MilaWang commited on
Commit
50c8637
·
verified ·
1 Parent(s): 21670e5

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/README.md +202 -0
  2. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/adapter_config.json +29 -0
  3. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/adapter_model.safetensors +3 -0
  4. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/README.md +202 -0
  5. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/adapter_config.json +29 -0
  6. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/adapter_model.safetensors +3 -0
  7. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/optimizer.pt +3 -0
  8. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/rng_state.pth +3 -0
  9. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/scheduler.pt +3 -0
  10. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/special_tokens_map.json +24 -0
  11. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/tokenizer.json +0 -0
  12. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/tokenizer.model +3 -0
  13. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/tokenizer_config.json +0 -0
  14. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/trainer_state.json +1023 -0
  15. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/training_args.bin +3 -0
  16. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/README.md +202 -0
  17. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/adapter_config.json +29 -0
  18. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/adapter_model.safetensors +3 -0
  19. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/optimizer.pt +3 -0
  20. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/rng_state.pth +3 -0
  21. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/scheduler.pt +3 -0
  22. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/special_tokens_map.json +24 -0
  23. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/tokenizer.json +0 -0
  24. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/tokenizer.model +3 -0
  25. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/tokenizer_config.json +0 -0
  26. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/trainer_state.json +1353 -0
  27. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/training_args.bin +3 -0
  28. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/README.md +202 -0
  29. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/adapter_config.json +29 -0
  30. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/adapter_model.safetensors +3 -0
  31. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/optimizer.pt +3 -0
  32. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/rng_state.pth +3 -0
  33. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/scheduler.pt +3 -0
  34. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/special_tokens_map.json +24 -0
  35. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/tokenizer.json +0 -0
  36. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/tokenizer.model +3 -0
  37. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/tokenizer_config.json +0 -0
  38. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/trainer_state.json +1690 -0
  39. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/training_args.bin +3 -0
  40. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/README.md +202 -0
  41. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/adapter_config.json +29 -0
  42. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/adapter_model.safetensors +3 -0
  43. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/optimizer.pt +3 -0
  44. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/rng_state.pth +3 -0
  45. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/scheduler.pt +3 -0
  46. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/special_tokens_map.json +24 -0
  47. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/tokenizer.json +0 -0
  48. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/tokenizer.model +3 -0
  49. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/tokenizer_config.json +0 -0
  50. Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/trainer_state.json +2020 -0
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ef31f28a2864f9fd912d8347cc8ec69e66e1e28eca8b94c118f3681fdabf4a
3
+ size 109069176
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5885009d3afa60a99e03636cf99f23bab6c6c58ec194086469b27e4c52199fb4
3
+ size 109069176
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127f67d4db533203fb2fb44b827bf2235acf6444d7af9fd4d5d1a15c64674388
3
+ size 55532666
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3e79f7bd64822d835e92384e077f0fb05113f7887dae147256d3de6f245d5e
3
+ size 14244
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:237814caa6cb88953c1896aef7b5d4120ff5268c8f006284225db712de184866
3
+ size 1064
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/trainer_state.json ADDED
@@ -0,0 +1,1023 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.7847579717636108,
3
+ "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-462",
4
+ "epoch": 3.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1386,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021645021645021644,
13
+ "grad_norm": 1.200374722480774,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.5092,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04329004329004329,
20
+ "grad_norm": 0.974091112613678,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2672,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06493506493506493,
27
+ "grad_norm": 0.9070103168487549,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.1445,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08658008658008658,
34
+ "grad_norm": 0.6892510056495667,
35
+ "learning_rate": 0.0002,
36
+ "loss": 2.0634,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10822510822510822,
41
+ "grad_norm": 0.7840355038642883,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.039,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12987012987012986,
48
+ "grad_norm": 0.8381665349006653,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9527,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15151515151515152,
55
+ "grad_norm": 0.6969044804573059,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.8852,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17316017316017315,
62
+ "grad_norm": 0.6608849763870239,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8263,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19480519480519481,
69
+ "grad_norm": 0.6329185962677002,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.825,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21645021645021645,
76
+ "grad_norm": 0.723852276802063,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8256,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.23809523809523808,
83
+ "grad_norm": 0.8358765840530396,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8758,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2597402597402597,
90
+ "grad_norm": 0.6025514006614685,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8468,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2813852813852814,
97
+ "grad_norm": 0.5782386064529419,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.7487,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30303030303030304,
104
+ "grad_norm": 0.8589595556259155,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.7717,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3246753246753247,
111
+ "grad_norm": 0.5718036890029907,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.7726,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3463203463203463,
118
+ "grad_norm": 0.632756769657135,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.784,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.36796536796536794,
125
+ "grad_norm": 0.5307920575141907,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8176,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.38961038961038963,
132
+ "grad_norm": 0.5692276358604431,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7744,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41125541125541126,
139
+ "grad_norm": 0.6083813309669495,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8075,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4329004329004329,
146
+ "grad_norm": 0.7849981188774109,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8718,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.45454545454545453,
153
+ "grad_norm": 0.6536546945571899,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.7946,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.47619047619047616,
160
+ "grad_norm": 0.5180730223655701,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8174,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.49783549783549785,
167
+ "grad_norm": 0.5796821713447571,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.7857,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5194805194805194,
174
+ "grad_norm": 0.6185894012451172,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8062,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5411255411255411,
181
+ "grad_norm": 0.6040953397750854,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.825,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5627705627705628,
188
+ "grad_norm": 0.6005431413650513,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.7785,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5844155844155844,
195
+ "grad_norm": 0.6693951487541199,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8444,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6060606060606061,
202
+ "grad_norm": 0.5105443596839905,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8471,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6277056277056277,
209
+ "grad_norm": 0.5175243616104126,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8274,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6493506493506493,
216
+ "grad_norm": 0.4775221049785614,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.81,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.670995670995671,
223
+ "grad_norm": 0.9106342792510986,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7816,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6926406926406926,
230
+ "grad_norm": 1.9134571552276611,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.7764,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7142857142857143,
237
+ "grad_norm": 0.6287537217140198,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7877,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7359307359307359,
244
+ "grad_norm": 0.5587132573127747,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.8499,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7575757575757576,
251
+ "grad_norm": 0.5827193260192871,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.7328,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7792207792207793,
258
+ "grad_norm": 0.572600781917572,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8022,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8008658008658008,
265
+ "grad_norm": 0.6280586123466492,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.88,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8225108225108225,
272
+ "grad_norm": 0.6878819465637207,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8116,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8441558441558441,
279
+ "grad_norm": 0.5876027345657349,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8042,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8658008658008658,
286
+ "grad_norm": 0.5249695777893066,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7501,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.8874458874458875,
293
+ "grad_norm": 0.5510677695274353,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.7599,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9090909090909091,
300
+ "grad_norm": 0.6817089915275574,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7737,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9307359307359307,
307
+ "grad_norm": 0.5116859078407288,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.7857,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9523809523809523,
314
+ "grad_norm": 0.5427846312522888,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7361,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.974025974025974,
321
+ "grad_norm": 0.5605915784835815,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.7812,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9956709956709957,
328
+ "grad_norm": 0.5166691541671753,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7699,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0,
335
+ "eval_loss": 1.7847579717636108,
336
+ "eval_runtime": 144.877,
337
+ "eval_samples_per_second": 3.679,
338
+ "eval_steps_per_second": 0.462,
339
+ "step": 462
340
+ },
341
+ {
342
+ "epoch": 1.0173160173160174,
343
+ "grad_norm": 0.5665210485458374,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.6725,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0389610389610389,
350
+ "grad_norm": 1.0514339208602905,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.6996,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0606060606060606,
357
+ "grad_norm": 0.5494309663772583,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.6573,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0822510822510822,
364
+ "grad_norm": 0.557016909122467,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.7314,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.103896103896104,
371
+ "grad_norm": 0.6585943102836609,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.7284,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1255411255411256,
378
+ "grad_norm": 0.6703357696533203,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7575,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1471861471861473,
385
+ "grad_norm": 1.9358264207839966,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7013,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1688311688311688,
392
+ "grad_norm": 0.6128601431846619,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.6914,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1904761904761905,
399
+ "grad_norm": 0.6610239744186401,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.6358,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2121212121212122,
406
+ "grad_norm": 0.6083669662475586,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.7122,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2337662337662338,
413
+ "grad_norm": 0.7784225940704346,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.6771,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2554112554112553,
420
+ "grad_norm": 0.6141694784164429,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.6372,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.277056277056277,
427
+ "grad_norm": 0.6129311323165894,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.6795,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.2987012987012987,
434
+ "grad_norm": 0.6802751421928406,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.6664,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3203463203463204,
441
+ "grad_norm": 0.6065750122070312,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.6555,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.341991341991342,
448
+ "grad_norm": 0.6713075637817383,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.679,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3636363636363638,
455
+ "grad_norm": 0.627552330493927,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7412,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.3852813852813852,
462
+ "grad_norm": 0.6579778790473938,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.6477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.406926406926407,
469
+ "grad_norm": 0.6381745934486389,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7282,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4285714285714286,
476
+ "grad_norm": 0.7358919382095337,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7218,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4502164502164503,
483
+ "grad_norm": 0.6294736266136169,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7046,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4718614718614718,
490
+ "grad_norm": 0.6542870998382568,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7143,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.4935064935064934,
497
+ "grad_norm": 0.6003480553627014,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7417,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5151515151515151,
504
+ "grad_norm": 0.8322144150733948,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.6487,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5367965367965368,
511
+ "grad_norm": 0.6853126287460327,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7217,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5584415584415585,
518
+ "grad_norm": 0.6571378707885742,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6888,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.5800865800865802,
525
+ "grad_norm": 0.6957149505615234,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7111,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.601731601731602,
532
+ "grad_norm": 0.6495681405067444,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7361,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6233766233766234,
539
+ "grad_norm": 0.6954384446144104,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.5709,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.645021645021645,
546
+ "grad_norm": 0.7402207851409912,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.6851,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.6666666666666665,
553
+ "grad_norm": 0.6827481985092163,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.6651,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.6883116883116882,
560
+ "grad_norm": 0.6176769733428955,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.6827,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.70995670995671,
567
+ "grad_norm": 0.6565108299255371,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.6291,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.7316017316017316,
574
+ "grad_norm": 0.6303038001060486,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6805,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.7532467532467533,
581
+ "grad_norm": 0.6866182684898376,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7321,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.774891774891775,
588
+ "grad_norm": 0.7522535920143127,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.6847,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.7965367965367967,
595
+ "grad_norm": 0.7703698873519897,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.679,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8181818181818183,
602
+ "grad_norm": 0.5955503582954407,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.6817,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8398268398268398,
609
+ "grad_norm": 0.707340657711029,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7159,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8614718614718615,
616
+ "grad_norm": 0.7305465936660767,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.709,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.883116883116883,
623
+ "grad_norm": 0.667972207069397,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.71,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9047619047619047,
630
+ "grad_norm": 0.654872477054596,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7051,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9264069264069263,
637
+ "grad_norm": 0.6718705296516418,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.6316,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.948051948051948,
644
+ "grad_norm": 0.6363692879676819,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.623,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9696969696969697,
651
+ "grad_norm": 0.6861362457275391,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.6725,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.9913419913419914,
658
+ "grad_norm": 0.6531493067741394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.6833,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 2.0,
665
+ "eval_loss": 1.7908068895339966,
666
+ "eval_runtime": 144.0281,
667
+ "eval_samples_per_second": 3.701,
668
+ "eval_steps_per_second": 0.465,
669
+ "step": 924
670
+ },
671
+ {
672
+ "epoch": 2.012987012987013,
673
+ "grad_norm": 0.6030914187431335,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.5922,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.034632034632035,
680
+ "grad_norm": 0.7416430711746216,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.5215,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0562770562770565,
687
+ "grad_norm": 0.7020093202590942,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.5759,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.0779220779220777,
694
+ "grad_norm": 0.8007868528366089,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.4751,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.0995670995670994,
701
+ "grad_norm": 0.7111671566963196,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.4808,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.121212121212121,
708
+ "grad_norm": 0.7257682085037231,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.53,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.142857142857143,
715
+ "grad_norm": 0.8737282156944275,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.5097,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1645021645021645,
722
+ "grad_norm": 0.9281378984451294,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.537,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.186147186147186,
729
+ "grad_norm": 1.0217959880828857,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.5223,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.207792207792208,
736
+ "grad_norm": 0.8430958986282349,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.4253,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.2294372294372296,
743
+ "grad_norm": 0.8123440742492676,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.5294,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.2510822510822512,
750
+ "grad_norm": 0.9429558515548706,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.5167,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.2727272727272725,
757
+ "grad_norm": 0.811696469783783,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.4711,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.2943722943722946,
764
+ "grad_norm": 0.8424768447875977,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.4656,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.316017316017316,
771
+ "grad_norm": 0.8870340585708618,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.5618,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3376623376623376,
778
+ "grad_norm": 0.8600393533706665,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5368,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.3593073593073592,
785
+ "grad_norm": 0.8447834253311157,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.5028,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.380952380952381,
792
+ "grad_norm": 0.9303842186927795,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.4885,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.4025974025974026,
799
+ "grad_norm": 0.8144819140434265,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.5163,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4242424242424243,
806
+ "grad_norm": 0.92924964427948,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.4805,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.445887445887446,
813
+ "grad_norm": 0.8560649156570435,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.4608,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.4675324675324677,
820
+ "grad_norm": 0.8532574772834778,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.5541,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.4891774891774894,
827
+ "grad_norm": 0.8702793717384338,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.5607,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5108225108225106,
834
+ "grad_norm": 0.9125854969024658,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.5194,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5324675324675323,
841
+ "grad_norm": 0.9579735398292542,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.5953,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.554112554112554,
848
+ "grad_norm": 0.8561005592346191,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5088,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.5757575757575757,
855
+ "grad_norm": 0.9103630185127258,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.5636,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.5974025974025974,
862
+ "grad_norm": 0.8527248501777649,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.5497,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.619047619047619,
869
+ "grad_norm": 0.8368656039237976,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.5845,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6406926406926408,
876
+ "grad_norm": 0.9644360542297363,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.574,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.6623376623376624,
883
+ "grad_norm": 0.9691457748413086,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.5623,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.683982683982684,
890
+ "grad_norm": 0.8851862549781799,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.5894,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.7056277056277054,
897
+ "grad_norm": 1.0715088844299316,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5251,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7272727272727275,
904
+ "grad_norm": 0.8532006740570068,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.5903,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.7489177489177488,
911
+ "grad_norm": 0.9172760248184204,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5261,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.7705627705627704,
918
+ "grad_norm": 0.8991577625274658,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.5029,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.792207792207792,
925
+ "grad_norm": 0.8205381631851196,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.5207,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.813852813852814,
932
+ "grad_norm": 0.9733313918113708,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.5328,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8354978354978355,
939
+ "grad_norm": 1.0313537120819092,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.5373,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.857142857142857,
946
+ "grad_norm": 0.8865208625793457,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.4832,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.878787878787879,
953
+ "grad_norm": 1.1407958269119263,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5297,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.9004329004329006,
960
+ "grad_norm": 0.879891574382782,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.5435,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.9220779220779223,
967
+ "grad_norm": 0.9538708925247192,
968
+ "learning_rate": 0.0002,
969
+ "loss": 1.5523,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9437229437229435,
974
+ "grad_norm": 0.7732896208763123,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.4881,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.965367965367965,
981
+ "grad_norm": 0.9062705636024475,
982
+ "learning_rate": 0.0002,
983
+ "loss": 1.4959,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.987012987012987,
988
+ "grad_norm": 0.9082673192024231,
989
+ "learning_rate": 0.0002,
990
+ "loss": 1.5508,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 3.0,
995
+ "eval_loss": 1.842921257019043,
996
+ "eval_runtime": 138.5715,
997
+ "eval_samples_per_second": 3.846,
998
+ "eval_steps_per_second": 0.484,
999
+ "step": 1386
1000
+ }
1001
+ ],
1002
+ "logging_steps": 10,
1003
+ "max_steps": 3696,
1004
+ "num_input_tokens_seen": 0,
1005
+ "num_train_epochs": 8,
1006
+ "save_steps": 200,
1007
+ "stateful_callbacks": {
1008
+ "TrainerControl": {
1009
+ "args": {
1010
+ "should_epoch_stop": false,
1011
+ "should_evaluate": false,
1012
+ "should_log": false,
1013
+ "should_save": true,
1014
+ "should_training_stop": false
1015
+ },
1016
+ "attributes": {}
1017
+ }
1018
+ },
1019
+ "total_flos": 6.08103712161792e+16,
1020
+ "train_batch_size": 1,
1021
+ "trial_name": null,
1022
+ "trial_params": null
1023
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1386/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d349b8fe4d8871a8479d9bb3b1cba8d39e96d113c8c86cdb28a7fc6969f53ba6
3
+ size 5560
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5504f650277854d192b97753ca606c988a632c2cbcd62d444cab21f0ab82a141
3
+ size 109069176
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c0ccaca6638a1a73230fc361bc5359206353e084c132ed1e15188820c42965
3
+ size 55532666
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c9519a423472b0e09caffb8a1a47938b6b04cd535a5ec771672c03e6a23ebc
3
+ size 14244
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30fcae4a89d4c234120b0406d6521923488e077e6c4aa142e4c91c84ecd612c3
3
+ size 1064
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/trainer_state.json ADDED
@@ -0,0 +1,1353 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.7847579717636108,
3
+ "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-462",
4
+ "epoch": 4.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1848,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021645021645021644,
13
+ "grad_norm": 1.200374722480774,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.5092,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04329004329004329,
20
+ "grad_norm": 0.974091112613678,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2672,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06493506493506493,
27
+ "grad_norm": 0.9070103168487549,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.1445,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08658008658008658,
34
+ "grad_norm": 0.6892510056495667,
35
+ "learning_rate": 0.0002,
36
+ "loss": 2.0634,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10822510822510822,
41
+ "grad_norm": 0.7840355038642883,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.039,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12987012987012986,
48
+ "grad_norm": 0.8381665349006653,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9527,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15151515151515152,
55
+ "grad_norm": 0.6969044804573059,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.8852,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17316017316017315,
62
+ "grad_norm": 0.6608849763870239,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8263,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19480519480519481,
69
+ "grad_norm": 0.6329185962677002,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.825,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21645021645021645,
76
+ "grad_norm": 0.723852276802063,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8256,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.23809523809523808,
83
+ "grad_norm": 0.8358765840530396,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8758,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2597402597402597,
90
+ "grad_norm": 0.6025514006614685,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8468,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2813852813852814,
97
+ "grad_norm": 0.5782386064529419,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.7487,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30303030303030304,
104
+ "grad_norm": 0.8589595556259155,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.7717,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3246753246753247,
111
+ "grad_norm": 0.5718036890029907,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.7726,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3463203463203463,
118
+ "grad_norm": 0.632756769657135,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.784,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.36796536796536794,
125
+ "grad_norm": 0.5307920575141907,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8176,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.38961038961038963,
132
+ "grad_norm": 0.5692276358604431,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7744,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41125541125541126,
139
+ "grad_norm": 0.6083813309669495,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8075,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4329004329004329,
146
+ "grad_norm": 0.7849981188774109,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8718,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.45454545454545453,
153
+ "grad_norm": 0.6536546945571899,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.7946,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.47619047619047616,
160
+ "grad_norm": 0.5180730223655701,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8174,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.49783549783549785,
167
+ "grad_norm": 0.5796821713447571,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.7857,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5194805194805194,
174
+ "grad_norm": 0.6185894012451172,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8062,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5411255411255411,
181
+ "grad_norm": 0.6040953397750854,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.825,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5627705627705628,
188
+ "grad_norm": 0.6005431413650513,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.7785,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5844155844155844,
195
+ "grad_norm": 0.6693951487541199,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8444,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6060606060606061,
202
+ "grad_norm": 0.5105443596839905,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8471,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6277056277056277,
209
+ "grad_norm": 0.5175243616104126,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8274,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6493506493506493,
216
+ "grad_norm": 0.4775221049785614,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.81,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.670995670995671,
223
+ "grad_norm": 0.9106342792510986,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7816,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6926406926406926,
230
+ "grad_norm": 1.9134571552276611,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.7764,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7142857142857143,
237
+ "grad_norm": 0.6287537217140198,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7877,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7359307359307359,
244
+ "grad_norm": 0.5587132573127747,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.8499,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7575757575757576,
251
+ "grad_norm": 0.5827193260192871,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.7328,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7792207792207793,
258
+ "grad_norm": 0.572600781917572,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8022,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8008658008658008,
265
+ "grad_norm": 0.6280586123466492,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.88,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8225108225108225,
272
+ "grad_norm": 0.6878819465637207,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8116,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8441558441558441,
279
+ "grad_norm": 0.5876027345657349,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8042,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8658008658008658,
286
+ "grad_norm": 0.5249695777893066,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7501,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.8874458874458875,
293
+ "grad_norm": 0.5510677695274353,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.7599,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9090909090909091,
300
+ "grad_norm": 0.6817089915275574,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7737,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9307359307359307,
307
+ "grad_norm": 0.5116859078407288,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.7857,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9523809523809523,
314
+ "grad_norm": 0.5427846312522888,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7361,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.974025974025974,
321
+ "grad_norm": 0.5605915784835815,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.7812,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9956709956709957,
328
+ "grad_norm": 0.5166691541671753,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7699,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0,
335
+ "eval_loss": 1.7847579717636108,
336
+ "eval_runtime": 144.877,
337
+ "eval_samples_per_second": 3.679,
338
+ "eval_steps_per_second": 0.462,
339
+ "step": 462
340
+ },
341
+ {
342
+ "epoch": 1.0173160173160174,
343
+ "grad_norm": 0.5665210485458374,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.6725,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0389610389610389,
350
+ "grad_norm": 1.0514339208602905,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.6996,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0606060606060606,
357
+ "grad_norm": 0.5494309663772583,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.6573,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0822510822510822,
364
+ "grad_norm": 0.557016909122467,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.7314,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.103896103896104,
371
+ "grad_norm": 0.6585943102836609,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.7284,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1255411255411256,
378
+ "grad_norm": 0.6703357696533203,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7575,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1471861471861473,
385
+ "grad_norm": 1.9358264207839966,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7013,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1688311688311688,
392
+ "grad_norm": 0.6128601431846619,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.6914,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1904761904761905,
399
+ "grad_norm": 0.6610239744186401,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.6358,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2121212121212122,
406
+ "grad_norm": 0.6083669662475586,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.7122,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2337662337662338,
413
+ "grad_norm": 0.7784225940704346,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.6771,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2554112554112553,
420
+ "grad_norm": 0.6141694784164429,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.6372,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.277056277056277,
427
+ "grad_norm": 0.6129311323165894,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.6795,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.2987012987012987,
434
+ "grad_norm": 0.6802751421928406,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.6664,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3203463203463204,
441
+ "grad_norm": 0.6065750122070312,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.6555,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.341991341991342,
448
+ "grad_norm": 0.6713075637817383,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.679,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3636363636363638,
455
+ "grad_norm": 0.627552330493927,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7412,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.3852813852813852,
462
+ "grad_norm": 0.6579778790473938,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.6477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.406926406926407,
469
+ "grad_norm": 0.6381745934486389,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7282,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4285714285714286,
476
+ "grad_norm": 0.7358919382095337,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7218,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4502164502164503,
483
+ "grad_norm": 0.6294736266136169,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7046,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4718614718614718,
490
+ "grad_norm": 0.6542870998382568,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7143,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.4935064935064934,
497
+ "grad_norm": 0.6003480553627014,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7417,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5151515151515151,
504
+ "grad_norm": 0.8322144150733948,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.6487,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5367965367965368,
511
+ "grad_norm": 0.6853126287460327,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7217,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5584415584415585,
518
+ "grad_norm": 0.6571378707885742,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6888,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.5800865800865802,
525
+ "grad_norm": 0.6957149505615234,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7111,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.601731601731602,
532
+ "grad_norm": 0.6495681405067444,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7361,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6233766233766234,
539
+ "grad_norm": 0.6954384446144104,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.5709,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.645021645021645,
546
+ "grad_norm": 0.7402207851409912,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.6851,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.6666666666666665,
553
+ "grad_norm": 0.6827481985092163,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.6651,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.6883116883116882,
560
+ "grad_norm": 0.6176769733428955,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.6827,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.70995670995671,
567
+ "grad_norm": 0.6565108299255371,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.6291,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.7316017316017316,
574
+ "grad_norm": 0.6303038001060486,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6805,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.7532467532467533,
581
+ "grad_norm": 0.6866182684898376,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7321,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.774891774891775,
588
+ "grad_norm": 0.7522535920143127,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.6847,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.7965367965367967,
595
+ "grad_norm": 0.7703698873519897,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.679,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8181818181818183,
602
+ "grad_norm": 0.5955503582954407,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.6817,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8398268398268398,
609
+ "grad_norm": 0.707340657711029,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7159,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8614718614718615,
616
+ "grad_norm": 0.7305465936660767,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.709,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.883116883116883,
623
+ "grad_norm": 0.667972207069397,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.71,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9047619047619047,
630
+ "grad_norm": 0.654872477054596,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7051,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9264069264069263,
637
+ "grad_norm": 0.6718705296516418,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.6316,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.948051948051948,
644
+ "grad_norm": 0.6363692879676819,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.623,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9696969696969697,
651
+ "grad_norm": 0.6861362457275391,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.6725,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.9913419913419914,
658
+ "grad_norm": 0.6531493067741394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.6833,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 2.0,
665
+ "eval_loss": 1.7908068895339966,
666
+ "eval_runtime": 144.0281,
667
+ "eval_samples_per_second": 3.701,
668
+ "eval_steps_per_second": 0.465,
669
+ "step": 924
670
+ },
671
+ {
672
+ "epoch": 2.012987012987013,
673
+ "grad_norm": 0.6030914187431335,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.5922,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.034632034632035,
680
+ "grad_norm": 0.7416430711746216,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.5215,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0562770562770565,
687
+ "grad_norm": 0.7020093202590942,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.5759,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.0779220779220777,
694
+ "grad_norm": 0.8007868528366089,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.4751,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.0995670995670994,
701
+ "grad_norm": 0.7111671566963196,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.4808,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.121212121212121,
708
+ "grad_norm": 0.7257682085037231,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.53,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.142857142857143,
715
+ "grad_norm": 0.8737282156944275,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.5097,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1645021645021645,
722
+ "grad_norm": 0.9281378984451294,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.537,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.186147186147186,
729
+ "grad_norm": 1.0217959880828857,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.5223,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.207792207792208,
736
+ "grad_norm": 0.8430958986282349,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.4253,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.2294372294372296,
743
+ "grad_norm": 0.8123440742492676,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.5294,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.2510822510822512,
750
+ "grad_norm": 0.9429558515548706,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.5167,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.2727272727272725,
757
+ "grad_norm": 0.811696469783783,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.4711,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.2943722943722946,
764
+ "grad_norm": 0.8424768447875977,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.4656,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.316017316017316,
771
+ "grad_norm": 0.8870340585708618,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.5618,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3376623376623376,
778
+ "grad_norm": 0.8600393533706665,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5368,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.3593073593073592,
785
+ "grad_norm": 0.8447834253311157,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.5028,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.380952380952381,
792
+ "grad_norm": 0.9303842186927795,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.4885,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.4025974025974026,
799
+ "grad_norm": 0.8144819140434265,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.5163,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4242424242424243,
806
+ "grad_norm": 0.92924964427948,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.4805,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.445887445887446,
813
+ "grad_norm": 0.8560649156570435,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.4608,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.4675324675324677,
820
+ "grad_norm": 0.8532574772834778,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.5541,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.4891774891774894,
827
+ "grad_norm": 0.8702793717384338,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.5607,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5108225108225106,
834
+ "grad_norm": 0.9125854969024658,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.5194,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5324675324675323,
841
+ "grad_norm": 0.9579735398292542,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.5953,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.554112554112554,
848
+ "grad_norm": 0.8561005592346191,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5088,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.5757575757575757,
855
+ "grad_norm": 0.9103630185127258,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.5636,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.5974025974025974,
862
+ "grad_norm": 0.8527248501777649,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.5497,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.619047619047619,
869
+ "grad_norm": 0.8368656039237976,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.5845,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6406926406926408,
876
+ "grad_norm": 0.9644360542297363,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.574,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.6623376623376624,
883
+ "grad_norm": 0.9691457748413086,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.5623,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.683982683982684,
890
+ "grad_norm": 0.8851862549781799,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.5894,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.7056277056277054,
897
+ "grad_norm": 1.0715088844299316,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5251,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7272727272727275,
904
+ "grad_norm": 0.8532006740570068,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.5903,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.7489177489177488,
911
+ "grad_norm": 0.9172760248184204,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5261,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.7705627705627704,
918
+ "grad_norm": 0.8991577625274658,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.5029,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.792207792207792,
925
+ "grad_norm": 0.8205381631851196,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.5207,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.813852813852814,
932
+ "grad_norm": 0.9733313918113708,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.5328,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8354978354978355,
939
+ "grad_norm": 1.0313537120819092,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.5373,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.857142857142857,
946
+ "grad_norm": 0.8865208625793457,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.4832,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.878787878787879,
953
+ "grad_norm": 1.1407958269119263,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5297,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.9004329004329006,
960
+ "grad_norm": 0.879891574382782,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.5435,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.9220779220779223,
967
+ "grad_norm": 0.9538708925247192,
968
+ "learning_rate": 0.0002,
969
+ "loss": 1.5523,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9437229437229435,
974
+ "grad_norm": 0.7732896208763123,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.4881,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.965367965367965,
981
+ "grad_norm": 0.9062705636024475,
982
+ "learning_rate": 0.0002,
983
+ "loss": 1.4959,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.987012987012987,
988
+ "grad_norm": 0.9082673192024231,
989
+ "learning_rate": 0.0002,
990
+ "loss": 1.5508,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 3.0,
995
+ "eval_loss": 1.842921257019043,
996
+ "eval_runtime": 138.5715,
997
+ "eval_samples_per_second": 3.846,
998
+ "eval_steps_per_second": 0.484,
999
+ "step": 1386
1000
+ },
1001
+ {
1002
+ "epoch": 3.0086580086580086,
1003
+ "grad_norm": 0.8586050868034363,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 1.4376,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.0303030303030303,
1010
+ "grad_norm": 1.127321720123291,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 1.2973,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.051948051948052,
1017
+ "grad_norm": 1.3029290437698364,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 1.2804,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.0735930735930737,
1024
+ "grad_norm": 1.4397313594818115,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 1.3353,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.0952380952380953,
1031
+ "grad_norm": 1.5687700510025024,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 1.2783,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.116883116883117,
1038
+ "grad_norm": 1.0821301937103271,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 1.2991,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.1385281385281387,
1045
+ "grad_norm": 1.1222467422485352,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 1.2772,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.16017316017316,
1052
+ "grad_norm": 1.196321964263916,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 1.3571,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.1818181818181817,
1059
+ "grad_norm": 1.1099780797958374,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 1.2597,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.2034632034632033,
1066
+ "grad_norm": 1.1216720342636108,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 1.3297,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.225108225108225,
1073
+ "grad_norm": 1.2393304109573364,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 1.3066,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.2467532467532467,
1080
+ "grad_norm": 1.2331798076629639,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 1.2445,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.2683982683982684,
1087
+ "grad_norm": 1.1466370820999146,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 1.292,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.29004329004329,
1094
+ "grad_norm": 1.6869697570800781,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 1.338,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.311688311688312,
1101
+ "grad_norm": 1.2315126657485962,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 1.3152,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.3333333333333335,
1108
+ "grad_norm": 1.2909607887268066,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 1.3555,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.354978354978355,
1115
+ "grad_norm": 1.2874510288238525,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 1.2782,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.3766233766233764,
1122
+ "grad_norm": 1.5269776582717896,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 1.308,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.398268398268398,
1129
+ "grad_norm": 1.2578439712524414,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 1.3256,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.41991341991342,
1136
+ "grad_norm": 1.1697931289672852,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 1.2783,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.4415584415584415,
1143
+ "grad_norm": 1.314573049545288,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 1.3834,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.463203463203463,
1150
+ "grad_norm": 1.2375879287719727,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 1.2516,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.484848484848485,
1157
+ "grad_norm": 1.0980405807495117,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 1.2872,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.5064935064935066,
1164
+ "grad_norm": 1.5183982849121094,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 1.2586,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.5281385281385282,
1171
+ "grad_norm": 1.7712465524673462,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 1.3149,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.54978354978355,
1178
+ "grad_norm": 1.4033244848251343,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 1.3097,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.571428571428571,
1185
+ "grad_norm": 1.3502216339111328,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 1.3614,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.5930735930735933,
1192
+ "grad_norm": 1.2922712564468384,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 1.3743,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.6147186147186146,
1199
+ "grad_norm": 1.4703474044799805,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 1.3313,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.6363636363636362,
1206
+ "grad_norm": 1.2576347589492798,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 1.3053,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.658008658008658,
1213
+ "grad_norm": 1.361474633216858,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 1.3733,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.6796536796536796,
1220
+ "grad_norm": 1.3686575889587402,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 1.4326,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.7012987012987013,
1227
+ "grad_norm": 1.480577826499939,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 1.3832,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.722943722943723,
1234
+ "grad_norm": 1.1896449327468872,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 1.3488,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.7445887445887447,
1241
+ "grad_norm": 1.1765750646591187,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 1.2901,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.7662337662337664,
1248
+ "grad_norm": 1.1575956344604492,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 1.3259,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.787878787878788,
1255
+ "grad_norm": 1.1376453638076782,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 1.3073,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.8095238095238093,
1262
+ "grad_norm": 1.1058441400527954,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 1.2997,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.8311688311688314,
1269
+ "grad_norm": 1.3807097673416138,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 1.3549,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.8528138528138527,
1276
+ "grad_norm": 1.1583185195922852,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 1.3589,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.8744588744588744,
1283
+ "grad_norm": 1.0412019491195679,
1284
+ "learning_rate": 0.0002,
1285
+ "loss": 1.3855,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.896103896103896,
1290
+ "grad_norm": 1.2590245008468628,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 1.3263,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.9177489177489178,
1297
+ "grad_norm": 1.1784659624099731,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 1.333,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.9393939393939394,
1304
+ "grad_norm": 1.2848402261734009,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 1.3326,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.961038961038961,
1311
+ "grad_norm": 1.2152059078216553,
1312
+ "learning_rate": 0.0002,
1313
+ "loss": 1.3734,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.982683982683983,
1318
+ "grad_norm": 1.3694654703140259,
1319
+ "learning_rate": 0.0002,
1320
+ "loss": 1.3563,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 4.0,
1325
+ "eval_loss": 1.9379768371582031,
1326
+ "eval_runtime": 138.0181,
1327
+ "eval_samples_per_second": 3.862,
1328
+ "eval_steps_per_second": 0.485,
1329
+ "step": 1848
1330
+ }
1331
+ ],
1332
+ "logging_steps": 10,
1333
+ "max_steps": 3696,
1334
+ "num_input_tokens_seen": 0,
1335
+ "num_train_epochs": 8,
1336
+ "save_steps": 200,
1337
+ "stateful_callbacks": {
1338
+ "TrainerControl": {
1339
+ "args": {
1340
+ "should_epoch_stop": false,
1341
+ "should_evaluate": false,
1342
+ "should_log": false,
1343
+ "should_save": true,
1344
+ "should_training_stop": false
1345
+ },
1346
+ "attributes": {}
1347
+ }
1348
+ },
1349
+ "total_flos": 8.10804949549056e+16,
1350
+ "train_batch_size": 1,
1351
+ "trial_name": null,
1352
+ "trial_params": null
1353
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-1848/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d349b8fe4d8871a8479d9bb3b1cba8d39e96d113c8c86cdb28a7fc6969f53ba6
3
+ size 5560
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3409ee7371681afe09dede9dc9270429f58fe1b94ef9e951ba0091e3a58b0d1f
3
+ size 109069176
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24fd38c322977fe2a8a77055a1a4b6fab5e45b708064b8cb41e98b9b5fe0604c
3
+ size 55532666
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea3496e20fbdb98594e1ecf075be3338c434c9afa2ad29244c8d1e62c6b8baa
3
+ size 14244
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431b0fd475a4105d53ed604f0820e31e6c6e3e1a227ef81e9ad538a706e56df2
3
+ size 1064
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/trainer_state.json ADDED
@@ -0,0 +1,1690 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.7847579717636108,
3
+ "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-462",
4
+ "epoch": 5.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2310,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021645021645021644,
13
+ "grad_norm": 1.200374722480774,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.5092,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04329004329004329,
20
+ "grad_norm": 0.974091112613678,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2672,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06493506493506493,
27
+ "grad_norm": 0.9070103168487549,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.1445,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08658008658008658,
34
+ "grad_norm": 0.6892510056495667,
35
+ "learning_rate": 0.0002,
36
+ "loss": 2.0634,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10822510822510822,
41
+ "grad_norm": 0.7840355038642883,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.039,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12987012987012986,
48
+ "grad_norm": 0.8381665349006653,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9527,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15151515151515152,
55
+ "grad_norm": 0.6969044804573059,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.8852,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17316017316017315,
62
+ "grad_norm": 0.6608849763870239,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8263,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19480519480519481,
69
+ "grad_norm": 0.6329185962677002,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.825,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21645021645021645,
76
+ "grad_norm": 0.723852276802063,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8256,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.23809523809523808,
83
+ "grad_norm": 0.8358765840530396,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8758,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2597402597402597,
90
+ "grad_norm": 0.6025514006614685,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8468,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2813852813852814,
97
+ "grad_norm": 0.5782386064529419,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.7487,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30303030303030304,
104
+ "grad_norm": 0.8589595556259155,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.7717,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3246753246753247,
111
+ "grad_norm": 0.5718036890029907,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.7726,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3463203463203463,
118
+ "grad_norm": 0.632756769657135,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.784,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.36796536796536794,
125
+ "grad_norm": 0.5307920575141907,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8176,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.38961038961038963,
132
+ "grad_norm": 0.5692276358604431,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7744,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41125541125541126,
139
+ "grad_norm": 0.6083813309669495,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8075,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4329004329004329,
146
+ "grad_norm": 0.7849981188774109,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8718,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.45454545454545453,
153
+ "grad_norm": 0.6536546945571899,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.7946,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.47619047619047616,
160
+ "grad_norm": 0.5180730223655701,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8174,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.49783549783549785,
167
+ "grad_norm": 0.5796821713447571,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.7857,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5194805194805194,
174
+ "grad_norm": 0.6185894012451172,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8062,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5411255411255411,
181
+ "grad_norm": 0.6040953397750854,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.825,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5627705627705628,
188
+ "grad_norm": 0.6005431413650513,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.7785,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5844155844155844,
195
+ "grad_norm": 0.6693951487541199,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8444,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6060606060606061,
202
+ "grad_norm": 0.5105443596839905,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8471,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6277056277056277,
209
+ "grad_norm": 0.5175243616104126,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8274,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6493506493506493,
216
+ "grad_norm": 0.4775221049785614,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.81,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.670995670995671,
223
+ "grad_norm": 0.9106342792510986,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7816,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6926406926406926,
230
+ "grad_norm": 1.9134571552276611,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.7764,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7142857142857143,
237
+ "grad_norm": 0.6287537217140198,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7877,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7359307359307359,
244
+ "grad_norm": 0.5587132573127747,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.8499,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7575757575757576,
251
+ "grad_norm": 0.5827193260192871,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.7328,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7792207792207793,
258
+ "grad_norm": 0.572600781917572,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8022,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8008658008658008,
265
+ "grad_norm": 0.6280586123466492,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.88,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8225108225108225,
272
+ "grad_norm": 0.6878819465637207,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8116,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8441558441558441,
279
+ "grad_norm": 0.5876027345657349,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8042,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8658008658008658,
286
+ "grad_norm": 0.5249695777893066,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7501,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.8874458874458875,
293
+ "grad_norm": 0.5510677695274353,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.7599,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9090909090909091,
300
+ "grad_norm": 0.6817089915275574,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7737,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9307359307359307,
307
+ "grad_norm": 0.5116859078407288,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.7857,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9523809523809523,
314
+ "grad_norm": 0.5427846312522888,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7361,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.974025974025974,
321
+ "grad_norm": 0.5605915784835815,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.7812,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9956709956709957,
328
+ "grad_norm": 0.5166691541671753,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7699,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0,
335
+ "eval_loss": 1.7847579717636108,
336
+ "eval_runtime": 144.877,
337
+ "eval_samples_per_second": 3.679,
338
+ "eval_steps_per_second": 0.462,
339
+ "step": 462
340
+ },
341
+ {
342
+ "epoch": 1.0173160173160174,
343
+ "grad_norm": 0.5665210485458374,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.6725,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0389610389610389,
350
+ "grad_norm": 1.0514339208602905,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.6996,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0606060606060606,
357
+ "grad_norm": 0.5494309663772583,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.6573,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0822510822510822,
364
+ "grad_norm": 0.557016909122467,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.7314,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.103896103896104,
371
+ "grad_norm": 0.6585943102836609,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.7284,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1255411255411256,
378
+ "grad_norm": 0.6703357696533203,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7575,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1471861471861473,
385
+ "grad_norm": 1.9358264207839966,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7013,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1688311688311688,
392
+ "grad_norm": 0.6128601431846619,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.6914,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1904761904761905,
399
+ "grad_norm": 0.6610239744186401,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.6358,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2121212121212122,
406
+ "grad_norm": 0.6083669662475586,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.7122,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2337662337662338,
413
+ "grad_norm": 0.7784225940704346,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.6771,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2554112554112553,
420
+ "grad_norm": 0.6141694784164429,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.6372,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.277056277056277,
427
+ "grad_norm": 0.6129311323165894,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.6795,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.2987012987012987,
434
+ "grad_norm": 0.6802751421928406,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.6664,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3203463203463204,
441
+ "grad_norm": 0.6065750122070312,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.6555,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.341991341991342,
448
+ "grad_norm": 0.6713075637817383,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.679,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3636363636363638,
455
+ "grad_norm": 0.627552330493927,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7412,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.3852813852813852,
462
+ "grad_norm": 0.6579778790473938,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.6477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.406926406926407,
469
+ "grad_norm": 0.6381745934486389,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7282,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4285714285714286,
476
+ "grad_norm": 0.7358919382095337,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7218,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4502164502164503,
483
+ "grad_norm": 0.6294736266136169,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7046,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4718614718614718,
490
+ "grad_norm": 0.6542870998382568,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7143,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.4935064935064934,
497
+ "grad_norm": 0.6003480553627014,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7417,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5151515151515151,
504
+ "grad_norm": 0.8322144150733948,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.6487,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5367965367965368,
511
+ "grad_norm": 0.6853126287460327,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7217,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5584415584415585,
518
+ "grad_norm": 0.6571378707885742,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6888,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.5800865800865802,
525
+ "grad_norm": 0.6957149505615234,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7111,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.601731601731602,
532
+ "grad_norm": 0.6495681405067444,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7361,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6233766233766234,
539
+ "grad_norm": 0.6954384446144104,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.5709,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.645021645021645,
546
+ "grad_norm": 0.7402207851409912,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.6851,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.6666666666666665,
553
+ "grad_norm": 0.6827481985092163,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.6651,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.6883116883116882,
560
+ "grad_norm": 0.6176769733428955,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.6827,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.70995670995671,
567
+ "grad_norm": 0.6565108299255371,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.6291,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.7316017316017316,
574
+ "grad_norm": 0.6303038001060486,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6805,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.7532467532467533,
581
+ "grad_norm": 0.6866182684898376,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7321,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.774891774891775,
588
+ "grad_norm": 0.7522535920143127,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.6847,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.7965367965367967,
595
+ "grad_norm": 0.7703698873519897,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.679,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8181818181818183,
602
+ "grad_norm": 0.5955503582954407,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.6817,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8398268398268398,
609
+ "grad_norm": 0.707340657711029,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7159,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8614718614718615,
616
+ "grad_norm": 0.7305465936660767,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.709,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.883116883116883,
623
+ "grad_norm": 0.667972207069397,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.71,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9047619047619047,
630
+ "grad_norm": 0.654872477054596,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7051,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9264069264069263,
637
+ "grad_norm": 0.6718705296516418,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.6316,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.948051948051948,
644
+ "grad_norm": 0.6363692879676819,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.623,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9696969696969697,
651
+ "grad_norm": 0.6861362457275391,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.6725,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.9913419913419914,
658
+ "grad_norm": 0.6531493067741394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.6833,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 2.0,
665
+ "eval_loss": 1.7908068895339966,
666
+ "eval_runtime": 144.0281,
667
+ "eval_samples_per_second": 3.701,
668
+ "eval_steps_per_second": 0.465,
669
+ "step": 924
670
+ },
671
+ {
672
+ "epoch": 2.012987012987013,
673
+ "grad_norm": 0.6030914187431335,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.5922,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.034632034632035,
680
+ "grad_norm": 0.7416430711746216,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.5215,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0562770562770565,
687
+ "grad_norm": 0.7020093202590942,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.5759,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.0779220779220777,
694
+ "grad_norm": 0.8007868528366089,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.4751,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.0995670995670994,
701
+ "grad_norm": 0.7111671566963196,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.4808,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.121212121212121,
708
+ "grad_norm": 0.7257682085037231,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.53,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.142857142857143,
715
+ "grad_norm": 0.8737282156944275,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.5097,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1645021645021645,
722
+ "grad_norm": 0.9281378984451294,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.537,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.186147186147186,
729
+ "grad_norm": 1.0217959880828857,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.5223,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.207792207792208,
736
+ "grad_norm": 0.8430958986282349,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.4253,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.2294372294372296,
743
+ "grad_norm": 0.8123440742492676,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.5294,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.2510822510822512,
750
+ "grad_norm": 0.9429558515548706,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.5167,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.2727272727272725,
757
+ "grad_norm": 0.811696469783783,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.4711,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.2943722943722946,
764
+ "grad_norm": 0.8424768447875977,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.4656,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.316017316017316,
771
+ "grad_norm": 0.8870340585708618,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.5618,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3376623376623376,
778
+ "grad_norm": 0.8600393533706665,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5368,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.3593073593073592,
785
+ "grad_norm": 0.8447834253311157,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.5028,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.380952380952381,
792
+ "grad_norm": 0.9303842186927795,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.4885,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.4025974025974026,
799
+ "grad_norm": 0.8144819140434265,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.5163,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4242424242424243,
806
+ "grad_norm": 0.92924964427948,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.4805,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.445887445887446,
813
+ "grad_norm": 0.8560649156570435,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.4608,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.4675324675324677,
820
+ "grad_norm": 0.8532574772834778,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.5541,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.4891774891774894,
827
+ "grad_norm": 0.8702793717384338,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.5607,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5108225108225106,
834
+ "grad_norm": 0.9125854969024658,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.5194,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5324675324675323,
841
+ "grad_norm": 0.9579735398292542,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.5953,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.554112554112554,
848
+ "grad_norm": 0.8561005592346191,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5088,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.5757575757575757,
855
+ "grad_norm": 0.9103630185127258,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.5636,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.5974025974025974,
862
+ "grad_norm": 0.8527248501777649,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.5497,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.619047619047619,
869
+ "grad_norm": 0.8368656039237976,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.5845,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6406926406926408,
876
+ "grad_norm": 0.9644360542297363,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.574,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.6623376623376624,
883
+ "grad_norm": 0.9691457748413086,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.5623,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.683982683982684,
890
+ "grad_norm": 0.8851862549781799,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.5894,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.7056277056277054,
897
+ "grad_norm": 1.0715088844299316,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5251,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7272727272727275,
904
+ "grad_norm": 0.8532006740570068,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.5903,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.7489177489177488,
911
+ "grad_norm": 0.9172760248184204,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5261,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.7705627705627704,
918
+ "grad_norm": 0.8991577625274658,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.5029,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.792207792207792,
925
+ "grad_norm": 0.8205381631851196,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.5207,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.813852813852814,
932
+ "grad_norm": 0.9733313918113708,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.5328,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8354978354978355,
939
+ "grad_norm": 1.0313537120819092,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.5373,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.857142857142857,
946
+ "grad_norm": 0.8865208625793457,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.4832,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.878787878787879,
953
+ "grad_norm": 1.1407958269119263,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5297,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.9004329004329006,
960
+ "grad_norm": 0.879891574382782,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.5435,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.9220779220779223,
967
+ "grad_norm": 0.9538708925247192,
968
+ "learning_rate": 0.0002,
969
+ "loss": 1.5523,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9437229437229435,
974
+ "grad_norm": 0.7732896208763123,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.4881,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.965367965367965,
981
+ "grad_norm": 0.9062705636024475,
982
+ "learning_rate": 0.0002,
983
+ "loss": 1.4959,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.987012987012987,
988
+ "grad_norm": 0.9082673192024231,
989
+ "learning_rate": 0.0002,
990
+ "loss": 1.5508,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 3.0,
995
+ "eval_loss": 1.842921257019043,
996
+ "eval_runtime": 138.5715,
997
+ "eval_samples_per_second": 3.846,
998
+ "eval_steps_per_second": 0.484,
999
+ "step": 1386
1000
+ },
1001
+ {
1002
+ "epoch": 3.0086580086580086,
1003
+ "grad_norm": 0.8586050868034363,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 1.4376,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.0303030303030303,
1010
+ "grad_norm": 1.127321720123291,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 1.2973,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.051948051948052,
1017
+ "grad_norm": 1.3029290437698364,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 1.2804,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.0735930735930737,
1024
+ "grad_norm": 1.4397313594818115,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 1.3353,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.0952380952380953,
1031
+ "grad_norm": 1.5687700510025024,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 1.2783,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.116883116883117,
1038
+ "grad_norm": 1.0821301937103271,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 1.2991,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.1385281385281387,
1045
+ "grad_norm": 1.1222467422485352,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 1.2772,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.16017316017316,
1052
+ "grad_norm": 1.196321964263916,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 1.3571,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.1818181818181817,
1059
+ "grad_norm": 1.1099780797958374,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 1.2597,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.2034632034632033,
1066
+ "grad_norm": 1.1216720342636108,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 1.3297,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.225108225108225,
1073
+ "grad_norm": 1.2393304109573364,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 1.3066,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.2467532467532467,
1080
+ "grad_norm": 1.2331798076629639,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 1.2445,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.2683982683982684,
1087
+ "grad_norm": 1.1466370820999146,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 1.292,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.29004329004329,
1094
+ "grad_norm": 1.6869697570800781,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 1.338,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.311688311688312,
1101
+ "grad_norm": 1.2315126657485962,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 1.3152,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.3333333333333335,
1108
+ "grad_norm": 1.2909607887268066,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 1.3555,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.354978354978355,
1115
+ "grad_norm": 1.2874510288238525,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 1.2782,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.3766233766233764,
1122
+ "grad_norm": 1.5269776582717896,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 1.308,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.398268398268398,
1129
+ "grad_norm": 1.2578439712524414,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 1.3256,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.41991341991342,
1136
+ "grad_norm": 1.1697931289672852,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 1.2783,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.4415584415584415,
1143
+ "grad_norm": 1.314573049545288,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 1.3834,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.463203463203463,
1150
+ "grad_norm": 1.2375879287719727,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 1.2516,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.484848484848485,
1157
+ "grad_norm": 1.0980405807495117,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 1.2872,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.5064935064935066,
1164
+ "grad_norm": 1.5183982849121094,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 1.2586,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.5281385281385282,
1171
+ "grad_norm": 1.7712465524673462,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 1.3149,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.54978354978355,
1178
+ "grad_norm": 1.4033244848251343,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 1.3097,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.571428571428571,
1185
+ "grad_norm": 1.3502216339111328,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 1.3614,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.5930735930735933,
1192
+ "grad_norm": 1.2922712564468384,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 1.3743,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.6147186147186146,
1199
+ "grad_norm": 1.4703474044799805,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 1.3313,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.6363636363636362,
1206
+ "grad_norm": 1.2576347589492798,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 1.3053,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.658008658008658,
1213
+ "grad_norm": 1.361474633216858,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 1.3733,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.6796536796536796,
1220
+ "grad_norm": 1.3686575889587402,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 1.4326,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.7012987012987013,
1227
+ "grad_norm": 1.480577826499939,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 1.3832,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.722943722943723,
1234
+ "grad_norm": 1.1896449327468872,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 1.3488,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.7445887445887447,
1241
+ "grad_norm": 1.1765750646591187,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 1.2901,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.7662337662337664,
1248
+ "grad_norm": 1.1575956344604492,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 1.3259,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.787878787878788,
1255
+ "grad_norm": 1.1376453638076782,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 1.3073,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.8095238095238093,
1262
+ "grad_norm": 1.1058441400527954,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 1.2997,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.8311688311688314,
1269
+ "grad_norm": 1.3807097673416138,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 1.3549,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.8528138528138527,
1276
+ "grad_norm": 1.1583185195922852,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 1.3589,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.8744588744588744,
1283
+ "grad_norm": 1.0412019491195679,
1284
+ "learning_rate": 0.0002,
1285
+ "loss": 1.3855,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.896103896103896,
1290
+ "grad_norm": 1.2590245008468628,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 1.3263,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.9177489177489178,
1297
+ "grad_norm": 1.1784659624099731,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 1.333,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.9393939393939394,
1304
+ "grad_norm": 1.2848402261734009,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 1.3326,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.961038961038961,
1311
+ "grad_norm": 1.2152059078216553,
1312
+ "learning_rate": 0.0002,
1313
+ "loss": 1.3734,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.982683982683983,
1318
+ "grad_norm": 1.3694654703140259,
1319
+ "learning_rate": 0.0002,
1320
+ "loss": 1.3563,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 4.0,
1325
+ "eval_loss": 1.9379768371582031,
1326
+ "eval_runtime": 138.0181,
1327
+ "eval_samples_per_second": 3.862,
1328
+ "eval_steps_per_second": 0.485,
1329
+ "step": 1848
1330
+ },
1331
+ {
1332
+ "epoch": 4.004329004329004,
1333
+ "grad_norm": 1.1592340469360352,
1334
+ "learning_rate": 0.0002,
1335
+ "loss": 1.2715,
1336
+ "step": 1850
1337
+ },
1338
+ {
1339
+ "epoch": 4.025974025974026,
1340
+ "grad_norm": 1.4811842441558838,
1341
+ "learning_rate": 0.0002,
1342
+ "loss": 1.0985,
1343
+ "step": 1860
1344
+ },
1345
+ {
1346
+ "epoch": 4.0476190476190474,
1347
+ "grad_norm": 1.4762481451034546,
1348
+ "learning_rate": 0.0002,
1349
+ "loss": 1.0392,
1350
+ "step": 1870
1351
+ },
1352
+ {
1353
+ "epoch": 4.06926406926407,
1354
+ "grad_norm": 1.1761656999588013,
1355
+ "learning_rate": 0.0002,
1356
+ "loss": 1.1076,
1357
+ "step": 1880
1358
+ },
1359
+ {
1360
+ "epoch": 4.090909090909091,
1361
+ "grad_norm": 1.621068000793457,
1362
+ "learning_rate": 0.0002,
1363
+ "loss": 1.0813,
1364
+ "step": 1890
1365
+ },
1366
+ {
1367
+ "epoch": 4.112554112554113,
1368
+ "grad_norm": 1.7963402271270752,
1369
+ "learning_rate": 0.0002,
1370
+ "loss": 1.0849,
1371
+ "step": 1900
1372
+ },
1373
+ {
1374
+ "epoch": 4.134199134199134,
1375
+ "grad_norm": 1.682166337966919,
1376
+ "learning_rate": 0.0002,
1377
+ "loss": 1.115,
1378
+ "step": 1910
1379
+ },
1380
+ {
1381
+ "epoch": 4.1558441558441555,
1382
+ "grad_norm": 1.765175700187683,
1383
+ "learning_rate": 0.0002,
1384
+ "loss": 1.0142,
1385
+ "step": 1920
1386
+ },
1387
+ {
1388
+ "epoch": 4.177489177489178,
1389
+ "grad_norm": 1.7437595129013062,
1390
+ "learning_rate": 0.0002,
1391
+ "loss": 1.0237,
1392
+ "step": 1930
1393
+ },
1394
+ {
1395
+ "epoch": 4.199134199134199,
1396
+ "grad_norm": 1.487619400024414,
1397
+ "learning_rate": 0.0002,
1398
+ "loss": 1.1269,
1399
+ "step": 1940
1400
+ },
1401
+ {
1402
+ "epoch": 4.220779220779221,
1403
+ "grad_norm": 1.5726702213287354,
1404
+ "learning_rate": 0.0002,
1405
+ "loss": 1.1398,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 4.242424242424242,
1410
+ "grad_norm": 1.675681471824646,
1411
+ "learning_rate": 0.0002,
1412
+ "loss": 1.0203,
1413
+ "step": 1960
1414
+ },
1415
+ {
1416
+ "epoch": 4.264069264069264,
1417
+ "grad_norm": 1.5381293296813965,
1418
+ "learning_rate": 0.0002,
1419
+ "loss": 1.0001,
1420
+ "step": 1970
1421
+ },
1422
+ {
1423
+ "epoch": 4.285714285714286,
1424
+ "grad_norm": 1.6634043455123901,
1425
+ "learning_rate": 0.0002,
1426
+ "loss": 1.1608,
1427
+ "step": 1980
1428
+ },
1429
+ {
1430
+ "epoch": 4.307359307359308,
1431
+ "grad_norm": 1.4991868734359741,
1432
+ "learning_rate": 0.0002,
1433
+ "loss": 1.0914,
1434
+ "step": 1990
1435
+ },
1436
+ {
1437
+ "epoch": 4.329004329004329,
1438
+ "grad_norm": 1.7046575546264648,
1439
+ "learning_rate": 0.0002,
1440
+ "loss": 1.0208,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 4.35064935064935,
1445
+ "grad_norm": 1.8189613819122314,
1446
+ "learning_rate": 0.0002,
1447
+ "loss": 1.0671,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 4.372294372294372,
1452
+ "grad_norm": 1.7232930660247803,
1453
+ "learning_rate": 0.0002,
1454
+ "loss": 1.0771,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 4.393939393939394,
1459
+ "grad_norm": 2.037747859954834,
1460
+ "learning_rate": 0.0002,
1461
+ "loss": 1.0849,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 4.415584415584416,
1466
+ "grad_norm": 1.6157771348953247,
1467
+ "learning_rate": 0.0002,
1468
+ "loss": 1.0984,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 4.437229437229437,
1473
+ "grad_norm": 1.6834640502929688,
1474
+ "learning_rate": 0.0002,
1475
+ "loss": 1.0542,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 4.458874458874459,
1480
+ "grad_norm": 1.5155940055847168,
1481
+ "learning_rate": 0.0002,
1482
+ "loss": 1.1582,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 4.48051948051948,
1487
+ "grad_norm": 1.9364410638809204,
1488
+ "learning_rate": 0.0002,
1489
+ "loss": 1.1593,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.5021645021645025,
1494
+ "grad_norm": 1.512215256690979,
1495
+ "learning_rate": 0.0002,
1496
+ "loss": 1.1484,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 4.523809523809524,
1501
+ "grad_norm": 1.7659000158309937,
1502
+ "learning_rate": 0.0002,
1503
+ "loss": 1.0858,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 4.545454545454545,
1508
+ "grad_norm": 1.8038681745529175,
1509
+ "learning_rate": 0.0002,
1510
+ "loss": 1.1309,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 4.567099567099567,
1515
+ "grad_norm": 1.6234548091888428,
1516
+ "learning_rate": 0.0002,
1517
+ "loss": 1.1466,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 4.588744588744589,
1522
+ "grad_norm": 1.7181912660598755,
1523
+ "learning_rate": 0.0002,
1524
+ "loss": 1.1237,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 4.6103896103896105,
1529
+ "grad_norm": 1.5204529762268066,
1530
+ "learning_rate": 0.0002,
1531
+ "loss": 1.129,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 4.632034632034632,
1536
+ "grad_norm": 1.6626766920089722,
1537
+ "learning_rate": 0.0002,
1538
+ "loss": 1.1338,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 4.653679653679654,
1543
+ "grad_norm": 1.6722981929779053,
1544
+ "learning_rate": 0.0002,
1545
+ "loss": 1.1135,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 4.675324675324675,
1550
+ "grad_norm": 1.5929896831512451,
1551
+ "learning_rate": 0.0002,
1552
+ "loss": 1.1243,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 4.696969696969697,
1557
+ "grad_norm": 1.8637045621871948,
1558
+ "learning_rate": 0.0002,
1559
+ "loss": 1.1511,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 4.7186147186147185,
1564
+ "grad_norm": 1.7406965494155884,
1565
+ "learning_rate": 0.0002,
1566
+ "loss": 1.0816,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 4.740259740259741,
1571
+ "grad_norm": 1.9259464740753174,
1572
+ "learning_rate": 0.0002,
1573
+ "loss": 1.0913,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.761904761904762,
1578
+ "grad_norm": 1.5640064477920532,
1579
+ "learning_rate": 0.0002,
1580
+ "loss": 1.1273,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 4.783549783549784,
1585
+ "grad_norm": 1.5039080381393433,
1586
+ "learning_rate": 0.0002,
1587
+ "loss": 1.095,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 4.805194805194805,
1592
+ "grad_norm": 2.086487293243408,
1593
+ "learning_rate": 0.0002,
1594
+ "loss": 1.1082,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 4.8268398268398265,
1599
+ "grad_norm": 1.8213051557540894,
1600
+ "learning_rate": 0.0002,
1601
+ "loss": 1.1299,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 4.848484848484849,
1606
+ "grad_norm": 1.6772842407226562,
1607
+ "learning_rate": 0.0002,
1608
+ "loss": 1.1339,
1609
+ "step": 2240
1610
+ },
1611
+ {
1612
+ "epoch": 4.87012987012987,
1613
+ "grad_norm": 1.855952262878418,
1614
+ "learning_rate": 0.0002,
1615
+ "loss": 1.0688,
1616
+ "step": 2250
1617
+ },
1618
+ {
1619
+ "epoch": 4.891774891774892,
1620
+ "grad_norm": 1.703018069267273,
1621
+ "learning_rate": 0.0002,
1622
+ "loss": 1.1242,
1623
+ "step": 2260
1624
+ },
1625
+ {
1626
+ "epoch": 4.913419913419913,
1627
+ "grad_norm": 1.5779869556427002,
1628
+ "learning_rate": 0.0002,
1629
+ "loss": 1.1745,
1630
+ "step": 2270
1631
+ },
1632
+ {
1633
+ "epoch": 4.935064935064935,
1634
+ "grad_norm": 1.873153567314148,
1635
+ "learning_rate": 0.0002,
1636
+ "loss": 1.1367,
1637
+ "step": 2280
1638
+ },
1639
+ {
1640
+ "epoch": 4.956709956709957,
1641
+ "grad_norm": 1.845137119293213,
1642
+ "learning_rate": 0.0002,
1643
+ "loss": 1.1469,
1644
+ "step": 2290
1645
+ },
1646
+ {
1647
+ "epoch": 4.978354978354979,
1648
+ "grad_norm": 1.5848972797393799,
1649
+ "learning_rate": 0.0002,
1650
+ "loss": 1.176,
1651
+ "step": 2300
1652
+ },
1653
+ {
1654
+ "epoch": 5.0,
1655
+ "grad_norm": 1.7801740169525146,
1656
+ "learning_rate": 0.0002,
1657
+ "loss": 1.1427,
1658
+ "step": 2310
1659
+ },
1660
+ {
1661
+ "epoch": 5.0,
1662
+ "eval_loss": 2.1164023876190186,
1663
+ "eval_runtime": 138.8921,
1664
+ "eval_samples_per_second": 3.838,
1665
+ "eval_steps_per_second": 0.482,
1666
+ "step": 2310
1667
+ }
1668
+ ],
1669
+ "logging_steps": 10,
1670
+ "max_steps": 3696,
1671
+ "num_input_tokens_seen": 0,
1672
+ "num_train_epochs": 8,
1673
+ "save_steps": 200,
1674
+ "stateful_callbacks": {
1675
+ "TrainerControl": {
1676
+ "args": {
1677
+ "should_epoch_stop": false,
1678
+ "should_evaluate": false,
1679
+ "should_log": false,
1680
+ "should_save": true,
1681
+ "should_training_stop": false
1682
+ },
1683
+ "attributes": {}
1684
+ }
1685
+ },
1686
+ "total_flos": 1.01350618693632e+17,
1687
+ "train_batch_size": 1,
1688
+ "trial_name": null,
1689
+ "trial_params": null
1690
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2310/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d349b8fe4d8871a8479d9bb3b1cba8d39e96d113c8c86cdb28a7fc6969f53ba6
3
+ size 5560
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c02bd8f9cbf6c31e6614a5974b6e5ce60c0d6410e340dda226b60e2cbe1a215a
3
+ size 109069176
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c16e7eabbb413a68f670fe00cc27b12eab63ec8e22687cd91ee3c8c648f0a7
3
+ size 55532666
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf48f2f778bc43abea17e7d1a1b0d37289965aac2075f6d73208cec0b0aa8c8
3
+ size 14244
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496b2f188f4b585c8b55ecd150fb699fd83971e2fa6797790d5b503c86f79829
3
+ size 1064
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-2772/trainer_state.json ADDED
@@ -0,0 +1,2020 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.7847579717636108,
3
+ "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-1/checkpoint-462",
4
+ "epoch": 6.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2772,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021645021645021644,
13
+ "grad_norm": 1.200374722480774,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.5092,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04329004329004329,
20
+ "grad_norm": 0.974091112613678,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2672,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06493506493506493,
27
+ "grad_norm": 0.9070103168487549,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.1445,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08658008658008658,
34
+ "grad_norm": 0.6892510056495667,
35
+ "learning_rate": 0.0002,
36
+ "loss": 2.0634,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10822510822510822,
41
+ "grad_norm": 0.7840355038642883,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.039,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12987012987012986,
48
+ "grad_norm": 0.8381665349006653,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9527,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15151515151515152,
55
+ "grad_norm": 0.6969044804573059,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.8852,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17316017316017315,
62
+ "grad_norm": 0.6608849763870239,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8263,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19480519480519481,
69
+ "grad_norm": 0.6329185962677002,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.825,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21645021645021645,
76
+ "grad_norm": 0.723852276802063,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8256,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.23809523809523808,
83
+ "grad_norm": 0.8358765840530396,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8758,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2597402597402597,
90
+ "grad_norm": 0.6025514006614685,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8468,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2813852813852814,
97
+ "grad_norm": 0.5782386064529419,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.7487,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30303030303030304,
104
+ "grad_norm": 0.8589595556259155,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.7717,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3246753246753247,
111
+ "grad_norm": 0.5718036890029907,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.7726,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3463203463203463,
118
+ "grad_norm": 0.632756769657135,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.784,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.36796536796536794,
125
+ "grad_norm": 0.5307920575141907,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8176,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.38961038961038963,
132
+ "grad_norm": 0.5692276358604431,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7744,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41125541125541126,
139
+ "grad_norm": 0.6083813309669495,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8075,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4329004329004329,
146
+ "grad_norm": 0.7849981188774109,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8718,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.45454545454545453,
153
+ "grad_norm": 0.6536546945571899,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.7946,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.47619047619047616,
160
+ "grad_norm": 0.5180730223655701,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8174,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.49783549783549785,
167
+ "grad_norm": 0.5796821713447571,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.7857,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5194805194805194,
174
+ "grad_norm": 0.6185894012451172,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8062,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5411255411255411,
181
+ "grad_norm": 0.6040953397750854,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.825,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5627705627705628,
188
+ "grad_norm": 0.6005431413650513,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.7785,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5844155844155844,
195
+ "grad_norm": 0.6693951487541199,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8444,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6060606060606061,
202
+ "grad_norm": 0.5105443596839905,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8471,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6277056277056277,
209
+ "grad_norm": 0.5175243616104126,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8274,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6493506493506493,
216
+ "grad_norm": 0.4775221049785614,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.81,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.670995670995671,
223
+ "grad_norm": 0.9106342792510986,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7816,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6926406926406926,
230
+ "grad_norm": 1.9134571552276611,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.7764,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7142857142857143,
237
+ "grad_norm": 0.6287537217140198,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7877,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7359307359307359,
244
+ "grad_norm": 0.5587132573127747,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.8499,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7575757575757576,
251
+ "grad_norm": 0.5827193260192871,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.7328,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7792207792207793,
258
+ "grad_norm": 0.572600781917572,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8022,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8008658008658008,
265
+ "grad_norm": 0.6280586123466492,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.88,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8225108225108225,
272
+ "grad_norm": 0.6878819465637207,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8116,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8441558441558441,
279
+ "grad_norm": 0.5876027345657349,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8042,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8658008658008658,
286
+ "grad_norm": 0.5249695777893066,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7501,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.8874458874458875,
293
+ "grad_norm": 0.5510677695274353,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.7599,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9090909090909091,
300
+ "grad_norm": 0.6817089915275574,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7737,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9307359307359307,
307
+ "grad_norm": 0.5116859078407288,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.7857,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9523809523809523,
314
+ "grad_norm": 0.5427846312522888,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7361,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.974025974025974,
321
+ "grad_norm": 0.5605915784835815,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.7812,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9956709956709957,
328
+ "grad_norm": 0.5166691541671753,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7699,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0,
335
+ "eval_loss": 1.7847579717636108,
336
+ "eval_runtime": 144.877,
337
+ "eval_samples_per_second": 3.679,
338
+ "eval_steps_per_second": 0.462,
339
+ "step": 462
340
+ },
341
+ {
342
+ "epoch": 1.0173160173160174,
343
+ "grad_norm": 0.5665210485458374,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.6725,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0389610389610389,
350
+ "grad_norm": 1.0514339208602905,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.6996,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0606060606060606,
357
+ "grad_norm": 0.5494309663772583,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.6573,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0822510822510822,
364
+ "grad_norm": 0.557016909122467,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.7314,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.103896103896104,
371
+ "grad_norm": 0.6585943102836609,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.7284,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1255411255411256,
378
+ "grad_norm": 0.6703357696533203,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7575,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1471861471861473,
385
+ "grad_norm": 1.9358264207839966,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7013,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1688311688311688,
392
+ "grad_norm": 0.6128601431846619,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.6914,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1904761904761905,
399
+ "grad_norm": 0.6610239744186401,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.6358,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2121212121212122,
406
+ "grad_norm": 0.6083669662475586,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.7122,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2337662337662338,
413
+ "grad_norm": 0.7784225940704346,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.6771,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2554112554112553,
420
+ "grad_norm": 0.6141694784164429,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.6372,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.277056277056277,
427
+ "grad_norm": 0.6129311323165894,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.6795,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.2987012987012987,
434
+ "grad_norm": 0.6802751421928406,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.6664,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3203463203463204,
441
+ "grad_norm": 0.6065750122070312,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.6555,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.341991341991342,
448
+ "grad_norm": 0.6713075637817383,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.679,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3636363636363638,
455
+ "grad_norm": 0.627552330493927,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7412,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.3852813852813852,
462
+ "grad_norm": 0.6579778790473938,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.6477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.406926406926407,
469
+ "grad_norm": 0.6381745934486389,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7282,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4285714285714286,
476
+ "grad_norm": 0.7358919382095337,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7218,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4502164502164503,
483
+ "grad_norm": 0.6294736266136169,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7046,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4718614718614718,
490
+ "grad_norm": 0.6542870998382568,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7143,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.4935064935064934,
497
+ "grad_norm": 0.6003480553627014,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7417,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5151515151515151,
504
+ "grad_norm": 0.8322144150733948,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.6487,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5367965367965368,
511
+ "grad_norm": 0.6853126287460327,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7217,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5584415584415585,
518
+ "grad_norm": 0.6571378707885742,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6888,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.5800865800865802,
525
+ "grad_norm": 0.6957149505615234,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7111,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.601731601731602,
532
+ "grad_norm": 0.6495681405067444,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7361,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6233766233766234,
539
+ "grad_norm": 0.6954384446144104,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.5709,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.645021645021645,
546
+ "grad_norm": 0.7402207851409912,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.6851,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.6666666666666665,
553
+ "grad_norm": 0.6827481985092163,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.6651,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.6883116883116882,
560
+ "grad_norm": 0.6176769733428955,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.6827,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.70995670995671,
567
+ "grad_norm": 0.6565108299255371,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.6291,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.7316017316017316,
574
+ "grad_norm": 0.6303038001060486,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6805,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.7532467532467533,
581
+ "grad_norm": 0.6866182684898376,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7321,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.774891774891775,
588
+ "grad_norm": 0.7522535920143127,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.6847,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.7965367965367967,
595
+ "grad_norm": 0.7703698873519897,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.679,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8181818181818183,
602
+ "grad_norm": 0.5955503582954407,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.6817,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8398268398268398,
609
+ "grad_norm": 0.707340657711029,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7159,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8614718614718615,
616
+ "grad_norm": 0.7305465936660767,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.709,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.883116883116883,
623
+ "grad_norm": 0.667972207069397,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.71,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9047619047619047,
630
+ "grad_norm": 0.654872477054596,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7051,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9264069264069263,
637
+ "grad_norm": 0.6718705296516418,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.6316,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.948051948051948,
644
+ "grad_norm": 0.6363692879676819,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.623,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9696969696969697,
651
+ "grad_norm": 0.6861362457275391,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.6725,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.9913419913419914,
658
+ "grad_norm": 0.6531493067741394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.6833,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 2.0,
665
+ "eval_loss": 1.7908068895339966,
666
+ "eval_runtime": 144.0281,
667
+ "eval_samples_per_second": 3.701,
668
+ "eval_steps_per_second": 0.465,
669
+ "step": 924
670
+ },
671
+ {
672
+ "epoch": 2.012987012987013,
673
+ "grad_norm": 0.6030914187431335,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.5922,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.034632034632035,
680
+ "grad_norm": 0.7416430711746216,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.5215,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0562770562770565,
687
+ "grad_norm": 0.7020093202590942,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.5759,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.0779220779220777,
694
+ "grad_norm": 0.8007868528366089,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.4751,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.0995670995670994,
701
+ "grad_norm": 0.7111671566963196,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.4808,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.121212121212121,
708
+ "grad_norm": 0.7257682085037231,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.53,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.142857142857143,
715
+ "grad_norm": 0.8737282156944275,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.5097,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1645021645021645,
722
+ "grad_norm": 0.9281378984451294,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.537,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.186147186147186,
729
+ "grad_norm": 1.0217959880828857,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.5223,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.207792207792208,
736
+ "grad_norm": 0.8430958986282349,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.4253,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.2294372294372296,
743
+ "grad_norm": 0.8123440742492676,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.5294,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.2510822510822512,
750
+ "grad_norm": 0.9429558515548706,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.5167,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.2727272727272725,
757
+ "grad_norm": 0.811696469783783,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.4711,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.2943722943722946,
764
+ "grad_norm": 0.8424768447875977,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.4656,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.316017316017316,
771
+ "grad_norm": 0.8870340585708618,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.5618,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3376623376623376,
778
+ "grad_norm": 0.8600393533706665,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5368,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.3593073593073592,
785
+ "grad_norm": 0.8447834253311157,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.5028,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.380952380952381,
792
+ "grad_norm": 0.9303842186927795,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.4885,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.4025974025974026,
799
+ "grad_norm": 0.8144819140434265,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.5163,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4242424242424243,
806
+ "grad_norm": 0.92924964427948,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.4805,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.445887445887446,
813
+ "grad_norm": 0.8560649156570435,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.4608,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.4675324675324677,
820
+ "grad_norm": 0.8532574772834778,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.5541,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.4891774891774894,
827
+ "grad_norm": 0.8702793717384338,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.5607,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5108225108225106,
834
+ "grad_norm": 0.9125854969024658,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.5194,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5324675324675323,
841
+ "grad_norm": 0.9579735398292542,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.5953,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.554112554112554,
848
+ "grad_norm": 0.8561005592346191,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5088,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.5757575757575757,
855
+ "grad_norm": 0.9103630185127258,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.5636,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.5974025974025974,
862
+ "grad_norm": 0.8527248501777649,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.5497,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.619047619047619,
869
+ "grad_norm": 0.8368656039237976,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.5845,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6406926406926408,
876
+ "grad_norm": 0.9644360542297363,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.574,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.6623376623376624,
883
+ "grad_norm": 0.9691457748413086,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.5623,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.683982683982684,
890
+ "grad_norm": 0.8851862549781799,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.5894,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.7056277056277054,
897
+ "grad_norm": 1.0715088844299316,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5251,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7272727272727275,
904
+ "grad_norm": 0.8532006740570068,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.5903,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.7489177489177488,
911
+ "grad_norm": 0.9172760248184204,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5261,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.7705627705627704,
918
+ "grad_norm": 0.8991577625274658,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.5029,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.792207792207792,
925
+ "grad_norm": 0.8205381631851196,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.5207,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.813852813852814,
932
+ "grad_norm": 0.9733313918113708,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.5328,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8354978354978355,
939
+ "grad_norm": 1.0313537120819092,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.5373,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.857142857142857,
946
+ "grad_norm": 0.8865208625793457,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.4832,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.878787878787879,
953
+ "grad_norm": 1.1407958269119263,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5297,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.9004329004329006,
960
+ "grad_norm": 0.879891574382782,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.5435,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.9220779220779223,
967
+ "grad_norm": 0.9538708925247192,
968
+ "learning_rate": 0.0002,
969
+ "loss": 1.5523,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9437229437229435,
974
+ "grad_norm": 0.7732896208763123,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.4881,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.965367965367965,
981
+ "grad_norm": 0.9062705636024475,
982
+ "learning_rate": 0.0002,
983
+ "loss": 1.4959,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.987012987012987,
988
+ "grad_norm": 0.9082673192024231,
989
+ "learning_rate": 0.0002,
990
+ "loss": 1.5508,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 3.0,
995
+ "eval_loss": 1.842921257019043,
996
+ "eval_runtime": 138.5715,
997
+ "eval_samples_per_second": 3.846,
998
+ "eval_steps_per_second": 0.484,
999
+ "step": 1386
1000
+ },
1001
+ {
1002
+ "epoch": 3.0086580086580086,
1003
+ "grad_norm": 0.8586050868034363,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 1.4376,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.0303030303030303,
1010
+ "grad_norm": 1.127321720123291,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 1.2973,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.051948051948052,
1017
+ "grad_norm": 1.3029290437698364,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 1.2804,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.0735930735930737,
1024
+ "grad_norm": 1.4397313594818115,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 1.3353,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.0952380952380953,
1031
+ "grad_norm": 1.5687700510025024,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 1.2783,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.116883116883117,
1038
+ "grad_norm": 1.0821301937103271,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 1.2991,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.1385281385281387,
1045
+ "grad_norm": 1.1222467422485352,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 1.2772,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.16017316017316,
1052
+ "grad_norm": 1.196321964263916,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 1.3571,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.1818181818181817,
1059
+ "grad_norm": 1.1099780797958374,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 1.2597,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.2034632034632033,
1066
+ "grad_norm": 1.1216720342636108,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 1.3297,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.225108225108225,
1073
+ "grad_norm": 1.2393304109573364,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 1.3066,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.2467532467532467,
1080
+ "grad_norm": 1.2331798076629639,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 1.2445,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.2683982683982684,
1087
+ "grad_norm": 1.1466370820999146,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 1.292,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.29004329004329,
1094
+ "grad_norm": 1.6869697570800781,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 1.338,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.311688311688312,
1101
+ "grad_norm": 1.2315126657485962,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 1.3152,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.3333333333333335,
1108
+ "grad_norm": 1.2909607887268066,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 1.3555,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.354978354978355,
1115
+ "grad_norm": 1.2874510288238525,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 1.2782,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.3766233766233764,
1122
+ "grad_norm": 1.5269776582717896,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 1.308,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.398268398268398,
1129
+ "grad_norm": 1.2578439712524414,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 1.3256,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.41991341991342,
1136
+ "grad_norm": 1.1697931289672852,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 1.2783,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.4415584415584415,
1143
+ "grad_norm": 1.314573049545288,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 1.3834,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.463203463203463,
1150
+ "grad_norm": 1.2375879287719727,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 1.2516,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.484848484848485,
1157
+ "grad_norm": 1.0980405807495117,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 1.2872,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.5064935064935066,
1164
+ "grad_norm": 1.5183982849121094,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 1.2586,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.5281385281385282,
1171
+ "grad_norm": 1.7712465524673462,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 1.3149,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.54978354978355,
1178
+ "grad_norm": 1.4033244848251343,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 1.3097,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.571428571428571,
1185
+ "grad_norm": 1.3502216339111328,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 1.3614,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.5930735930735933,
1192
+ "grad_norm": 1.2922712564468384,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 1.3743,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.6147186147186146,
1199
+ "grad_norm": 1.4703474044799805,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 1.3313,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.6363636363636362,
1206
+ "grad_norm": 1.2576347589492798,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 1.3053,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.658008658008658,
1213
+ "grad_norm": 1.361474633216858,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 1.3733,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.6796536796536796,
1220
+ "grad_norm": 1.3686575889587402,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 1.4326,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.7012987012987013,
1227
+ "grad_norm": 1.480577826499939,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 1.3832,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.722943722943723,
1234
+ "grad_norm": 1.1896449327468872,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 1.3488,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.7445887445887447,
1241
+ "grad_norm": 1.1765750646591187,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 1.2901,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.7662337662337664,
1248
+ "grad_norm": 1.1575956344604492,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 1.3259,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.787878787878788,
1255
+ "grad_norm": 1.1376453638076782,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 1.3073,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.8095238095238093,
1262
+ "grad_norm": 1.1058441400527954,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 1.2997,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.8311688311688314,
1269
+ "grad_norm": 1.3807097673416138,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 1.3549,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.8528138528138527,
1276
+ "grad_norm": 1.1583185195922852,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 1.3589,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.8744588744588744,
1283
+ "grad_norm": 1.0412019491195679,
1284
+ "learning_rate": 0.0002,
1285
+ "loss": 1.3855,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.896103896103896,
1290
+ "grad_norm": 1.2590245008468628,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 1.3263,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.9177489177489178,
1297
+ "grad_norm": 1.1784659624099731,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 1.333,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.9393939393939394,
1304
+ "grad_norm": 1.2848402261734009,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 1.3326,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.961038961038961,
1311
+ "grad_norm": 1.2152059078216553,
1312
+ "learning_rate": 0.0002,
1313
+ "loss": 1.3734,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.982683982683983,
1318
+ "grad_norm": 1.3694654703140259,
1319
+ "learning_rate": 0.0002,
1320
+ "loss": 1.3563,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 4.0,
1325
+ "eval_loss": 1.9379768371582031,
1326
+ "eval_runtime": 138.0181,
1327
+ "eval_samples_per_second": 3.862,
1328
+ "eval_steps_per_second": 0.485,
1329
+ "step": 1848
1330
+ },
1331
+ {
1332
+ "epoch": 4.004329004329004,
1333
+ "grad_norm": 1.1592340469360352,
1334
+ "learning_rate": 0.0002,
1335
+ "loss": 1.2715,
1336
+ "step": 1850
1337
+ },
1338
+ {
1339
+ "epoch": 4.025974025974026,
1340
+ "grad_norm": 1.4811842441558838,
1341
+ "learning_rate": 0.0002,
1342
+ "loss": 1.0985,
1343
+ "step": 1860
1344
+ },
1345
+ {
1346
+ "epoch": 4.0476190476190474,
1347
+ "grad_norm": 1.4762481451034546,
1348
+ "learning_rate": 0.0002,
1349
+ "loss": 1.0392,
1350
+ "step": 1870
1351
+ },
1352
+ {
1353
+ "epoch": 4.06926406926407,
1354
+ "grad_norm": 1.1761656999588013,
1355
+ "learning_rate": 0.0002,
1356
+ "loss": 1.1076,
1357
+ "step": 1880
1358
+ },
1359
+ {
1360
+ "epoch": 4.090909090909091,
1361
+ "grad_norm": 1.621068000793457,
1362
+ "learning_rate": 0.0002,
1363
+ "loss": 1.0813,
1364
+ "step": 1890
1365
+ },
1366
+ {
1367
+ "epoch": 4.112554112554113,
1368
+ "grad_norm": 1.7963402271270752,
1369
+ "learning_rate": 0.0002,
1370
+ "loss": 1.0849,
1371
+ "step": 1900
1372
+ },
1373
+ {
1374
+ "epoch": 4.134199134199134,
1375
+ "grad_norm": 1.682166337966919,
1376
+ "learning_rate": 0.0002,
1377
+ "loss": 1.115,
1378
+ "step": 1910
1379
+ },
1380
+ {
1381
+ "epoch": 4.1558441558441555,
1382
+ "grad_norm": 1.765175700187683,
1383
+ "learning_rate": 0.0002,
1384
+ "loss": 1.0142,
1385
+ "step": 1920
1386
+ },
1387
+ {
1388
+ "epoch": 4.177489177489178,
1389
+ "grad_norm": 1.7437595129013062,
1390
+ "learning_rate": 0.0002,
1391
+ "loss": 1.0237,
1392
+ "step": 1930
1393
+ },
1394
+ {
1395
+ "epoch": 4.199134199134199,
1396
+ "grad_norm": 1.487619400024414,
1397
+ "learning_rate": 0.0002,
1398
+ "loss": 1.1269,
1399
+ "step": 1940
1400
+ },
1401
+ {
1402
+ "epoch": 4.220779220779221,
1403
+ "grad_norm": 1.5726702213287354,
1404
+ "learning_rate": 0.0002,
1405
+ "loss": 1.1398,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 4.242424242424242,
1410
+ "grad_norm": 1.675681471824646,
1411
+ "learning_rate": 0.0002,
1412
+ "loss": 1.0203,
1413
+ "step": 1960
1414
+ },
1415
+ {
1416
+ "epoch": 4.264069264069264,
1417
+ "grad_norm": 1.5381293296813965,
1418
+ "learning_rate": 0.0002,
1419
+ "loss": 1.0001,
1420
+ "step": 1970
1421
+ },
1422
+ {
1423
+ "epoch": 4.285714285714286,
1424
+ "grad_norm": 1.6634043455123901,
1425
+ "learning_rate": 0.0002,
1426
+ "loss": 1.1608,
1427
+ "step": 1980
1428
+ },
1429
+ {
1430
+ "epoch": 4.307359307359308,
1431
+ "grad_norm": 1.4991868734359741,
1432
+ "learning_rate": 0.0002,
1433
+ "loss": 1.0914,
1434
+ "step": 1990
1435
+ },
1436
+ {
1437
+ "epoch": 4.329004329004329,
1438
+ "grad_norm": 1.7046575546264648,
1439
+ "learning_rate": 0.0002,
1440
+ "loss": 1.0208,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 4.35064935064935,
1445
+ "grad_norm": 1.8189613819122314,
1446
+ "learning_rate": 0.0002,
1447
+ "loss": 1.0671,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 4.372294372294372,
1452
+ "grad_norm": 1.7232930660247803,
1453
+ "learning_rate": 0.0002,
1454
+ "loss": 1.0771,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 4.393939393939394,
1459
+ "grad_norm": 2.037747859954834,
1460
+ "learning_rate": 0.0002,
1461
+ "loss": 1.0849,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 4.415584415584416,
1466
+ "grad_norm": 1.6157771348953247,
1467
+ "learning_rate": 0.0002,
1468
+ "loss": 1.0984,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 4.437229437229437,
1473
+ "grad_norm": 1.6834640502929688,
1474
+ "learning_rate": 0.0002,
1475
+ "loss": 1.0542,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 4.458874458874459,
1480
+ "grad_norm": 1.5155940055847168,
1481
+ "learning_rate": 0.0002,
1482
+ "loss": 1.1582,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 4.48051948051948,
1487
+ "grad_norm": 1.9364410638809204,
1488
+ "learning_rate": 0.0002,
1489
+ "loss": 1.1593,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.5021645021645025,
1494
+ "grad_norm": 1.512215256690979,
1495
+ "learning_rate": 0.0002,
1496
+ "loss": 1.1484,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 4.523809523809524,
1501
+ "grad_norm": 1.7659000158309937,
1502
+ "learning_rate": 0.0002,
1503
+ "loss": 1.0858,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 4.545454545454545,
1508
+ "grad_norm": 1.8038681745529175,
1509
+ "learning_rate": 0.0002,
1510
+ "loss": 1.1309,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 4.567099567099567,
1515
+ "grad_norm": 1.6234548091888428,
1516
+ "learning_rate": 0.0002,
1517
+ "loss": 1.1466,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 4.588744588744589,
1522
+ "grad_norm": 1.7181912660598755,
1523
+ "learning_rate": 0.0002,
1524
+ "loss": 1.1237,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 4.6103896103896105,
1529
+ "grad_norm": 1.5204529762268066,
1530
+ "learning_rate": 0.0002,
1531
+ "loss": 1.129,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 4.632034632034632,
1536
+ "grad_norm": 1.6626766920089722,
1537
+ "learning_rate": 0.0002,
1538
+ "loss": 1.1338,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 4.653679653679654,
1543
+ "grad_norm": 1.6722981929779053,
1544
+ "learning_rate": 0.0002,
1545
+ "loss": 1.1135,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 4.675324675324675,
1550
+ "grad_norm": 1.5929896831512451,
1551
+ "learning_rate": 0.0002,
1552
+ "loss": 1.1243,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 4.696969696969697,
1557
+ "grad_norm": 1.8637045621871948,
1558
+ "learning_rate": 0.0002,
1559
+ "loss": 1.1511,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 4.7186147186147185,
1564
+ "grad_norm": 1.7406965494155884,
1565
+ "learning_rate": 0.0002,
1566
+ "loss": 1.0816,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 4.740259740259741,
1571
+ "grad_norm": 1.9259464740753174,
1572
+ "learning_rate": 0.0002,
1573
+ "loss": 1.0913,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.761904761904762,
1578
+ "grad_norm": 1.5640064477920532,
1579
+ "learning_rate": 0.0002,
1580
+ "loss": 1.1273,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 4.783549783549784,
1585
+ "grad_norm": 1.5039080381393433,
1586
+ "learning_rate": 0.0002,
1587
+ "loss": 1.095,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 4.805194805194805,
1592
+ "grad_norm": 2.086487293243408,
1593
+ "learning_rate": 0.0002,
1594
+ "loss": 1.1082,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 4.8268398268398265,
1599
+ "grad_norm": 1.8213051557540894,
1600
+ "learning_rate": 0.0002,
1601
+ "loss": 1.1299,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 4.848484848484849,
1606
+ "grad_norm": 1.6772842407226562,
1607
+ "learning_rate": 0.0002,
1608
+ "loss": 1.1339,
1609
+ "step": 2240
1610
+ },
1611
+ {
1612
+ "epoch": 4.87012987012987,
1613
+ "grad_norm": 1.855952262878418,
1614
+ "learning_rate": 0.0002,
1615
+ "loss": 1.0688,
1616
+ "step": 2250
1617
+ },
1618
+ {
1619
+ "epoch": 4.891774891774892,
1620
+ "grad_norm": 1.703018069267273,
1621
+ "learning_rate": 0.0002,
1622
+ "loss": 1.1242,
1623
+ "step": 2260
1624
+ },
1625
+ {
1626
+ "epoch": 4.913419913419913,
1627
+ "grad_norm": 1.5779869556427002,
1628
+ "learning_rate": 0.0002,
1629
+ "loss": 1.1745,
1630
+ "step": 2270
1631
+ },
1632
+ {
1633
+ "epoch": 4.935064935064935,
1634
+ "grad_norm": 1.873153567314148,
1635
+ "learning_rate": 0.0002,
1636
+ "loss": 1.1367,
1637
+ "step": 2280
1638
+ },
1639
+ {
1640
+ "epoch": 4.956709956709957,
1641
+ "grad_norm": 1.845137119293213,
1642
+ "learning_rate": 0.0002,
1643
+ "loss": 1.1469,
1644
+ "step": 2290
1645
+ },
1646
+ {
1647
+ "epoch": 4.978354978354979,
1648
+ "grad_norm": 1.5848972797393799,
1649
+ "learning_rate": 0.0002,
1650
+ "loss": 1.176,
1651
+ "step": 2300
1652
+ },
1653
+ {
1654
+ "epoch": 5.0,
1655
+ "grad_norm": 1.7801740169525146,
1656
+ "learning_rate": 0.0002,
1657
+ "loss": 1.1427,
1658
+ "step": 2310
1659
+ },
1660
+ {
1661
+ "epoch": 5.0,
1662
+ "eval_loss": 2.1164023876190186,
1663
+ "eval_runtime": 138.8921,
1664
+ "eval_samples_per_second": 3.838,
1665
+ "eval_steps_per_second": 0.482,
1666
+ "step": 2310
1667
+ },
1668
+ {
1669
+ "epoch": 5.021645021645021,
1670
+ "grad_norm": 2.066721200942993,
1671
+ "learning_rate": 0.0002,
1672
+ "loss": 0.8797,
1673
+ "step": 2320
1674
+ },
1675
+ {
1676
+ "epoch": 5.043290043290043,
1677
+ "grad_norm": 2.151554822921753,
1678
+ "learning_rate": 0.0002,
1679
+ "loss": 0.8525,
1680
+ "step": 2330
1681
+ },
1682
+ {
1683
+ "epoch": 5.064935064935065,
1684
+ "grad_norm": 2.2179667949676514,
1685
+ "learning_rate": 0.0002,
1686
+ "loss": 0.8484,
1687
+ "step": 2340
1688
+ },
1689
+ {
1690
+ "epoch": 5.086580086580087,
1691
+ "grad_norm": 2.125246047973633,
1692
+ "learning_rate": 0.0002,
1693
+ "loss": 0.8321,
1694
+ "step": 2350
1695
+ },
1696
+ {
1697
+ "epoch": 5.108225108225108,
1698
+ "grad_norm": 2.4084312915802,
1699
+ "learning_rate": 0.0002,
1700
+ "loss": 0.7672,
1701
+ "step": 2360
1702
+ },
1703
+ {
1704
+ "epoch": 5.12987012987013,
1705
+ "grad_norm": 2.2142670154571533,
1706
+ "learning_rate": 0.0002,
1707
+ "loss": 0.8809,
1708
+ "step": 2370
1709
+ },
1710
+ {
1711
+ "epoch": 5.151515151515151,
1712
+ "grad_norm": 2.1560709476470947,
1713
+ "learning_rate": 0.0002,
1714
+ "loss": 0.9011,
1715
+ "step": 2380
1716
+ },
1717
+ {
1718
+ "epoch": 5.1731601731601735,
1719
+ "grad_norm": 1.8703010082244873,
1720
+ "learning_rate": 0.0002,
1721
+ "loss": 0.8028,
1722
+ "step": 2390
1723
+ },
1724
+ {
1725
+ "epoch": 5.194805194805195,
1726
+ "grad_norm": 1.8351138830184937,
1727
+ "learning_rate": 0.0002,
1728
+ "loss": 0.8215,
1729
+ "step": 2400
1730
+ },
1731
+ {
1732
+ "epoch": 5.216450216450216,
1733
+ "grad_norm": 2.173983573913574,
1734
+ "learning_rate": 0.0002,
1735
+ "loss": 0.8257,
1736
+ "step": 2410
1737
+ },
1738
+ {
1739
+ "epoch": 5.238095238095238,
1740
+ "grad_norm": 2.6962268352508545,
1741
+ "learning_rate": 0.0002,
1742
+ "loss": 0.8822,
1743
+ "step": 2420
1744
+ },
1745
+ {
1746
+ "epoch": 5.259740259740259,
1747
+ "grad_norm": 1.917742133140564,
1748
+ "learning_rate": 0.0002,
1749
+ "loss": 0.8879,
1750
+ "step": 2430
1751
+ },
1752
+ {
1753
+ "epoch": 5.2813852813852815,
1754
+ "grad_norm": 2.2485885620117188,
1755
+ "learning_rate": 0.0002,
1756
+ "loss": 0.8619,
1757
+ "step": 2440
1758
+ },
1759
+ {
1760
+ "epoch": 5.303030303030303,
1761
+ "grad_norm": 2.158888816833496,
1762
+ "learning_rate": 0.0002,
1763
+ "loss": 0.8841,
1764
+ "step": 2450
1765
+ },
1766
+ {
1767
+ "epoch": 5.324675324675325,
1768
+ "grad_norm": 2.187177896499634,
1769
+ "learning_rate": 0.0002,
1770
+ "loss": 0.8522,
1771
+ "step": 2460
1772
+ },
1773
+ {
1774
+ "epoch": 5.346320346320346,
1775
+ "grad_norm": 2.137540340423584,
1776
+ "learning_rate": 0.0002,
1777
+ "loss": 0.839,
1778
+ "step": 2470
1779
+ },
1780
+ {
1781
+ "epoch": 5.367965367965368,
1782
+ "grad_norm": 2.399334669113159,
1783
+ "learning_rate": 0.0002,
1784
+ "loss": 0.904,
1785
+ "step": 2480
1786
+ },
1787
+ {
1788
+ "epoch": 5.3896103896103895,
1789
+ "grad_norm": 2.04976749420166,
1790
+ "learning_rate": 0.0002,
1791
+ "loss": 0.8378,
1792
+ "step": 2490
1793
+ },
1794
+ {
1795
+ "epoch": 5.411255411255412,
1796
+ "grad_norm": 2.226628541946411,
1797
+ "learning_rate": 0.0002,
1798
+ "loss": 0.9134,
1799
+ "step": 2500
1800
+ },
1801
+ {
1802
+ "epoch": 5.432900432900433,
1803
+ "grad_norm": 1.9237712621688843,
1804
+ "learning_rate": 0.0002,
1805
+ "loss": 0.8879,
1806
+ "step": 2510
1807
+ },
1808
+ {
1809
+ "epoch": 5.454545454545454,
1810
+ "grad_norm": 2.0607564449310303,
1811
+ "learning_rate": 0.0002,
1812
+ "loss": 0.9233,
1813
+ "step": 2520
1814
+ },
1815
+ {
1816
+ "epoch": 5.476190476190476,
1817
+ "grad_norm": 2.0660619735717773,
1818
+ "learning_rate": 0.0002,
1819
+ "loss": 0.9363,
1820
+ "step": 2530
1821
+ },
1822
+ {
1823
+ "epoch": 5.4978354978354975,
1824
+ "grad_norm": 2.276259183883667,
1825
+ "learning_rate": 0.0002,
1826
+ "loss": 0.9041,
1827
+ "step": 2540
1828
+ },
1829
+ {
1830
+ "epoch": 5.51948051948052,
1831
+ "grad_norm": 2.2037975788116455,
1832
+ "learning_rate": 0.0002,
1833
+ "loss": 0.9227,
1834
+ "step": 2550
1835
+ },
1836
+ {
1837
+ "epoch": 5.541125541125541,
1838
+ "grad_norm": 2.0093777179718018,
1839
+ "learning_rate": 0.0002,
1840
+ "loss": 0.9183,
1841
+ "step": 2560
1842
+ },
1843
+ {
1844
+ "epoch": 5.562770562770563,
1845
+ "grad_norm": 1.7906461954116821,
1846
+ "learning_rate": 0.0002,
1847
+ "loss": 0.9106,
1848
+ "step": 2570
1849
+ },
1850
+ {
1851
+ "epoch": 5.584415584415584,
1852
+ "grad_norm": 2.3503541946411133,
1853
+ "learning_rate": 0.0002,
1854
+ "loss": 0.9136,
1855
+ "step": 2580
1856
+ },
1857
+ {
1858
+ "epoch": 5.606060606060606,
1859
+ "grad_norm": 1.9468884468078613,
1860
+ "learning_rate": 0.0002,
1861
+ "loss": 0.9194,
1862
+ "step": 2590
1863
+ },
1864
+ {
1865
+ "epoch": 5.627705627705628,
1866
+ "grad_norm": 2.4006402492523193,
1867
+ "learning_rate": 0.0002,
1868
+ "loss": 0.9215,
1869
+ "step": 2600
1870
+ },
1871
+ {
1872
+ "epoch": 5.64935064935065,
1873
+ "grad_norm": 2.1397976875305176,
1874
+ "learning_rate": 0.0002,
1875
+ "loss": 0.9575,
1876
+ "step": 2610
1877
+ },
1878
+ {
1879
+ "epoch": 5.670995670995671,
1880
+ "grad_norm": 2.331625461578369,
1881
+ "learning_rate": 0.0002,
1882
+ "loss": 0.9327,
1883
+ "step": 2620
1884
+ },
1885
+ {
1886
+ "epoch": 5.692640692640692,
1887
+ "grad_norm": 2.3320906162261963,
1888
+ "learning_rate": 0.0002,
1889
+ "loss": 0.9834,
1890
+ "step": 2630
1891
+ },
1892
+ {
1893
+ "epoch": 5.714285714285714,
1894
+ "grad_norm": 2.0336201190948486,
1895
+ "learning_rate": 0.0002,
1896
+ "loss": 0.8753,
1897
+ "step": 2640
1898
+ },
1899
+ {
1900
+ "epoch": 5.735930735930736,
1901
+ "grad_norm": 2.29776930809021,
1902
+ "learning_rate": 0.0002,
1903
+ "loss": 0.9356,
1904
+ "step": 2650
1905
+ },
1906
+ {
1907
+ "epoch": 5.757575757575758,
1908
+ "grad_norm": 2.0348799228668213,
1909
+ "learning_rate": 0.0002,
1910
+ "loss": 0.8807,
1911
+ "step": 2660
1912
+ },
1913
+ {
1914
+ "epoch": 5.779220779220779,
1915
+ "grad_norm": 2.993572235107422,
1916
+ "learning_rate": 0.0002,
1917
+ "loss": 0.9054,
1918
+ "step": 2670
1919
+ },
1920
+ {
1921
+ "epoch": 5.800865800865801,
1922
+ "grad_norm": 1.9768412113189697,
1923
+ "learning_rate": 0.0002,
1924
+ "loss": 0.9626,
1925
+ "step": 2680
1926
+ },
1927
+ {
1928
+ "epoch": 5.822510822510822,
1929
+ "grad_norm": 2.4398624897003174,
1930
+ "learning_rate": 0.0002,
1931
+ "loss": 0.9142,
1932
+ "step": 2690
1933
+ },
1934
+ {
1935
+ "epoch": 5.8441558441558445,
1936
+ "grad_norm": 1.9682047367095947,
1937
+ "learning_rate": 0.0002,
1938
+ "loss": 0.9422,
1939
+ "step": 2700
1940
+ },
1941
+ {
1942
+ "epoch": 5.865800865800866,
1943
+ "grad_norm": 2.1124305725097656,
1944
+ "learning_rate": 0.0002,
1945
+ "loss": 0.9564,
1946
+ "step": 2710
1947
+ },
1948
+ {
1949
+ "epoch": 5.887445887445887,
1950
+ "grad_norm": 2.2763118743896484,
1951
+ "learning_rate": 0.0002,
1952
+ "loss": 0.95,
1953
+ "step": 2720
1954
+ },
1955
+ {
1956
+ "epoch": 5.909090909090909,
1957
+ "grad_norm": 1.8851757049560547,
1958
+ "learning_rate": 0.0002,
1959
+ "loss": 0.9262,
1960
+ "step": 2730
1961
+ },
1962
+ {
1963
+ "epoch": 5.93073593073593,
1964
+ "grad_norm": 1.7605366706848145,
1965
+ "learning_rate": 0.0002,
1966
+ "loss": 0.8785,
1967
+ "step": 2740
1968
+ },
1969
+ {
1970
+ "epoch": 5.9523809523809526,
1971
+ "grad_norm": 2.063319683074951,
1972
+ "learning_rate": 0.0002,
1973
+ "loss": 0.9263,
1974
+ "step": 2750
1975
+ },
1976
+ {
1977
+ "epoch": 5.974025974025974,
1978
+ "grad_norm": 1.972980260848999,
1979
+ "learning_rate": 0.0002,
1980
+ "loss": 0.9285,
1981
+ "step": 2760
1982
+ },
1983
+ {
1984
+ "epoch": 5.995670995670996,
1985
+ "grad_norm": 2.29889178276062,
1986
+ "learning_rate": 0.0002,
1987
+ "loss": 0.9176,
1988
+ "step": 2770
1989
+ },
1990
+ {
1991
+ "epoch": 6.0,
1992
+ "eval_loss": 2.265646457672119,
1993
+ "eval_runtime": 137.3578,
1994
+ "eval_samples_per_second": 3.88,
1995
+ "eval_steps_per_second": 0.488,
1996
+ "step": 2772
1997
+ }
1998
+ ],
1999
+ "logging_steps": 10,
2000
+ "max_steps": 3696,
2001
+ "num_input_tokens_seen": 0,
2002
+ "num_train_epochs": 8,
2003
+ "save_steps": 200,
2004
+ "stateful_callbacks": {
2005
+ "TrainerControl": {
2006
+ "args": {
2007
+ "should_epoch_stop": false,
2008
+ "should_evaluate": false,
2009
+ "should_log": false,
2010
+ "should_save": true,
2011
+ "should_training_stop": false
2012
+ },
2013
+ "attributes": {}
2014
+ }
2015
+ },
2016
+ "total_flos": 1.216207424323584e+17,
2017
+ "train_batch_size": 1,
2018
+ "trial_name": null,
2019
+ "trial_params": null
2020
+ }