
+ {"current_steps": 97, "total_steps": 410, "loss": 0.0302, "lr": 9.442402617075765e-05, "epoch": 1.1757575757575758, "percentage": 23.66, "elapsed_time": "0:20:05", "remaining_time": "1:04:50"}
117
+ {"current_steps": 98, "total_steps": 410, "loss": 0.0305, "lr": 9.422706323888397e-05, "epoch": 1.187878787878788, "percentage": 23.9, "elapsed_time": "0:20:14", "remaining_time": "1:04:26"}
118
+ {"current_steps": 99, "total_steps": 410, "loss": 0.0384, "lr": 9.402689453603815e-05, "epoch": 1.2, "percentage": 24.15, "elapsed_time": "0:20:25", "remaining_time": "1:04:09"}
119
+ {"current_steps": 100, "total_steps": 410, "loss": 0.0308, "lr": 9.382353457132317e-05, "epoch": 1.2121212121212122, "percentage": 24.39, "elapsed_time": "0:20:37", "remaining_time": "1:03:55"}
120
+ {"current_steps": 100, "total_steps": 410, "eval_loss": 0.03338392823934555, "epoch": 1.2121212121212122, "percentage": 24.39, "elapsed_time": "0:20:43", "remaining_time": "1:04:14"}
121
+ {"current_steps": 101, "total_steps": 410, "loss": 0.0341, "lr": 9.361699808515876e-05, "epoch": 1.2242424242424241, "percentage": 24.63, "elapsed_time": "0:20:59", "remaining_time": "1:04:13"}
122
+ {"current_steps": 102, "total_steps": 410, "loss": 0.0346, "lr": 9.340730004821266e-05, "epoch": 1.2363636363636363, "percentage": 24.88, "elapsed_time": "0:21:08", "remaining_time": "1:03:50"}
123
+ {"current_steps": 103, "total_steps": 410, "loss": 0.0408, "lr": 9.31944556603157e-05, "epoch": 1.2484848484848485, "percentage": 25.12, "elapsed_time": "0:21:20", "remaining_time": "1:03:37"}
124
+ {"current_steps": 104, "total_steps": 410, "loss": 0.0332, "lr": 9.297848034936006e-05, "epoch": 1.2606060606060607, "percentage": 25.37, "elapsed_time": "0:21:31", "remaining_time": "1:03:18"}
125
+ {"current_steps": 105, "total_steps": 410, "loss": 0.0318, "lr": 9.275938977018081e-05, "epoch": 1.2727272727272727, "percentage": 25.61, "elapsed_time": "0:21:42", "remaining_time": "1:03:03"}
126
+ {"current_steps": 105, "total_steps": 410, "eval_loss": 0.03301350772380829, "epoch": 1.2727272727272727, "percentage": 25.61, "elapsed_time": "0:21:48", "remaining_time": "1:03:21"}
127
+ {"current_steps": 106, "total_steps": 410, "loss": 0.0339, "lr": 9.253719980342135e-05, "epoch": 1.284848484848485, "percentage": 25.85, "elapsed_time": "0:21:59", "remaining_time": "1:03:04"}
128
+ {"current_steps": 107, "total_steps": 410, "loss": 0.0336, "lr": 9.231192655438221e-05, "epoch": 1.2969696969696969, "percentage": 26.1, "elapsed_time": "0:22:08", "remaining_time": "1:02:43"}
129
+ {"current_steps": 108, "total_steps": 410, "loss": 0.0324, "lr": 9.208358635185373e-05, "epoch": 1.309090909090909, "percentage": 26.34, "elapsed_time": "0:22:19", "remaining_time": "1:02:25"}
130
+ {"current_steps": 109, "total_steps": 410, "loss": 0.0332, "lr": 9.185219574693242e-05, "epoch": 1.3212121212121213, "percentage": 26.59, "elapsed_time": "0:22:27", "remaining_time": "1:02:01"}
131
+ {"current_steps": 110, "total_steps": 410, "loss": 0.028, "lr": 9.161777151182136e-05, "epoch": 1.3333333333333333, "percentage": 26.83, "elapsed_time": "0:22:38", "remaining_time": "1:01:43"}
132
+ {"current_steps": 110, "total_steps": 410, "eval_loss": 0.03218723088502884, "epoch": 1.3333333333333333, "percentage": 26.83, "elapsed_time": "0:22:44", "remaining_time": "1:02:00"}
133
+ {"current_steps": 111, "total_steps": 410, "loss": 0.0346, "lr": 9.138033063861436e-05, "epoch": 1.3454545454545455, "percentage": 27.07, "elapsed_time": "0:22:56", "remaining_time": "1:01:48"}
134
+ {"current_steps": 112, "total_steps": 410, "loss": 0.0283, "lr": 9.113989033806434e-05, "epoch": 1.3575757575757577, "percentage": 27.32, "elapsed_time": "0:23:08", "remaining_time": "1:01:35"}
135
+ {"current_steps": 113, "total_steps": 410, "loss": 0.0246, "lr": 9.089646803833589e-05, "epoch": 1.3696969696969696, "percentage": 27.56, "elapsed_time": "0:23:21", "remaining_time": "1:01:23"}
136
+ {"current_steps": 114, "total_steps": 410, "loss": 0.0317, "lr": 9.065008138374189e-05, "epoch": 1.3818181818181818, "percentage": 27.8, "elapsed_time": "0:23:32", "remaining_time": "1:01:07"}
137
+ {"current_steps": 115, "total_steps": 410, "loss": 0.0311, "lr": 9.040074823346465e-05, "epoch": 1.393939393939394, "percentage": 28.05, "elapsed_time": "0:23:43", "remaining_time": "1:00:51"}
138
+ {"current_steps": 115, "total_steps": 410, "eval_loss": 0.032092493027448654, "epoch": 1.393939393939394, "percentage": 28.05, "elapsed_time": "0:23:49", "remaining_time": "1:01:07"}
139
+ {"current_steps": 116, "total_steps": 410, "loss": 0.0389, "lr": 9.014848666026138e-05, "epoch": 1.406060606060606, "percentage": 28.29, "elapsed_time": "0:24:00", "remaining_time": "1:00:52"}
140
+ {"current_steps": 117, "total_steps": 410, "loss": 0.0287, "lr": 8.989331494915417e-05, "epoch": 1.4181818181818182, "percentage": 28.54, "elapsed_time": "0:24:13", "remaining_time": "1:00:39"}
141
+ {"current_steps": 118, "total_steps": 410, "loss": 0.0265, "lr": 8.963525159610465e-05, "epoch": 1.4303030303030302, "percentage": 28.78, "elapsed_time": "0:24:23", "remaining_time": "1:00:22"}
142
+ {"current_steps": 119, "total_steps": 410, "loss": 0.0262, "lr": 8.937431530667328e-05, "epoch": 1.4424242424242424, "percentage": 29.02, "elapsed_time": "0:24:33", "remaining_time": "1:00:02"}
143
+ {"current_steps": 120, "total_steps": 410, "loss": 0.0382, "lr": 8.911052499466357e-05, "epoch": 1.4545454545454546, "percentage": 29.27, "elapsed_time": "0:24:41", "remaining_time": "0:59:40"}
144
+ {"current_steps": 120, "total_steps": 410, "eval_loss": 0.031465690582990646, "epoch": 1.4545454545454546, "percentage": 29.27, "elapsed_time": "0:24:47", "remaining_time": "0:59:55"}
145
+ {"current_steps": 121, "total_steps": 410, "loss": 0.0336, "lr": 8.884389978075098e-05, "epoch": 1.4666666666666668, "percentage": 29.51, "elapsed_time": "0:24:57", "remaining_time": "0:59:36"}
146
+ {"current_steps": 122, "total_steps": 410, "loss": 0.0267, "lr": 8.857445899109715e-05, "epoch": 1.4787878787878788, "percentage": 29.76, "elapsed_time": "0:25:10", "remaining_time": "0:59:25"}
147
+ {"current_steps": 123, "total_steps": 410, "loss": 0.0258, "lr": 8.83022221559489e-05, "epoch": 1.490909090909091, "percentage": 30.0, "elapsed_time": "0:25:22", "remaining_time": "0:59:13"}
148
+ {"current_steps": 124, "total_steps": 410, "loss": 0.0344, "lr": 8.80272090082227e-05, "epoch": 1.503030303030303, "percentage": 30.24, "elapsed_time": "0:25:34", "remaining_time": "0:58:59"}
149
+ {"current_steps": 125, "total_steps": 410, "loss": 0.0316, "lr": 8.774943948207426e-05, "epoch": 1.5151515151515151, "percentage": 30.49, "elapsed_time": "0:25:44", "remaining_time": "0:58:41"}
150
+ {"current_steps": 125, "total_steps": 410, "eval_loss": 0.030392121523618698, "epoch": 1.5151515151515151, "percentage": 30.49, "elapsed_time": "0:25:50", "remaining_time": "0:58:56"}
151
+ {"current_steps": 126, "total_steps": 410, "loss": 0.0279, "lr": 8.746893371145366e-05, "epoch": 1.5272727272727273, "percentage": 30.73, "elapsed_time": "0:26:03", "remaining_time": "0:58:43"}
152
+ {"current_steps": 127, "total_steps": 410, "loss": 0.0292, "lr": 8.718571202864598e-05, "epoch": 1.5393939393939395, "percentage": 30.98, "elapsed_time": "0:26:12", "remaining_time": "0:58:24"}
153
+ {"current_steps": 128, "total_steps": 410, "loss": 0.0296, "lr": 8.689979496279746e-05, "epoch": 1.5515151515151515, "percentage": 31.22, "elapsed_time": "0:26:20", "remaining_time": "0:58:02"}
154
+ {"current_steps": 129, "total_steps": 410, "loss": 0.0286, "lr": 8.661120323842751e-05, "epoch": 1.5636363636363635, "percentage": 31.46, "elapsed_time": "0:26:33", "remaining_time": "0:57:50"}
155
+ {"current_steps": 130, "total_steps": 410, "loss": 0.0278, "lr": 8.631995777392645e-05, "epoch": 1.5757575757575757, "percentage": 31.71, "elapsed_time": "0:26:43", "remaining_time": "0:57:34"}
156
+ {"current_steps": 130, "total_steps": 410, "eval_loss": 0.029901880770921707, "epoch": 1.5757575757575757, "percentage": 31.71, "elapsed_time": "0:26:50", "remaining_time": "0:57:47"}
157
+ {"current_steps": 131, "total_steps": 410, "loss": 0.0277, "lr": 8.602607968003935e-05, "epoch": 1.587878787878788, "percentage": 31.95, "elapsed_time": "0:27:02", "remaining_time": "0:57:34"}
158
+ {"current_steps": 132, "total_steps": 410, "loss": 0.023, "lr": 8.572959025833573e-05, "epoch": 1.6, "percentage": 32.2, "elapsed_time": "0:27:15", "remaining_time": "0:57:24"}
159
+ {"current_steps": 133, "total_steps": 410, "loss": 0.0253, "lr": 8.543051099966558e-05, "epoch": 1.612121212121212, "percentage": 32.44, "elapsed_time": "0:27:29", "remaining_time": "0:57:15"}
160
+ {"current_steps": 134, "total_steps": 410, "loss": 0.0249, "lr": 8.512886358260162e-05, "epoch": 1.6242424242424243, "percentage": 32.68, "elapsed_time": "0:27:40", "remaining_time": "0:57:00"}
161
+ {"current_steps": 135, "total_steps": 410, "loss": 0.0285, "lr": 8.482466987186785e-05, "epoch": 1.6363636363636362, "percentage": 32.93, "elapsed_time": "0:27:50", "remaining_time": "0:56:43"}
162
+ {"current_steps": 135, "total_steps": 410, "eval_loss": 0.029229959473013878, "epoch": 1.6363636363636362, "percentage": 32.93, "elapsed_time": "0:27:56", "remaining_time": "0:56:55"}
163
+ {"current_steps": 136, "total_steps": 410, "loss": 0.0268, "lr": 8.451795191675488e-05, "epoch": 1.6484848484848484, "percentage": 33.17, "elapsed_time": "0:28:09", "remaining_time": "0:56:42"}
164
+ {"current_steps": 137, "total_steps": 410, "loss": 0.0351, "lr": 8.420873194952152e-05, "epoch": 1.6606060606060606, "percentage": 33.41, "elapsed_time": "0:28:20", "remaining_time": "0:56:27"}
165
+ {"current_steps": 138, "total_steps": 410, "loss": 0.0309, "lr": 8.389703238378339e-05, "epoch": 1.6727272727272728, "percentage": 33.66, "elapsed_time": "0:28:32", "remaining_time": "0:56:14"}
166
+ {"current_steps": 139, "total_steps": 410, "loss": 0.0244, "lr": 8.358287581288822e-05, "epoch": 1.6848484848484848, "percentage": 33.9, "elapsed_time": "0:28:43", "remaining_time": "0:56:00"}
167
+ {"current_steps": 140, "total_steps": 410, "loss": 0.0257, "lr": 8.326628500827826e-05, "epoch": 1.696969696969697, "percentage": 34.15, "elapsed_time": "0:28:53", "remaining_time": "0:55:42"}
168
+ {"current_steps": 140, "total_steps": 410, "eval_loss": 0.02854442596435547, "epoch": 1.696969696969697, "percentage": 34.15, "elapsed_time": "0:28:59", "remaining_time": "0:55:54"}
169
+ {"current_steps": 141, "total_steps": 410, "loss": 0.0301, "lr": 8.294728291783966e-05, "epoch": 1.709090909090909, "percentage": 34.39, "elapsed_time": "0:29:10", "remaining_time": "0:55:39"}
170
+ {"current_steps": 142, "total_steps": 410, "loss": 0.0254, "lr": 8.262589266423908e-05, "epoch": 1.7212121212121212, "percentage": 34.63, "elapsed_time": "0:29:21", "remaining_time": "0:55:24"}
171
+ {"current_steps": 143, "total_steps": 410, "loss": 0.0338, "lr": 8.230213754324773e-05, "epoch": 1.7333333333333334, "percentage": 34.88, "elapsed_time": "0:29:33", "remaining_time": "0:55:11"}
172
+ {"current_steps": 144, "total_steps": 410, "loss": 0.0265, "lr": 8.197604102205271e-05, "epoch": 1.7454545454545456, "percentage": 35.12, "elapsed_time": "0:29:44", "remaining_time": "0:54:55"}
173
+ {"current_steps": 145, "total_steps": 410, "loss": 0.0244, "lr": 8.16476267375561e-05, "epoch": 1.7575757575757576, "percentage": 35.37, "elapsed_time": "0:29:54", "remaining_time": "0:54:39"}
174
+ {"current_steps": 145, "total_steps": 410, "eval_loss": 0.028112677857279778, "epoch": 1.7575757575757576, "percentage": 35.37, "elapsed_time": "0:30:00", "remaining_time": "0:54:50"}
175
+ {"current_steps": 146, "total_steps": 410, "loss": 0.0351, "lr": 8.131691849466153e-05, "epoch": 1.7696969696969695, "percentage": 35.61, "elapsed_time": "0:30:10", "remaining_time": "0:54:33"}
176
+ {"current_steps": 147, "total_steps": 410, "loss": 0.0318, "lr": 8.098394026454885e-05, "epoch": 1.7818181818181817, "percentage": 35.85, "elapsed_time": "0:30:19", "remaining_time": "0:54:15"}
177
+ {"current_steps": 148, "total_steps": 410, "loss": 0.0258, "lr": 8.064871618293646e-05, "epoch": 1.793939393939394, "percentage": 36.1, "elapsed_time": "0:30:31", "remaining_time": "0:54:01"}
178
+ {"current_steps": 149, "total_steps": 410, "loss": 0.0322, "lr": 8.03112705483319e-05, "epoch": 1.8060606060606061, "percentage": 36.34, "elapsed_time": "0:30:41", "remaining_time": "0:53:45"}
179
+ {"current_steps": 150, "total_steps": 410, "loss": 0.0256, "lr": 7.997162782027061e-05, "epoch": 1.8181818181818183, "percentage": 36.59, "elapsed_time": "0:30:52", "remaining_time": "0:53:30"}
180
+ {"current_steps": 150, "total_steps": 410, "eval_loss": 0.027805332094430923, "epoch": 1.8181818181818183, "percentage": 36.59, "elapsed_time": "0:30:58", "remaining_time": "0:53:41"}
181
+ {"current_steps": 151, "total_steps": 410, "loss": 0.0265, "lr": 7.962981261754294e-05, "epoch": 1.8303030303030303, "percentage": 36.83, "elapsed_time": "0:31:16", "remaining_time": "0:53:39"}
182
+ {"current_steps": 152, "total_steps": 410, "loss": 0.0302, "lr": 7.928584971640974e-05, "epoch": 1.8424242424242423, "percentage": 37.07, "elapsed_time": "0:31:28", "remaining_time": "0:53:26"}
183
+ {"current_steps": 153, "total_steps": 410, "loss": 0.0331, "lr": 7.893976404880643e-05, "epoch": 1.8545454545454545, "percentage": 37.32, "elapsed_time": "0:31:39", "remaining_time": "0:53:10"}
184
+ {"current_steps": 154, "total_steps": 410, "loss": 0.0245, "lr": 7.859158070053577e-05, "epoch": 1.8666666666666667, "percentage": 37.56, "elapsed_time": "0:31:50", "remaining_time": "0:52:55"}
185
+ {"current_steps": 155, "total_steps": 410, "loss": 0.0338, "lr": 7.824132490944967e-05, "epoch": 1.878787878787879, "percentage": 37.8, "elapsed_time": "0:32:02", "remaining_time": "0:52:42"}
186
+ {"current_steps": 155, "total_steps": 410, "eval_loss": 0.027029650285840034, "epoch": 1.878787878787879, "percentage": 37.8, "elapsed_time": "0:32:08", "remaining_time": "0:52:52"}
187
+ {"current_steps": 156, "total_steps": 410, "loss": 0.0241, "lr": 7.788902206361973e-05, "epoch": 1.8909090909090909, "percentage": 38.05, "elapsed_time": "0:32:20", "remaining_time": "0:52:38"}
188
+ {"current_steps": 157, "total_steps": 410, "loss": 0.0301, "lr": 7.7534697699497e-05, "epoch": 1.903030303030303, "percentage": 38.29, "elapsed_time": "0:32:29", "remaining_time": "0:52:21"}
189
+ {"current_steps": 158, "total_steps": 410, "loss": 0.0274, "lr": 7.717837750006106e-05, "epoch": 1.915151515151515, "percentage": 38.54, "elapsed_time": "0:32:43", "remaining_time": "0:52:11"}
190
+ {"current_steps": 159, "total_steps": 410, "loss": 0.026, "lr": 7.682008729295833e-05, "epoch": 1.9272727272727272, "percentage": 38.78, "elapsed_time": "0:32:52", "remaining_time": "0:51:53"}
191
+ {"current_steps": 160, "total_steps": 410, "loss": 0.0309, "lr": 7.645985304863003e-05, "epoch": 1.9393939393939394, "percentage": 39.02, "elapsed_time": "0:33:03", "remaining_time": "0:51:38"}
192
+ {"current_steps": 160, "total_steps": 410, "eval_loss": 0.02624826692044735, "epoch": 1.9393939393939394, "percentage": 39.02, "elapsed_time": "0:33:09", "remaining_time": "0:51:48"}
193
+ {"current_steps": 161, "total_steps": 410, "loss": 0.0275, "lr": 7.609770087842969e-05, "epoch": 1.9515151515151516, "percentage": 39.27, "elapsed_time": "0:33:18", "remaining_time": "0:51:30"}
194
+ {"current_steps": 162, "total_steps": 410, "loss": 0.0263, "lr": 7.573365703273046e-05, "epoch": 1.9636363636363636, "percentage": 39.51, "elapsed_time": "0:33:28", "remaining_time": "0:51:15"}
195
+ {"current_steps": 163, "total_steps": 410, "loss": 0.0293, "lr": 7.536774789902246e-05, "epoch": 1.9757575757575756, "percentage": 39.76, "elapsed_time": "0:33:39", "remaining_time": "0:50:59"}
196
+ {"current_steps": 164, "total_steps": 410, "loss": 0.0292, "lr": 7.500000000000001e-05, "epoch": 1.9878787878787878, "percentage": 40.0, "elapsed_time": "0:33:51", "remaining_time": "0:50:46"}
197
+ {"current_steps": 165, "total_steps": 410, "loss": 0.0378, "lr": 7.463043999163919e-05, "epoch": 2.0, "percentage": 40.24, "elapsed_time": "0:34:02", "remaining_time": "0:50:32"}
198
+ {"current_steps": 165, "total_steps": 410, "eval_loss": 0.02608395926654339, "epoch": 2.0, "percentage": 40.24, "elapsed_time": "0:34:08", "remaining_time": "0:50:41"}
199
+ {"current_steps": 166, "total_steps": 410, "loss": 0.024, "lr": 7.425909466126568e-05, "epoch": 2.012121212121212, "percentage": 40.49, "elapsed_time": "0:34:17", "remaining_time": "0:50:23"}
200
+ {"current_steps": 167, "total_steps": 410, "loss": 0.0238, "lr": 7.388599092561315e-05, "epoch": 2.0242424242424244, "percentage": 40.73, "elapsed_time": "0:34:28", "remaining_time": "0:50:10"}
201
+ {"current_steps": 168, "total_steps": 410, "loss": 0.0218, "lr": 7.351115582887211e-05, "epoch": 2.036363636363636, "percentage": 40.98, "elapsed_time": "0:34:38", "remaining_time": "0:49:53"}
202
+ {"current_steps": 169, "total_steps": 410, "loss": 0.0199, "lr": 7.313461654072973e-05, "epoch": 2.0484848484848484, "percentage": 41.22, "elapsed_time": "0:34:50", "remaining_time": "0:49:40"}
203
+ {"current_steps": 170, "total_steps": 410, "loss": 0.0275, "lr": 7.275640035440045e-05, "epoch": 2.0606060606060606, "percentage": 41.46, "elapsed_time": "0:35:01", "remaining_time": "0:49:27"}
204
+ {"current_steps": 170, "total_steps": 410, "eval_loss": 0.026318900287151337, "epoch": 2.0606060606060606, "percentage": 41.46, "elapsed_time": "0:35:07", "remaining_time": "0:49:35"}
205
+ {"current_steps": 171, "total_steps": 410, "loss": 0.0256, "lr": 7.237653468464756e-05, "epoch": 2.0727272727272728, "percentage": 41.71, "elapsed_time": "0:35:20", "remaining_time": "0:49:23"}
206
+ {"current_steps": 172, "total_steps": 410, "loss": 0.0226, "lr": 7.199504706579617e-05, "epoch": 2.084848484848485, "percentage": 41.95, "elapsed_time": "0:35:32", "remaining_time": "0:49:10"}
207
+ {"current_steps": 173, "total_steps": 410, "loss": 0.0188, "lr": 7.161196514973734e-05, "epoch": 2.096969696969697, "percentage": 42.2, "elapsed_time": "0:35:43", "remaining_time": "0:48:55"}
208
+ {"current_steps": 174, "total_steps": 410, "loss": 0.0232, "lr": 7.12273167039238e-05, "epoch": 2.109090909090909, "percentage": 42.44, "elapsed_time": "0:35:53", "remaining_time": "0:48:40"}
209
+ {"current_steps": 175, "total_steps": 410, "loss": 0.0225, "lr": 7.084112960935716e-05, "epoch": 2.121212121212121, "percentage": 42.68, "elapsed_time": "0:36:02", "remaining_time": "0:48:24"}
210
+ {"current_steps": 175, "total_steps": 410, "eval_loss": 0.025883661583065987, "epoch": 2.121212121212121, "percentage": 42.68, "elapsed_time": "0:36:09", "remaining_time": "0:48:32"}
211
+ {"current_steps": 176, "total_steps": 410, "loss": 0.0248, "lr": 7.045343185856701e-05, "epoch": 2.1333333333333333, "percentage": 42.93, "elapsed_time": "0:36:20", "remaining_time": "0:48:19"}
212
+ {"current_steps": 177, "total_steps": 410, "loss": 0.0244, "lr": 7.006425155358195e-05, "epoch": 2.1454545454545455, "percentage": 43.17, "elapsed_time": "0:36:32", "remaining_time": "0:48:06"}
213
+ {"current_steps": 178, "total_steps": 410, "loss": 0.0242, "lr": 6.967361690389258e-05, "epoch": 2.1575757575757577, "percentage": 43.41, "elapsed_time": "0:36:43", "remaining_time": "0:47:51"}
214
+ {"current_steps": 179, "total_steps": 410, "loss": 0.0246, "lr": 6.92815562244068e-05, "epoch": 2.16969696969697, "percentage": 43.66, "elapsed_time": "0:36:55", "remaining_time": "0:47:38"}
215
+ {"current_steps": 180, "total_steps": 410, "loss": 0.0232, "lr": 6.88880979333973e-05, "epoch": 2.1818181818181817, "percentage": 43.9, "elapsed_time": "0:37:04", "remaining_time": "0:47:22"}
216
+ {"current_steps": 180, "total_steps": 410, "eval_loss": 0.025616060942411423, "epoch": 2.1818181818181817, "percentage": 43.9, "elapsed_time": "0:37:10", "remaining_time": "0:47:30"}
217
+ {"current_steps": 181, "total_steps": 410, "loss": 0.0251, "lr": 6.849327055044183e-05, "epoch": 2.193939393939394, "percentage": 44.15, "elapsed_time": "0:37:22", "remaining_time": "0:47:17"}
218
+ {"current_steps": 182, "total_steps": 410, "loss": 0.022, "lr": 6.809710269435589e-05, "epoch": 2.206060606060606, "percentage": 44.39, "elapsed_time": "0:37:34", "remaining_time": "0:47:04"}
219
+ {"current_steps": 183, "total_steps": 410, "loss": 0.0234, "lr": 6.769962308111839e-05, "epoch": 2.2181818181818183, "percentage": 44.63, "elapsed_time": "0:37:44", "remaining_time": "0:46:49"}
220
+ {"current_steps": 184, "total_steps": 410, "loss": 0.0221, "lr": 6.730086052179004e-05, "epoch": 2.2303030303030305, "percentage": 44.88, "elapsed_time": "0:37:57", "remaining_time": "0:46:37"}
221
+ {"current_steps": 185, "total_steps": 410, "loss": 0.0193, "lr": 6.690084392042513e-05, "epoch": 2.242424242424242, "percentage": 45.12, "elapsed_time": "0:38:08", "remaining_time": "0:46:23"}
222
+ {"current_steps": 185, "total_steps": 410, "eval_loss": 0.025547849014401436, "epoch": 2.242424242424242, "percentage": 45.12, "elapsed_time": "0:38:14", "remaining_time": "0:46:30"}
223
+ {"current_steps": 186, "total_steps": 410, "loss": 0.0217, "lr": 6.649960227197647e-05, "epoch": 2.2545454545454544, "percentage": 45.37, "elapsed_time": "0:38:26", "remaining_time": "0:46:18"}
224
+ {"current_steps": 187, "total_steps": 410, "loss": 0.0239, "lr": 6.609716466019356e-05, "epoch": 2.2666666666666666, "percentage": 45.61, "elapsed_time": "0:38:36", "remaining_time": "0:46:02"}
225
+ {"current_steps": 188, "total_steps": 410, "loss": 0.0232, "lr": 6.569356025551454e-05, "epoch": 2.278787878787879, "percentage": 45.85, "elapsed_time": "0:38:47", "remaining_time": "0:45:48"}
226
+ {"current_steps": 189, "total_steps": 410, "loss": 0.02, "lr": 6.528881831295188e-05, "epoch": 2.290909090909091, "percentage": 46.1, "elapsed_time": "0:38:56", "remaining_time": "0:45:31"}
227
+ {"current_steps": 190, "total_steps": 410, "loss": 0.0251, "lr": 6.488296816997173e-05, "epoch": 2.303030303030303, "percentage": 46.34, "elapsed_time": "0:39:06", "remaining_time": "0:45:17"}
228
+ {"current_steps": 190, "total_steps": 410, "eval_loss": 0.02527759224176407, "epoch": 2.303030303030303, "percentage": 46.34, "elapsed_time": "0:39:12", "remaining_time": "0:45:24"}
229
+ {"current_steps": 191, "total_steps": 410, "loss": 0.0243, "lr": 6.447603924436744e-05, "epoch": 2.315151515151515, "percentage": 46.59, "elapsed_time": "0:39:24", "remaining_time": "0:45:10"}
230
+ {"current_steps": 192, "total_steps": 410, "loss": 0.0204, "lr": 6.406806103212725e-05, "epoch": 2.327272727272727, "percentage": 46.83, "elapsed_time": "0:39:36", "remaining_time": "0:44:58"}
231
+ {"current_steps": 193, "total_steps": 410, "loss": 0.0232, "lr": 6.36590631052963e-05, "epoch": 2.3393939393939394, "percentage": 47.07, "elapsed_time": "0:39:45", "remaining_time": "0:44:42"}
232
+ {"current_steps": 194, "total_steps": 410, "loss": 0.0324, "lr": 6.32490751098331e-05, "epoch": 2.3515151515151516, "percentage": 47.32, "elapsed_time": "0:39:55", "remaining_time": "0:44:26"}
233
+ {"current_steps": 195, "total_steps": 410, "loss": 0.0228, "lr": 6.283812676346063e-05, "epoch": 2.3636363636363638, "percentage": 47.56, "elapsed_time": "0:40:07", "remaining_time": "0:44:14"}
234
+ {"current_steps": 195, "total_steps": 410, "eval_loss": 0.024870626628398895, "epoch": 2.3636363636363638, "percentage": 47.56, "elapsed_time": "0:40:13", "remaining_time": "0:44:20"}
235
+ {"current_steps": 196, "total_steps": 410, "loss": 0.0231, "lr": 6.242624785351236e-05, "epoch": 2.375757575757576, "percentage": 47.8, "elapsed_time": "0:40:24", "remaining_time": "0:44:06"}
236
+ {"current_steps": 197, "total_steps": 410, "loss": 0.0193, "lr": 6.201346823477303e-05, "epoch": 2.3878787878787877, "percentage": 48.05, "elapsed_time": "0:40:36", "remaining_time": "0:43:54"}
237
+ {"current_steps": 198, "total_steps": 410, "loss": 0.0227, "lr": 6.159981782731474e-05, "epoch": 2.4, "percentage": 48.29, "elapsed_time": "0:40:49", "remaining_time": "0:43:42"}
238
+ {"current_steps": 199, "total_steps": 410, "loss": 0.0224, "lr": 6.118532661432812e-05, "epoch": 2.412121212121212, "percentage": 48.54, "elapsed_time": "0:41:00", "remaining_time": "0:43:28"}
239
+ {"current_steps": 200, "total_steps": 410, "loss": 0.0195, "lr": 6.0770024639949074e-05, "epoch": 2.4242424242424243, "percentage": 48.78, "elapsed_time": "0:41:09", "remaining_time": "0:43:12"}
240
+ {"current_steps": 200, "total_steps": 410, "eval_loss": 0.024939175695180893, "epoch": 2.4242424242424243, "percentage": 48.78, "elapsed_time": "0:41:15", "remaining_time": "0:43:19"}
241
+ {"current_steps": 201, "total_steps": 410, "loss": 0.0198, "lr": 6.0353942007081046e-05, "epoch": 2.4363636363636365, "percentage": 49.02, "elapsed_time": "0:41:34", "remaining_time": "0:43:13"}
242
+ {"current_steps": 202, "total_steps": 410, "loss": 0.0184, "lr": 5.993710887521302e-05, "epoch": 2.4484848484848483, "percentage": 49.27, "elapsed_time": "0:41:46", "remaining_time": "0:43:01"}
243
+ {"current_steps": 203, "total_steps": 410, "loss": 0.0207, "lr": 5.951955545823342e-05, "epoch": 2.4606060606060605, "percentage": 49.51, "elapsed_time": "0:41:57", "remaining_time": "0:42:47"}
244
+ {"current_steps": 204, "total_steps": 410, "loss": 0.0217, "lr": 5.9101312022240106e-05, "epoch": 2.4727272727272727, "percentage": 49.76, "elapsed_time": "0:42:09", "remaining_time": "0:42:34"}
245
+ {"current_steps": 205, "total_steps": 410, "loss": 0.0219, "lr": 5.868240888334653e-05, "epoch": 2.484848484848485, "percentage": 50.0, "elapsed_time": "0:42:18", "remaining_time": "0:42:18"}
246
+ {"current_steps": 205, "total_steps": 410, "eval_loss": 0.024136777967214584, "epoch": 2.484848484848485, "percentage": 50.0, "elapsed_time": "0:42:25", "remaining_time": "0:42:25"}
247
+ {"current_steps": 206, "total_steps": 410, "loss": 0.0231, "lr": 5.826287640548425e-05, "epoch": 2.496969696969697, "percentage": 50.24, "elapsed_time": "0:42:36", "remaining_time": "0:42:11"}
248
+ {"current_steps": 207, "total_steps": 410, "loss": 0.0243, "lr": 5.784274499820214e-05, "epoch": 2.509090909090909, "percentage": 50.49, "elapsed_time": "0:42:45", "remaining_time": "0:41:55"}
249
+ {"current_steps": 208, "total_steps": 410, "loss": 0.0241, "lr": 5.742204511446203e-05, "epoch": 2.5212121212121215, "percentage": 50.73, "elapsed_time": "0:42:54", "remaining_time": "0:41:40"}
250
+ {"current_steps": 209, "total_steps": 410, "loss": 0.0217, "lr": 5.700080724843147e-05, "epoch": 2.533333333333333, "percentage": 50.98, "elapsed_time": "0:43:05", "remaining_time": "0:41:26"}
251
+ {"current_steps": 210, "total_steps": 410, "loss": 0.0184, "lr": 5.657906193327325e-05, "epoch": 2.5454545454545454, "percentage": 51.22, "elapsed_time": "0:43:16", "remaining_time": "0:41:12"}
252
+ {"current_steps": 210, "total_steps": 410, "eval_loss": 0.023839673027396202, "epoch": 2.5454545454545454, "percentage": 51.22, "elapsed_time": "0:43:22", "remaining_time": "0:41:18"}
253
+ {"current_steps": 211, "total_steps": 410, "loss": 0.0233, "lr": 5.6156839738932343e-05, "epoch": 2.5575757575757576, "percentage": 51.46, "elapsed_time": "0:43:31", "remaining_time": "0:41:03"}
254
+ {"current_steps": 212, "total_steps": 410, "loss": 0.0419, "lr": 5.573417126992003e-05, "epoch": 2.56969696969697, "percentage": 51.71, "elapsed_time": "0:43:43", "remaining_time": "0:40:50"}
255
+ {"current_steps": 213, "total_steps": 410, "loss": 0.0208, "lr": 5.531108716309547e-05, "epoch": 2.581818181818182, "percentage": 51.95, "elapsed_time": "0:43:52", "remaining_time": "0:40:35"}
256
+ {"current_steps": 214, "total_steps": 410, "loss": 0.0356, "lr": 5.4887618085445094e-05, "epoch": 2.5939393939393938, "percentage": 52.2, "elapsed_time": "0:44:02", "remaining_time": "0:40:20"}
257
+ {"current_steps": 215, "total_steps": 410, "loss": 0.0199, "lr": 5.446379473185972e-05, "epoch": 2.606060606060606, "percentage": 52.44, "elapsed_time": "0:44:14", "remaining_time": "0:40:07"}
258
+ {"current_steps": 215, "total_steps": 410, "eval_loss": 0.023647097870707512, "epoch": 2.606060606060606, "percentage": 52.44, "elapsed_time": "0:44:20", "remaining_time": "0:40:13"}
259
+ {"current_steps": 216, "total_steps": 410, "loss": 0.0185, "lr": 5.4039647822909624e-05, "epoch": 2.618181818181818, "percentage": 52.68, "elapsed_time": "0:44:32", "remaining_time": "0:40:00"}
260
+ {"current_steps": 217, "total_steps": 410, "loss": 0.0212, "lr": 5.361520810261779e-05, "epoch": 2.6303030303030304, "percentage": 52.93, "elapsed_time": "0:44:43", "remaining_time": "0:39:46"}
261
+ {"current_steps": 218, "total_steps": 410, "loss": 0.0208, "lr": 5.319050633623142e-05, "epoch": 2.6424242424242426, "percentage": 53.17, "elapsed_time": "0:44:54", "remaining_time": "0:39:32"}
262
+ {"current_steps": 219, "total_steps": 410, "loss": 0.0343, "lr": 5.2765573307992036e-05, "epoch": 2.6545454545454543, "percentage": 53.41, "elapsed_time": "0:45:05", "remaining_time": "0:39:19"}
263
+ {"current_steps": 220, "total_steps": 410, "loss": 0.023, "lr": 5.234043981890394e-05, "epoch": 2.6666666666666665, "percentage": 53.66, "elapsed_time": "0:45:14", "remaining_time": "0:39:04"}
264
+ {"current_steps": 220, "total_steps": 410, "eval_loss": 0.02315612882375717, "epoch": 2.6666666666666665, "percentage": 53.66, "elapsed_time": "0:45:21", "remaining_time": "0:39:10"}
265
+ {"current_steps": 221, "total_steps": 410, "loss": 0.0208, "lr": 5.191513668450178e-05, "epoch": 2.6787878787878787, "percentage": 53.9, "elapsed_time": "0:45:33", "remaining_time": "0:38:57"}
266
+ {"current_steps": 222, "total_steps": 410, "loss": 0.0178, "lr": 5.14896947326168e-05, "epoch": 2.690909090909091, "percentage": 54.15, "elapsed_time": "0:45:46", "remaining_time": "0:38:45"}
267
+ {"current_steps": 223, "total_steps": 410, "loss": 0.019, "lr": 5.1064144801142374e-05, "epoch": 2.703030303030303, "percentage": 54.39, "elapsed_time": "0:45:56", "remaining_time": "0:38:31"}
268
+ {"current_steps": 224, "total_steps": 410, "loss": 0.0184, "lr": 5.0638517735798696e-05, "epoch": 2.7151515151515153, "percentage": 54.63, "elapsed_time": "0:46:09", "remaining_time": "0:38:19"}
269
+ {"current_steps": 225, "total_steps": 410, "loss": 0.0227, "lr": 5.021284438789694e-05, "epoch": 2.7272727272727275, "percentage": 54.88, "elapsed_time": "0:46:18", "remaining_time": "0:38:04"}
270
+ {"current_steps": 225, "total_steps": 410, "eval_loss": 0.023449590429663658, "epoch": 2.7272727272727275, "percentage": 54.88, "elapsed_time": "0:46:25", "remaining_time": "0:38:10"}
271
+ {"current_steps": 226, "total_steps": 410, "loss": 0.0205, "lr": 4.9787155612103074e-05, "epoch": 2.7393939393939393, "percentage": 55.12, "elapsed_time": "0:46:36", "remaining_time": "0:37:56"}
272
+ {"current_steps": 227, "total_steps": 410, "loss": 0.0171, "lr": 4.936148226420132e-05, "epoch": 2.7515151515151515, "percentage": 55.37, "elapsed_time": "0:46:47", "remaining_time": "0:37:43"}
273
+ {"current_steps": 228, "total_steps": 410, "loss": 0.0197, "lr": 4.893585519885764e-05, "epoch": 2.7636363636363637, "percentage": 55.61, "elapsed_time": "0:47:01", "remaining_time": "0:37:32"}
274
+ {"current_steps": 229, "total_steps": 410, "loss": 0.0204, "lr": 4.851030526738321e-05, "epoch": 2.775757575757576, "percentage": 55.85, "elapsed_time": "0:47:12", "remaining_time": "0:37:18"}
275
+ {"current_steps": 230, "total_steps": 410, "loss": 0.0206, "lr": 4.8084863315498234e-05, "epoch": 2.787878787878788, "percentage": 56.1, "elapsed_time": "0:47:22", "remaining_time": "0:37:04"}
276
+ {"current_steps": 230, "total_steps": 410, "eval_loss": 0.022967081516981125, "epoch": 2.787878787878788, "percentage": 56.1, "elapsed_time": "0:47:28", "remaining_time": "0:37:09"}
277
+ {"current_steps": 231, "total_steps": 410, "loss": 0.0197, "lr": 4.765956018109607e-05, "epoch": 2.8, "percentage": 56.34, "elapsed_time": "0:47:40", "remaining_time": "0:36:56"}
278
+ {"current_steps": 232, "total_steps": 410, "loss": 0.0213, "lr": 4.723442669200798e-05, "epoch": 2.812121212121212, "percentage": 56.59, "elapsed_time": "0:47:52", "remaining_time": "0:36:43"}
279
+ {"current_steps": 233, "total_steps": 410, "loss": 0.0237, "lr": 4.680949366376858e-05, "epoch": 2.824242424242424, "percentage": 56.83, "elapsed_time": "0:48:03", "remaining_time": "0:36:30"}
280
+ {"current_steps": 234, "total_steps": 410, "loss": 0.0235, "lr": 4.638479189738224e-05, "epoch": 2.8363636363636364, "percentage": 57.07, "elapsed_time": "0:48:15", "remaining_time": "0:36:18"}
281
+ {"current_steps": 235, "total_steps": 410, "loss": 0.0217, "lr": 4.5960352177090395e-05, "epoch": 2.8484848484848486, "percentage": 57.32, "elapsed_time": "0:48:25", "remaining_time": "0:36:03"}
282
+ {"current_steps": 235, "total_steps": 410, "eval_loss": 0.022518714889883995, "epoch": 2.8484848484848486, "percentage": 57.32, "elapsed_time": "0:48:31", "remaining_time": "0:36:08"}
283
+ {"current_steps": 236, "total_steps": 410, "loss": 0.0189, "lr": 4.5536205268140294e-05, "epoch": 2.8606060606060604, "percentage": 57.56, "elapsed_time": "0:48:42", "remaining_time": "0:35:54"}
284
+ {"current_steps": 237, "total_steps": 410, "loss": 0.0166, "lr": 4.511238191455491e-05, "epoch": 2.8727272727272726, "percentage": 57.8, "elapsed_time": "0:48:53", "remaining_time": "0:35:41"}
285
+ {"current_steps": 238, "total_steps": 410, "loss": 0.0183, "lr": 4.468891283690454e-05, "epoch": 2.8848484848484848, "percentage": 58.05, "elapsed_time": "0:49:04", "remaining_time": "0:35:27"}
286
+ {"current_steps": 239, "total_steps": 410, "loss": 0.0221, "lr": 4.4265828730079987e-05, "epoch": 2.896969696969697, "percentage": 58.29, "elapsed_time": "0:49:14", "remaining_time": "0:35:14"}
287
+ {"current_steps": 240, "total_steps": 410, "loss": 0.0186, "lr": 4.3843160261067655e-05, "epoch": 2.909090909090909, "percentage": 58.54, "elapsed_time": "0:49:26", "remaining_time": "0:35:00"}
288
+ {"current_steps": 240, "total_steps": 410, "eval_loss": 0.022352781146764755, "epoch": 2.909090909090909, "percentage": 58.54, "elapsed_time": "0:49:32", "remaining_time": "0:35:05"}
289
+ {"current_steps": 241, "total_steps": 410, "loss": 0.0181, "lr": 4.342093806672678e-05, "epoch": 2.9212121212121214, "percentage": 58.78, "elapsed_time": "0:49:43", "remaining_time": "0:34:52"}
290
+ {"current_steps": 242, "total_steps": 410, "loss": 0.0203, "lr": 4.2999192751568564e-05, "epoch": 2.9333333333333336, "percentage": 59.02, "elapsed_time": "0:49:52", "remaining_time": "0:34:37"}
291
+ {"current_steps": 243, "total_steps": 410, "loss": 0.0181, "lr": 4.2577954885537986e-05, "epoch": 2.9454545454545453, "percentage": 59.27, "elapsed_time": "0:50:04", "remaining_time": "0:34:25"}
292
+ {"current_steps": 244, "total_steps": 410, "loss": 0.0191, "lr": 4.215725500179787e-05, "epoch": 2.9575757575757575, "percentage": 59.51, "elapsed_time": "0:50:14", "remaining_time": "0:34:11"}
293
+ {"current_steps": 245, "total_steps": 410, "loss": 0.0201, "lr": 4.1737123594515756e-05, "epoch": 2.9696969696969697, "percentage": 59.76, "elapsed_time": "0:50:23", "remaining_time": "0:33:56"}
294
+ {"current_steps": 245, "total_steps": 410, "eval_loss": 0.02198323793709278, "epoch": 2.9696969696969697, "percentage": 59.76, "elapsed_time": "0:50:30", "remaining_time": "0:34:00"}
295
+ {"current_steps": 246, "total_steps": 410, "loss": 0.0191, "lr": 4.131759111665349e-05, "epoch": 2.981818181818182, "percentage": 60.0, "elapsed_time": "0:50:41", "remaining_time": "0:33:47"}
296
+ {"current_steps": 247, "total_steps": 410, "loss": 0.0185, "lr": 4.089868797775989e-05, "epoch": 2.993939393939394, "percentage": 60.24, "elapsed_time": "0:50:50", "remaining_time": "0:33:33"}
297
+ {"current_steps": 248, "total_steps": 410, "loss": 0.0301, "lr": 4.0480444541766576e-05, "epoch": 3.006060606060606, "percentage": 60.49, "elapsed_time": "0:50:59", "remaining_time": "0:33:18"}
298
+ {"current_steps": 249, "total_steps": 410, "loss": 0.0188, "lr": 4.0062891124787e-05, "epoch": 3.018181818181818, "percentage": 60.73, "elapsed_time": "0:51:11", "remaining_time": "0:33:06"}
299
+ {"current_steps": 250, "total_steps": 410, "loss": 0.0147, "lr": 3.964605799291897e-05, "epoch": 3.0303030303030303, "percentage": 60.98, "elapsed_time": "0:51:22", "remaining_time": "0:32:52"}
300
+ {"current_steps": 250, "total_steps": 410, "eval_loss": 0.021969465538859367, "epoch": 3.0303030303030303, "percentage": 60.98, "elapsed_time": "0:51:28", "remaining_time": "0:32:56"}
301
+ {"current_steps": 251, "total_steps": 410, "loss": 0.0178, "lr": 3.922997536005094e-05, "epoch": 3.0424242424242425, "percentage": 61.22, "elapsed_time": "0:51:47", "remaining_time": "0:32:48"}
302
+ {"current_steps": 252, "total_steps": 410, "loss": 0.0157, "lr": 3.8814673385671894e-05, "epoch": 3.0545454545454547, "percentage": 61.46, "elapsed_time": "0:51:58", "remaining_time": "0:32:35"}
303
+ {"current_steps": 253, "total_steps": 410, "loss": 0.0161, "lr": 3.840018217268527e-05, "epoch": 3.066666666666667, "percentage": 61.71, "elapsed_time": "0:52:06", "remaining_time": "0:32:20"}
304
+ {"current_steps": 254, "total_steps": 410, "loss": 0.0161, "lr": 3.7986531765226964e-05, "epoch": 3.0787878787878786, "percentage": 61.95, "elapsed_time": "0:52:18", "remaining_time": "0:32:07"}
305
+ {"current_steps": 255, "total_steps": 410, "loss": 0.0142, "lr": 3.757375214648764e-05, "epoch": 3.090909090909091, "percentage": 62.2, "elapsed_time": "0:52:29", "remaining_time": "0:31:54"}
306
+ {"current_steps": 255, "total_steps": 410, "eval_loss": 0.022621195763349533, "epoch": 3.090909090909091, "percentage": 62.2, "elapsed_time": "0:52:36", "remaining_time": "0:31:58"}
307
+ {"current_steps": 256, "total_steps": 410, "loss": 0.0167, "lr": 3.716187323653939e-05, "epoch": 3.103030303030303, "percentage": 62.44, "elapsed_time": "0:52:46", "remaining_time": "0:31:44"}
308
+ {"current_steps": 257, "total_steps": 410, "loss": 0.0168, "lr": 3.675092489016693e-05, "epoch": 3.1151515151515152, "percentage": 62.68, "elapsed_time": "0:52:55", "remaining_time": "0:31:30"}
309
+ {"current_steps": 258, "total_steps": 410, "loss": 0.017, "lr": 3.634093689470371e-05, "epoch": 3.1272727272727274, "percentage": 62.93, "elapsed_time": "0:53:06", "remaining_time": "0:31:17"}
310
+ {"current_steps": 259, "total_steps": 410, "loss": 0.016, "lr": 3.5931938967872766e-05, "epoch": 3.1393939393939396, "percentage": 63.17, "elapsed_time": "0:53:15", "remaining_time": "0:31:03"}
311
+ {"current_steps": 260, "total_steps": 410, "loss": 0.0149, "lr": 3.5523960755632574e-05, "epoch": 3.1515151515151514, "percentage": 63.41, "elapsed_time": "0:53:26", "remaining_time": "0:30:49"}
312
+ {"current_steps": 260, "total_steps": 410, "eval_loss": 0.021824924275279045, "epoch": 3.1515151515151514, "percentage": 63.41, "elapsed_time": "0:53:32", "remaining_time": "0:30:53"}
313
+ {"current_steps": 261, "total_steps": 410, "loss": 0.0127, "lr": 3.5117031830028274e-05, "epoch": 3.1636363636363636, "percentage": 63.66, "elapsed_time": "0:53:45", "remaining_time": "0:30:41"}
314
+ {"current_steps": 262, "total_steps": 410, "loss": 0.015, "lr": 3.471118168704811e-05, "epoch": 3.175757575757576, "percentage": 63.9, "elapsed_time": "0:53:56", "remaining_time": "0:30:28"}
315
+ {"current_steps": 263, "total_steps": 410, "loss": 0.0154, "lr": 3.4306439744485454e-05, "epoch": 3.187878787878788, "percentage": 64.15, "elapsed_time": "0:54:08", "remaining_time": "0:30:15"}
316
+ {"current_steps": 264, "total_steps": 410, "loss": 0.0167, "lr": 3.390283533980646e-05, "epoch": 3.2, "percentage": 64.39, "elapsed_time": "0:54:19", "remaining_time": "0:30:02"}
317
+ {"current_steps": 265, "total_steps": 410, "loss": 0.0151, "lr": 3.350039772802354e-05, "epoch": 3.212121212121212, "percentage": 64.63, "elapsed_time": "0:54:32", "remaining_time": "0:29:50"}
318
+ {"current_steps": 265, "total_steps": 410, "eval_loss": 0.02153392694890499, "epoch": 3.212121212121212, "percentage": 64.63, "elapsed_time": "0:54:38", "remaining_time": "0:29:53"}
319
+ {"current_steps": 266, "total_steps": 410, "loss": 0.0171, "lr": 3.309915607957487e-05, "epoch": 3.224242424242424, "percentage": 64.88, "elapsed_time": "0:54:48", "remaining_time": "0:29:40"}
320
+ {"current_steps": 267, "total_steps": 410, "loss": 0.0158, "lr": 3.269913947820998e-05, "epoch": 3.2363636363636363, "percentage": 65.12, "elapsed_time": "0:54:58", "remaining_time": "0:29:26"}
321
+ {"current_steps": 268, "total_steps": 410, "loss": 0.0156, "lr": 3.2300376918881624e-05, "epoch": 3.2484848484848485, "percentage": 65.37, "elapsed_time": "0:55:10", "remaining_time": "0:29:13"}
322
+ {"current_steps": 269, "total_steps": 410, "loss": 0.0134, "lr": 3.1902897305644095e-05, "epoch": 3.2606060606060607, "percentage": 65.61, "elapsed_time": "0:55:19", "remaining_time": "0:29:00"}
323
+ {"current_steps": 270, "total_steps": 410, "loss": 0.0174, "lr": 3.1506729449558184e-05, "epoch": 3.2727272727272725, "percentage": 65.85, "elapsed_time": "0:55:30", "remaining_time": "0:28:46"}
324
+ {"current_steps": 270, "total_steps": 410, "eval_loss": 0.021679332479834557, "epoch": 3.2727272727272725, "percentage": 65.85, "elapsed_time": "0:55:36", "remaining_time": "0:28:50"}
325
+ {"current_steps": 271, "total_steps": 410, "loss": 0.018, "lr": 3.1111902066602724e-05, "epoch": 3.2848484848484847, "percentage": 66.1, "elapsed_time": "0:55:49", "remaining_time": "0:28:37"}
326
+ {"current_steps": 272, "total_steps": 410, "loss": 0.016, "lr": 3.071844377559323e-05, "epoch": 3.296969696969697, "percentage": 66.34, "elapsed_time": "0:55:59", "remaining_time": "0:28:24"}
327
+ {"current_steps": 273, "total_steps": 410, "loss": 0.014, "lr": 3.0326383096107426e-05, "epoch": 3.309090909090909, "percentage": 66.59, "elapsed_time": "0:56:08", "remaining_time": "0:28:10"}
328
+ {"current_steps": 274, "total_steps": 410, "loss": 0.0169, "lr": 2.9935748446418066e-05, "epoch": 3.3212121212121213, "percentage": 66.83, "elapsed_time": "0:56:21", "remaining_time": "0:27:58"}
329
+ {"current_steps": 275, "total_steps": 410, "loss": 0.0172, "lr": 2.9546568141433006e-05, "epoch": 3.3333333333333335, "percentage": 67.07, "elapsed_time": "0:56:33", "remaining_time": "0:27:45"}
330
+ {"current_steps": 275, "total_steps": 410, "eval_loss": 0.021324800327420235, "epoch": 3.3333333333333335, "percentage": 67.07, "elapsed_time": "0:56:39", "remaining_time": "0:27:48"}
331
+ {"current_steps": 276, "total_steps": 410, "loss": 0.0141, "lr": 2.915887039064287e-05, "epoch": 3.3454545454545457, "percentage": 67.32, "elapsed_time": "0:56:51", "remaining_time": "0:27:36"}
332
+ {"current_steps": 277, "total_steps": 410, "loss": 0.0126, "lr": 2.8772683296076196e-05, "epoch": 3.3575757575757574, "percentage": 67.56, "elapsed_time": "0:57:01", "remaining_time": "0:27:22"}
333
+ {"current_steps": 278, "total_steps": 410, "loss": 0.0376, "lr": 2.8388034850262646e-05, "epoch": 3.3696969696969696, "percentage": 67.8, "elapsed_time": "0:57:14", "remaining_time": "0:27:10"}
334
+ {"current_steps": 279, "total_steps": 410, "loss": 0.017, "lr": 2.8004952934203838e-05, "epoch": 3.381818181818182, "percentage": 68.05, "elapsed_time": "0:57:26", "remaining_time": "0:26:58"}
335
+ {"current_steps": 280, "total_steps": 410, "loss": 0.017, "lr": 2.762346531535246e-05, "epoch": 3.393939393939394, "percentage": 68.29, "elapsed_time": "0:57:38", "remaining_time": "0:26:45"}
336
+ {"current_steps": 280, "total_steps": 410, "eval_loss": 0.02108747698366642, "epoch": 3.393939393939394, "percentage": 68.29, "elapsed_time": "0:57:44", "remaining_time": "0:26:48"}
337
+ {"current_steps": 281, "total_steps": 410, "loss": 0.014, "lr": 2.7243599645599576e-05, "epoch": 3.4060606060606062, "percentage": 68.54, "elapsed_time": "0:57:59", "remaining_time": "0:26:37"}
338
+ {"current_steps": 282, "total_steps": 410, "loss": 0.0158, "lr": 2.6865383459270265e-05, "epoch": 3.418181818181818, "percentage": 68.78, "elapsed_time": "0:58:11", "remaining_time": "0:26:24"}
339
+ {"current_steps": 283, "total_steps": 410, "loss": 0.017, "lr": 2.6488844171127903e-05, "epoch": 3.43030303030303, "percentage": 69.02, "elapsed_time": "0:58:23", "remaining_time": "0:26:12"}
340
+ {"current_steps": 284, "total_steps": 410, "loss": 0.0124, "lr": 2.6114009074386846e-05, "epoch": 3.4424242424242424, "percentage": 69.27, "elapsed_time": "0:58:33", "remaining_time": "0:25:58"}
341
+ {"current_steps": 285, "total_steps": 410, "loss": 0.0223, "lr": 2.574090533873431e-05, "epoch": 3.4545454545454546, "percentage": 69.51, "elapsed_time": "0:58:44", "remaining_time": "0:25:46"}
342
+ {"current_steps": 285, "total_steps": 410, "eval_loss": 0.021236957982182503, "epoch": 3.4545454545454546, "percentage": 69.51, "elapsed_time": "0:58:51", "remaining_time": "0:25:48"}
343
+ {"current_steps": 286, "total_steps": 410, "loss": 0.0132, "lr": 2.5369560008360828e-05, "epoch": 3.466666666666667, "percentage": 69.76, "elapsed_time": "0:59:00", "remaining_time": "0:25:35"}
344
+ {"current_steps": 287, "total_steps": 410, "loss": 0.0132, "lr": 2.500000000000001e-05, "epoch": 3.4787878787878785, "percentage": 70.0, "elapsed_time": "0:59:11", "remaining_time": "0:25:22"}
345
+ {"current_steps": 288, "total_steps": 410, "loss": 0.0136, "lr": 2.4632252100977566e-05, "epoch": 3.4909090909090907, "percentage": 70.24, "elapsed_time": "0:59:24", "remaining_time": "0:25:09"}
346
+ {"current_steps": 289, "total_steps": 410, "loss": 0.0157, "lr": 2.4266342967269552e-05, "epoch": 3.503030303030303, "percentage": 70.49, "elapsed_time": "0:59:36", "remaining_time": "0:24:57"}
347
+ {"current_steps": 290, "total_steps": 410, "loss": 0.0144, "lr": 2.3902299121570333e-05, "epoch": 3.515151515151515, "percentage": 70.73, "elapsed_time": "0:59:45", "remaining_time": "0:24:43"}
348
+ {"current_steps": 290, "total_steps": 410, "eval_loss": 0.02107882872223854, "epoch": 3.515151515151515, "percentage": 70.73, "elapsed_time": "0:59:52", "remaining_time": "0:24:46"}
349
+ {"current_steps": 291, "total_steps": 410, "loss": 0.0131, "lr": 2.354014695136997e-05, "epoch": 3.5272727272727273, "percentage": 70.98, "elapsed_time": "1:00:05", "remaining_time": "0:24:34"}
350
+ {"current_steps": 292, "total_steps": 410, "loss": 0.0151, "lr": 2.317991270704167e-05, "epoch": 3.5393939393939395, "percentage": 71.22, "elapsed_time": "1:00:15", "remaining_time": "0:24:21"}
351
+ {"current_steps": 293, "total_steps": 410, "loss": 0.0125, "lr": 2.282162249993895e-05, "epoch": 3.5515151515151517, "percentage": 71.46, "elapsed_time": "1:00:25", "remaining_time": "0:24:07"}
352
+ {"current_steps": 294, "total_steps": 410, "loss": 0.0162, "lr": 2.246530230050301e-05, "epoch": 3.5636363636363635, "percentage": 71.71, "elapsed_time": "1:00:35", "remaining_time": "0:23:54"}
353
+ {"current_steps": 295, "total_steps": 410, "loss": 0.0125, "lr": 2.211097793638029e-05, "epoch": 3.5757575757575757, "percentage": 71.95, "elapsed_time": "1:00:44", "remaining_time": "0:23:40"}
354
+ {"current_steps": 295, "total_steps": 410, "eval_loss": 0.020796656608581543, "epoch": 3.5757575757575757, "percentage": 71.95, "elapsed_time": "1:00:50", "remaining_time": "0:23:43"}
355
+ {"current_steps": 296, "total_steps": 410, "loss": 0.0111, "lr": 2.175867509055033e-05, "epoch": 3.587878787878788, "percentage": 72.2, "elapsed_time": "1:01:01", "remaining_time": "0:23:30"}
356
+ {"current_steps": 297, "total_steps": 410, "loss": 0.0165, "lr": 2.1408419299464245e-05, "epoch": 3.6, "percentage": 72.44, "elapsed_time": "1:01:09", "remaining_time": "0:23:16"}
357
+ {"current_steps": 298, "total_steps": 410, "loss": 0.0139, "lr": 2.106023595119358e-05, "epoch": 3.6121212121212123, "percentage": 72.68, "elapsed_time": "1:01:21", "remaining_time": "0:23:03"}
358
+ {"current_steps": 299, "total_steps": 410, "loss": 0.0148, "lr": 2.071415028359026e-05, "epoch": 3.624242424242424, "percentage": 72.93, "elapsed_time": "1:01:32", "remaining_time": "0:22:50"}
359
+ {"current_steps": 300, "total_steps": 410, "loss": 0.0163, "lr": 2.0370187382457068e-05, "epoch": 3.6363636363636362, "percentage": 73.17, "elapsed_time": "1:01:44", "remaining_time": "0:22:38"}
360
+ {"current_steps": 300, "total_steps": 410, "eval_loss": 0.02069205790758133, "epoch": 3.6363636363636362, "percentage": 73.17, "elapsed_time": "1:01:51", "remaining_time": "0:22:40"}
361
+ {"current_steps": 301, "total_steps": 410, "loss": 0.0143, "lr": 2.0028372179729403e-05, "epoch": 3.6484848484848484, "percentage": 73.41, "elapsed_time": "1:02:08", "remaining_time": "0:22:30"}
362
+ {"current_steps": 302, "total_steps": 410, "loss": 0.0168, "lr": 1.9688729451668114e-05, "epoch": 3.6606060606060606, "percentage": 73.66, "elapsed_time": "1:02:18", "remaining_time": "0:22:16"}
363
+ {"current_steps": 303, "total_steps": 410, "loss": 0.0129, "lr": 1.935128381706355e-05, "epoch": 3.672727272727273, "percentage": 73.9, "elapsed_time": "1:02:29", "remaining_time": "0:22:04"}
364
+ {"current_steps": 304, "total_steps": 410, "loss": 0.0194, "lr": 1.901605973545116e-05, "epoch": 3.6848484848484846, "percentage": 74.15, "elapsed_time": "1:02:43", "remaining_time": "0:21:52"}
365
+ {"current_steps": 305, "total_steps": 410, "loss": 0.015, "lr": 1.868308150533847e-05, "epoch": 3.6969696969696972, "percentage": 74.39, "elapsed_time": "1:02:54", "remaining_time": "0:21:39"}
366
+ {"current_steps": 305, "total_steps": 410, "eval_loss": 0.020683376118540764, "epoch": 3.6969696969696972, "percentage": 74.39, "elapsed_time": "1:03:00", "remaining_time": "0:21:41"}
367
+ {"current_steps": 306, "total_steps": 410, "loss": 0.0147, "lr": 1.8352373262443916e-05, "epoch": 3.709090909090909, "percentage": 74.63, "elapsed_time": "1:03:11", "remaining_time": "0:21:28"}
368
+ {"current_steps": 307, "total_steps": 410, "loss": 0.0157, "lr": 1.8023958977947304e-05, "epoch": 3.721212121212121, "percentage": 74.88, "elapsed_time": "1:03:21", "remaining_time": "0:21:15"}
369
+ {"current_steps": 308, "total_steps": 410, "loss": 0.0152, "lr": 1.7697862456752273e-05, "epoch": 3.7333333333333334, "percentage": 75.12, "elapsed_time": "1:03:32", "remaining_time": "0:21:02"}
370
+ {"current_steps": 309, "total_steps": 410, "loss": 0.0172, "lr": 1.7374107335760936e-05, "epoch": 3.7454545454545456, "percentage": 75.37, "elapsed_time": "1:03:41", "remaining_time": "0:20:49"}
371
+ {"current_steps": 310, "total_steps": 410, "loss": 0.0154, "lr": 1.7052717082160346e-05, "epoch": 3.757575757575758, "percentage": 75.61, "elapsed_time": "1:03:53", "remaining_time": "0:20:36"}
372
+ {"current_steps": 310, "total_steps": 410, "eval_loss": 0.02056981809437275, "epoch": 3.757575757575758, "percentage": 75.61, "elapsed_time": "1:03:59", "remaining_time": "0:20:38"}
373
+ {"current_steps": 311, "total_steps": 410, "loss": 0.015, "lr": 1.673371499172174e-05, "epoch": 3.7696969696969695, "percentage": 75.85, "elapsed_time": "1:04:09", "remaining_time": "0:20:25"}
374
+ {"current_steps": 312, "total_steps": 410, "loss": 0.017, "lr": 1.6417124187111775e-05, "epoch": 3.7818181818181817, "percentage": 76.1, "elapsed_time": "1:04:20", "remaining_time": "0:20:12"}
375
+ {"current_steps": 313, "total_steps": 410, "loss": 0.0145, "lr": 1.610296761621662e-05, "epoch": 3.793939393939394, "percentage": 76.34, "elapsed_time": "1:04:30", "remaining_time": "0:19:59"}
376
+ {"current_steps": 314, "total_steps": 410, "loss": 0.0228, "lr": 1.5791268050478486e-05, "epoch": 3.806060606060606, "percentage": 76.59, "elapsed_time": "1:04:40", "remaining_time": "0:19:46"}
377
+ {"current_steps": 315, "total_steps": 410, "loss": 0.0186, "lr": 1.5482048083245114e-05, "epoch": 3.8181818181818183, "percentage": 76.83, "elapsed_time": "1:04:53", "remaining_time": "0:19:34"}
378
+ {"current_steps": 315, "total_steps": 410, "eval_loss": 0.02028246596455574, "epoch": 3.8181818181818183, "percentage": 76.83, "elapsed_time": "1:04:59", "remaining_time": "0:19:36"}
379
+ {"current_steps": 316, "total_steps": 410, "loss": 0.0159, "lr": 1.517533012813217e-05, "epoch": 3.83030303030303, "percentage": 77.07, "elapsed_time": "1:05:12", "remaining_time": "0:19:23"}
380
+ {"current_steps": 317, "total_steps": 410, "loss": 0.0123, "lr": 1.4871136417398406e-05, "epoch": 3.8424242424242423, "percentage": 77.32, "elapsed_time": "1:05:24", "remaining_time": "0:19:11"}
381
+ {"current_steps": 318, "total_steps": 410, "loss": 0.0137, "lr": 1.4569489000334436e-05, "epoch": 3.8545454545454545, "percentage": 77.56, "elapsed_time": "1:05:35", "remaining_time": "0:18:58"}
382
+ {"current_steps": 319, "total_steps": 410, "loss": 0.0159, "lr": 1.427040974166427e-05, "epoch": 3.8666666666666667, "percentage": 77.8, "elapsed_time": "1:05:44", "remaining_time": "0:18:45"}
383
+ {"current_steps": 320, "total_steps": 410, "loss": 0.0135, "lr": 1.3973920319960655e-05, "epoch": 3.878787878787879, "percentage": 78.05, "elapsed_time": "1:05:53", "remaining_time": "0:18:31"}
384
+ {"current_steps": 320, "total_steps": 410, "eval_loss": 0.020162392407655716, "epoch": 3.878787878787879, "percentage": 78.05, "elapsed_time": "1:05:59", "remaining_time": "0:18:33"}
385
+ {"current_steps": 321, "total_steps": 410, "loss": 0.0148, "lr": 1.3680042226073552e-05, "epoch": 3.8909090909090907, "percentage": 78.29, "elapsed_time": "1:06:09", "remaining_time": "0:18:20"}
386
+ {"current_steps": 322, "total_steps": 410, "loss": 0.0141, "lr": 1.3388796761572492e-05, "epoch": 3.9030303030303033, "percentage": 78.54, "elapsed_time": "1:06:20", "remaining_time": "0:18:07"}
387
+ {"current_steps": 323, "total_steps": 410, "loss": 0.0132, "lr": 1.310020503720254e-05, "epoch": 3.915151515151515, "percentage": 78.78, "elapsed_time": "1:06:32", "remaining_time": "0:17:55"}
388
+ {"current_steps": 324, "total_steps": 410, "loss": 0.0161, "lr": 1.2814287971354022e-05, "epoch": 3.9272727272727272, "percentage": 79.02, "elapsed_time": "1:06:41", "remaining_time": "0:17:42"}
389
+ {"current_steps": 325, "total_steps": 410, "loss": 0.0159, "lr": 1.253106628854635e-05, "epoch": 3.9393939393939394, "percentage": 79.27, "elapsed_time": "1:06:52", "remaining_time": "0:17:29"}
390
+ {"current_steps": 325, "total_steps": 410, "eval_loss": 0.020128030329942703, "epoch": 3.9393939393939394, "percentage": 79.27, "elapsed_time": "1:06:58", "remaining_time": "0:17:30"}
391
+ {"current_steps": 326, "total_steps": 410, "loss": 0.0142, "lr": 1.2250560517925746e-05, "epoch": 3.9515151515151516, "percentage": 79.51, "elapsed_time": "1:07:07", "remaining_time": "0:17:17"}
392
+ {"current_steps": 327, "total_steps": 410, "loss": 0.0155, "lr": 1.1972790991777311e-05, "epoch": 3.963636363636364, "percentage": 79.76, "elapsed_time": "1:07:19", "remaining_time": "0:17:05"}
393
+ {"current_steps": 328, "total_steps": 410, "loss": 0.0142, "lr": 1.1697777844051105e-05, "epoch": 3.9757575757575756, "percentage": 80.0, "elapsed_time": "1:07:31", "remaining_time": "0:16:52"}
394
+ {"current_steps": 329, "total_steps": 410, "loss": 0.0147, "lr": 1.1425541008902851e-05, "epoch": 3.987878787878788, "percentage": 80.24, "elapsed_time": "1:07:41", "remaining_time": "0:16:39"}
395
+ {"current_steps": 330, "total_steps": 410, "loss": 0.0211, "lr": 1.1156100219249022e-05, "epoch": 4.0, "percentage": 80.49, "elapsed_time": "1:07:52", "remaining_time": "0:16:27"}
396
+ {"current_steps": 330, "total_steps": 410, "eval_loss": 0.01995450258255005, "epoch": 4.0, "percentage": 80.49, "elapsed_time": "1:07:58", "remaining_time": "0:16:28"}
397
+ {"current_steps": 331, "total_steps": 410, "loss": 0.0133, "lr": 1.0889475005336446e-05, "epoch": 4.012121212121212, "percentage": 80.73, "elapsed_time": "1:08:07", "remaining_time": "0:16:15"}
398
+ {"current_steps": 332, "total_steps": 410, "loss": 0.013, "lr": 1.0625684693326727e-05, "epoch": 4.024242424242424, "percentage": 80.98, "elapsed_time": "1:08:19", "remaining_time": "0:16:03"}
399
+ {"current_steps": 333, "total_steps": 410, "loss": 0.0132, "lr": 1.036474840389537e-05, "epoch": 4.036363636363636, "percentage": 81.22, "elapsed_time": "1:08:28", "remaining_time": "0:15:50"}
400
+ {"current_steps": 334, "total_steps": 410, "loss": 0.0121, "lr": 1.0106685050845838e-05, "epoch": 4.048484848484849, "percentage": 81.46, "elapsed_time": "1:08:38", "remaining_time": "0:15:37"}
401
+ {"current_steps": 335, "total_steps": 410, "loss": 0.0134, "lr": 9.851513339738628e-06, "epoch": 4.0606060606060606, "percentage": 81.71, "elapsed_time": "1:08:49", "remaining_time": "0:15:24"}
402
+ {"current_steps": 335, "total_steps": 410, "eval_loss": 0.0202109944075346, "epoch": 4.0606060606060606, "percentage": 81.71, "elapsed_time": "1:08:55", "remaining_time": "0:15:25"}
403
+ {"current_steps": 336, "total_steps": 410, "loss": 0.0121, "lr": 9.599251766535345e-06, "epoch": 4.072727272727272, "percentage": 81.95, "elapsed_time": "1:09:07", "remaining_time": "0:15:13"}
404
+ {"current_steps": 337, "total_steps": 410, "loss": 0.0126, "lr": 9.349918616258114e-06, "epoch": 4.084848484848485, "percentage": 82.2, "elapsed_time": "1:09:16", "remaining_time": "0:15:00"}
405
+ {"current_steps": 338, "total_steps": 410, "loss": 0.0122, "lr": 9.103531961664118e-06, "epoch": 4.096969696969697, "percentage": 82.44, "elapsed_time": "1:09:27", "remaining_time": "0:14:47"}
406
+ {"current_steps": 339, "total_steps": 410, "loss": 0.0155, "lr": 8.860109661935674e-06, "epoch": 4.109090909090909, "percentage": 82.68, "elapsed_time": "1:09:40", "remaining_time": "0:14:35"}
407
+ {"current_steps": 340, "total_steps": 410, "loss": 0.0113, "lr": 8.619669361385663e-06, "epoch": 4.121212121212121, "percentage": 82.93, "elapsed_time": "1:09:50", "remaining_time": "0:14:22"}
408
+ {"current_steps": 340, "total_steps": 410, "eval_loss": 0.020561667159199715, "epoch": 4.121212121212121, "percentage": 82.93, "elapsed_time": "1:09:56", "remaining_time": "0:14:24"}
409
+ {"current_steps": 341, "total_steps": 410, "loss": 0.0127, "lr": 8.38222848817864e-06, "epoch": 4.133333333333334, "percentage": 83.17, "elapsed_time": "1:10:07", "remaining_time": "0:14:11"}
410
+ {"current_steps": 342, "total_steps": 410, "loss": 0.0121, "lr": 8.14780425306758e-06, "epoch": 4.1454545454545455, "percentage": 83.41, "elapsed_time": "1:10:15", "remaining_time": "0:13:58"}
411
+ {"current_steps": 343, "total_steps": 410, "loss": 0.0109, "lr": 7.91641364814628e-06, "epoch": 4.157575757575757, "percentage": 83.66, "elapsed_time": "1:10:26", "remaining_time": "0:13:45"}
412
+ {"current_steps": 344, "total_steps": 410, "loss": 0.0108, "lr": 7.688073445617799e-06, "epoch": 4.16969696969697, "percentage": 83.9, "elapsed_time": "1:10:35", "remaining_time": "0:13:32"}
413
+ {"current_steps": 345, "total_steps": 410, "loss": 0.0117, "lr": 7.462800196578662e-06, "epoch": 4.181818181818182, "percentage": 84.15, "elapsed_time": "1:10:46", "remaining_time": "0:13:19"}
414
+ {"current_steps": 345, "total_steps": 410, "eval_loss": 0.0208114180713892, "epoch": 4.181818181818182, "percentage": 84.15, "elapsed_time": "1:10:52", "remaining_time": "0:13:21"}
415
+ {"current_steps": 346, "total_steps": 410, "loss": 0.013, "lr": 7.240610229819195e-06, "epoch": 4.193939393939394, "percentage": 84.39, "elapsed_time": "1:11:05", "remaining_time": "0:13:09"}
416
+ {"current_steps": 347, "total_steps": 410, "loss": 0.0108, "lr": 7.0215196506399515e-06, "epoch": 4.206060606060606, "percentage": 84.63, "elapsed_time": "1:11:18", "remaining_time": "0:12:56"}
417
+ {"current_steps": 348, "total_steps": 410, "loss": 0.0103, "lr": 6.8055443396842945e-06, "epoch": 4.218181818181818, "percentage": 84.88, "elapsed_time": "1:11:30", "remaining_time": "0:12:44"}
418
+ {"current_steps": 349, "total_steps": 410, "loss": 0.0138, "lr": 6.592699951787362e-06, "epoch": 4.2303030303030305, "percentage": 85.12, "elapsed_time": "1:11:41", "remaining_time": "0:12:31"}
419
+ {"current_steps": 350, "total_steps": 410, "loss": 0.0108, "lr": 6.3830019148412525e-06, "epoch": 4.242424242424242, "percentage": 85.37, "elapsed_time": "1:11:53", "remaining_time": "0:12:19"}
420
+ {"current_steps": 350, "total_steps": 410, "eval_loss": 0.020906535908579826, "epoch": 4.242424242424242, "percentage": 85.37, "elapsed_time": "1:11:59", "remaining_time": "0:12:20"}
421
+ {"current_steps": 351, "total_steps": 410, "loss": 0.0144, "lr": 6.17646542867682e-06, "epoch": 4.254545454545455, "percentage": 85.61, "elapsed_time": "1:12:16", "remaining_time": "0:12:08"}
422
+ {"current_steps": 352, "total_steps": 410, "loss": 0.0107, "lr": 5.973105463961865e-06, "epoch": 4.266666666666667, "percentage": 85.85, "elapsed_time": "1:12:28", "remaining_time": "0:11:56"}
423
+ {"current_steps": 353, "total_steps": 410, "loss": 0.0139, "lr": 5.772936761116027e-06, "epoch": 4.278787878787879, "percentage": 86.1, "elapsed_time": "1:12:37", "remaining_time": "0:11:43"}
424
+ {"current_steps": 354, "total_steps": 410, "loss": 0.0126, "lr": 5.575973829242364e-06, "epoch": 4.290909090909091, "percentage": 86.34, "elapsed_time": "1:12:47", "remaining_time": "0:11:30"}
425
+ {"current_steps": 355, "total_steps": 410, "loss": 0.012, "lr": 5.382230945075556e-06, "epoch": 4.303030303030303, "percentage": 86.59, "elapsed_time": "1:12:58", "remaining_time": "0:11:18"}
426
+ {"current_steps": 355, "total_steps": 410, "eval_loss": 0.020746439695358276, "epoch": 4.303030303030303, "percentage": 86.59, "elapsed_time": "1:13:04", "remaining_time": "0:11:19"}
427
+ {"current_steps": 356, "total_steps": 410, "loss": 0.0099, "lr": 5.191722151947226e-06, "epoch": 4.315151515151515, "percentage": 86.83, "elapsed_time": "1:13:16", "remaining_time": "0:11:06"}
428
+ {"current_steps": 357, "total_steps": 410, "loss": 0.0143, "lr": 5.004461258767873e-06, "epoch": 4.327272727272727, "percentage": 87.07, "elapsed_time": "1:13:28", "remaining_time": "0:10:54"}
429
+ {"current_steps": 358, "total_steps": 410, "loss": 0.0126, "lr": 4.820461839026047e-06, "epoch": 4.33939393939394, "percentage": 87.32, "elapsed_time": "1:13:39", "remaining_time": "0:10:41"}
430
+ {"current_steps": 359, "total_steps": 410, "loss": 0.0115, "lr": 4.639737229804403e-06, "epoch": 4.351515151515152, "percentage": 87.56, "elapsed_time": "1:13:51", "remaining_time": "0:10:29"}
431
+ {"current_steps": 360, "total_steps": 410, "loss": 0.0111, "lr": 4.462300530813024e-06, "epoch": 4.363636363636363, "percentage": 87.8, "elapsed_time": "1:14:01", "remaining_time": "0:10:16"}
432
+ {"current_steps": 360, "total_steps": 410, "eval_loss": 0.020565090700984, "epoch": 4.363636363636363, "percentage": 87.8, "elapsed_time": "1:14:07", "remaining_time": "0:10:17"}
433
+ {"current_steps": 361, "total_steps": 410, "loss": 0.0114, "lr": 4.2881646034398925e-06, "epoch": 4.375757575757576, "percentage": 88.05, "elapsed_time": "1:14:18", "remaining_time": "0:10:05"}
434
+ {"current_steps": 362, "total_steps": 410, "loss": 0.0113, "lr": 4.117342069818603e-06, "epoch": 4.387878787878788, "percentage": 88.29, "elapsed_time": "1:14:27", "remaining_time": "0:09:52"}
435
+ {"current_steps": 363, "total_steps": 410, "loss": 0.0115, "lr": 3.949845311913492e-06, "epoch": 4.4, "percentage": 88.54, "elapsed_time": "1:14:37", "remaining_time": "0:09:39"}
436
+ {"current_steps": 364, "total_steps": 410, "loss": 0.0098, "lr": 3.7856864706221185e-06, "epoch": 4.412121212121212, "percentage": 88.78, "elapsed_time": "1:14:51", "remaining_time": "0:09:27"}
437
+ {"current_steps": 365, "total_steps": 410, "loss": 0.0118, "lr": 3.6248774448952695e-06, "epoch": 4.424242424242424, "percentage": 89.02, "elapsed_time": "1:15:00", "remaining_time": "0:09:14"}
438
+ {"current_steps": 365, "total_steps": 410, "eval_loss": 0.02050224132835865, "epoch": 4.424242424242424, "percentage": 89.02, "elapsed_time": "1:15:07", "remaining_time": "0:09:15"}
439
+ {"current_steps": 366, "total_steps": 410, "loss": 0.0111, "lr": 3.467429890874424e-06, "epoch": 4.4363636363636365, "percentage": 89.27, "elapsed_time": "1:15:21", "remaining_time": "0:09:03"}
440
+ {"current_steps": 367, "total_steps": 410, "loss": 0.0122, "lr": 3.3133552210468875e-06, "epoch": 4.448484848484848, "percentage": 89.51, "elapsed_time": "1:15:30", "remaining_time": "0:08:50"}
441
+ {"current_steps": 368, "total_steps": 410, "loss": 0.0136, "lr": 3.162664603418608e-06, "epoch": 4.460606060606061, "percentage": 89.76, "elapsed_time": "1:15:42", "remaining_time": "0:08:38"}
442
+ {"current_steps": 369, "total_steps": 410, "loss": 0.0116, "lr": 3.0153689607045845e-06, "epoch": 4.472727272727273, "percentage": 90.0, "elapsed_time": "1:15:56", "remaining_time": "0:08:26"}
443
+ {"current_steps": 370, "total_steps": 410, "loss": 0.0099, "lr": 2.871478969537206e-06, "epoch": 4.484848484848484, "percentage": 90.24, "elapsed_time": "1:16:09", "remaining_time": "0:08:13"}
444
+ {"current_steps": 370, "total_steps": 410, "eval_loss": 0.02058413252234459, "epoch": 4.484848484848484, "percentage": 90.24, "elapsed_time": "1:16:15", "remaining_time": "0:08:14"}
445
+ {"current_steps": 371, "total_steps": 410, "loss": 0.0212, "lr": 2.731005059692332e-06, "epoch": 4.496969696969697, "percentage": 90.49, "elapsed_time": "1:16:26", "remaining_time": "0:08:02"}
446
+ {"current_steps": 372, "total_steps": 410, "loss": 0.0275, "lr": 2.5939574133333312e-06, "epoch": 4.509090909090909, "percentage": 90.73, "elapsed_time": "1:16:37", "remaining_time": "0:07:49"}
447
+ {"current_steps": 373, "total_steps": 410, "loss": 0.0104, "lr": 2.4603459642729863e-06, "epoch": 4.5212121212121215, "percentage": 90.98, "elapsed_time": "1:16:50", "remaining_time": "0:07:37"}
448
+ {"current_steps": 374, "total_steps": 410, "loss": 0.0099, "lr": 2.330180397253473e-06, "epoch": 4.533333333333333, "percentage": 91.22, "elapsed_time": "1:17:01", "remaining_time": "0:07:24"}
449
+ {"current_steps": 375, "total_steps": 410, "loss": 0.0118, "lr": 2.203470147244385e-06, "epoch": 4.545454545454545, "percentage": 91.46, "elapsed_time": "1:17:11", "remaining_time": "0:07:12"}
450
+ {"current_steps": 375, "total_steps": 410, "eval_loss": 0.020584262907505035, "epoch": 4.545454545454545, "percentage": 91.46, "elapsed_time": "1:17:17", "remaining_time": "0:07:12"}
451
+ {"current_steps": 376, "total_steps": 410, "loss": 0.0104, "lr": 2.0802243987588066e-06, "epoch": 4.557575757575758, "percentage": 91.71, "elapsed_time": "1:17:28", "remaining_time": "0:07:00"}
452
+ {"current_steps": 377, "total_steps": 410, "loss": 0.0121, "lr": 1.9604520851876198e-06, "epoch": 4.569696969696969, "percentage": 91.95, "elapsed_time": "1:17:40", "remaining_time": "0:06:47"}
453
+ {"current_steps": 378, "total_steps": 410, "loss": 0.0113, "lr": 1.8441618881519184e-06, "epoch": 4.581818181818182, "percentage": 92.2, "elapsed_time": "1:17:50", "remaining_time": "0:06:35"}
454
+ {"current_steps": 379, "total_steps": 410, "loss": 0.0105, "lr": 1.7313622368738014e-06, "epoch": 4.593939393939394, "percentage": 92.44, "elapsed_time": "1:18:00", "remaining_time": "0:06:22"}
455
+ {"current_steps": 380, "total_steps": 410, "loss": 0.0119, "lr": 1.6220613075653202e-06, "epoch": 4.606060606060606, "percentage": 92.68, "elapsed_time": "1:18:11", "remaining_time": "0:06:10"}
456
+ {"current_steps": 380, "total_steps": 410, "eval_loss": 0.02056843228638172, "epoch": 4.606060606060606, "percentage": 92.68, "elapsed_time": "1:18:17", "remaining_time": "0:06:10"}
457
+ {"current_steps": 381, "total_steps": 410, "loss": 0.0098, "lr": 1.51626702283586e-06, "epoch": 4.618181818181818, "percentage": 92.93, "elapsed_time": "1:18:28", "remaining_time": "0:05:58"}
458
+ {"current_steps": 382, "total_steps": 410, "loss": 0.0116, "lr": 1.4139870511178766e-06, "epoch": 4.63030303030303, "percentage": 93.17, "elapsed_time": "1:18:39", "remaining_time": "0:05:45"}
459
+ {"current_steps": 383, "total_steps": 410, "loss": 0.0101, "lr": 1.3152288061110518e-06, "epoch": 4.642424242424243, "percentage": 93.41, "elapsed_time": "1:18:51", "remaining_time": "0:05:33"}
460
+ {"current_steps": 384, "total_steps": 410, "loss": 0.0113, "lr": 1.2199994462448904e-06, "epoch": 4.654545454545454, "percentage": 93.66, "elapsed_time": "1:19:03", "remaining_time": "0:05:21"}
461
+ {"current_steps": 385, "total_steps": 410, "loss": 0.0114, "lr": 1.128305874159896e-06, "epoch": 4.666666666666667, "percentage": 93.9, "elapsed_time": "1:19:13", "remaining_time": "0:05:08"}
462
+ {"current_steps": 385, "total_steps": 410, "eval_loss": 0.02059413306415081, "epoch": 4.666666666666667, "percentage": 93.9, "elapsed_time": "1:19:19", "remaining_time": "0:05:09"}
463
+ {"current_steps": 386, "total_steps": 410, "loss": 0.0106, "lr": 1.040154736207194e-06, "epoch": 4.678787878787879, "percentage": 94.15, "elapsed_time": "1:19:29", "remaining_time": "0:04:56"}
464
+ {"current_steps": 387, "total_steps": 410, "loss": 0.0122, "lr": 9.555524219667989e-07, "epoch": 4.690909090909091, "percentage": 94.39, "elapsed_time": "1:19:39", "remaining_time": "0:04:44"}
465
+ {"current_steps": 388, "total_steps": 410, "loss": 0.0097, "lr": 8.745050637844532e-07, "epoch": 4.703030303030303, "percentage": 94.63, "elapsed_time": "1:19:50", "remaining_time": "0:04:31"}
466
+ {"current_steps": 389, "total_steps": 410, "loss": 0.0121, "lr": 7.970185363271431e-07, "epoch": 4.715151515151515, "percentage": 94.88, "elapsed_time": "1:20:01", "remaining_time": "0:04:19"}
467
+ {"current_steps": 390, "total_steps": 410, "loss": 0.0109, "lr": 7.230984561572729e-07, "epoch": 4.7272727272727275, "percentage": 95.12, "elapsed_time": "1:20:14", "remaining_time": "0:04:06"}
468
+ {"current_steps": 390, "total_steps": 410, "eval_loss": 0.020591916516423225, "epoch": 4.7272727272727275, "percentage": 95.12, "elapsed_time": "1:20:20", "remaining_time": "0:04:07"}
469
+ {"current_steps": 391, "total_steps": 410, "loss": 0.0165, "lr": 6.527501813255344e-07, "epoch": 4.739393939393939, "percentage": 95.37, "elapsed_time": "1:20:31", "remaining_time": "0:03:54"}
470
+ {"current_steps": 392, "total_steps": 410, "loss": 0.0096, "lr": 5.859788109825793e-07, "epoch": 4.751515151515152, "percentage": 95.61, "elapsed_time": "1:20:47", "remaining_time": "0:03:42"}
471
+ {"current_steps": 393, "total_steps": 410, "loss": 0.0129, "lr": 5.227891850093314e-07, "epoch": 4.763636363636364, "percentage": 95.85, "elapsed_time": "1:20:58", "remaining_time": "0:03:30"}
472
+ {"current_steps": 394, "total_steps": 410, "loss": 0.0122, "lr": 4.6318588366625616e-07, "epoch": 4.775757575757575, "percentage": 96.1, "elapsed_time": "1:21:10", "remaining_time": "0:03:17"}
473
+ {"current_steps": 395, "total_steps": 410, "loss": 0.0124, "lr": 4.071732272613149e-07, "epoch": 4.787878787878788, "percentage": 96.34, "elapsed_time": "1:21:19", "remaining_time": "0:03:05"}
474
+ {"current_steps": 395, "total_steps": 410, "eval_loss": 0.020531287416815758, "epoch": 4.787878787878788, "percentage": 96.34, "elapsed_time": "1:21:25", "remaining_time": "0:03:05"}
475
+ {"current_steps": 396, "total_steps": 410, "loss": 0.0112, "lr": 3.5475527583681e-07, "epoch": 4.8, "percentage": 96.59, "elapsed_time": "1:21:33", "remaining_time": "0:02:53"}
476
+ {"current_steps": 397, "total_steps": 410, "loss": 0.0102, "lr": 3.059358288751202e-07, "epoch": 4.8121212121212125, "percentage": 96.83, "elapsed_time": "1:21:44", "remaining_time": "0:02:40"}
477
+ {"current_steps": 398, "total_steps": 410, "loss": 0.0119, "lr": 2.6071842502326527e-07, "epoch": 4.824242424242424, "percentage": 97.07, "elapsed_time": "1:21:57", "remaining_time": "0:02:28"}
478
+ {"current_steps": 399, "total_steps": 410, "loss": 0.0117, "lr": 2.1910634183644474e-07, "epoch": 4.836363636363636, "percentage": 97.32, "elapsed_time": "1:22:09", "remaining_time": "0:02:15"}
479
+ {"current_steps": 400, "total_steps": 410, "loss": 0.0111, "lr": 1.811025955404333e-07, "epoch": 4.848484848484849, "percentage": 97.56, "elapsed_time": "1:22:20", "remaining_time": "0:02:03"}
480
+ {"current_steps": 400, "total_steps": 410, "eval_loss": 0.020571600645780563, "epoch": 4.848484848484849, "percentage": 97.56, "elapsed_time": "1:22:26", "remaining_time": "0:02:03"}
481
+ {"current_steps": 401, "total_steps": 410, "loss": 0.0141, "lr": 1.4670994081297795e-07, "epoch": 4.86060606060606, "percentage": 97.8, "elapsed_time": "1:22:43", "remaining_time": "0:01:51"}
482
+ {"current_steps": 402, "total_steps": 410, "loss": 0.0113, "lr": 1.1593087058410779e-07, "epoch": 4.872727272727273, "percentage": 98.05, "elapsed_time": "1:22:55", "remaining_time": "0:01:39"}
483
+ {"current_steps": 403, "total_steps": 410, "loss": 0.0104, "lr": 8.876761585545068e-08, "epoch": 4.884848484848485, "percentage": 98.29, "elapsed_time": "1:23:03", "remaining_time": "0:01:26"}
484
+ {"current_steps": 404, "total_steps": 410, "loss": 0.0122, "lr": 6.522214553850159e-08, "epoch": 4.8969696969696965, "percentage": 98.54, "elapsed_time": "1:23:16", "remaining_time": "0:01:14"}
485
+ {"current_steps": 405, "total_steps": 410, "loss": 0.012, "lr": 4.529616631193112e-08, "epoch": 4.909090909090909, "percentage": 98.78, "elapsed_time": "1:23:27", "remaining_time": "0:01:01"}
486
+ {"current_steps": 405, "total_steps": 410, "eval_loss": 0.020557112991809845, "epoch": 4.909090909090909, "percentage": 98.78, "elapsed_time": "1:23:33", "remaining_time": "0:01:01"}
487
+ {"current_steps": 406, "total_steps": 410, "loss": 0.0115, "lr": 2.899112249786229e-08, "epoch": 4.921212121212121, "percentage": 99.02, "elapsed_time": "1:23:41", "remaining_time": "0:00:49"}
488
+ {"current_steps": 407, "total_steps": 410, "loss": 0.0125, "lr": 1.6308195957182027e-08, "epoch": 4.933333333333334, "percentage": 99.27, "elapsed_time": "1:23:53", "remaining_time": "0:00:37"}
489
+ {"current_steps": 408, "total_steps": 410, "loss": 0.0123, "lr": 7.248306003865279e-09, "epoch": 4.945454545454545, "percentage": 99.51, "elapsed_time": "1:24:02", "remaining_time": "0:00:24"}
490
+ {"current_steps": 409, "total_steps": 410, "loss": 0.0117, "lr": 1.8121093383671738e-09, "epoch": 4.957575757575757, "percentage": 99.76, "elapsed_time": "1:24:12", "remaining_time": "0:00:12"}
491
+ {"current_steps": 410, "total_steps": 410, "loss": 0.0104, "lr": 0.0, "epoch": 4.96969696969697, "percentage": 100.0, "elapsed_time": "1:24:24", "remaining_time": "0:00:00"}
492
+ {"current_steps": 410, "total_steps": 410, "eval_loss": 0.020535213872790337, "epoch": 4.96969696969697, "percentage": 100.0, "elapsed_time": "1:24:30", "remaining_time": "0:00:00"}
493
+ {"current_steps": 410, "total_steps": 410, "epoch": 4.96969696969697, "percentage": 100.0, "elapsed_time": "1:24:37", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,3568 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.020535213872790337,
3
+ "best_model_checkpoint": "/home/paperspace/Data/models/brasingh_publicis_f5f/llm3br256/checkpoint-410",
4
+ "epoch": 4.96969696969697,
5
+ "eval_steps": 5,
6
+ "global_step": 410,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.012121212121212121,
13
+ "grad_norm": 0.17719489336013794,
14
+ "learning_rate": 2.4390243902439027e-06,
15
+ "loss": 0.103,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.024242424242424242,
20
+ "grad_norm": 0.1567779779434204,
21
+ "learning_rate": 4.8780487804878055e-06,
22
+ "loss": 0.11,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03636363636363636,
27
+ "grad_norm": 0.1601039469242096,
28
+ "learning_rate": 7.317073170731707e-06,
29
+ "loss": 0.1104,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.048484848484848485,
34
+ "grad_norm": 0.16313816606998444,
35
+ "learning_rate": 9.756097560975611e-06,
36
+ "loss": 0.1076,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.06060606060606061,
41
+ "grad_norm": 0.15266162157058716,
42
+ "learning_rate": 1.2195121951219513e-05,
43
+ "loss": 0.1038,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.06060606060606061,
48
+ "eval_loss": 0.09789121896028519,
49
+ "eval_runtime": 8.116,
50
+ "eval_samples_per_second": 6.161,
51
+ "eval_steps_per_second": 1.602,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.07272727272727272,
56
+ "grad_norm": 0.1329907476902008,
57
+ "learning_rate": 1.4634146341463415e-05,
58
+ "loss": 0.0995,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.08484848484848485,
63
+ "grad_norm": 0.09588994085788727,
64
+ "learning_rate": 1.707317073170732e-05,
65
+ "loss": 0.0833,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.09696969696969697,
70
+ "grad_norm": 0.07421080023050308,
71
+ "learning_rate": 1.9512195121951222e-05,
72
+ "loss": 0.0756,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.10909090909090909,
77
+ "grad_norm": 0.0636032298207283,
78
+ "learning_rate": 2.1951219512195124e-05,
79
+ "loss": 0.0681,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.12121212121212122,
84
+ "grad_norm": 0.07186830043792725,
85
+ "learning_rate": 2.4390243902439026e-05,
86
+ "loss": 0.0759,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.12121212121212122,
91
+ "eval_loss": 0.07647334039211273,
92
+ "eval_runtime": 6.2195,
93
+ "eval_samples_per_second": 8.039,
94
+ "eval_steps_per_second": 2.09,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.13333333333333333,
99
+ "grad_norm": 0.07592587172985077,
100
+ "learning_rate": 2.682926829268293e-05,
101
+ "loss": 0.0757,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.14545454545454545,
106
+ "grad_norm": 0.057555243372917175,
107
+ "learning_rate": 2.926829268292683e-05,
108
+ "loss": 0.0733,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.15757575757575756,
113
+ "grad_norm": 0.04685232415795326,
114
+ "learning_rate": 3.170731707317073e-05,
115
+ "loss": 0.0751,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.1696969696969697,
120
+ "grad_norm": 0.04220229387283325,
121
+ "learning_rate": 3.414634146341464e-05,
122
+ "loss": 0.0784,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.18181818181818182,
127
+ "grad_norm": 0.050287775695323944,
128
+ "learning_rate": 3.6585365853658535e-05,
129
+ "loss": 0.069,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.18181818181818182,
134
+ "eval_loss": 0.06831522285938263,
135
+ "eval_runtime": 6.1929,
136
+ "eval_samples_per_second": 8.074,
137
+ "eval_steps_per_second": 2.099,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.19393939393939394,
142
+ "grad_norm": 0.04325024411082268,
143
+ "learning_rate": 3.9024390243902444e-05,
144
+ "loss": 0.0691,
145
+ "step": 16
146
+ },
147
+ {
148
+ "epoch": 0.20606060606060606,
149
+ "grad_norm": 0.037937626242637634,
150
+ "learning_rate": 4.146341463414634e-05,
151
+ "loss": 0.0813,
152
+ "step": 17
153
+ },
154
+ {
155
+ "epoch": 0.21818181818181817,
156
+ "grad_norm": 0.03867847099900246,
157
+ "learning_rate": 4.390243902439025e-05,
158
+ "loss": 0.065,
159
+ "step": 18
160
+ },
161
+ {
162
+ "epoch": 0.23030303030303031,
163
+ "grad_norm": 0.03792285919189453,
164
+ "learning_rate": 4.634146341463415e-05,
165
+ "loss": 0.0617,
166
+ "step": 19
167
+ },
168
+ {
169
+ "epoch": 0.24242424242424243,
170
+ "grad_norm": 0.03528020903468132,
171
+ "learning_rate": 4.878048780487805e-05,
172
+ "loss": 0.0729,
173
+ "step": 20
174
+ },
175
+ {
176
+ "epoch": 0.24242424242424243,
177
+ "eval_loss": 0.062009546905756,
178
+ "eval_runtime": 6.1891,
179
+ "eval_samples_per_second": 8.079,
180
+ "eval_steps_per_second": 2.1,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.2545454545454545,
185
+ "grad_norm": 0.031467072665691376,
186
+ "learning_rate": 5.121951219512195e-05,
187
+ "loss": 0.0602,
188
+ "step": 21
189
+ },
190
+ {
191
+ "epoch": 0.26666666666666666,
192
+ "grad_norm": 0.03714953735470772,
193
+ "learning_rate": 5.365853658536586e-05,
194
+ "loss": 0.0772,
195
+ "step": 22
196
+ },
197
+ {
198
+ "epoch": 0.2787878787878788,
199
+ "grad_norm": 0.03779144585132599,
200
+ "learning_rate": 5.6097560975609764e-05,
201
+ "loss": 0.0584,
202
+ "step": 23
203
+ },
204
+ {
205
+ "epoch": 0.2909090909090909,
206
+ "grad_norm": 0.030055589973926544,
207
+ "learning_rate": 5.853658536585366e-05,
208
+ "loss": 0.0568,
209
+ "step": 24
210
+ },
211
+ {
212
+ "epoch": 0.30303030303030304,
213
+ "grad_norm": 0.029797468334436417,
214
+ "learning_rate": 6.097560975609756e-05,
215
+ "loss": 0.0545,
216
+ "step": 25
217
+ },
218
+ {
219
+ "epoch": 0.30303030303030304,
220
+ "eval_loss": 0.057142239063978195,
221
+ "eval_runtime": 6.2052,
222
+ "eval_samples_per_second": 8.058,
223
+ "eval_steps_per_second": 2.095,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 0.3151515151515151,
228
+ "grad_norm": 0.029303744435310364,
229
+ "learning_rate": 6.341463414634146e-05,
230
+ "loss": 0.0591,
231
+ "step": 26
232
+ },
233
+ {
234
+ "epoch": 0.32727272727272727,
235
+ "grad_norm": 0.03735222667455673,
236
+ "learning_rate": 6.585365853658538e-05,
237
+ "loss": 0.0836,
238
+ "step": 27
239
+ },
240
+ {
241
+ "epoch": 0.3393939393939394,
242
+ "grad_norm": 0.02950606681406498,
243
+ "learning_rate": 6.829268292682928e-05,
244
+ "loss": 0.0574,
245
+ "step": 28
246
+ },
247
+ {
248
+ "epoch": 0.3515151515151515,
249
+ "grad_norm": 0.02479255013167858,
250
+ "learning_rate": 7.073170731707317e-05,
251
+ "loss": 0.0506,
252
+ "step": 29
253
+ },
254
+ {
255
+ "epoch": 0.36363636363636365,
256
+ "grad_norm": 0.030447915196418762,
257
+ "learning_rate": 7.317073170731707e-05,
258
+ "loss": 0.0589,
259
+ "step": 30
260
+ },
261
+ {
262
+ "epoch": 0.36363636363636365,
263
+ "eval_loss": 0.05275052413344383,
264
+ "eval_runtime": 6.1946,
265
+ "eval_samples_per_second": 8.072,
266
+ "eval_steps_per_second": 2.099,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.37575757575757573,
271
+ "grad_norm": 0.029138660058379173,
272
+ "learning_rate": 7.560975609756099e-05,
273
+ "loss": 0.0536,
274
+ "step": 31
275
+ },
276
+ {
277
+ "epoch": 0.3878787878787879,
278
+ "grad_norm": 0.029026566073298454,
279
+ "learning_rate": 7.804878048780489e-05,
280
+ "loss": 0.0454,
281
+ "step": 32
282
+ },
283
+ {
284
+ "epoch": 0.4,
285
+ "grad_norm": 0.03538930043578148,
286
+ "learning_rate": 8.048780487804879e-05,
287
+ "loss": 0.0727,
288
+ "step": 33
289
+ },
290
+ {
291
+ "epoch": 0.4121212121212121,
292
+ "grad_norm": 0.028354594483971596,
293
+ "learning_rate": 8.292682926829268e-05,
294
+ "loss": 0.0557,
295
+ "step": 34
296
+ },
297
+ {
298
+ "epoch": 0.42424242424242425,
299
+ "grad_norm": 0.02743169106543064,
300
+ "learning_rate": 8.53658536585366e-05,
301
+ "loss": 0.0461,
302
+ "step": 35
303
+ },
304
+ {
305
+ "epoch": 0.42424242424242425,
306
+ "eval_loss": 0.05005570873618126,
307
+ "eval_runtime": 6.192,
308
+ "eval_samples_per_second": 8.075,
309
+ "eval_steps_per_second": 2.099,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.43636363636363634,
314
+ "grad_norm": 0.03530753031373024,
315
+ "learning_rate": 8.78048780487805e-05,
316
+ "loss": 0.0627,
317
+ "step": 36
318
+ },
319
+ {
320
+ "epoch": 0.4484848484848485,
321
+ "grad_norm": 0.02797996811568737,
322
+ "learning_rate": 9.02439024390244e-05,
323
+ "loss": 0.0527,
324
+ "step": 37
325
+ },
326
+ {
327
+ "epoch": 0.46060606060606063,
328
+ "grad_norm": 0.022809529677033424,
329
+ "learning_rate": 9.26829268292683e-05,
330
+ "loss": 0.0509,
331
+ "step": 38
332
+ },
333
+ {
334
+ "epoch": 0.4727272727272727,
335
+ "grad_norm": 0.02468150481581688,
336
+ "learning_rate": 9.51219512195122e-05,
337
+ "loss": 0.0488,
338
+ "step": 39
339
+ },
340
+ {
341
+ "epoch": 0.48484848484848486,
342
+ "grad_norm": 0.030917035415768623,
343
+ "learning_rate": 9.75609756097561e-05,
344
+ "loss": 0.0522,
345
+ "step": 40
346
+ },
347
+ {
348
+ "epoch": 0.48484848484848486,
349
+ "eval_loss": 0.049276672303676605,
350
+ "eval_runtime": 6.1874,
351
+ "eval_samples_per_second": 8.081,
352
+ "eval_steps_per_second": 2.101,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.49696969696969695,
357
+ "grad_norm": 0.026523206382989883,
358
+ "learning_rate": 0.0001,
359
+ "loss": 0.0463,
360
+ "step": 41
361
+ },
362
+ {
363
+ "epoch": 0.509090909090909,
364
+ "grad_norm": 0.028745442628860474,
365
+ "learning_rate": 9.999818789066165e-05,
366
+ "loss": 0.0433,
367
+ "step": 42
368
+ },
369
+ {
370
+ "epoch": 0.5212121212121212,
371
+ "grad_norm": 0.026402153074741364,
372
+ "learning_rate": 9.999275169399614e-05,
373
+ "loss": 0.0393,
374
+ "step": 43
375
+ },
376
+ {
377
+ "epoch": 0.5333333333333333,
378
+ "grad_norm": 0.02671145275235176,
379
+ "learning_rate": 9.998369180404283e-05,
380
+ "loss": 0.044,
381
+ "step": 44
382
+ },
383
+ {
384
+ "epoch": 0.5454545454545454,
385
+ "grad_norm": 0.034986190497875214,
386
+ "learning_rate": 9.997100887750215e-05,
387
+ "loss": 0.052,
388
+ "step": 45
389
+ },
390
+ {
391
+ "epoch": 0.5454545454545454,
392
+ "eval_loss": 0.04825693741440773,
393
+ "eval_runtime": 6.1973,
394
+ "eval_samples_per_second": 8.068,
395
+ "eval_steps_per_second": 2.098,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.5575757575757576,
400
+ "grad_norm": 0.029590139165520668,
401
+ "learning_rate": 9.995470383368808e-05,
402
+ "loss": 0.0436,
403
+ "step": 46
404
+ },
405
+ {
406
+ "epoch": 0.5696969696969697,
407
+ "grad_norm": 0.03095312975347042,
408
+ "learning_rate": 9.99347778544615e-05,
409
+ "loss": 0.0431,
410
+ "step": 47
411
+ },
412
+ {
413
+ "epoch": 0.5818181818181818,
414
+ "grad_norm": 0.030565602704882622,
415
+ "learning_rate": 9.991123238414455e-05,
416
+ "loss": 0.0526,
417
+ "step": 48
418
+ },
419
+ {
420
+ "epoch": 0.593939393939394,
421
+ "grad_norm": 0.027898119762539864,
422
+ "learning_rate": 9.98840691294159e-05,
423
+ "loss": 0.0447,
424
+ "step": 49
425
+ },
426
+ {
427
+ "epoch": 0.6060606060606061,
428
+ "grad_norm": 0.03219461813569069,
429
+ "learning_rate": 9.985329005918702e-05,
430
+ "loss": 0.0459,
431
+ "step": 50
432
+ },
433
+ {
434
+ "epoch": 0.6060606060606061,
435
+ "eval_loss": 0.045825447887182236,
436
+ "eval_runtime": 6.1916,
437
+ "eval_samples_per_second": 8.075,
438
+ "eval_steps_per_second": 2.1,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.6181818181818182,
443
+ "grad_norm": 0.02641221322119236,
444
+ "learning_rate": 9.981889740445958e-05,
445
+ "loss": 0.0417,
446
+ "step": 51
447
+ },
448
+ {
449
+ "epoch": 0.6303030303030303,
450
+ "grad_norm": 0.028501464053988457,
451
+ "learning_rate": 9.978089365816357e-05,
452
+ "loss": 0.0446,
453
+ "step": 52
454
+ },
455
+ {
456
+ "epoch": 0.6424242424242425,
457
+ "grad_norm": 0.0260939784348011,
458
+ "learning_rate": 9.973928157497674e-05,
459
+ "loss": 0.0451,
460
+ "step": 53
461
+ },
462
+ {
463
+ "epoch": 0.6545454545454545,
464
+ "grad_norm": 0.029564740136265755,
465
+ "learning_rate": 9.969406417112489e-05,
466
+ "loss": 0.0416,
467
+ "step": 54
468
+ },
469
+ {
470
+ "epoch": 0.6666666666666666,
471
+ "grad_norm": 0.027353042736649513,
472
+ "learning_rate": 9.964524472416319e-05,
473
+ "loss": 0.0363,
474
+ "step": 55
475
+ },
476
+ {
477
+ "epoch": 0.6666666666666666,
478
+ "eval_loss": 0.0433911457657814,
479
+ "eval_runtime": 6.2376,
480
+ "eval_samples_per_second": 8.016,
481
+ "eval_steps_per_second": 2.084,
482
+ "step": 55
483
+ },
484
+ {
485
+ "epoch": 0.6787878787878788,
486
+ "grad_norm": 0.03154386952519417,
487
+ "learning_rate": 9.95928267727387e-05,
488
+ "loss": 0.0457,
489
+ "step": 56
490
+ },
491
+ {
492
+ "epoch": 0.6909090909090909,
493
+ "grad_norm": 0.0249126385897398,
494
+ "learning_rate": 9.953681411633376e-05,
495
+ "loss": 0.0367,
496
+ "step": 57
497
+ },
498
+ {
499
+ "epoch": 0.703030303030303,
500
+ "grad_norm": 0.02522316575050354,
501
+ "learning_rate": 9.947721081499068e-05,
502
+ "loss": 0.0428,
503
+ "step": 58
504
+ },
505
+ {
506
+ "epoch": 0.7151515151515152,
507
+ "grad_norm": 0.028446340933442116,
508
+ "learning_rate": 9.941402118901744e-05,
509
+ "loss": 0.0456,
510
+ "step": 59
511
+ },
512
+ {
513
+ "epoch": 0.7272727272727273,
514
+ "grad_norm": 0.0324234701693058,
515
+ "learning_rate": 9.934724981867446e-05,
516
+ "loss": 0.0553,
517
+ "step": 60
518
+ },
519
+ {
520
+ "epoch": 0.7272727272727273,
521
+ "eval_loss": 0.04182567819952965,
522
+ "eval_runtime": 6.2053,
523
+ "eval_samples_per_second": 8.058,
524
+ "eval_steps_per_second": 2.095,
525
+ "step": 60
526
+ },
527
+ {
528
+ "epoch": 0.7393939393939394,
529
+ "grad_norm": 0.027509605512022972,
530
+ "learning_rate": 9.927690154384273e-05,
531
+ "loss": 0.0443,
532
+ "step": 61
533
+ },
534
+ {
535
+ "epoch": 0.7515151515151515,
536
+ "grad_norm": 0.025798741728067398,
537
+ "learning_rate": 9.920298146367286e-05,
538
+ "loss": 0.0423,
539
+ "step": 62
540
+ },
541
+ {
542
+ "epoch": 0.7636363636363637,
543
+ "grad_norm": 0.029940692707896233,
544
+ "learning_rate": 9.912549493621554e-05,
545
+ "loss": 0.0469,
546
+ "step": 63
547
+ },
548
+ {
549
+ "epoch": 0.7757575757575758,
550
+ "grad_norm": 0.032555170357227325,
551
+ "learning_rate": 9.904444757803321e-05,
552
+ "loss": 0.0428,
553
+ "step": 64
554
+ },
555
+ {
556
+ "epoch": 0.7878787878787878,
557
+ "grad_norm": 0.03051156736910343,
558
+ "learning_rate": 9.895984526379281e-05,
559
+ "loss": 0.0444,
560
+ "step": 65
561
+ },
562
+ {
563
+ "epoch": 0.7878787878787878,
564
+ "eval_loss": 0.0403163880109787,
565
+ "eval_runtime": 6.1935,
566
+ "eval_samples_per_second": 8.073,
567
+ "eval_steps_per_second": 2.099,
568
+ "step": 65
569
+ },
570
+ {
571
+ "epoch": 0.8,
572
+ "grad_norm": 0.02734997309744358,
573
+ "learning_rate": 9.887169412584011e-05,
574
+ "loss": 0.0389,
575
+ "step": 66
576
+ },
577
+ {
578
+ "epoch": 0.8121212121212121,
579
+ "grad_norm": 0.026902060955762863,
580
+ "learning_rate": 9.878000055375512e-05,
581
+ "loss": 0.0397,
582
+ "step": 67
583
+ },
584
+ {
585
+ "epoch": 0.8242424242424242,
586
+ "grad_norm": 0.03240904584527016,
587
+ "learning_rate": 9.868477119388896e-05,
588
+ "loss": 0.0387,
589
+ "step": 68
590
+ },
591
+ {
592
+ "epoch": 0.8363636363636363,
593
+ "grad_norm": 0.02606021985411644,
594
+ "learning_rate": 9.858601294888213e-05,
595
+ "loss": 0.0344,
596
+ "step": 69
597
+ },
598
+ {
599
+ "epoch": 0.8484848484848485,
600
+ "grad_norm": 0.029814746230840683,
601
+ "learning_rate": 9.848373297716414e-05,
602
+ "loss": 0.0469,
603
+ "step": 70
604
+ },
605
+ {
606
+ "epoch": 0.8484848484848485,
607
+ "eval_loss": 0.03973233327269554,
608
+ "eval_runtime": 6.2308,
609
+ "eval_samples_per_second": 8.025,
610
+ "eval_steps_per_second": 2.086,
611
+ "step": 70
612
+ },
613
+ {
614
+ "epoch": 0.8606060606060606,
615
+ "grad_norm": 0.025392569601535797,
616
+ "learning_rate": 9.837793869243468e-05,
617
+ "loss": 0.0388,
618
+ "step": 71
619
+ },
620
+ {
621
+ "epoch": 0.8727272727272727,
622
+ "grad_norm": 0.03046100027859211,
623
+ "learning_rate": 9.82686377631262e-05,
624
+ "loss": 0.0415,
625
+ "step": 72
626
+ },
627
+ {
628
+ "epoch": 0.8848484848484849,
629
+ "grad_norm": 0.02428356185555458,
630
+ "learning_rate": 9.815583811184808e-05,
631
+ "loss": 0.037,
632
+ "step": 73
633
+ },
634
+ {
635
+ "epoch": 0.896969696969697,
636
+ "grad_norm": 0.029197214171290398,
637
+ "learning_rate": 9.803954791481239e-05,
638
+ "loss": 0.0408,
639
+ "step": 74
640
+ },
641
+ {
642
+ "epoch": 0.9090909090909091,
643
+ "grad_norm": 0.027502721175551414,
644
+ "learning_rate": 9.791977560124119e-05,
645
+ "loss": 0.0417,
646
+ "step": 75
647
+ },
648
+ {
649
+ "epoch": 0.9090909090909091,
650
+ "eval_loss": 0.038558006286621094,
651
+ "eval_runtime": 6.2,
652
+ "eval_samples_per_second": 8.065,
653
+ "eval_steps_per_second": 2.097,
654
+ "step": 75
655
+ },
656
+ {
657
+ "epoch": 0.9212121212121213,
658
+ "grad_norm": 0.030016757547855377,
659
+ "learning_rate": 9.779652985275562e-05,
660
+ "loss": 0.0427,
661
+ "step": 76
662
+ },
663
+ {
664
+ "epoch": 0.9333333333333333,
665
+ "grad_norm": 0.029366502538323402,
666
+ "learning_rate": 9.766981960274653e-05,
667
+ "loss": 0.0312,
668
+ "step": 77
669
+ },
670
+ {
671
+ "epoch": 0.9454545454545454,
672
+ "grad_norm": 0.02805924229323864,
673
+ "learning_rate": 9.753965403572703e-05,
674
+ "loss": 0.0424,
675
+ "step": 78
676
+ },
677
+ {
678
+ "epoch": 0.9575757575757575,
679
+ "grad_norm": 0.027496378868818283,
680
+ "learning_rate": 9.740604258666668e-05,
681
+ "loss": 0.0368,
682
+ "step": 79
683
+ },
684
+ {
685
+ "epoch": 0.9696969696969697,
686
+ "grad_norm": 0.02711924910545349,
687
+ "learning_rate": 9.726899494030768e-05,
688
+ "loss": 0.0388,
689
+ "step": 80
690
+ },
691
+ {
692
+ "epoch": 0.9696969696969697,
693
+ "eval_loss": 0.037164073437452316,
694
+ "eval_runtime": 6.2151,
695
+ "eval_samples_per_second": 8.045,
696
+ "eval_steps_per_second": 2.092,
697
+ "step": 80
698
+ },
699
+ {
700
+ "epoch": 0.9818181818181818,
701
+ "grad_norm": 0.02877042628824711,
702
+ "learning_rate": 9.71285210304628e-05,
703
+ "loss": 0.0367,
704
+ "step": 81
705
+ },
706
+ {
707
+ "epoch": 0.9939393939393939,
708
+ "grad_norm": 0.029804140329360962,
709
+ "learning_rate": 9.698463103929542e-05,
710
+ "loss": 0.0399,
711
+ "step": 82
712
+ },
713
+ {
714
+ "epoch": 1.006060606060606,
715
+ "grad_norm": 0.04405470937490463,
716
+ "learning_rate": 9.683733539658139e-05,
717
+ "loss": 0.0545,
718
+ "step": 83
719
+ },
720
+ {
721
+ "epoch": 1.018181818181818,
722
+ "grad_norm": 0.0315798744559288,
723
+ "learning_rate": 9.66866447789531e-05,
724
+ "loss": 0.048,
725
+ "step": 84
726
+ },
727
+ {
728
+ "epoch": 1.0303030303030303,
729
+ "grad_norm": 0.02551027573645115,
730
+ "learning_rate": 9.653257010912559e-05,
731
+ "loss": 0.0309,
732
+ "step": 85
733
+ },
734
+ {
735
+ "epoch": 1.0303030303030303,
736
+ "eval_loss": 0.03581343591213226,
737
+ "eval_runtime": 6.2558,
738
+ "eval_samples_per_second": 7.993,
739
+ "eval_steps_per_second": 2.078,
740
+ "step": 85
741
+ },
742
+ {
743
+ "epoch": 1.0424242424242425,
744
+ "grad_norm": 0.03550685569643974,
745
+ "learning_rate": 9.637512255510475e-05,
746
+ "loss": 0.0659,
747
+ "step": 86
748
+ },
749
+ {
750
+ "epoch": 1.0545454545454545,
751
+ "grad_norm": 0.03085348755121231,
752
+ "learning_rate": 9.621431352937789e-05,
753
+ "loss": 0.0502,
754
+ "step": 87
755
+ },
756
+ {
757
+ "epoch": 1.0666666666666667,
758
+ "grad_norm": 0.02470513805747032,
759
+ "learning_rate": 9.605015468808651e-05,
760
+ "loss": 0.0318,
761
+ "step": 88
762
+ },
763
+ {
764
+ "epoch": 1.0787878787878789,
765
+ "grad_norm": 0.02803831174969673,
766
+ "learning_rate": 9.58826579301814e-05,
767
+ "loss": 0.0446,
768
+ "step": 89
769
+ },
770
+ {
771
+ "epoch": 1.0909090909090908,
772
+ "grad_norm": 0.03941066190600395,
773
+ "learning_rate": 9.571183539656011e-05,
774
+ "loss": 0.0487,
775
+ "step": 90
776
+ },
777
+ {
778
+ "epoch": 1.0909090909090908,
779
+ "eval_loss": 0.0354202575981617,
780
+ "eval_runtime": 6.1921,
781
+ "eval_samples_per_second": 8.075,
782
+ "eval_steps_per_second": 2.099,
783
+ "step": 90
784
+ },
785
+ {
786
+ "epoch": 1.103030303030303,
787
+ "grad_norm": 0.029008885845541954,
788
+ "learning_rate": 9.553769946918697e-05,
789
+ "loss": 0.0403,
790
+ "step": 91
791
+ },
792
+ {
793
+ "epoch": 1.1151515151515152,
794
+ "grad_norm": 0.025633882731199265,
795
+ "learning_rate": 9.536026277019561e-05,
796
+ "loss": 0.032,
797
+ "step": 92
798
+ },
799
+ {
800
+ "epoch": 1.1272727272727272,
801
+ "grad_norm": 0.02955947443842888,
802
+ "learning_rate": 9.517953816097396e-05,
803
+ "loss": 0.0366,
804
+ "step": 93
805
+ },
806
+ {
807
+ "epoch": 1.1393939393939394,
808
+ "grad_norm": 0.029836708679795265,
809
+ "learning_rate": 9.499553874123212e-05,
810
+ "loss": 0.0383,
811
+ "step": 94
812
+ },
813
+ {
814
+ "epoch": 1.1515151515151516,
815
+ "grad_norm": 0.030258659273386,
816
+ "learning_rate": 9.480827784805278e-05,
817
+ "loss": 0.0348,
818
+ "step": 95
819
+ },
820
+ {
821
+ "epoch": 1.1515151515151516,
822
+ "eval_loss": 0.034031517803668976,
823
+ "eval_runtime": 6.1911,
824
+ "eval_samples_per_second": 8.076,
825
+ "eval_steps_per_second": 2.1,
826
+ "step": 95
827
+ },
828
+ {
829
+ "epoch": 1.1636363636363636,
830
+ "grad_norm": 0.02571636624634266,
831
+ "learning_rate": 9.461776905492446e-05,
832
+ "loss": 0.0322,
833
+ "step": 96
834
+ },
835
+ {
836
+ "epoch": 1.1757575757575758,
837
+ "grad_norm": 0.025425300002098083,
838
+ "learning_rate": 9.442402617075765e-05,
839
+ "loss": 0.0302,
840
+ "step": 97
841
+ },
842
+ {
843
+ "epoch": 1.187878787878788,
844
+ "grad_norm": 0.02790471538901329,
845
+ "learning_rate": 9.422706323888397e-05,
846
+ "loss": 0.0305,
847
+ "step": 98
848
+ },
849
+ {
850
+ "epoch": 1.2,
851
+ "grad_norm": 0.031999390572309494,
852
+ "learning_rate": 9.402689453603815e-05,
853
+ "loss": 0.0384,
854
+ "step": 99
855
+ },
856
+ {
857
+ "epoch": 1.2121212121212122,
858
+ "grad_norm": 0.02810075506567955,
859
+ "learning_rate": 9.382353457132317e-05,
860
+ "loss": 0.0308,
861
+ "step": 100
862
+ },
863
+ {
864
+ "epoch": 1.2121212121212122,
865
+ "eval_loss": 0.03338392823934555,
866
+ "eval_runtime": 6.1917,
867
+ "eval_samples_per_second": 8.075,
868
+ "eval_steps_per_second": 2.1,
869
+ "step": 100
870
+ },
871
+ {
872
+ "epoch": 1.2242424242424241,
873
+ "grad_norm": 0.0302734412252903,
874
+ "learning_rate": 9.361699808515876e-05,
875
+ "loss": 0.0341,
876
+ "step": 101
877
+ },
878
+ {
879
+ "epoch": 1.2363636363636363,
880
+ "grad_norm": 0.033730726689100266,
881
+ "learning_rate": 9.340730004821266e-05,
882
+ "loss": 0.0346,
883
+ "step": 102
884
+ },
885
+ {
886
+ "epoch": 1.2484848484848485,
887
+ "grad_norm": 0.03323773667216301,
888
+ "learning_rate": 9.31944556603157e-05,
889
+ "loss": 0.0408,
890
+ "step": 103
891
+ },
892
+ {
893
+ "epoch": 1.2606060606060607,
894
+ "grad_norm": 0.027124911546707153,
895
+ "learning_rate": 9.297848034936006e-05,
896
+ "loss": 0.0332,
897
+ "step": 104
898
+ },
899
+ {
900
+ "epoch": 1.2727272727272727,
901
+ "grad_norm": 0.026853900402784348,
902
+ "learning_rate": 9.275938977018081e-05,
903
+ "loss": 0.0318,
904
+ "step": 105
905
+ },
906
+ {
907
+ "epoch": 1.2727272727272727,
908
+ "eval_loss": 0.03301350772380829,
909
+ "eval_runtime": 6.1968,
910
+ "eval_samples_per_second": 8.069,
911
+ "eval_steps_per_second": 2.098,
912
+ "step": 105
913
+ },
914
+ {
915
+ "epoch": 1.284848484848485,
916
+ "grad_norm": 0.027320127934217453,
917
+ "learning_rate": 9.253719980342135e-05,
918
+ "loss": 0.0339,
919
+ "step": 106
920
+ },
921
+ {
922
+ "epoch": 1.2969696969696969,
923
+ "grad_norm": 0.0313449464738369,
924
+ "learning_rate": 9.231192655438221e-05,
925
+ "loss": 0.0336,
926
+ "step": 107
927
+ },
928
+ {
929
+ "epoch": 1.309090909090909,
930
+ "grad_norm": 0.029063764959573746,
931
+ "learning_rate": 9.208358635185373e-05,
932
+ "loss": 0.0324,
933
+ "step": 108
934
+ },
935
+ {
936
+ "epoch": 1.3212121212121213,
937
+ "grad_norm": 0.03135693818330765,
938
+ "learning_rate": 9.185219574693242e-05,
939
+ "loss": 0.0332,
940
+ "step": 109
941
+ },
942
+ {
943
+ "epoch": 1.3333333333333333,
944
+ "grad_norm": 0.0317191518843174,
945
+ "learning_rate": 9.161777151182136e-05,
946
+ "loss": 0.028,
947
+ "step": 110
948
+ },
949
+ {
950
+ "epoch": 1.3333333333333333,
951
+ "eval_loss": 0.03218723088502884,
952
+ "eval_runtime": 6.2118,
953
+ "eval_samples_per_second": 8.049,
954
+ "eval_steps_per_second": 2.093,
955
+ "step": 110
956
+ },
957
+ {
958
+ "epoch": 1.3454545454545455,
959
+ "grad_norm": 0.031457044184207916,
960
+ "learning_rate": 9.138033063861436e-05,
961
+ "loss": 0.0346,
962
+ "step": 111
963
+ },
964
+ {
965
+ "epoch": 1.3575757575757577,
966
+ "grad_norm": 0.031810589134693146,
967
+ "learning_rate": 9.113989033806434e-05,
968
+ "loss": 0.0283,
969
+ "step": 112
970
+ },
971
+ {
972
+ "epoch": 1.3696969696969696,
973
+ "grad_norm": 0.030629124492406845,
974
+ "learning_rate": 9.089646803833589e-05,
975
+ "loss": 0.0246,
976
+ "step": 113
977
+ },
978
+ {
979
+ "epoch": 1.3818181818181818,
980
+ "grad_norm": 0.030411459505558014,
981
+ "learning_rate": 9.065008138374189e-05,
982
+ "loss": 0.0317,
983
+ "step": 114
984
+ },
985
+ {
986
+ "epoch": 1.393939393939394,
987
+ "grad_norm": 0.029815878719091415,
988
+ "learning_rate": 9.040074823346465e-05,
989
+ "loss": 0.0311,
990
+ "step": 115
991
+ },
992
+ {
993
+ "epoch": 1.393939393939394,
994
+ "eval_loss": 0.032092493027448654,
995
+ "eval_runtime": 6.1885,
996
+ "eval_samples_per_second": 8.08,
997
+ "eval_steps_per_second": 2.101,
998
+ "step": 115
999
+ },
1000
+ {
1001
+ "epoch": 1.406060606060606,
1002
+ "grad_norm": 0.030812319368124008,
1003
+ "learning_rate": 9.014848666026138e-05,
1004
+ "loss": 0.0389,
1005
+ "step": 116
1006
+ },
1007
+ {
1008
+ "epoch": 1.4181818181818182,
1009
+ "grad_norm": 0.02588343806564808,
1010
+ "learning_rate": 8.989331494915417e-05,
1011
+ "loss": 0.0287,
1012
+ "step": 117
1013
+ },
1014
+ {
1015
+ "epoch": 1.4303030303030302,
1016
+ "grad_norm": 0.02780727669596672,
1017
+ "learning_rate": 8.963525159610465e-05,
1018
+ "loss": 0.0265,
1019
+ "step": 118
1020
+ },
1021
+ {
1022
+ "epoch": 1.4424242424242424,
1023
+ "grad_norm": 0.026163380593061447,
1024
+ "learning_rate": 8.937431530667328e-05,
1025
+ "loss": 0.0262,
1026
+ "step": 119
1027
+ },
1028
+ {
1029
+ "epoch": 1.4545454545454546,
1030
+ "grad_norm": 0.0316736213862896,
1031
+ "learning_rate": 8.911052499466357e-05,
1032
+ "loss": 0.0382,
1033
+ "step": 120
1034
+ },
1035
+ {
1036
+ "epoch": 1.4545454545454546,
1037
+ "eval_loss": 0.031465690582990646,
1038
+ "eval_runtime": 6.1922,
1039
+ "eval_samples_per_second": 8.075,
1040
+ "eval_steps_per_second": 2.099,
1041
+ "step": 120
1042
+ },
1043
+ {
1044
+ "epoch": 1.4666666666666668,
1045
+ "grad_norm": 0.03706022724509239,
1046
+ "learning_rate": 8.884389978075098e-05,
1047
+ "loss": 0.0336,
1048
+ "step": 121
1049
+ },
1050
+ {
1051
+ "epoch": 1.4787878787878788,
1052
+ "grad_norm": 0.027684392407536507,
1053
+ "learning_rate": 8.857445899109715e-05,
1054
+ "loss": 0.0267,
1055
+ "step": 122
1056
+ },
1057
+ {
1058
+ "epoch": 1.490909090909091,
1059
+ "grad_norm": 0.02498454973101616,
1060
+ "learning_rate": 8.83022221559489e-05,
1061
+ "loss": 0.0258,
1062
+ "step": 123
1063
+ },
1064
+ {
1065
+ "epoch": 1.503030303030303,
1066
+ "grad_norm": 0.03206618130207062,
1067
+ "learning_rate": 8.80272090082227e-05,
1068
+ "loss": 0.0344,
1069
+ "step": 124
1070
+ },
1071
+ {
1072
+ "epoch": 1.5151515151515151,
1073
+ "grad_norm": 0.03329097852110863,
1074
+ "learning_rate": 8.774943948207426e-05,
1075
+ "loss": 0.0316,
1076
+ "step": 125
1077
+ },
1078
+ {
1079
+ "epoch": 1.5151515151515151,
1080
+ "eval_loss": 0.030392121523618698,
1081
+ "eval_runtime": 6.2076,
1082
+ "eval_samples_per_second": 8.055,
1083
+ "eval_steps_per_second": 2.094,
1084
+ "step": 125
1085
+ },
1086
+ {
1087
+ "epoch": 1.5272727272727273,
1088
+ "grad_norm": 0.029471345245838165,
1089
+ "learning_rate": 8.746893371145366e-05,
1090
+ "loss": 0.0279,
1091
+ "step": 126
1092
+ },
1093
+ {
1094
+ "epoch": 1.5393939393939395,
1095
+ "grad_norm": 0.030292104929685593,
1096
+ "learning_rate": 8.718571202864598e-05,
1097
+ "loss": 0.0292,
1098
+ "step": 127
1099
+ },
1100
+ {
1101
+ "epoch": 1.5515151515151515,
1102
+ "grad_norm": 0.028025031089782715,
1103
+ "learning_rate": 8.689979496279746e-05,
1104
+ "loss": 0.0296,
1105
+ "step": 128
1106
+ },
1107
+ {
1108
+ "epoch": 1.5636363636363635,
1109
+ "grad_norm": 0.027177123352885246,
1110
+ "learning_rate": 8.661120323842751e-05,
1111
+ "loss": 0.0286,
1112
+ "step": 129
1113
+ },
1114
+ {
1115
+ "epoch": 1.5757575757575757,
1116
+ "grad_norm": 0.03291260078549385,
1117
+ "learning_rate": 8.631995777392645e-05,
1118
+ "loss": 0.0278,
1119
+ "step": 130
1120
+ },
1121
+ {
1122
+ "epoch": 1.5757575757575757,
1123
+ "eval_loss": 0.029901880770921707,
1124
+ "eval_runtime": 6.1931,
1125
+ "eval_samples_per_second": 8.073,
1126
+ "eval_steps_per_second": 2.099,
1127
+ "step": 130
1128
+ },
1129
+ {
1130
+ "epoch": 1.587878787878788,
1131
+ "grad_norm": 0.027456866577267647,
1132
+ "learning_rate": 8.602607968003935e-05,
1133
+ "loss": 0.0277,
1134
+ "step": 131
1135
+ },
1136
+ {
1137
+ "epoch": 1.6,
1138
+ "grad_norm": 0.02367628738284111,
1139
+ "learning_rate": 8.572959025833573e-05,
1140
+ "loss": 0.023,
1141
+ "step": 132
1142
+ },
1143
+ {
1144
+ "epoch": 1.612121212121212,
1145
+ "grad_norm": 0.030250705778598785,
1146
+ "learning_rate": 8.543051099966558e-05,
1147
+ "loss": 0.0253,
1148
+ "step": 133
1149
+ },
1150
+ {
1151
+ "epoch": 1.6242424242424243,
1152
+ "grad_norm": 0.02687668427824974,
1153
+ "learning_rate": 8.512886358260162e-05,
1154
+ "loss": 0.0249,
1155
+ "step": 134
1156
+ },
1157
+ {
1158
+ "epoch": 1.6363636363636362,
1159
+ "grad_norm": 0.032938696444034576,
1160
+ "learning_rate": 8.482466987186785e-05,
1161
+ "loss": 0.0285,
1162
+ "step": 135
1163
+ },
1164
+ {
1165
+ "epoch": 1.6363636363636362,
1166
+ "eval_loss": 0.029229959473013878,
1167
+ "eval_runtime": 6.1897,
1168
+ "eval_samples_per_second": 8.078,
1169
+ "eval_steps_per_second": 2.1,
1170
+ "step": 135
1171
+ },
1172
+ {
1173
+ "epoch": 1.6484848484848484,
1174
+ "grad_norm": 0.02894946001470089,
1175
+ "learning_rate": 8.451795191675488e-05,
1176
+ "loss": 0.0268,
1177
+ "step": 136
1178
+ },
1179
+ {
1180
+ "epoch": 1.6606060606060606,
1181
+ "grad_norm": 0.03599061071872711,
1182
+ "learning_rate": 8.420873194952152e-05,
1183
+ "loss": 0.0351,
1184
+ "step": 137
1185
+ },
1186
+ {
1187
+ "epoch": 1.6727272727272728,
1188
+ "grad_norm": 0.031365521252155304,
1189
+ "learning_rate": 8.389703238378339e-05,
1190
+ "loss": 0.0309,
1191
+ "step": 138
1192
+ },
1193
+ {
1194
+ "epoch": 1.6848484848484848,
1195
+ "grad_norm": 0.024763284251093864,
1196
+ "learning_rate": 8.358287581288822e-05,
1197
+ "loss": 0.0244,
1198
+ "step": 139
1199
+ },
1200
+ {
1201
+ "epoch": 1.696969696969697,
1202
+ "grad_norm": 0.026635024696588516,
1203
+ "learning_rate": 8.326628500827826e-05,
1204
+ "loss": 0.0257,
1205
+ "step": 140
1206
+ },
1207
+ {
1208
+ "epoch": 1.696969696969697,
1209
+ "eval_loss": 0.02854442596435547,
1210
+ "eval_runtime": 6.2016,
1211
+ "eval_samples_per_second": 8.062,
1212
+ "eval_steps_per_second": 2.096,
1213
+ "step": 140
1214
+ },
1215
+ {
1216
+ "epoch": 1.709090909090909,
1217
+ "grad_norm": 0.03084694594144821,
1218
+ "learning_rate": 8.294728291783966e-05,
1219
+ "loss": 0.0301,
1220
+ "step": 141
1221
+ },
1222
+ {
1223
+ "epoch": 1.7212121212121212,
1224
+ "grad_norm": 0.024888882413506508,
1225
+ "learning_rate": 8.262589266423908e-05,
1226
+ "loss": 0.0254,
1227
+ "step": 142
1228
+ },
1229
+ {
1230
+ "epoch": 1.7333333333333334,
1231
+ "grad_norm": 0.02867315709590912,
1232
+ "learning_rate": 8.230213754324773e-05,
1233
+ "loss": 0.0338,
1234
+ "step": 143
1235
+ },
1236
+ {
1237
+ "epoch": 1.7454545454545456,
1238
+ "grad_norm": 0.030578091740608215,
1239
+ "learning_rate": 8.197604102205271e-05,
1240
+ "loss": 0.0265,
1241
+ "step": 144
1242
+ },
1243
+ {
1244
+ "epoch": 1.7575757575757576,
1245
+ "grad_norm": 0.025194313377141953,
1246
+ "learning_rate": 8.16476267375561e-05,
1247
+ "loss": 0.0244,
1248
+ "step": 145
1249
+ },
1250
+ {
1251
+ "epoch": 1.7575757575757576,
1252
+ "eval_loss": 0.028112677857279778,
1253
+ "eval_runtime": 6.1903,
1254
+ "eval_samples_per_second": 8.077,
1255
+ "eval_steps_per_second": 2.1,
1256
+ "step": 145
1257
+ },
1258
+ {
1259
+ "epoch": 1.7696969696969695,
1260
+ "grad_norm": 0.03511481732130051,
1261
+ "learning_rate": 8.131691849466153e-05,
1262
+ "loss": 0.0351,
1263
+ "step": 146
1264
+ },
1265
+ {
1266
+ "epoch": 1.7818181818181817,
1267
+ "grad_norm": 0.034265320748090744,
1268
+ "learning_rate": 8.098394026454885e-05,
1269
+ "loss": 0.0318,
1270
+ "step": 147
1271
+ },
1272
+ {
1273
+ "epoch": 1.793939393939394,
1274
+ "grad_norm": 0.02798490971326828,
1275
+ "learning_rate": 8.064871618293646e-05,
1276
+ "loss": 0.0258,
1277
+ "step": 148
1278
+ },
1279
+ {
1280
+ "epoch": 1.8060606060606061,
1281
+ "grad_norm": 0.031277846544981,
1282
+ "learning_rate": 8.03112705483319e-05,
1283
+ "loss": 0.0322,
1284
+ "step": 149
1285
+ },
1286
+ {
1287
+ "epoch": 1.8181818181818183,
1288
+ "grad_norm": 0.025352105498313904,
1289
+ "learning_rate": 7.997162782027061e-05,
1290
+ "loss": 0.0256,
1291
+ "step": 150
1292
+ },
1293
+ {
1294
+ "epoch": 1.8181818181818183,
1295
+ "eval_loss": 0.027805332094430923,
1296
+ "eval_runtime": 6.1948,
1297
+ "eval_samples_per_second": 8.071,
1298
+ "eval_steps_per_second": 2.099,
1299
+ "step": 150
1300
+ },
1301
+ {
1302
+ "epoch": 1.8303030303030303,
1303
+ "grad_norm": 0.03179726377129555,
1304
+ "learning_rate": 7.962981261754294e-05,
1305
+ "loss": 0.0265,
1306
+ "step": 151
1307
+ },
1308
+ {
1309
+ "epoch": 1.8424242424242423,
1310
+ "grad_norm": 0.02985468879342079,
1311
+ "learning_rate": 7.928584971640974e-05,
1312
+ "loss": 0.0302,
1313
+ "step": 152
1314
+ },
1315
+ {
1316
+ "epoch": 1.8545454545454545,
1317
+ "grad_norm": 0.031871821731328964,
1318
+ "learning_rate": 7.893976404880643e-05,
1319
+ "loss": 0.0331,
1320
+ "step": 153
1321
+ },
1322
+ {
1323
+ "epoch": 1.8666666666666667,
1324
+ "grad_norm": 0.028416186571121216,
1325
+ "learning_rate": 7.859158070053577e-05,
1326
+ "loss": 0.0245,
1327
+ "step": 154
1328
+ },
1329
+ {
1330
+ "epoch": 1.878787878787879,
1331
+ "grad_norm": 0.03054559975862503,
1332
+ "learning_rate": 7.824132490944967e-05,
1333
+ "loss": 0.0338,
1334
+ "step": 155
1335
+ },
1336
+ {
1337
+ "epoch": 1.878787878787879,
1338
+ "eval_loss": 0.027029650285840034,
1339
+ "eval_runtime": 6.235,
1340
+ "eval_samples_per_second": 8.019,
1341
+ "eval_steps_per_second": 2.085,
1342
+ "step": 155
1343
+ },
1344
+ {
1345
+ "epoch": 1.8909090909090909,
1346
+ "grad_norm": 0.028330031782388687,
1347
+ "learning_rate": 7.788902206361973e-05,
1348
+ "loss": 0.0241,
1349
+ "step": 156
1350
+ },
1351
+ {
1352
+ "epoch": 1.903030303030303,
1353
+ "grad_norm": 0.031616389751434326,
1354
+ "learning_rate": 7.7534697699497e-05,
1355
+ "loss": 0.0301,
1356
+ "step": 157
1357
+ },
1358
+ {
1359
+ "epoch": 1.915151515151515,
1360
+ "grad_norm": 0.027048081159591675,
1361
+ "learning_rate": 7.717837750006106e-05,
1362
+ "loss": 0.0274,
1363
+ "step": 158
1364
+ },
1365
+ {
1366
+ "epoch": 1.9272727272727272,
1367
+ "grad_norm": 0.028316281735897064,
1368
+ "learning_rate": 7.682008729295833e-05,
1369
+ "loss": 0.026,
1370
+ "step": 159
1371
+ },
1372
+ {
1373
+ "epoch": 1.9393939393939394,
1374
+ "grad_norm": 0.02987455017864704,
1375
+ "learning_rate": 7.645985304863003e-05,
1376
+ "loss": 0.0309,
1377
+ "step": 160
1378
+ },
1379
+ {
1380
+ "epoch": 1.9393939393939394,
1381
+ "eval_loss": 0.02624826692044735,
1382
+ "eval_runtime": 6.1867,
1383
+ "eval_samples_per_second": 8.082,
1384
+ "eval_steps_per_second": 2.101,
1385
+ "step": 160
1386
+ },
1387
+ {
1388
+ "epoch": 1.9515151515151516,
1389
+ "grad_norm": 0.02562532387673855,
1390
+ "learning_rate": 7.609770087842969e-05,
1391
+ "loss": 0.0275,
1392
+ "step": 161
1393
+ },
1394
+ {
1395
+ "epoch": 1.9636363636363636,
1396
+ "grad_norm": 0.026776108890771866,
1397
+ "learning_rate": 7.573365703273046e-05,
1398
+ "loss": 0.0263,
1399
+ "step": 162
1400
+ },
1401
+ {
1402
+ "epoch": 1.9757575757575756,
1403
+ "grad_norm": 0.031301844865083694,
1404
+ "learning_rate": 7.536774789902246e-05,
1405
+ "loss": 0.0293,
1406
+ "step": 163
1407
+ },
1408
+ {
1409
+ "epoch": 1.9878787878787878,
1410
+ "grad_norm": 0.02761393040418625,
1411
+ "learning_rate": 7.500000000000001e-05,
1412
+ "loss": 0.0292,
1413
+ "step": 164
1414
+ },
1415
+ {
1416
+ "epoch": 2.0,
1417
+ "grad_norm": 0.04325617477297783,
1418
+ "learning_rate": 7.463043999163919e-05,
1419
+ "loss": 0.0378,
1420
+ "step": 165
1421
+ },
1422
+ {
1423
+ "epoch": 2.0,
1424
+ "eval_loss": 0.02608395926654339,
1425
+ "eval_runtime": 6.2208,
1426
+ "eval_samples_per_second": 8.038,
1427
+ "eval_steps_per_second": 2.09,
1428
+ "step": 165
1429
+ },
1430
+ {
1431
+ "epoch": 2.012121212121212,
1432
+ "grad_norm": 0.026866400614380836,
1433
+ "learning_rate": 7.425909466126568e-05,
1434
+ "loss": 0.024,
1435
+ "step": 166
1436
+ },
1437
+ {
1438
+ "epoch": 2.0242424242424244,
1439
+ "grad_norm": 0.026734622195363045,
1440
+ "learning_rate": 7.388599092561315e-05,
1441
+ "loss": 0.0238,
1442
+ "step": 167
1443
+ },
1444
+ {
1445
+ "epoch": 2.036363636363636,
1446
+ "grad_norm": 0.02514388971030712,
1447
+ "learning_rate": 7.351115582887211e-05,
1448
+ "loss": 0.0218,
1449
+ "step": 168
1450
+ },
1451
+ {
1452
+ "epoch": 2.0484848484848484,
1453
+ "grad_norm": 0.02405986562371254,
1454
+ "learning_rate": 7.313461654072973e-05,
1455
+ "loss": 0.0199,
1456
+ "step": 169
1457
+ },
1458
+ {
1459
+ "epoch": 2.0606060606060606,
1460
+ "grad_norm": 0.030505580827593803,
1461
+ "learning_rate": 7.275640035440045e-05,
1462
+ "loss": 0.0275,
1463
+ "step": 170
1464
+ },
1465
+ {
1466
+ "epoch": 2.0606060606060606,
1467
+ "eval_loss": 0.026318900287151337,
1468
+ "eval_runtime": 6.2393,
1469
+ "eval_samples_per_second": 8.014,
1470
+ "eval_steps_per_second": 2.084,
1471
+ "step": 170
1472
+ },
1473
+ {
1474
+ "epoch": 2.0727272727272728,
1475
+ "grad_norm": 0.03722088038921356,
1476
+ "learning_rate": 7.237653468464756e-05,
1477
+ "loss": 0.0256,
1478
+ "step": 171
1479
+ },
1480
+ {
1481
+ "epoch": 2.084848484848485,
1482
+ "grad_norm": 0.03724412992596626,
1483
+ "learning_rate": 7.199504706579617e-05,
1484
+ "loss": 0.0226,
1485
+ "step": 172
1486
+ },
1487
+ {
1488
+ "epoch": 2.096969696969697,
1489
+ "grad_norm": 0.030355574563145638,
1490
+ "learning_rate": 7.161196514973734e-05,
1491
+ "loss": 0.0188,
1492
+ "step": 173
1493
+ },
1494
+ {
1495
+ "epoch": 2.109090909090909,
1496
+ "grad_norm": 0.03693992272019386,
1497
+ "learning_rate": 7.12273167039238e-05,
1498
+ "loss": 0.0232,
1499
+ "step": 174
1500
+ },
1501
+ {
1502
+ "epoch": 2.121212121212121,
1503
+ "grad_norm": 0.03164402395486832,
1504
+ "learning_rate": 7.084112960935716e-05,
1505
+ "loss": 0.0225,
1506
+ "step": 175
1507
+ },
1508
+ {
1509
+ "epoch": 2.121212121212121,
1510
+ "eval_loss": 0.025883661583065987,
1511
+ "eval_runtime": 6.2414,
1512
+ "eval_samples_per_second": 8.011,
1513
+ "eval_steps_per_second": 2.083,
1514
+ "step": 175
1515
+ },
1516
+ {
1517
+ "epoch": 2.1333333333333333,
1518
+ "grad_norm": 0.031605158001184464,
1519
+ "learning_rate": 7.045343185856701e-05,
1520
+ "loss": 0.0248,
1521
+ "step": 176
1522
+ },
1523
+ {
1524
+ "epoch": 2.1454545454545455,
1525
+ "grad_norm": 0.0310862734913826,
1526
+ "learning_rate": 7.006425155358195e-05,
1527
+ "loss": 0.0244,
1528
+ "step": 177
1529
+ },
1530
+ {
1531
+ "epoch": 2.1575757575757577,
1532
+ "grad_norm": 0.031485848128795624,
1533
+ "learning_rate": 6.967361690389258e-05,
1534
+ "loss": 0.0242,
1535
+ "step": 178
1536
+ },
1537
+ {
1538
+ "epoch": 2.16969696969697,
1539
+ "grad_norm": 0.03367177024483681,
1540
+ "learning_rate": 6.92815562244068e-05,
1541
+ "loss": 0.0246,
1542
+ "step": 179
1543
+ },
1544
+ {
1545
+ "epoch": 2.1818181818181817,
1546
+ "grad_norm": 0.028202077373862267,
1547
+ "learning_rate": 6.88880979333973e-05,
1548
+ "loss": 0.0232,
1549
+ "step": 180
1550
+ },
1551
+ {
1552
+ "epoch": 2.1818181818181817,
1553
+ "eval_loss": 0.025616060942411423,
1554
+ "eval_runtime": 6.1872,
1555
+ "eval_samples_per_second": 8.081,
1556
+ "eval_steps_per_second": 2.101,
1557
+ "step": 180
1558
+ },
1559
+ {
1560
+ "epoch": 2.193939393939394,
1561
+ "grad_norm": 0.03502137213945389,
1562
+ "learning_rate": 6.849327055044183e-05,
1563
+ "loss": 0.0251,
1564
+ "step": 181
1565
+ },
1566
+ {
1567
+ "epoch": 2.206060606060606,
1568
+ "grad_norm": 0.029362250119447708,
1569
+ "learning_rate": 6.809710269435589e-05,
1570
+ "loss": 0.022,
1571
+ "step": 182
1572
+ },
1573
+ {
1574
+ "epoch": 2.2181818181818183,
1575
+ "grad_norm": 0.033701106905937195,
1576
+ "learning_rate": 6.769962308111839e-05,
1577
+ "loss": 0.0234,
1578
+ "step": 183
1579
+ },
1580
+ {
1581
+ "epoch": 2.2303030303030305,
1582
+ "grad_norm": 0.03379302844405174,
1583
+ "learning_rate": 6.730086052179004e-05,
1584
+ "loss": 0.0221,
1585
+ "step": 184
1586
+ },
1587
+ {
1588
+ "epoch": 2.242424242424242,
1589
+ "grad_norm": 0.027100039646029472,
1590
+ "learning_rate": 6.690084392042513e-05,
1591
+ "loss": 0.0193,
1592
+ "step": 185
1593
+ },
1594
+ {
1595
+ "epoch": 2.242424242424242,
1596
+ "eval_loss": 0.025547849014401436,
1597
+ "eval_runtime": 6.2367,
1598
+ "eval_samples_per_second": 8.017,
1599
+ "eval_steps_per_second": 2.084,
1600
+ "step": 185
1601
+ },
1602
+ {
1603
+ "epoch": 2.2545454545454544,
1604
+ "grad_norm": 0.03181413188576698,
1605
+ "learning_rate": 6.649960227197647e-05,
1606
+ "loss": 0.0217,
1607
+ "step": 186
1608
+ },
1609
+ {
1610
+ "epoch": 2.2666666666666666,
1611
+ "grad_norm": 0.03648809716105461,
1612
+ "learning_rate": 6.609716466019356e-05,
1613
+ "loss": 0.0239,
1614
+ "step": 187
1615
+ },
1616
+ {
1617
+ "epoch": 2.278787878787879,
1618
+ "grad_norm": 0.0302013847976923,
1619
+ "learning_rate": 6.569356025551454e-05,
1620
+ "loss": 0.0232,
1621
+ "step": 188
1622
+ },
1623
+ {
1624
+ "epoch": 2.290909090909091,
1625
+ "grad_norm": 0.028094977140426636,
1626
+ "learning_rate": 6.528881831295188e-05,
1627
+ "loss": 0.02,
1628
+ "step": 189
1629
+ },
1630
+ {
1631
+ "epoch": 2.303030303030303,
1632
+ "grad_norm": 0.03214862942695618,
1633
+ "learning_rate": 6.488296816997173e-05,
1634
+ "loss": 0.0251,
1635
+ "step": 190
1636
+ },
1637
+ {
1638
+ "epoch": 2.303030303030303,
1639
+ "eval_loss": 0.02527759224176407,
1640
+ "eval_runtime": 6.19,
1641
+ "eval_samples_per_second": 8.078,
1642
+ "eval_steps_per_second": 2.1,
1643
+ "step": 190
1644
+ },
1645
+ {
1646
+ "epoch": 2.315151515151515,
1647
+ "grad_norm": 0.033984988927841187,
1648
+ "learning_rate": 6.447603924436744e-05,
1649
+ "loss": 0.0243,
1650
+ "step": 191
1651
+ },
1652
+ {
1653
+ "epoch": 2.327272727272727,
1654
+ "grad_norm": 0.027719179168343544,
1655
+ "learning_rate": 6.406806103212725e-05,
1656
+ "loss": 0.0204,
1657
+ "step": 192
1658
+ },
1659
+ {
1660
+ "epoch": 2.3393939393939394,
1661
+ "grad_norm": 0.029257657006382942,
1662
+ "learning_rate": 6.36590631052963e-05,
1663
+ "loss": 0.0232,
1664
+ "step": 193
1665
+ },
1666
+ {
1667
+ "epoch": 2.3515151515151516,
1668
+ "grad_norm": 0.050508007407188416,
1669
+ "learning_rate": 6.32490751098331e-05,
1670
+ "loss": 0.0324,
1671
+ "step": 194
1672
+ },
1673
+ {
1674
+ "epoch": 2.3636363636363638,
1675
+ "grad_norm": 0.029407154768705368,
1676
+ "learning_rate": 6.283812676346063e-05,
1677
+ "loss": 0.0228,
1678
+ "step": 195
1679
+ },
1680
+ {
1681
+ "epoch": 2.3636363636363638,
1682
+ "eval_loss": 0.024870626628398895,
1683
+ "eval_runtime": 6.191,
1684
+ "eval_samples_per_second": 8.076,
1685
+ "eval_steps_per_second": 2.1,
1686
+ "step": 195
1687
+ },
1688
+ {
1689
+ "epoch": 2.375757575757576,
1690
+ "grad_norm": 0.0258539617061615,
1691
+ "learning_rate": 6.242624785351236e-05,
1692
+ "loss": 0.0231,
1693
+ "step": 196
1694
+ },
1695
+ {
1696
+ "epoch": 2.3878787878787877,
1697
+ "grad_norm": 0.02586168795824051,
1698
+ "learning_rate": 6.201346823477303e-05,
1699
+ "loss": 0.0193,
1700
+ "step": 197
1701
+ },
1702
+ {
1703
+ "epoch": 2.4,
1704
+ "grad_norm": 0.029741084203124046,
1705
+ "learning_rate": 6.159981782731474e-05,
1706
+ "loss": 0.0227,
1707
+ "step": 198
1708
+ },
1709
+ {
1710
+ "epoch": 2.412121212121212,
1711
+ "grad_norm": 0.029881663620471954,
1712
+ "learning_rate": 6.118532661432812e-05,
1713
+ "loss": 0.0224,
1714
+ "step": 199
1715
+ },
1716
+ {
1717
+ "epoch": 2.4242424242424243,
1718
+ "grad_norm": 0.027224918827414513,
1719
+ "learning_rate": 6.0770024639949074e-05,
1720
+ "loss": 0.0195,
1721
+ "step": 200
1722
+ },
1723
+ {
1724
+ "epoch": 2.4242424242424243,
1725
+ "eval_loss": 0.024939175695180893,
1726
+ "eval_runtime": 6.1942,
1727
+ "eval_samples_per_second": 8.072,
1728
+ "eval_steps_per_second": 2.099,
1729
+ "step": 200
1730
+ },
1731
+ {
1732
+ "epoch": 2.4363636363636365,
1733
+ "grad_norm": 0.028513159602880478,
1734
+ "learning_rate": 6.0353942007081046e-05,
1735
+ "loss": 0.0198,
1736
+ "step": 201
1737
+ },
1738
+ {
1739
+ "epoch": 2.4484848484848483,
1740
+ "grad_norm": 0.028778916224837303,
1741
+ "learning_rate": 5.993710887521302e-05,
1742
+ "loss": 0.0184,
1743
+ "step": 202
1744
+ },
1745
+ {
1746
+ "epoch": 2.4606060606060605,
1747
+ "grad_norm": 0.03407447412610054,
1748
+ "learning_rate": 5.951955545823342e-05,
1749
+ "loss": 0.0207,
1750
+ "step": 203
1751
+ },
1752
+ {
1753
+ "epoch": 2.4727272727272727,
1754
+ "grad_norm": 0.033413201570510864,
1755
+ "learning_rate": 5.9101312022240106e-05,
1756
+ "loss": 0.0217,
1757
+ "step": 204
1758
+ },
1759
+ {
1760
+ "epoch": 2.484848484848485,
1761
+ "grad_norm": 0.031220227479934692,
1762
+ "learning_rate": 5.868240888334653e-05,
1763
+ "loss": 0.0219,
1764
+ "step": 205
1765
+ },
1766
+ {
1767
+ "epoch": 2.484848484848485,
1768
+ "eval_loss": 0.024136777967214584,
1769
+ "eval_runtime": 6.2,
1770
+ "eval_samples_per_second": 8.065,
1771
+ "eval_steps_per_second": 2.097,
1772
+ "step": 205
1773
+ },
1774
+ {
1775
+ "epoch": 2.496969696969697,
1776
+ "grad_norm": 0.0299720149487257,
1777
+ "learning_rate": 5.826287640548425e-05,
1778
+ "loss": 0.0231,
1779
+ "step": 206
1780
+ },
1781
+ {
1782
+ "epoch": 2.509090909090909,
1783
+ "grad_norm": 0.030199084430933,
1784
+ "learning_rate": 5.784274499820214e-05,
1785
+ "loss": 0.0243,
1786
+ "step": 207
1787
+ },
1788
+ {
1789
+ "epoch": 2.5212121212121215,
1790
+ "grad_norm": 0.03225167095661163,
1791
+ "learning_rate": 5.742204511446203e-05,
1792
+ "loss": 0.0241,
1793
+ "step": 208
1794
+ },
1795
+ {
1796
+ "epoch": 2.533333333333333,
1797
+ "grad_norm": 0.02794428914785385,
1798
+ "learning_rate": 5.700080724843147e-05,
1799
+ "loss": 0.0217,
1800
+ "step": 209
1801
+ },
1802
+ {
1803
+ "epoch": 2.5454545454545454,
1804
+ "grad_norm": 0.026055919006466866,
1805
+ "learning_rate": 5.657906193327325e-05,
1806
+ "loss": 0.0184,
1807
+ "step": 210
1808
+ },
1809
+ {
1810
+ "epoch": 2.5454545454545454,
1811
+ "eval_loss": 0.023839673027396202,
1812
+ "eval_runtime": 6.1855,
1813
+ "eval_samples_per_second": 8.083,
1814
+ "eval_steps_per_second": 2.102,
1815
+ "step": 210
1816
+ },
1817
+ {
1818
+ "epoch": 2.5575757575757576,
1819
+ "grad_norm": 0.03009297326207161,
1820
+ "learning_rate": 5.6156839738932343e-05,
1821
+ "loss": 0.0233,
1822
+ "step": 211
1823
+ },
1824
+ {
1825
+ "epoch": 2.56969696969697,
1826
+ "grad_norm": 0.038690801709890366,
1827
+ "learning_rate": 5.573417126992003e-05,
1828
+ "loss": 0.0419,
1829
+ "step": 212
1830
+ },
1831
+ {
1832
+ "epoch": 2.581818181818182,
1833
+ "grad_norm": 0.03184739127755165,
1834
+ "learning_rate": 5.531108716309547e-05,
1835
+ "loss": 0.0208,
1836
+ "step": 213
1837
+ },
1838
+ {
1839
+ "epoch": 2.5939393939393938,
1840
+ "grad_norm": 0.04226066172122955,
1841
+ "learning_rate": 5.4887618085445094e-05,
1842
+ "loss": 0.0356,
1843
+ "step": 214
1844
+ },
1845
+ {
1846
+ "epoch": 2.606060606060606,
1847
+ "grad_norm": 0.02787015587091446,
1848
+ "learning_rate": 5.446379473185972e-05,
1849
+ "loss": 0.0199,
1850
+ "step": 215
1851
+ },
1852
+ {
1853
+ "epoch": 2.606060606060606,
1854
+ "eval_loss": 0.023647097870707512,
1855
+ "eval_runtime": 6.1981,
1856
+ "eval_samples_per_second": 8.067,
1857
+ "eval_steps_per_second": 2.097,
1858
+ "step": 215
1859
+ },
1860
+ {
1861
+ "epoch": 2.618181818181818,
1862
+ "grad_norm": 0.028222182765603065,
1863
+ "learning_rate": 5.4039647822909624e-05,
1864
+ "loss": 0.0185,
1865
+ "step": 216
1866
+ },
1867
+ {
1868
+ "epoch": 2.6303030303030304,
1869
+ "grad_norm": 0.03137464076280594,
1870
+ "learning_rate": 5.361520810261779e-05,
1871
+ "loss": 0.0212,
1872
+ "step": 217
1873
+ },
1874
+ {
1875
+ "epoch": 2.6424242424242426,
1876
+ "grad_norm": 0.028826339170336723,
1877
+ "learning_rate": 5.319050633623142e-05,
1878
+ "loss": 0.0208,
1879
+ "step": 218
1880
+ },
1881
+ {
1882
+ "epoch": 2.6545454545454543,
1883
+ "grad_norm": 0.048953138291835785,
1884
+ "learning_rate": 5.2765573307992036e-05,
1885
+ "loss": 0.0343,
1886
+ "step": 219
1887
+ },
1888
+ {
1889
+ "epoch": 2.6666666666666665,
1890
+ "grad_norm": 0.03138812631368637,
1891
+ "learning_rate": 5.234043981890394e-05,
1892
+ "loss": 0.023,
1893
+ "step": 220
1894
+ },
1895
+ {
1896
+ "epoch": 2.6666666666666665,
1897
+ "eval_loss": 0.02315612882375717,
1898
+ "eval_runtime": 6.1852,
1899
+ "eval_samples_per_second": 8.084,
1900
+ "eval_steps_per_second": 2.102,
1901
+ "step": 220
1902
+ },
1903
+ {
1904
+ "epoch": 2.6787878787878787,
1905
+ "grad_norm": 0.03604348748922348,
1906
+ "learning_rate": 5.191513668450178e-05,
1907
+ "loss": 0.0208,
1908
+ "step": 221
1909
+ },
1910
+ {
1911
+ "epoch": 2.690909090909091,
1912
+ "grad_norm": 0.028721556067466736,
1913
+ "learning_rate": 5.14896947326168e-05,
1914
+ "loss": 0.0178,
1915
+ "step": 222
1916
+ },
1917
+ {
1918
+ "epoch": 2.703030303030303,
1919
+ "grad_norm": 0.02585718221962452,
1920
+ "learning_rate": 5.1064144801142374e-05,
1921
+ "loss": 0.019,
1922
+ "step": 223
1923
+ },
1924
+ {
1925
+ "epoch": 2.7151515151515153,
1926
+ "grad_norm": 0.02729875221848488,
1927
+ "learning_rate": 5.0638517735798696e-05,
1928
+ "loss": 0.0184,
1929
+ "step": 224
1930
+ },
1931
+ {
1932
+ "epoch": 2.7272727272727275,
1933
+ "grad_norm": 0.029812021180987358,
1934
+ "learning_rate": 5.021284438789694e-05,
1935
+ "loss": 0.0227,
1936
+ "step": 225
1937
+ },
1938
+ {
1939
+ "epoch": 2.7272727272727275,
1940
+ "eval_loss": 0.023449590429663658,
1941
+ "eval_runtime": 6.1841,
1942
+ "eval_samples_per_second": 8.085,
1943
+ "eval_steps_per_second": 2.102,
1944
+ "step": 225
1945
+ },
1946
+ {
1947
+ "epoch": 2.7393939393939393,
1948
+ "grad_norm": 0.02997618354856968,
1949
+ "learning_rate": 4.9787155612103074e-05,
1950
+ "loss": 0.0205,
1951
+ "step": 226
1952
+ },
1953
+ {
1954
+ "epoch": 2.7515151515151515,
1955
+ "grad_norm": 0.028398435562849045,
1956
+ "learning_rate": 4.936148226420132e-05,
1957
+ "loss": 0.0171,
1958
+ "step": 227
1959
+ },
1960
+ {
1961
+ "epoch": 2.7636363636363637,
1962
+ "grad_norm": 0.030046509578824043,
1963
+ "learning_rate": 4.893585519885764e-05,
1964
+ "loss": 0.0197,
1965
+ "step": 228
1966
+ },
1967
+ {
1968
+ "epoch": 2.775757575757576,
1969
+ "grad_norm": 0.029226917773485184,
1970
+ "learning_rate": 4.851030526738321e-05,
1971
+ "loss": 0.0204,
1972
+ "step": 229
1973
+ },
1974
+ {
1975
+ "epoch": 2.787878787878788,
1976
+ "grad_norm": 0.03432171046733856,
1977
+ "learning_rate": 4.8084863315498234e-05,
1978
+ "loss": 0.0206,
1979
+ "step": 230
1980
+ },
1981
+ {
1982
+ "epoch": 2.787878787878788,
1983
+ "eval_loss": 0.022967081516981125,
1984
+ "eval_runtime": 6.1905,
1985
+ "eval_samples_per_second": 8.077,
1986
+ "eval_steps_per_second": 2.1,
1987
+ "step": 230
1988
+ },
1989
+ {
1990
+ "epoch": 2.8,
1991
+ "grad_norm": 0.029804987832903862,
1992
+ "learning_rate": 4.765956018109607e-05,
1993
+ "loss": 0.0197,
1994
+ "step": 231
1995
+ },
1996
+ {
1997
+ "epoch": 2.812121212121212,
1998
+ "grad_norm": 0.029483767226338387,
1999
+ "learning_rate": 4.723442669200798e-05,
2000
+ "loss": 0.0213,
2001
+ "step": 232
2002
+ },
2003
+ {
2004
+ "epoch": 2.824242424242424,
2005
+ "grad_norm": 0.03142073005437851,
2006
+ "learning_rate": 4.680949366376858e-05,
2007
+ "loss": 0.0237,
2008
+ "step": 233
2009
+ },
2010
+ {
2011
+ "epoch": 2.8363636363636364,
2012
+ "grad_norm": 0.029062366113066673,
2013
+ "learning_rate": 4.638479189738224e-05,
2014
+ "loss": 0.0235,
2015
+ "step": 234
2016
+ },
2017
+ {
2018
+ "epoch": 2.8484848484848486,
2019
+ "grad_norm": 0.03055807389318943,
2020
+ "learning_rate": 4.5960352177090395e-05,
2021
+ "loss": 0.0217,
2022
+ "step": 235
2023
+ },
2024
+ {
2025
+ "epoch": 2.8484848484848486,
2026
+ "eval_loss": 0.022518714889883995,
2027
+ "eval_runtime": 6.1918,
2028
+ "eval_samples_per_second": 8.075,
2029
+ "eval_steps_per_second": 2.1,
2030
+ "step": 235
2031
+ },
2032
+ {
2033
+ "epoch": 2.8606060606060604,
2034
+ "grad_norm": 0.027205798774957657,
2035
+ "learning_rate": 4.5536205268140294e-05,
2036
+ "loss": 0.0189,
2037
+ "step": 236
2038
+ },
2039
+ {
2040
+ "epoch": 2.8727272727272726,
2041
+ "grad_norm": 0.025477448478341103,
2042
+ "learning_rate": 4.511238191455491e-05,
2043
+ "loss": 0.0166,
2044
+ "step": 237
2045
+ },
2046
+ {
2047
+ "epoch": 2.8848484848484848,
2048
+ "grad_norm": 0.025487707927823067,
2049
+ "learning_rate": 4.468891283690454e-05,
2050
+ "loss": 0.0183,
2051
+ "step": 238
2052
+ },
2053
+ {
2054
+ "epoch": 2.896969696969697,
2055
+ "grad_norm": 0.0332886204123497,
2056
+ "learning_rate": 4.4265828730079987e-05,
2057
+ "loss": 0.0221,
2058
+ "step": 239
2059
+ },
2060
+ {
2061
+ "epoch": 2.909090909090909,
2062
+ "grad_norm": 0.029150154441595078,
2063
+ "learning_rate": 4.3843160261067655e-05,
2064
+ "loss": 0.0186,
2065
+ "step": 240
2066
+ },
2067
+ {
2068
+ "epoch": 2.909090909090909,
2069
+ "eval_loss": 0.022352781146764755,
2070
+ "eval_runtime": 6.1961,
2071
+ "eval_samples_per_second": 8.07,
2072
+ "eval_steps_per_second": 2.098,
2073
+ "step": 240
2074
+ },
2075
+ {
2076
+ "epoch": 2.9212121212121214,
2077
+ "grad_norm": 0.029591498896479607,
2078
+ "learning_rate": 4.342093806672678e-05,
2079
+ "loss": 0.0181,
2080
+ "step": 241
2081
+ },
2082
+ {
2083
+ "epoch": 2.9333333333333336,
2084
+ "grad_norm": 0.03216252475976944,
2085
+ "learning_rate": 4.2999192751568564e-05,
2086
+ "loss": 0.0203,
2087
+ "step": 242
2088
+ },
2089
+ {
2090
+ "epoch": 2.9454545454545453,
2091
+ "grad_norm": 0.02891668863594532,
2092
+ "learning_rate": 4.2577954885537986e-05,
2093
+ "loss": 0.0181,
2094
+ "step": 243
2095
+ },
2096
+ {
2097
+ "epoch": 2.9575757575757575,
2098
+ "grad_norm": 0.028023086488246918,
2099
+ "learning_rate": 4.215725500179787e-05,
2100
+ "loss": 0.0191,
2101
+ "step": 244
2102
+ },
2103
+ {
2104
+ "epoch": 2.9696969696969697,
2105
+ "grad_norm": 0.03082926571369171,
2106
+ "learning_rate": 4.1737123594515756e-05,
2107
+ "loss": 0.0201,
2108
+ "step": 245
2109
+ },
2110
+ {
2111
+ "epoch": 2.9696969696969697,
2112
+ "eval_loss": 0.02198323793709278,
2113
+ "eval_runtime": 6.1948,
2114
+ "eval_samples_per_second": 8.071,
2115
+ "eval_steps_per_second": 2.099,
2116
+ "step": 245
2117
+ },
2118
+ {
2119
+ "epoch": 2.981818181818182,
2120
+ "grad_norm": 0.0321161188185215,
2121
+ "learning_rate": 4.131759111665349e-05,
2122
+ "loss": 0.0191,
2123
+ "step": 246
2124
+ },
2125
+ {
2126
+ "epoch": 2.993939393939394,
2127
+ "grad_norm": 0.026935642585158348,
2128
+ "learning_rate": 4.089868797775989e-05,
2129
+ "loss": 0.0185,
2130
+ "step": 247
2131
+ },
2132
+ {
2133
+ "epoch": 3.006060606060606,
2134
+ "grad_norm": 0.05411810800433159,
2135
+ "learning_rate": 4.0480444541766576e-05,
2136
+ "loss": 0.0301,
2137
+ "step": 248
2138
+ },
2139
+ {
2140
+ "epoch": 3.018181818181818,
2141
+ "grad_norm": 0.027184097096323967,
2142
+ "learning_rate": 4.0062891124787e-05,
2143
+ "loss": 0.0188,
2144
+ "step": 249
2145
+ },
2146
+ {
2147
+ "epoch": 3.0303030303030303,
2148
+ "grad_norm": 0.022542983293533325,
2149
+ "learning_rate": 3.964605799291897e-05,
2150
+ "loss": 0.0147,
2151
+ "step": 250
2152
+ },
2153
+ {
2154
+ "epoch": 3.0303030303030303,
2155
+ "eval_loss": 0.021969465538859367,
2156
+ "eval_runtime": 6.1917,
2157
+ "eval_samples_per_second": 8.075,
2158
+ "eval_steps_per_second": 2.1,
2159
+ "step": 250
2160
+ },
2161
+ {
2162
+ "epoch": 3.0424242424242425,
2163
+ "grad_norm": 0.03472661226987839,
2164
+ "learning_rate": 3.922997536005094e-05,
2165
+ "loss": 0.0178,
2166
+ "step": 251
2167
+ },
2168
+ {
2169
+ "epoch": 3.0545454545454547,
2170
+ "grad_norm": 0.028128741309046745,
2171
+ "learning_rate": 3.8814673385671894e-05,
2172
+ "loss": 0.0157,
2173
+ "step": 252
2174
+ },
2175
+ {
2176
+ "epoch": 3.066666666666667,
2177
+ "grad_norm": 0.03135592117905617,
2178
+ "learning_rate": 3.840018217268527e-05,
2179
+ "loss": 0.0161,
2180
+ "step": 253
2181
+ },
2182
+ {
2183
+ "epoch": 3.0787878787878786,
2184
+ "grad_norm": 0.03661385551095009,
2185
+ "learning_rate": 3.7986531765226964e-05,
2186
+ "loss": 0.0161,
2187
+ "step": 254
2188
+ },
2189
+ {
2190
+ "epoch": 3.090909090909091,
2191
+ "grad_norm": 0.03205974027514458,
2192
+ "learning_rate": 3.757375214648764e-05,
2193
+ "loss": 0.0142,
2194
+ "step": 255
2195
+ },
2196
+ {
2197
+ "epoch": 3.090909090909091,
2198
+ "eval_loss": 0.022621195763349533,
2199
+ "eval_runtime": 6.2467,
2200
+ "eval_samples_per_second": 8.004,
2201
+ "eval_steps_per_second": 2.081,
2202
+ "step": 255
2203
+ },
2204
+ {
2205
+ "epoch": 3.103030303030303,
2206
+ "grad_norm": 0.037527382373809814,
2207
+ "learning_rate": 3.716187323653939e-05,
2208
+ "loss": 0.0167,
2209
+ "step": 256
2210
+ },
2211
+ {
2212
+ "epoch": 3.1151515151515152,
2213
+ "grad_norm": 0.03540443629026413,
2214
+ "learning_rate": 3.675092489016693e-05,
2215
+ "loss": 0.0168,
2216
+ "step": 257
2217
+ },
2218
+ {
2219
+ "epoch": 3.1272727272727274,
2220
+ "grad_norm": 0.034389954060316086,
2221
+ "learning_rate": 3.634093689470371e-05,
2222
+ "loss": 0.017,
2223
+ "step": 258
2224
+ },
2225
+ {
2226
+ "epoch": 3.1393939393939396,
2227
+ "grad_norm": 0.033294420689344406,
2228
+ "learning_rate": 3.5931938967872766e-05,
2229
+ "loss": 0.016,
2230
+ "step": 259
2231
+ },
2232
+ {
2233
+ "epoch": 3.1515151515151514,
2234
+ "grad_norm": 0.028759747743606567,
2235
+ "learning_rate": 3.5523960755632574e-05,
2236
+ "loss": 0.0149,
2237
+ "step": 260
2238
+ },
2239
+ {
2240
+ "epoch": 3.1515151515151514,
2241
+ "eval_loss": 0.021824924275279045,
2242
+ "eval_runtime": 6.1966,
2243
+ "eval_samples_per_second": 8.069,
2244
+ "eval_steps_per_second": 2.098,
2245
+ "step": 260
2246
+ },
2247
+ {
2248
+ "epoch": 3.1636363636363636,
2249
+ "grad_norm": 0.02833370864391327,
2250
+ "learning_rate": 3.5117031830028274e-05,
2251
+ "loss": 0.0127,
2252
+ "step": 261
2253
+ },
2254
+ {
2255
+ "epoch": 3.175757575757576,
2256
+ "grad_norm": 0.0286524910479784,
2257
+ "learning_rate": 3.471118168704811e-05,
2258
+ "loss": 0.015,
2259
+ "step": 262
2260
+ },
2261
+ {
2262
+ "epoch": 3.187878787878788,
2263
+ "grad_norm": 0.02769540622830391,
2264
+ "learning_rate": 3.4306439744485454e-05,
2265
+ "loss": 0.0154,
2266
+ "step": 263
2267
+ },
2268
+ {
2269
+ "epoch": 3.2,
2270
+ "grad_norm": 0.03221355006098747,
2271
+ "learning_rate": 3.390283533980646e-05,
2272
+ "loss": 0.0167,
2273
+ "step": 264
2274
+ },
2275
+ {
2276
+ "epoch": 3.212121212121212,
2277
+ "grad_norm": 0.026392612606287003,
2278
+ "learning_rate": 3.350039772802354e-05,
2279
+ "loss": 0.0151,
2280
+ "step": 265
2281
+ },
2282
+ {
2283
+ "epoch": 3.212121212121212,
2284
+ "eval_loss": 0.02153392694890499,
2285
+ "eval_runtime": 6.1848,
2286
+ "eval_samples_per_second": 8.084,
2287
+ "eval_steps_per_second": 2.102,
2288
+ "step": 265
2289
+ },
2290
+ {
2291
+ "epoch": 3.224242424242424,
2292
+ "grad_norm": 0.03104759193956852,
2293
+ "learning_rate": 3.309915607957487e-05,
2294
+ "loss": 0.0171,
2295
+ "step": 266
2296
+ },
2297
+ {
2298
+ "epoch": 3.2363636363636363,
2299
+ "grad_norm": 0.028836429119110107,
2300
+ "learning_rate": 3.269913947820998e-05,
2301
+ "loss": 0.0158,
2302
+ "step": 267
2303
+ },
2304
+ {
2305
+ "epoch": 3.2484848484848485,
2306
+ "grad_norm": 0.032903432846069336,
2307
+ "learning_rate": 3.2300376918881624e-05,
2308
+ "loss": 0.0156,
2309
+ "step": 268
2310
+ },
2311
+ {
2312
+ "epoch": 3.2606060606060607,
2313
+ "grad_norm": 0.030551951378583908,
2314
+ "learning_rate": 3.1902897305644095e-05,
2315
+ "loss": 0.0134,
2316
+ "step": 269
2317
+ },
2318
+ {
2319
+ "epoch": 3.2727272727272725,
2320
+ "grad_norm": 0.030059080570936203,
2321
+ "learning_rate": 3.1506729449558184e-05,
2322
+ "loss": 0.0174,
2323
+ "step": 270
2324
+ },
2325
+ {
2326
+ "epoch": 3.2727272727272725,
2327
+ "eval_loss": 0.021679332479834557,
2328
+ "eval_runtime": 6.1964,
2329
+ "eval_samples_per_second": 8.069,
2330
+ "eval_steps_per_second": 2.098,
2331
+ "step": 270
2332
+ },
2333
+ {
2334
+ "epoch": 3.2848484848484847,
2335
+ "grad_norm": 0.030379703268408775,
2336
+ "learning_rate": 3.1111902066602724e-05,
2337
+ "loss": 0.018,
2338
+ "step": 271
2339
+ },
2340
+ {
2341
+ "epoch": 3.296969696969697,
2342
+ "grad_norm": 0.02761555276811123,
2343
+ "learning_rate": 3.071844377559323e-05,
2344
+ "loss": 0.016,
2345
+ "step": 272
2346
+ },
2347
+ {
2348
+ "epoch": 3.309090909090909,
2349
+ "grad_norm": 0.026775086298584938,
2350
+ "learning_rate": 3.0326383096107426e-05,
2351
+ "loss": 0.014,
2352
+ "step": 273
2353
+ },
2354
+ {
2355
+ "epoch": 3.3212121212121213,
2356
+ "grad_norm": 0.03328753635287285,
2357
+ "learning_rate": 2.9935748446418066e-05,
2358
+ "loss": 0.0169,
2359
+ "step": 274
2360
+ },
2361
+ {
2362
+ "epoch": 3.3333333333333335,
2363
+ "grad_norm": 0.03564237430691719,
2364
+ "learning_rate": 2.9546568141433006e-05,
2365
+ "loss": 0.0172,
2366
+ "step": 275
2367
+ },
2368
+ {
2369
+ "epoch": 3.3333333333333335,
2370
+ "eval_loss": 0.021324800327420235,
2371
+ "eval_runtime": 6.1942,
2372
+ "eval_samples_per_second": 8.072,
2373
+ "eval_steps_per_second": 2.099,
2374
+ "step": 275
2375
+ },
2376
+ {
2377
+ "epoch": 3.3454545454545457,
2378
+ "grad_norm": 0.028079047799110413,
2379
+ "learning_rate": 2.915887039064287e-05,
2380
+ "loss": 0.0141,
2381
+ "step": 276
2382
+ },
2383
+ {
2384
+ "epoch": 3.3575757575757574,
2385
+ "grad_norm": 0.02460673451423645,
2386
+ "learning_rate": 2.8772683296076196e-05,
2387
+ "loss": 0.0126,
2388
+ "step": 277
2389
+ },
2390
+ {
2391
+ "epoch": 3.3696969696969696,
2392
+ "grad_norm": 0.04345537722110748,
2393
+ "learning_rate": 2.8388034850262646e-05,
2394
+ "loss": 0.0376,
2395
+ "step": 278
2396
+ },
2397
+ {
2398
+ "epoch": 3.381818181818182,
2399
+ "grad_norm": 0.0306687094271183,
2400
+ "learning_rate": 2.8004952934203838e-05,
2401
+ "loss": 0.017,
2402
+ "step": 279
2403
+ },
2404
+ {
2405
+ "epoch": 3.393939393939394,
2406
+ "grad_norm": 0.033993735909461975,
2407
+ "learning_rate": 2.762346531535246e-05,
2408
+ "loss": 0.017,
2409
+ "step": 280
2410
+ },
2411
+ {
2412
+ "epoch": 3.393939393939394,
2413
+ "eval_loss": 0.02108747698366642,
2414
+ "eval_runtime": 6.2236,
2415
+ "eval_samples_per_second": 8.034,
2416
+ "eval_steps_per_second": 2.089,
2417
+ "step": 280
2418
+ },
2419
+ {
2420
+ "epoch": 3.4060606060606062,
2421
+ "grad_norm": 0.02444186620414257,
2422
+ "learning_rate": 2.7243599645599576e-05,
2423
+ "loss": 0.014,
2424
+ "step": 281
2425
+ },
2426
+ {
2427
+ "epoch": 3.418181818181818,
2428
+ "grad_norm": 0.028384167701005936,
2429
+ "learning_rate": 2.6865383459270265e-05,
2430
+ "loss": 0.0158,
2431
+ "step": 282
2432
+ },
2433
+ {
2434
+ "epoch": 3.43030303030303,
2435
+ "grad_norm": 0.03162846714258194,
2436
+ "learning_rate": 2.6488844171127903e-05,
2437
+ "loss": 0.017,
2438
+ "step": 283
2439
+ },
2440
+ {
2441
+ "epoch": 3.4424242424242424,
2442
+ "grad_norm": 0.027297567576169968,
2443
+ "learning_rate": 2.6114009074386846e-05,
2444
+ "loss": 0.0124,
2445
+ "step": 284
2446
+ },
2447
+ {
2448
+ "epoch": 3.4545454545454546,
2449
+ "grad_norm": 0.03545952960848808,
2450
+ "learning_rate": 2.574090533873431e-05,
2451
+ "loss": 0.0223,
2452
+ "step": 285
2453
+ },
2454
+ {
2455
+ "epoch": 3.4545454545454546,
2456
+ "eval_loss": 0.021236957982182503,
2457
+ "eval_runtime": 6.1899,
2458
+ "eval_samples_per_second": 8.078,
2459
+ "eval_steps_per_second": 2.1,
2460
+ "step": 285
2461
+ },
2462
+ {
2463
+ "epoch": 3.466666666666667,
2464
+ "grad_norm": 0.024587715044617653,
2465
+ "learning_rate": 2.5369560008360828e-05,
2466
+ "loss": 0.0132,
2467
+ "step": 286
2468
+ },
2469
+ {
2470
+ "epoch": 3.4787878787878785,
2471
+ "grad_norm": 0.025963526219129562,
2472
+ "learning_rate": 2.500000000000001e-05,
2473
+ "loss": 0.0132,
2474
+ "step": 287
2475
+ },
2476
+ {
2477
+ "epoch": 3.4909090909090907,
2478
+ "grad_norm": 0.03487967699766159,
2479
+ "learning_rate": 2.4632252100977566e-05,
2480
+ "loss": 0.0136,
2481
+ "step": 288
2482
+ },
2483
+ {
2484
+ "epoch": 3.503030303030303,
2485
+ "grad_norm": 0.030390363186597824,
2486
+ "learning_rate": 2.4266342967269552e-05,
2487
+ "loss": 0.0157,
2488
+ "step": 289
2489
+ },
2490
+ {
2491
+ "epoch": 3.515151515151515,
2492
+ "grad_norm": 0.030459538102149963,
2493
+ "learning_rate": 2.3902299121570333e-05,
2494
+ "loss": 0.0144,
2495
+ "step": 290
2496
+ },
2497
+ {
2498
+ "epoch": 3.515151515151515,
2499
+ "eval_loss": 0.02107882872223854,
2500
+ "eval_runtime": 6.2006,
2501
+ "eval_samples_per_second": 8.064,
2502
+ "eval_steps_per_second": 2.097,
2503
+ "step": 290
2504
+ },
2505
+ {
2506
+ "epoch": 3.5272727272727273,
2507
+ "grad_norm": 0.02951274998486042,
2508
+ "learning_rate": 2.354014695136997e-05,
2509
+ "loss": 0.0131,
2510
+ "step": 291
2511
+ },
2512
+ {
2513
+ "epoch": 3.5393939393939395,
2514
+ "grad_norm": 0.029193086549639702,
2515
+ "learning_rate": 2.317991270704167e-05,
2516
+ "loss": 0.0151,
2517
+ "step": 292
2518
+ },
2519
+ {
2520
+ "epoch": 3.5515151515151517,
2521
+ "grad_norm": 0.02726319245994091,
2522
+ "learning_rate": 2.282162249993895e-05,
2523
+ "loss": 0.0125,
2524
+ "step": 293
2525
+ },
2526
+ {
2527
+ "epoch": 3.5636363636363635,
2528
+ "grad_norm": 0.03212954103946686,
2529
+ "learning_rate": 2.246530230050301e-05,
2530
+ "loss": 0.0162,
2531
+ "step": 294
2532
+ },
2533
+ {
2534
+ "epoch": 3.5757575757575757,
2535
+ "grad_norm": 0.024175025522708893,
2536
+ "learning_rate": 2.211097793638029e-05,
2537
+ "loss": 0.0125,
2538
+ "step": 295
2539
+ },
2540
+ {
2541
+ "epoch": 3.5757575757575757,
2542
+ "eval_loss": 0.020796656608581543,
2543
+ "eval_runtime": 6.1933,
2544
+ "eval_samples_per_second": 8.073,
2545
+ "eval_steps_per_second": 2.099,
2546
+ "step": 295
2547
+ },
2548
+ {
2549
+ "epoch": 3.587878787878788,
2550
+ "grad_norm": 0.02679980918765068,
2551
+ "learning_rate": 2.175867509055033e-05,
2552
+ "loss": 0.0111,
2553
+ "step": 296
2554
+ },
2555
+ {
2556
+ "epoch": 3.6,
2557
+ "grad_norm": 0.031121132895350456,
2558
+ "learning_rate": 2.1408419299464245e-05,
2559
+ "loss": 0.0165,
2560
+ "step": 297
2561
+ },
2562
+ {
2563
+ "epoch": 3.6121212121212123,
2564
+ "grad_norm": 0.030764909461140633,
2565
+ "learning_rate": 2.106023595119358e-05,
2566
+ "loss": 0.0139,
2567
+ "step": 298
2568
+ },
2569
+ {
2570
+ "epoch": 3.624242424242424,
2571
+ "grad_norm": 0.0302122812718153,
2572
+ "learning_rate": 2.071415028359026e-05,
2573
+ "loss": 0.0148,
2574
+ "step": 299
2575
+ },
2576
+ {
2577
+ "epoch": 3.6363636363636362,
2578
+ "grad_norm": 0.029834948480129242,
2579
+ "learning_rate": 2.0370187382457068e-05,
2580
+ "loss": 0.0163,
2581
+ "step": 300
2582
+ },
2583
+ {
2584
+ "epoch": 3.6363636363636362,
2585
+ "eval_loss": 0.02069205790758133,
2586
+ "eval_runtime": 6.2054,
2587
+ "eval_samples_per_second": 8.057,
2588
+ "eval_steps_per_second": 2.095,
2589
+ "step": 300
2590
+ },
2591
+ {
2592
+ "epoch": 3.6484848484848484,
2593
+ "grad_norm": 0.03009135089814663,
2594
+ "learning_rate": 2.0028372179729403e-05,
2595
+ "loss": 0.0143,
2596
+ "step": 301
2597
+ },
2598
+ {
2599
+ "epoch": 3.6606060606060606,
2600
+ "grad_norm": 0.029639270156621933,
2601
+ "learning_rate": 1.9688729451668114e-05,
2602
+ "loss": 0.0168,
2603
+ "step": 302
2604
+ },
2605
+ {
2606
+ "epoch": 3.672727272727273,
2607
+ "grad_norm": 0.026824606582522392,
2608
+ "learning_rate": 1.935128381706355e-05,
2609
+ "loss": 0.0129,
2610
+ "step": 303
2611
+ },
2612
+ {
2613
+ "epoch": 3.6848484848484846,
2614
+ "grad_norm": 0.03427920117974281,
2615
+ "learning_rate": 1.901605973545116e-05,
2616
+ "loss": 0.0194,
2617
+ "step": 304
2618
+ },
2619
+ {
2620
+ "epoch": 3.6969696969696972,
2621
+ "grad_norm": 0.031160475686192513,
2622
+ "learning_rate": 1.868308150533847e-05,
2623
+ "loss": 0.015,
2624
+ "step": 305
2625
+ },
2626
+ {
2627
+ "epoch": 3.6969696969696972,
2628
+ "eval_loss": 0.020683376118540764,
2629
+ "eval_runtime": 6.1876,
2630
+ "eval_samples_per_second": 8.081,
2631
+ "eval_steps_per_second": 2.101,
2632
+ "step": 305
2633
+ },
2634
+ {
2635
+ "epoch": 3.709090909090909,
2636
+ "grad_norm": 0.033249229192733765,
2637
+ "learning_rate": 1.8352373262443916e-05,
2638
+ "loss": 0.0147,
2639
+ "step": 306
2640
+ },
2641
+ {
2642
+ "epoch": 3.721212121212121,
2643
+ "grad_norm": 0.029073260724544525,
2644
+ "learning_rate": 1.8023958977947304e-05,
2645
+ "loss": 0.0157,
2646
+ "step": 307
2647
+ },
2648
+ {
2649
+ "epoch": 3.7333333333333334,
2650
+ "grad_norm": 0.030520522966980934,
2651
+ "learning_rate": 1.7697862456752273e-05,
2652
+ "loss": 0.0152,
2653
+ "step": 308
2654
+ },
2655
+ {
2656
+ "epoch": 3.7454545454545456,
2657
+ "grad_norm": 0.029693983495235443,
2658
+ "learning_rate": 1.7374107335760936e-05,
2659
+ "loss": 0.0172,
2660
+ "step": 309
2661
+ },
2662
+ {
2663
+ "epoch": 3.757575757575758,
2664
+ "grad_norm": 0.03103681467473507,
2665
+ "learning_rate": 1.7052717082160346e-05,
2666
+ "loss": 0.0154,
2667
+ "step": 310
2668
+ },
2669
+ {
2670
+ "epoch": 3.757575757575758,
2671
+ "eval_loss": 0.02056981809437275,
2672
+ "eval_runtime": 6.1896,
2673
+ "eval_samples_per_second": 8.078,
2674
+ "eval_steps_per_second": 2.1,
2675
+ "step": 310
2676
+ },
2677
+ {
2678
+ "epoch": 3.7696969696969695,
2679
+ "grad_norm": 0.030047744512557983,
2680
+ "learning_rate": 1.673371499172174e-05,
2681
+ "loss": 0.015,
2682
+ "step": 311
2683
+ },
2684
+ {
2685
+ "epoch": 3.7818181818181817,
2686
+ "grad_norm": 0.03367823734879494,
2687
+ "learning_rate": 1.6417124187111775e-05,
2688
+ "loss": 0.017,
2689
+ "step": 312
2690
+ },
2691
+ {
2692
+ "epoch": 3.793939393939394,
2693
+ "grad_norm": 0.027037424966692924,
2694
+ "learning_rate": 1.610296761621662e-05,
2695
+ "loss": 0.0145,
2696
+ "step": 313
2697
+ },
2698
+ {
2699
+ "epoch": 3.806060606060606,
2700
+ "grad_norm": 0.030140092596411705,
2701
+ "learning_rate": 1.5791268050478486e-05,
2702
+ "loss": 0.0228,
2703
+ "step": 314
2704
+ },
2705
+ {
2706
+ "epoch": 3.8181818181818183,
2707
+ "grad_norm": 0.031016338616609573,
2708
+ "learning_rate": 1.5482048083245114e-05,
2709
+ "loss": 0.0186,
2710
+ "step": 315
2711
+ },
2712
+ {
2713
+ "epoch": 3.8181818181818183,
2714
+ "eval_loss": 0.02028246596455574,
2715
+ "eval_runtime": 6.1869,
2716
+ "eval_samples_per_second": 8.082,
2717
+ "eval_steps_per_second": 2.101,
2718
+ "step": 315
2719
+ },
2720
+ {
2721
+ "epoch": 3.83030303030303,
2722
+ "grad_norm": 0.02848219871520996,
2723
+ "learning_rate": 1.517533012813217e-05,
2724
+ "loss": 0.0159,
2725
+ "step": 316
2726
+ },
2727
+ {
2728
+ "epoch": 3.8424242424242423,
2729
+ "grad_norm": 0.024206412956118584,
2730
+ "learning_rate": 1.4871136417398406e-05,
2731
+ "loss": 0.0123,
2732
+ "step": 317
2733
+ },
2734
+ {
2735
+ "epoch": 3.8545454545454545,
2736
+ "grad_norm": 0.03030635416507721,
2737
+ "learning_rate": 1.4569489000334436e-05,
2738
+ "loss": 0.0137,
2739
+ "step": 318
2740
+ },
2741
+ {
2742
+ "epoch": 3.8666666666666667,
2743
+ "grad_norm": 0.03156241029500961,
2744
+ "learning_rate": 1.427040974166427e-05,
2745
+ "loss": 0.0159,
2746
+ "step": 319
2747
+ },
2748
+ {
2749
+ "epoch": 3.878787878787879,
2750
+ "grad_norm": 0.028942270204424858,
2751
+ "learning_rate": 1.3973920319960655e-05,
2752
+ "loss": 0.0135,
2753
+ "step": 320
2754
+ },
2755
+ {
2756
+ "epoch": 3.878787878787879,
2757
+ "eval_loss": 0.020162392407655716,
2758
+ "eval_runtime": 6.1914,
2759
+ "eval_samples_per_second": 8.076,
2760
+ "eval_steps_per_second": 2.1,
2761
+ "step": 320
2762
+ },
2763
+ {
2764
+ "epoch": 3.8909090909090907,
2765
+ "grad_norm": 0.03344618156552315,
2766
+ "learning_rate": 1.3680042226073552e-05,
2767
+ "loss": 0.0148,
2768
+ "step": 321
2769
+ },
2770
+ {
2771
+ "epoch": 3.9030303030303033,
2772
+ "grad_norm": 0.02961633913218975,
2773
+ "learning_rate": 1.3388796761572492e-05,
2774
+ "loss": 0.0141,
2775
+ "step": 322
2776
+ },
2777
+ {
2778
+ "epoch": 3.915151515151515,
2779
+ "grad_norm": 0.030708983540534973,
2780
+ "learning_rate": 1.310020503720254e-05,
2781
+ "loss": 0.0132,
2782
+ "step": 323
2783
+ },
2784
+ {
2785
+ "epoch": 3.9272727272727272,
2786
+ "grad_norm": 0.030072160065174103,
2787
+ "learning_rate": 1.2814287971354022e-05,
2788
+ "loss": 0.0161,
2789
+ "step": 324
2790
+ },
2791
+ {
2792
+ "epoch": 3.9393939393939394,
2793
+ "grad_norm": 0.03028644621372223,
2794
+ "learning_rate": 1.253106628854635e-05,
2795
+ "loss": 0.0159,
2796
+ "step": 325
2797
+ },
2798
+ {
2799
+ "epoch": 3.9393939393939394,
2800
+ "eval_loss": 0.020128030329942703,
2801
+ "eval_runtime": 6.1885,
2802
+ "eval_samples_per_second": 8.08,
2803
+ "eval_steps_per_second": 2.101,
2804
+ "step": 325
2805
+ },
2806
+ {
2807
+ "epoch": 3.9515151515151516,
2808
+ "grad_norm": 0.02972756326198578,
2809
+ "learning_rate": 1.2250560517925746e-05,
2810
+ "loss": 0.0142,
2811
+ "step": 326
2812
+ },
2813
+ {
2814
+ "epoch": 3.963636363636364,
2815
+ "grad_norm": 0.02873014286160469,
2816
+ "learning_rate": 1.1972790991777311e-05,
2817
+ "loss": 0.0155,
2818
+ "step": 327
2819
+ },
2820
+ {
2821
+ "epoch": 3.9757575757575756,
2822
+ "grad_norm": 0.028870223090052605,
2823
+ "learning_rate": 1.1697777844051105e-05,
2824
+ "loss": 0.0142,
2825
+ "step": 328
2826
+ },
2827
+ {
2828
+ "epoch": 3.987878787878788,
2829
+ "grad_norm": 0.02774449624121189,
2830
+ "learning_rate": 1.1425541008902851e-05,
2831
+ "loss": 0.0147,
2832
+ "step": 329
2833
+ },
2834
+ {
2835
+ "epoch": 4.0,
2836
+ "grad_norm": 0.04664117470383644,
2837
+ "learning_rate": 1.1156100219249022e-05,
2838
+ "loss": 0.0211,
2839
+ "step": 330
2840
+ },
2841
+ {
2842
+ "epoch": 4.0,
2843
+ "eval_loss": 0.01995450258255005,
2844
+ "eval_runtime": 6.191,
2845
+ "eval_samples_per_second": 8.076,
2846
+ "eval_steps_per_second": 2.1,
2847
+ "step": 330
2848
+ },
2849
+ {
2850
+ "epoch": 4.012121212121212,
2851
+ "grad_norm": 0.024339957162737846,
2852
+ "learning_rate": 1.0889475005336446e-05,
2853
+ "loss": 0.0133,
2854
+ "step": 331
2855
+ },
2856
+ {
2857
+ "epoch": 4.024242424242424,
2858
+ "grad_norm": 0.023921139538288116,
2859
+ "learning_rate": 1.0625684693326727e-05,
2860
+ "loss": 0.013,
2861
+ "step": 332
2862
+ },
2863
+ {
2864
+ "epoch": 4.036363636363636,
2865
+ "grad_norm": 0.02364080585539341,
2866
+ "learning_rate": 1.036474840389537e-05,
2867
+ "loss": 0.0132,
2868
+ "step": 333
2869
+ },
2870
+ {
2871
+ "epoch": 4.048484848484849,
2872
+ "grad_norm": 0.02356121875345707,
2873
+ "learning_rate": 1.0106685050845838e-05,
2874
+ "loss": 0.0121,
2875
+ "step": 334
2876
+ },
2877
+ {
2878
+ "epoch": 4.0606060606060606,
2879
+ "grad_norm": 0.025879928842186928,
2880
+ "learning_rate": 9.851513339738628e-06,
2881
+ "loss": 0.0134,
2882
+ "step": 335
2883
+ },
2884
+ {
2885
+ "epoch": 4.0606060606060606,
2886
+ "eval_loss": 0.0202109944075346,
2887
+ "eval_runtime": 6.1925,
2888
+ "eval_samples_per_second": 8.074,
2889
+ "eval_steps_per_second": 2.099,
2890
+ "step": 335
2891
+ },
2892
+ {
2893
+ "epoch": 4.072727272727272,
2894
+ "grad_norm": 0.02288251556456089,
2895
+ "learning_rate": 9.599251766535345e-06,
2896
+ "loss": 0.0121,
2897
+ "step": 336
2898
+ },
2899
+ {
2900
+ "epoch": 4.084848484848485,
2901
+ "grad_norm": 0.02703404612839222,
2902
+ "learning_rate": 9.349918616258114e-06,
2903
+ "loss": 0.0126,
2904
+ "step": 337
2905
+ },
2906
+ {
2907
+ "epoch": 4.096969696969697,
2908
+ "grad_norm": 0.025494417175650597,
2909
+ "learning_rate": 9.103531961664118e-06,
2910
+ "loss": 0.0122,
2911
+ "step": 338
2912
+ },
2913
+ {
2914
+ "epoch": 4.109090909090909,
2915
+ "grad_norm": 0.02807869389653206,
2916
+ "learning_rate": 8.860109661935674e-06,
2917
+ "loss": 0.0155,
2918
+ "step": 339
2919
+ },
2920
+ {
2921
+ "epoch": 4.121212121212121,
2922
+ "grad_norm": 0.027642810717225075,
2923
+ "learning_rate": 8.619669361385663e-06,
2924
+ "loss": 0.0113,
2925
+ "step": 340
2926
+ },
2927
+ {
2928
+ "epoch": 4.121212121212121,
2929
+ "eval_loss": 0.020561667159199715,
2930
+ "eval_runtime": 6.1965,
2931
+ "eval_samples_per_second": 8.069,
2932
+ "eval_steps_per_second": 2.098,
2933
+ "step": 340
2934
+ },
2935
+ {
2936
+ "epoch": 4.133333333333334,
2937
+ "grad_norm": 0.030346019193530083,
2938
+ "learning_rate": 8.38222848817864e-06,
2939
+ "loss": 0.0127,
2940
+ "step": 341
2941
+ },
2942
+ {
2943
+ "epoch": 4.1454545454545455,
2944
+ "grad_norm": 0.024746423587203026,
2945
+ "learning_rate": 8.14780425306758e-06,
2946
+ "loss": 0.0121,
2947
+ "step": 342
2948
+ },
2949
+ {
2950
+ "epoch": 4.157575757575757,
2951
+ "grad_norm": 0.026435259729623795,
2952
+ "learning_rate": 7.91641364814628e-06,
2953
+ "loss": 0.0109,
2954
+ "step": 343
2955
+ },
2956
+ {
2957
+ "epoch": 4.16969696969697,
2958
+ "grad_norm": 0.02962976135313511,
2959
+ "learning_rate": 7.688073445617799e-06,
2960
+ "loss": 0.0108,
2961
+ "step": 344
2962
+ },
2963
+ {
2964
+ "epoch": 4.181818181818182,
2965
+ "grad_norm": 0.02813326194882393,
2966
+ "learning_rate": 7.462800196578662e-06,
2967
+ "loss": 0.0117,
2968
+ "step": 345
2969
+ },
2970
+ {
2971
+ "epoch": 4.181818181818182,
2972
+ "eval_loss": 0.0208114180713892,
2973
+ "eval_runtime": 6.1943,
2974
+ "eval_samples_per_second": 8.072,
2975
+ "eval_steps_per_second": 2.099,
2976
+ "step": 345
2977
+ },
2978
+ {
2979
+ "epoch": 4.193939393939394,
2980
+ "grad_norm": 0.03237050771713257,
2981
+ "learning_rate": 7.240610229819195e-06,
2982
+ "loss": 0.013,
2983
+ "step": 346
2984
+ },
2985
+ {
2986
+ "epoch": 4.206060606060606,
2987
+ "grad_norm": 0.026286713778972626,
2988
+ "learning_rate": 7.0215196506399515e-06,
2989
+ "loss": 0.0108,
2990
+ "step": 347
2991
+ },
2992
+ {
2993
+ "epoch": 4.218181818181818,
2994
+ "grad_norm": 0.026608100160956383,
2995
+ "learning_rate": 6.8055443396842945e-06,
2996
+ "loss": 0.0103,
2997
+ "step": 348
2998
+ },
2999
+ {
3000
+ "epoch": 4.2303030303030305,
3001
+ "grad_norm": 0.03118029236793518,
3002
+ "learning_rate": 6.592699951787362e-06,
3003
+ "loss": 0.0138,
3004
+ "step": 349
3005
+ },
3006
+ {
3007
+ "epoch": 4.242424242424242,
3008
+ "grad_norm": 0.030633771792054176,
3009
+ "learning_rate": 6.3830019148412525e-06,
3010
+ "loss": 0.0108,
3011
+ "step": 350
3012
+ },
3013
+ {
3014
+ "epoch": 4.242424242424242,
3015
+ "eval_loss": 0.020906535908579826,
3016
+ "eval_runtime": 6.1873,
3017
+ "eval_samples_per_second": 8.081,
3018
+ "eval_steps_per_second": 2.101,
3019
+ "step": 350
3020
+ },
3021
+ {
3022
+ "epoch": 4.254545454545455,
3023
+ "grad_norm": 0.03377068042755127,
3024
+ "learning_rate": 6.17646542867682e-06,
3025
+ "loss": 0.0144,
3026
+ "step": 351
3027
+ },
3028
+ {
3029
+ "epoch": 4.266666666666667,
3030
+ "grad_norm": 0.027513034641742706,
3031
+ "learning_rate": 5.973105463961865e-06,
3032
+ "loss": 0.0107,
3033
+ "step": 352
3034
+ },
3035
+ {
3036
+ "epoch": 4.278787878787879,
3037
+ "grad_norm": 0.03077622503042221,
3038
+ "learning_rate": 5.772936761116027e-06,
3039
+ "loss": 0.0139,
3040
+ "step": 353
3041
+ },
3042
+ {
3043
+ "epoch": 4.290909090909091,
3044
+ "grad_norm": 0.026948513463139534,
3045
+ "learning_rate": 5.575973829242364e-06,
3046
+ "loss": 0.0126,
3047
+ "step": 354
3048
+ },
3049
+ {
3050
+ "epoch": 4.303030303030303,
3051
+ "grad_norm": 0.02911302261054516,
3052
+ "learning_rate": 5.382230945075556e-06,
3053
+ "loss": 0.012,
3054
+ "step": 355
3055
+ },
3056
+ {
3057
+ "epoch": 4.303030303030303,
3058
+ "eval_loss": 0.020746439695358276,
3059
+ "eval_runtime": 6.1873,
3060
+ "eval_samples_per_second": 8.081,
3061
+ "eval_steps_per_second": 2.101,
3062
+ "step": 355
3063
+ },
3064
+ {
3065
+ "epoch": 4.315151515151515,
3066
+ "grad_norm": 0.02364683710038662,
3067
+ "learning_rate": 5.191722151947226e-06,
3068
+ "loss": 0.0099,
3069
+ "step": 356
3070
+ },
3071
+ {
3072
+ "epoch": 4.327272727272727,
3073
+ "grad_norm": 0.031056983396410942,
3074
+ "learning_rate": 5.004461258767873e-06,
3075
+ "loss": 0.0143,
3076
+ "step": 357
3077
+ },
3078
+ {
3079
+ "epoch": 4.33939393939394,
3080
+ "grad_norm": 0.02985430881381035,
3081
+ "learning_rate": 4.820461839026047e-06,
3082
+ "loss": 0.0126,
3083
+ "step": 358
3084
+ },
3085
+ {
3086
+ "epoch": 4.351515151515152,
3087
+ "grad_norm": 0.02651560679078102,
3088
+ "learning_rate": 4.639737229804403e-06,
3089
+ "loss": 0.0115,
3090
+ "step": 359
3091
+ },
3092
+ {
3093
+ "epoch": 4.363636363636363,
3094
+ "grad_norm": 0.026479771360754967,
3095
+ "learning_rate": 4.462300530813024e-06,
3096
+ "loss": 0.0111,
3097
+ "step": 360
3098
+ },
3099
+ {
3100
+ "epoch": 4.363636363636363,
3101
+ "eval_loss": 0.020565090700984,
3102
+ "eval_runtime": 6.2012,
3103
+ "eval_samples_per_second": 8.063,
3104
+ "eval_steps_per_second": 2.096,
3105
+ "step": 360
3106
+ },
3107
+ {
3108
+ "epoch": 4.375757575757576,
3109
+ "grad_norm": 0.02071288600564003,
3110
+ "learning_rate": 4.2881646034398925e-06,
3111
+ "loss": 0.0114,
3112
+ "step": 361
3113
+ },
3114
+ {
3115
+ "epoch": 4.387878787878788,
3116
+ "grad_norm": 0.02533382549881935,
3117
+ "learning_rate": 4.117342069818603e-06,
3118
+ "loss": 0.0113,
3119
+ "step": 362
3120
+ },
3121
+ {
3122
+ "epoch": 4.4,
3123
+ "grad_norm": 0.021412553265690804,
3124
+ "learning_rate": 3.949845311913492e-06,
3125
+ "loss": 0.0115,
3126
+ "step": 363
3127
+ },
3128
+ {
3129
+ "epoch": 4.412121212121212,
3130
+ "grad_norm": 0.024555562064051628,
3131
+ "learning_rate": 3.7856864706221185e-06,
3132
+ "loss": 0.0098,
3133
+ "step": 364
3134
+ },
3135
+ {
3136
+ "epoch": 4.424242424242424,
3137
+ "grad_norm": 0.027632344514131546,
3138
+ "learning_rate": 3.6248774448952695e-06,
3139
+ "loss": 0.0118,
3140
+ "step": 365
3141
+ },
3142
+ {
3143
+ "epoch": 4.424242424242424,
3144
+ "eval_loss": 0.02050224132835865,
3145
+ "eval_runtime": 6.1859,
3146
+ "eval_samples_per_second": 8.083,
3147
+ "eval_steps_per_second": 2.102,
3148
+ "step": 365
3149
+ },
3150
+ {
3151
+ "epoch": 4.4363636363636365,
3152
+ "grad_norm": 0.028998758643865585,
3153
+ "learning_rate": 3.467429890874424e-06,
3154
+ "loss": 0.0111,
3155
+ "step": 366
3156
+ },
3157
+ {
3158
+ "epoch": 4.448484848484848,
3159
+ "grad_norm": 0.027949200943112373,
3160
+ "learning_rate": 3.3133552210468875e-06,
3161
+ "loss": 0.0122,
3162
+ "step": 367
3163
+ },
3164
+ {
3165
+ "epoch": 4.460606060606061,
3166
+ "grad_norm": 0.029877539724111557,
3167
+ "learning_rate": 3.162664603418608e-06,
3168
+ "loss": 0.0136,
3169
+ "step": 368
3170
+ },
3171
+ {
3172
+ "epoch": 4.472727272727273,
3173
+ "grad_norm": 0.02742207795381546,
3174
+ "learning_rate": 3.0153689607045845e-06,
3175
+ "loss": 0.0116,
3176
+ "step": 369
3177
+ },
3178
+ {
3179
+ "epoch": 4.484848484848484,
3180
+ "grad_norm": 0.02200300246477127,
3181
+ "learning_rate": 2.871478969537206e-06,
3182
+ "loss": 0.0099,
3183
+ "step": 370
3184
+ },
3185
+ {
3186
+ "epoch": 4.484848484848484,
3187
+ "eval_loss": 0.02058413252234459,
3188
+ "eval_runtime": 6.1924,
3189
+ "eval_samples_per_second": 8.074,
3190
+ "eval_steps_per_second": 2.099,
3191
+ "step": 370
3192
+ },
3193
+ {
3194
+ "epoch": 4.496969696969697,
3195
+ "grad_norm": 0.029120702296495438,
3196
+ "learning_rate": 2.731005059692332e-06,
3197
+ "loss": 0.0212,
3198
+ "step": 371
3199
+ },
3200
+ {
3201
+ "epoch": 4.509090909090909,
3202
+ "grad_norm": 0.030737141147255898,
3203
+ "learning_rate": 2.5939574133333312e-06,
3204
+ "loss": 0.0275,
3205
+ "step": 372
3206
+ },
3207
+ {
3208
+ "epoch": 4.5212121212121215,
3209
+ "grad_norm": 0.02619299292564392,
3210
+ "learning_rate": 2.4603459642729863e-06,
3211
+ "loss": 0.0104,
3212
+ "step": 373
3213
+ },
3214
+ {
3215
+ "epoch": 4.533333333333333,
3216
+ "grad_norm": 0.02171757072210312,
3217
+ "learning_rate": 2.330180397253473e-06,
3218
+ "loss": 0.0099,
3219
+ "step": 374
3220
+ },
3221
+ {
3222
+ "epoch": 4.545454545454545,
3223
+ "grad_norm": 0.022865932434797287,
3224
+ "learning_rate": 2.203470147244385e-06,
3225
+ "loss": 0.0118,
3226
+ "step": 375
3227
+ },
3228
+ {
3229
+ "epoch": 4.545454545454545,
3230
+ "eval_loss": 0.020584262907505035,
3231
+ "eval_runtime": 6.193,
3232
+ "eval_samples_per_second": 8.074,
3233
+ "eval_steps_per_second": 2.099,
3234
+ "step": 375
3235
+ },
3236
+ {
3237
+ "epoch": 4.557575757575758,
3238
+ "grad_norm": 0.02180948108434677,
3239
+ "learning_rate": 2.0802243987588066e-06,
3240
+ "loss": 0.0104,
3241
+ "step": 376
3242
+ },
3243
+ {
3244
+ "epoch": 4.569696969696969,
3245
+ "grad_norm": 0.027300819754600525,
3246
+ "learning_rate": 1.9604520851876198e-06,
3247
+ "loss": 0.0121,
3248
+ "step": 377
3249
+ },
3250
+ {
3251
+ "epoch": 4.581818181818182,
3252
+ "grad_norm": 0.027127033099532127,
3253
+ "learning_rate": 1.8441618881519184e-06,
3254
+ "loss": 0.0113,
3255
+ "step": 378
3256
+ },
3257
+ {
3258
+ "epoch": 4.593939393939394,
3259
+ "grad_norm": 0.026878971606492996,
3260
+ "learning_rate": 1.7313622368738014e-06,
3261
+ "loss": 0.0105,
3262
+ "step": 379
3263
+ },
3264
+ {
3265
+ "epoch": 4.606060606060606,
3266
+ "grad_norm": 0.02648119069635868,
3267
+ "learning_rate": 1.6220613075653202e-06,
3268
+ "loss": 0.0119,
3269
+ "step": 380
3270
+ },
3271
+ {
3272
+ "epoch": 4.606060606060606,
3273
+ "eval_loss": 0.02056843228638172,
3274
+ "eval_runtime": 6.1957,
3275
+ "eval_samples_per_second": 8.07,
3276
+ "eval_steps_per_second": 2.098,
3277
+ "step": 380
3278
+ },
3279
+ {
3280
+ "epoch": 4.618181818181818,
3281
+ "grad_norm": 0.026216818019747734,
3282
+ "learning_rate": 1.51626702283586e-06,
3283
+ "loss": 0.0098,
3284
+ "step": 381
3285
+ },
3286
+ {
3287
+ "epoch": 4.63030303030303,
3288
+ "grad_norm": 0.02351340465247631,
3289
+ "learning_rate": 1.4139870511178766e-06,
3290
+ "loss": 0.0116,
3291
+ "step": 382
3292
+ },
3293
+ {
3294
+ "epoch": 4.642424242424243,
3295
+ "grad_norm": 0.030724933370947838,
3296
+ "learning_rate": 1.3152288061110518e-06,
3297
+ "loss": 0.0101,
3298
+ "step": 383
3299
+ },
3300
+ {
3301
+ "epoch": 4.654545454545454,
3302
+ "grad_norm": 0.02688099816441536,
3303
+ "learning_rate": 1.2199994462448904e-06,
3304
+ "loss": 0.0113,
3305
+ "step": 384
3306
+ },
3307
+ {
3308
+ "epoch": 4.666666666666667,
3309
+ "grad_norm": 0.02722257934510708,
3310
+ "learning_rate": 1.128305874159896e-06,
3311
+ "loss": 0.0114,
3312
+ "step": 385
3313
+ },
3314
+ {
3315
+ "epoch": 4.666666666666667,
3316
+ "eval_loss": 0.02059413306415081,
3317
+ "eval_runtime": 6.2059,
3318
+ "eval_samples_per_second": 8.057,
3319
+ "eval_steps_per_second": 2.095,
3320
+ "step": 385
3321
+ },
3322
+ {
3323
+ "epoch": 4.678787878787879,
3324
+ "grad_norm": 0.02383565530180931,
3325
+ "learning_rate": 1.040154736207194e-06,
3326
+ "loss": 0.0106,
3327
+ "step": 386
3328
+ },
3329
+ {
3330
+ "epoch": 4.690909090909091,
3331
+ "grad_norm": 0.028037432581186295,
3332
+ "learning_rate": 9.555524219667989e-07,
3333
+ "loss": 0.0122,
3334
+ "step": 387
3335
+ },
3336
+ {
3337
+ "epoch": 4.703030303030303,
3338
+ "grad_norm": 0.021838784217834473,
3339
+ "learning_rate": 8.745050637844532e-07,
3340
+ "loss": 0.0097,
3341
+ "step": 388
3342
+ },
3343
+ {
3344
+ "epoch": 4.715151515151515,
3345
+ "grad_norm": 0.030912073329091072,
3346
+ "learning_rate": 7.970185363271431e-07,
3347
+ "loss": 0.0121,
3348
+ "step": 389
3349
+ },
3350
+ {
3351
+ "epoch": 4.7272727272727275,
3352
+ "grad_norm": 0.02470664493739605,
3353
+ "learning_rate": 7.230984561572729e-07,
3354
+ "loss": 0.0109,
3355
+ "step": 390
3356
+ },
3357
+ {
3358
+ "epoch": 4.7272727272727275,
3359
+ "eval_loss": 0.020591916516423225,
3360
+ "eval_runtime": 6.1901,
3361
+ "eval_samples_per_second": 8.077,
3362
+ "eval_steps_per_second": 2.1,
3363
+ "step": 390
3364
+ },
3365
+ {
3366
+ "epoch": 4.739393939393939,
3367
+ "grad_norm": 0.030810924246907234,
3368
+ "learning_rate": 6.527501813255344e-07,
3369
+ "loss": 0.0165,
3370
+ "step": 391
3371
+ },
3372
+ {
3373
+ "epoch": 4.751515151515152,
3374
+ "grad_norm": 0.025043383240699768,
3375
+ "learning_rate": 5.859788109825793e-07,
3376
+ "loss": 0.0096,
3377
+ "step": 392
3378
+ },
3379
+ {
3380
+ "epoch": 4.763636363636364,
3381
+ "grad_norm": 0.028706299141049385,
3382
+ "learning_rate": 5.227891850093314e-07,
3383
+ "loss": 0.0129,
3384
+ "step": 393
3385
+ },
3386
+ {
3387
+ "epoch": 4.775757575757575,
3388
+ "grad_norm": 0.0277020912617445,
3389
+ "learning_rate": 4.6318588366625616e-07,
3390
+ "loss": 0.0122,
3391
+ "step": 394
3392
+ },
3393
+ {
3394
+ "epoch": 4.787878787878788,
3395
+ "grad_norm": 0.02909735217690468,
3396
+ "learning_rate": 4.071732272613149e-07,
3397
+ "loss": 0.0124,
3398
+ "step": 395
3399
+ },
3400
+ {
3401
+ "epoch": 4.787878787878788,
3402
+ "eval_loss": 0.020531287416815758,
3403
+ "eval_runtime": 6.1957,
3404
+ "eval_samples_per_second": 8.07,
3405
+ "eval_steps_per_second": 2.098,
3406
+ "step": 395
3407
+ },
3408
+ {
3409
+ "epoch": 4.8,
3410
+ "grad_norm": 0.024658478796482086,
3411
+ "learning_rate": 3.5475527583681e-07,
3412
+ "loss": 0.0112,
3413
+ "step": 396
3414
+ },
3415
+ {
3416
+ "epoch": 4.8121212121212125,
3417
+ "grad_norm": 0.023081207647919655,
3418
+ "learning_rate": 3.059358288751202e-07,
3419
+ "loss": 0.0102,
3420
+ "step": 397
3421
+ },
3422
+ {
3423
+ "epoch": 4.824242424242424,
3424
+ "grad_norm": 0.03320831060409546,
3425
+ "learning_rate": 2.6071842502326527e-07,
3426
+ "loss": 0.0119,
3427
+ "step": 398
3428
+ },
3429
+ {
3430
+ "epoch": 4.836363636363636,
3431
+ "grad_norm": 0.025276964530348778,
3432
+ "learning_rate": 2.1910634183644474e-07,
3433
+ "loss": 0.0117,
3434
+ "step": 399
3435
+ },
3436
+ {
3437
+ "epoch": 4.848484848484849,
3438
+ "grad_norm": 0.02636777050793171,
3439
+ "learning_rate": 1.811025955404333e-07,
3440
+ "loss": 0.0111,
3441
+ "step": 400
3442
+ },
3443
+ {
3444
+ "epoch": 4.848484848484849,
3445
+ "eval_loss": 0.020571600645780563,
3446
+ "eval_runtime": 6.1951,
3447
+ "eval_samples_per_second": 8.071,
3448
+ "eval_steps_per_second": 2.098,
3449
+ "step": 400
3450
+ },
3451
+ {
3452
+ "epoch": 4.86060606060606,
3453
+ "grad_norm": 0.0283295139670372,
3454
+ "learning_rate": 1.4670994081297795e-07,
3455
+ "loss": 0.0141,
3456
+ "step": 401
3457
+ },
3458
+ {
3459
+ "epoch": 4.872727272727273,
3460
+ "grad_norm": 0.025880116969347,
3461
+ "learning_rate": 1.1593087058410779e-07,
3462
+ "loss": 0.0113,
3463
+ "step": 402
3464
+ },
3465
+ {
3466
+ "epoch": 4.884848484848485,
3467
+ "grad_norm": 0.02684679627418518,
3468
+ "learning_rate": 8.876761585545068e-08,
3469
+ "loss": 0.0104,
3470
+ "step": 403
3471
+ },
3472
+ {
3473
+ "epoch": 4.8969696969696965,
3474
+ "grad_norm": 0.027327047660946846,
3475
+ "learning_rate": 6.522214553850159e-08,
3476
+ "loss": 0.0122,
3477
+ "step": 404
3478
+ },
3479
+ {
3480
+ "epoch": 4.909090909090909,
3481
+ "grad_norm": 0.033394601196050644,
3482
+ "learning_rate": 4.529616631193112e-08,
3483
+ "loss": 0.012,
3484
+ "step": 405
3485
+ },
3486
+ {
3487
+ "epoch": 4.909090909090909,
3488
+ "eval_loss": 0.020557112991809845,
3489
+ "eval_runtime": 6.1866,
3490
+ "eval_samples_per_second": 8.082,
3491
+ "eval_steps_per_second": 2.101,
3492
+ "step": 405
3493
+ },
3494
+ {
3495
+ "epoch": 4.921212121212121,
3496
+ "grad_norm": 0.02917388454079628,
3497
+ "learning_rate": 2.899112249786229e-08,
3498
+ "loss": 0.0115,
3499
+ "step": 406
3500
+ },
3501
+ {
3502
+ "epoch": 4.933333333333334,
3503
+ "grad_norm": 0.032552849501371384,
3504
+ "learning_rate": 1.6308195957182027e-08,
3505
+ "loss": 0.0125,
3506
+ "step": 407
3507
+ },
3508
+ {
3509
+ "epoch": 4.945454545454545,
3510
+ "grad_norm": 0.026771927252411842,
3511
+ "learning_rate": 7.248306003865279e-09,
3512
+ "loss": 0.0123,
3513
+ "step": 408
3514
+ },
3515
+ {
3516
+ "epoch": 4.957575757575757,
3517
+ "grad_norm": 0.024449503049254417,
3518
+ "learning_rate": 1.8121093383671738e-09,
3519
+ "loss": 0.0117,
3520
+ "step": 409
3521
+ },
3522
+ {
3523
+ "epoch": 4.96969696969697,
3524
+ "grad_norm": 0.02603001333773136,
3525
+ "learning_rate": 0.0,
3526
+ "loss": 0.0104,
3527
+ "step": 410
3528
+ },
3529
+ {
3530
+ "epoch": 4.96969696969697,
3531
+ "eval_loss": 0.020535213872790337,
3532
+ "eval_runtime": 6.2062,
3533
+ "eval_samples_per_second": 8.056,
3534
+ "eval_steps_per_second": 2.095,
3535
+ "step": 410
3536
+ },
3537
+ {
3538
+ "epoch": 4.96969696969697,
3539
+ "step": 410,
3540
+ "total_flos": 6.27193584892674e+17,
3541
+ "train_loss": 0.027697906577278202,
3542
+ "train_runtime": 5078.5288,
3543
+ "train_samples_per_second": 2.598,
3544
+ "train_steps_per_second": 0.081
3545
+ }
3546
+ ],
3547
+ "logging_steps": 1,
3548
+ "max_steps": 410,
3549
+ "num_input_tokens_seen": 0,
3550
+ "num_train_epochs": 5,
3551
+ "save_steps": 50,
3552
+ "stateful_callbacks": {
3553
+ "TrainerControl": {
3554
+ "args": {
3555
+ "should_epoch_stop": false,
3556
+ "should_evaluate": false,
3557
+ "should_log": false,
3558
+ "should_save": true,
3559
+ "should_training_stop": true
3560
+ },
3561
+ "attributes": {}
3562
+ }
3563
+ },
3564
+ "total_flos": 6.27193584892674e+17,
3565
+ "train_batch_size": 4,
3566
+ "trial_name": null,
3567
+ "trial_params": null
3568
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96aa9d85c0c8aaa8150b6566c50c34edbca6adae21b4dd043144f9d0462346e
3
+ size 5496
training_eval_loss.png ADDED
training_loss.png ADDED