kaisser commited on
Commit
e2d1cf9
·
verified ·
1 Parent(s): 305a42c

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. lora_model/adapter_config.json +5 -5
  2. lora_model/adapter_model.safetensors +1 -1
  3. outputs/README.md +2 -2
  4. outputs/checkpoint-100/README.md +210 -0
  5. outputs/checkpoint-100/adapter_config.json +41 -0
  6. outputs/checkpoint-100/adapter_model.safetensors +3 -0
  7. outputs/checkpoint-100/chat_template.jinja +1 -0
  8. outputs/checkpoint-100/merges.txt +0 -0
  9. outputs/checkpoint-100/optimizer.pt +3 -0
  10. outputs/checkpoint-100/rng_state.pth +3 -0
  11. outputs/checkpoint-100/scaler.pt +3 -0
  12. outputs/checkpoint-100/scheduler.pt +3 -0
  13. outputs/checkpoint-100/special_tokens_map.json +30 -0
  14. outputs/checkpoint-100/tokenizer.json +0 -0
  15. outputs/checkpoint-100/tokenizer_config.json +790 -0
  16. outputs/checkpoint-100/trainer_state.json +734 -0
  17. outputs/checkpoint-100/training_args.bin +3 -0
  18. outputs/checkpoint-100/vocab.json +0 -0
  19. outputs/checkpoint-150/README.md +210 -0
  20. outputs/checkpoint-150/adapter_config.json +41 -0
  21. outputs/checkpoint-150/adapter_model.safetensors +3 -0
  22. outputs/checkpoint-150/chat_template.jinja +1 -0
  23. outputs/checkpoint-150/merges.txt +0 -0
  24. outputs/checkpoint-150/optimizer.pt +3 -0
  25. outputs/checkpoint-150/rng_state.pth +3 -0
  26. outputs/checkpoint-150/scaler.pt +3 -0
  27. outputs/checkpoint-150/scheduler.pt +3 -0
  28. outputs/checkpoint-150/special_tokens_map.json +30 -0
  29. outputs/checkpoint-150/tokenizer.json +0 -0
  30. outputs/checkpoint-150/tokenizer_config.json +790 -0
  31. outputs/checkpoint-150/trainer_state.json +1084 -0
  32. outputs/checkpoint-150/training_args.bin +3 -0
  33. outputs/checkpoint-150/vocab.json +0 -0
  34. unsloth_compiled_cache/UnslothAlignPropTrainer.py +2 -2
  35. unsloth_compiled_cache/UnslothBCOTrainer.py +2 -2
  36. unsloth_compiled_cache/UnslothCPOTrainer.py +2 -2
  37. unsloth_compiled_cache/UnslothDDPOTrainer.py +2 -2
  38. unsloth_compiled_cache/UnslothDPOTrainer.py +2 -2
  39. unsloth_compiled_cache/UnslothGKDTrainer.py +2 -2
  40. unsloth_compiled_cache/UnslothGRPOTrainer.py +2 -2
  41. unsloth_compiled_cache/UnslothIterativeSFTTrainer.py +2 -2
  42. unsloth_compiled_cache/UnslothKTOTrainer.py +2 -2
  43. unsloth_compiled_cache/UnslothNashMDTrainer.py +2 -2
  44. unsloth_compiled_cache/UnslothORPOTrainer.py +2 -2
  45. unsloth_compiled_cache/UnslothOnlineDPOTrainer.py +2 -2
  46. unsloth_compiled_cache/UnslothPPOTrainer.py +2 -2
  47. unsloth_compiled_cache/UnslothPRMTrainer.py +2 -2
  48. unsloth_compiled_cache/UnslothRLOOTrainer.py +2 -2
  49. unsloth_compiled_cache/UnslothRewardTrainer.py +2 -2
  50. unsloth_compiled_cache/UnslothSFTTrainer.py +2 -2
lora_model/adapter_config.json CHANGED
@@ -25,13 +25,13 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "down_proj",
29
- "o_proj",
30
- "v_proj",
31
- "k_proj",
32
  "q_proj",
 
 
33
  "gate_proj",
34
- "up_proj"
 
 
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
 
 
 
28
  "q_proj",
29
+ "k_proj",
30
+ "o_proj",
31
  "gate_proj",
32
+ "up_proj",
33
+ "v_proj",
34
+ "down_proj"
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
lora_model/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e2cd78c07327378efb3ad6d312d6fdefa045d6d07f92d4844c5617479b75d0a
3
  size 262219392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bddf678ba845612458f34c6ca85ce2a6f8397b743474b982faaf6158e3a65a
3
  size 262219392
outputs/README.md CHANGED
@@ -4,9 +4,9 @@ library_name: transformers
4
  model_name: outputs
5
  tags:
6
  - generated_from_trainer
7
- - unsloth
8
- - sft
9
  - trl
 
 
10
  licence: license
11
  ---
12
 
 
4
  model_name: outputs
5
  tags:
6
  - generated_from_trainer
 
 
7
  - trl
8
+ - sft
9
+ - unsloth
10
  licence: license
11
  ---
12
 
outputs/checkpoint-100/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/phi-4-unsloth-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/phi-4-unsloth-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.16.0
outputs/checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/phi-4-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "k_proj",
30
+ "o_proj",
31
+ "gate_proj",
32
+ "up_proj",
33
+ "v_proj",
34
+ "down_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_qalora": false,
40
+ "use_rslora": false
41
+ }
outputs/checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b4b147064df6474cfd066d841da1dbc3582f55f353e2886d175fdc45ec3f326
3
+ size 262219392
outputs/checkpoint-100/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}
outputs/checkpoint-100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
outputs/checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c02bf3d2e778068eedb5fd910b48d63943e28ecd23aeff777f0b49df5dc1901a
3
+ size 133777940
outputs/checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ae31f3bd6abd5e088309ad57fa2e995bc6dd61c02221bc158a3d63e6ad1f06
3
+ size 14244
outputs/checkpoint-100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4a558c5b93581a5c41e2922404490319bcd15a10296c927a72a41012ff7f27
3
+ size 988
outputs/checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
3
+ size 1064
outputs/checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|dummy_87|>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "�",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
outputs/checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
outputs/checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,790 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "5809": {
5
+ "content": "�",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100256": {
13
+ "content": "<|dummy_0|>",
14
+ "lstrip": true,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100257": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100258": {
29
+ "content": "<|fim_prefix|>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100259": {
37
+ "content": "<|fim_middle|>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100260": {
45
+ "content": "<|fim_suffix|>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100261": {
53
+ "content": "<|dummy_1|>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100262": {
61
+ "content": "<|dummy_2|>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100263": {
69
+ "content": "<|dummy_3|>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100264": {
77
+ "content": "<|im_start|>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100265": {
85
+ "content": "<|im_end|>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100266": {
93
+ "content": "<|im_sep|>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100267": {
101
+ "content": "<|dummy_4|>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100268": {
109
+ "content": "<|dummy_5|>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100269": {
117
+ "content": "<|dummy_6|>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100270": {
125
+ "content": "<|dummy_7|>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100271": {
133
+ "content": "<|dummy_8|>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100272": {
141
+ "content": "<|dummy_9|>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100273": {
149
+ "content": "<|dummy_10|>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100274": {
157
+ "content": "<|dummy_11|>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100275": {
165
+ "content": "<|dummy_12|>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100276": {
173
+ "content": "<|endofprompt|>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "100277": {
181
+ "content": "<|dummy_13|>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "100278": {
189
+ "content": "<|dummy_14|>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "100279": {
197
+ "content": "<|dummy_15|>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "100280": {
205
+ "content": "<|dummy_16|>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "100281": {
213
+ "content": "<|dummy_17|>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "100282": {
221
+ "content": "<|dummy_18|>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "100283": {
229
+ "content": "<|dummy_19|>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "100284": {
237
+ "content": "<|dummy_20|>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "100285": {
245
+ "content": "<|dummy_21|>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "100286": {
253
+ "content": "<|dummy_22|>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "100287": {
261
+ "content": "<|dummy_23|>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "100288": {
269
+ "content": "<|dummy_24|>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "100289": {
277
+ "content": "<|dummy_25|>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "100290": {
285
+ "content": "<|dummy_26|>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "100291": {
293
+ "content": "<|dummy_27|>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "100292": {
301
+ "content": "<|dummy_28|>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "100293": {
309
+ "content": "<|dummy_29|>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "100294": {
317
+ "content": "<|dummy_30|>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "100295": {
325
+ "content": "<|dummy_31|>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "100296": {
333
+ "content": "<|dummy_32|>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "100297": {
341
+ "content": "<|dummy_33|>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "100298": {
349
+ "content": "<|dummy_34|>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "100299": {
357
+ "content": "<|dummy_35|>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "100300": {
365
+ "content": "<|dummy_36|>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "100301": {
373
+ "content": "<|dummy_37|>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "100302": {
381
+ "content": "<|dummy_38|>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "100303": {
389
+ "content": "<|dummy_39|>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "100304": {
397
+ "content": "<|dummy_40|>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "100305": {
405
+ "content": "<|dummy_41|>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "100306": {
413
+ "content": "<|dummy_42|>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "100307": {
421
+ "content": "<|dummy_43|>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "100308": {
429
+ "content": "<|dummy_44|>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "100309": {
437
+ "content": "<|dummy_45|>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "100310": {
445
+ "content": "<|dummy_46|>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "100311": {
453
+ "content": "<|dummy_47|>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "100312": {
461
+ "content": "<|dummy_48|>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "100313": {
469
+ "content": "<|dummy_49|>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "100314": {
477
+ "content": "<|dummy_50|>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "100315": {
485
+ "content": "<|dummy_51|>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "100316": {
493
+ "content": "<|dummy_52|>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "100317": {
501
+ "content": "<|dummy_53|>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "100318": {
509
+ "content": "<|dummy_54|>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "100319": {
517
+ "content": "<|dummy_55|>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "100320": {
525
+ "content": "<|dummy_56|>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "100321": {
533
+ "content": "<|dummy_57|>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "100322": {
541
+ "content": "<|dummy_58|>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "100323": {
549
+ "content": "<|dummy_59|>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "100324": {
557
+ "content": "<|dummy_60|>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "100325": {
565
+ "content": "<|dummy_61|>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "100326": {
573
+ "content": "<|dummy_62|>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "100327": {
581
+ "content": "<|dummy_63|>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "100328": {
589
+ "content": "<|dummy_64|>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "100329": {
597
+ "content": "<|dummy_65|>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "100330": {
605
+ "content": "<|dummy_66|>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "100331": {
613
+ "content": "<|dummy_67|>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "100332": {
621
+ "content": "<|dummy_68|>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "100333": {
629
+ "content": "<|dummy_69|>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "100334": {
637
+ "content": "<|dummy_70|>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "100335": {
645
+ "content": "<|dummy_71|>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "100336": {
653
+ "content": "<|dummy_72|>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "100337": {
661
+ "content": "<|dummy_73|>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "100338": {
669
+ "content": "<|dummy_74|>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "100339": {
677
+ "content": "<|dummy_75|>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "100340": {
685
+ "content": "<|dummy_76|>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "100341": {
693
+ "content": "<|dummy_77|>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "100342": {
701
+ "content": "<|dummy_78|>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "100343": {
709
+ "content": "<|dummy_79|>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "100344": {
717
+ "content": "<|dummy_80|>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "100345": {
725
+ "content": "<|dummy_81|>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "100346": {
733
+ "content": "<|dummy_82|>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "100347": {
741
+ "content": "<|dummy_83|>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "100348": {
749
+ "content": "<|dummy_84|>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "100349": {
757
+ "content": "<|dummy_85|>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "100350": {
765
+ "content": "<|dummy_86|>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "100351": {
773
+ "content": "<|dummy_87|>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ }
780
+ },
781
+ "bos_token": "<|endoftext|>",
782
+ "clean_up_tokenization_spaces": false,
783
+ "eos_token": "<|im_end|>",
784
+ "extra_special_tokens": {},
785
+ "model_max_length": 16384,
786
+ "pad_token": "<|dummy_87|>",
787
+ "padding_side": "right",
788
+ "tokenizer_class": "GPT2Tokenizer",
789
+ "unk_token": "�"
790
+ }
outputs/checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02030456852791878,
14
+ "grad_norm": 0.2358761727809906,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.061,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.04060913705583756,
21
+ "grad_norm": 0.19159996509552002,
22
+ "learning_rate": 4e-05,
23
+ "loss": 0.8027,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.06091370558375635,
28
+ "grad_norm": 0.2133062779903412,
29
+ "learning_rate": 8e-05,
30
+ "loss": 0.9829,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.08121827411167512,
35
+ "grad_norm": 0.17393389344215393,
36
+ "learning_rate": 0.00012,
37
+ "loss": 0.9216,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.10152284263959391,
42
+ "grad_norm": 0.18812920153141022,
43
+ "learning_rate": 0.00016,
44
+ "loss": 0.9648,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.1218274111675127,
49
+ "grad_norm": 0.21234126389026642,
50
+ "learning_rate": 0.0002,
51
+ "loss": 0.9093,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.14213197969543148,
56
+ "grad_norm": 0.21176289021968842,
57
+ "learning_rate": 0.00019789473684210526,
58
+ "loss": 0.8466,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.16243654822335024,
63
+ "grad_norm": 0.28129369020462036,
64
+ "learning_rate": 0.00019578947368421054,
65
+ "loss": 0.9012,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.18274111675126903,
70
+ "grad_norm": 0.2939411699771881,
71
+ "learning_rate": 0.0001936842105263158,
72
+ "loss": 0.8235,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.20304568527918782,
77
+ "grad_norm": 0.24552834033966064,
78
+ "learning_rate": 0.00019157894736842104,
79
+ "loss": 1.0237,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.2233502538071066,
84
+ "grad_norm": 0.2185751348733902,
85
+ "learning_rate": 0.00018947368421052632,
86
+ "loss": 0.8512,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.2436548223350254,
91
+ "grad_norm": 0.2420736402273178,
92
+ "learning_rate": 0.0001873684210526316,
93
+ "loss": 0.781,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.2639593908629442,
98
+ "grad_norm": 0.25216007232666016,
99
+ "learning_rate": 0.00018526315789473685,
100
+ "loss": 0.8861,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.28426395939086296,
105
+ "grad_norm": 0.30759602785110474,
106
+ "learning_rate": 0.0001831578947368421,
107
+ "loss": 0.8343,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.30456852791878175,
112
+ "grad_norm": 0.24671927094459534,
113
+ "learning_rate": 0.00018105263157894739,
114
+ "loss": 0.7646,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.3248730964467005,
119
+ "grad_norm": 0.24498353898525238,
120
+ "learning_rate": 0.00017894736842105264,
121
+ "loss": 0.8954,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.34517766497461927,
126
+ "grad_norm": 0.2881005108356476,
127
+ "learning_rate": 0.0001768421052631579,
128
+ "loss": 0.7359,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.36548223350253806,
133
+ "grad_norm": 0.32868778705596924,
134
+ "learning_rate": 0.00017473684210526317,
135
+ "loss": 0.8019,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.38578680203045684,
140
+ "grad_norm": 0.31457120180130005,
141
+ "learning_rate": 0.00017263157894736842,
142
+ "loss": 0.7548,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.40609137055837563,
147
+ "grad_norm": 0.28515103459358215,
148
+ "learning_rate": 0.0001705263157894737,
149
+ "loss": 0.822,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.4263959390862944,
154
+ "grad_norm": 0.25426560640335083,
155
+ "learning_rate": 0.00016842105263157895,
156
+ "loss": 0.6463,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.4467005076142132,
161
+ "grad_norm": 0.31064561009407043,
162
+ "learning_rate": 0.00016631578947368423,
163
+ "loss": 0.7524,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.467005076142132,
168
+ "grad_norm": 0.32200193405151367,
169
+ "learning_rate": 0.00016421052631578948,
170
+ "loss": 0.7906,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.4873096446700508,
175
+ "grad_norm": 0.3093065023422241,
176
+ "learning_rate": 0.00016210526315789473,
177
+ "loss": 0.7202,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.5076142131979695,
182
+ "grad_norm": 0.26636677980422974,
183
+ "learning_rate": 0.00016,
184
+ "loss": 0.7524,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.5279187817258884,
189
+ "grad_norm": 0.27639704942703247,
190
+ "learning_rate": 0.00015789473684210527,
191
+ "loss": 0.7717,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.5482233502538071,
196
+ "grad_norm": 0.298368364572525,
197
+ "learning_rate": 0.00015578947368421052,
198
+ "loss": 0.7707,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.5685279187817259,
203
+ "grad_norm": 0.2771599292755127,
204
+ "learning_rate": 0.0001536842105263158,
205
+ "loss": 0.6989,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.5888324873096447,
210
+ "grad_norm": 0.3153183162212372,
211
+ "learning_rate": 0.00015157894736842108,
212
+ "loss": 0.8322,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.6091370558375635,
217
+ "grad_norm": 0.3349651098251343,
218
+ "learning_rate": 0.00014947368421052633,
219
+ "loss": 0.6446,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.6294416243654822,
224
+ "grad_norm": 0.2659667730331421,
225
+ "learning_rate": 0.00014736842105263158,
226
+ "loss": 0.5852,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.649746192893401,
231
+ "grad_norm": 0.33582568168640137,
232
+ "learning_rate": 0.00014526315789473686,
233
+ "loss": 0.71,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.6700507614213198,
238
+ "grad_norm": 0.34108102321624756,
239
+ "learning_rate": 0.0001431578947368421,
240
+ "loss": 0.66,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.6903553299492385,
245
+ "grad_norm": 0.29342642426490784,
246
+ "learning_rate": 0.00014105263157894736,
247
+ "loss": 0.6948,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.7106598984771574,
252
+ "grad_norm": 0.34535396099090576,
253
+ "learning_rate": 0.00013894736842105264,
254
+ "loss": 0.6553,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.7309644670050761,
259
+ "grad_norm": 0.2724352180957794,
260
+ "learning_rate": 0.0001368421052631579,
261
+ "loss": 0.6731,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.751269035532995,
266
+ "grad_norm": 0.39729994535446167,
267
+ "learning_rate": 0.00013473684210526317,
268
+ "loss": 0.762,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.7715736040609137,
273
+ "grad_norm": 0.35020238161087036,
274
+ "learning_rate": 0.00013263157894736842,
275
+ "loss": 0.5407,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.7918781725888325,
280
+ "grad_norm": 0.413173109292984,
281
+ "learning_rate": 0.0001305263157894737,
282
+ "loss": 0.7383,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.8121827411167513,
287
+ "grad_norm": 0.5108655691146851,
288
+ "learning_rate": 0.00012842105263157895,
289
+ "loss": 0.6093,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.8324873096446701,
294
+ "grad_norm": 0.38690420985221863,
295
+ "learning_rate": 0.0001263157894736842,
296
+ "loss": 0.6208,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.8527918781725888,
301
+ "grad_norm": 0.3925853669643402,
302
+ "learning_rate": 0.00012421052631578949,
303
+ "loss": 0.549,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.8730964467005076,
308
+ "grad_norm": 0.4626946747303009,
309
+ "learning_rate": 0.00012210526315789474,
310
+ "loss": 0.6687,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.8934010152284264,
315
+ "grad_norm": 0.3530731201171875,
316
+ "learning_rate": 0.00012,
317
+ "loss": 0.5182,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.9137055837563451,
322
+ "grad_norm": 0.4326516091823578,
323
+ "learning_rate": 0.00011789473684210525,
324
+ "loss": 0.6945,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.934010152284264,
329
+ "grad_norm": 0.3974042534828186,
330
+ "learning_rate": 0.00011578947368421053,
331
+ "loss": 0.5961,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.9543147208121827,
336
+ "grad_norm": 0.39741021394729614,
337
+ "learning_rate": 0.0001136842105263158,
338
+ "loss": 0.5913,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.9746192893401016,
343
+ "grad_norm": 0.41986003518104553,
344
+ "learning_rate": 0.00011157894736842105,
345
+ "loss": 0.6244,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.9949238578680203,
350
+ "grad_norm": 0.4072142541408539,
351
+ "learning_rate": 0.00010947368421052633,
352
+ "loss": 0.6412,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 1.0,
357
+ "grad_norm": 1.2582309246063232,
358
+ "learning_rate": 0.00010736842105263158,
359
+ "loss": 0.6974,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 1.0203045685279188,
364
+ "grad_norm": 0.5687114596366882,
365
+ "learning_rate": 0.00010526315789473685,
366
+ "loss": 0.5625,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 1.0406091370558375,
371
+ "grad_norm": 0.42633959650993347,
372
+ "learning_rate": 0.00010315789473684211,
373
+ "loss": 0.4151,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 1.0609137055837563,
378
+ "grad_norm": 0.4131942689418793,
379
+ "learning_rate": 0.00010105263157894738,
380
+ "loss": 0.4535,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.0812182741116751,
385
+ "grad_norm": 0.43178242444992065,
386
+ "learning_rate": 9.894736842105263e-05,
387
+ "loss": 0.5203,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.101522842639594,
392
+ "grad_norm": 0.6631357073783875,
393
+ "learning_rate": 9.68421052631579e-05,
394
+ "loss": 0.5942,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 1.1218274111675126,
399
+ "grad_norm": 0.5230205059051514,
400
+ "learning_rate": 9.473684210526316e-05,
401
+ "loss": 0.5493,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 1.1421319796954315,
406
+ "grad_norm": 0.4349292516708374,
407
+ "learning_rate": 9.263157894736843e-05,
408
+ "loss": 0.5118,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 1.1624365482233503,
413
+ "grad_norm": 0.4475697875022888,
414
+ "learning_rate": 9.052631578947369e-05,
415
+ "loss": 0.4895,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 1.1827411167512691,
420
+ "grad_norm": 0.4655645489692688,
421
+ "learning_rate": 8.842105263157894e-05,
422
+ "loss": 0.5282,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 1.2030456852791878,
427
+ "grad_norm": 0.5771047472953796,
428
+ "learning_rate": 8.631578947368421e-05,
429
+ "loss": 0.476,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 1.2233502538071066,
434
+ "grad_norm": 0.4800933003425598,
435
+ "learning_rate": 8.421052631578948e-05,
436
+ "loss": 0.4605,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 1.2436548223350254,
441
+ "grad_norm": 0.48124876618385315,
442
+ "learning_rate": 8.210526315789474e-05,
443
+ "loss": 0.4605,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 1.263959390862944,
448
+ "grad_norm": 0.56474769115448,
449
+ "learning_rate": 8e-05,
450
+ "loss": 0.483,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 1.284263959390863,
455
+ "grad_norm": 0.5908192992210388,
456
+ "learning_rate": 7.789473684210526e-05,
457
+ "loss": 0.4486,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 1.3045685279187818,
462
+ "grad_norm": 0.5335825085639954,
463
+ "learning_rate": 7.578947368421054e-05,
464
+ "loss": 0.4695,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 1.3248730964467006,
469
+ "grad_norm": 0.4991109073162079,
470
+ "learning_rate": 7.368421052631579e-05,
471
+ "loss": 0.4082,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 1.3451776649746192,
476
+ "grad_norm": 0.6000704169273376,
477
+ "learning_rate": 7.157894736842105e-05,
478
+ "loss": 0.4642,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 1.365482233502538,
483
+ "grad_norm": 0.4307476878166199,
484
+ "learning_rate": 6.947368421052632e-05,
485
+ "loss": 0.382,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 1.385786802030457,
490
+ "grad_norm": 0.49018386006355286,
491
+ "learning_rate": 6.736842105263159e-05,
492
+ "loss": 0.444,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 1.4060913705583755,
497
+ "grad_norm": 0.5581446290016174,
498
+ "learning_rate": 6.526315789473685e-05,
499
+ "loss": 0.3854,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 1.4263959390862944,
504
+ "grad_norm": 0.6309856176376343,
505
+ "learning_rate": 6.31578947368421e-05,
506
+ "loss": 0.4092,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 1.4467005076142132,
511
+ "grad_norm": 0.5829585790634155,
512
+ "learning_rate": 6.105263157894737e-05,
513
+ "loss": 0.482,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 1.467005076142132,
518
+ "grad_norm": 0.540630578994751,
519
+ "learning_rate": 5.894736842105263e-05,
520
+ "loss": 0.395,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 1.487309644670051,
525
+ "grad_norm": 0.5814833641052246,
526
+ "learning_rate": 5.68421052631579e-05,
527
+ "loss": 0.4509,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 1.5076142131979695,
532
+ "grad_norm": 0.5953724384307861,
533
+ "learning_rate": 5.4736842105263165e-05,
534
+ "loss": 0.4331,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 1.5279187817258884,
539
+ "grad_norm": 0.5561730265617371,
540
+ "learning_rate": 5.2631578947368424e-05,
541
+ "loss": 0.4325,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 1.548223350253807,
546
+ "grad_norm": 0.46784505248069763,
547
+ "learning_rate": 5.052631578947369e-05,
548
+ "loss": 0.3044,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 1.5685279187817258,
553
+ "grad_norm": 0.5854106545448303,
554
+ "learning_rate": 4.842105263157895e-05,
555
+ "loss": 0.4428,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 1.5888324873096447,
560
+ "grad_norm": 0.7446750998497009,
561
+ "learning_rate": 4.6315789473684214e-05,
562
+ "loss": 0.4597,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 1.6091370558375635,
567
+ "grad_norm": 0.6265136003494263,
568
+ "learning_rate": 4.421052631578947e-05,
569
+ "loss": 0.3621,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 1.6294416243654823,
574
+ "grad_norm": 0.5996136665344238,
575
+ "learning_rate": 4.210526315789474e-05,
576
+ "loss": 0.386,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 1.649746192893401,
581
+ "grad_norm": 0.4954428970813751,
582
+ "learning_rate": 4e-05,
583
+ "loss": 0.3964,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 1.6700507614213198,
588
+ "grad_norm": 0.5309467911720276,
589
+ "learning_rate": 3.789473684210527e-05,
590
+ "loss": 0.4182,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 1.6903553299492384,
595
+ "grad_norm": 0.6088101863861084,
596
+ "learning_rate": 3.578947368421053e-05,
597
+ "loss": 0.39,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 1.7106598984771573,
602
+ "grad_norm": 0.681597113609314,
603
+ "learning_rate": 3.368421052631579e-05,
604
+ "loss": 0.2925,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 1.7309644670050761,
609
+ "grad_norm": 0.6232784390449524,
610
+ "learning_rate": 3.157894736842105e-05,
611
+ "loss": 0.3687,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 1.751269035532995,
616
+ "grad_norm": 0.6489880084991455,
617
+ "learning_rate": 2.9473684210526314e-05,
618
+ "loss": 0.3535,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 1.7715736040609138,
623
+ "grad_norm": 0.5224277973175049,
624
+ "learning_rate": 2.7368421052631583e-05,
625
+ "loss": 0.352,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 1.7918781725888326,
630
+ "grad_norm": 0.6222900152206421,
631
+ "learning_rate": 2.5263157894736845e-05,
632
+ "loss": 0.3236,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 1.8121827411167513,
637
+ "grad_norm": 0.6584295034408569,
638
+ "learning_rate": 2.3157894736842107e-05,
639
+ "loss": 0.3383,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 1.83248730964467,
644
+ "grad_norm": 0.5199370980262756,
645
+ "learning_rate": 2.105263157894737e-05,
646
+ "loss": 0.2871,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 1.8527918781725887,
651
+ "grad_norm": 0.5921876430511475,
652
+ "learning_rate": 1.8947368421052634e-05,
653
+ "loss": 0.3826,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 1.8730964467005076,
658
+ "grad_norm": 0.6221027970314026,
659
+ "learning_rate": 1.6842105263157896e-05,
660
+ "loss": 0.3419,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 1.8934010152284264,
665
+ "grad_norm": 0.5613209009170532,
666
+ "learning_rate": 1.4736842105263157e-05,
667
+ "loss": 0.2796,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 1.9137055837563453,
672
+ "grad_norm": 0.5658890604972839,
673
+ "learning_rate": 1.2631578947368422e-05,
674
+ "loss": 0.3001,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 1.934010152284264,
679
+ "grad_norm": 0.7296081185340881,
680
+ "learning_rate": 1.0526315789473684e-05,
681
+ "loss": 0.3707,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 1.9543147208121827,
686
+ "grad_norm": 0.5506954789161682,
687
+ "learning_rate": 8.421052631578948e-06,
688
+ "loss": 0.3157,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 1.9746192893401016,
693
+ "grad_norm": 0.5977337956428528,
694
+ "learning_rate": 6.315789473684211e-06,
695
+ "loss": 0.3808,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 1.9949238578680202,
700
+ "grad_norm": 0.5295936465263367,
701
+ "learning_rate": 4.210526315789474e-06,
702
+ "loss": 0.3303,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 2.0,
707
+ "grad_norm": 1.224145770072937,
708
+ "learning_rate": 2.105263157894737e-06,
709
+ "loss": 0.163,
710
+ "step": 100
711
+ }
712
+ ],
713
+ "logging_steps": 1,
714
+ "max_steps": 100,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 2,
717
+ "save_steps": 500,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": true
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 4.935399135012864e+16,
731
+ "train_batch_size": 2,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
outputs/checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d956d14bf7ff00368bd8e3aacb0d3f72235247bdd9605a63a60ac1bab96833ad
3
+ size 5688
outputs/checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
outputs/checkpoint-150/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/phi-4-unsloth-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/phi-4-unsloth-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.16.0
outputs/checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/phi-4-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "k_proj",
30
+ "o_proj",
31
+ "gate_proj",
32
+ "up_proj",
33
+ "v_proj",
34
+ "down_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_qalora": false,
40
+ "use_rslora": false
41
+ }
outputs/checkpoint-150/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bddf678ba845612458f34c6ca85ce2a6f8397b743474b982faaf6158e3a65a
3
+ size 262219392
outputs/checkpoint-150/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}
outputs/checkpoint-150/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
outputs/checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2a34f68da09a66cbc37b6ad9f57642ee2a15aea14f1e6afce19f45f6e88717
3
+ size 133777940
outputs/checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7ecf15e83ac4d18e0d90f8a44821af2f304313a6ae05eeb21767226a79c463
3
+ size 14244
outputs/checkpoint-150/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da800fd5ac660f36778294f9df633c4f039b5f7bde42ca6a92dea5ac7d9666b1
3
+ size 988
outputs/checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194456d3c9e165255d5406a0f3f62973b0bede79d91784f72431350783e27ae7
3
+ size 1064
outputs/checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|dummy_87|>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "�",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
outputs/checkpoint-150/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
outputs/checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,790 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "5809": {
5
+ "content": "�",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100256": {
13
+ "content": "<|dummy_0|>",
14
+ "lstrip": true,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100257": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100258": {
29
+ "content": "<|fim_prefix|>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100259": {
37
+ "content": "<|fim_middle|>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100260": {
45
+ "content": "<|fim_suffix|>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100261": {
53
+ "content": "<|dummy_1|>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100262": {
61
+ "content": "<|dummy_2|>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100263": {
69
+ "content": "<|dummy_3|>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100264": {
77
+ "content": "<|im_start|>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100265": {
85
+ "content": "<|im_end|>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100266": {
93
+ "content": "<|im_sep|>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100267": {
101
+ "content": "<|dummy_4|>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100268": {
109
+ "content": "<|dummy_5|>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100269": {
117
+ "content": "<|dummy_6|>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100270": {
125
+ "content": "<|dummy_7|>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100271": {
133
+ "content": "<|dummy_8|>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100272": {
141
+ "content": "<|dummy_9|>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100273": {
149
+ "content": "<|dummy_10|>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100274": {
157
+ "content": "<|dummy_11|>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100275": {
165
+ "content": "<|dummy_12|>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100276": {
173
+ "content": "<|endofprompt|>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "100277": {
181
+ "content": "<|dummy_13|>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "100278": {
189
+ "content": "<|dummy_14|>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "100279": {
197
+ "content": "<|dummy_15|>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "100280": {
205
+ "content": "<|dummy_16|>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "100281": {
213
+ "content": "<|dummy_17|>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "100282": {
221
+ "content": "<|dummy_18|>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "100283": {
229
+ "content": "<|dummy_19|>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "100284": {
237
+ "content": "<|dummy_20|>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "100285": {
245
+ "content": "<|dummy_21|>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "100286": {
253
+ "content": "<|dummy_22|>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "100287": {
261
+ "content": "<|dummy_23|>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "100288": {
269
+ "content": "<|dummy_24|>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "100289": {
277
+ "content": "<|dummy_25|>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "100290": {
285
+ "content": "<|dummy_26|>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "100291": {
293
+ "content": "<|dummy_27|>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "100292": {
301
+ "content": "<|dummy_28|>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "100293": {
309
+ "content": "<|dummy_29|>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "100294": {
317
+ "content": "<|dummy_30|>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "100295": {
325
+ "content": "<|dummy_31|>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "100296": {
333
+ "content": "<|dummy_32|>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "100297": {
341
+ "content": "<|dummy_33|>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "100298": {
349
+ "content": "<|dummy_34|>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "100299": {
357
+ "content": "<|dummy_35|>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "100300": {
365
+ "content": "<|dummy_36|>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "100301": {
373
+ "content": "<|dummy_37|>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "100302": {
381
+ "content": "<|dummy_38|>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "100303": {
389
+ "content": "<|dummy_39|>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "100304": {
397
+ "content": "<|dummy_40|>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "100305": {
405
+ "content": "<|dummy_41|>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "100306": {
413
+ "content": "<|dummy_42|>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "100307": {
421
+ "content": "<|dummy_43|>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "100308": {
429
+ "content": "<|dummy_44|>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "100309": {
437
+ "content": "<|dummy_45|>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "100310": {
445
+ "content": "<|dummy_46|>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "100311": {
453
+ "content": "<|dummy_47|>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "100312": {
461
+ "content": "<|dummy_48|>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "100313": {
469
+ "content": "<|dummy_49|>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "100314": {
477
+ "content": "<|dummy_50|>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "100315": {
485
+ "content": "<|dummy_51|>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "100316": {
493
+ "content": "<|dummy_52|>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "100317": {
501
+ "content": "<|dummy_53|>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "100318": {
509
+ "content": "<|dummy_54|>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "100319": {
517
+ "content": "<|dummy_55|>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "100320": {
525
+ "content": "<|dummy_56|>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "100321": {
533
+ "content": "<|dummy_57|>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "100322": {
541
+ "content": "<|dummy_58|>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "100323": {
549
+ "content": "<|dummy_59|>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "100324": {
557
+ "content": "<|dummy_60|>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "100325": {
565
+ "content": "<|dummy_61|>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "100326": {
573
+ "content": "<|dummy_62|>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "100327": {
581
+ "content": "<|dummy_63|>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "100328": {
589
+ "content": "<|dummy_64|>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "100329": {
597
+ "content": "<|dummy_65|>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "100330": {
605
+ "content": "<|dummy_66|>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "100331": {
613
+ "content": "<|dummy_67|>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "100332": {
621
+ "content": "<|dummy_68|>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "100333": {
629
+ "content": "<|dummy_69|>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "100334": {
637
+ "content": "<|dummy_70|>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "100335": {
645
+ "content": "<|dummy_71|>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "100336": {
653
+ "content": "<|dummy_72|>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "100337": {
661
+ "content": "<|dummy_73|>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "100338": {
669
+ "content": "<|dummy_74|>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "100339": {
677
+ "content": "<|dummy_75|>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "100340": {
685
+ "content": "<|dummy_76|>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "100341": {
693
+ "content": "<|dummy_77|>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "100342": {
701
+ "content": "<|dummy_78|>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "100343": {
709
+ "content": "<|dummy_79|>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "100344": {
717
+ "content": "<|dummy_80|>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "100345": {
725
+ "content": "<|dummy_81|>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "100346": {
733
+ "content": "<|dummy_82|>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "100347": {
741
+ "content": "<|dummy_83|>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "100348": {
749
+ "content": "<|dummy_84|>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "100349": {
757
+ "content": "<|dummy_85|>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "100350": {
765
+ "content": "<|dummy_86|>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "100351": {
773
+ "content": "<|dummy_87|>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ }
780
+ },
781
+ "bos_token": "<|endoftext|>",
782
+ "clean_up_tokenization_spaces": false,
783
+ "eos_token": "<|im_end|>",
784
+ "extra_special_tokens": {},
785
+ "model_max_length": 16384,
786
+ "pad_token": "<|dummy_87|>",
787
+ "padding_side": "right",
788
+ "tokenizer_class": "GPT2Tokenizer",
789
+ "unk_token": "�"
790
+ }
outputs/checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,1084 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 150,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02030456852791878,
14
+ "grad_norm": 0.46351274847984314,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.0912,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.04060913705583756,
21
+ "grad_norm": 0.3804264962673187,
22
+ "learning_rate": 6.666666666666667e-05,
23
+ "loss": 0.1072,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.06091370558375635,
28
+ "grad_norm": 0.5822153091430664,
29
+ "learning_rate": 0.00013333333333333334,
30
+ "loss": 0.0922,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.08121827411167512,
35
+ "grad_norm": 1.0116138458251953,
36
+ "learning_rate": 0.0002,
37
+ "loss": 0.1168,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.10152284263959391,
42
+ "grad_norm": 1.267458200454712,
43
+ "learning_rate": 0.00019863945578231293,
44
+ "loss": 0.1606,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.1218274111675127,
49
+ "grad_norm": 0.9032717943191528,
50
+ "learning_rate": 0.00019727891156462587,
51
+ "loss": 0.1262,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.14213197969543148,
56
+ "grad_norm": 0.8178703784942627,
57
+ "learning_rate": 0.0001959183673469388,
58
+ "loss": 0.1642,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.16243654822335024,
63
+ "grad_norm": 0.901324450969696,
64
+ "learning_rate": 0.0001945578231292517,
65
+ "loss": 0.1902,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.18274111675126903,
70
+ "grad_norm": 0.7721088528633118,
71
+ "learning_rate": 0.00019319727891156462,
72
+ "loss": 0.1508,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.20304568527918782,
77
+ "grad_norm": 0.7926129698753357,
78
+ "learning_rate": 0.00019183673469387756,
79
+ "loss": 0.2247,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.2233502538071066,
84
+ "grad_norm": 0.68562251329422,
85
+ "learning_rate": 0.00019047619047619048,
86
+ "loss": 0.2178,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.2436548223350254,
91
+ "grad_norm": 0.697933554649353,
92
+ "learning_rate": 0.00018911564625850343,
93
+ "loss": 0.1753,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.2639593908629442,
98
+ "grad_norm": 0.8777951598167419,
99
+ "learning_rate": 0.00018775510204081634,
100
+ "loss": 0.212,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.28426395939086296,
105
+ "grad_norm": 1.0281987190246582,
106
+ "learning_rate": 0.00018639455782312926,
107
+ "loss": 0.2235,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.30456852791878175,
112
+ "grad_norm": 0.7087022662162781,
113
+ "learning_rate": 0.0001850340136054422,
114
+ "loss": 0.1557,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.3248730964467005,
119
+ "grad_norm": 0.6727551221847534,
120
+ "learning_rate": 0.00018367346938775512,
121
+ "loss": 0.1908,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.34517766497461927,
126
+ "grad_norm": 0.5988404154777527,
127
+ "learning_rate": 0.00018231292517006804,
128
+ "loss": 0.1426,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.36548223350253806,
133
+ "grad_norm": 0.7992706894874573,
134
+ "learning_rate": 0.00018095238095238095,
135
+ "loss": 0.1926,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.38578680203045684,
140
+ "grad_norm": 0.6529021263122559,
141
+ "learning_rate": 0.0001795918367346939,
142
+ "loss": 0.1241,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.40609137055837563,
147
+ "grad_norm": 0.7720218896865845,
148
+ "learning_rate": 0.00017823129251700681,
149
+ "loss": 0.2345,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.4263959390862944,
154
+ "grad_norm": 0.5576862096786499,
155
+ "learning_rate": 0.00017687074829931973,
156
+ "loss": 0.1406,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.4467005076142132,
161
+ "grad_norm": 0.9700397849082947,
162
+ "learning_rate": 0.00017551020408163265,
163
+ "loss": 0.2808,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.467005076142132,
168
+ "grad_norm": 0.8212639689445496,
169
+ "learning_rate": 0.0001741496598639456,
170
+ "loss": 0.2432,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.4873096446700508,
175
+ "grad_norm": 0.6683560609817505,
176
+ "learning_rate": 0.0001727891156462585,
177
+ "loss": 0.1759,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.5076142131979695,
182
+ "grad_norm": 0.7638088464736938,
183
+ "learning_rate": 0.00017142857142857143,
184
+ "loss": 0.2277,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.5279187817258884,
189
+ "grad_norm": 0.7591285705566406,
190
+ "learning_rate": 0.00017006802721088434,
191
+ "loss": 0.2083,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.5482233502538071,
196
+ "grad_norm": 0.9049777388572693,
197
+ "learning_rate": 0.00016870748299319729,
198
+ "loss": 0.2989,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.5685279187817259,
203
+ "grad_norm": 0.5733493566513062,
204
+ "learning_rate": 0.00016734693877551023,
205
+ "loss": 0.1467,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.5888324873096447,
210
+ "grad_norm": 0.8058221936225891,
211
+ "learning_rate": 0.00016598639455782315,
212
+ "loss": 0.2024,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.6091370558375635,
217
+ "grad_norm": 0.692622721195221,
218
+ "learning_rate": 0.00016462585034013606,
219
+ "loss": 0.1531,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.6294416243654822,
224
+ "grad_norm": 0.5021050572395325,
225
+ "learning_rate": 0.00016326530612244898,
226
+ "loss": 0.1473,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.649746192893401,
231
+ "grad_norm": 0.672785758972168,
232
+ "learning_rate": 0.00016190476190476192,
233
+ "loss": 0.1829,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.6700507614213198,
238
+ "grad_norm": 0.8167020082473755,
239
+ "learning_rate": 0.00016054421768707484,
240
+ "loss": 0.1914,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.6903553299492385,
245
+ "grad_norm": 0.6360740661621094,
246
+ "learning_rate": 0.00015918367346938776,
247
+ "loss": 0.1589,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.7106598984771574,
252
+ "grad_norm": 0.7196878790855408,
253
+ "learning_rate": 0.00015782312925170067,
254
+ "loss": 0.1543,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.7309644670050761,
259
+ "grad_norm": 0.49419939517974854,
260
+ "learning_rate": 0.00015646258503401362,
261
+ "loss": 0.0999,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.751269035532995,
266
+ "grad_norm": 0.8485663533210754,
267
+ "learning_rate": 0.00015510204081632654,
268
+ "loss": 0.1598,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.7715736040609137,
273
+ "grad_norm": 0.6495020985603333,
274
+ "learning_rate": 0.00015374149659863945,
275
+ "loss": 0.1036,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.7918781725888325,
280
+ "grad_norm": 0.8282960057258606,
281
+ "learning_rate": 0.00015238095238095237,
282
+ "loss": 0.1944,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.8121827411167513,
287
+ "grad_norm": 0.8367117047309875,
288
+ "learning_rate": 0.0001510204081632653,
289
+ "loss": 0.1404,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.8324873096446701,
294
+ "grad_norm": 0.5914992690086365,
295
+ "learning_rate": 0.00014965986394557826,
296
+ "loss": 0.1084,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.8527918781725888,
301
+ "grad_norm": 0.6257866621017456,
302
+ "learning_rate": 0.00014829931972789117,
303
+ "loss": 0.1085,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.8730964467005076,
308
+ "grad_norm": 0.8163577914237976,
309
+ "learning_rate": 0.0001469387755102041,
310
+ "loss": 0.1506,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.8934010152284264,
315
+ "grad_norm": 0.4754215478897095,
316
+ "learning_rate": 0.000145578231292517,
317
+ "loss": 0.0887,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.9137055837563451,
322
+ "grad_norm": 0.6383790969848633,
323
+ "learning_rate": 0.00014421768707482995,
324
+ "loss": 0.1118,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.934010152284264,
329
+ "grad_norm": 0.6515761613845825,
330
+ "learning_rate": 0.00014285714285714287,
331
+ "loss": 0.1154,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.9543147208121827,
336
+ "grad_norm": 0.6699874401092529,
337
+ "learning_rate": 0.00014149659863945578,
338
+ "loss": 0.104,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.9746192893401016,
343
+ "grad_norm": 0.6663119196891785,
344
+ "learning_rate": 0.0001401360544217687,
345
+ "loss": 0.1103,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.9949238578680203,
350
+ "grad_norm": 0.5753883123397827,
351
+ "learning_rate": 0.00013877551020408165,
352
+ "loss": 0.0831,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 1.0,
357
+ "grad_norm": 1.9068312644958496,
358
+ "learning_rate": 0.00013741496598639456,
359
+ "loss": 0.054,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 1.0203045685279188,
364
+ "grad_norm": 0.546940803527832,
365
+ "learning_rate": 0.00013605442176870748,
366
+ "loss": 0.0652,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 1.0406091370558375,
371
+ "grad_norm": 0.4074535369873047,
372
+ "learning_rate": 0.0001346938775510204,
373
+ "loss": 0.0447,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 1.0609137055837563,
378
+ "grad_norm": 0.3076671063899994,
379
+ "learning_rate": 0.00013333333333333334,
380
+ "loss": 0.0401,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.0812182741116751,
385
+ "grad_norm": 0.4675501585006714,
386
+ "learning_rate": 0.00013197278911564626,
387
+ "loss": 0.0576,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.101522842639594,
392
+ "grad_norm": 0.4893474876880646,
393
+ "learning_rate": 0.00013061224489795917,
394
+ "loss": 0.0506,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 1.1218274111675126,
399
+ "grad_norm": 0.5409421920776367,
400
+ "learning_rate": 0.00012925170068027212,
401
+ "loss": 0.0557,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 1.1421319796954315,
406
+ "grad_norm": 0.44050920009613037,
407
+ "learning_rate": 0.00012789115646258506,
408
+ "loss": 0.0503,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 1.1624365482233503,
413
+ "grad_norm": 0.3851899206638336,
414
+ "learning_rate": 0.00012653061224489798,
415
+ "loss": 0.0406,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 1.1827411167512691,
420
+ "grad_norm": 0.3573797047138214,
421
+ "learning_rate": 0.0001251700680272109,
422
+ "loss": 0.0357,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 1.2030456852791878,
427
+ "grad_norm": 0.5621812343597412,
428
+ "learning_rate": 0.0001238095238095238,
429
+ "loss": 0.0402,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 1.2233502538071066,
434
+ "grad_norm": 0.3651388883590698,
435
+ "learning_rate": 0.00012244897959183676,
436
+ "loss": 0.0357,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 1.2436548223350254,
441
+ "grad_norm": 0.31054311990737915,
442
+ "learning_rate": 0.00012108843537414967,
443
+ "loss": 0.0335,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 1.263959390862944,
448
+ "grad_norm": 0.4868326485157013,
449
+ "learning_rate": 0.00011972789115646259,
450
+ "loss": 0.0466,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 1.284263959390863,
455
+ "grad_norm": 0.4604259133338928,
456
+ "learning_rate": 0.00011836734693877552,
457
+ "loss": 0.039,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 1.3045685279187818,
462
+ "grad_norm": 0.4411635100841522,
463
+ "learning_rate": 0.00011700680272108844,
464
+ "loss": 0.0426,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 1.3248730964467006,
469
+ "grad_norm": 0.3887002766132355,
470
+ "learning_rate": 0.00011564625850340137,
471
+ "loss": 0.0297,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 1.3451776649746192,
476
+ "grad_norm": 0.5058308243751526,
477
+ "learning_rate": 0.00011428571428571428,
478
+ "loss": 0.0438,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 1.365482233502538,
483
+ "grad_norm": 0.5483447313308716,
484
+ "learning_rate": 0.00011292517006802721,
485
+ "loss": 0.0596,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 1.385786802030457,
490
+ "grad_norm": 0.3938705325126648,
491
+ "learning_rate": 0.00011156462585034013,
492
+ "loss": 0.0378,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 1.4060913705583755,
497
+ "grad_norm": 0.39620518684387207,
498
+ "learning_rate": 0.00011020408163265306,
499
+ "loss": 0.0372,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 1.4263959390862944,
504
+ "grad_norm": 0.4564354121685028,
505
+ "learning_rate": 0.000108843537414966,
506
+ "loss": 0.038,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 1.4467005076142132,
511
+ "grad_norm": 0.6096150875091553,
512
+ "learning_rate": 0.00010748299319727892,
513
+ "loss": 0.0589,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 1.467005076142132,
518
+ "grad_norm": 0.4684588313102722,
519
+ "learning_rate": 0.00010612244897959185,
520
+ "loss": 0.0334,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 1.487309644670051,
525
+ "grad_norm": 0.49702298641204834,
526
+ "learning_rate": 0.00010476190476190477,
527
+ "loss": 0.0507,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 1.5076142131979695,
532
+ "grad_norm": 0.3441038131713867,
533
+ "learning_rate": 0.0001034013605442177,
534
+ "loss": 0.0313,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 1.5279187817258884,
539
+ "grad_norm": 0.28676465153694153,
540
+ "learning_rate": 0.00010204081632653062,
541
+ "loss": 0.0248,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 1.548223350253807,
546
+ "grad_norm": 0.3125196099281311,
547
+ "learning_rate": 0.00010068027210884355,
548
+ "loss": 0.0331,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 1.5685279187817258,
553
+ "grad_norm": 0.3866737484931946,
554
+ "learning_rate": 9.931972789115646e-05,
555
+ "loss": 0.0457,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 1.5888324873096447,
560
+ "grad_norm": 0.38057267665863037,
561
+ "learning_rate": 9.79591836734694e-05,
562
+ "loss": 0.0361,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 1.6091370558375635,
567
+ "grad_norm": 0.3501664400100708,
568
+ "learning_rate": 9.659863945578231e-05,
569
+ "loss": 0.0266,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 1.6294416243654823,
574
+ "grad_norm": 0.3670511543750763,
575
+ "learning_rate": 9.523809523809524e-05,
576
+ "loss": 0.041,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 1.649746192893401,
581
+ "grad_norm": 0.22293201088905334,
582
+ "learning_rate": 9.387755102040817e-05,
583
+ "loss": 0.0242,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 1.6700507614213198,
588
+ "grad_norm": 0.19051635265350342,
589
+ "learning_rate": 9.25170068027211e-05,
590
+ "loss": 0.0198,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 1.6903553299492384,
595
+ "grad_norm": 0.3275824785232544,
596
+ "learning_rate": 9.115646258503402e-05,
597
+ "loss": 0.0253,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 1.7106598984771573,
602
+ "grad_norm": 0.2463853657245636,
603
+ "learning_rate": 8.979591836734695e-05,
604
+ "loss": 0.0173,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 1.7309644670050761,
609
+ "grad_norm": 0.36210179328918457,
610
+ "learning_rate": 8.843537414965987e-05,
611
+ "loss": 0.0243,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 1.751269035532995,
616
+ "grad_norm": 0.36934608221054077,
617
+ "learning_rate": 8.70748299319728e-05,
618
+ "loss": 0.0291,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 1.7715736040609138,
623
+ "grad_norm": 0.2966545820236206,
624
+ "learning_rate": 8.571428571428571e-05,
625
+ "loss": 0.0274,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 1.7918781725888326,
630
+ "grad_norm": 0.41154393553733826,
631
+ "learning_rate": 8.435374149659864e-05,
632
+ "loss": 0.0208,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 1.8121827411167513,
637
+ "grad_norm": 0.3862360715866089,
638
+ "learning_rate": 8.299319727891157e-05,
639
+ "loss": 0.0321,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 1.83248730964467,
644
+ "grad_norm": 0.2056417316198349,
645
+ "learning_rate": 8.163265306122449e-05,
646
+ "loss": 0.0171,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 1.8527918781725887,
651
+ "grad_norm": 0.2836405336856842,
652
+ "learning_rate": 8.027210884353742e-05,
653
+ "loss": 0.0227,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 1.8730964467005076,
658
+ "grad_norm": 0.2541104853153229,
659
+ "learning_rate": 7.891156462585034e-05,
660
+ "loss": 0.0199,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 1.8934010152284264,
665
+ "grad_norm": 0.2865837514400482,
666
+ "learning_rate": 7.755102040816327e-05,
667
+ "loss": 0.023,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 1.9137055837563453,
672
+ "grad_norm": 0.34340551495552063,
673
+ "learning_rate": 7.619047619047618e-05,
674
+ "loss": 0.0233,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 1.934010152284264,
679
+ "grad_norm": 0.31388527154922485,
680
+ "learning_rate": 7.482993197278913e-05,
681
+ "loss": 0.0206,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 1.9543147208121827,
686
+ "grad_norm": 0.22681647539138794,
687
+ "learning_rate": 7.346938775510205e-05,
688
+ "loss": 0.0187,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 1.9746192893401016,
693
+ "grad_norm": 0.24601863324642181,
694
+ "learning_rate": 7.210884353741498e-05,
695
+ "loss": 0.0219,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 1.9949238578680202,
700
+ "grad_norm": 0.21390770375728607,
701
+ "learning_rate": 7.074829931972789e-05,
702
+ "loss": 0.0155,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 2.0,
707
+ "grad_norm": 0.5080230832099915,
708
+ "learning_rate": 6.938775510204082e-05,
709
+ "loss": 0.0123,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 2.020304568527919,
714
+ "grad_norm": 0.17045630514621735,
715
+ "learning_rate": 6.802721088435374e-05,
716
+ "loss": 0.0114,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 2.0406091370558377,
721
+ "grad_norm": 0.2537500560283661,
722
+ "learning_rate": 6.666666666666667e-05,
723
+ "loss": 0.013,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 2.0609137055837565,
728
+ "grad_norm": 0.2204536497592926,
729
+ "learning_rate": 6.530612244897959e-05,
730
+ "loss": 0.0115,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 2.081218274111675,
735
+ "grad_norm": 0.15217559039592743,
736
+ "learning_rate": 6.394557823129253e-05,
737
+ "loss": 0.0121,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 2.1015228426395938,
742
+ "grad_norm": 0.13445383310317993,
743
+ "learning_rate": 6.258503401360545e-05,
744
+ "loss": 0.0122,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 2.1218274111675126,
749
+ "grad_norm": 0.22312460839748383,
750
+ "learning_rate": 6.122448979591838e-05,
751
+ "loss": 0.0172,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 2.1421319796954315,
756
+ "grad_norm": 0.15204404294490814,
757
+ "learning_rate": 5.9863945578231295e-05,
758
+ "loss": 0.0104,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 2.1624365482233503,
763
+ "grad_norm": 0.11004563421010971,
764
+ "learning_rate": 5.850340136054422e-05,
765
+ "loss": 0.0108,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 2.182741116751269,
770
+ "grad_norm": 0.18134009838104248,
771
+ "learning_rate": 5.714285714285714e-05,
772
+ "loss": 0.0114,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 2.203045685279188,
777
+ "grad_norm": 0.31723207235336304,
778
+ "learning_rate": 5.5782312925170065e-05,
779
+ "loss": 0.0168,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 2.223350253807107,
784
+ "grad_norm": 0.1572827845811844,
785
+ "learning_rate": 5.4421768707483e-05,
786
+ "loss": 0.013,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 2.2436548223350252,
791
+ "grad_norm": 0.16151772439479828,
792
+ "learning_rate": 5.3061224489795926e-05,
793
+ "loss": 0.0091,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 2.263959390862944,
798
+ "grad_norm": 0.1043572872877121,
799
+ "learning_rate": 5.170068027210885e-05,
800
+ "loss": 0.0089,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 2.284263959390863,
805
+ "grad_norm": 0.14589852094650269,
806
+ "learning_rate": 5.034013605442177e-05,
807
+ "loss": 0.0106,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 2.3045685279187818,
812
+ "grad_norm": 0.14490854740142822,
813
+ "learning_rate": 4.89795918367347e-05,
814
+ "loss": 0.0091,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 2.3248730964467006,
819
+ "grad_norm": 0.2695333659648895,
820
+ "learning_rate": 4.761904761904762e-05,
821
+ "loss": 0.0185,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 2.3451776649746194,
826
+ "grad_norm": 0.19077694416046143,
827
+ "learning_rate": 4.625850340136055e-05,
828
+ "loss": 0.0138,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 2.3654822335025383,
833
+ "grad_norm": 0.19048897922039032,
834
+ "learning_rate": 4.4897959183673474e-05,
835
+ "loss": 0.0113,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 2.3857868020304567,
840
+ "grad_norm": 0.11512188613414764,
841
+ "learning_rate": 4.35374149659864e-05,
842
+ "loss": 0.0075,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 2.4060913705583755,
847
+ "grad_norm": 0.170390784740448,
848
+ "learning_rate": 4.217687074829932e-05,
849
+ "loss": 0.013,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 2.4263959390862944,
854
+ "grad_norm": 0.12413187325000763,
855
+ "learning_rate": 4.0816326530612245e-05,
856
+ "loss": 0.0078,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 2.446700507614213,
861
+ "grad_norm": 0.12575551867485046,
862
+ "learning_rate": 3.945578231292517e-05,
863
+ "loss": 0.0065,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 2.467005076142132,
868
+ "grad_norm": 0.15719905495643616,
869
+ "learning_rate": 3.809523809523809e-05,
870
+ "loss": 0.0081,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 2.487309644670051,
875
+ "grad_norm": 0.11935609579086304,
876
+ "learning_rate": 3.673469387755102e-05,
877
+ "loss": 0.0109,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 2.5076142131979697,
882
+ "grad_norm": 0.24808360636234283,
883
+ "learning_rate": 3.5374149659863946e-05,
884
+ "loss": 0.012,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 2.527918781725888,
889
+ "grad_norm": 0.12832510471343994,
890
+ "learning_rate": 3.401360544217687e-05,
891
+ "loss": 0.0122,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 2.548223350253807,
896
+ "grad_norm": 0.11230963468551636,
897
+ "learning_rate": 3.265306122448979e-05,
898
+ "loss": 0.0083,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 2.568527918781726,
903
+ "grad_norm": 0.11887276917695999,
904
+ "learning_rate": 3.1292517006802724e-05,
905
+ "loss": 0.0098,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 2.5888324873096447,
910
+ "grad_norm": 0.13349293172359467,
911
+ "learning_rate": 2.9931972789115647e-05,
912
+ "loss": 0.0093,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 2.6091370558375635,
917
+ "grad_norm": 0.1103711724281311,
918
+ "learning_rate": 2.857142857142857e-05,
919
+ "loss": 0.0074,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 2.6294416243654823,
924
+ "grad_norm": 0.2013791799545288,
925
+ "learning_rate": 2.72108843537415e-05,
926
+ "loss": 0.0108,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 2.649746192893401,
931
+ "grad_norm": 0.17673830687999725,
932
+ "learning_rate": 2.5850340136054425e-05,
933
+ "loss": 0.012,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 2.6700507614213196,
938
+ "grad_norm": 0.13741633296012878,
939
+ "learning_rate": 2.448979591836735e-05,
940
+ "loss": 0.0116,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 2.6903553299492384,
945
+ "grad_norm": 0.17437736690044403,
946
+ "learning_rate": 2.3129251700680275e-05,
947
+ "loss": 0.0077,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 2.7106598984771573,
952
+ "grad_norm": 0.0926632434129715,
953
+ "learning_rate": 2.17687074829932e-05,
954
+ "loss": 0.0075,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 2.730964467005076,
959
+ "grad_norm": 0.10590869933366776,
960
+ "learning_rate": 2.0408163265306123e-05,
961
+ "loss": 0.0082,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 2.751269035532995,
966
+ "grad_norm": 0.10046230256557465,
967
+ "learning_rate": 1.9047619047619046e-05,
968
+ "loss": 0.0062,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 2.771573604060914,
973
+ "grad_norm": 0.16863778233528137,
974
+ "learning_rate": 1.7687074829931973e-05,
975
+ "loss": 0.0108,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 2.7918781725888326,
980
+ "grad_norm": 0.0949164554476738,
981
+ "learning_rate": 1.6326530612244897e-05,
982
+ "loss": 0.0061,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 2.812182741116751,
987
+ "grad_norm": 0.10832765698432922,
988
+ "learning_rate": 1.4965986394557824e-05,
989
+ "loss": 0.0078,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 2.8324873096446703,
994
+ "grad_norm": 0.1075611487030983,
995
+ "learning_rate": 1.360544217687075e-05,
996
+ "loss": 0.0073,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 2.8527918781725887,
1001
+ "grad_norm": 0.1366114318370819,
1002
+ "learning_rate": 1.2244897959183674e-05,
1003
+ "loss": 0.011,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 2.8730964467005076,
1008
+ "grad_norm": 0.07364023476839066,
1009
+ "learning_rate": 1.08843537414966e-05,
1010
+ "loss": 0.0072,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 2.8934010152284264,
1015
+ "grad_norm": 0.10056645423173904,
1016
+ "learning_rate": 9.523809523809523e-06,
1017
+ "loss": 0.0063,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 2.9137055837563453,
1022
+ "grad_norm": 0.10261747986078262,
1023
+ "learning_rate": 8.163265306122448e-06,
1024
+ "loss": 0.0065,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 2.934010152284264,
1029
+ "grad_norm": 0.12682732939720154,
1030
+ "learning_rate": 6.802721088435375e-06,
1031
+ "loss": 0.0096,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 2.9543147208121825,
1036
+ "grad_norm": 0.101406529545784,
1037
+ "learning_rate": 5.4421768707483e-06,
1038
+ "loss": 0.0081,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 2.974619289340102,
1043
+ "grad_norm": 0.19208553433418274,
1044
+ "learning_rate": 4.081632653061224e-06,
1045
+ "loss": 0.016,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 2.99492385786802,
1050
+ "grad_norm": 0.08324164152145386,
1051
+ "learning_rate": 2.72108843537415e-06,
1052
+ "loss": 0.0054,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 3.0,
1057
+ "grad_norm": 0.1876908838748932,
1058
+ "learning_rate": 1.360544217687075e-06,
1059
+ "loss": 0.0053,
1060
+ "step": 150
1061
+ }
1062
+ ],
1063
+ "logging_steps": 1,
1064
+ "max_steps": 150,
1065
+ "num_input_tokens_seen": 0,
1066
+ "num_train_epochs": 3,
1067
+ "save_steps": 500,
1068
+ "stateful_callbacks": {
1069
+ "TrainerControl": {
1070
+ "args": {
1071
+ "should_epoch_stop": false,
1072
+ "should_evaluate": false,
1073
+ "should_log": false,
1074
+ "should_save": true,
1075
+ "should_training_stop": true
1076
+ },
1077
+ "attributes": {}
1078
+ }
1079
+ },
1080
+ "total_flos": 7.412077364557824e+16,
1081
+ "train_batch_size": 2,
1082
+ "trial_name": null,
1083
+ "trial_params": null
1084
+ }
outputs/checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835172956df823ad9b679eccb10f6cdacbbf2e4f6f7ecd2f8d7b9d8b9685116e
3
+ size 5688
outputs/checkpoint-150/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_compiled_cache/UnslothAlignPropTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothBCOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothCPOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothDDPOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothDPOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothGKDTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothGRPOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothIterativeSFTTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothKTOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothNashMDTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothORPOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothOnlineDPOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothPPOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothPRMTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothRLOOTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothRewardTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
unsloth_compiled_cache/UnslothSFTTrainer.py CHANGED
@@ -1,6 +1,6 @@
1
  """
2
- 2025.7.6
3
- 2025.7.4
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__
 
1
  """
2
+ 2025.7.7
3
+ 2025.7.5
4
  4.53.2
5
  0.19.1
6
  __UNSLOTH_VERSIONING__