kloodia commited on
Commit
2442c9d
1 Parent(s): e6259ac

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +154 -0
  2. adapter_config.json +34 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-1096/README.md +202 -0
  5. checkpoint-1096/adapter_config.json +34 -0
  6. checkpoint-1096/adapter_model.safetensors +3 -0
  7. checkpoint-1096/optimizer.pt +3 -0
  8. checkpoint-1096/rng_state_0.pth +3 -0
  9. checkpoint-1096/rng_state_1.pth +3 -0
  10. checkpoint-1096/rng_state_2.pth +3 -0
  11. checkpoint-1096/rng_state_3.pth +3 -0
  12. checkpoint-1096/scheduler.pt +3 -0
  13. checkpoint-1096/special_tokens_map.json +23 -0
  14. checkpoint-1096/tokenizer.json +0 -0
  15. checkpoint-1096/tokenizer_config.json +2062 -0
  16. checkpoint-1096/trainer_state.json +0 -0
  17. checkpoint-1096/training_args.bin +3 -0
  18. checkpoint-1644/README.md +202 -0
  19. checkpoint-1644/adapter_config.json +34 -0
  20. checkpoint-1644/adapter_model.safetensors +3 -0
  21. checkpoint-1644/optimizer.pt +3 -0
  22. checkpoint-1644/rng_state_0.pth +3 -0
  23. checkpoint-1644/rng_state_1.pth +3 -0
  24. checkpoint-1644/rng_state_2.pth +3 -0
  25. checkpoint-1644/rng_state_3.pth +3 -0
  26. checkpoint-1644/scheduler.pt +3 -0
  27. checkpoint-1644/special_tokens_map.json +23 -0
  28. checkpoint-1644/tokenizer.json +0 -0
  29. checkpoint-1644/tokenizer_config.json +2062 -0
  30. checkpoint-1644/trainer_state.json +0 -0
  31. checkpoint-1644/training_args.bin +3 -0
  32. checkpoint-548/README.md +202 -0
  33. checkpoint-548/adapter_config.json +34 -0
  34. checkpoint-548/adapter_model.safetensors +3 -0
  35. checkpoint-548/optimizer.pt +3 -0
  36. checkpoint-548/rng_state_0.pth +3 -0
  37. checkpoint-548/rng_state_1.pth +3 -0
  38. checkpoint-548/rng_state_2.pth +3 -0
  39. checkpoint-548/rng_state_3.pth +3 -0
  40. checkpoint-548/scheduler.pt +3 -0
  41. checkpoint-548/special_tokens_map.json +23 -0
  42. checkpoint-548/tokenizer.json +0 -0
  43. checkpoint-548/tokenizer_config.json +2062 -0
  44. checkpoint-548/trainer_state.json +3897 -0
  45. checkpoint-548/training_args.bin +3 -0
  46. config.json +43 -0
  47. runs/Apr29_09-19-25_5912cc4aac40/events.out.tfevents.1714382369.5912cc4aac40.532.0 +3 -0
  48. runs/Apr29_09-24-53_5912cc4aac40/events.out.tfevents.1714382696.5912cc4aac40.3175.0 +3 -0
  49. special_tokens_map.json +23 -0
  50. tokenizer.json +0 -0
README.md ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: meta-llama/Meta-Llama-3-8B
7
+ model-index:
8
+ - name: lora-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ base_model: meta-llama/Meta-Llama-3-8B
21
+ model_type: LlamaForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+
24
+ load_in_8bit: true
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: kloodia/raw_bio
30
+ type: oasst
31
+ dataset_prepared_path:
32
+ val_set_size: 0.05
33
+ output_dir: ./lora-out
34
+
35
+ sequence_len: 4096
36
+ sample_packing: true
37
+ pad_to_sequence_len: true
38
+
39
+ adapter: lora
40
+ lora_model_dir:
41
+ lora_r: 32
42
+ lora_alpha: 16
43
+ lora_dropout: 0.05
44
+ lora_target_linear: true
45
+ lora_fan_in_fan_out:
46
+
47
+ wandb_project:
48
+ wandb_entity:
49
+ wandb_watch:
50
+ wandb_name:
51
+ wandb_log_model:
52
+
53
+ gradient_accumulation_steps: 4
54
+ micro_batch_size: 1
55
+ num_epochs: 3
56
+ optimizer: adamw_bnb_8bit
57
+ lr_scheduler: cosine
58
+ learning_rate: 0.0002
59
+
60
+ train_on_inputs: false
61
+ group_by_length: false
62
+ bf16: auto
63
+ fp16:
64
+ tf32: false
65
+
66
+ gradient_checkpointing: true
67
+ early_stopping_patience:
68
+ resume_from_checkpoint:
69
+ local_rank:
70
+ logging_steps: 1
71
+ xformers_attention:
72
+ flash_attention: true
73
+ s2_attention:
74
+
75
+ warmup_steps: 10
76
+ evals_per_epoch: 4
77
+ eval_table_size:
78
+ eval_max_new_tokens: 128
79
+ saves_per_epoch: 1
80
+ debug:
81
+ deepspeed:
82
+ weight_decay: 0.0
83
+ fsdp:
84
+ fsdp_config:
85
+ special_tokens:
86
+ pad_token: <|end_of_text|>
87
+
88
+ ```
89
+
90
+ </details><br>
91
+
92
+ # lora-out
93
+
94
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
95
+ It achieves the following results on the evaluation set:
96
+ - Loss: 1.7317
97
+
98
+ ## Model description
99
+
100
+ More information needed
101
+
102
+ ## Intended uses & limitations
103
+
104
+ More information needed
105
+
106
+ ## Training and evaluation data
107
+
108
+ More information needed
109
+
110
+ ## Training procedure
111
+
112
+ ### Training hyperparameters
113
+
114
+ The following hyperparameters were used during training:
115
+ - learning_rate: 0.0002
116
+ - train_batch_size: 1
117
+ - eval_batch_size: 1
118
+ - seed: 42
119
+ - distributed_type: multi-GPU
120
+ - num_devices: 4
121
+ - gradient_accumulation_steps: 4
122
+ - total_train_batch_size: 16
123
+ - total_eval_batch_size: 4
124
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
125
+ - lr_scheduler_type: cosine
126
+ - lr_scheduler_warmup_steps: 10
127
+ - num_epochs: 3
128
+
129
+ ### Training results
130
+
131
+ | Training Loss | Epoch | Step | Validation Loss |
132
+ |:-------------:|:-----:|:----:|:---------------:|
133
+ | 1.795 | 0.0 | 1 | 1.8088 |
134
+ | 1.7519 | 0.25 | 137 | 1.7284 |
135
+ | 1.7442 | 0.5 | 274 | 1.7260 |
136
+ | 1.7182 | 0.75 | 411 | 1.7249 |
137
+ | 1.743 | 1.0 | 548 | 1.7237 |
138
+ | 1.7075 | 1.24 | 685 | 1.7265 |
139
+ | 1.7264 | 1.49 | 822 | 1.7267 |
140
+ | 1.6604 | 1.74 | 959 | 1.7260 |
141
+ | 1.6562 | 1.99 | 1096 | 1.7255 |
142
+ | 1.6455 | 2.22 | 1233 | 1.7308 |
143
+ | 1.6258 | 2.47 | 1370 | 1.7315 |
144
+ | 1.6792 | 2.72 | 1507 | 1.7317 |
145
+ | 1.6364 | 2.97 | 1644 | 1.7317 |
146
+
147
+
148
+ ### Framework versions
149
+
150
+ - PEFT 0.10.0
151
+ - Transformers 4.40.0.dev0
152
+ - Pytorch 2.1.2+cu118
153
+ - Datasets 2.15.0
154
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db06b9fff7c58ed41413d9c70457843810b3b2524cba6923947a42f184337816
3
+ size 335706186
checkpoint-1096/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.10.0
checkpoint-1096/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-1096/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dedd288efdbd47b4a2ebb2c3d178f8bc13c6dd967f3439356002996232edd36
3
+ size 335604696
checkpoint-1096/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc46530dee720d2a86ab902946d23c365ff80ed672729144aff9cede3019074
3
+ size 168625172
checkpoint-1096/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2492bb60f5ec457b2e2e5ab5c9510c7dbd51253f9629ebdcb5da0d2bacb18129
3
+ size 15024
checkpoint-1096/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f855c5f3789e031725eb1e4e35f2cf0e5a75b452d2f6b16520335327d6d1fc
3
+ size 15024
checkpoint-1096/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fd6e1b82907683fbbeea7ada61ea4aa0e9e7287381427daef83a1896541fb0
3
+ size 15024
checkpoint-1096/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60bd679fc791e706067934fe1a2e336ded6d374f96afa54474e20000e44c35f2
3
+ size 15024
checkpoint-1096/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af032506f7ad072bd0842320f6654ff8f10671ed4b2b6df2bb6add615f4e884
3
+ size 1064
checkpoint-1096/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-1096/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1096/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-1096/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1096/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd78228e3983a51f5b936399e1ca9efff3d96013153c81dbb4604c7bc5616374
3
+ size 5752
checkpoint-1644/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.10.0
checkpoint-1644/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-1644/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd589ae3d40d92bc823fc81839f7884a07dd3397fd5d160d8785a09d47b09606
3
+ size 335604696
checkpoint-1644/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e4e5a49da7d371944118ab5dedb087a7579f6c08a44a235a92c5e0ec593628
3
+ size 168625172
checkpoint-1644/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc07d373b0b7a0a24222fa514816fbc9ec6ffa63eb31de3659e312973fc74625
3
+ size 15024
checkpoint-1644/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512ed6f03084b9ff3f24d60fe69f516ff045f75f803186417d592ffdd7fe4a83
3
+ size 15024
checkpoint-1644/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd46715a99662c9925baea34be420c94630b2602efd9faa49fc86d31838a04a1
3
+ size 15024
checkpoint-1644/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6385b25b9dc0191ef426effaf7cf7c48f08609985b05f4592b01e854d2df4b3a
3
+ size 15024
checkpoint-1644/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7b0d52b9f62340ff88ae52519af438d59292757de8acb1474a280daadffaab
3
+ size 1064
checkpoint-1644/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-1644/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1644/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-1644/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1644/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd78228e3983a51f5b936399e1ca9efff3d96013153c81dbb4604c7bc5616374
3
+ size 5752
checkpoint-548/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.10.0
checkpoint-548/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-548/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59aefc1ca53c58d46143157c1911e21ad6c5cca949e81fe383dc52c859d7b4bd
3
+ size 335604696
checkpoint-548/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95bef7bb97a1c9d133cc7577aa0590d5c381ceec66bdb827c2fa7d06522b576
3
+ size 168625172
checkpoint-548/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e52ac1928ad5fcbc8f4174354018d9ac54ccbb5a34113d6fd0e1ae4048808f9
3
+ size 15024
checkpoint-548/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94dc85e01ac2cac3a8d08dece836e3af1b4883b80edd0164fcaafbc69abfd318
3
+ size 15024
checkpoint-548/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18fc2fd84f58f9fa0173ab54e6d9f9d1b9a8d069868c02e0c2442f199125975
3
+ size 15024
checkpoint-548/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb346e9330359c8fb744b05e608e8cf4cb3dd31cc84d9fdc58203b76d00a3a2
3
+ size 15024
checkpoint-548/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041c56476285ce19b0027ba3754fd3871cad8427fd9e12b0a714b2be88587173
3
+ size 1064
checkpoint-548/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-548/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-548/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-548/trainer_state.json ADDED
@@ -0,0 +1,3897 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9990884229717412,
5
+ "eval_steps": 137,
6
+ "global_step": 548,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.07610916346311569,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.795,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 1.8087825775146484,
21
+ "eval_runtime": 75.9539,
22
+ "eval_samples_per_second": 65.829,
23
+ "eval_steps_per_second": 16.457,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0,
28
+ "grad_norm": 0.0771929994225502,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.7825,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 0.08941341191530228,
36
+ "learning_rate": 6e-05,
37
+ "loss": 1.7737,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "grad_norm": 0.08335491269826889,
43
+ "learning_rate": 8e-05,
44
+ "loss": 1.8004,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "grad_norm": 0.08835520595312119,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.8495,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.01,
56
+ "grad_norm": 0.08816578984260559,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.7758,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.01,
63
+ "grad_norm": 0.09536299854516983,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.8001,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.01,
70
+ "grad_norm": 0.07634323835372925,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.7022,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.02,
77
+ "grad_norm": 0.06886536628007889,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.8428,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "grad_norm": 0.07389801740646362,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.7598,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "grad_norm": 0.06829163432121277,
92
+ "learning_rate": 0.00019999981517295864,
93
+ "loss": 1.7479,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.02,
98
+ "grad_norm": 0.060045819729566574,
99
+ "learning_rate": 0.0001999992606925178,
100
+ "loss": 1.7454,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.02,
105
+ "grad_norm": 0.08187604695558548,
106
+ "learning_rate": 0.0001999983365607271,
107
+ "loss": 1.7679,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.03,
112
+ "grad_norm": 0.05995490401983261,
113
+ "learning_rate": 0.00019999704278100263,
114
+ "loss": 1.7599,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.03,
119
+ "grad_norm": 0.055336710065603256,
120
+ "learning_rate": 0.00019999537935812698,
121
+ "loss": 1.8244,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "grad_norm": 0.0541992112994194,
127
+ "learning_rate": 0.00019999334629824895,
128
+ "loss": 1.7756,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "grad_norm": 0.05088195204734802,
134
+ "learning_rate": 0.00019999094360888392,
135
+ "loss": 1.7352,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.03,
140
+ "grad_norm": 0.05157861113548279,
141
+ "learning_rate": 0.00019998817129891346,
142
+ "loss": 1.7634,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.03,
147
+ "grad_norm": 0.055710840970277786,
148
+ "learning_rate": 0.00019998502937858557,
149
+ "loss": 1.7802,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.04,
154
+ "grad_norm": 0.055150121450424194,
155
+ "learning_rate": 0.00019998151785951448,
156
+ "loss": 1.7445,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.04,
161
+ "grad_norm": 0.0526655912399292,
162
+ "learning_rate": 0.0001999776367546806,
163
+ "loss": 1.6634,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.04,
168
+ "grad_norm": 0.04809674620628357,
169
+ "learning_rate": 0.00019997338607843075,
170
+ "loss": 1.7277,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "grad_norm": 0.049412671476602554,
176
+ "learning_rate": 0.00019996876584647754,
177
+ "loss": 1.7357,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.04,
182
+ "grad_norm": 0.04948608949780464,
183
+ "learning_rate": 0.00019996377607589997,
184
+ "loss": 1.7323,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.05,
189
+ "grad_norm": 0.050225820392370224,
190
+ "learning_rate": 0.00019995841678514294,
191
+ "loss": 1.7273,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.05,
196
+ "grad_norm": 0.05085042864084244,
197
+ "learning_rate": 0.00019995268799401718,
198
+ "loss": 1.7564,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.05,
203
+ "grad_norm": 0.04916631057858467,
204
+ "learning_rate": 0.00019994658972369948,
205
+ "loss": 1.7439,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.05,
210
+ "grad_norm": 0.04791415110230446,
211
+ "learning_rate": 0.00019994012199673234,
212
+ "loss": 1.6813,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.05,
217
+ "grad_norm": 0.04975065216422081,
218
+ "learning_rate": 0.00019993328483702393,
219
+ "loss": 1.691,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.05,
224
+ "grad_norm": 0.055913638323545456,
225
+ "learning_rate": 0.00019992607826984816,
226
+ "loss": 1.7242,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.06,
231
+ "grad_norm": 0.045829374343156815,
232
+ "learning_rate": 0.00019991850232184435,
233
+ "loss": 1.7334,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.06,
238
+ "grad_norm": 0.053105831146240234,
239
+ "learning_rate": 0.00019991055702101734,
240
+ "loss": 1.7214,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.06,
245
+ "grad_norm": 0.04539350047707558,
246
+ "learning_rate": 0.00019990224239673722,
247
+ "loss": 1.7698,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.06,
252
+ "grad_norm": 0.046983517706394196,
253
+ "learning_rate": 0.00019989355847973932,
254
+ "loss": 1.6887,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.06,
259
+ "grad_norm": 0.0471692830324173,
260
+ "learning_rate": 0.00019988450530212414,
261
+ "loss": 1.7571,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.07,
266
+ "grad_norm": 0.046874694526195526,
267
+ "learning_rate": 0.00019987508289735716,
268
+ "loss": 1.7558,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.07,
273
+ "grad_norm": 0.04474163055419922,
274
+ "learning_rate": 0.00019986529130026857,
275
+ "loss": 1.7465,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.07,
280
+ "grad_norm": 0.044651810079813004,
281
+ "learning_rate": 0.00019985513054705348,
282
+ "loss": 1.6983,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.07,
287
+ "grad_norm": 0.04951983690261841,
288
+ "learning_rate": 0.00019984460067527153,
289
+ "loss": 1.761,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.07,
294
+ "grad_norm": 0.04424133151769638,
295
+ "learning_rate": 0.00019983370172384682,
296
+ "loss": 1.6383,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.07,
301
+ "grad_norm": 0.052418872714042664,
302
+ "learning_rate": 0.00019982243373306772,
303
+ "loss": 1.779,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.08,
308
+ "grad_norm": 0.04530750587582588,
309
+ "learning_rate": 0.0001998107967445869,
310
+ "loss": 1.6942,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.08,
315
+ "grad_norm": 0.04790988191962242,
316
+ "learning_rate": 0.0001997987908014209,
317
+ "loss": 1.7053,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.08,
322
+ "grad_norm": 0.04889607056975365,
323
+ "learning_rate": 0.0001997864159479502,
324
+ "loss": 1.7275,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.08,
329
+ "grad_norm": 0.04314807429909706,
330
+ "learning_rate": 0.00019977367222991893,
331
+ "loss": 1.7393,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.08,
336
+ "grad_norm": 0.04405505582690239,
337
+ "learning_rate": 0.00019976055969443479,
338
+ "loss": 1.7306,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.09,
343
+ "grad_norm": 0.04656574875116348,
344
+ "learning_rate": 0.00019974707838996882,
345
+ "loss": 1.7686,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.09,
350
+ "grad_norm": 0.04246290400624275,
351
+ "learning_rate": 0.00019973322836635518,
352
+ "loss": 1.7209,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.09,
357
+ "grad_norm": 0.05493748560547829,
358
+ "learning_rate": 0.00019971900967479106,
359
+ "loss": 1.7155,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.09,
364
+ "grad_norm": 0.0450466088950634,
365
+ "learning_rate": 0.0001997044223678364,
366
+ "loss": 1.6604,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.09,
371
+ "grad_norm": 0.08634985238313675,
372
+ "learning_rate": 0.00019968946649941382,
373
+ "loss": 1.7321,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.09,
378
+ "grad_norm": 0.04310084879398346,
379
+ "learning_rate": 0.00019967414212480831,
380
+ "loss": 1.7281,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.1,
385
+ "grad_norm": 0.04666193947196007,
386
+ "learning_rate": 0.000199658449300667,
387
+ "loss": 1.6787,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.1,
392
+ "grad_norm": 0.04957772046327591,
393
+ "learning_rate": 0.00019964238808499907,
394
+ "loss": 1.6919,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.1,
399
+ "grad_norm": 0.0421697273850441,
400
+ "learning_rate": 0.00019962595853717548,
401
+ "loss": 1.7245,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.1,
406
+ "grad_norm": 0.04654068127274513,
407
+ "learning_rate": 0.0001996091607179287,
408
+ "loss": 1.7123,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.1,
413
+ "grad_norm": 0.04076274484395981,
414
+ "learning_rate": 0.00019959199468935258,
415
+ "loss": 1.7066,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.11,
420
+ "grad_norm": 0.04215634986758232,
421
+ "learning_rate": 0.00019957446051490198,
422
+ "loss": 1.7748,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.11,
427
+ "grad_norm": 0.04252045601606369,
428
+ "learning_rate": 0.0001995565582593928,
429
+ "loss": 1.7396,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.11,
434
+ "grad_norm": 0.04455842077732086,
435
+ "learning_rate": 0.00019953828798900135,
436
+ "loss": 1.7236,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.11,
441
+ "grad_norm": 0.044083647429943085,
442
+ "learning_rate": 0.0001995196497712645,
443
+ "loss": 1.7416,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.11,
448
+ "grad_norm": 0.04511955380439758,
449
+ "learning_rate": 0.00019950064367507916,
450
+ "loss": 1.7481,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.11,
455
+ "grad_norm": 0.0424315445125103,
456
+ "learning_rate": 0.00019948126977070217,
457
+ "loss": 1.7712,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.12,
462
+ "grad_norm": 0.04309271275997162,
463
+ "learning_rate": 0.00019946152812974993,
464
+ "loss": 1.6927,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.12,
469
+ "grad_norm": 0.042915165424346924,
470
+ "learning_rate": 0.00019944141882519817,
471
+ "loss": 1.7465,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.12,
476
+ "grad_norm": 0.05950941890478134,
477
+ "learning_rate": 0.00019942094193138186,
478
+ "loss": 1.7035,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.12,
483
+ "grad_norm": 0.042048510164022446,
484
+ "learning_rate": 0.0001994000975239946,
485
+ "loss": 1.7521,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.12,
490
+ "grad_norm": 0.041577938944101334,
491
+ "learning_rate": 0.00019937888568008862,
492
+ "loss": 1.7439,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.13,
497
+ "grad_norm": 0.04538682475686073,
498
+ "learning_rate": 0.00019935730647807436,
499
+ "loss": 1.7528,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.13,
504
+ "grad_norm": 0.04102981090545654,
505
+ "learning_rate": 0.00019933535999772025,
506
+ "loss": 1.6828,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.13,
511
+ "grad_norm": 0.04318905994296074,
512
+ "learning_rate": 0.00019931304632015228,
513
+ "loss": 1.7532,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.13,
518
+ "grad_norm": 0.043007493019104004,
519
+ "learning_rate": 0.00019929036552785397,
520
+ "loss": 1.7353,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.13,
525
+ "grad_norm": 0.04308176040649414,
526
+ "learning_rate": 0.00019926731770466568,
527
+ "loss": 1.6882,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.13,
532
+ "grad_norm": 0.04227353632450104,
533
+ "learning_rate": 0.00019924390293578472,
534
+ "loss": 1.7302,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.14,
539
+ "grad_norm": 0.0429629310965538,
540
+ "learning_rate": 0.0001992201213077647,
541
+ "loss": 1.6822,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.14,
546
+ "grad_norm": 0.042203355580568314,
547
+ "learning_rate": 0.00019919597290851538,
548
+ "loss": 1.7601,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.14,
553
+ "grad_norm": 0.04265713319182396,
554
+ "learning_rate": 0.00019917145782730232,
555
+ "loss": 1.7725,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.14,
560
+ "grad_norm": 0.04848012328147888,
561
+ "learning_rate": 0.00019914657615474653,
562
+ "loss": 1.7587,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.14,
567
+ "grad_norm": 0.042650256305933,
568
+ "learning_rate": 0.00019912132798282408,
569
+ "loss": 1.7422,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.15,
574
+ "grad_norm": 0.04107372462749481,
575
+ "learning_rate": 0.00019909571340486593,
576
+ "loss": 1.7059,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.15,
581
+ "grad_norm": 0.04788720980286598,
582
+ "learning_rate": 0.00019906973251555734,
583
+ "loss": 1.7205,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.15,
588
+ "grad_norm": 0.041231803596019745,
589
+ "learning_rate": 0.0001990433854109378,
590
+ "loss": 1.7277,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.15,
595
+ "grad_norm": 0.04246293380856514,
596
+ "learning_rate": 0.0001990166721884004,
597
+ "loss": 1.7739,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.15,
602
+ "grad_norm": 0.04331424832344055,
603
+ "learning_rate": 0.00019898959294669167,
604
+ "loss": 1.6913,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.15,
609
+ "grad_norm": 0.04720227047801018,
610
+ "learning_rate": 0.00019896214778591115,
611
+ "loss": 1.7079,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.16,
616
+ "grad_norm": 0.05255519971251488,
617
+ "learning_rate": 0.00019893433680751103,
618
+ "loss": 1.7182,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.16,
623
+ "grad_norm": 0.042392294853925705,
624
+ "learning_rate": 0.00019890616011429568,
625
+ "loss": 1.778,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.16,
630
+ "grad_norm": 0.043008286505937576,
631
+ "learning_rate": 0.0001988776178104214,
632
+ "loss": 1.7518,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.16,
637
+ "grad_norm": 0.044135116040706635,
638
+ "learning_rate": 0.00019884871000139595,
639
+ "loss": 1.7534,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.16,
644
+ "grad_norm": 0.041827455163002014,
645
+ "learning_rate": 0.00019881943679407832,
646
+ "loss": 1.7291,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.17,
651
+ "grad_norm": 0.05515114963054657,
652
+ "learning_rate": 0.00019878979829667803,
653
+ "loss": 1.7471,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.17,
658
+ "grad_norm": 0.040826503187417984,
659
+ "learning_rate": 0.00019875979461875503,
660
+ "loss": 1.6408,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.17,
665
+ "grad_norm": 0.04585504159331322,
666
+ "learning_rate": 0.00019872942587121915,
667
+ "loss": 1.6874,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.17,
672
+ "grad_norm": 0.04665527120232582,
673
+ "learning_rate": 0.00019869869216632968,
674
+ "loss": 1.6968,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.17,
679
+ "grad_norm": 0.046703219413757324,
680
+ "learning_rate": 0.000198667593617695,
681
+ "loss": 1.7401,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.18,
686
+ "grad_norm": 0.04115475341677666,
687
+ "learning_rate": 0.00019863613034027224,
688
+ "loss": 1.7227,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.18,
693
+ "grad_norm": 0.04217168688774109,
694
+ "learning_rate": 0.00019860430245036663,
695
+ "loss": 1.7268,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.18,
700
+ "grad_norm": 0.044889383018016815,
701
+ "learning_rate": 0.00019857211006563125,
702
+ "loss": 1.7006,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.18,
707
+ "grad_norm": 0.04161443933844566,
708
+ "learning_rate": 0.00019853955330506663,
709
+ "loss": 1.7266,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.18,
714
+ "grad_norm": 0.042708829045295715,
715
+ "learning_rate": 0.00019850663228902012,
716
+ "loss": 1.7314,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.18,
721
+ "grad_norm": 0.046648308634757996,
722
+ "learning_rate": 0.00019847334713918557,
723
+ "loss": 1.7362,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.19,
728
+ "grad_norm": 0.04414999857544899,
729
+ "learning_rate": 0.00019843969797860294,
730
+ "loss": 1.7065,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.19,
735
+ "grad_norm": 0.04574083164334297,
736
+ "learning_rate": 0.00019840568493165772,
737
+ "loss": 1.7333,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.19,
742
+ "grad_norm": 0.041924796998500824,
743
+ "learning_rate": 0.0001983713081240805,
744
+ "loss": 1.6517,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.19,
749
+ "grad_norm": 0.04238827899098396,
750
+ "learning_rate": 0.00019833656768294662,
751
+ "loss": 1.776,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.19,
756
+ "grad_norm": 0.04292167350649834,
757
+ "learning_rate": 0.00019830146373667548,
758
+ "loss": 1.6601,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.2,
763
+ "grad_norm": 0.0433412566781044,
764
+ "learning_rate": 0.00019826599641503025,
765
+ "loss": 1.6841,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.2,
770
+ "grad_norm": 0.04201202839612961,
771
+ "learning_rate": 0.00019823016584911735,
772
+ "loss": 1.764,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.2,
777
+ "grad_norm": 0.04234587028622627,
778
+ "learning_rate": 0.00019819397217138595,
779
+ "loss": 1.7243,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.2,
784
+ "grad_norm": 0.04268571734428406,
785
+ "learning_rate": 0.0001981574155156274,
786
+ "loss": 1.7656,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.2,
791
+ "grad_norm": 0.041506245732307434,
792
+ "learning_rate": 0.00019812049601697492,
793
+ "loss": 1.6636,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.2,
798
+ "grad_norm": 0.04152766987681389,
799
+ "learning_rate": 0.00019808321381190294,
800
+ "loss": 1.7478,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.21,
805
+ "grad_norm": 0.041750356554985046,
806
+ "learning_rate": 0.00019804556903822663,
807
+ "loss": 1.7518,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.21,
812
+ "grad_norm": 0.04935223609209061,
813
+ "learning_rate": 0.00019800756183510144,
814
+ "loss": 1.7673,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.21,
819
+ "grad_norm": 0.042300984263420105,
820
+ "learning_rate": 0.00019796919234302255,
821
+ "loss": 1.7753,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.21,
826
+ "grad_norm": 0.04224342852830887,
827
+ "learning_rate": 0.00019793046070382437,
828
+ "loss": 1.7226,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.21,
833
+ "grad_norm": 0.044274065643548965,
834
+ "learning_rate": 0.00019789136706067998,
835
+ "loss": 1.7065,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.22,
840
+ "grad_norm": 0.04910755529999733,
841
+ "learning_rate": 0.00019785191155810062,
842
+ "loss": 1.6387,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.22,
847
+ "grad_norm": 0.04774147644639015,
848
+ "learning_rate": 0.00019781209434193515,
849
+ "loss": 1.7297,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.22,
854
+ "grad_norm": 0.04416586086153984,
855
+ "learning_rate": 0.00019777191555936957,
856
+ "loss": 1.8096,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.22,
861
+ "grad_norm": 0.04406105354428291,
862
+ "learning_rate": 0.00019773137535892635,
863
+ "loss": 1.7629,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.22,
868
+ "grad_norm": 0.043473679572343826,
869
+ "learning_rate": 0.00019769047389046402,
870
+ "loss": 1.6979,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.22,
875
+ "grad_norm": 0.04570621997117996,
876
+ "learning_rate": 0.00019764921130517653,
877
+ "loss": 1.7123,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.23,
882
+ "grad_norm": 0.04326749965548515,
883
+ "learning_rate": 0.00019760758775559274,
884
+ "loss": 1.716,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.23,
889
+ "grad_norm": 0.04397182539105415,
890
+ "learning_rate": 0.00019756560339557572,
891
+ "loss": 1.73,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.23,
896
+ "grad_norm": 0.04468885809183121,
897
+ "learning_rate": 0.00019752325838032244,
898
+ "loss": 1.7136,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.23,
903
+ "grad_norm": 0.04554520919919014,
904
+ "learning_rate": 0.00019748055286636295,
905
+ "loss": 1.7448,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.23,
910
+ "grad_norm": 0.04646708443760872,
911
+ "learning_rate": 0.00019743748701155995,
912
+ "loss": 1.6956,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.24,
917
+ "grad_norm": 0.042717937380075455,
918
+ "learning_rate": 0.00019739406097510812,
919
+ "loss": 1.7245,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.24,
924
+ "grad_norm": 0.04367038235068321,
925
+ "learning_rate": 0.00019735027491753353,
926
+ "loss": 1.7102,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.24,
931
+ "grad_norm": 0.04296841099858284,
932
+ "learning_rate": 0.0001973061290006932,
933
+ "loss": 1.7163,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.24,
938
+ "grad_norm": 0.043665811419487,
939
+ "learning_rate": 0.00019726162338777424,
940
+ "loss": 1.7172,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.24,
945
+ "grad_norm": 0.046134624630212784,
946
+ "learning_rate": 0.00019721675824329354,
947
+ "loss": 1.7327,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.24,
952
+ "grad_norm": 0.04857848584651947,
953
+ "learning_rate": 0.00019717153373309692,
954
+ "loss": 1.6647,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.25,
959
+ "grad_norm": 0.047723885625600815,
960
+ "learning_rate": 0.00019712595002435861,
961
+ "loss": 1.7422,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.25,
966
+ "grad_norm": 0.04413154348731041,
967
+ "learning_rate": 0.00019708000728558064,
968
+ "loss": 1.6943,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.25,
973
+ "grad_norm": 0.043105412274599075,
974
+ "learning_rate": 0.00019703370568659225,
975
+ "loss": 1.7519,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.25,
980
+ "eval_loss": 1.7284438610076904,
981
+ "eval_runtime": 76.3963,
982
+ "eval_samples_per_second": 65.448,
983
+ "eval_steps_per_second": 16.362,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.25,
988
+ "grad_norm": 0.04300757125020027,
989
+ "learning_rate": 0.00019698704539854918,
990
+ "loss": 1.7341,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.25,
995
+ "grad_norm": 0.043961744755506516,
996
+ "learning_rate": 0.00019694002659393305,
997
+ "loss": 1.777,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.26,
1002
+ "grad_norm": 0.04376057907938957,
1003
+ "learning_rate": 0.00019689264944655084,
1004
+ "loss": 1.7403,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.26,
1009
+ "grad_norm": 0.04482461139559746,
1010
+ "learning_rate": 0.00019684491413153411,
1011
+ "loss": 1.6852,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.26,
1016
+ "grad_norm": 0.045192863792181015,
1017
+ "learning_rate": 0.0001967968208253384,
1018
+ "loss": 1.7494,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.26,
1023
+ "grad_norm": 0.04361759498715401,
1024
+ "learning_rate": 0.00019674836970574254,
1025
+ "loss": 1.7331,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.26,
1030
+ "grad_norm": 0.04294734448194504,
1031
+ "learning_rate": 0.0001966995609518481,
1032
+ "loss": 1.6375,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.26,
1037
+ "grad_norm": 0.04528161138296127,
1038
+ "learning_rate": 0.00019665039474407863,
1039
+ "loss": 1.746,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.27,
1044
+ "grad_norm": 0.04510699212551117,
1045
+ "learning_rate": 0.00019660087126417906,
1046
+ "loss": 1.7053,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.27,
1051
+ "grad_norm": 0.042807720601558685,
1052
+ "learning_rate": 0.00019655099069521486,
1053
+ "loss": 1.6748,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.27,
1058
+ "grad_norm": 0.04657953232526779,
1059
+ "learning_rate": 0.00019650075322157168,
1060
+ "loss": 1.684,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.27,
1065
+ "grad_norm": 0.04593012481927872,
1066
+ "learning_rate": 0.00019645015902895437,
1067
+ "loss": 1.7076,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.27,
1072
+ "grad_norm": 0.04362139105796814,
1073
+ "learning_rate": 0.0001963992083043864,
1074
+ "loss": 1.6773,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.28,
1079
+ "grad_norm": 0.04773354157805443,
1080
+ "learning_rate": 0.00019634790123620926,
1081
+ "loss": 1.7107,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.28,
1086
+ "grad_norm": 0.05423569679260254,
1087
+ "learning_rate": 0.00019629623801408155,
1088
+ "loss": 1.7052,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.28,
1093
+ "grad_norm": 0.043550509959459305,
1094
+ "learning_rate": 0.00019624421882897855,
1095
+ "loss": 1.7151,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.28,
1100
+ "grad_norm": 0.04896851256489754,
1101
+ "learning_rate": 0.00019619184387319123,
1102
+ "loss": 1.6611,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.28,
1107
+ "grad_norm": 0.04392845928668976,
1108
+ "learning_rate": 0.00019613911334032583,
1109
+ "loss": 1.738,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.28,
1114
+ "grad_norm": 0.04582325741648674,
1115
+ "learning_rate": 0.00019608602742530283,
1116
+ "loss": 1.6885,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.29,
1121
+ "grad_norm": 0.045696284621953964,
1122
+ "learning_rate": 0.00019603258632435656,
1123
+ "loss": 1.7365,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.29,
1128
+ "grad_norm": 0.043873440474271774,
1129
+ "learning_rate": 0.00019597879023503417,
1130
+ "loss": 1.8094,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.29,
1135
+ "grad_norm": 0.05078018456697464,
1136
+ "learning_rate": 0.00019592463935619517,
1137
+ "loss": 1.7341,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.29,
1142
+ "grad_norm": 0.042483873665332794,
1143
+ "learning_rate": 0.00019587013388801047,
1144
+ "loss": 1.7351,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.29,
1149
+ "grad_norm": 0.045154914259910583,
1150
+ "learning_rate": 0.00019581527403196168,
1151
+ "loss": 1.6645,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.3,
1156
+ "grad_norm": 0.04563280567526817,
1157
+ "learning_rate": 0.0001957600599908406,
1158
+ "loss": 1.7069,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.3,
1163
+ "grad_norm": 0.0451313816010952,
1164
+ "learning_rate": 0.00019570449196874815,
1165
+ "loss": 1.7392,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.3,
1170
+ "grad_norm": 0.04682654142379761,
1171
+ "learning_rate": 0.0001956485701710938,
1172
+ "loss": 1.6987,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.3,
1177
+ "grad_norm": 0.04211273416876793,
1178
+ "learning_rate": 0.00019559229480459474,
1179
+ "loss": 1.6973,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.3,
1184
+ "grad_norm": 0.04460490494966507,
1185
+ "learning_rate": 0.00019553566607727517,
1186
+ "loss": 1.7233,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.3,
1191
+ "grad_norm": 0.044608812779188156,
1192
+ "learning_rate": 0.00019547868419846548,
1193
+ "loss": 1.7371,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.31,
1198
+ "grad_norm": 0.04518236592411995,
1199
+ "learning_rate": 0.00019542134937880154,
1200
+ "loss": 1.7257,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.31,
1205
+ "grad_norm": 0.04374237731099129,
1206
+ "learning_rate": 0.00019536366183022384,
1207
+ "loss": 1.7136,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.31,
1212
+ "grad_norm": 0.04429790750145912,
1213
+ "learning_rate": 0.00019530562176597673,
1214
+ "loss": 1.7216,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.31,
1219
+ "grad_norm": 0.04807354509830475,
1220
+ "learning_rate": 0.0001952472294006077,
1221
+ "loss": 1.6568,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.31,
1226
+ "grad_norm": 0.04785493016242981,
1227
+ "learning_rate": 0.00019518848494996655,
1228
+ "loss": 1.7272,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.32,
1233
+ "grad_norm": 0.04472104460000992,
1234
+ "learning_rate": 0.0001951293886312045,
1235
+ "loss": 1.7283,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.32,
1240
+ "grad_norm": 0.04852326214313507,
1241
+ "learning_rate": 0.00019506994066277348,
1242
+ "loss": 1.6968,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.32,
1247
+ "grad_norm": 0.04624422639608383,
1248
+ "learning_rate": 0.0001950101412644254,
1249
+ "loss": 1.758,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.32,
1254
+ "grad_norm": 0.044666189700365067,
1255
+ "learning_rate": 0.00019494999065721108,
1256
+ "loss": 1.6933,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.32,
1261
+ "grad_norm": 0.05367857217788696,
1262
+ "learning_rate": 0.0001948894890634798,
1263
+ "loss": 1.7328,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.32,
1268
+ "grad_norm": 0.046923939138650894,
1269
+ "learning_rate": 0.0001948286367068781,
1270
+ "loss": 1.7367,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.33,
1275
+ "grad_norm": 0.04480034112930298,
1276
+ "learning_rate": 0.00019476743381234926,
1277
+ "loss": 1.7677,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.33,
1282
+ "grad_norm": 0.045380428433418274,
1283
+ "learning_rate": 0.00019470588060613222,
1284
+ "loss": 1.7439,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.33,
1289
+ "grad_norm": 0.04550057277083397,
1290
+ "learning_rate": 0.00019464397731576094,
1291
+ "loss": 1.6895,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.33,
1296
+ "grad_norm": 0.049537234008312225,
1297
+ "learning_rate": 0.00019458172417006347,
1298
+ "loss": 1.7274,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.33,
1303
+ "grad_norm": 0.04696514084935188,
1304
+ "learning_rate": 0.0001945191213991611,
1305
+ "loss": 1.7121,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.34,
1310
+ "grad_norm": 0.04783783480525017,
1311
+ "learning_rate": 0.00019445616923446755,
1312
+ "loss": 1.6942,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.34,
1317
+ "grad_norm": 0.04514686018228531,
1318
+ "learning_rate": 0.00019439286790868802,
1319
+ "loss": 1.7219,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.34,
1324
+ "grad_norm": 0.045743513852357864,
1325
+ "learning_rate": 0.00019432921765581847,
1326
+ "loss": 1.76,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.34,
1331
+ "grad_norm": 0.04406295716762543,
1332
+ "learning_rate": 0.00019426521871114468,
1333
+ "loss": 1.7531,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.34,
1338
+ "grad_norm": 0.04445353150367737,
1339
+ "learning_rate": 0.00019420087131124131,
1340
+ "loss": 1.7742,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.34,
1345
+ "grad_norm": 0.04396241530776024,
1346
+ "learning_rate": 0.0001941361756939712,
1347
+ "loss": 1.7701,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.35,
1352
+ "grad_norm": 0.04415050894021988,
1353
+ "learning_rate": 0.0001940711320984843,
1354
+ "loss": 1.7062,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.35,
1359
+ "grad_norm": 0.04672138765454292,
1360
+ "learning_rate": 0.00019400574076521693,
1361
+ "loss": 1.754,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.35,
1366
+ "grad_norm": 0.04417939484119415,
1367
+ "learning_rate": 0.00019394000193589088,
1368
+ "loss": 1.7357,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.35,
1373
+ "grad_norm": 0.04567494988441467,
1374
+ "learning_rate": 0.00019387391585351234,
1375
+ "loss": 1.752,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.35,
1380
+ "grad_norm": 0.045080311596393585,
1381
+ "learning_rate": 0.00019380748276237123,
1382
+ "loss": 1.736,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.36,
1387
+ "grad_norm": 0.04506627842783928,
1388
+ "learning_rate": 0.0001937407029080402,
1389
+ "loss": 1.6726,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.36,
1394
+ "grad_norm": 0.04523961618542671,
1395
+ "learning_rate": 0.0001936735765373737,
1396
+ "loss": 1.7621,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.36,
1401
+ "grad_norm": 0.04326867312192917,
1402
+ "learning_rate": 0.00019360610389850712,
1403
+ "loss": 1.7341,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.36,
1408
+ "grad_norm": 0.05188523977994919,
1409
+ "learning_rate": 0.00019353828524085577,
1410
+ "loss": 1.7277,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.36,
1415
+ "grad_norm": 0.04654062166810036,
1416
+ "learning_rate": 0.00019347012081511415,
1417
+ "loss": 1.6845,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.36,
1422
+ "grad_norm": 0.044841405004262924,
1423
+ "learning_rate": 0.0001934016108732548,
1424
+ "loss": 1.6611,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.37,
1429
+ "grad_norm": 0.0941338911652565,
1430
+ "learning_rate": 0.00019333275566852756,
1431
+ "loss": 1.6978,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.37,
1436
+ "grad_norm": 0.05048836022615433,
1437
+ "learning_rate": 0.00019326355545545845,
1438
+ "loss": 1.7056,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.37,
1443
+ "grad_norm": 0.046358656138181686,
1444
+ "learning_rate": 0.00019319401048984892,
1445
+ "loss": 1.649,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.37,
1450
+ "grad_norm": 0.04557095095515251,
1451
+ "learning_rate": 0.00019312412102877473,
1452
+ "loss": 1.6793,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.37,
1457
+ "grad_norm": 0.04551040008664131,
1458
+ "learning_rate": 0.0001930538873305852,
1459
+ "loss": 1.7339,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.38,
1464
+ "grad_norm": 0.044258005917072296,
1465
+ "learning_rate": 0.000192983309654902,
1466
+ "loss": 1.6627,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.38,
1471
+ "grad_norm": 0.0485963337123394,
1472
+ "learning_rate": 0.00019291238826261843,
1473
+ "loss": 1.715,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.38,
1478
+ "grad_norm": 0.047103844583034515,
1479
+ "learning_rate": 0.00019284112341589832,
1480
+ "loss": 1.6855,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.38,
1485
+ "grad_norm": 0.045252177864313126,
1486
+ "learning_rate": 0.000192769515378175,
1487
+ "loss": 1.7557,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.38,
1492
+ "grad_norm": 0.049794841557741165,
1493
+ "learning_rate": 0.00019269756441415062,
1494
+ "loss": 1.7116,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.38,
1499
+ "grad_norm": 0.04380947723984718,
1500
+ "learning_rate": 0.00019262527078979478,
1501
+ "loss": 1.7663,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.39,
1506
+ "grad_norm": 0.046488065272569656,
1507
+ "learning_rate": 0.00019255263477234381,
1508
+ "loss": 1.6724,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.39,
1513
+ "grad_norm": 0.0422043539583683,
1514
+ "learning_rate": 0.00019247965663029976,
1515
+ "loss": 1.7345,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.39,
1520
+ "grad_norm": 0.05002991482615471,
1521
+ "learning_rate": 0.0001924063366334293,
1522
+ "loss": 1.7468,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.39,
1527
+ "grad_norm": 0.04376322776079178,
1528
+ "learning_rate": 0.0001923326750527628,
1529
+ "loss": 1.7748,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.39,
1534
+ "grad_norm": 0.04664807394146919,
1535
+ "learning_rate": 0.00019225867216059325,
1536
+ "loss": 1.7156,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.4,
1541
+ "grad_norm": 0.047952812165021896,
1542
+ "learning_rate": 0.0001921843282304754,
1543
+ "loss": 1.7247,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.4,
1548
+ "grad_norm": 0.045118216425180435,
1549
+ "learning_rate": 0.00019210964353722464,
1550
+ "loss": 1.7354,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.4,
1555
+ "grad_norm": 0.054903436452150345,
1556
+ "learning_rate": 0.00019203461835691594,
1557
+ "loss": 1.7241,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.4,
1562
+ "grad_norm": 0.04747498407959938,
1563
+ "learning_rate": 0.000191959252966883,
1564
+ "loss": 1.7498,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.4,
1569
+ "grad_norm": 0.04605628177523613,
1570
+ "learning_rate": 0.000191883547645717,
1571
+ "loss": 1.6889,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.4,
1576
+ "grad_norm": 0.04835960268974304,
1577
+ "learning_rate": 0.00019180750267326578,
1578
+ "loss": 1.715,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.41,
1583
+ "grad_norm": 0.04828386381268501,
1584
+ "learning_rate": 0.00019173111833063273,
1585
+ "loss": 1.6931,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.41,
1590
+ "grad_norm": 0.04604095220565796,
1591
+ "learning_rate": 0.0001916543949001756,
1592
+ "loss": 1.6717,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.41,
1597
+ "grad_norm": 0.049674633890390396,
1598
+ "learning_rate": 0.00019157733266550575,
1599
+ "loss": 1.7746,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.41,
1604
+ "grad_norm": 0.04439341649413109,
1605
+ "learning_rate": 0.00019149993191148687,
1606
+ "loss": 1.6925,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.41,
1611
+ "grad_norm": 0.04741811007261276,
1612
+ "learning_rate": 0.00019142219292423395,
1613
+ "loss": 1.7219,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.42,
1618
+ "grad_norm": 0.049409981817007065,
1619
+ "learning_rate": 0.00019134411599111242,
1620
+ "loss": 1.7306,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.42,
1625
+ "grad_norm": 0.04618163779377937,
1626
+ "learning_rate": 0.00019126570140073676,
1627
+ "loss": 1.7271,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.42,
1632
+ "grad_norm": 0.04557076469063759,
1633
+ "learning_rate": 0.0001911869494429698,
1634
+ "loss": 1.7188,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.42,
1639
+ "grad_norm": 0.04645569249987602,
1640
+ "learning_rate": 0.0001911078604089213,
1641
+ "loss": 1.7191,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.42,
1646
+ "grad_norm": 0.04584849998354912,
1647
+ "learning_rate": 0.0001910284345909471,
1648
+ "loss": 1.7592,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.42,
1653
+ "grad_norm": 0.045582644641399384,
1654
+ "learning_rate": 0.000190948672282648,
1655
+ "loss": 1.6902,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.43,
1660
+ "grad_norm": 0.04627401754260063,
1661
+ "learning_rate": 0.00019086857377886865,
1662
+ "loss": 1.6937,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.43,
1667
+ "grad_norm": 0.04470285400748253,
1668
+ "learning_rate": 0.00019078813937569643,
1669
+ "loss": 1.6977,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.43,
1674
+ "grad_norm": 0.05287547782063484,
1675
+ "learning_rate": 0.00019070736937046035,
1676
+ "loss": 1.7539,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.43,
1681
+ "grad_norm": 0.04990493878722191,
1682
+ "learning_rate": 0.00019062626406173006,
1683
+ "loss": 1.7469,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.43,
1688
+ "grad_norm": 0.048645589500665665,
1689
+ "learning_rate": 0.00019054482374931467,
1690
+ "loss": 1.7037,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.44,
1695
+ "grad_norm": 0.04730357602238655,
1696
+ "learning_rate": 0.0001904630487342616,
1697
+ "loss": 1.7388,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.44,
1702
+ "grad_norm": 0.04754168912768364,
1703
+ "learning_rate": 0.00019038093931885553,
1704
+ "loss": 1.7805,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.44,
1709
+ "grad_norm": 0.04760801047086716,
1710
+ "learning_rate": 0.00019029849580661727,
1711
+ "loss": 1.7383,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.44,
1716
+ "grad_norm": 0.048467203974723816,
1717
+ "learning_rate": 0.0001902157185023026,
1718
+ "loss": 1.7078,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.44,
1723
+ "grad_norm": 0.0522041916847229,
1724
+ "learning_rate": 0.00019013260771190126,
1725
+ "loss": 1.7052,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.44,
1730
+ "grad_norm": 0.0501788929104805,
1731
+ "learning_rate": 0.00019004916374263563,
1732
+ "loss": 1.7818,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.45,
1737
+ "grad_norm": 0.04538620635867119,
1738
+ "learning_rate": 0.00018996538690295979,
1739
+ "loss": 1.6589,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.45,
1744
+ "grad_norm": 0.04511679336428642,
1745
+ "learning_rate": 0.00018988127750255824,
1746
+ "loss": 1.7179,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.45,
1751
+ "grad_norm": 0.04756203666329384,
1752
+ "learning_rate": 0.0001897968358523448,
1753
+ "loss": 1.7333,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.45,
1758
+ "grad_norm": 0.05278336629271507,
1759
+ "learning_rate": 0.00018971206226446147,
1760
+ "loss": 1.7431,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.45,
1765
+ "grad_norm": 0.05926801264286041,
1766
+ "learning_rate": 0.00018962695705227728,
1767
+ "loss": 1.7768,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 0.46,
1772
+ "grad_norm": 0.049290940165519714,
1773
+ "learning_rate": 0.00018954152053038712,
1774
+ "loss": 1.7119,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 0.46,
1779
+ "grad_norm": 0.04777907952666283,
1780
+ "learning_rate": 0.0001894557530146106,
1781
+ "loss": 1.7559,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 0.46,
1786
+ "grad_norm": 0.04726920276880264,
1787
+ "learning_rate": 0.00018936965482199084,
1788
+ "loss": 1.7861,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 0.46,
1793
+ "grad_norm": 0.04677857458591461,
1794
+ "learning_rate": 0.0001892832262707933,
1795
+ "loss": 1.7039,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 0.46,
1800
+ "grad_norm": 0.04724700003862381,
1801
+ "learning_rate": 0.00018919646768050468,
1802
+ "loss": 1.6704,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 0.46,
1807
+ "grad_norm": 0.04969072341918945,
1808
+ "learning_rate": 0.00018910937937183166,
1809
+ "loss": 1.7168,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 0.47,
1814
+ "grad_norm": 0.04533353075385094,
1815
+ "learning_rate": 0.0001890219616666997,
1816
+ "loss": 1.6751,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 0.47,
1821
+ "grad_norm": 0.04647386819124222,
1822
+ "learning_rate": 0.0001889342148882519,
1823
+ "loss": 1.7146,
1824
+ "step": 257
1825
+ },
1826
+ {
1827
+ "epoch": 0.47,
1828
+ "grad_norm": 0.047208696603775024,
1829
+ "learning_rate": 0.00018884613936084784,
1830
+ "loss": 1.7378,
1831
+ "step": 258
1832
+ },
1833
+ {
1834
+ "epoch": 0.47,
1835
+ "grad_norm": 0.04841624200344086,
1836
+ "learning_rate": 0.0001887577354100623,
1837
+ "loss": 1.7128,
1838
+ "step": 259
1839
+ },
1840
+ {
1841
+ "epoch": 0.47,
1842
+ "grad_norm": 0.05073019117116928,
1843
+ "learning_rate": 0.00018866900336268408,
1844
+ "loss": 1.7206,
1845
+ "step": 260
1846
+ },
1847
+ {
1848
+ "epoch": 0.48,
1849
+ "grad_norm": 0.051456011831760406,
1850
+ "learning_rate": 0.00018857994354671482,
1851
+ "loss": 1.755,
1852
+ "step": 261
1853
+ },
1854
+ {
1855
+ "epoch": 0.48,
1856
+ "grad_norm": 0.04637736827135086,
1857
+ "learning_rate": 0.0001884905562913678,
1858
+ "loss": 1.7395,
1859
+ "step": 262
1860
+ },
1861
+ {
1862
+ "epoch": 0.48,
1863
+ "grad_norm": 0.061346374452114105,
1864
+ "learning_rate": 0.00018840084192706658,
1865
+ "loss": 1.674,
1866
+ "step": 263
1867
+ },
1868
+ {
1869
+ "epoch": 0.48,
1870
+ "grad_norm": 0.04413258284330368,
1871
+ "learning_rate": 0.00018831080078544402,
1872
+ "loss": 1.7288,
1873
+ "step": 264
1874
+ },
1875
+ {
1876
+ "epoch": 0.48,
1877
+ "grad_norm": 0.0531301349401474,
1878
+ "learning_rate": 0.0001882204331993409,
1879
+ "loss": 1.7625,
1880
+ "step": 265
1881
+ },
1882
+ {
1883
+ "epoch": 0.48,
1884
+ "grad_norm": 0.05146196484565735,
1885
+ "learning_rate": 0.00018812973950280468,
1886
+ "loss": 1.6815,
1887
+ "step": 266
1888
+ },
1889
+ {
1890
+ "epoch": 0.49,
1891
+ "grad_norm": 0.047678787261247635,
1892
+ "learning_rate": 0.0001880387200310883,
1893
+ "loss": 1.7278,
1894
+ "step": 267
1895
+ },
1896
+ {
1897
+ "epoch": 0.49,
1898
+ "grad_norm": 0.0556582510471344,
1899
+ "learning_rate": 0.0001879473751206489,
1900
+ "loss": 1.74,
1901
+ "step": 268
1902
+ },
1903
+ {
1904
+ "epoch": 0.49,
1905
+ "grad_norm": 0.047515787184238434,
1906
+ "learning_rate": 0.00018785570510914678,
1907
+ "loss": 1.7207,
1908
+ "step": 269
1909
+ },
1910
+ {
1911
+ "epoch": 0.49,
1912
+ "grad_norm": 0.04592055827379227,
1913
+ "learning_rate": 0.0001877637103354438,
1914
+ "loss": 1.6589,
1915
+ "step": 270
1916
+ },
1917
+ {
1918
+ "epoch": 0.49,
1919
+ "grad_norm": 0.04531411454081535,
1920
+ "learning_rate": 0.0001876713911396024,
1921
+ "loss": 1.706,
1922
+ "step": 271
1923
+ },
1924
+ {
1925
+ "epoch": 0.5,
1926
+ "grad_norm": 0.04682420939207077,
1927
+ "learning_rate": 0.0001875787478628843,
1928
+ "loss": 1.7297,
1929
+ "step": 272
1930
+ },
1931
+ {
1932
+ "epoch": 0.5,
1933
+ "grad_norm": 0.04545978829264641,
1934
+ "learning_rate": 0.00018748578084774913,
1935
+ "loss": 1.6572,
1936
+ "step": 273
1937
+ },
1938
+ {
1939
+ "epoch": 0.5,
1940
+ "grad_norm": 0.04849430173635483,
1941
+ "learning_rate": 0.00018739249043785324,
1942
+ "loss": 1.7442,
1943
+ "step": 274
1944
+ },
1945
+ {
1946
+ "epoch": 0.5,
1947
+ "eval_loss": 1.726025938987732,
1948
+ "eval_runtime": 76.0967,
1949
+ "eval_samples_per_second": 65.706,
1950
+ "eval_steps_per_second": 16.426,
1951
+ "step": 274
1952
+ },
1953
+ {
1954
+ "epoch": 0.5,
1955
+ "grad_norm": 0.04745488613843918,
1956
+ "learning_rate": 0.00018729887697804847,
1957
+ "loss": 1.7398,
1958
+ "step": 275
1959
+ },
1960
+ {
1961
+ "epoch": 0.5,
1962
+ "grad_norm": 0.05489857494831085,
1963
+ "learning_rate": 0.00018720494081438078,
1964
+ "loss": 1.701,
1965
+ "step": 276
1966
+ },
1967
+ {
1968
+ "epoch": 0.51,
1969
+ "grad_norm": 0.04818108305335045,
1970
+ "learning_rate": 0.00018711068229408903,
1971
+ "loss": 1.7068,
1972
+ "step": 277
1973
+ },
1974
+ {
1975
+ "epoch": 0.51,
1976
+ "grad_norm": 0.04530555009841919,
1977
+ "learning_rate": 0.0001870161017656037,
1978
+ "loss": 1.6966,
1979
+ "step": 278
1980
+ },
1981
+ {
1982
+ "epoch": 0.51,
1983
+ "grad_norm": 0.045606572180986404,
1984
+ "learning_rate": 0.00018692119957854558,
1985
+ "loss": 1.7086,
1986
+ "step": 279
1987
+ },
1988
+ {
1989
+ "epoch": 0.51,
1990
+ "grad_norm": 0.04626869410276413,
1991
+ "learning_rate": 0.00018682597608372445,
1992
+ "loss": 1.6981,
1993
+ "step": 280
1994
+ },
1995
+ {
1996
+ "epoch": 0.51,
1997
+ "grad_norm": 0.04752146080136299,
1998
+ "learning_rate": 0.0001867304316331379,
1999
+ "loss": 1.692,
2000
+ "step": 281
2001
+ },
2002
+ {
2003
+ "epoch": 0.51,
2004
+ "grad_norm": 0.046230729669332504,
2005
+ "learning_rate": 0.0001866345665799698,
2006
+ "loss": 1.7338,
2007
+ "step": 282
2008
+ },
2009
+ {
2010
+ "epoch": 0.52,
2011
+ "grad_norm": 0.04928119108080864,
2012
+ "learning_rate": 0.00018653838127858933,
2013
+ "loss": 1.738,
2014
+ "step": 283
2015
+ },
2016
+ {
2017
+ "epoch": 0.52,
2018
+ "grad_norm": 0.04641352593898773,
2019
+ "learning_rate": 0.00018644187608454936,
2020
+ "loss": 1.6792,
2021
+ "step": 284
2022
+ },
2023
+ {
2024
+ "epoch": 0.52,
2025
+ "grad_norm": 0.04860611632466316,
2026
+ "learning_rate": 0.00018634505135458525,
2027
+ "loss": 1.663,
2028
+ "step": 285
2029
+ },
2030
+ {
2031
+ "epoch": 0.52,
2032
+ "grad_norm": 0.046515002846717834,
2033
+ "learning_rate": 0.00018624790744661355,
2034
+ "loss": 1.7327,
2035
+ "step": 286
2036
+ },
2037
+ {
2038
+ "epoch": 0.52,
2039
+ "grad_norm": 0.04668186604976654,
2040
+ "learning_rate": 0.00018615044471973074,
2041
+ "loss": 1.6987,
2042
+ "step": 287
2043
+ },
2044
+ {
2045
+ "epoch": 0.53,
2046
+ "grad_norm": 0.047913163900375366,
2047
+ "learning_rate": 0.00018605266353421176,
2048
+ "loss": 1.7953,
2049
+ "step": 288
2050
+ },
2051
+ {
2052
+ "epoch": 0.53,
2053
+ "grad_norm": 0.04924839362502098,
2054
+ "learning_rate": 0.00018595456425150872,
2055
+ "loss": 1.7891,
2056
+ "step": 289
2057
+ },
2058
+ {
2059
+ "epoch": 0.53,
2060
+ "grad_norm": 0.049241986125707626,
2061
+ "learning_rate": 0.00018585614723424962,
2062
+ "loss": 1.7451,
2063
+ "step": 290
2064
+ },
2065
+ {
2066
+ "epoch": 0.53,
2067
+ "grad_norm": 0.05132036283612251,
2068
+ "learning_rate": 0.00018575741284623703,
2069
+ "loss": 1.7598,
2070
+ "step": 291
2071
+ },
2072
+ {
2073
+ "epoch": 0.53,
2074
+ "grad_norm": 0.04659922048449516,
2075
+ "learning_rate": 0.00018565836145244662,
2076
+ "loss": 1.7331,
2077
+ "step": 292
2078
+ },
2079
+ {
2080
+ "epoch": 0.53,
2081
+ "grad_norm": 0.0466977022588253,
2082
+ "learning_rate": 0.0001855589934190259,
2083
+ "loss": 1.7171,
2084
+ "step": 293
2085
+ },
2086
+ {
2087
+ "epoch": 0.54,
2088
+ "grad_norm": 0.049368374049663544,
2089
+ "learning_rate": 0.00018545930911329287,
2090
+ "loss": 1.6929,
2091
+ "step": 294
2092
+ },
2093
+ {
2094
+ "epoch": 0.54,
2095
+ "grad_norm": 0.04552480950951576,
2096
+ "learning_rate": 0.00018535930890373466,
2097
+ "loss": 1.753,
2098
+ "step": 295
2099
+ },
2100
+ {
2101
+ "epoch": 0.54,
2102
+ "grad_norm": 0.04755065590143204,
2103
+ "learning_rate": 0.00018525899316000608,
2104
+ "loss": 1.7472,
2105
+ "step": 296
2106
+ },
2107
+ {
2108
+ "epoch": 0.54,
2109
+ "grad_norm": 0.050540413707494736,
2110
+ "learning_rate": 0.0001851583622529284,
2111
+ "loss": 1.7585,
2112
+ "step": 297
2113
+ },
2114
+ {
2115
+ "epoch": 0.54,
2116
+ "grad_norm": 0.04644971713423729,
2117
+ "learning_rate": 0.00018505741655448792,
2118
+ "loss": 1.7531,
2119
+ "step": 298
2120
+ },
2121
+ {
2122
+ "epoch": 0.55,
2123
+ "grad_norm": 0.05085503309965134,
2124
+ "learning_rate": 0.00018495615643783446,
2125
+ "loss": 1.6954,
2126
+ "step": 299
2127
+ },
2128
+ {
2129
+ "epoch": 0.55,
2130
+ "grad_norm": 0.0480993427336216,
2131
+ "learning_rate": 0.0001848545822772802,
2132
+ "loss": 1.6976,
2133
+ "step": 300
2134
+ },
2135
+ {
2136
+ "epoch": 0.55,
2137
+ "grad_norm": 0.0487300269305706,
2138
+ "learning_rate": 0.00018475269444829818,
2139
+ "loss": 1.7642,
2140
+ "step": 301
2141
+ },
2142
+ {
2143
+ "epoch": 0.55,
2144
+ "grad_norm": 0.04805615171790123,
2145
+ "learning_rate": 0.0001846504933275209,
2146
+ "loss": 1.6666,
2147
+ "step": 302
2148
+ },
2149
+ {
2150
+ "epoch": 0.55,
2151
+ "grad_norm": 0.045554857701063156,
2152
+ "learning_rate": 0.00018454797929273902,
2153
+ "loss": 1.7259,
2154
+ "step": 303
2155
+ },
2156
+ {
2157
+ "epoch": 0.55,
2158
+ "grad_norm": 0.04570743814110756,
2159
+ "learning_rate": 0.00018444515272289982,
2160
+ "loss": 1.7067,
2161
+ "step": 304
2162
+ },
2163
+ {
2164
+ "epoch": 0.56,
2165
+ "grad_norm": 0.047652073204517365,
2166
+ "learning_rate": 0.00018434201399810594,
2167
+ "loss": 1.8147,
2168
+ "step": 305
2169
+ },
2170
+ {
2171
+ "epoch": 0.56,
2172
+ "grad_norm": 0.046781569719314575,
2173
+ "learning_rate": 0.00018423856349961384,
2174
+ "loss": 1.7509,
2175
+ "step": 306
2176
+ },
2177
+ {
2178
+ "epoch": 0.56,
2179
+ "grad_norm": 0.04698612168431282,
2180
+ "learning_rate": 0.00018413480160983254,
2181
+ "loss": 1.7074,
2182
+ "step": 307
2183
+ },
2184
+ {
2185
+ "epoch": 0.56,
2186
+ "grad_norm": 0.04796341061592102,
2187
+ "learning_rate": 0.0001840307287123221,
2188
+ "loss": 1.7444,
2189
+ "step": 308
2190
+ },
2191
+ {
2192
+ "epoch": 0.56,
2193
+ "grad_norm": 0.047553375363349915,
2194
+ "learning_rate": 0.00018392634519179225,
2195
+ "loss": 1.7103,
2196
+ "step": 309
2197
+ },
2198
+ {
2199
+ "epoch": 0.57,
2200
+ "grad_norm": 0.046323925256729126,
2201
+ "learning_rate": 0.00018382165143410092,
2202
+ "loss": 1.716,
2203
+ "step": 310
2204
+ },
2205
+ {
2206
+ "epoch": 0.57,
2207
+ "grad_norm": 0.04571986570954323,
2208
+ "learning_rate": 0.00018371664782625287,
2209
+ "loss": 1.7035,
2210
+ "step": 311
2211
+ },
2212
+ {
2213
+ "epoch": 0.57,
2214
+ "grad_norm": 0.05170504003763199,
2215
+ "learning_rate": 0.0001836113347563982,
2216
+ "loss": 1.7151,
2217
+ "step": 312
2218
+ },
2219
+ {
2220
+ "epoch": 0.57,
2221
+ "grad_norm": 0.047869808971881866,
2222
+ "learning_rate": 0.000183505712613831,
2223
+ "loss": 1.7223,
2224
+ "step": 313
2225
+ },
2226
+ {
2227
+ "epoch": 0.57,
2228
+ "grad_norm": 0.0482964813709259,
2229
+ "learning_rate": 0.0001833997817889878,
2230
+ "loss": 1.6805,
2231
+ "step": 314
2232
+ },
2233
+ {
2234
+ "epoch": 0.57,
2235
+ "grad_norm": 0.0486602708697319,
2236
+ "learning_rate": 0.00018329354267344625,
2237
+ "loss": 1.7303,
2238
+ "step": 315
2239
+ },
2240
+ {
2241
+ "epoch": 0.58,
2242
+ "grad_norm": 0.046554964035749435,
2243
+ "learning_rate": 0.00018318699565992357,
2244
+ "loss": 1.7745,
2245
+ "step": 316
2246
+ },
2247
+ {
2248
+ "epoch": 0.58,
2249
+ "grad_norm": 0.047917045652866364,
2250
+ "learning_rate": 0.00018308014114227513,
2251
+ "loss": 1.718,
2252
+ "step": 317
2253
+ },
2254
+ {
2255
+ "epoch": 0.58,
2256
+ "grad_norm": 0.0479004867374897,
2257
+ "learning_rate": 0.00018297297951549304,
2258
+ "loss": 1.7707,
2259
+ "step": 318
2260
+ },
2261
+ {
2262
+ "epoch": 0.58,
2263
+ "grad_norm": 0.04681101068854332,
2264
+ "learning_rate": 0.0001828655111757046,
2265
+ "loss": 1.7646,
2266
+ "step": 319
2267
+ },
2268
+ {
2269
+ "epoch": 0.58,
2270
+ "grad_norm": 0.05201521888375282,
2271
+ "learning_rate": 0.00018275773652017097,
2272
+ "loss": 1.7479,
2273
+ "step": 320
2274
+ },
2275
+ {
2276
+ "epoch": 0.59,
2277
+ "grad_norm": 0.04852493852376938,
2278
+ "learning_rate": 0.00018264965594728548,
2279
+ "loss": 1.7463,
2280
+ "step": 321
2281
+ },
2282
+ {
2283
+ "epoch": 0.59,
2284
+ "grad_norm": 0.046121757477521896,
2285
+ "learning_rate": 0.00018254126985657246,
2286
+ "loss": 1.7444,
2287
+ "step": 322
2288
+ },
2289
+ {
2290
+ "epoch": 0.59,
2291
+ "grad_norm": 0.05163992941379547,
2292
+ "learning_rate": 0.00018243257864868548,
2293
+ "loss": 1.7134,
2294
+ "step": 323
2295
+ },
2296
+ {
2297
+ "epoch": 0.59,
2298
+ "grad_norm": 0.06267976760864258,
2299
+ "learning_rate": 0.00018232358272540604,
2300
+ "loss": 1.6712,
2301
+ "step": 324
2302
+ },
2303
+ {
2304
+ "epoch": 0.59,
2305
+ "grad_norm": 0.04854287579655647,
2306
+ "learning_rate": 0.00018221428248964202,
2307
+ "loss": 1.6932,
2308
+ "step": 325
2309
+ },
2310
+ {
2311
+ "epoch": 0.59,
2312
+ "grad_norm": 0.046650100499391556,
2313
+ "learning_rate": 0.00018210467834542615,
2314
+ "loss": 1.768,
2315
+ "step": 326
2316
+ },
2317
+ {
2318
+ "epoch": 0.6,
2319
+ "grad_norm": 0.04779491573572159,
2320
+ "learning_rate": 0.00018199477069791474,
2321
+ "loss": 1.7109,
2322
+ "step": 327
2323
+ },
2324
+ {
2325
+ "epoch": 0.6,
2326
+ "grad_norm": 0.05170130729675293,
2327
+ "learning_rate": 0.0001818845599533858,
2328
+ "loss": 1.6926,
2329
+ "step": 328
2330
+ },
2331
+ {
2332
+ "epoch": 0.6,
2333
+ "grad_norm": 0.04867775738239288,
2334
+ "learning_rate": 0.00018177404651923787,
2335
+ "loss": 1.6908,
2336
+ "step": 329
2337
+ },
2338
+ {
2339
+ "epoch": 0.6,
2340
+ "grad_norm": 0.04707460105419159,
2341
+ "learning_rate": 0.00018166323080398835,
2342
+ "loss": 1.7461,
2343
+ "step": 330
2344
+ },
2345
+ {
2346
+ "epoch": 0.6,
2347
+ "grad_norm": 0.048908475786447525,
2348
+ "learning_rate": 0.00018155211321727212,
2349
+ "loss": 1.7214,
2350
+ "step": 331
2351
+ },
2352
+ {
2353
+ "epoch": 0.61,
2354
+ "grad_norm": 0.04802173003554344,
2355
+ "learning_rate": 0.00018144069416983985,
2356
+ "loss": 1.7528,
2357
+ "step": 332
2358
+ },
2359
+ {
2360
+ "epoch": 0.61,
2361
+ "grad_norm": 0.04747573658823967,
2362
+ "learning_rate": 0.00018132897407355657,
2363
+ "loss": 1.6726,
2364
+ "step": 333
2365
+ },
2366
+ {
2367
+ "epoch": 0.61,
2368
+ "grad_norm": 0.049620069563388824,
2369
+ "learning_rate": 0.00018121695334140017,
2370
+ "loss": 1.7215,
2371
+ "step": 334
2372
+ },
2373
+ {
2374
+ "epoch": 0.61,
2375
+ "grad_norm": 0.047733817249536514,
2376
+ "learning_rate": 0.00018110463238745988,
2377
+ "loss": 1.7538,
2378
+ "step": 335
2379
+ },
2380
+ {
2381
+ "epoch": 0.61,
2382
+ "grad_norm": 0.04856455698609352,
2383
+ "learning_rate": 0.00018099201162693476,
2384
+ "loss": 1.6833,
2385
+ "step": 336
2386
+ },
2387
+ {
2388
+ "epoch": 0.61,
2389
+ "grad_norm": 0.04885758087038994,
2390
+ "learning_rate": 0.00018087909147613193,
2391
+ "loss": 1.7141,
2392
+ "step": 337
2393
+ },
2394
+ {
2395
+ "epoch": 0.62,
2396
+ "grad_norm": 0.047947369515895844,
2397
+ "learning_rate": 0.0001807658723524654,
2398
+ "loss": 1.733,
2399
+ "step": 338
2400
+ },
2401
+ {
2402
+ "epoch": 0.62,
2403
+ "grad_norm": 0.0499010868370533,
2404
+ "learning_rate": 0.0001806523546744543,
2405
+ "loss": 1.6825,
2406
+ "step": 339
2407
+ },
2408
+ {
2409
+ "epoch": 0.62,
2410
+ "grad_norm": 0.048193834722042084,
2411
+ "learning_rate": 0.0001805385388617213,
2412
+ "loss": 1.7282,
2413
+ "step": 340
2414
+ },
2415
+ {
2416
+ "epoch": 0.62,
2417
+ "grad_norm": 0.05272866412997246,
2418
+ "learning_rate": 0.00018042442533499123,
2419
+ "loss": 1.7599,
2420
+ "step": 341
2421
+ },
2422
+ {
2423
+ "epoch": 0.62,
2424
+ "grad_norm": 0.047657158225774765,
2425
+ "learning_rate": 0.00018031001451608943,
2426
+ "loss": 1.7292,
2427
+ "step": 342
2428
+ },
2429
+ {
2430
+ "epoch": 0.63,
2431
+ "grad_norm": 0.0498197004199028,
2432
+ "learning_rate": 0.00018019530682794014,
2433
+ "loss": 1.7417,
2434
+ "step": 343
2435
+ },
2436
+ {
2437
+ "epoch": 0.63,
2438
+ "grad_norm": 0.04958554729819298,
2439
+ "learning_rate": 0.00018008030269456505,
2440
+ "loss": 1.7274,
2441
+ "step": 344
2442
+ },
2443
+ {
2444
+ "epoch": 0.63,
2445
+ "grad_norm": 0.04730832576751709,
2446
+ "learning_rate": 0.00017996500254108152,
2447
+ "loss": 1.778,
2448
+ "step": 345
2449
+ },
2450
+ {
2451
+ "epoch": 0.63,
2452
+ "grad_norm": 0.050828639417886734,
2453
+ "learning_rate": 0.0001798494067937014,
2454
+ "loss": 1.7285,
2455
+ "step": 346
2456
+ },
2457
+ {
2458
+ "epoch": 0.63,
2459
+ "grad_norm": 0.046292368322610855,
2460
+ "learning_rate": 0.00017973351587972905,
2461
+ "loss": 1.7334,
2462
+ "step": 347
2463
+ },
2464
+ {
2465
+ "epoch": 0.63,
2466
+ "grad_norm": 0.04758565500378609,
2467
+ "learning_rate": 0.00017961733022755992,
2468
+ "loss": 1.6814,
2469
+ "step": 348
2470
+ },
2471
+ {
2472
+ "epoch": 0.64,
2473
+ "grad_norm": 0.050507742911577225,
2474
+ "learning_rate": 0.00017950085026667903,
2475
+ "loss": 1.6949,
2476
+ "step": 349
2477
+ },
2478
+ {
2479
+ "epoch": 0.64,
2480
+ "grad_norm": 0.04801836982369423,
2481
+ "learning_rate": 0.00017938407642765938,
2482
+ "loss": 1.6594,
2483
+ "step": 350
2484
+ },
2485
+ {
2486
+ "epoch": 0.64,
2487
+ "grad_norm": 0.04616666957736015,
2488
+ "learning_rate": 0.00017926700914216016,
2489
+ "loss": 1.6969,
2490
+ "step": 351
2491
+ },
2492
+ {
2493
+ "epoch": 0.64,
2494
+ "grad_norm": 0.048213839530944824,
2495
+ "learning_rate": 0.00017914964884292544,
2496
+ "loss": 1.6908,
2497
+ "step": 352
2498
+ },
2499
+ {
2500
+ "epoch": 0.64,
2501
+ "grad_norm": 0.04909725859761238,
2502
+ "learning_rate": 0.00017903199596378227,
2503
+ "loss": 1.7213,
2504
+ "step": 353
2505
+ },
2506
+ {
2507
+ "epoch": 0.65,
2508
+ "grad_norm": 0.050252340734004974,
2509
+ "learning_rate": 0.00017891405093963938,
2510
+ "loss": 1.7094,
2511
+ "step": 354
2512
+ },
2513
+ {
2514
+ "epoch": 0.65,
2515
+ "grad_norm": 0.05401075631380081,
2516
+ "learning_rate": 0.00017879581420648534,
2517
+ "loss": 1.7163,
2518
+ "step": 355
2519
+ },
2520
+ {
2521
+ "epoch": 0.65,
2522
+ "grad_norm": 0.05027545616030693,
2523
+ "learning_rate": 0.00017867728620138708,
2524
+ "loss": 1.7362,
2525
+ "step": 356
2526
+ },
2527
+ {
2528
+ "epoch": 0.65,
2529
+ "grad_norm": 0.047479428350925446,
2530
+ "learning_rate": 0.00017855846736248822,
2531
+ "loss": 1.6785,
2532
+ "step": 357
2533
+ },
2534
+ {
2535
+ "epoch": 0.65,
2536
+ "grad_norm": 0.05026884377002716,
2537
+ "learning_rate": 0.0001784393581290074,
2538
+ "loss": 1.7221,
2539
+ "step": 358
2540
+ },
2541
+ {
2542
+ "epoch": 0.65,
2543
+ "grad_norm": 0.04901432618498802,
2544
+ "learning_rate": 0.00017831995894123683,
2545
+ "loss": 1.6401,
2546
+ "step": 359
2547
+ },
2548
+ {
2549
+ "epoch": 0.66,
2550
+ "grad_norm": 0.04764765873551369,
2551
+ "learning_rate": 0.00017820027024054044,
2552
+ "loss": 1.7361,
2553
+ "step": 360
2554
+ },
2555
+ {
2556
+ "epoch": 0.66,
2557
+ "grad_norm": 0.046871528029441833,
2558
+ "learning_rate": 0.0001780802924693524,
2559
+ "loss": 1.7986,
2560
+ "step": 361
2561
+ },
2562
+ {
2563
+ "epoch": 0.66,
2564
+ "grad_norm": 0.05453401803970337,
2565
+ "learning_rate": 0.00017796002607117545,
2566
+ "loss": 1.7447,
2567
+ "step": 362
2568
+ },
2569
+ {
2570
+ "epoch": 0.66,
2571
+ "grad_norm": 0.04958674684166908,
2572
+ "learning_rate": 0.00017783947149057925,
2573
+ "loss": 1.7091,
2574
+ "step": 363
2575
+ },
2576
+ {
2577
+ "epoch": 0.66,
2578
+ "grad_norm": 0.053141675889492035,
2579
+ "learning_rate": 0.0001777186291731987,
2580
+ "loss": 1.6866,
2581
+ "step": 364
2582
+ },
2583
+ {
2584
+ "epoch": 0.67,
2585
+ "grad_norm": 0.047340743243694305,
2586
+ "learning_rate": 0.00017759749956573238,
2587
+ "loss": 1.7191,
2588
+ "step": 365
2589
+ },
2590
+ {
2591
+ "epoch": 0.67,
2592
+ "grad_norm": 0.051203418523073196,
2593
+ "learning_rate": 0.00017747608311594087,
2594
+ "loss": 1.7238,
2595
+ "step": 366
2596
+ },
2597
+ {
2598
+ "epoch": 0.67,
2599
+ "grad_norm": 0.047188933938741684,
2600
+ "learning_rate": 0.00017735438027264495,
2601
+ "loss": 1.762,
2602
+ "step": 367
2603
+ },
2604
+ {
2605
+ "epoch": 0.67,
2606
+ "grad_norm": 0.056479763239622116,
2607
+ "learning_rate": 0.00017723239148572422,
2608
+ "loss": 1.6587,
2609
+ "step": 368
2610
+ },
2611
+ {
2612
+ "epoch": 0.67,
2613
+ "grad_norm": 0.04922572523355484,
2614
+ "learning_rate": 0.00017711011720611514,
2615
+ "loss": 1.6988,
2616
+ "step": 369
2617
+ },
2618
+ {
2619
+ "epoch": 0.67,
2620
+ "grad_norm": 0.046839334070682526,
2621
+ "learning_rate": 0.00017698755788580963,
2622
+ "loss": 1.7092,
2623
+ "step": 370
2624
+ },
2625
+ {
2626
+ "epoch": 0.68,
2627
+ "grad_norm": 0.0491393506526947,
2628
+ "learning_rate": 0.0001768647139778532,
2629
+ "loss": 1.7313,
2630
+ "step": 371
2631
+ },
2632
+ {
2633
+ "epoch": 0.68,
2634
+ "grad_norm": 0.04811710864305496,
2635
+ "learning_rate": 0.0001767415859363434,
2636
+ "loss": 1.8071,
2637
+ "step": 372
2638
+ },
2639
+ {
2640
+ "epoch": 0.68,
2641
+ "grad_norm": 0.04601633548736572,
2642
+ "learning_rate": 0.00017661817421642804,
2643
+ "loss": 1.7594,
2644
+ "step": 373
2645
+ },
2646
+ {
2647
+ "epoch": 0.68,
2648
+ "grad_norm": 0.05098440870642662,
2649
+ "learning_rate": 0.00017649447927430362,
2650
+ "loss": 1.6524,
2651
+ "step": 374
2652
+ },
2653
+ {
2654
+ "epoch": 0.68,
2655
+ "grad_norm": 0.04978582262992859,
2656
+ "learning_rate": 0.00017637050156721346,
2657
+ "loss": 1.7448,
2658
+ "step": 375
2659
+ },
2660
+ {
2661
+ "epoch": 0.69,
2662
+ "grad_norm": 0.05097389221191406,
2663
+ "learning_rate": 0.00017624624155344626,
2664
+ "loss": 1.7362,
2665
+ "step": 376
2666
+ },
2667
+ {
2668
+ "epoch": 0.69,
2669
+ "grad_norm": 0.05258944630622864,
2670
+ "learning_rate": 0.00017612169969233424,
2671
+ "loss": 1.7033,
2672
+ "step": 377
2673
+ },
2674
+ {
2675
+ "epoch": 0.69,
2676
+ "grad_norm": 0.05384654179215431,
2677
+ "learning_rate": 0.0001759968764442515,
2678
+ "loss": 1.6349,
2679
+ "step": 378
2680
+ },
2681
+ {
2682
+ "epoch": 0.69,
2683
+ "grad_norm": 0.047803860157728195,
2684
+ "learning_rate": 0.00017587177227061226,
2685
+ "loss": 1.6655,
2686
+ "step": 379
2687
+ },
2688
+ {
2689
+ "epoch": 0.69,
2690
+ "grad_norm": 0.04812454432249069,
2691
+ "learning_rate": 0.00017574638763386916,
2692
+ "loss": 1.7064,
2693
+ "step": 380
2694
+ },
2695
+ {
2696
+ "epoch": 0.69,
2697
+ "grad_norm": 0.04860275238752365,
2698
+ "learning_rate": 0.00017562072299751163,
2699
+ "loss": 1.6648,
2700
+ "step": 381
2701
+ },
2702
+ {
2703
+ "epoch": 0.7,
2704
+ "grad_norm": 0.049836620688438416,
2705
+ "learning_rate": 0.00017549477882606418,
2706
+ "loss": 1.6957,
2707
+ "step": 382
2708
+ },
2709
+ {
2710
+ "epoch": 0.7,
2711
+ "grad_norm": 0.05114325135946274,
2712
+ "learning_rate": 0.00017536855558508458,
2713
+ "loss": 1.6257,
2714
+ "step": 383
2715
+ },
2716
+ {
2717
+ "epoch": 0.7,
2718
+ "grad_norm": 0.054609425365924835,
2719
+ "learning_rate": 0.00017524205374116214,
2720
+ "loss": 1.6854,
2721
+ "step": 384
2722
+ },
2723
+ {
2724
+ "epoch": 0.7,
2725
+ "grad_norm": 0.04757620766758919,
2726
+ "learning_rate": 0.00017511527376191618,
2727
+ "loss": 1.7425,
2728
+ "step": 385
2729
+ },
2730
+ {
2731
+ "epoch": 0.7,
2732
+ "grad_norm": 0.05384545028209686,
2733
+ "learning_rate": 0.00017498821611599397,
2734
+ "loss": 1.712,
2735
+ "step": 386
2736
+ },
2737
+ {
2738
+ "epoch": 0.71,
2739
+ "grad_norm": 0.04726232588291168,
2740
+ "learning_rate": 0.00017486088127306932,
2741
+ "loss": 1.701,
2742
+ "step": 387
2743
+ },
2744
+ {
2745
+ "epoch": 0.71,
2746
+ "grad_norm": 0.04885297268629074,
2747
+ "learning_rate": 0.0001747332697038407,
2748
+ "loss": 1.7227,
2749
+ "step": 388
2750
+ },
2751
+ {
2752
+ "epoch": 0.71,
2753
+ "grad_norm": 0.04793693870306015,
2754
+ "learning_rate": 0.00017460538188002946,
2755
+ "loss": 1.7058,
2756
+ "step": 389
2757
+ },
2758
+ {
2759
+ "epoch": 0.71,
2760
+ "grad_norm": 0.04942973330616951,
2761
+ "learning_rate": 0.0001744772182743782,
2762
+ "loss": 1.7443,
2763
+ "step": 390
2764
+ },
2765
+ {
2766
+ "epoch": 0.71,
2767
+ "grad_norm": 0.05246872082352638,
2768
+ "learning_rate": 0.00017434877936064886,
2769
+ "loss": 1.6807,
2770
+ "step": 391
2771
+ },
2772
+ {
2773
+ "epoch": 0.71,
2774
+ "grad_norm": 0.04894121363759041,
2775
+ "learning_rate": 0.0001742200656136212,
2776
+ "loss": 1.7963,
2777
+ "step": 392
2778
+ },
2779
+ {
2780
+ "epoch": 0.72,
2781
+ "grad_norm": 0.05082324892282486,
2782
+ "learning_rate": 0.00017409107750909078,
2783
+ "loss": 1.7024,
2784
+ "step": 393
2785
+ },
2786
+ {
2787
+ "epoch": 0.72,
2788
+ "grad_norm": 0.04718152433633804,
2789
+ "learning_rate": 0.00017396181552386741,
2790
+ "loss": 1.711,
2791
+ "step": 394
2792
+ },
2793
+ {
2794
+ "epoch": 0.72,
2795
+ "grad_norm": 0.05174902826547623,
2796
+ "learning_rate": 0.00017383228013577331,
2797
+ "loss": 1.7362,
2798
+ "step": 395
2799
+ },
2800
+ {
2801
+ "epoch": 0.72,
2802
+ "grad_norm": 0.048003047704696655,
2803
+ "learning_rate": 0.0001737024718236413,
2804
+ "loss": 1.6944,
2805
+ "step": 396
2806
+ },
2807
+ {
2808
+ "epoch": 0.72,
2809
+ "grad_norm": 0.0462164506316185,
2810
+ "learning_rate": 0.00017357239106731317,
2811
+ "loss": 1.7297,
2812
+ "step": 397
2813
+ },
2814
+ {
2815
+ "epoch": 0.73,
2816
+ "grad_norm": 0.04808316007256508,
2817
+ "learning_rate": 0.0001734420383476377,
2818
+ "loss": 1.6971,
2819
+ "step": 398
2820
+ },
2821
+ {
2822
+ "epoch": 0.73,
2823
+ "grad_norm": 0.05553476884961128,
2824
+ "learning_rate": 0.00017331141414646904,
2825
+ "loss": 1.7262,
2826
+ "step": 399
2827
+ },
2828
+ {
2829
+ "epoch": 0.73,
2830
+ "grad_norm": 0.046341411769390106,
2831
+ "learning_rate": 0.00017318051894666487,
2832
+ "loss": 1.7135,
2833
+ "step": 400
2834
+ },
2835
+ {
2836
+ "epoch": 0.73,
2837
+ "grad_norm": 0.048155754804611206,
2838
+ "learning_rate": 0.00017304935323208466,
2839
+ "loss": 1.7377,
2840
+ "step": 401
2841
+ },
2842
+ {
2843
+ "epoch": 0.73,
2844
+ "grad_norm": 0.05066389963030815,
2845
+ "learning_rate": 0.00017291791748758785,
2846
+ "loss": 1.6516,
2847
+ "step": 402
2848
+ },
2849
+ {
2850
+ "epoch": 0.73,
2851
+ "grad_norm": 0.05046610161662102,
2852
+ "learning_rate": 0.000172786212199032,
2853
+ "loss": 1.7536,
2854
+ "step": 403
2855
+ },
2856
+ {
2857
+ "epoch": 0.74,
2858
+ "grad_norm": 0.0542440302670002,
2859
+ "learning_rate": 0.00017265423785327107,
2860
+ "loss": 1.7857,
2861
+ "step": 404
2862
+ },
2863
+ {
2864
+ "epoch": 0.74,
2865
+ "grad_norm": 0.04833053797483444,
2866
+ "learning_rate": 0.0001725219949381537,
2867
+ "loss": 1.7594,
2868
+ "step": 405
2869
+ },
2870
+ {
2871
+ "epoch": 0.74,
2872
+ "grad_norm": 0.047335654497146606,
2873
+ "learning_rate": 0.00017238948394252115,
2874
+ "loss": 1.7495,
2875
+ "step": 406
2876
+ },
2877
+ {
2878
+ "epoch": 0.74,
2879
+ "grad_norm": 0.04961543157696724,
2880
+ "learning_rate": 0.00017225670535620576,
2881
+ "loss": 1.7201,
2882
+ "step": 407
2883
+ },
2884
+ {
2885
+ "epoch": 0.74,
2886
+ "grad_norm": 0.04761854186654091,
2887
+ "learning_rate": 0.00017212365967002893,
2888
+ "loss": 1.7522,
2889
+ "step": 408
2890
+ },
2891
+ {
2892
+ "epoch": 0.75,
2893
+ "grad_norm": 0.05010442063212395,
2894
+ "learning_rate": 0.0001719903473757996,
2895
+ "loss": 1.7535,
2896
+ "step": 409
2897
+ },
2898
+ {
2899
+ "epoch": 0.75,
2900
+ "grad_norm": 0.049323149025440216,
2901
+ "learning_rate": 0.000171856768966312,
2902
+ "loss": 1.6984,
2903
+ "step": 410
2904
+ },
2905
+ {
2906
+ "epoch": 0.75,
2907
+ "grad_norm": 0.08661342412233353,
2908
+ "learning_rate": 0.0001717229249353442,
2909
+ "loss": 1.7182,
2910
+ "step": 411
2911
+ },
2912
+ {
2913
+ "epoch": 0.75,
2914
+ "eval_loss": 1.724851131439209,
2915
+ "eval_runtime": 76.3068,
2916
+ "eval_samples_per_second": 65.525,
2917
+ "eval_steps_per_second": 16.381,
2918
+ "step": 411
2919
+ },
2920
+ {
2921
+ "epoch": 0.75,
2922
+ "grad_norm": 0.05118868127465248,
2923
+ "learning_rate": 0.00017158881577765612,
2924
+ "loss": 1.683,
2925
+ "step": 412
2926
+ },
2927
+ {
2928
+ "epoch": 0.75,
2929
+ "grad_norm": 0.053089968860149384,
2930
+ "learning_rate": 0.00017145444198898776,
2931
+ "loss": 1.7162,
2932
+ "step": 413
2933
+ },
2934
+ {
2935
+ "epoch": 0.75,
2936
+ "grad_norm": 0.05191902816295624,
2937
+ "learning_rate": 0.0001713198040660573,
2938
+ "loss": 1.7223,
2939
+ "step": 414
2940
+ },
2941
+ {
2942
+ "epoch": 0.76,
2943
+ "grad_norm": 0.05995416268706322,
2944
+ "learning_rate": 0.00017118490250655932,
2945
+ "loss": 1.7148,
2946
+ "step": 415
2947
+ },
2948
+ {
2949
+ "epoch": 0.76,
2950
+ "grad_norm": 0.04749016463756561,
2951
+ "learning_rate": 0.00017104973780916294,
2952
+ "loss": 1.7364,
2953
+ "step": 416
2954
+ },
2955
+ {
2956
+ "epoch": 0.76,
2957
+ "grad_norm": 0.047870930284261703,
2958
+ "learning_rate": 0.00017091431047351,
2959
+ "loss": 1.7607,
2960
+ "step": 417
2961
+ },
2962
+ {
2963
+ "epoch": 0.76,
2964
+ "grad_norm": 0.04802364483475685,
2965
+ "learning_rate": 0.00017077862100021318,
2966
+ "loss": 1.6957,
2967
+ "step": 418
2968
+ },
2969
+ {
2970
+ "epoch": 0.76,
2971
+ "grad_norm": 0.04796374961733818,
2972
+ "learning_rate": 0.00017064266989085412,
2973
+ "loss": 1.6972,
2974
+ "step": 419
2975
+ },
2976
+ {
2977
+ "epoch": 0.77,
2978
+ "grad_norm": 0.048874564468860626,
2979
+ "learning_rate": 0.00017050645764798164,
2980
+ "loss": 1.736,
2981
+ "step": 420
2982
+ },
2983
+ {
2984
+ "epoch": 0.77,
2985
+ "grad_norm": 0.052477337419986725,
2986
+ "learning_rate": 0.00017036998477510992,
2987
+ "loss": 1.7447,
2988
+ "step": 421
2989
+ },
2990
+ {
2991
+ "epoch": 0.77,
2992
+ "grad_norm": 0.049993280321359634,
2993
+ "learning_rate": 0.00017023325177671647,
2994
+ "loss": 1.7635,
2995
+ "step": 422
2996
+ },
2997
+ {
2998
+ "epoch": 0.77,
2999
+ "grad_norm": 0.09700744599103928,
3000
+ "learning_rate": 0.00017009625915824037,
3001
+ "loss": 1.7402,
3002
+ "step": 423
3003
+ },
3004
+ {
3005
+ "epoch": 0.77,
3006
+ "grad_norm": 0.048865802586078644,
3007
+ "learning_rate": 0.0001699590074260805,
3008
+ "loss": 1.7229,
3009
+ "step": 424
3010
+ },
3011
+ {
3012
+ "epoch": 0.77,
3013
+ "grad_norm": 0.04994821920990944,
3014
+ "learning_rate": 0.00016982149708759343,
3015
+ "loss": 1.672,
3016
+ "step": 425
3017
+ },
3018
+ {
3019
+ "epoch": 0.78,
3020
+ "grad_norm": 0.05008814111351967,
3021
+ "learning_rate": 0.00016968372865109176,
3022
+ "loss": 1.7338,
3023
+ "step": 426
3024
+ },
3025
+ {
3026
+ "epoch": 0.78,
3027
+ "grad_norm": 0.04830687865614891,
3028
+ "learning_rate": 0.00016954570262584214,
3029
+ "loss": 1.7177,
3030
+ "step": 427
3031
+ },
3032
+ {
3033
+ "epoch": 0.78,
3034
+ "grad_norm": 0.04781452193856239,
3035
+ "learning_rate": 0.0001694074195220634,
3036
+ "loss": 1.7628,
3037
+ "step": 428
3038
+ },
3039
+ {
3040
+ "epoch": 0.78,
3041
+ "grad_norm": 0.04739667847752571,
3042
+ "learning_rate": 0.00016926887985092468,
3043
+ "loss": 1.7107,
3044
+ "step": 429
3045
+ },
3046
+ {
3047
+ "epoch": 0.78,
3048
+ "grad_norm": 0.0481286458671093,
3049
+ "learning_rate": 0.00016913008412454357,
3050
+ "loss": 1.7646,
3051
+ "step": 430
3052
+ },
3053
+ {
3054
+ "epoch": 0.79,
3055
+ "grad_norm": 0.06283537298440933,
3056
+ "learning_rate": 0.0001689910328559841,
3057
+ "loss": 1.6896,
3058
+ "step": 431
3059
+ },
3060
+ {
3061
+ "epoch": 0.79,
3062
+ "grad_norm": 0.04944480583071709,
3063
+ "learning_rate": 0.00016885172655925495,
3064
+ "loss": 1.6931,
3065
+ "step": 432
3066
+ },
3067
+ {
3068
+ "epoch": 0.79,
3069
+ "grad_norm": 0.05051645264029503,
3070
+ "learning_rate": 0.00016871216574930754,
3071
+ "loss": 1.7752,
3072
+ "step": 433
3073
+ },
3074
+ {
3075
+ "epoch": 0.79,
3076
+ "grad_norm": 0.05406402051448822,
3077
+ "learning_rate": 0.0001685723509420341,
3078
+ "loss": 1.7203,
3079
+ "step": 434
3080
+ },
3081
+ {
3082
+ "epoch": 0.79,
3083
+ "grad_norm": 0.0995137020945549,
3084
+ "learning_rate": 0.00016843228265426584,
3085
+ "loss": 1.6454,
3086
+ "step": 435
3087
+ },
3088
+ {
3089
+ "epoch": 0.79,
3090
+ "grad_norm": 0.05356389284133911,
3091
+ "learning_rate": 0.00016829196140377085,
3092
+ "loss": 1.7327,
3093
+ "step": 436
3094
+ },
3095
+ {
3096
+ "epoch": 0.8,
3097
+ "grad_norm": 0.04902141913771629,
3098
+ "learning_rate": 0.0001681513877092523,
3099
+ "loss": 1.7262,
3100
+ "step": 437
3101
+ },
3102
+ {
3103
+ "epoch": 0.8,
3104
+ "grad_norm": 0.047820378094911575,
3105
+ "learning_rate": 0.00016801056209034672,
3106
+ "loss": 1.7294,
3107
+ "step": 438
3108
+ },
3109
+ {
3110
+ "epoch": 0.8,
3111
+ "grad_norm": 0.048359643667936325,
3112
+ "learning_rate": 0.00016786948506762164,
3113
+ "loss": 1.6959,
3114
+ "step": 439
3115
+ },
3116
+ {
3117
+ "epoch": 0.8,
3118
+ "grad_norm": 0.04830753803253174,
3119
+ "learning_rate": 0.00016772815716257412,
3120
+ "loss": 1.7714,
3121
+ "step": 440
3122
+ },
3123
+ {
3124
+ "epoch": 0.8,
3125
+ "grad_norm": 0.05318046733736992,
3126
+ "learning_rate": 0.0001675865788976285,
3127
+ "loss": 1.7325,
3128
+ "step": 441
3129
+ },
3130
+ {
3131
+ "epoch": 0.81,
3132
+ "grad_norm": 0.04992082715034485,
3133
+ "learning_rate": 0.0001674447507961346,
3134
+ "loss": 1.7866,
3135
+ "step": 442
3136
+ },
3137
+ {
3138
+ "epoch": 0.81,
3139
+ "grad_norm": 0.05253741890192032,
3140
+ "learning_rate": 0.0001673026733823658,
3141
+ "loss": 1.7273,
3142
+ "step": 443
3143
+ },
3144
+ {
3145
+ "epoch": 0.81,
3146
+ "grad_norm": 0.05121272802352905,
3147
+ "learning_rate": 0.00016716034718151706,
3148
+ "loss": 1.7063,
3149
+ "step": 444
3150
+ },
3151
+ {
3152
+ "epoch": 0.81,
3153
+ "grad_norm": 0.04715156927704811,
3154
+ "learning_rate": 0.000167017772719703,
3155
+ "loss": 1.7575,
3156
+ "step": 445
3157
+ },
3158
+ {
3159
+ "epoch": 0.81,
3160
+ "grad_norm": 0.05717930197715759,
3161
+ "learning_rate": 0.00016687495052395595,
3162
+ "loss": 1.7835,
3163
+ "step": 446
3164
+ },
3165
+ {
3166
+ "epoch": 0.81,
3167
+ "grad_norm": 0.04992460459470749,
3168
+ "learning_rate": 0.00016673188112222394,
3169
+ "loss": 1.7218,
3170
+ "step": 447
3171
+ },
3172
+ {
3173
+ "epoch": 0.82,
3174
+ "grad_norm": 0.0481155663728714,
3175
+ "learning_rate": 0.0001665885650433689,
3176
+ "loss": 1.7269,
3177
+ "step": 448
3178
+ },
3179
+ {
3180
+ "epoch": 0.82,
3181
+ "grad_norm": 0.0485762394964695,
3182
+ "learning_rate": 0.00016644500281716456,
3183
+ "loss": 1.6857,
3184
+ "step": 449
3185
+ },
3186
+ {
3187
+ "epoch": 0.82,
3188
+ "grad_norm": 0.04729575663805008,
3189
+ "learning_rate": 0.00016630119497429457,
3190
+ "loss": 1.7208,
3191
+ "step": 450
3192
+ },
3193
+ {
3194
+ "epoch": 0.82,
3195
+ "grad_norm": 0.051819782704114914,
3196
+ "learning_rate": 0.00016615714204635043,
3197
+ "loss": 1.7117,
3198
+ "step": 451
3199
+ },
3200
+ {
3201
+ "epoch": 0.82,
3202
+ "grad_norm": 0.052782051265239716,
3203
+ "learning_rate": 0.0001660128445658297,
3204
+ "loss": 1.7811,
3205
+ "step": 452
3206
+ },
3207
+ {
3208
+ "epoch": 0.83,
3209
+ "grad_norm": 0.05251288414001465,
3210
+ "learning_rate": 0.00016586830306613393,
3211
+ "loss": 1.7517,
3212
+ "step": 453
3213
+ },
3214
+ {
3215
+ "epoch": 0.83,
3216
+ "grad_norm": 0.047806352376937866,
3217
+ "learning_rate": 0.00016572351808156666,
3218
+ "loss": 1.7132,
3219
+ "step": 454
3220
+ },
3221
+ {
3222
+ "epoch": 0.83,
3223
+ "grad_norm": 0.05114049091935158,
3224
+ "learning_rate": 0.0001655784901473315,
3225
+ "loss": 1.7729,
3226
+ "step": 455
3227
+ },
3228
+ {
3229
+ "epoch": 0.83,
3230
+ "grad_norm": 0.04811178147792816,
3231
+ "learning_rate": 0.00016543321979953007,
3232
+ "loss": 1.7855,
3233
+ "step": 456
3234
+ },
3235
+ {
3236
+ "epoch": 0.83,
3237
+ "grad_norm": 0.05107167363166809,
3238
+ "learning_rate": 0.00016528770757516027,
3239
+ "loss": 1.7331,
3240
+ "step": 457
3241
+ },
3242
+ {
3243
+ "epoch": 0.84,
3244
+ "grad_norm": 0.04712466895580292,
3245
+ "learning_rate": 0.00016514195401211388,
3246
+ "loss": 1.7048,
3247
+ "step": 458
3248
+ },
3249
+ {
3250
+ "epoch": 0.84,
3251
+ "grad_norm": 0.05438878387212753,
3252
+ "learning_rate": 0.0001649959596491749,
3253
+ "loss": 1.753,
3254
+ "step": 459
3255
+ },
3256
+ {
3257
+ "epoch": 0.84,
3258
+ "grad_norm": 0.04884348064661026,
3259
+ "learning_rate": 0.00016484972502601753,
3260
+ "loss": 1.6734,
3261
+ "step": 460
3262
+ },
3263
+ {
3264
+ "epoch": 0.84,
3265
+ "grad_norm": 0.0536276139318943,
3266
+ "learning_rate": 0.00016470325068320392,
3267
+ "loss": 1.711,
3268
+ "step": 461
3269
+ },
3270
+ {
3271
+ "epoch": 0.84,
3272
+ "grad_norm": 0.05346493422985077,
3273
+ "learning_rate": 0.00016455653716218252,
3274
+ "loss": 1.7366,
3275
+ "step": 462
3276
+ },
3277
+ {
3278
+ "epoch": 0.84,
3279
+ "grad_norm": 0.05044522508978844,
3280
+ "learning_rate": 0.0001644095850052858,
3281
+ "loss": 1.7269,
3282
+ "step": 463
3283
+ },
3284
+ {
3285
+ "epoch": 0.85,
3286
+ "grad_norm": 0.05273488536477089,
3287
+ "learning_rate": 0.00016426239475572852,
3288
+ "loss": 1.7586,
3289
+ "step": 464
3290
+ },
3291
+ {
3292
+ "epoch": 0.85,
3293
+ "grad_norm": 0.053452517837285995,
3294
+ "learning_rate": 0.0001641149669576053,
3295
+ "loss": 1.7379,
3296
+ "step": 465
3297
+ },
3298
+ {
3299
+ "epoch": 0.85,
3300
+ "grad_norm": 0.047611016780138016,
3301
+ "learning_rate": 0.00016396730215588915,
3302
+ "loss": 1.7471,
3303
+ "step": 466
3304
+ },
3305
+ {
3306
+ "epoch": 0.85,
3307
+ "grad_norm": 0.05317235738039017,
3308
+ "learning_rate": 0.00016381940089642893,
3309
+ "loss": 1.6925,
3310
+ "step": 467
3311
+ },
3312
+ {
3313
+ "epoch": 0.85,
3314
+ "grad_norm": 0.049223560839891434,
3315
+ "learning_rate": 0.00016367126372594774,
3316
+ "loss": 1.7229,
3317
+ "step": 468
3318
+ },
3319
+ {
3320
+ "epoch": 0.86,
3321
+ "grad_norm": 0.047821756452322006,
3322
+ "learning_rate": 0.0001635228911920407,
3323
+ "loss": 1.7484,
3324
+ "step": 469
3325
+ },
3326
+ {
3327
+ "epoch": 0.86,
3328
+ "grad_norm": 0.05013042315840721,
3329
+ "learning_rate": 0.00016337428384317288,
3330
+ "loss": 1.7435,
3331
+ "step": 470
3332
+ },
3333
+ {
3334
+ "epoch": 0.86,
3335
+ "grad_norm": 0.04820725694298744,
3336
+ "learning_rate": 0.00016322544222867742,
3337
+ "loss": 1.7594,
3338
+ "step": 471
3339
+ },
3340
+ {
3341
+ "epoch": 0.86,
3342
+ "grad_norm": 0.04791193827986717,
3343
+ "learning_rate": 0.00016307636689875347,
3344
+ "loss": 1.644,
3345
+ "step": 472
3346
+ },
3347
+ {
3348
+ "epoch": 0.86,
3349
+ "grad_norm": 0.04905365779995918,
3350
+ "learning_rate": 0.00016292705840446404,
3351
+ "loss": 1.7144,
3352
+ "step": 473
3353
+ },
3354
+ {
3355
+ "epoch": 0.86,
3356
+ "grad_norm": 0.04875028133392334,
3357
+ "learning_rate": 0.00016277751729773407,
3358
+ "loss": 1.712,
3359
+ "step": 474
3360
+ },
3361
+ {
3362
+ "epoch": 0.87,
3363
+ "grad_norm": 0.05170164629817009,
3364
+ "learning_rate": 0.0001626277441313484,
3365
+ "loss": 1.7367,
3366
+ "step": 475
3367
+ },
3368
+ {
3369
+ "epoch": 0.87,
3370
+ "grad_norm": 0.05205371975898743,
3371
+ "learning_rate": 0.00016247773945894962,
3372
+ "loss": 1.689,
3373
+ "step": 476
3374
+ },
3375
+ {
3376
+ "epoch": 0.87,
3377
+ "grad_norm": 0.0485403798520565,
3378
+ "learning_rate": 0.00016232750383503617,
3379
+ "loss": 1.706,
3380
+ "step": 477
3381
+ },
3382
+ {
3383
+ "epoch": 0.87,
3384
+ "grad_norm": 0.0538201630115509,
3385
+ "learning_rate": 0.0001621770378149601,
3386
+ "loss": 1.7284,
3387
+ "step": 478
3388
+ },
3389
+ {
3390
+ "epoch": 0.87,
3391
+ "grad_norm": 0.04828377440571785,
3392
+ "learning_rate": 0.00016202634195492524,
3393
+ "loss": 1.661,
3394
+ "step": 479
3395
+ },
3396
+ {
3397
+ "epoch": 0.88,
3398
+ "grad_norm": 0.050310611724853516,
3399
+ "learning_rate": 0.000161875416811985,
3400
+ "loss": 1.6852,
3401
+ "step": 480
3402
+ },
3403
+ {
3404
+ "epoch": 0.88,
3405
+ "grad_norm": 0.050804853439331055,
3406
+ "learning_rate": 0.00016172426294404032,
3407
+ "loss": 1.7358,
3408
+ "step": 481
3409
+ },
3410
+ {
3411
+ "epoch": 0.88,
3412
+ "grad_norm": 0.051962971687316895,
3413
+ "learning_rate": 0.00016157288090983763,
3414
+ "loss": 1.6692,
3415
+ "step": 482
3416
+ },
3417
+ {
3418
+ "epoch": 0.88,
3419
+ "grad_norm": 0.05179814621806145,
3420
+ "learning_rate": 0.0001614212712689668,
3421
+ "loss": 1.6983,
3422
+ "step": 483
3423
+ },
3424
+ {
3425
+ "epoch": 0.88,
3426
+ "grad_norm": 0.05398216098546982,
3427
+ "learning_rate": 0.00016126943458185907,
3428
+ "loss": 1.7261,
3429
+ "step": 484
3430
+ },
3431
+ {
3432
+ "epoch": 0.88,
3433
+ "grad_norm": 0.049869704991579056,
3434
+ "learning_rate": 0.00016111737140978494,
3435
+ "loss": 1.6951,
3436
+ "step": 485
3437
+ },
3438
+ {
3439
+ "epoch": 0.89,
3440
+ "grad_norm": 0.048107776790857315,
3441
+ "learning_rate": 0.00016096508231485217,
3442
+ "loss": 1.6941,
3443
+ "step": 486
3444
+ },
3445
+ {
3446
+ "epoch": 0.89,
3447
+ "grad_norm": 0.05527656897902489,
3448
+ "learning_rate": 0.00016081256786000357,
3449
+ "loss": 1.7054,
3450
+ "step": 487
3451
+ },
3452
+ {
3453
+ "epoch": 0.89,
3454
+ "grad_norm": 0.05169270187616348,
3455
+ "learning_rate": 0.00016065982860901504,
3456
+ "loss": 1.7307,
3457
+ "step": 488
3458
+ },
3459
+ {
3460
+ "epoch": 0.89,
3461
+ "grad_norm": 0.04972197115421295,
3462
+ "learning_rate": 0.00016050686512649354,
3463
+ "loss": 1.6955,
3464
+ "step": 489
3465
+ },
3466
+ {
3467
+ "epoch": 0.89,
3468
+ "grad_norm": 0.05033208429813385,
3469
+ "learning_rate": 0.00016035367797787476,
3470
+ "loss": 1.7013,
3471
+ "step": 490
3472
+ },
3473
+ {
3474
+ "epoch": 0.9,
3475
+ "grad_norm": 0.05073223263025284,
3476
+ "learning_rate": 0.00016020026772942125,
3477
+ "loss": 1.6831,
3478
+ "step": 491
3479
+ },
3480
+ {
3481
+ "epoch": 0.9,
3482
+ "grad_norm": 0.056367356330156326,
3483
+ "learning_rate": 0.00016004663494822028,
3484
+ "loss": 1.6654,
3485
+ "step": 492
3486
+ },
3487
+ {
3488
+ "epoch": 0.9,
3489
+ "grad_norm": 0.049483008682727814,
3490
+ "learning_rate": 0.0001598927802021817,
3491
+ "loss": 1.7285,
3492
+ "step": 493
3493
+ },
3494
+ {
3495
+ "epoch": 0.9,
3496
+ "grad_norm": 0.052070703357458115,
3497
+ "learning_rate": 0.00015973870406003578,
3498
+ "loss": 1.7948,
3499
+ "step": 494
3500
+ },
3501
+ {
3502
+ "epoch": 0.9,
3503
+ "grad_norm": 0.05687413364648819,
3504
+ "learning_rate": 0.0001595844070913314,
3505
+ "loss": 1.7336,
3506
+ "step": 495
3507
+ },
3508
+ {
3509
+ "epoch": 0.9,
3510
+ "grad_norm": 0.048987727612257004,
3511
+ "learning_rate": 0.00015942988986643352,
3512
+ "loss": 1.6661,
3513
+ "step": 496
3514
+ },
3515
+ {
3516
+ "epoch": 0.91,
3517
+ "grad_norm": 0.05027730017900467,
3518
+ "learning_rate": 0.00015927515295652143,
3519
+ "loss": 1.7364,
3520
+ "step": 497
3521
+ },
3522
+ {
3523
+ "epoch": 0.91,
3524
+ "grad_norm": 0.048406291753053665,
3525
+ "learning_rate": 0.00015912019693358636,
3526
+ "loss": 1.6419,
3527
+ "step": 498
3528
+ },
3529
+ {
3530
+ "epoch": 0.91,
3531
+ "grad_norm": 0.05071192979812622,
3532
+ "learning_rate": 0.00015896502237042963,
3533
+ "loss": 1.6301,
3534
+ "step": 499
3535
+ },
3536
+ {
3537
+ "epoch": 0.91,
3538
+ "grad_norm": 0.05111885070800781,
3539
+ "learning_rate": 0.00015880962984066036,
3540
+ "loss": 1.7112,
3541
+ "step": 500
3542
+ },
3543
+ {
3544
+ "epoch": 0.91,
3545
+ "grad_norm": 0.06297910958528519,
3546
+ "learning_rate": 0.0001586540199186933,
3547
+ "loss": 1.7438,
3548
+ "step": 501
3549
+ },
3550
+ {
3551
+ "epoch": 0.92,
3552
+ "grad_norm": 0.04950469359755516,
3553
+ "learning_rate": 0.00015849819317974694,
3554
+ "loss": 1.6837,
3555
+ "step": 502
3556
+ },
3557
+ {
3558
+ "epoch": 0.92,
3559
+ "grad_norm": 0.04900701716542244,
3560
+ "learning_rate": 0.0001583421501998412,
3561
+ "loss": 1.7432,
3562
+ "step": 503
3563
+ },
3564
+ {
3565
+ "epoch": 0.92,
3566
+ "grad_norm": 0.04949019104242325,
3567
+ "learning_rate": 0.0001581858915557953,
3568
+ "loss": 1.688,
3569
+ "step": 504
3570
+ },
3571
+ {
3572
+ "epoch": 0.92,
3573
+ "grad_norm": 0.05047097057104111,
3574
+ "learning_rate": 0.00015802941782522569,
3575
+ "loss": 1.7256,
3576
+ "step": 505
3577
+ },
3578
+ {
3579
+ "epoch": 0.92,
3580
+ "grad_norm": 0.04921870306134224,
3581
+ "learning_rate": 0.0001578727295865439,
3582
+ "loss": 1.7723,
3583
+ "step": 506
3584
+ },
3585
+ {
3586
+ "epoch": 0.92,
3587
+ "grad_norm": 0.04841122031211853,
3588
+ "learning_rate": 0.0001577158274189544,
3589
+ "loss": 1.71,
3590
+ "step": 507
3591
+ },
3592
+ {
3593
+ "epoch": 0.93,
3594
+ "grad_norm": 0.04886234924197197,
3595
+ "learning_rate": 0.00015755871190245251,
3596
+ "loss": 1.6622,
3597
+ "step": 508
3598
+ },
3599
+ {
3600
+ "epoch": 0.93,
3601
+ "grad_norm": 0.04966573417186737,
3602
+ "learning_rate": 0.00015740138361782207,
3603
+ "loss": 1.7357,
3604
+ "step": 509
3605
+ },
3606
+ {
3607
+ "epoch": 0.93,
3608
+ "grad_norm": 0.050070296972990036,
3609
+ "learning_rate": 0.0001572438431466336,
3610
+ "loss": 1.6803,
3611
+ "step": 510
3612
+ },
3613
+ {
3614
+ "epoch": 0.93,
3615
+ "grad_norm": 0.054121073335409164,
3616
+ "learning_rate": 0.00015708609107124177,
3617
+ "loss": 1.7659,
3618
+ "step": 511
3619
+ },
3620
+ {
3621
+ "epoch": 0.93,
3622
+ "grad_norm": 0.05084529519081116,
3623
+ "learning_rate": 0.00015692812797478368,
3624
+ "loss": 1.6943,
3625
+ "step": 512
3626
+ },
3627
+ {
3628
+ "epoch": 0.94,
3629
+ "grad_norm": 0.056926507502794266,
3630
+ "learning_rate": 0.0001567699544411763,
3631
+ "loss": 1.6562,
3632
+ "step": 513
3633
+ },
3634
+ {
3635
+ "epoch": 0.94,
3636
+ "grad_norm": 0.05053721368312836,
3637
+ "learning_rate": 0.00015661157105511457,
3638
+ "loss": 1.7624,
3639
+ "step": 514
3640
+ },
3641
+ {
3642
+ "epoch": 0.94,
3643
+ "grad_norm": 0.048727016896009445,
3644
+ "learning_rate": 0.00015645297840206915,
3645
+ "loss": 1.7364,
3646
+ "step": 515
3647
+ },
3648
+ {
3649
+ "epoch": 0.94,
3650
+ "grad_norm": 0.051376283168792725,
3651
+ "learning_rate": 0.00015629417706828423,
3652
+ "loss": 1.699,
3653
+ "step": 516
3654
+ },
3655
+ {
3656
+ "epoch": 0.94,
3657
+ "grad_norm": 0.05029591917991638,
3658
+ "learning_rate": 0.00015613516764077548,
3659
+ "loss": 1.6972,
3660
+ "step": 517
3661
+ },
3662
+ {
3663
+ "epoch": 0.94,
3664
+ "grad_norm": 0.053968969732522964,
3665
+ "learning_rate": 0.00015597595070732765,
3666
+ "loss": 1.7128,
3667
+ "step": 518
3668
+ },
3669
+ {
3670
+ "epoch": 0.95,
3671
+ "grad_norm": 0.050694871693849564,
3672
+ "learning_rate": 0.00015581652685649276,
3673
+ "loss": 1.7681,
3674
+ "step": 519
3675
+ },
3676
+ {
3677
+ "epoch": 0.95,
3678
+ "grad_norm": 0.052369993180036545,
3679
+ "learning_rate": 0.00015565689667758746,
3680
+ "loss": 1.7321,
3681
+ "step": 520
3682
+ },
3683
+ {
3684
+ "epoch": 0.95,
3685
+ "grad_norm": 0.04850650206208229,
3686
+ "learning_rate": 0.00015549706076069128,
3687
+ "loss": 1.7162,
3688
+ "step": 521
3689
+ },
3690
+ {
3691
+ "epoch": 0.95,
3692
+ "grad_norm": 0.04979635775089264,
3693
+ "learning_rate": 0.00015533701969664424,
3694
+ "loss": 1.7429,
3695
+ "step": 522
3696
+ },
3697
+ {
3698
+ "epoch": 0.95,
3699
+ "grad_norm": 0.04920853301882744,
3700
+ "learning_rate": 0.0001551767740770446,
3701
+ "loss": 1.7103,
3702
+ "step": 523
3703
+ },
3704
+ {
3705
+ "epoch": 0.96,
3706
+ "grad_norm": 0.05081456899642944,
3707
+ "learning_rate": 0.0001550163244942469,
3708
+ "loss": 1.7781,
3709
+ "step": 524
3710
+ },
3711
+ {
3712
+ "epoch": 0.96,
3713
+ "grad_norm": 0.050754062831401825,
3714
+ "learning_rate": 0.00015485567154135952,
3715
+ "loss": 1.7496,
3716
+ "step": 525
3717
+ },
3718
+ {
3719
+ "epoch": 0.96,
3720
+ "grad_norm": 0.050315603613853455,
3721
+ "learning_rate": 0.00015469481581224272,
3722
+ "loss": 1.7303,
3723
+ "step": 526
3724
+ },
3725
+ {
3726
+ "epoch": 0.96,
3727
+ "grad_norm": 0.05050061643123627,
3728
+ "learning_rate": 0.00015453375790150617,
3729
+ "loss": 1.679,
3730
+ "step": 527
3731
+ },
3732
+ {
3733
+ "epoch": 0.96,
3734
+ "grad_norm": 0.06212810054421425,
3735
+ "learning_rate": 0.00015437249840450715,
3736
+ "loss": 1.713,
3737
+ "step": 528
3738
+ },
3739
+ {
3740
+ "epoch": 0.96,
3741
+ "grad_norm": 0.050966355949640274,
3742
+ "learning_rate": 0.00015421103791734786,
3743
+ "loss": 1.7551,
3744
+ "step": 529
3745
+ },
3746
+ {
3747
+ "epoch": 0.97,
3748
+ "grad_norm": 0.04892159253358841,
3749
+ "learning_rate": 0.00015404937703687363,
3750
+ "loss": 1.6758,
3751
+ "step": 530
3752
+ },
3753
+ {
3754
+ "epoch": 0.97,
3755
+ "grad_norm": 0.05551762133836746,
3756
+ "learning_rate": 0.00015388751636067052,
3757
+ "loss": 1.703,
3758
+ "step": 531
3759
+ },
3760
+ {
3761
+ "epoch": 0.97,
3762
+ "grad_norm": 0.0516047477722168,
3763
+ "learning_rate": 0.00015372545648706306,
3764
+ "loss": 1.7407,
3765
+ "step": 532
3766
+ },
3767
+ {
3768
+ "epoch": 0.97,
3769
+ "grad_norm": 0.05094458907842636,
3770
+ "learning_rate": 0.0001535631980151123,
3771
+ "loss": 1.6534,
3772
+ "step": 533
3773
+ },
3774
+ {
3775
+ "epoch": 0.97,
3776
+ "grad_norm": 0.05045678839087486,
3777
+ "learning_rate": 0.00015340074154461316,
3778
+ "loss": 1.7335,
3779
+ "step": 534
3780
+ },
3781
+ {
3782
+ "epoch": 0.98,
3783
+ "grad_norm": 0.05067756026983261,
3784
+ "learning_rate": 0.00015323808767609277,
3785
+ "loss": 1.7169,
3786
+ "step": 535
3787
+ },
3788
+ {
3789
+ "epoch": 0.98,
3790
+ "grad_norm": 0.05005278438329697,
3791
+ "learning_rate": 0.00015307523701080768,
3792
+ "loss": 1.7778,
3793
+ "step": 536
3794
+ },
3795
+ {
3796
+ "epoch": 0.98,
3797
+ "grad_norm": 0.04952746629714966,
3798
+ "learning_rate": 0.0001529121901507421,
3799
+ "loss": 1.7199,
3800
+ "step": 537
3801
+ },
3802
+ {
3803
+ "epoch": 0.98,
3804
+ "grad_norm": 0.04711218178272247,
3805
+ "learning_rate": 0.00015274894769860538,
3806
+ "loss": 1.734,
3807
+ "step": 538
3808
+ },
3809
+ {
3810
+ "epoch": 0.98,
3811
+ "grad_norm": 0.05313078686594963,
3812
+ "learning_rate": 0.0001525855102578299,
3813
+ "loss": 1.7733,
3814
+ "step": 539
3815
+ },
3816
+ {
3817
+ "epoch": 0.98,
3818
+ "grad_norm": 0.04977120831608772,
3819
+ "learning_rate": 0.0001524218784325688,
3820
+ "loss": 1.731,
3821
+ "step": 540
3822
+ },
3823
+ {
3824
+ "epoch": 0.99,
3825
+ "grad_norm": 0.05076899752020836,
3826
+ "learning_rate": 0.00015225805282769383,
3827
+ "loss": 1.7277,
3828
+ "step": 541
3829
+ },
3830
+ {
3831
+ "epoch": 0.99,
3832
+ "grad_norm": 0.049164701253175735,
3833
+ "learning_rate": 0.00015209403404879303,
3834
+ "loss": 1.7032,
3835
+ "step": 542
3836
+ },
3837
+ {
3838
+ "epoch": 0.99,
3839
+ "grad_norm": 0.0488349013030529,
3840
+ "learning_rate": 0.00015192982270216854,
3841
+ "loss": 1.765,
3842
+ "step": 543
3843
+ },
3844
+ {
3845
+ "epoch": 0.99,
3846
+ "grad_norm": 0.04831582307815552,
3847
+ "learning_rate": 0.0001517654193948343,
3848
+ "loss": 1.7548,
3849
+ "step": 544
3850
+ },
3851
+ {
3852
+ "epoch": 0.99,
3853
+ "grad_norm": 0.052940741181373596,
3854
+ "learning_rate": 0.00015160082473451378,
3855
+ "loss": 1.7209,
3856
+ "step": 545
3857
+ },
3858
+ {
3859
+ "epoch": 1.0,
3860
+ "grad_norm": 0.056908875703811646,
3861
+ "learning_rate": 0.00015143603932963795,
3862
+ "loss": 1.6537,
3863
+ "step": 546
3864
+ },
3865
+ {
3866
+ "epoch": 1.0,
3867
+ "grad_norm": 0.0509711354970932,
3868
+ "learning_rate": 0.00015127106378934273,
3869
+ "loss": 1.7151,
3870
+ "step": 547
3871
+ },
3872
+ {
3873
+ "epoch": 1.0,
3874
+ "grad_norm": 0.04795239865779877,
3875
+ "learning_rate": 0.000151105898723467,
3876
+ "loss": 1.743,
3877
+ "step": 548
3878
+ },
3879
+ {
3880
+ "epoch": 1.0,
3881
+ "eval_loss": 1.7236659526824951,
3882
+ "eval_runtime": 76.6784,
3883
+ "eval_samples_per_second": 65.207,
3884
+ "eval_steps_per_second": 16.302,
3885
+ "step": 548
3886
+ }
3887
+ ],
3888
+ "logging_steps": 1,
3889
+ "max_steps": 1644,
3890
+ "num_input_tokens_seen": 0,
3891
+ "num_train_epochs": 3,
3892
+ "save_steps": 548,
3893
+ "total_flos": 1.6352549111448207e+18,
3894
+ "train_batch_size": 1,
3895
+ "trial_name": null,
3896
+ "trial_params": null
3897
+ }
checkpoint-548/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd78228e3983a51f5b936399e1ca9efff3d96013153c81dbb4604c7bc5616374
3
+ size 5752
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": false,
22
+ "_load_in_8bit": true,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "fp4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": false,
32
+ "load_in_8bit": true,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 500000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.40.0.dev0",
41
+ "use_cache": false,
42
+ "vocab_size": 128256
43
+ }
runs/Apr29_09-19-25_5912cc4aac40/events.out.tfevents.1714382369.5912cc4aac40.532.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4555750c3c774ff8ee5d053714a644f8be94e8b1c05b474f6ada000057def36
3
+ size 10060
runs/Apr29_09-24-53_5912cc4aac40/events.out.tfevents.1714382696.5912cc4aac40.3175.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a9d1f363f0bd023c71f51d07bb4701eedf6e03a28a97609905a7af132e4e12
3
+ size 356343
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff