jspr commited on
Commit
4672c95
1 Parent(s): af667ea

initial commit

Browse files
Files changed (40) hide show
  1. README.md +153 -0
  2. adapter_config.json +32 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-132/README.md +204 -0
  5. checkpoint-132/adapter_config.json +32 -0
  6. checkpoint-132/adapter_model.safetensors +3 -0
  7. checkpoint-132/optimizer.pt +3 -0
  8. checkpoint-132/rng_state.pth +3 -0
  9. checkpoint-132/scheduler.pt +3 -0
  10. checkpoint-132/trainer_state.json +877 -0
  11. checkpoint-132/training_args.bin +3 -0
  12. checkpoint-198/README.md +204 -0
  13. checkpoint-198/adapter_config.json +32 -0
  14. checkpoint-198/adapter_model.safetensors +3 -0
  15. checkpoint-198/optimizer.pt +3 -0
  16. checkpoint-198/rng_state.pth +3 -0
  17. checkpoint-198/scheduler.pt +3 -0
  18. checkpoint-198/trainer_state.json +1305 -0
  19. checkpoint-198/training_args.bin +3 -0
  20. checkpoint-264/README.md +204 -0
  21. checkpoint-264/adapter_config.json +32 -0
  22. checkpoint-264/adapter_model.safetensors +3 -0
  23. checkpoint-264/optimizer.pt +3 -0
  24. checkpoint-264/rng_state.pth +3 -0
  25. checkpoint-264/scheduler.pt +3 -0
  26. checkpoint-264/trainer_state.json +1733 -0
  27. checkpoint-264/training_args.bin +3 -0
  28. checkpoint-66/README.md +204 -0
  29. checkpoint-66/adapter_config.json +32 -0
  30. checkpoint-66/adapter_model.safetensors +3 -0
  31. checkpoint-66/optimizer.pt +3 -0
  32. checkpoint-66/rng_state.pth +3 -0
  33. checkpoint-66/scheduler.pt +3 -0
  34. checkpoint-66/trainer_state.json +449 -0
  35. checkpoint-66/training_args.bin +3 -0
  36. config.json +43 -0
  37. runs/Feb20_06-57-12_16b73cf3ac9a/events.out.tfevents.1708412232.16b73cf3ac9a.583.0 +3 -0
  38. special_tokens_map.json +30 -0
  39. tokenizer.model +3 -0
  40. tokenizer_config.json +43 -0
README.md ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: NousResearch/Llama-2-7b-hf
6
+ model-index:
7
+ - name: lora-out
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<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)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.4.0`
18
+ ```yaml
19
+ base_model: NousResearch/Llama-2-7b-hf
20
+ model_type: LlamaForCausalLM
21
+ tokenizer_type: LlamaTokenizer
22
+ is_llama_derived_model: true
23
+
24
+ load_in_8bit: true
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: datasets-jsonl/smut-bts-responses-881.jsonl
30
+ ds_type: json
31
+ type: alpaca
32
+ dataset_prepared_path:
33
+ val_set_size: 0.05
34
+ output_dir: ./lora-out
35
+
36
+ sequence_len: 4096
37
+ sample_packing: true
38
+ pad_to_sequence_len: true
39
+
40
+ adapter: lora
41
+ lora_model_dir:
42
+ lora_r: 32
43
+ lora_alpha: 16
44
+ lora_dropout: 0.05
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project:
49
+ wandb_entity:
50
+ wandb_watch:
51
+ wandb_name:
52
+ wandb_log_model:
53
+
54
+ gradient_accumulation_steps: 4
55
+ micro_batch_size: 2
56
+ num_epochs: 4
57
+ optimizer: adamw_bnb_8bit
58
+ lr_scheduler: cosine
59
+ learning_rate: 0.0002
60
+
61
+ train_on_inputs: false
62
+ group_by_length: false
63
+ bf16: auto
64
+ fp16:
65
+ tf32: false
66
+
67
+ gradient_checkpointing: true
68
+ early_stopping_patience:
69
+ resume_from_checkpoint:
70
+ local_rank:
71
+ logging_steps: 1
72
+ xformers_attention:
73
+ flash_attention: true
74
+ s2_attention:
75
+
76
+ warmup_steps: 10
77
+ evals_per_epoch: 4
78
+ eval_table_size:
79
+ eval_max_new_tokens: 128
80
+ saves_per_epoch: 1
81
+ debug:
82
+ deepspeed:
83
+ weight_decay: 0.0
84
+ fsdp:
85
+ fsdp_config:
86
+ special_tokens:
87
+ ```
88
+
89
+ </details><br>
90
+
91
+ # lora-out
92
+
93
+ This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
94
+ It achieves the following results on the evaluation set:
95
+ - Loss: 1.9196
96
+
97
+ ## Model description
98
+
99
+ More information needed
100
+
101
+ ## Intended uses & limitations
102
+
103
+ More information needed
104
+
105
+ ## Training and evaluation data
106
+
107
+ More information needed
108
+
109
+ ## Training procedure
110
+
111
+ ### Training hyperparameters
112
+
113
+ The following hyperparameters were used during training:
114
+ - learning_rate: 0.0002
115
+ - train_batch_size: 2
116
+ - eval_batch_size: 2
117
+ - seed: 42
118
+ - gradient_accumulation_steps: 4
119
+ - total_train_batch_size: 8
120
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
121
+ - lr_scheduler_type: cosine
122
+ - lr_scheduler_warmup_steps: 10
123
+ - num_epochs: 4
124
+
125
+ ### Training results
126
+
127
+ | Training Loss | Epoch | Step | Validation Loss |
128
+ |:-------------:|:-----:|:----:|:---------------:|
129
+ | 1.8373 | 0.02 | 1 | 1.8334 |
130
+ | 1.738 | 0.26 | 17 | 1.7546 |
131
+ | 1.704 | 0.51 | 34 | 1.7389 |
132
+ | 1.6762 | 0.77 | 51 | 1.7410 |
133
+ | 1.5981 | 1.02 | 68 | 1.7487 |
134
+ | 1.5593 | 1.26 | 85 | 1.7956 |
135
+ | 1.4415 | 1.51 | 102 | 1.7860 |
136
+ | 1.6098 | 1.77 | 119 | 1.8020 |
137
+ | 1.5458 | 2.02 | 136 | 1.8526 |
138
+ | 1.4358 | 2.26 | 153 | 1.8557 |
139
+ | 1.4608 | 2.51 | 170 | 1.8844 |
140
+ | 1.4465 | 2.77 | 187 | 1.8980 |
141
+ | 1.3986 | 3.02 | 204 | 1.8998 |
142
+ | 1.5333 | 3.26 | 221 | 1.9195 |
143
+ | 1.3554 | 3.51 | 238 | 1.9184 |
144
+ | 1.3287 | 3.77 | 255 | 1.9196 |
145
+
146
+
147
+ ### Framework versions
148
+
149
+ - PEFT 0.8.2
150
+ - Transformers 4.38.0.dev0
151
+ - Pytorch 2.1.2+cu118
152
+ - Datasets 2.17.0
153
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a86c191d946fa4b885845f13a7aec1f83b893f9a289c8a5783c9863b4d7f1c7
3
+ size 319977674
checkpoint-132/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-132/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-132/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff66d5f4bbef473ecef9c32dfe7e07970394c6cb7cfa4fe242d2ddde57594abe
3
+ size 319876032
checkpoint-132/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa395d6f6c760283905f252fffcd87786e09d507ff6b01abdae43a13c3940dbc
3
+ size 160736084
checkpoint-132/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033777bd103409834094d47469b3cca17c2d5a6248cfb7c36f0e494a487e3a7a
3
+ size 14244
checkpoint-132/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4eb642ec55bc27ceb634e128c48f859bc0520c824cc983a09eeecbc166cb01
3
+ size 1064
checkpoint-132/trainer_state.json ADDED
@@ -0,0 +1,877 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.962406015037594,
5
+ "eval_steps": 17,
6
+ "global_step": 132,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.8373,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "eval_loss": 1.8333783149719238,
20
+ "eval_runtime": 16.5756,
21
+ "eval_samples_per_second": 2.715,
22
+ "eval_steps_per_second": 1.388,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.8119,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.05,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.8301,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.06,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.7976,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.08,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.853,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.09,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.7586,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.11,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8416,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.12,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.7755,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.14,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.804,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.15,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.7858,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.17,
81
+ "learning_rate": 0.0001999923511388017,
82
+ "loss": 1.7311,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.18,
87
+ "learning_rate": 0.0001999694057253083,
88
+ "loss": 1.7012,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.2,
93
+ "learning_rate": 0.00019993116726964554,
94
+ "loss": 1.742,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.21,
99
+ "learning_rate": 0.00019987764162142613,
100
+ "loss": 1.7209,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.23,
105
+ "learning_rate": 0.0001998088369688552,
106
+ "loss": 1.7578,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.24,
111
+ "learning_rate": 0.00019972476383747748,
112
+ "loss": 1.6906,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.26,
117
+ "learning_rate": 0.0001996254350885672,
118
+ "loss": 1.738,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.26,
123
+ "eval_loss": 1.754616141319275,
124
+ "eval_runtime": 16.6372,
125
+ "eval_samples_per_second": 2.705,
126
+ "eval_steps_per_second": 1.382,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 0.27,
131
+ "learning_rate": 0.0001995108659171607,
132
+ "loss": 1.7976,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 0.29,
137
+ "learning_rate": 0.00019938107384973166,
138
+ "loss": 1.7781,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 0.3,
143
+ "learning_rate": 0.00019923607874151032,
144
+ "loss": 1.7737,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 0.32,
149
+ "learning_rate": 0.00019907590277344582,
150
+ "loss": 1.6662,
151
+ "step": 21
152
+ },
153
+ {
154
+ "epoch": 0.33,
155
+ "learning_rate": 0.00019890057044881306,
156
+ "loss": 1.7869,
157
+ "step": 22
158
+ },
159
+ {
160
+ "epoch": 0.35,
161
+ "learning_rate": 0.0001987101085894644,
162
+ "loss": 1.6646,
163
+ "step": 23
164
+ },
165
+ {
166
+ "epoch": 0.36,
167
+ "learning_rate": 0.00019850454633172631,
168
+ "loss": 1.7482,
169
+ "step": 24
170
+ },
171
+ {
172
+ "epoch": 0.38,
173
+ "learning_rate": 0.0001982839151219424,
174
+ "loss": 1.7112,
175
+ "step": 25
176
+ },
177
+ {
178
+ "epoch": 0.39,
179
+ "learning_rate": 0.00019804824871166255,
180
+ "loss": 1.7083,
181
+ "step": 26
182
+ },
183
+ {
184
+ "epoch": 0.41,
185
+ "learning_rate": 0.00019779758315248004,
186
+ "loss": 1.728,
187
+ "step": 27
188
+ },
189
+ {
190
+ "epoch": 0.42,
191
+ "learning_rate": 0.00019753195679051628,
192
+ "loss": 1.7292,
193
+ "step": 28
194
+ },
195
+ {
196
+ "epoch": 0.44,
197
+ "learning_rate": 0.0001972514102605547,
198
+ "loss": 1.6902,
199
+ "step": 29
200
+ },
201
+ {
202
+ "epoch": 0.45,
203
+ "learning_rate": 0.00019695598647982468,
204
+ "loss": 1.7432,
205
+ "step": 30
206
+ },
207
+ {
208
+ "epoch": 0.47,
209
+ "learning_rate": 0.00019664573064143604,
210
+ "loss": 1.7258,
211
+ "step": 31
212
+ },
213
+ {
214
+ "epoch": 0.48,
215
+ "learning_rate": 0.00019632069020746572,
216
+ "loss": 1.7363,
217
+ "step": 32
218
+ },
219
+ {
220
+ "epoch": 0.5,
221
+ "learning_rate": 0.00019598091490169694,
222
+ "loss": 1.7142,
223
+ "step": 33
224
+ },
225
+ {
226
+ "epoch": 0.51,
227
+ "learning_rate": 0.00019562645670201276,
228
+ "loss": 1.704,
229
+ "step": 34
230
+ },
231
+ {
232
+ "epoch": 0.51,
233
+ "eval_loss": 1.7388739585876465,
234
+ "eval_runtime": 16.5955,
235
+ "eval_samples_per_second": 2.712,
236
+ "eval_steps_per_second": 1.386,
237
+ "step": 34
238
+ },
239
+ {
240
+ "epoch": 0.53,
241
+ "learning_rate": 0.0001952573698324446,
242
+ "loss": 1.7393,
243
+ "step": 35
244
+ },
245
+ {
246
+ "epoch": 0.54,
247
+ "learning_rate": 0.00019487371075487713,
248
+ "loss": 1.7568,
249
+ "step": 36
250
+ },
251
+ {
252
+ "epoch": 0.56,
253
+ "learning_rate": 0.000194475538160411,
254
+ "loss": 1.7445,
255
+ "step": 37
256
+ },
257
+ {
258
+ "epoch": 0.57,
259
+ "learning_rate": 0.0001940629129603844,
260
+ "loss": 1.6595,
261
+ "step": 38
262
+ },
263
+ {
264
+ "epoch": 0.59,
265
+ "learning_rate": 0.00019363589827705492,
266
+ "loss": 1.7288,
267
+ "step": 39
268
+ },
269
+ {
270
+ "epoch": 0.6,
271
+ "learning_rate": 0.00019319455943394347,
272
+ "loss": 1.6342,
273
+ "step": 40
274
+ },
275
+ {
276
+ "epoch": 0.62,
277
+ "learning_rate": 0.00019273896394584103,
278
+ "loss": 1.7066,
279
+ "step": 41
280
+ },
281
+ {
282
+ "epoch": 0.63,
283
+ "learning_rate": 0.00019226918150848068,
284
+ "loss": 1.6558,
285
+ "step": 42
286
+ },
287
+ {
288
+ "epoch": 0.65,
289
+ "learning_rate": 0.00019178528398787551,
290
+ "loss": 1.6756,
291
+ "step": 43
292
+ },
293
+ {
294
+ "epoch": 0.66,
295
+ "learning_rate": 0.00019128734540932495,
296
+ "loss": 1.7146,
297
+ "step": 44
298
+ },
299
+ {
300
+ "epoch": 0.68,
301
+ "learning_rate": 0.00019077544194609042,
302
+ "loss": 1.7043,
303
+ "step": 45
304
+ },
305
+ {
306
+ "epoch": 0.69,
307
+ "learning_rate": 0.00019024965190774263,
308
+ "loss": 1.6396,
309
+ "step": 46
310
+ },
311
+ {
312
+ "epoch": 0.71,
313
+ "learning_rate": 0.00018971005572818213,
314
+ "loss": 1.648,
315
+ "step": 47
316
+ },
317
+ {
318
+ "epoch": 0.72,
319
+ "learning_rate": 0.00018915673595333444,
320
+ "loss": 1.5988,
321
+ "step": 48
322
+ },
323
+ {
324
+ "epoch": 0.74,
325
+ "learning_rate": 0.00018858977722852275,
326
+ "loss": 1.7394,
327
+ "step": 49
328
+ },
329
+ {
330
+ "epoch": 0.75,
331
+ "learning_rate": 0.00018800926628551886,
332
+ "loss": 1.6362,
333
+ "step": 50
334
+ },
335
+ {
336
+ "epoch": 0.77,
337
+ "learning_rate": 0.00018741529192927526,
338
+ "loss": 1.6762,
339
+ "step": 51
340
+ },
341
+ {
342
+ "epoch": 0.77,
343
+ "eval_loss": 1.7409569025039673,
344
+ "eval_runtime": 16.7147,
345
+ "eval_samples_per_second": 2.692,
346
+ "eval_steps_per_second": 1.376,
347
+ "step": 51
348
+ },
349
+ {
350
+ "epoch": 0.78,
351
+ "learning_rate": 0.00018680794502434018,
352
+ "loss": 1.6534,
353
+ "step": 52
354
+ },
355
+ {
356
+ "epoch": 0.8,
357
+ "learning_rate": 0.00018618731848095706,
358
+ "loss": 1.6551,
359
+ "step": 53
360
+ },
361
+ {
362
+ "epoch": 0.81,
363
+ "learning_rate": 0.00018555350724085162,
364
+ "loss": 1.6297,
365
+ "step": 54
366
+ },
367
+ {
368
+ "epoch": 0.83,
369
+ "learning_rate": 0.0001849066082627079,
370
+ "loss": 1.7152,
371
+ "step": 55
372
+ },
373
+ {
374
+ "epoch": 0.84,
375
+ "learning_rate": 0.00018424672050733576,
376
+ "loss": 1.7062,
377
+ "step": 56
378
+ },
379
+ {
380
+ "epoch": 0.86,
381
+ "learning_rate": 0.00018357394492253215,
382
+ "loss": 1.5742,
383
+ "step": 57
384
+ },
385
+ {
386
+ "epoch": 0.87,
387
+ "learning_rate": 0.00018288838442763838,
388
+ "loss": 1.6424,
389
+ "step": 58
390
+ },
391
+ {
392
+ "epoch": 0.89,
393
+ "learning_rate": 0.00018219014389779585,
394
+ "loss": 1.6544,
395
+ "step": 59
396
+ },
397
+ {
398
+ "epoch": 0.9,
399
+ "learning_rate": 0.00018147933014790244,
400
+ "loss": 1.6179,
401
+ "step": 60
402
+ },
403
+ {
404
+ "epoch": 0.92,
405
+ "learning_rate": 0.0001807560519162724,
406
+ "loss": 1.6823,
407
+ "step": 61
408
+ },
409
+ {
410
+ "epoch": 0.93,
411
+ "learning_rate": 0.00018002041984800174,
412
+ "loss": 1.5845,
413
+ "step": 62
414
+ },
415
+ {
416
+ "epoch": 0.95,
417
+ "learning_rate": 0.00017927254647804209,
418
+ "loss": 1.6177,
419
+ "step": 63
420
+ },
421
+ {
422
+ "epoch": 0.96,
423
+ "learning_rate": 0.0001785125462139855,
424
+ "loss": 1.6196,
425
+ "step": 64
426
+ },
427
+ {
428
+ "epoch": 0.98,
429
+ "learning_rate": 0.00017774053531856258,
430
+ "loss": 1.6526,
431
+ "step": 65
432
+ },
433
+ {
434
+ "epoch": 0.99,
435
+ "learning_rate": 0.000176956631891857,
436
+ "loss": 1.5792,
437
+ "step": 66
438
+ },
439
+ {
440
+ "epoch": 1.01,
441
+ "learning_rate": 0.00017616095585323878,
442
+ "loss": 1.6652,
443
+ "step": 67
444
+ },
445
+ {
446
+ "epoch": 1.02,
447
+ "learning_rate": 0.00017535362892301954,
448
+ "loss": 1.5981,
449
+ "step": 68
450
+ },
451
+ {
452
+ "epoch": 1.02,
453
+ "eval_loss": 1.7487449645996094,
454
+ "eval_runtime": 16.6837,
455
+ "eval_samples_per_second": 2.697,
456
+ "eval_steps_per_second": 1.379,
457
+ "step": 68
458
+ },
459
+ {
460
+ "epoch": 1.02,
461
+ "learning_rate": 0.0001745347746038319,
462
+ "loss": 1.6053,
463
+ "step": 69
464
+ },
465
+ {
466
+ "epoch": 1.03,
467
+ "learning_rate": 0.0001737045181617364,
468
+ "loss": 1.6171,
469
+ "step": 70
470
+ },
471
+ {
472
+ "epoch": 1.05,
473
+ "learning_rate": 0.00017286298660705875,
474
+ "loss": 1.631,
475
+ "step": 71
476
+ },
477
+ {
478
+ "epoch": 1.06,
479
+ "learning_rate": 0.00017201030867496005,
480
+ "loss": 1.5558,
481
+ "step": 72
482
+ },
483
+ {
484
+ "epoch": 1.08,
485
+ "learning_rate": 0.00017114661480574332,
486
+ "loss": 1.5339,
487
+ "step": 73
488
+ },
489
+ {
490
+ "epoch": 1.09,
491
+ "learning_rate": 0.000170272037124899,
492
+ "loss": 1.6548,
493
+ "step": 74
494
+ },
495
+ {
496
+ "epoch": 1.11,
497
+ "learning_rate": 0.00016938670942289293,
498
+ "loss": 1.5526,
499
+ "step": 75
500
+ },
501
+ {
502
+ "epoch": 1.12,
503
+ "learning_rate": 0.00016849076713469914,
504
+ "loss": 1.5565,
505
+ "step": 76
506
+ },
507
+ {
508
+ "epoch": 1.14,
509
+ "learning_rate": 0.00016758434731908178,
510
+ "loss": 1.5604,
511
+ "step": 77
512
+ },
513
+ {
514
+ "epoch": 1.15,
515
+ "learning_rate": 0.00016666758863762793,
516
+ "loss": 1.5654,
517
+ "step": 78
518
+ },
519
+ {
520
+ "epoch": 1.17,
521
+ "learning_rate": 0.00016574063133353582,
522
+ "loss": 1.5967,
523
+ "step": 79
524
+ },
525
+ {
526
+ "epoch": 1.18,
527
+ "learning_rate": 0.00016480361721016054,
528
+ "loss": 1.5608,
529
+ "step": 80
530
+ },
531
+ {
532
+ "epoch": 1.2,
533
+ "learning_rate": 0.00016385668960932143,
534
+ "loss": 1.5801,
535
+ "step": 81
536
+ },
537
+ {
538
+ "epoch": 1.21,
539
+ "learning_rate": 0.00016289999338937427,
540
+ "loss": 1.5472,
541
+ "step": 82
542
+ },
543
+ {
544
+ "epoch": 1.23,
545
+ "learning_rate": 0.00016193367490305088,
546
+ "loss": 1.5126,
547
+ "step": 83
548
+ },
549
+ {
550
+ "epoch": 1.24,
551
+ "learning_rate": 0.00016095788197507081,
552
+ "loss": 1.5896,
553
+ "step": 84
554
+ },
555
+ {
556
+ "epoch": 1.26,
557
+ "learning_rate": 0.00015997276387952732,
558
+ "loss": 1.5593,
559
+ "step": 85
560
+ },
561
+ {
562
+ "epoch": 1.26,
563
+ "eval_loss": 1.79562509059906,
564
+ "eval_runtime": 16.6149,
565
+ "eval_samples_per_second": 2.708,
566
+ "eval_steps_per_second": 1.384,
567
+ "step": 85
568
+ },
569
+ {
570
+ "epoch": 1.27,
571
+ "learning_rate": 0.00015897847131705195,
572
+ "loss": 1.5616,
573
+ "step": 86
574
+ },
575
+ {
576
+ "epoch": 1.29,
577
+ "learning_rate": 0.00015797515639176074,
578
+ "loss": 1.596,
579
+ "step": 87
580
+ },
581
+ {
582
+ "epoch": 1.3,
583
+ "learning_rate": 0.0001569629725879857,
584
+ "loss": 1.595,
585
+ "step": 88
586
+ },
587
+ {
588
+ "epoch": 1.32,
589
+ "learning_rate": 0.00015594207474679532,
590
+ "loss": 1.5442,
591
+ "step": 89
592
+ },
593
+ {
594
+ "epoch": 1.33,
595
+ "learning_rate": 0.00015491261904230727,
596
+ "loss": 1.5812,
597
+ "step": 90
598
+ },
599
+ {
600
+ "epoch": 1.35,
601
+ "learning_rate": 0.00015387476295779736,
602
+ "loss": 1.5214,
603
+ "step": 91
604
+ },
605
+ {
606
+ "epoch": 1.36,
607
+ "learning_rate": 0.00015282866526160837,
608
+ "loss": 1.5403,
609
+ "step": 92
610
+ },
611
+ {
612
+ "epoch": 1.38,
613
+ "learning_rate": 0.0001517744859828618,
614
+ "loss": 1.4751,
615
+ "step": 93
616
+ },
617
+ {
618
+ "epoch": 1.39,
619
+ "learning_rate": 0.00015071238638697732,
620
+ "loss": 1.5861,
621
+ "step": 94
622
+ },
623
+ {
624
+ "epoch": 1.41,
625
+ "learning_rate": 0.00014964252895100264,
626
+ "loss": 1.5334,
627
+ "step": 95
628
+ },
629
+ {
630
+ "epoch": 1.42,
631
+ "learning_rate": 0.00014856507733875836,
632
+ "loss": 1.4884,
633
+ "step": 96
634
+ },
635
+ {
636
+ "epoch": 1.44,
637
+ "learning_rate": 0.00014748019637580114,
638
+ "loss": 1.5297,
639
+ "step": 97
640
+ },
641
+ {
642
+ "epoch": 1.45,
643
+ "learning_rate": 0.00014638805202420895,
644
+ "loss": 1.4725,
645
+ "step": 98
646
+ },
647
+ {
648
+ "epoch": 1.47,
649
+ "learning_rate": 0.0001452888113571929,
650
+ "loss": 1.4849,
651
+ "step": 99
652
+ },
653
+ {
654
+ "epoch": 1.48,
655
+ "learning_rate": 0.0001441826425335387,
656
+ "loss": 1.5654,
657
+ "step": 100
658
+ },
659
+ {
660
+ "epoch": 1.5,
661
+ "learning_rate": 0.00014306971477188223,
662
+ "loss": 1.6349,
663
+ "step": 101
664
+ },
665
+ {
666
+ "epoch": 1.51,
667
+ "learning_rate": 0.0001419501983248229,
668
+ "loss": 1.4415,
669
+ "step": 102
670
+ },
671
+ {
672
+ "epoch": 1.51,
673
+ "eval_loss": 1.7860450744628906,
674
+ "eval_runtime": 16.6303,
675
+ "eval_samples_per_second": 2.706,
676
+ "eval_steps_per_second": 1.383,
677
+ "step": 102
678
+ },
679
+ {
680
+ "epoch": 1.53,
681
+ "learning_rate": 0.00014082426445287903,
682
+ "loss": 1.5735,
683
+ "step": 103
684
+ },
685
+ {
686
+ "epoch": 1.54,
687
+ "learning_rate": 0.00013969208539828872,
688
+ "loss": 1.5328,
689
+ "step": 104
690
+ },
691
+ {
692
+ "epoch": 1.56,
693
+ "learning_rate": 0.00013855383435866077,
694
+ "loss": 1.5466,
695
+ "step": 105
696
+ },
697
+ {
698
+ "epoch": 1.57,
699
+ "learning_rate": 0.00013740968546047935,
700
+ "loss": 1.5861,
701
+ "step": 106
702
+ },
703
+ {
704
+ "epoch": 1.59,
705
+ "learning_rate": 0.0001362598137324667,
706
+ "loss": 1.5449,
707
+ "step": 107
708
+ },
709
+ {
710
+ "epoch": 1.6,
711
+ "learning_rate": 0.00013510439507880776,
712
+ "loss": 1.6084,
713
+ "step": 108
714
+ },
715
+ {
716
+ "epoch": 1.62,
717
+ "learning_rate": 0.00013394360625224068,
718
+ "loss": 1.5249,
719
+ "step": 109
720
+ },
721
+ {
722
+ "epoch": 1.63,
723
+ "learning_rate": 0.00013277762482701767,
724
+ "loss": 1.5594,
725
+ "step": 110
726
+ },
727
+ {
728
+ "epoch": 1.65,
729
+ "learning_rate": 0.00013160662917174044,
730
+ "loss": 1.5877,
731
+ "step": 111
732
+ },
733
+ {
734
+ "epoch": 1.66,
735
+ "learning_rate": 0.0001304307984220736,
736
+ "loss": 1.4964,
737
+ "step": 112
738
+ },
739
+ {
740
+ "epoch": 1.68,
741
+ "learning_rate": 0.0001292503124533411,
742
+ "loss": 1.4538,
743
+ "step": 113
744
+ },
745
+ {
746
+ "epoch": 1.69,
747
+ "learning_rate": 0.0001280653518530093,
748
+ "loss": 1.4454,
749
+ "step": 114
750
+ },
751
+ {
752
+ "epoch": 1.71,
753
+ "learning_rate": 0.00012687609789306144,
754
+ "loss": 1.4512,
755
+ "step": 115
756
+ },
757
+ {
758
+ "epoch": 1.72,
759
+ "learning_rate": 0.0001256827325022668,
760
+ "loss": 1.38,
761
+ "step": 116
762
+ },
763
+ {
764
+ "epoch": 1.74,
765
+ "learning_rate": 0.00012448543823835015,
766
+ "loss": 1.5207,
767
+ "step": 117
768
+ },
769
+ {
770
+ "epoch": 1.75,
771
+ "learning_rate": 0.00012328439826006415,
772
+ "loss": 1.4787,
773
+ "step": 118
774
+ },
775
+ {
776
+ "epoch": 1.77,
777
+ "learning_rate": 0.0001220797962991706,
778
+ "loss": 1.6098,
779
+ "step": 119
780
+ },
781
+ {
782
+ "epoch": 1.77,
783
+ "eval_loss": 1.8019659519195557,
784
+ "eval_runtime": 16.646,
785
+ "eval_samples_per_second": 2.703,
786
+ "eval_steps_per_second": 1.382,
787
+ "step": 119
788
+ },
789
+ {
790
+ "epoch": 1.78,
791
+ "learning_rate": 0.00012087181663233354,
792
+ "loss": 1.4798,
793
+ "step": 120
794
+ },
795
+ {
796
+ "epoch": 1.8,
797
+ "learning_rate": 0.00011966064405292887,
798
+ "loss": 1.5248,
799
+ "step": 121
800
+ },
801
+ {
802
+ "epoch": 1.81,
803
+ "learning_rate": 0.0001184464638427756,
804
+ "loss": 1.4309,
805
+ "step": 122
806
+ },
807
+ {
808
+ "epoch": 1.83,
809
+ "learning_rate": 0.00011722946174379168,
810
+ "loss": 1.4477,
811
+ "step": 123
812
+ },
813
+ {
814
+ "epoch": 1.84,
815
+ "learning_rate": 0.00011600982392957978,
816
+ "loss": 1.4843,
817
+ "step": 124
818
+ },
819
+ {
820
+ "epoch": 1.86,
821
+ "learning_rate": 0.00011478773697694691,
822
+ "loss": 1.4298,
823
+ "step": 125
824
+ },
825
+ {
826
+ "epoch": 1.87,
827
+ "learning_rate": 0.00011356338783736255,
828
+ "loss": 1.4775,
829
+ "step": 126
830
+ },
831
+ {
832
+ "epoch": 1.89,
833
+ "learning_rate": 0.0001123369638083593,
834
+ "loss": 1.5159,
835
+ "step": 127
836
+ },
837
+ {
838
+ "epoch": 1.9,
839
+ "learning_rate": 0.00011110865250488047,
840
+ "loss": 1.3696,
841
+ "step": 128
842
+ },
843
+ {
844
+ "epoch": 1.92,
845
+ "learning_rate": 0.00010987864183057943,
846
+ "loss": 1.4259,
847
+ "step": 129
848
+ },
849
+ {
850
+ "epoch": 1.93,
851
+ "learning_rate": 0.00010864711994907458,
852
+ "loss": 1.5685,
853
+ "step": 130
854
+ },
855
+ {
856
+ "epoch": 1.95,
857
+ "learning_rate": 0.00010741427525516463,
858
+ "loss": 1.4997,
859
+ "step": 131
860
+ },
861
+ {
862
+ "epoch": 1.96,
863
+ "learning_rate": 0.00010618029634600843,
864
+ "loss": 1.4718,
865
+ "step": 132
866
+ }
867
+ ],
868
+ "logging_steps": 1,
869
+ "max_steps": 264,
870
+ "num_input_tokens_seen": 0,
871
+ "num_train_epochs": 4,
872
+ "save_steps": 66,
873
+ "total_flos": 1.735504576024412e+17,
874
+ "train_batch_size": 2,
875
+ "trial_name": null,
876
+ "trial_params": null
877
+ }
checkpoint-132/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136f5d9dd7fc2fabff6e80dd48a495a4cd5f0ab1af46964ed1af4cae2dae0a30
3
+ size 5368
checkpoint-198/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-198/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-198/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d60df740d004f2f8fc02ab7629f17eda12e7f196d4e3ca2007a1c01e241070
3
+ size 319876032
checkpoint-198/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf9f9f4e2352f491ffe3174aab029a8f216fd109f0969ae76546b26b87abad3
3
+ size 160736084
checkpoint-198/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b24c8f59fb317620940030d2ae7ef634f7daed1f9db265c73e4e71c9e414c70
3
+ size 14244
checkpoint-198/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12cb0c64acf3eef37e83a0dd97998eb7ff772c6f1dd6f52d79dbdcdbe2d2264
3
+ size 1064
checkpoint-198/trainer_state.json ADDED
@@ -0,0 +1,1305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.932330827067669,
5
+ "eval_steps": 17,
6
+ "global_step": 198,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.8373,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "eval_loss": 1.8333783149719238,
20
+ "eval_runtime": 16.5756,
21
+ "eval_samples_per_second": 2.715,
22
+ "eval_steps_per_second": 1.388,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.8119,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.05,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.8301,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.06,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.7976,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.08,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.853,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.09,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.7586,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.11,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8416,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.12,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.7755,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.14,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.804,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.15,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.7858,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.17,
81
+ "learning_rate": 0.0001999923511388017,
82
+ "loss": 1.7311,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.18,
87
+ "learning_rate": 0.0001999694057253083,
88
+ "loss": 1.7012,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.2,
93
+ "learning_rate": 0.00019993116726964554,
94
+ "loss": 1.742,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.21,
99
+ "learning_rate": 0.00019987764162142613,
100
+ "loss": 1.7209,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.23,
105
+ "learning_rate": 0.0001998088369688552,
106
+ "loss": 1.7578,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.24,
111
+ "learning_rate": 0.00019972476383747748,
112
+ "loss": 1.6906,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.26,
117
+ "learning_rate": 0.0001996254350885672,
118
+ "loss": 1.738,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.26,
123
+ "eval_loss": 1.754616141319275,
124
+ "eval_runtime": 16.6372,
125
+ "eval_samples_per_second": 2.705,
126
+ "eval_steps_per_second": 1.382,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 0.27,
131
+ "learning_rate": 0.0001995108659171607,
132
+ "loss": 1.7976,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 0.29,
137
+ "learning_rate": 0.00019938107384973166,
138
+ "loss": 1.7781,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 0.3,
143
+ "learning_rate": 0.00019923607874151032,
144
+ "loss": 1.7737,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 0.32,
149
+ "learning_rate": 0.00019907590277344582,
150
+ "loss": 1.6662,
151
+ "step": 21
152
+ },
153
+ {
154
+ "epoch": 0.33,
155
+ "learning_rate": 0.00019890057044881306,
156
+ "loss": 1.7869,
157
+ "step": 22
158
+ },
159
+ {
160
+ "epoch": 0.35,
161
+ "learning_rate": 0.0001987101085894644,
162
+ "loss": 1.6646,
163
+ "step": 23
164
+ },
165
+ {
166
+ "epoch": 0.36,
167
+ "learning_rate": 0.00019850454633172631,
168
+ "loss": 1.7482,
169
+ "step": 24
170
+ },
171
+ {
172
+ "epoch": 0.38,
173
+ "learning_rate": 0.0001982839151219424,
174
+ "loss": 1.7112,
175
+ "step": 25
176
+ },
177
+ {
178
+ "epoch": 0.39,
179
+ "learning_rate": 0.00019804824871166255,
180
+ "loss": 1.7083,
181
+ "step": 26
182
+ },
183
+ {
184
+ "epoch": 0.41,
185
+ "learning_rate": 0.00019779758315248004,
186
+ "loss": 1.728,
187
+ "step": 27
188
+ },
189
+ {
190
+ "epoch": 0.42,
191
+ "learning_rate": 0.00019753195679051628,
192
+ "loss": 1.7292,
193
+ "step": 28
194
+ },
195
+ {
196
+ "epoch": 0.44,
197
+ "learning_rate": 0.0001972514102605547,
198
+ "loss": 1.6902,
199
+ "step": 29
200
+ },
201
+ {
202
+ "epoch": 0.45,
203
+ "learning_rate": 0.00019695598647982468,
204
+ "loss": 1.7432,
205
+ "step": 30
206
+ },
207
+ {
208
+ "epoch": 0.47,
209
+ "learning_rate": 0.00019664573064143604,
210
+ "loss": 1.7258,
211
+ "step": 31
212
+ },
213
+ {
214
+ "epoch": 0.48,
215
+ "learning_rate": 0.00019632069020746572,
216
+ "loss": 1.7363,
217
+ "step": 32
218
+ },
219
+ {
220
+ "epoch": 0.5,
221
+ "learning_rate": 0.00019598091490169694,
222
+ "loss": 1.7142,
223
+ "step": 33
224
+ },
225
+ {
226
+ "epoch": 0.51,
227
+ "learning_rate": 0.00019562645670201276,
228
+ "loss": 1.704,
229
+ "step": 34
230
+ },
231
+ {
232
+ "epoch": 0.51,
233
+ "eval_loss": 1.7388739585876465,
234
+ "eval_runtime": 16.5955,
235
+ "eval_samples_per_second": 2.712,
236
+ "eval_steps_per_second": 1.386,
237
+ "step": 34
238
+ },
239
+ {
240
+ "epoch": 0.53,
241
+ "learning_rate": 0.0001952573698324446,
242
+ "loss": 1.7393,
243
+ "step": 35
244
+ },
245
+ {
246
+ "epoch": 0.54,
247
+ "learning_rate": 0.00019487371075487713,
248
+ "loss": 1.7568,
249
+ "step": 36
250
+ },
251
+ {
252
+ "epoch": 0.56,
253
+ "learning_rate": 0.000194475538160411,
254
+ "loss": 1.7445,
255
+ "step": 37
256
+ },
257
+ {
258
+ "epoch": 0.57,
259
+ "learning_rate": 0.0001940629129603844,
260
+ "loss": 1.6595,
261
+ "step": 38
262
+ },
263
+ {
264
+ "epoch": 0.59,
265
+ "learning_rate": 0.00019363589827705492,
266
+ "loss": 1.7288,
267
+ "step": 39
268
+ },
269
+ {
270
+ "epoch": 0.6,
271
+ "learning_rate": 0.00019319455943394347,
272
+ "loss": 1.6342,
273
+ "step": 40
274
+ },
275
+ {
276
+ "epoch": 0.62,
277
+ "learning_rate": 0.00019273896394584103,
278
+ "loss": 1.7066,
279
+ "step": 41
280
+ },
281
+ {
282
+ "epoch": 0.63,
283
+ "learning_rate": 0.00019226918150848068,
284
+ "loss": 1.6558,
285
+ "step": 42
286
+ },
287
+ {
288
+ "epoch": 0.65,
289
+ "learning_rate": 0.00019178528398787551,
290
+ "loss": 1.6756,
291
+ "step": 43
292
+ },
293
+ {
294
+ "epoch": 0.66,
295
+ "learning_rate": 0.00019128734540932495,
296
+ "loss": 1.7146,
297
+ "step": 44
298
+ },
299
+ {
300
+ "epoch": 0.68,
301
+ "learning_rate": 0.00019077544194609042,
302
+ "loss": 1.7043,
303
+ "step": 45
304
+ },
305
+ {
306
+ "epoch": 0.69,
307
+ "learning_rate": 0.00019024965190774263,
308
+ "loss": 1.6396,
309
+ "step": 46
310
+ },
311
+ {
312
+ "epoch": 0.71,
313
+ "learning_rate": 0.00018971005572818213,
314
+ "loss": 1.648,
315
+ "step": 47
316
+ },
317
+ {
318
+ "epoch": 0.72,
319
+ "learning_rate": 0.00018915673595333444,
320
+ "loss": 1.5988,
321
+ "step": 48
322
+ },
323
+ {
324
+ "epoch": 0.74,
325
+ "learning_rate": 0.00018858977722852275,
326
+ "loss": 1.7394,
327
+ "step": 49
328
+ },
329
+ {
330
+ "epoch": 0.75,
331
+ "learning_rate": 0.00018800926628551886,
332
+ "loss": 1.6362,
333
+ "step": 50
334
+ },
335
+ {
336
+ "epoch": 0.77,
337
+ "learning_rate": 0.00018741529192927526,
338
+ "loss": 1.6762,
339
+ "step": 51
340
+ },
341
+ {
342
+ "epoch": 0.77,
343
+ "eval_loss": 1.7409569025039673,
344
+ "eval_runtime": 16.7147,
345
+ "eval_samples_per_second": 2.692,
346
+ "eval_steps_per_second": 1.376,
347
+ "step": 51
348
+ },
349
+ {
350
+ "epoch": 0.78,
351
+ "learning_rate": 0.00018680794502434018,
352
+ "loss": 1.6534,
353
+ "step": 52
354
+ },
355
+ {
356
+ "epoch": 0.8,
357
+ "learning_rate": 0.00018618731848095706,
358
+ "loss": 1.6551,
359
+ "step": 53
360
+ },
361
+ {
362
+ "epoch": 0.81,
363
+ "learning_rate": 0.00018555350724085162,
364
+ "loss": 1.6297,
365
+ "step": 54
366
+ },
367
+ {
368
+ "epoch": 0.83,
369
+ "learning_rate": 0.0001849066082627079,
370
+ "loss": 1.7152,
371
+ "step": 55
372
+ },
373
+ {
374
+ "epoch": 0.84,
375
+ "learning_rate": 0.00018424672050733576,
376
+ "loss": 1.7062,
377
+ "step": 56
378
+ },
379
+ {
380
+ "epoch": 0.86,
381
+ "learning_rate": 0.00018357394492253215,
382
+ "loss": 1.5742,
383
+ "step": 57
384
+ },
385
+ {
386
+ "epoch": 0.87,
387
+ "learning_rate": 0.00018288838442763838,
388
+ "loss": 1.6424,
389
+ "step": 58
390
+ },
391
+ {
392
+ "epoch": 0.89,
393
+ "learning_rate": 0.00018219014389779585,
394
+ "loss": 1.6544,
395
+ "step": 59
396
+ },
397
+ {
398
+ "epoch": 0.9,
399
+ "learning_rate": 0.00018147933014790244,
400
+ "loss": 1.6179,
401
+ "step": 60
402
+ },
403
+ {
404
+ "epoch": 0.92,
405
+ "learning_rate": 0.0001807560519162724,
406
+ "loss": 1.6823,
407
+ "step": 61
408
+ },
409
+ {
410
+ "epoch": 0.93,
411
+ "learning_rate": 0.00018002041984800174,
412
+ "loss": 1.5845,
413
+ "step": 62
414
+ },
415
+ {
416
+ "epoch": 0.95,
417
+ "learning_rate": 0.00017927254647804209,
418
+ "loss": 1.6177,
419
+ "step": 63
420
+ },
421
+ {
422
+ "epoch": 0.96,
423
+ "learning_rate": 0.0001785125462139855,
424
+ "loss": 1.6196,
425
+ "step": 64
426
+ },
427
+ {
428
+ "epoch": 0.98,
429
+ "learning_rate": 0.00017774053531856258,
430
+ "loss": 1.6526,
431
+ "step": 65
432
+ },
433
+ {
434
+ "epoch": 0.99,
435
+ "learning_rate": 0.000176956631891857,
436
+ "loss": 1.5792,
437
+ "step": 66
438
+ },
439
+ {
440
+ "epoch": 1.01,
441
+ "learning_rate": 0.00017616095585323878,
442
+ "loss": 1.6652,
443
+ "step": 67
444
+ },
445
+ {
446
+ "epoch": 1.02,
447
+ "learning_rate": 0.00017535362892301954,
448
+ "loss": 1.5981,
449
+ "step": 68
450
+ },
451
+ {
452
+ "epoch": 1.02,
453
+ "eval_loss": 1.7487449645996094,
454
+ "eval_runtime": 16.6837,
455
+ "eval_samples_per_second": 2.697,
456
+ "eval_steps_per_second": 1.379,
457
+ "step": 68
458
+ },
459
+ {
460
+ "epoch": 1.02,
461
+ "learning_rate": 0.0001745347746038319,
462
+ "loss": 1.6053,
463
+ "step": 69
464
+ },
465
+ {
466
+ "epoch": 1.03,
467
+ "learning_rate": 0.0001737045181617364,
468
+ "loss": 1.6171,
469
+ "step": 70
470
+ },
471
+ {
472
+ "epoch": 1.05,
473
+ "learning_rate": 0.00017286298660705875,
474
+ "loss": 1.631,
475
+ "step": 71
476
+ },
477
+ {
478
+ "epoch": 1.06,
479
+ "learning_rate": 0.00017201030867496005,
480
+ "loss": 1.5558,
481
+ "step": 72
482
+ },
483
+ {
484
+ "epoch": 1.08,
485
+ "learning_rate": 0.00017114661480574332,
486
+ "loss": 1.5339,
487
+ "step": 73
488
+ },
489
+ {
490
+ "epoch": 1.09,
491
+ "learning_rate": 0.000170272037124899,
492
+ "loss": 1.6548,
493
+ "step": 74
494
+ },
495
+ {
496
+ "epoch": 1.11,
497
+ "learning_rate": 0.00016938670942289293,
498
+ "loss": 1.5526,
499
+ "step": 75
500
+ },
501
+ {
502
+ "epoch": 1.12,
503
+ "learning_rate": 0.00016849076713469914,
504
+ "loss": 1.5565,
505
+ "step": 76
506
+ },
507
+ {
508
+ "epoch": 1.14,
509
+ "learning_rate": 0.00016758434731908178,
510
+ "loss": 1.5604,
511
+ "step": 77
512
+ },
513
+ {
514
+ "epoch": 1.15,
515
+ "learning_rate": 0.00016666758863762793,
516
+ "loss": 1.5654,
517
+ "step": 78
518
+ },
519
+ {
520
+ "epoch": 1.17,
521
+ "learning_rate": 0.00016574063133353582,
522
+ "loss": 1.5967,
523
+ "step": 79
524
+ },
525
+ {
526
+ "epoch": 1.18,
527
+ "learning_rate": 0.00016480361721016054,
528
+ "loss": 1.5608,
529
+ "step": 80
530
+ },
531
+ {
532
+ "epoch": 1.2,
533
+ "learning_rate": 0.00016385668960932143,
534
+ "loss": 1.5801,
535
+ "step": 81
536
+ },
537
+ {
538
+ "epoch": 1.21,
539
+ "learning_rate": 0.00016289999338937427,
540
+ "loss": 1.5472,
541
+ "step": 82
542
+ },
543
+ {
544
+ "epoch": 1.23,
545
+ "learning_rate": 0.00016193367490305088,
546
+ "loss": 1.5126,
547
+ "step": 83
548
+ },
549
+ {
550
+ "epoch": 1.24,
551
+ "learning_rate": 0.00016095788197507081,
552
+ "loss": 1.5896,
553
+ "step": 84
554
+ },
555
+ {
556
+ "epoch": 1.26,
557
+ "learning_rate": 0.00015997276387952732,
558
+ "loss": 1.5593,
559
+ "step": 85
560
+ },
561
+ {
562
+ "epoch": 1.26,
563
+ "eval_loss": 1.79562509059906,
564
+ "eval_runtime": 16.6149,
565
+ "eval_samples_per_second": 2.708,
566
+ "eval_steps_per_second": 1.384,
567
+ "step": 85
568
+ },
569
+ {
570
+ "epoch": 1.27,
571
+ "learning_rate": 0.00015897847131705195,
572
+ "loss": 1.5616,
573
+ "step": 86
574
+ },
575
+ {
576
+ "epoch": 1.29,
577
+ "learning_rate": 0.00015797515639176074,
578
+ "loss": 1.596,
579
+ "step": 87
580
+ },
581
+ {
582
+ "epoch": 1.3,
583
+ "learning_rate": 0.0001569629725879857,
584
+ "loss": 1.595,
585
+ "step": 88
586
+ },
587
+ {
588
+ "epoch": 1.32,
589
+ "learning_rate": 0.00015594207474679532,
590
+ "loss": 1.5442,
591
+ "step": 89
592
+ },
593
+ {
594
+ "epoch": 1.33,
595
+ "learning_rate": 0.00015491261904230727,
596
+ "loss": 1.5812,
597
+ "step": 90
598
+ },
599
+ {
600
+ "epoch": 1.35,
601
+ "learning_rate": 0.00015387476295779736,
602
+ "loss": 1.5214,
603
+ "step": 91
604
+ },
605
+ {
606
+ "epoch": 1.36,
607
+ "learning_rate": 0.00015282866526160837,
608
+ "loss": 1.5403,
609
+ "step": 92
610
+ },
611
+ {
612
+ "epoch": 1.38,
613
+ "learning_rate": 0.0001517744859828618,
614
+ "loss": 1.4751,
615
+ "step": 93
616
+ },
617
+ {
618
+ "epoch": 1.39,
619
+ "learning_rate": 0.00015071238638697732,
620
+ "loss": 1.5861,
621
+ "step": 94
622
+ },
623
+ {
624
+ "epoch": 1.41,
625
+ "learning_rate": 0.00014964252895100264,
626
+ "loss": 1.5334,
627
+ "step": 95
628
+ },
629
+ {
630
+ "epoch": 1.42,
631
+ "learning_rate": 0.00014856507733875836,
632
+ "loss": 1.4884,
633
+ "step": 96
634
+ },
635
+ {
636
+ "epoch": 1.44,
637
+ "learning_rate": 0.00014748019637580114,
638
+ "loss": 1.5297,
639
+ "step": 97
640
+ },
641
+ {
642
+ "epoch": 1.45,
643
+ "learning_rate": 0.00014638805202420895,
644
+ "loss": 1.4725,
645
+ "step": 98
646
+ },
647
+ {
648
+ "epoch": 1.47,
649
+ "learning_rate": 0.0001452888113571929,
650
+ "loss": 1.4849,
651
+ "step": 99
652
+ },
653
+ {
654
+ "epoch": 1.48,
655
+ "learning_rate": 0.0001441826425335387,
656
+ "loss": 1.5654,
657
+ "step": 100
658
+ },
659
+ {
660
+ "epoch": 1.5,
661
+ "learning_rate": 0.00014306971477188223,
662
+ "loss": 1.6349,
663
+ "step": 101
664
+ },
665
+ {
666
+ "epoch": 1.51,
667
+ "learning_rate": 0.0001419501983248229,
668
+ "loss": 1.4415,
669
+ "step": 102
670
+ },
671
+ {
672
+ "epoch": 1.51,
673
+ "eval_loss": 1.7860450744628906,
674
+ "eval_runtime": 16.6303,
675
+ "eval_samples_per_second": 2.706,
676
+ "eval_steps_per_second": 1.383,
677
+ "step": 102
678
+ },
679
+ {
680
+ "epoch": 1.53,
681
+ "learning_rate": 0.00014082426445287903,
682
+ "loss": 1.5735,
683
+ "step": 103
684
+ },
685
+ {
686
+ "epoch": 1.54,
687
+ "learning_rate": 0.00013969208539828872,
688
+ "loss": 1.5328,
689
+ "step": 104
690
+ },
691
+ {
692
+ "epoch": 1.56,
693
+ "learning_rate": 0.00013855383435866077,
694
+ "loss": 1.5466,
695
+ "step": 105
696
+ },
697
+ {
698
+ "epoch": 1.57,
699
+ "learning_rate": 0.00013740968546047935,
700
+ "loss": 1.5861,
701
+ "step": 106
702
+ },
703
+ {
704
+ "epoch": 1.59,
705
+ "learning_rate": 0.0001362598137324667,
706
+ "loss": 1.5449,
707
+ "step": 107
708
+ },
709
+ {
710
+ "epoch": 1.6,
711
+ "learning_rate": 0.00013510439507880776,
712
+ "loss": 1.6084,
713
+ "step": 108
714
+ },
715
+ {
716
+ "epoch": 1.62,
717
+ "learning_rate": 0.00013394360625224068,
718
+ "loss": 1.5249,
719
+ "step": 109
720
+ },
721
+ {
722
+ "epoch": 1.63,
723
+ "learning_rate": 0.00013277762482701767,
724
+ "loss": 1.5594,
725
+ "step": 110
726
+ },
727
+ {
728
+ "epoch": 1.65,
729
+ "learning_rate": 0.00013160662917174044,
730
+ "loss": 1.5877,
731
+ "step": 111
732
+ },
733
+ {
734
+ "epoch": 1.66,
735
+ "learning_rate": 0.0001304307984220736,
736
+ "loss": 1.4964,
737
+ "step": 112
738
+ },
739
+ {
740
+ "epoch": 1.68,
741
+ "learning_rate": 0.0001292503124533411,
742
+ "loss": 1.4538,
743
+ "step": 113
744
+ },
745
+ {
746
+ "epoch": 1.69,
747
+ "learning_rate": 0.0001280653518530093,
748
+ "loss": 1.4454,
749
+ "step": 114
750
+ },
751
+ {
752
+ "epoch": 1.71,
753
+ "learning_rate": 0.00012687609789306144,
754
+ "loss": 1.4512,
755
+ "step": 115
756
+ },
757
+ {
758
+ "epoch": 1.72,
759
+ "learning_rate": 0.0001256827325022668,
760
+ "loss": 1.38,
761
+ "step": 116
762
+ },
763
+ {
764
+ "epoch": 1.74,
765
+ "learning_rate": 0.00012448543823835015,
766
+ "loss": 1.5207,
767
+ "step": 117
768
+ },
769
+ {
770
+ "epoch": 1.75,
771
+ "learning_rate": 0.00012328439826006415,
772
+ "loss": 1.4787,
773
+ "step": 118
774
+ },
775
+ {
776
+ "epoch": 1.77,
777
+ "learning_rate": 0.0001220797962991706,
778
+ "loss": 1.6098,
779
+ "step": 119
780
+ },
781
+ {
782
+ "epoch": 1.77,
783
+ "eval_loss": 1.8019659519195557,
784
+ "eval_runtime": 16.646,
785
+ "eval_samples_per_second": 2.703,
786
+ "eval_steps_per_second": 1.382,
787
+ "step": 119
788
+ },
789
+ {
790
+ "epoch": 1.78,
791
+ "learning_rate": 0.00012087181663233354,
792
+ "loss": 1.4798,
793
+ "step": 120
794
+ },
795
+ {
796
+ "epoch": 1.8,
797
+ "learning_rate": 0.00011966064405292887,
798
+ "loss": 1.5248,
799
+ "step": 121
800
+ },
801
+ {
802
+ "epoch": 1.81,
803
+ "learning_rate": 0.0001184464638427756,
804
+ "loss": 1.4309,
805
+ "step": 122
806
+ },
807
+ {
808
+ "epoch": 1.83,
809
+ "learning_rate": 0.00011722946174379168,
810
+ "loss": 1.4477,
811
+ "step": 123
812
+ },
813
+ {
814
+ "epoch": 1.84,
815
+ "learning_rate": 0.00011600982392957978,
816
+ "loss": 1.4843,
817
+ "step": 124
818
+ },
819
+ {
820
+ "epoch": 1.86,
821
+ "learning_rate": 0.00011478773697694691,
822
+ "loss": 1.4298,
823
+ "step": 125
824
+ },
825
+ {
826
+ "epoch": 1.87,
827
+ "learning_rate": 0.00011356338783736255,
828
+ "loss": 1.4775,
829
+ "step": 126
830
+ },
831
+ {
832
+ "epoch": 1.89,
833
+ "learning_rate": 0.0001123369638083593,
834
+ "loss": 1.5159,
835
+ "step": 127
836
+ },
837
+ {
838
+ "epoch": 1.9,
839
+ "learning_rate": 0.00011110865250488047,
840
+ "loss": 1.3696,
841
+ "step": 128
842
+ },
843
+ {
844
+ "epoch": 1.92,
845
+ "learning_rate": 0.00010987864183057943,
846
+ "loss": 1.4259,
847
+ "step": 129
848
+ },
849
+ {
850
+ "epoch": 1.93,
851
+ "learning_rate": 0.00010864711994907458,
852
+ "loss": 1.5685,
853
+ "step": 130
854
+ },
855
+ {
856
+ "epoch": 1.95,
857
+ "learning_rate": 0.00010741427525516463,
858
+ "loss": 1.4997,
859
+ "step": 131
860
+ },
861
+ {
862
+ "epoch": 1.96,
863
+ "learning_rate": 0.00010618029634600843,
864
+ "loss": 1.4718,
865
+ "step": 132
866
+ },
867
+ {
868
+ "epoch": 1.98,
869
+ "learning_rate": 0.00010494537199227392,
870
+ "loss": 1.5824,
871
+ "step": 133
872
+ },
873
+ {
874
+ "epoch": 1.99,
875
+ "learning_rate": 0.00010370969110926052,
876
+ "loss": 1.5392,
877
+ "step": 134
878
+ },
879
+ {
880
+ "epoch": 2.01,
881
+ "learning_rate": 0.0001024734427279995,
882
+ "loss": 1.5724,
883
+ "step": 135
884
+ },
885
+ {
886
+ "epoch": 2.02,
887
+ "learning_rate": 0.00010123681596633629,
888
+ "loss": 1.5458,
889
+ "step": 136
890
+ },
891
+ {
892
+ "epoch": 2.02,
893
+ "eval_loss": 1.852607250213623,
894
+ "eval_runtime": 16.6761,
895
+ "eval_samples_per_second": 2.698,
896
+ "eval_steps_per_second": 1.379,
897
+ "step": 136
898
+ },
899
+ {
900
+ "epoch": 2.02,
901
+ "learning_rate": 0.0001,
902
+ "loss": 1.3,
903
+ "step": 137
904
+ },
905
+ {
906
+ "epoch": 2.03,
907
+ "learning_rate": 9.876318403366372e-05,
908
+ "loss": 1.4398,
909
+ "step": 138
910
+ },
911
+ {
912
+ "epoch": 2.05,
913
+ "learning_rate": 9.75265572720005e-05,
914
+ "loss": 1.4742,
915
+ "step": 139
916
+ },
917
+ {
918
+ "epoch": 2.06,
919
+ "learning_rate": 9.629030889073949e-05,
920
+ "loss": 1.428,
921
+ "step": 140
922
+ },
923
+ {
924
+ "epoch": 2.08,
925
+ "learning_rate": 9.505462800772612e-05,
926
+ "loss": 1.4537,
927
+ "step": 141
928
+ },
929
+ {
930
+ "epoch": 2.09,
931
+ "learning_rate": 9.38197036539916e-05,
932
+ "loss": 1.4288,
933
+ "step": 142
934
+ },
935
+ {
936
+ "epoch": 2.11,
937
+ "learning_rate": 9.25857247448354e-05,
938
+ "loss": 1.4514,
939
+ "step": 143
940
+ },
941
+ {
942
+ "epoch": 2.12,
943
+ "learning_rate": 9.135288005092546e-05,
944
+ "loss": 1.3794,
945
+ "step": 144
946
+ },
947
+ {
948
+ "epoch": 2.14,
949
+ "learning_rate": 9.012135816942058e-05,
950
+ "loss": 1.4776,
951
+ "step": 145
952
+ },
953
+ {
954
+ "epoch": 2.15,
955
+ "learning_rate": 8.889134749511955e-05,
956
+ "loss": 1.3694,
957
+ "step": 146
958
+ },
959
+ {
960
+ "epoch": 2.17,
961
+ "learning_rate": 8.76630361916407e-05,
962
+ "loss": 1.4572,
963
+ "step": 147
964
+ },
965
+ {
966
+ "epoch": 2.18,
967
+ "learning_rate": 8.643661216263743e-05,
968
+ "loss": 1.4835,
969
+ "step": 148
970
+ },
971
+ {
972
+ "epoch": 2.2,
973
+ "learning_rate": 8.521226302305311e-05,
974
+ "loss": 1.3926,
975
+ "step": 149
976
+ },
977
+ {
978
+ "epoch": 2.21,
979
+ "learning_rate": 8.399017607042025e-05,
980
+ "loss": 1.367,
981
+ "step": 150
982
+ },
983
+ {
984
+ "epoch": 2.23,
985
+ "learning_rate": 8.277053825620836e-05,
986
+ "loss": 1.426,
987
+ "step": 151
988
+ },
989
+ {
990
+ "epoch": 2.24,
991
+ "learning_rate": 8.155353615722442e-05,
992
+ "loss": 1.3622,
993
+ "step": 152
994
+ },
995
+ {
996
+ "epoch": 2.26,
997
+ "learning_rate": 8.033935594707117e-05,
998
+ "loss": 1.4358,
999
+ "step": 153
1000
+ },
1001
+ {
1002
+ "epoch": 2.26,
1003
+ "eval_loss": 1.855719804763794,
1004
+ "eval_runtime": 16.6995,
1005
+ "eval_samples_per_second": 2.695,
1006
+ "eval_steps_per_second": 1.377,
1007
+ "step": 153
1008
+ },
1009
+ {
1010
+ "epoch": 2.27,
1011
+ "learning_rate": 7.91281833676665e-05,
1012
+ "loss": 1.5099,
1013
+ "step": 154
1014
+ },
1015
+ {
1016
+ "epoch": 2.29,
1017
+ "learning_rate": 7.79202037008294e-05,
1018
+ "loss": 1.4327,
1019
+ "step": 155
1020
+ },
1021
+ {
1022
+ "epoch": 2.3,
1023
+ "learning_rate": 7.671560173993587e-05,
1024
+ "loss": 1.4428,
1025
+ "step": 156
1026
+ },
1027
+ {
1028
+ "epoch": 2.32,
1029
+ "learning_rate": 7.551456176164989e-05,
1030
+ "loss": 1.4409,
1031
+ "step": 157
1032
+ },
1033
+ {
1034
+ "epoch": 2.33,
1035
+ "learning_rate": 7.431726749773322e-05,
1036
+ "loss": 1.4845,
1037
+ "step": 158
1038
+ },
1039
+ {
1040
+ "epoch": 2.35,
1041
+ "learning_rate": 7.312390210693863e-05,
1042
+ "loss": 1.4052,
1043
+ "step": 159
1044
+ },
1045
+ {
1046
+ "epoch": 2.36,
1047
+ "learning_rate": 7.193464814699073e-05,
1048
+ "loss": 1.4676,
1049
+ "step": 160
1050
+ },
1051
+ {
1052
+ "epoch": 2.38,
1053
+ "learning_rate": 7.07496875466589e-05,
1054
+ "loss": 1.4254,
1055
+ "step": 161
1056
+ },
1057
+ {
1058
+ "epoch": 2.39,
1059
+ "learning_rate": 6.956920157792639e-05,
1060
+ "loss": 1.5144,
1061
+ "step": 162
1062
+ },
1063
+ {
1064
+ "epoch": 2.41,
1065
+ "learning_rate": 6.839337082825955e-05,
1066
+ "loss": 1.4274,
1067
+ "step": 163
1068
+ },
1069
+ {
1070
+ "epoch": 2.42,
1071
+ "learning_rate": 6.722237517298232e-05,
1072
+ "loss": 1.3997,
1073
+ "step": 164
1074
+ },
1075
+ {
1076
+ "epoch": 2.44,
1077
+ "learning_rate": 6.605639374775934e-05,
1078
+ "loss": 1.4757,
1079
+ "step": 165
1080
+ },
1081
+ {
1082
+ "epoch": 2.45,
1083
+ "learning_rate": 6.489560492119225e-05,
1084
+ "loss": 1.424,
1085
+ "step": 166
1086
+ },
1087
+ {
1088
+ "epoch": 2.47,
1089
+ "learning_rate": 6.374018626753331e-05,
1090
+ "loss": 1.434,
1091
+ "step": 167
1092
+ },
1093
+ {
1094
+ "epoch": 2.48,
1095
+ "learning_rate": 6.259031453952069e-05,
1096
+ "loss": 1.4782,
1097
+ "step": 168
1098
+ },
1099
+ {
1100
+ "epoch": 2.5,
1101
+ "learning_rate": 6.144616564133928e-05,
1102
+ "loss": 1.3865,
1103
+ "step": 169
1104
+ },
1105
+ {
1106
+ "epoch": 2.51,
1107
+ "learning_rate": 6.0307914601711305e-05,
1108
+ "loss": 1.4608,
1109
+ "step": 170
1110
+ },
1111
+ {
1112
+ "epoch": 2.51,
1113
+ "eval_loss": 1.884387731552124,
1114
+ "eval_runtime": 16.8363,
1115
+ "eval_samples_per_second": 2.673,
1116
+ "eval_steps_per_second": 1.366,
1117
+ "step": 170
1118
+ },
1119
+ {
1120
+ "epoch": 2.53,
1121
+ "learning_rate": 5.917573554712097e-05,
1122
+ "loss": 1.5069,
1123
+ "step": 171
1124
+ },
1125
+ {
1126
+ "epoch": 2.54,
1127
+ "learning_rate": 5.8049801675177115e-05,
1128
+ "loss": 1.4022,
1129
+ "step": 172
1130
+ },
1131
+ {
1132
+ "epoch": 2.56,
1133
+ "learning_rate": 5.693028522811783e-05,
1134
+ "loss": 1.4741,
1135
+ "step": 173
1136
+ },
1137
+ {
1138
+ "epoch": 2.57,
1139
+ "learning_rate": 5.5817357466461336e-05,
1140
+ "loss": 1.527,
1141
+ "step": 174
1142
+ },
1143
+ {
1144
+ "epoch": 2.59,
1145
+ "learning_rate": 5.471118864280716e-05,
1146
+ "loss": 1.4785,
1147
+ "step": 175
1148
+ },
1149
+ {
1150
+ "epoch": 2.6,
1151
+ "learning_rate": 5.361194797579108e-05,
1152
+ "loss": 1.4178,
1153
+ "step": 176
1154
+ },
1155
+ {
1156
+ "epoch": 2.62,
1157
+ "learning_rate": 5.251980362419886e-05,
1158
+ "loss": 1.4574,
1159
+ "step": 177
1160
+ },
1161
+ {
1162
+ "epoch": 2.63,
1163
+ "learning_rate": 5.1434922661241635e-05,
1164
+ "loss": 1.3573,
1165
+ "step": 178
1166
+ },
1167
+ {
1168
+ "epoch": 2.65,
1169
+ "learning_rate": 5.035747104899739e-05,
1170
+ "loss": 1.4175,
1171
+ "step": 179
1172
+ },
1173
+ {
1174
+ "epoch": 2.66,
1175
+ "learning_rate": 4.928761361302269e-05,
1176
+ "loss": 1.3781,
1177
+ "step": 180
1178
+ },
1179
+ {
1180
+ "epoch": 2.68,
1181
+ "learning_rate": 4.822551401713821e-05,
1182
+ "loss": 1.466,
1183
+ "step": 181
1184
+ },
1185
+ {
1186
+ "epoch": 2.69,
1187
+ "learning_rate": 4.717133473839163e-05,
1188
+ "loss": 1.4341,
1189
+ "step": 182
1190
+ },
1191
+ {
1192
+ "epoch": 2.71,
1193
+ "learning_rate": 4.612523704220264e-05,
1194
+ "loss": 1.4537,
1195
+ "step": 183
1196
+ },
1197
+ {
1198
+ "epoch": 2.72,
1199
+ "learning_rate": 4.5087380957692784e-05,
1200
+ "loss": 1.4164,
1201
+ "step": 184
1202
+ },
1203
+ {
1204
+ "epoch": 2.74,
1205
+ "learning_rate": 4.405792525320469e-05,
1206
+ "loss": 1.4499,
1207
+ "step": 185
1208
+ },
1209
+ {
1210
+ "epoch": 2.75,
1211
+ "learning_rate": 4.303702741201431e-05,
1212
+ "loss": 1.4119,
1213
+ "step": 186
1214
+ },
1215
+ {
1216
+ "epoch": 2.77,
1217
+ "learning_rate": 4.2024843608239264e-05,
1218
+ "loss": 1.4465,
1219
+ "step": 187
1220
+ },
1221
+ {
1222
+ "epoch": 2.77,
1223
+ "eval_loss": 1.89795982837677,
1224
+ "eval_runtime": 16.6564,
1225
+ "eval_samples_per_second": 2.702,
1226
+ "eval_steps_per_second": 1.381,
1227
+ "step": 187
1228
+ },
1229
+ {
1230
+ "epoch": 2.78,
1231
+ "learning_rate": 4.1021528682948066e-05,
1232
+ "loss": 1.3902,
1233
+ "step": 188
1234
+ },
1235
+ {
1236
+ "epoch": 2.8,
1237
+ "learning_rate": 4.0027236120472724e-05,
1238
+ "loss": 1.4166,
1239
+ "step": 189
1240
+ },
1241
+ {
1242
+ "epoch": 2.81,
1243
+ "learning_rate": 3.904211802492922e-05,
1244
+ "loss": 1.4699,
1245
+ "step": 190
1246
+ },
1247
+ {
1248
+ "epoch": 2.83,
1249
+ "learning_rate": 3.806632509694915e-05,
1250
+ "loss": 1.4347,
1251
+ "step": 191
1252
+ },
1253
+ {
1254
+ "epoch": 2.84,
1255
+ "learning_rate": 3.7100006610625784e-05,
1256
+ "loss": 1.4858,
1257
+ "step": 192
1258
+ },
1259
+ {
1260
+ "epoch": 2.86,
1261
+ "learning_rate": 3.614331039067854e-05,
1262
+ "loss": 1.5347,
1263
+ "step": 193
1264
+ },
1265
+ {
1266
+ "epoch": 2.87,
1267
+ "learning_rate": 3.519638278983948e-05,
1268
+ "loss": 1.4619,
1269
+ "step": 194
1270
+ },
1271
+ {
1272
+ "epoch": 2.89,
1273
+ "learning_rate": 3.425936866646419e-05,
1274
+ "loss": 1.3705,
1275
+ "step": 195
1276
+ },
1277
+ {
1278
+ "epoch": 2.9,
1279
+ "learning_rate": 3.333241136237206e-05,
1280
+ "loss": 1.4704,
1281
+ "step": 196
1282
+ },
1283
+ {
1284
+ "epoch": 2.92,
1285
+ "learning_rate": 3.2415652680918264e-05,
1286
+ "loss": 1.5148,
1287
+ "step": 197
1288
+ },
1289
+ {
1290
+ "epoch": 2.93,
1291
+ "learning_rate": 3.150923286530089e-05,
1292
+ "loss": 1.3734,
1293
+ "step": 198
1294
+ }
1295
+ ],
1296
+ "logging_steps": 1,
1297
+ "max_steps": 264,
1298
+ "num_input_tokens_seen": 0,
1299
+ "num_train_epochs": 4,
1300
+ "save_steps": 66,
1301
+ "total_flos": 2.601613393794171e+17,
1302
+ "train_batch_size": 2,
1303
+ "trial_name": null,
1304
+ "trial_params": null
1305
+ }
checkpoint-198/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136f5d9dd7fc2fabff6e80dd48a495a4cd5f0ab1af46964ed1af4cae2dae0a30
3
+ size 5368
checkpoint-264/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-264/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-264/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9a4091d2f49e380ddfed0a19fe0875af996325d0b479b6526f069edc80a284
3
+ size 319876032
checkpoint-264/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6d6c6e1bd68e74152e6a06eb79143a9b58137b71e5730ccef2240b5369bfcb
3
+ size 160736532
checkpoint-264/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bbb045e13babd3fb0b725a290a0af694c2b8d2291519ad624a6ceb46494f6b6
3
+ size 14244
checkpoint-264/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4834c2a43acd42004d05f9c2506492d0eab6431c2e7158f20b8516b9a177b83
3
+ size 1064
checkpoint-264/trainer_state.json ADDED
@@ -0,0 +1,1733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9022556390977443,
5
+ "eval_steps": 17,
6
+ "global_step": 264,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.8373,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "eval_loss": 1.8333783149719238,
20
+ "eval_runtime": 16.5756,
21
+ "eval_samples_per_second": 2.715,
22
+ "eval_steps_per_second": 1.388,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.8119,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.05,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.8301,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.06,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.7976,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.08,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.853,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.09,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.7586,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.11,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8416,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.12,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.7755,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.14,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.804,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.15,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.7858,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.17,
81
+ "learning_rate": 0.0001999923511388017,
82
+ "loss": 1.7311,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.18,
87
+ "learning_rate": 0.0001999694057253083,
88
+ "loss": 1.7012,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.2,
93
+ "learning_rate": 0.00019993116726964554,
94
+ "loss": 1.742,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.21,
99
+ "learning_rate": 0.00019987764162142613,
100
+ "loss": 1.7209,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.23,
105
+ "learning_rate": 0.0001998088369688552,
106
+ "loss": 1.7578,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.24,
111
+ "learning_rate": 0.00019972476383747748,
112
+ "loss": 1.6906,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.26,
117
+ "learning_rate": 0.0001996254350885672,
118
+ "loss": 1.738,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.26,
123
+ "eval_loss": 1.754616141319275,
124
+ "eval_runtime": 16.6372,
125
+ "eval_samples_per_second": 2.705,
126
+ "eval_steps_per_second": 1.382,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 0.27,
131
+ "learning_rate": 0.0001995108659171607,
132
+ "loss": 1.7976,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 0.29,
137
+ "learning_rate": 0.00019938107384973166,
138
+ "loss": 1.7781,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 0.3,
143
+ "learning_rate": 0.00019923607874151032,
144
+ "loss": 1.7737,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 0.32,
149
+ "learning_rate": 0.00019907590277344582,
150
+ "loss": 1.6662,
151
+ "step": 21
152
+ },
153
+ {
154
+ "epoch": 0.33,
155
+ "learning_rate": 0.00019890057044881306,
156
+ "loss": 1.7869,
157
+ "step": 22
158
+ },
159
+ {
160
+ "epoch": 0.35,
161
+ "learning_rate": 0.0001987101085894644,
162
+ "loss": 1.6646,
163
+ "step": 23
164
+ },
165
+ {
166
+ "epoch": 0.36,
167
+ "learning_rate": 0.00019850454633172631,
168
+ "loss": 1.7482,
169
+ "step": 24
170
+ },
171
+ {
172
+ "epoch": 0.38,
173
+ "learning_rate": 0.0001982839151219424,
174
+ "loss": 1.7112,
175
+ "step": 25
176
+ },
177
+ {
178
+ "epoch": 0.39,
179
+ "learning_rate": 0.00019804824871166255,
180
+ "loss": 1.7083,
181
+ "step": 26
182
+ },
183
+ {
184
+ "epoch": 0.41,
185
+ "learning_rate": 0.00019779758315248004,
186
+ "loss": 1.728,
187
+ "step": 27
188
+ },
189
+ {
190
+ "epoch": 0.42,
191
+ "learning_rate": 0.00019753195679051628,
192
+ "loss": 1.7292,
193
+ "step": 28
194
+ },
195
+ {
196
+ "epoch": 0.44,
197
+ "learning_rate": 0.0001972514102605547,
198
+ "loss": 1.6902,
199
+ "step": 29
200
+ },
201
+ {
202
+ "epoch": 0.45,
203
+ "learning_rate": 0.00019695598647982468,
204
+ "loss": 1.7432,
205
+ "step": 30
206
+ },
207
+ {
208
+ "epoch": 0.47,
209
+ "learning_rate": 0.00019664573064143604,
210
+ "loss": 1.7258,
211
+ "step": 31
212
+ },
213
+ {
214
+ "epoch": 0.48,
215
+ "learning_rate": 0.00019632069020746572,
216
+ "loss": 1.7363,
217
+ "step": 32
218
+ },
219
+ {
220
+ "epoch": 0.5,
221
+ "learning_rate": 0.00019598091490169694,
222
+ "loss": 1.7142,
223
+ "step": 33
224
+ },
225
+ {
226
+ "epoch": 0.51,
227
+ "learning_rate": 0.00019562645670201276,
228
+ "loss": 1.704,
229
+ "step": 34
230
+ },
231
+ {
232
+ "epoch": 0.51,
233
+ "eval_loss": 1.7388739585876465,
234
+ "eval_runtime": 16.5955,
235
+ "eval_samples_per_second": 2.712,
236
+ "eval_steps_per_second": 1.386,
237
+ "step": 34
238
+ },
239
+ {
240
+ "epoch": 0.53,
241
+ "learning_rate": 0.0001952573698324446,
242
+ "loss": 1.7393,
243
+ "step": 35
244
+ },
245
+ {
246
+ "epoch": 0.54,
247
+ "learning_rate": 0.00019487371075487713,
248
+ "loss": 1.7568,
249
+ "step": 36
250
+ },
251
+ {
252
+ "epoch": 0.56,
253
+ "learning_rate": 0.000194475538160411,
254
+ "loss": 1.7445,
255
+ "step": 37
256
+ },
257
+ {
258
+ "epoch": 0.57,
259
+ "learning_rate": 0.0001940629129603844,
260
+ "loss": 1.6595,
261
+ "step": 38
262
+ },
263
+ {
264
+ "epoch": 0.59,
265
+ "learning_rate": 0.00019363589827705492,
266
+ "loss": 1.7288,
267
+ "step": 39
268
+ },
269
+ {
270
+ "epoch": 0.6,
271
+ "learning_rate": 0.00019319455943394347,
272
+ "loss": 1.6342,
273
+ "step": 40
274
+ },
275
+ {
276
+ "epoch": 0.62,
277
+ "learning_rate": 0.00019273896394584103,
278
+ "loss": 1.7066,
279
+ "step": 41
280
+ },
281
+ {
282
+ "epoch": 0.63,
283
+ "learning_rate": 0.00019226918150848068,
284
+ "loss": 1.6558,
285
+ "step": 42
286
+ },
287
+ {
288
+ "epoch": 0.65,
289
+ "learning_rate": 0.00019178528398787551,
290
+ "loss": 1.6756,
291
+ "step": 43
292
+ },
293
+ {
294
+ "epoch": 0.66,
295
+ "learning_rate": 0.00019128734540932495,
296
+ "loss": 1.7146,
297
+ "step": 44
298
+ },
299
+ {
300
+ "epoch": 0.68,
301
+ "learning_rate": 0.00019077544194609042,
302
+ "loss": 1.7043,
303
+ "step": 45
304
+ },
305
+ {
306
+ "epoch": 0.69,
307
+ "learning_rate": 0.00019024965190774263,
308
+ "loss": 1.6396,
309
+ "step": 46
310
+ },
311
+ {
312
+ "epoch": 0.71,
313
+ "learning_rate": 0.00018971005572818213,
314
+ "loss": 1.648,
315
+ "step": 47
316
+ },
317
+ {
318
+ "epoch": 0.72,
319
+ "learning_rate": 0.00018915673595333444,
320
+ "loss": 1.5988,
321
+ "step": 48
322
+ },
323
+ {
324
+ "epoch": 0.74,
325
+ "learning_rate": 0.00018858977722852275,
326
+ "loss": 1.7394,
327
+ "step": 49
328
+ },
329
+ {
330
+ "epoch": 0.75,
331
+ "learning_rate": 0.00018800926628551886,
332
+ "loss": 1.6362,
333
+ "step": 50
334
+ },
335
+ {
336
+ "epoch": 0.77,
337
+ "learning_rate": 0.00018741529192927526,
338
+ "loss": 1.6762,
339
+ "step": 51
340
+ },
341
+ {
342
+ "epoch": 0.77,
343
+ "eval_loss": 1.7409569025039673,
344
+ "eval_runtime": 16.7147,
345
+ "eval_samples_per_second": 2.692,
346
+ "eval_steps_per_second": 1.376,
347
+ "step": 51
348
+ },
349
+ {
350
+ "epoch": 0.78,
351
+ "learning_rate": 0.00018680794502434018,
352
+ "loss": 1.6534,
353
+ "step": 52
354
+ },
355
+ {
356
+ "epoch": 0.8,
357
+ "learning_rate": 0.00018618731848095706,
358
+ "loss": 1.6551,
359
+ "step": 53
360
+ },
361
+ {
362
+ "epoch": 0.81,
363
+ "learning_rate": 0.00018555350724085162,
364
+ "loss": 1.6297,
365
+ "step": 54
366
+ },
367
+ {
368
+ "epoch": 0.83,
369
+ "learning_rate": 0.0001849066082627079,
370
+ "loss": 1.7152,
371
+ "step": 55
372
+ },
373
+ {
374
+ "epoch": 0.84,
375
+ "learning_rate": 0.00018424672050733576,
376
+ "loss": 1.7062,
377
+ "step": 56
378
+ },
379
+ {
380
+ "epoch": 0.86,
381
+ "learning_rate": 0.00018357394492253215,
382
+ "loss": 1.5742,
383
+ "step": 57
384
+ },
385
+ {
386
+ "epoch": 0.87,
387
+ "learning_rate": 0.00018288838442763838,
388
+ "loss": 1.6424,
389
+ "step": 58
390
+ },
391
+ {
392
+ "epoch": 0.89,
393
+ "learning_rate": 0.00018219014389779585,
394
+ "loss": 1.6544,
395
+ "step": 59
396
+ },
397
+ {
398
+ "epoch": 0.9,
399
+ "learning_rate": 0.00018147933014790244,
400
+ "loss": 1.6179,
401
+ "step": 60
402
+ },
403
+ {
404
+ "epoch": 0.92,
405
+ "learning_rate": 0.0001807560519162724,
406
+ "loss": 1.6823,
407
+ "step": 61
408
+ },
409
+ {
410
+ "epoch": 0.93,
411
+ "learning_rate": 0.00018002041984800174,
412
+ "loss": 1.5845,
413
+ "step": 62
414
+ },
415
+ {
416
+ "epoch": 0.95,
417
+ "learning_rate": 0.00017927254647804209,
418
+ "loss": 1.6177,
419
+ "step": 63
420
+ },
421
+ {
422
+ "epoch": 0.96,
423
+ "learning_rate": 0.0001785125462139855,
424
+ "loss": 1.6196,
425
+ "step": 64
426
+ },
427
+ {
428
+ "epoch": 0.98,
429
+ "learning_rate": 0.00017774053531856258,
430
+ "loss": 1.6526,
431
+ "step": 65
432
+ },
433
+ {
434
+ "epoch": 0.99,
435
+ "learning_rate": 0.000176956631891857,
436
+ "loss": 1.5792,
437
+ "step": 66
438
+ },
439
+ {
440
+ "epoch": 1.01,
441
+ "learning_rate": 0.00017616095585323878,
442
+ "loss": 1.6652,
443
+ "step": 67
444
+ },
445
+ {
446
+ "epoch": 1.02,
447
+ "learning_rate": 0.00017535362892301954,
448
+ "loss": 1.5981,
449
+ "step": 68
450
+ },
451
+ {
452
+ "epoch": 1.02,
453
+ "eval_loss": 1.7487449645996094,
454
+ "eval_runtime": 16.6837,
455
+ "eval_samples_per_second": 2.697,
456
+ "eval_steps_per_second": 1.379,
457
+ "step": 68
458
+ },
459
+ {
460
+ "epoch": 1.02,
461
+ "learning_rate": 0.0001745347746038319,
462
+ "loss": 1.6053,
463
+ "step": 69
464
+ },
465
+ {
466
+ "epoch": 1.03,
467
+ "learning_rate": 0.0001737045181617364,
468
+ "loss": 1.6171,
469
+ "step": 70
470
+ },
471
+ {
472
+ "epoch": 1.05,
473
+ "learning_rate": 0.00017286298660705875,
474
+ "loss": 1.631,
475
+ "step": 71
476
+ },
477
+ {
478
+ "epoch": 1.06,
479
+ "learning_rate": 0.00017201030867496005,
480
+ "loss": 1.5558,
481
+ "step": 72
482
+ },
483
+ {
484
+ "epoch": 1.08,
485
+ "learning_rate": 0.00017114661480574332,
486
+ "loss": 1.5339,
487
+ "step": 73
488
+ },
489
+ {
490
+ "epoch": 1.09,
491
+ "learning_rate": 0.000170272037124899,
492
+ "loss": 1.6548,
493
+ "step": 74
494
+ },
495
+ {
496
+ "epoch": 1.11,
497
+ "learning_rate": 0.00016938670942289293,
498
+ "loss": 1.5526,
499
+ "step": 75
500
+ },
501
+ {
502
+ "epoch": 1.12,
503
+ "learning_rate": 0.00016849076713469914,
504
+ "loss": 1.5565,
505
+ "step": 76
506
+ },
507
+ {
508
+ "epoch": 1.14,
509
+ "learning_rate": 0.00016758434731908178,
510
+ "loss": 1.5604,
511
+ "step": 77
512
+ },
513
+ {
514
+ "epoch": 1.15,
515
+ "learning_rate": 0.00016666758863762793,
516
+ "loss": 1.5654,
517
+ "step": 78
518
+ },
519
+ {
520
+ "epoch": 1.17,
521
+ "learning_rate": 0.00016574063133353582,
522
+ "loss": 1.5967,
523
+ "step": 79
524
+ },
525
+ {
526
+ "epoch": 1.18,
527
+ "learning_rate": 0.00016480361721016054,
528
+ "loss": 1.5608,
529
+ "step": 80
530
+ },
531
+ {
532
+ "epoch": 1.2,
533
+ "learning_rate": 0.00016385668960932143,
534
+ "loss": 1.5801,
535
+ "step": 81
536
+ },
537
+ {
538
+ "epoch": 1.21,
539
+ "learning_rate": 0.00016289999338937427,
540
+ "loss": 1.5472,
541
+ "step": 82
542
+ },
543
+ {
544
+ "epoch": 1.23,
545
+ "learning_rate": 0.00016193367490305088,
546
+ "loss": 1.5126,
547
+ "step": 83
548
+ },
549
+ {
550
+ "epoch": 1.24,
551
+ "learning_rate": 0.00016095788197507081,
552
+ "loss": 1.5896,
553
+ "step": 84
554
+ },
555
+ {
556
+ "epoch": 1.26,
557
+ "learning_rate": 0.00015997276387952732,
558
+ "loss": 1.5593,
559
+ "step": 85
560
+ },
561
+ {
562
+ "epoch": 1.26,
563
+ "eval_loss": 1.79562509059906,
564
+ "eval_runtime": 16.6149,
565
+ "eval_samples_per_second": 2.708,
566
+ "eval_steps_per_second": 1.384,
567
+ "step": 85
568
+ },
569
+ {
570
+ "epoch": 1.27,
571
+ "learning_rate": 0.00015897847131705195,
572
+ "loss": 1.5616,
573
+ "step": 86
574
+ },
575
+ {
576
+ "epoch": 1.29,
577
+ "learning_rate": 0.00015797515639176074,
578
+ "loss": 1.596,
579
+ "step": 87
580
+ },
581
+ {
582
+ "epoch": 1.3,
583
+ "learning_rate": 0.0001569629725879857,
584
+ "loss": 1.595,
585
+ "step": 88
586
+ },
587
+ {
588
+ "epoch": 1.32,
589
+ "learning_rate": 0.00015594207474679532,
590
+ "loss": 1.5442,
591
+ "step": 89
592
+ },
593
+ {
594
+ "epoch": 1.33,
595
+ "learning_rate": 0.00015491261904230727,
596
+ "loss": 1.5812,
597
+ "step": 90
598
+ },
599
+ {
600
+ "epoch": 1.35,
601
+ "learning_rate": 0.00015387476295779736,
602
+ "loss": 1.5214,
603
+ "step": 91
604
+ },
605
+ {
606
+ "epoch": 1.36,
607
+ "learning_rate": 0.00015282866526160837,
608
+ "loss": 1.5403,
609
+ "step": 92
610
+ },
611
+ {
612
+ "epoch": 1.38,
613
+ "learning_rate": 0.0001517744859828618,
614
+ "loss": 1.4751,
615
+ "step": 93
616
+ },
617
+ {
618
+ "epoch": 1.39,
619
+ "learning_rate": 0.00015071238638697732,
620
+ "loss": 1.5861,
621
+ "step": 94
622
+ },
623
+ {
624
+ "epoch": 1.41,
625
+ "learning_rate": 0.00014964252895100264,
626
+ "loss": 1.5334,
627
+ "step": 95
628
+ },
629
+ {
630
+ "epoch": 1.42,
631
+ "learning_rate": 0.00014856507733875836,
632
+ "loss": 1.4884,
633
+ "step": 96
634
+ },
635
+ {
636
+ "epoch": 1.44,
637
+ "learning_rate": 0.00014748019637580114,
638
+ "loss": 1.5297,
639
+ "step": 97
640
+ },
641
+ {
642
+ "epoch": 1.45,
643
+ "learning_rate": 0.00014638805202420895,
644
+ "loss": 1.4725,
645
+ "step": 98
646
+ },
647
+ {
648
+ "epoch": 1.47,
649
+ "learning_rate": 0.0001452888113571929,
650
+ "loss": 1.4849,
651
+ "step": 99
652
+ },
653
+ {
654
+ "epoch": 1.48,
655
+ "learning_rate": 0.0001441826425335387,
656
+ "loss": 1.5654,
657
+ "step": 100
658
+ },
659
+ {
660
+ "epoch": 1.5,
661
+ "learning_rate": 0.00014306971477188223,
662
+ "loss": 1.6349,
663
+ "step": 101
664
+ },
665
+ {
666
+ "epoch": 1.51,
667
+ "learning_rate": 0.0001419501983248229,
668
+ "loss": 1.4415,
669
+ "step": 102
670
+ },
671
+ {
672
+ "epoch": 1.51,
673
+ "eval_loss": 1.7860450744628906,
674
+ "eval_runtime": 16.6303,
675
+ "eval_samples_per_second": 2.706,
676
+ "eval_steps_per_second": 1.383,
677
+ "step": 102
678
+ },
679
+ {
680
+ "epoch": 1.53,
681
+ "learning_rate": 0.00014082426445287903,
682
+ "loss": 1.5735,
683
+ "step": 103
684
+ },
685
+ {
686
+ "epoch": 1.54,
687
+ "learning_rate": 0.00013969208539828872,
688
+ "loss": 1.5328,
689
+ "step": 104
690
+ },
691
+ {
692
+ "epoch": 1.56,
693
+ "learning_rate": 0.00013855383435866077,
694
+ "loss": 1.5466,
695
+ "step": 105
696
+ },
697
+ {
698
+ "epoch": 1.57,
699
+ "learning_rate": 0.00013740968546047935,
700
+ "loss": 1.5861,
701
+ "step": 106
702
+ },
703
+ {
704
+ "epoch": 1.59,
705
+ "learning_rate": 0.0001362598137324667,
706
+ "loss": 1.5449,
707
+ "step": 107
708
+ },
709
+ {
710
+ "epoch": 1.6,
711
+ "learning_rate": 0.00013510439507880776,
712
+ "loss": 1.6084,
713
+ "step": 108
714
+ },
715
+ {
716
+ "epoch": 1.62,
717
+ "learning_rate": 0.00013394360625224068,
718
+ "loss": 1.5249,
719
+ "step": 109
720
+ },
721
+ {
722
+ "epoch": 1.63,
723
+ "learning_rate": 0.00013277762482701767,
724
+ "loss": 1.5594,
725
+ "step": 110
726
+ },
727
+ {
728
+ "epoch": 1.65,
729
+ "learning_rate": 0.00013160662917174044,
730
+ "loss": 1.5877,
731
+ "step": 111
732
+ },
733
+ {
734
+ "epoch": 1.66,
735
+ "learning_rate": 0.0001304307984220736,
736
+ "loss": 1.4964,
737
+ "step": 112
738
+ },
739
+ {
740
+ "epoch": 1.68,
741
+ "learning_rate": 0.0001292503124533411,
742
+ "loss": 1.4538,
743
+ "step": 113
744
+ },
745
+ {
746
+ "epoch": 1.69,
747
+ "learning_rate": 0.0001280653518530093,
748
+ "loss": 1.4454,
749
+ "step": 114
750
+ },
751
+ {
752
+ "epoch": 1.71,
753
+ "learning_rate": 0.00012687609789306144,
754
+ "loss": 1.4512,
755
+ "step": 115
756
+ },
757
+ {
758
+ "epoch": 1.72,
759
+ "learning_rate": 0.0001256827325022668,
760
+ "loss": 1.38,
761
+ "step": 116
762
+ },
763
+ {
764
+ "epoch": 1.74,
765
+ "learning_rate": 0.00012448543823835015,
766
+ "loss": 1.5207,
767
+ "step": 117
768
+ },
769
+ {
770
+ "epoch": 1.75,
771
+ "learning_rate": 0.00012328439826006415,
772
+ "loss": 1.4787,
773
+ "step": 118
774
+ },
775
+ {
776
+ "epoch": 1.77,
777
+ "learning_rate": 0.0001220797962991706,
778
+ "loss": 1.6098,
779
+ "step": 119
780
+ },
781
+ {
782
+ "epoch": 1.77,
783
+ "eval_loss": 1.8019659519195557,
784
+ "eval_runtime": 16.646,
785
+ "eval_samples_per_second": 2.703,
786
+ "eval_steps_per_second": 1.382,
787
+ "step": 119
788
+ },
789
+ {
790
+ "epoch": 1.78,
791
+ "learning_rate": 0.00012087181663233354,
792
+ "loss": 1.4798,
793
+ "step": 120
794
+ },
795
+ {
796
+ "epoch": 1.8,
797
+ "learning_rate": 0.00011966064405292887,
798
+ "loss": 1.5248,
799
+ "step": 121
800
+ },
801
+ {
802
+ "epoch": 1.81,
803
+ "learning_rate": 0.0001184464638427756,
804
+ "loss": 1.4309,
805
+ "step": 122
806
+ },
807
+ {
808
+ "epoch": 1.83,
809
+ "learning_rate": 0.00011722946174379168,
810
+ "loss": 1.4477,
811
+ "step": 123
812
+ },
813
+ {
814
+ "epoch": 1.84,
815
+ "learning_rate": 0.00011600982392957978,
816
+ "loss": 1.4843,
817
+ "step": 124
818
+ },
819
+ {
820
+ "epoch": 1.86,
821
+ "learning_rate": 0.00011478773697694691,
822
+ "loss": 1.4298,
823
+ "step": 125
824
+ },
825
+ {
826
+ "epoch": 1.87,
827
+ "learning_rate": 0.00011356338783736255,
828
+ "loss": 1.4775,
829
+ "step": 126
830
+ },
831
+ {
832
+ "epoch": 1.89,
833
+ "learning_rate": 0.0001123369638083593,
834
+ "loss": 1.5159,
835
+ "step": 127
836
+ },
837
+ {
838
+ "epoch": 1.9,
839
+ "learning_rate": 0.00011110865250488047,
840
+ "loss": 1.3696,
841
+ "step": 128
842
+ },
843
+ {
844
+ "epoch": 1.92,
845
+ "learning_rate": 0.00010987864183057943,
846
+ "loss": 1.4259,
847
+ "step": 129
848
+ },
849
+ {
850
+ "epoch": 1.93,
851
+ "learning_rate": 0.00010864711994907458,
852
+ "loss": 1.5685,
853
+ "step": 130
854
+ },
855
+ {
856
+ "epoch": 1.95,
857
+ "learning_rate": 0.00010741427525516463,
858
+ "loss": 1.4997,
859
+ "step": 131
860
+ },
861
+ {
862
+ "epoch": 1.96,
863
+ "learning_rate": 0.00010618029634600843,
864
+ "loss": 1.4718,
865
+ "step": 132
866
+ },
867
+ {
868
+ "epoch": 1.98,
869
+ "learning_rate": 0.00010494537199227392,
870
+ "loss": 1.5824,
871
+ "step": 133
872
+ },
873
+ {
874
+ "epoch": 1.99,
875
+ "learning_rate": 0.00010370969110926052,
876
+ "loss": 1.5392,
877
+ "step": 134
878
+ },
879
+ {
880
+ "epoch": 2.01,
881
+ "learning_rate": 0.0001024734427279995,
882
+ "loss": 1.5724,
883
+ "step": 135
884
+ },
885
+ {
886
+ "epoch": 2.02,
887
+ "learning_rate": 0.00010123681596633629,
888
+ "loss": 1.5458,
889
+ "step": 136
890
+ },
891
+ {
892
+ "epoch": 2.02,
893
+ "eval_loss": 1.852607250213623,
894
+ "eval_runtime": 16.6761,
895
+ "eval_samples_per_second": 2.698,
896
+ "eval_steps_per_second": 1.379,
897
+ "step": 136
898
+ },
899
+ {
900
+ "epoch": 2.02,
901
+ "learning_rate": 0.0001,
902
+ "loss": 1.3,
903
+ "step": 137
904
+ },
905
+ {
906
+ "epoch": 2.03,
907
+ "learning_rate": 9.876318403366372e-05,
908
+ "loss": 1.4398,
909
+ "step": 138
910
+ },
911
+ {
912
+ "epoch": 2.05,
913
+ "learning_rate": 9.75265572720005e-05,
914
+ "loss": 1.4742,
915
+ "step": 139
916
+ },
917
+ {
918
+ "epoch": 2.06,
919
+ "learning_rate": 9.629030889073949e-05,
920
+ "loss": 1.428,
921
+ "step": 140
922
+ },
923
+ {
924
+ "epoch": 2.08,
925
+ "learning_rate": 9.505462800772612e-05,
926
+ "loss": 1.4537,
927
+ "step": 141
928
+ },
929
+ {
930
+ "epoch": 2.09,
931
+ "learning_rate": 9.38197036539916e-05,
932
+ "loss": 1.4288,
933
+ "step": 142
934
+ },
935
+ {
936
+ "epoch": 2.11,
937
+ "learning_rate": 9.25857247448354e-05,
938
+ "loss": 1.4514,
939
+ "step": 143
940
+ },
941
+ {
942
+ "epoch": 2.12,
943
+ "learning_rate": 9.135288005092546e-05,
944
+ "loss": 1.3794,
945
+ "step": 144
946
+ },
947
+ {
948
+ "epoch": 2.14,
949
+ "learning_rate": 9.012135816942058e-05,
950
+ "loss": 1.4776,
951
+ "step": 145
952
+ },
953
+ {
954
+ "epoch": 2.15,
955
+ "learning_rate": 8.889134749511955e-05,
956
+ "loss": 1.3694,
957
+ "step": 146
958
+ },
959
+ {
960
+ "epoch": 2.17,
961
+ "learning_rate": 8.76630361916407e-05,
962
+ "loss": 1.4572,
963
+ "step": 147
964
+ },
965
+ {
966
+ "epoch": 2.18,
967
+ "learning_rate": 8.643661216263743e-05,
968
+ "loss": 1.4835,
969
+ "step": 148
970
+ },
971
+ {
972
+ "epoch": 2.2,
973
+ "learning_rate": 8.521226302305311e-05,
974
+ "loss": 1.3926,
975
+ "step": 149
976
+ },
977
+ {
978
+ "epoch": 2.21,
979
+ "learning_rate": 8.399017607042025e-05,
980
+ "loss": 1.367,
981
+ "step": 150
982
+ },
983
+ {
984
+ "epoch": 2.23,
985
+ "learning_rate": 8.277053825620836e-05,
986
+ "loss": 1.426,
987
+ "step": 151
988
+ },
989
+ {
990
+ "epoch": 2.24,
991
+ "learning_rate": 8.155353615722442e-05,
992
+ "loss": 1.3622,
993
+ "step": 152
994
+ },
995
+ {
996
+ "epoch": 2.26,
997
+ "learning_rate": 8.033935594707117e-05,
998
+ "loss": 1.4358,
999
+ "step": 153
1000
+ },
1001
+ {
1002
+ "epoch": 2.26,
1003
+ "eval_loss": 1.855719804763794,
1004
+ "eval_runtime": 16.6995,
1005
+ "eval_samples_per_second": 2.695,
1006
+ "eval_steps_per_second": 1.377,
1007
+ "step": 153
1008
+ },
1009
+ {
1010
+ "epoch": 2.27,
1011
+ "learning_rate": 7.91281833676665e-05,
1012
+ "loss": 1.5099,
1013
+ "step": 154
1014
+ },
1015
+ {
1016
+ "epoch": 2.29,
1017
+ "learning_rate": 7.79202037008294e-05,
1018
+ "loss": 1.4327,
1019
+ "step": 155
1020
+ },
1021
+ {
1022
+ "epoch": 2.3,
1023
+ "learning_rate": 7.671560173993587e-05,
1024
+ "loss": 1.4428,
1025
+ "step": 156
1026
+ },
1027
+ {
1028
+ "epoch": 2.32,
1029
+ "learning_rate": 7.551456176164989e-05,
1030
+ "loss": 1.4409,
1031
+ "step": 157
1032
+ },
1033
+ {
1034
+ "epoch": 2.33,
1035
+ "learning_rate": 7.431726749773322e-05,
1036
+ "loss": 1.4845,
1037
+ "step": 158
1038
+ },
1039
+ {
1040
+ "epoch": 2.35,
1041
+ "learning_rate": 7.312390210693863e-05,
1042
+ "loss": 1.4052,
1043
+ "step": 159
1044
+ },
1045
+ {
1046
+ "epoch": 2.36,
1047
+ "learning_rate": 7.193464814699073e-05,
1048
+ "loss": 1.4676,
1049
+ "step": 160
1050
+ },
1051
+ {
1052
+ "epoch": 2.38,
1053
+ "learning_rate": 7.07496875466589e-05,
1054
+ "loss": 1.4254,
1055
+ "step": 161
1056
+ },
1057
+ {
1058
+ "epoch": 2.39,
1059
+ "learning_rate": 6.956920157792639e-05,
1060
+ "loss": 1.5144,
1061
+ "step": 162
1062
+ },
1063
+ {
1064
+ "epoch": 2.41,
1065
+ "learning_rate": 6.839337082825955e-05,
1066
+ "loss": 1.4274,
1067
+ "step": 163
1068
+ },
1069
+ {
1070
+ "epoch": 2.42,
1071
+ "learning_rate": 6.722237517298232e-05,
1072
+ "loss": 1.3997,
1073
+ "step": 164
1074
+ },
1075
+ {
1076
+ "epoch": 2.44,
1077
+ "learning_rate": 6.605639374775934e-05,
1078
+ "loss": 1.4757,
1079
+ "step": 165
1080
+ },
1081
+ {
1082
+ "epoch": 2.45,
1083
+ "learning_rate": 6.489560492119225e-05,
1084
+ "loss": 1.424,
1085
+ "step": 166
1086
+ },
1087
+ {
1088
+ "epoch": 2.47,
1089
+ "learning_rate": 6.374018626753331e-05,
1090
+ "loss": 1.434,
1091
+ "step": 167
1092
+ },
1093
+ {
1094
+ "epoch": 2.48,
1095
+ "learning_rate": 6.259031453952069e-05,
1096
+ "loss": 1.4782,
1097
+ "step": 168
1098
+ },
1099
+ {
1100
+ "epoch": 2.5,
1101
+ "learning_rate": 6.144616564133928e-05,
1102
+ "loss": 1.3865,
1103
+ "step": 169
1104
+ },
1105
+ {
1106
+ "epoch": 2.51,
1107
+ "learning_rate": 6.0307914601711305e-05,
1108
+ "loss": 1.4608,
1109
+ "step": 170
1110
+ },
1111
+ {
1112
+ "epoch": 2.51,
1113
+ "eval_loss": 1.884387731552124,
1114
+ "eval_runtime": 16.8363,
1115
+ "eval_samples_per_second": 2.673,
1116
+ "eval_steps_per_second": 1.366,
1117
+ "step": 170
1118
+ },
1119
+ {
1120
+ "epoch": 2.53,
1121
+ "learning_rate": 5.917573554712097e-05,
1122
+ "loss": 1.5069,
1123
+ "step": 171
1124
+ },
1125
+ {
1126
+ "epoch": 2.54,
1127
+ "learning_rate": 5.8049801675177115e-05,
1128
+ "loss": 1.4022,
1129
+ "step": 172
1130
+ },
1131
+ {
1132
+ "epoch": 2.56,
1133
+ "learning_rate": 5.693028522811783e-05,
1134
+ "loss": 1.4741,
1135
+ "step": 173
1136
+ },
1137
+ {
1138
+ "epoch": 2.57,
1139
+ "learning_rate": 5.5817357466461336e-05,
1140
+ "loss": 1.527,
1141
+ "step": 174
1142
+ },
1143
+ {
1144
+ "epoch": 2.59,
1145
+ "learning_rate": 5.471118864280716e-05,
1146
+ "loss": 1.4785,
1147
+ "step": 175
1148
+ },
1149
+ {
1150
+ "epoch": 2.6,
1151
+ "learning_rate": 5.361194797579108e-05,
1152
+ "loss": 1.4178,
1153
+ "step": 176
1154
+ },
1155
+ {
1156
+ "epoch": 2.62,
1157
+ "learning_rate": 5.251980362419886e-05,
1158
+ "loss": 1.4574,
1159
+ "step": 177
1160
+ },
1161
+ {
1162
+ "epoch": 2.63,
1163
+ "learning_rate": 5.1434922661241635e-05,
1164
+ "loss": 1.3573,
1165
+ "step": 178
1166
+ },
1167
+ {
1168
+ "epoch": 2.65,
1169
+ "learning_rate": 5.035747104899739e-05,
1170
+ "loss": 1.4175,
1171
+ "step": 179
1172
+ },
1173
+ {
1174
+ "epoch": 2.66,
1175
+ "learning_rate": 4.928761361302269e-05,
1176
+ "loss": 1.3781,
1177
+ "step": 180
1178
+ },
1179
+ {
1180
+ "epoch": 2.68,
1181
+ "learning_rate": 4.822551401713821e-05,
1182
+ "loss": 1.466,
1183
+ "step": 181
1184
+ },
1185
+ {
1186
+ "epoch": 2.69,
1187
+ "learning_rate": 4.717133473839163e-05,
1188
+ "loss": 1.4341,
1189
+ "step": 182
1190
+ },
1191
+ {
1192
+ "epoch": 2.71,
1193
+ "learning_rate": 4.612523704220264e-05,
1194
+ "loss": 1.4537,
1195
+ "step": 183
1196
+ },
1197
+ {
1198
+ "epoch": 2.72,
1199
+ "learning_rate": 4.5087380957692784e-05,
1200
+ "loss": 1.4164,
1201
+ "step": 184
1202
+ },
1203
+ {
1204
+ "epoch": 2.74,
1205
+ "learning_rate": 4.405792525320469e-05,
1206
+ "loss": 1.4499,
1207
+ "step": 185
1208
+ },
1209
+ {
1210
+ "epoch": 2.75,
1211
+ "learning_rate": 4.303702741201431e-05,
1212
+ "loss": 1.4119,
1213
+ "step": 186
1214
+ },
1215
+ {
1216
+ "epoch": 2.77,
1217
+ "learning_rate": 4.2024843608239264e-05,
1218
+ "loss": 1.4465,
1219
+ "step": 187
1220
+ },
1221
+ {
1222
+ "epoch": 2.77,
1223
+ "eval_loss": 1.89795982837677,
1224
+ "eval_runtime": 16.6564,
1225
+ "eval_samples_per_second": 2.702,
1226
+ "eval_steps_per_second": 1.381,
1227
+ "step": 187
1228
+ },
1229
+ {
1230
+ "epoch": 2.78,
1231
+ "learning_rate": 4.1021528682948066e-05,
1232
+ "loss": 1.3902,
1233
+ "step": 188
1234
+ },
1235
+ {
1236
+ "epoch": 2.8,
1237
+ "learning_rate": 4.0027236120472724e-05,
1238
+ "loss": 1.4166,
1239
+ "step": 189
1240
+ },
1241
+ {
1242
+ "epoch": 2.81,
1243
+ "learning_rate": 3.904211802492922e-05,
1244
+ "loss": 1.4699,
1245
+ "step": 190
1246
+ },
1247
+ {
1248
+ "epoch": 2.83,
1249
+ "learning_rate": 3.806632509694915e-05,
1250
+ "loss": 1.4347,
1251
+ "step": 191
1252
+ },
1253
+ {
1254
+ "epoch": 2.84,
1255
+ "learning_rate": 3.7100006610625784e-05,
1256
+ "loss": 1.4858,
1257
+ "step": 192
1258
+ },
1259
+ {
1260
+ "epoch": 2.86,
1261
+ "learning_rate": 3.614331039067854e-05,
1262
+ "loss": 1.5347,
1263
+ "step": 193
1264
+ },
1265
+ {
1266
+ "epoch": 2.87,
1267
+ "learning_rate": 3.519638278983948e-05,
1268
+ "loss": 1.4619,
1269
+ "step": 194
1270
+ },
1271
+ {
1272
+ "epoch": 2.89,
1273
+ "learning_rate": 3.425936866646419e-05,
1274
+ "loss": 1.3705,
1275
+ "step": 195
1276
+ },
1277
+ {
1278
+ "epoch": 2.9,
1279
+ "learning_rate": 3.333241136237206e-05,
1280
+ "loss": 1.4704,
1281
+ "step": 196
1282
+ },
1283
+ {
1284
+ "epoch": 2.92,
1285
+ "learning_rate": 3.2415652680918264e-05,
1286
+ "loss": 1.5148,
1287
+ "step": 197
1288
+ },
1289
+ {
1290
+ "epoch": 2.93,
1291
+ "learning_rate": 3.150923286530089e-05,
1292
+ "loss": 1.3734,
1293
+ "step": 198
1294
+ },
1295
+ {
1296
+ "epoch": 2.95,
1297
+ "learning_rate": 3.0613290577107115e-05,
1298
+ "loss": 1.5199,
1299
+ "step": 199
1300
+ },
1301
+ {
1302
+ "epoch": 2.96,
1303
+ "learning_rate": 2.9727962875101e-05,
1304
+ "loss": 1.3702,
1305
+ "step": 200
1306
+ },
1307
+ {
1308
+ "epoch": 2.98,
1309
+ "learning_rate": 2.8853385194256676e-05,
1310
+ "loss": 1.4275,
1311
+ "step": 201
1312
+ },
1313
+ {
1314
+ "epoch": 2.99,
1315
+ "learning_rate": 2.798969132503997e-05,
1316
+ "loss": 1.4594,
1317
+ "step": 202
1318
+ },
1319
+ {
1320
+ "epoch": 3.01,
1321
+ "learning_rate": 2.713701339294129e-05,
1322
+ "loss": 1.3708,
1323
+ "step": 203
1324
+ },
1325
+ {
1326
+ "epoch": 3.02,
1327
+ "learning_rate": 2.6295481838263626e-05,
1328
+ "loss": 1.3986,
1329
+ "step": 204
1330
+ },
1331
+ {
1332
+ "epoch": 3.02,
1333
+ "eval_loss": 1.899756669998169,
1334
+ "eval_runtime": 16.6316,
1335
+ "eval_samples_per_second": 2.706,
1336
+ "eval_steps_per_second": 1.383,
1337
+ "step": 204
1338
+ },
1339
+ {
1340
+ "epoch": 3.02,
1341
+ "learning_rate": 2.5465225396168134e-05,
1342
+ "loss": 1.3877,
1343
+ "step": 205
1344
+ },
1345
+ {
1346
+ "epoch": 3.03,
1347
+ "learning_rate": 2.4646371076980457e-05,
1348
+ "loss": 1.3825,
1349
+ "step": 206
1350
+ },
1351
+ {
1352
+ "epoch": 3.05,
1353
+ "learning_rate": 2.3839044146761225e-05,
1354
+ "loss": 1.3739,
1355
+ "step": 207
1356
+ },
1357
+ {
1358
+ "epoch": 3.06,
1359
+ "learning_rate": 2.3043368108143047e-05,
1360
+ "loss": 1.3736,
1361
+ "step": 208
1362
+ },
1363
+ {
1364
+ "epoch": 3.08,
1365
+ "learning_rate": 2.2259464681437404e-05,
1366
+ "loss": 1.4417,
1367
+ "step": 209
1368
+ },
1369
+ {
1370
+ "epoch": 3.09,
1371
+ "learning_rate": 2.1487453786014512e-05,
1372
+ "loss": 1.4593,
1373
+ "step": 210
1374
+ },
1375
+ {
1376
+ "epoch": 3.11,
1377
+ "learning_rate": 2.072745352195794e-05,
1378
+ "loss": 1.4009,
1379
+ "step": 211
1380
+ },
1381
+ {
1382
+ "epoch": 3.12,
1383
+ "learning_rate": 1.997958015199829e-05,
1384
+ "loss": 1.3663,
1385
+ "step": 212
1386
+ },
1387
+ {
1388
+ "epoch": 3.14,
1389
+ "learning_rate": 1.9243948083727626e-05,
1390
+ "loss": 1.4188,
1391
+ "step": 213
1392
+ },
1393
+ {
1394
+ "epoch": 3.15,
1395
+ "learning_rate": 1.8520669852097573e-05,
1396
+ "loss": 1.3341,
1397
+ "step": 214
1398
+ },
1399
+ {
1400
+ "epoch": 3.17,
1401
+ "learning_rate": 1.7809856102204147e-05,
1402
+ "loss": 1.4234,
1403
+ "step": 215
1404
+ },
1405
+ {
1406
+ "epoch": 3.18,
1407
+ "learning_rate": 1.7111615572361628e-05,
1408
+ "loss": 1.4341,
1409
+ "step": 216
1410
+ },
1411
+ {
1412
+ "epoch": 3.2,
1413
+ "learning_rate": 1.642605507746786e-05,
1414
+ "loss": 1.448,
1415
+ "step": 217
1416
+ },
1417
+ {
1418
+ "epoch": 3.21,
1419
+ "learning_rate": 1.5753279492664262e-05,
1420
+ "loss": 1.4208,
1421
+ "step": 218
1422
+ },
1423
+ {
1424
+ "epoch": 3.23,
1425
+ "learning_rate": 1.509339173729214e-05,
1426
+ "loss": 1.457,
1427
+ "step": 219
1428
+ },
1429
+ {
1430
+ "epoch": 3.24,
1431
+ "learning_rate": 1.4446492759148411e-05,
1432
+ "loss": 1.394,
1433
+ "step": 220
1434
+ },
1435
+ {
1436
+ "epoch": 3.26,
1437
+ "learning_rate": 1.381268151904298e-05,
1438
+ "loss": 1.5333,
1439
+ "step": 221
1440
+ },
1441
+ {
1442
+ "epoch": 3.26,
1443
+ "eval_loss": 1.919499158859253,
1444
+ "eval_runtime": 16.6053,
1445
+ "eval_samples_per_second": 2.71,
1446
+ "eval_steps_per_second": 1.385,
1447
+ "step": 221
1448
+ },
1449
+ {
1450
+ "epoch": 3.27,
1451
+ "learning_rate": 1.319205497565983e-05,
1452
+ "loss": 1.3947,
1453
+ "step": 222
1454
+ },
1455
+ {
1456
+ "epoch": 3.29,
1457
+ "learning_rate": 1.2584708070724737e-05,
1458
+ "loss": 1.3737,
1459
+ "step": 223
1460
+ },
1461
+ {
1462
+ "epoch": 3.3,
1463
+ "learning_rate": 1.1990733714481184e-05,
1464
+ "loss": 1.3943,
1465
+ "step": 224
1466
+ },
1467
+ {
1468
+ "epoch": 3.32,
1469
+ "learning_rate": 1.1410222771477274e-05,
1470
+ "loss": 1.3721,
1471
+ "step": 225
1472
+ },
1473
+ {
1474
+ "epoch": 3.33,
1475
+ "learning_rate": 1.0843264046665557e-05,
1476
+ "loss": 1.4123,
1477
+ "step": 226
1478
+ },
1479
+ {
1480
+ "epoch": 3.35,
1481
+ "learning_rate": 1.0289944271817897e-05,
1482
+ "loss": 1.4098,
1483
+ "step": 227
1484
+ },
1485
+ {
1486
+ "epoch": 3.36,
1487
+ "learning_rate": 9.750348092257367e-06,
1488
+ "loss": 1.4299,
1489
+ "step": 228
1490
+ },
1491
+ {
1492
+ "epoch": 3.38,
1493
+ "learning_rate": 9.224558053909615e-06,
1494
+ "loss": 1.3941,
1495
+ "step": 229
1496
+ },
1497
+ {
1498
+ "epoch": 3.39,
1499
+ "learning_rate": 8.712654590675085e-06,
1500
+ "loss": 1.4251,
1501
+ "step": 230
1502
+ },
1503
+ {
1504
+ "epoch": 3.41,
1505
+ "learning_rate": 8.21471601212449e-06,
1506
+ "loss": 1.3037,
1507
+ "step": 231
1508
+ },
1509
+ {
1510
+ "epoch": 3.42,
1511
+ "learning_rate": 7.730818491519343e-06,
1512
+ "loss": 1.4521,
1513
+ "step": 232
1514
+ },
1515
+ {
1516
+ "epoch": 3.44,
1517
+ "learning_rate": 7.261036054158965e-06,
1518
+ "loss": 1.3687,
1519
+ "step": 233
1520
+ },
1521
+ {
1522
+ "epoch": 3.45,
1523
+ "learning_rate": 6.805440566056553e-06,
1524
+ "loss": 1.3911,
1525
+ "step": 234
1526
+ },
1527
+ {
1528
+ "epoch": 3.47,
1529
+ "learning_rate": 6.364101722945082e-06,
1530
+ "loss": 1.3972,
1531
+ "step": 235
1532
+ },
1533
+ {
1534
+ "epoch": 3.48,
1535
+ "learning_rate": 5.937087039615619e-06,
1536
+ "loss": 1.3924,
1537
+ "step": 236
1538
+ },
1539
+ {
1540
+ "epoch": 3.5,
1541
+ "learning_rate": 5.524461839589013e-06,
1542
+ "loss": 1.3982,
1543
+ "step": 237
1544
+ },
1545
+ {
1546
+ "epoch": 3.51,
1547
+ "learning_rate": 5.126289245122906e-06,
1548
+ "loss": 1.3554,
1549
+ "step": 238
1550
+ },
1551
+ {
1552
+ "epoch": 3.51,
1553
+ "eval_loss": 1.9183728694915771,
1554
+ "eval_runtime": 16.6428,
1555
+ "eval_samples_per_second": 2.704,
1556
+ "eval_steps_per_second": 1.382,
1557
+ "step": 238
1558
+ },
1559
+ {
1560
+ "epoch": 3.53,
1561
+ "learning_rate": 4.742630167555428e-06,
1562
+ "loss": 1.3683,
1563
+ "step": 239
1564
+ },
1565
+ {
1566
+ "epoch": 3.54,
1567
+ "learning_rate": 4.37354329798726e-06,
1568
+ "loss": 1.3383,
1569
+ "step": 240
1570
+ },
1571
+ {
1572
+ "epoch": 3.56,
1573
+ "learning_rate": 4.019085098303077e-06,
1574
+ "loss": 1.4202,
1575
+ "step": 241
1576
+ },
1577
+ {
1578
+ "epoch": 3.57,
1579
+ "learning_rate": 3.679309792534291e-06,
1580
+ "loss": 1.3848,
1581
+ "step": 242
1582
+ },
1583
+ {
1584
+ "epoch": 3.59,
1585
+ "learning_rate": 3.3542693585639662e-06,
1586
+ "loss": 1.4633,
1587
+ "step": 243
1588
+ },
1589
+ {
1590
+ "epoch": 3.6,
1591
+ "learning_rate": 3.0440135201753374e-06,
1592
+ "loss": 1.4707,
1593
+ "step": 244
1594
+ },
1595
+ {
1596
+ "epoch": 3.62,
1597
+ "learning_rate": 2.7485897394453064e-06,
1598
+ "loss": 1.4323,
1599
+ "step": 245
1600
+ },
1601
+ {
1602
+ "epoch": 3.63,
1603
+ "learning_rate": 2.468043209483739e-06,
1604
+ "loss": 1.4162,
1605
+ "step": 246
1606
+ },
1607
+ {
1608
+ "epoch": 3.65,
1609
+ "learning_rate": 2.2024168475199614e-06,
1610
+ "loss": 1.3303,
1611
+ "step": 247
1612
+ },
1613
+ {
1614
+ "epoch": 3.66,
1615
+ "learning_rate": 1.951751288337467e-06,
1616
+ "loss": 1.4434,
1617
+ "step": 248
1618
+ },
1619
+ {
1620
+ "epoch": 3.68,
1621
+ "learning_rate": 1.7160848780576334e-06,
1622
+ "loss": 1.4763,
1623
+ "step": 249
1624
+ },
1625
+ {
1626
+ "epoch": 3.69,
1627
+ "learning_rate": 1.4954536682736719e-06,
1628
+ "loss": 1.4284,
1629
+ "step": 250
1630
+ },
1631
+ {
1632
+ "epoch": 3.71,
1633
+ "learning_rate": 1.289891410535593e-06,
1634
+ "loss": 1.5079,
1635
+ "step": 251
1636
+ },
1637
+ {
1638
+ "epoch": 3.72,
1639
+ "learning_rate": 1.0994295511869257e-06,
1640
+ "loss": 1.4137,
1641
+ "step": 252
1642
+ },
1643
+ {
1644
+ "epoch": 3.74,
1645
+ "learning_rate": 9.240972265541991e-07,
1646
+ "loss": 1.3556,
1647
+ "step": 253
1648
+ },
1649
+ {
1650
+ "epoch": 3.75,
1651
+ "learning_rate": 7.639212584897082e-07,
1652
+ "loss": 1.4151,
1653
+ "step": 254
1654
+ },
1655
+ {
1656
+ "epoch": 3.77,
1657
+ "learning_rate": 6.189261502683619e-07,
1658
+ "loss": 1.3287,
1659
+ "step": 255
1660
+ },
1661
+ {
1662
+ "epoch": 3.77,
1663
+ "eval_loss": 1.9195834398269653,
1664
+ "eval_runtime": 16.6389,
1665
+ "eval_samples_per_second": 2.705,
1666
+ "eval_steps_per_second": 1.382,
1667
+ "step": 255
1668
+ },
1669
+ {
1670
+ "epoch": 3.78,
1671
+ "learning_rate": 4.891340828393487e-07,
1672
+ "loss": 1.3766,
1673
+ "step": 256
1674
+ },
1675
+ {
1676
+ "epoch": 3.8,
1677
+ "learning_rate": 3.745649114328065e-07,
1678
+ "loss": 1.3085,
1679
+ "step": 257
1680
+ },
1681
+ {
1682
+ "epoch": 3.81,
1683
+ "learning_rate": 2.752361625225297e-07,
1684
+ "loss": 1.4159,
1685
+ "step": 258
1686
+ },
1687
+ {
1688
+ "epoch": 3.83,
1689
+ "learning_rate": 1.9116303114480315e-07,
1690
+ "loss": 1.3997,
1691
+ "step": 259
1692
+ },
1693
+ {
1694
+ "epoch": 3.84,
1695
+ "learning_rate": 1.2235837857387246e-07,
1696
+ "loss": 1.4732,
1697
+ "step": 260
1698
+ },
1699
+ {
1700
+ "epoch": 3.86,
1701
+ "learning_rate": 6.883273035447335e-08,
1702
+ "loss": 1.3565,
1703
+ "step": 261
1704
+ },
1705
+ {
1706
+ "epoch": 3.87,
1707
+ "learning_rate": 3.059427469168652e-08,
1708
+ "loss": 1.3847,
1709
+ "step": 262
1710
+ },
1711
+ {
1712
+ "epoch": 3.89,
1713
+ "learning_rate": 7.648861198306101e-09,
1714
+ "loss": 1.383,
1715
+ "step": 263
1716
+ },
1717
+ {
1718
+ "epoch": 3.9,
1719
+ "learning_rate": 0.0,
1720
+ "loss": 1.451,
1721
+ "step": 264
1722
+ }
1723
+ ],
1724
+ "logging_steps": 1,
1725
+ "max_steps": 264,
1726
+ "num_input_tokens_seen": 0,
1727
+ "num_train_epochs": 4,
1728
+ "save_steps": 66,
1729
+ "total_flos": 3.469365681806377e+17,
1730
+ "train_batch_size": 2,
1731
+ "trial_name": null,
1732
+ "trial_params": null
1733
+ }
checkpoint-264/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136f5d9dd7fc2fabff6e80dd48a495a4cd5f0ab1af46964ed1af4cae2dae0a30
3
+ size 5368
checkpoint-66/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-66/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-66/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293bc1bb75662c53df4e8eaa15a15400cb41bca80e5ca6028bf8ee42fd99748c
3
+ size 319876032
checkpoint-66/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b292502e6f520123ac2cd6906e20417a4eb68548a3b79dd1c995828ef65992c
3
+ size 160736084
checkpoint-66/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7dfa3a8d99d16570b86a87a9ffb0ff303326ff3e5c03953a2bda24ff05b5093
3
+ size 14244
checkpoint-66/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a08818356f220fd441067cc050505206bfaa7b03066efdd4ac677099eabbfe5a
3
+ size 1064
checkpoint-66/trainer_state.json ADDED
@@ -0,0 +1,449 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9924812030075187,
5
+ "eval_steps": 17,
6
+ "global_step": 66,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.8373,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "eval_loss": 1.8333783149719238,
20
+ "eval_runtime": 16.5756,
21
+ "eval_samples_per_second": 2.715,
22
+ "eval_steps_per_second": 1.388,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.8119,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.05,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.8301,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.06,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.7976,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.08,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.853,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.09,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.7586,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.11,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8416,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.12,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.7755,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.14,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.804,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.15,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.7858,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.17,
81
+ "learning_rate": 0.0001999923511388017,
82
+ "loss": 1.7311,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.18,
87
+ "learning_rate": 0.0001999694057253083,
88
+ "loss": 1.7012,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.2,
93
+ "learning_rate": 0.00019993116726964554,
94
+ "loss": 1.742,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.21,
99
+ "learning_rate": 0.00019987764162142613,
100
+ "loss": 1.7209,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.23,
105
+ "learning_rate": 0.0001998088369688552,
106
+ "loss": 1.7578,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.24,
111
+ "learning_rate": 0.00019972476383747748,
112
+ "loss": 1.6906,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.26,
117
+ "learning_rate": 0.0001996254350885672,
118
+ "loss": 1.738,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.26,
123
+ "eval_loss": 1.754616141319275,
124
+ "eval_runtime": 16.6372,
125
+ "eval_samples_per_second": 2.705,
126
+ "eval_steps_per_second": 1.382,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 0.27,
131
+ "learning_rate": 0.0001995108659171607,
132
+ "loss": 1.7976,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 0.29,
137
+ "learning_rate": 0.00019938107384973166,
138
+ "loss": 1.7781,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 0.3,
143
+ "learning_rate": 0.00019923607874151032,
144
+ "loss": 1.7737,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 0.32,
149
+ "learning_rate": 0.00019907590277344582,
150
+ "loss": 1.6662,
151
+ "step": 21
152
+ },
153
+ {
154
+ "epoch": 0.33,
155
+ "learning_rate": 0.00019890057044881306,
156
+ "loss": 1.7869,
157
+ "step": 22
158
+ },
159
+ {
160
+ "epoch": 0.35,
161
+ "learning_rate": 0.0001987101085894644,
162
+ "loss": 1.6646,
163
+ "step": 23
164
+ },
165
+ {
166
+ "epoch": 0.36,
167
+ "learning_rate": 0.00019850454633172631,
168
+ "loss": 1.7482,
169
+ "step": 24
170
+ },
171
+ {
172
+ "epoch": 0.38,
173
+ "learning_rate": 0.0001982839151219424,
174
+ "loss": 1.7112,
175
+ "step": 25
176
+ },
177
+ {
178
+ "epoch": 0.39,
179
+ "learning_rate": 0.00019804824871166255,
180
+ "loss": 1.7083,
181
+ "step": 26
182
+ },
183
+ {
184
+ "epoch": 0.41,
185
+ "learning_rate": 0.00019779758315248004,
186
+ "loss": 1.728,
187
+ "step": 27
188
+ },
189
+ {
190
+ "epoch": 0.42,
191
+ "learning_rate": 0.00019753195679051628,
192
+ "loss": 1.7292,
193
+ "step": 28
194
+ },
195
+ {
196
+ "epoch": 0.44,
197
+ "learning_rate": 0.0001972514102605547,
198
+ "loss": 1.6902,
199
+ "step": 29
200
+ },
201
+ {
202
+ "epoch": 0.45,
203
+ "learning_rate": 0.00019695598647982468,
204
+ "loss": 1.7432,
205
+ "step": 30
206
+ },
207
+ {
208
+ "epoch": 0.47,
209
+ "learning_rate": 0.00019664573064143604,
210
+ "loss": 1.7258,
211
+ "step": 31
212
+ },
213
+ {
214
+ "epoch": 0.48,
215
+ "learning_rate": 0.00019632069020746572,
216
+ "loss": 1.7363,
217
+ "step": 32
218
+ },
219
+ {
220
+ "epoch": 0.5,
221
+ "learning_rate": 0.00019598091490169694,
222
+ "loss": 1.7142,
223
+ "step": 33
224
+ },
225
+ {
226
+ "epoch": 0.51,
227
+ "learning_rate": 0.00019562645670201276,
228
+ "loss": 1.704,
229
+ "step": 34
230
+ },
231
+ {
232
+ "epoch": 0.51,
233
+ "eval_loss": 1.7388739585876465,
234
+ "eval_runtime": 16.5955,
235
+ "eval_samples_per_second": 2.712,
236
+ "eval_steps_per_second": 1.386,
237
+ "step": 34
238
+ },
239
+ {
240
+ "epoch": 0.53,
241
+ "learning_rate": 0.0001952573698324446,
242
+ "loss": 1.7393,
243
+ "step": 35
244
+ },
245
+ {
246
+ "epoch": 0.54,
247
+ "learning_rate": 0.00019487371075487713,
248
+ "loss": 1.7568,
249
+ "step": 36
250
+ },
251
+ {
252
+ "epoch": 0.56,
253
+ "learning_rate": 0.000194475538160411,
254
+ "loss": 1.7445,
255
+ "step": 37
256
+ },
257
+ {
258
+ "epoch": 0.57,
259
+ "learning_rate": 0.0001940629129603844,
260
+ "loss": 1.6595,
261
+ "step": 38
262
+ },
263
+ {
264
+ "epoch": 0.59,
265
+ "learning_rate": 0.00019363589827705492,
266
+ "loss": 1.7288,
267
+ "step": 39
268
+ },
269
+ {
270
+ "epoch": 0.6,
271
+ "learning_rate": 0.00019319455943394347,
272
+ "loss": 1.6342,
273
+ "step": 40
274
+ },
275
+ {
276
+ "epoch": 0.62,
277
+ "learning_rate": 0.00019273896394584103,
278
+ "loss": 1.7066,
279
+ "step": 41
280
+ },
281
+ {
282
+ "epoch": 0.63,
283
+ "learning_rate": 0.00019226918150848068,
284
+ "loss": 1.6558,
285
+ "step": 42
286
+ },
287
+ {
288
+ "epoch": 0.65,
289
+ "learning_rate": 0.00019178528398787551,
290
+ "loss": 1.6756,
291
+ "step": 43
292
+ },
293
+ {
294
+ "epoch": 0.66,
295
+ "learning_rate": 0.00019128734540932495,
296
+ "loss": 1.7146,
297
+ "step": 44
298
+ },
299
+ {
300
+ "epoch": 0.68,
301
+ "learning_rate": 0.00019077544194609042,
302
+ "loss": 1.7043,
303
+ "step": 45
304
+ },
305
+ {
306
+ "epoch": 0.69,
307
+ "learning_rate": 0.00019024965190774263,
308
+ "loss": 1.6396,
309
+ "step": 46
310
+ },
311
+ {
312
+ "epoch": 0.71,
313
+ "learning_rate": 0.00018971005572818213,
314
+ "loss": 1.648,
315
+ "step": 47
316
+ },
317
+ {
318
+ "epoch": 0.72,
319
+ "learning_rate": 0.00018915673595333444,
320
+ "loss": 1.5988,
321
+ "step": 48
322
+ },
323
+ {
324
+ "epoch": 0.74,
325
+ "learning_rate": 0.00018858977722852275,
326
+ "loss": 1.7394,
327
+ "step": 49
328
+ },
329
+ {
330
+ "epoch": 0.75,
331
+ "learning_rate": 0.00018800926628551886,
332
+ "loss": 1.6362,
333
+ "step": 50
334
+ },
335
+ {
336
+ "epoch": 0.77,
337
+ "learning_rate": 0.00018741529192927526,
338
+ "loss": 1.6762,
339
+ "step": 51
340
+ },
341
+ {
342
+ "epoch": 0.77,
343
+ "eval_loss": 1.7409569025039673,
344
+ "eval_runtime": 16.7147,
345
+ "eval_samples_per_second": 2.692,
346
+ "eval_steps_per_second": 1.376,
347
+ "step": 51
348
+ },
349
+ {
350
+ "epoch": 0.78,
351
+ "learning_rate": 0.00018680794502434018,
352
+ "loss": 1.6534,
353
+ "step": 52
354
+ },
355
+ {
356
+ "epoch": 0.8,
357
+ "learning_rate": 0.00018618731848095706,
358
+ "loss": 1.6551,
359
+ "step": 53
360
+ },
361
+ {
362
+ "epoch": 0.81,
363
+ "learning_rate": 0.00018555350724085162,
364
+ "loss": 1.6297,
365
+ "step": 54
366
+ },
367
+ {
368
+ "epoch": 0.83,
369
+ "learning_rate": 0.0001849066082627079,
370
+ "loss": 1.7152,
371
+ "step": 55
372
+ },
373
+ {
374
+ "epoch": 0.84,
375
+ "learning_rate": 0.00018424672050733576,
376
+ "loss": 1.7062,
377
+ "step": 56
378
+ },
379
+ {
380
+ "epoch": 0.86,
381
+ "learning_rate": 0.00018357394492253215,
382
+ "loss": 1.5742,
383
+ "step": 57
384
+ },
385
+ {
386
+ "epoch": 0.87,
387
+ "learning_rate": 0.00018288838442763838,
388
+ "loss": 1.6424,
389
+ "step": 58
390
+ },
391
+ {
392
+ "epoch": 0.89,
393
+ "learning_rate": 0.00018219014389779585,
394
+ "loss": 1.6544,
395
+ "step": 59
396
+ },
397
+ {
398
+ "epoch": 0.9,
399
+ "learning_rate": 0.00018147933014790244,
400
+ "loss": 1.6179,
401
+ "step": 60
402
+ },
403
+ {
404
+ "epoch": 0.92,
405
+ "learning_rate": 0.0001807560519162724,
406
+ "loss": 1.6823,
407
+ "step": 61
408
+ },
409
+ {
410
+ "epoch": 0.93,
411
+ "learning_rate": 0.00018002041984800174,
412
+ "loss": 1.5845,
413
+ "step": 62
414
+ },
415
+ {
416
+ "epoch": 0.95,
417
+ "learning_rate": 0.00017927254647804209,
418
+ "loss": 1.6177,
419
+ "step": 63
420
+ },
421
+ {
422
+ "epoch": 0.96,
423
+ "learning_rate": 0.0001785125462139855,
424
+ "loss": 1.6196,
425
+ "step": 64
426
+ },
427
+ {
428
+ "epoch": 0.98,
429
+ "learning_rate": 0.00017774053531856258,
430
+ "loss": 1.6526,
431
+ "step": 65
432
+ },
433
+ {
434
+ "epoch": 0.99,
435
+ "learning_rate": 0.000176956631891857,
436
+ "loss": 1.5792,
437
+ "step": 66
438
+ }
439
+ ],
440
+ "logging_steps": 1,
441
+ "max_steps": 264,
442
+ "num_input_tokens_seen": 0,
443
+ "num_train_epochs": 4,
444
+ "save_steps": 66,
445
+ "total_flos": 8.67752288012206e+16,
446
+ "train_batch_size": 2,
447
+ "trial_name": null,
448
+ "trial_params": null
449
+ }
checkpoint-66/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136f5d9dd7fc2fabff6e80dd48a495a4cd5f0ab1af46964ed1af4cae2dae0a30
3
+ size 5368
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NousResearch/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": false,
23
+ "_load_in_8bit": true,
24
+ "bnb_4bit_compute_dtype": "float32",
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": 10000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.38.0.dev0",
41
+ "use_cache": false,
42
+ "vocab_size": 32000
43
+ }
runs/Feb20_06-57-12_16b73cf3ac9a/events.out.tfevents.1708412232.16b73cf3ac9a.583.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4999b8c64b318a7cba734dadce56cb844d8313310d511aad36d2240ced08e6e7
3
+ size 51301
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<unk>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "trust_remote_code": false,
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false,
42
+ "use_fast": true
43
+ }