Hugging Face's logo

VoCuc
/
nnm

Safetensors
Model card Files
xet
 Community
VoCuc commited on
Commit
0c277cc
·
verified ·
1 Parent(s): f92ee72

Upload folder using huggingface_hub

Browse files
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. llama-3.2-3B-it-distillm2/README.md +63 -0
  3. llama-3.2-3B-it-distillm2/adapter_config.json +33 -0
  4. llama-3.2-3B-it-distillm2/adapter_model.bin +3 -0
  5. llama-3.2-3B-it-distillm2/all_results.json +18 -0
  6. llama-3.2-3B-it-distillm2/checkpoint-1869/README.md +202 -0
  7. llama-3.2-3B-it-distillm2/checkpoint-1869/adapter_config.json +33 -0
  8. llama-3.2-3B-it-distillm2/checkpoint-1869/adapter_model.bin +3 -0
  9. llama-3.2-3B-it-distillm2/checkpoint-1869/special_tokens_map.json +17 -0
  10. llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer.json +3 -0
  11. llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer_config.json +2063 -0
  12. llama-3.2-3B-it-distillm2/checkpoint-1869/trainer_state.json +2090 -0
  13. llama-3.2-3B-it-distillm2/checkpoint-1869/training_args.bin +3 -0
  14. llama-3.2-3B-it-distillm2/config.json +40 -0
  15. llama-3.2-3B-it-distillm2/eval_results.json +12 -0
  16. llama-3.2-3B-it-distillm2/special_tokens_map.json +17 -0
  17. llama-3.2-3B-it-distillm2/tokenizer.json +3 -0
  18. llama-3.2-3B-it-distillm2/tokenizer_config.json +2063 -0
  19. llama-3.2-3B-it-distillm2/train_results.json +9 -0
  20. llama-3.2-3B-it-distillm2/trainer_state.json +2099 -0
  21. llama-3.2-3B-it-distillm2/training_args.bin +3 -0
  22. logs/distillm_2_qwen2.5_1.5b_1e.log +0 -0
  23. logs/distillm_2_qwen2.5_1.5b_it.log +0 -0
  24. logs/llama3.2_3b_it_distillm_2.log +191 -1
  25. qwen2.5-1.5B-it-distillm2-1epoch/README.md +62 -0
  26. qwen2.5-1.5B-it-distillm2-1epoch/added_tokens.json +24 -0
  27. qwen2.5-1.5B-it-distillm2-1epoch/all_results.json +18 -0
  28. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/added_tokens.json +24 -0
  29. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/config.json +29 -0
  30. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/generation_config.json +14 -0
  31. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/merges.txt +0 -0
  32. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/pytorch_model.bin +3 -0
  33. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/special_tokens_map.json +32 -0
  34. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/tokenizer.json +3 -0
  35. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/tokenizer_config.json +207 -0
  36. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/trainer_state.json +2783 -0
  37. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/training_args.bin +3 -0
  38. qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/vocab.json +0 -0
  39. qwen2.5-1.5B-it-distillm2-1epoch/config.json +29 -0
  40. qwen2.5-1.5B-it-distillm2-1epoch/eval_results.json +12 -0
  41. qwen2.5-1.5B-it-distillm2-1epoch/generation_config.json +14 -0
  42. qwen2.5-1.5B-it-distillm2-1epoch/merges.txt +0 -0
  43. qwen2.5-1.5B-it-distillm2-1epoch/pytorch_model.bin +3 -0
  44. qwen2.5-1.5B-it-distillm2-1epoch/special_tokens_map.json +32 -0
  45. qwen2.5-1.5B-it-distillm2-1epoch/tokenizer.json +3 -0
  46. qwen2.5-1.5B-it-distillm2-1epoch/tokenizer_config.json +207 -0
  47. qwen2.5-1.5B-it-distillm2-1epoch/train_results.json +9 -0
  48. qwen2.5-1.5B-it-distillm2-1epoch/trainer_state.json +2792 -0
  49. qwen2.5-1.5B-it-distillm2-1epoch/training_args.bin +3 -0
  50. qwen2.5-1.5B-it-distillm2-1epoch/vocab.json +0 -0
.gitattributes CHANGED
@@ -45,3 +45,7 @@ qwen2.5-1.5B-it-sft/checkpoint-1149/tokenizer.json filter=lfs diff=lfs merge=lfs
45
  qwen2.5-1.5B-it-sft/checkpoint-383/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
  qwen2.5-1.5B-it-sft/checkpoint-767/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
  qwen2.5-1.5B-it-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
45
  qwen2.5-1.5B-it-sft/checkpoint-383/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
  qwen2.5-1.5B-it-sft/checkpoint-767/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
  qwen2.5-1.5B-it-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
+ llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ llama-3.2-3B-it-distillm2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ qwen2.5-1.5B-it-distillm2-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-distillm2/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.2
4
+ base_model: meta-llama/Llama-3.2-3B-Instruct
5
+ tags:
6
+ - alignment-handbook
7
+ - generated_from_trainer
8
+ datasets:
9
+ - data/reformatted/distill-deepSeek-R1-Distill-Llama-8B
10
+ model-index:
11
+ - name: llama-3.2-3B-it-distillm2
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # llama-3.2-3B-it-distillm2
19
+
20
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the data/reformatted/distill-deepSeek-R1-Distill-Llama-8B dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 2
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 2
45
+ - gradient_accumulation_steps: 64
46
+ - total_train_batch_size: 128
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 3
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.9.0
60
+ - Transformers 4.45.2
61
+ - Pytorch 2.5.1+cu124
62
+ - Datasets 4.8.5
63
+ - Tokenizers 0.20.3
llama-3.2-3B-it-distillm2/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 128,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": true,
32
+ "use_rslora": false
33
+ }
llama-3.2-3B-it-distillm2/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8dafff4f517c7a4be79fddbdf833efe9e37ffce90628daeb107aed66a7243f
3
+ size 50388282
llama-3.2-3B-it-distillm2/all_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.999699067108035,
3
+ "eval_logps_logqs/chosen": 0.095769964158535,
4
+ "eval_logqs/chosen": -0.8354007601737976,
5
+ "eval_logqs/rejected": -0.7743091583251953,
6
+ "eval_logqs_logps/rejected": 0.09668296575546265,
7
+ "eval_loss": 0.34429532289505005,
8
+ "eval_runtime": 1.1616,
9
+ "eval_samples": 10,
10
+ "eval_samples_per_second": 8.609,
11
+ "eval_steps_per_second": 2.583,
12
+ "total_flos": 0.0,
13
+ "train_loss": 0.347557685507881,
14
+ "train_runtime": 42290.5207,
15
+ "train_samples": 79751,
16
+ "train_samples_per_second": 5.657,
17
+ "train_steps_per_second": 0.044
18
+ }
llama-3.2-3B-it-distillm2/checkpoint-1869/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-3B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.9.0
llama-3.2-3B-it-distillm2/checkpoint-1869/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 128,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": true,
32
+ "use_rslora": false
33
+ }
llama-3.2-3B-it-distillm2/checkpoint-1869/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8dafff4f517c7a4be79fddbdf833efe9e37ffce90628daeb107aed66a7243f
3
+ size 50388282
llama-3.2-3B-it-distillm2/checkpoint-1869/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
llama-3.2-3B-it-distillm2/checkpoint-1869/trainer_state.json ADDED
@@ -0,0 +1,2090 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.999699067108035,
5
+ "eval_steps": 10000000,
6
+ "global_step": 1869,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0016049754238138228,
13
+ "grad_norm": 0.90625,
14
+ "learning_rate": 2.6737967914438503e-07,
15
+ "logps_logqs/chosen": 0.2574678659439087,
16
+ "logqs/chosen": -1.2981349229812622,
17
+ "logqs/rejected": -0.7383479475975037,
18
+ "logqs_logps/rejected": 0.1667567938566208,
19
+ "loss": 0.7904,
20
+ "step": 1
21
+ },
22
+ {
23
+ "epoch": 0.016049754238138227,
24
+ "grad_norm": 0.796875,
25
+ "learning_rate": 2.6737967914438504e-06,
26
+ "logps_logqs/chosen": 0.261772096157074,
27
+ "logqs/chosen": -1.3397735357284546,
28
+ "logqs/rejected": -0.7105537056922913,
29
+ "logqs_logps/rejected": 0.16120129823684692,
30
+ "loss": 0.7608,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.032099508476276455,
35
+ "grad_norm": 0.69140625,
36
+ "learning_rate": 5.347593582887701e-06,
37
+ "logps_logqs/chosen": 0.2507140040397644,
38
+ "logqs/chosen": -1.3112075328826904,
39
+ "logqs/rejected": -0.7247480750083923,
40
+ "logqs_logps/rejected": 0.1601167917251587,
41
+ "loss": 0.7473,
42
+ "step": 20
43
+ },
44
+ {
45
+ "epoch": 0.048149262714414685,
46
+ "grad_norm": 0.5625,
47
+ "learning_rate": 8.02139037433155e-06,
48
+ "logps_logqs/chosen": 0.23428936302661896,
49
+ "logqs/chosen": -1.2722276449203491,
50
+ "logqs/rejected": -0.7449068427085876,
51
+ "logqs_logps/rejected": 0.1634160578250885,
52
+ "loss": 0.7145,
53
+ "step": 30
54
+ },
55
+ {
56
+ "epoch": 0.06419901695255291,
57
+ "grad_norm": 0.494140625,
58
+ "learning_rate": 1.0695187165775402e-05,
59
+ "logps_logqs/chosen": 0.22127564251422882,
60
+ "logqs/chosen": -1.2067252397537231,
61
+ "logqs/rejected": -0.7258399724960327,
62
+ "logqs_logps/rejected": 0.16167941689491272,
63
+ "loss": 0.6827,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 0.08024877119069114,
68
+ "grad_norm": 0.40625,
69
+ "learning_rate": 1.3368983957219252e-05,
70
+ "logps_logqs/chosen": 0.20441269874572754,
71
+ "logqs/chosen": -1.144487977027893,
72
+ "logqs/rejected": -0.7239223718643188,
73
+ "logqs_logps/rejected": 0.16194146871566772,
74
+ "loss": 0.6414,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.09629852542882937,
79
+ "grad_norm": 0.921875,
80
+ "learning_rate": 1.60427807486631e-05,
81
+ "logps_logqs/chosen": 0.19416597485542297,
82
+ "logqs/chosen": -1.1013798713684082,
83
+ "logqs/rejected": -0.7783336639404297,
84
+ "logqs_logps/rejected": 0.1327773630619049,
85
+ "loss": 0.5906,
86
+ "step": 60
87
+ },
88
+ {
89
+ "epoch": 0.1123482796669676,
90
+ "grad_norm": 0.294921875,
91
+ "learning_rate": 1.8716577540106954e-05,
92
+ "logps_logqs/chosen": 0.20319707691669464,
93
+ "logqs/chosen": -1.1499295234680176,
94
+ "logqs/rejected": -0.9546529650688171,
95
+ "logqs_logps/rejected": 0.07568300515413284,
96
+ "loss": 0.5474,
97
+ "step": 70
98
+ },
99
+ {
100
+ "epoch": 0.12839803390510582,
101
+ "grad_norm": 0.296875,
102
+ "learning_rate": 2.1390374331550803e-05,
103
+ "logps_logqs/chosen": 0.2029210776090622,
104
+ "logqs/chosen": -1.1514651775360107,
105
+ "logqs/rejected": -0.9666783213615417,
106
+ "logqs_logps/rejected": 0.07000944763422012,
107
+ "loss": 0.5267,
108
+ "step": 80
109
+ },
110
+ {
111
+ "epoch": 0.14444778814324405,
112
+ "grad_norm": 0.2158203125,
113
+ "learning_rate": 2.4064171122994652e-05,
114
+ "logps_logqs/chosen": 0.19126488268375397,
115
+ "logqs/chosen": -1.1015961170196533,
116
+ "logqs/rejected": -0.9495261907577515,
117
+ "logqs_logps/rejected": 0.07096932828426361,
118
+ "loss": 0.505,
119
+ "step": 90
120
+ },
121
+ {
122
+ "epoch": 0.16049754238138228,
123
+ "grad_norm": 0.228515625,
124
+ "learning_rate": 2.6737967914438505e-05,
125
+ "logps_logqs/chosen": 0.17442497611045837,
126
+ "logqs/chosen": -1.0466772317886353,
127
+ "logqs/rejected": -0.9257510304450989,
128
+ "logqs_logps/rejected": 0.07788076251745224,
129
+ "loss": 0.4811,
130
+ "step": 100
131
+ },
132
+ {
133
+ "epoch": 0.1765472966195205,
134
+ "grad_norm": 0.2373046875,
135
+ "learning_rate": 2.9411764705882354e-05,
136
+ "logps_logqs/chosen": 0.16078680753707886,
137
+ "logqs/chosen": -1.029247522354126,
138
+ "logqs/rejected": -0.8865665197372437,
139
+ "logqs_logps/rejected": 0.09497503191232681,
140
+ "loss": 0.4736,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.19259705085765874,
145
+ "grad_norm": 0.22265625,
146
+ "learning_rate": 3.20855614973262e-05,
147
+ "logps_logqs/chosen": 0.1526278555393219,
148
+ "logqs/chosen": -0.9959474802017212,
149
+ "logqs/rejected": -0.8694570660591125,
150
+ "logqs_logps/rejected": 0.09631417691707611,
151
+ "loss": 0.4569,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.20864680509579697,
156
+ "grad_norm": 0.216796875,
157
+ "learning_rate": 3.4759358288770055e-05,
158
+ "logps_logqs/chosen": 0.14035369455814362,
159
+ "logqs/chosen": -0.9707647562026978,
160
+ "logqs/rejected": -0.8952853083610535,
161
+ "logqs_logps/rejected": 0.09752343595027924,
162
+ "loss": 0.4462,
163
+ "step": 130
164
+ },
165
+ {
166
+ "epoch": 0.2246965593339352,
167
+ "grad_norm": 0.21875,
168
+ "learning_rate": 3.743315508021391e-05,
169
+ "logps_logqs/chosen": 0.13420596718788147,
170
+ "logqs/chosen": -0.9546219706535339,
171
+ "logqs/rejected": -0.8874092102050781,
172
+ "logqs_logps/rejected": 0.09715182334184647,
173
+ "loss": 0.4316,
174
+ "step": 140
175
+ },
176
+ {
177
+ "epoch": 0.24074631357207343,
178
+ "grad_norm": 0.2451171875,
179
+ "learning_rate": 4.0106951871657754e-05,
180
+ "logps_logqs/chosen": 0.12938353419303894,
181
+ "logqs/chosen": -0.9377857446670532,
182
+ "logqs/rejected": -0.8700798749923706,
183
+ "logqs_logps/rejected": 0.09673669189214706,
184
+ "loss": 0.4268,
185
+ "step": 150
186
+ },
187
+ {
188
+ "epoch": 0.25679606781021164,
189
+ "grad_norm": 0.2255859375,
190
+ "learning_rate": 4.2780748663101606e-05,
191
+ "logps_logqs/chosen": 0.12080077081918716,
192
+ "logqs/chosen": -0.9156932830810547,
193
+ "logqs/rejected": -0.8663859367370605,
194
+ "logqs_logps/rejected": 0.09702957421541214,
195
+ "loss": 0.4138,
196
+ "step": 160
197
+ },
198
+ {
199
+ "epoch": 0.2728458220483499,
200
+ "grad_norm": 0.267578125,
201
+ "learning_rate": 4.545454545454546e-05,
202
+ "logps_logqs/chosen": 0.1205262765288353,
203
+ "logqs/chosen": -0.9165436625480652,
204
+ "logqs/rejected": -0.8856159448623657,
205
+ "logqs_logps/rejected": 0.09857054054737091,
206
+ "loss": 0.4114,
207
+ "step": 170
208
+ },
209
+ {
210
+ "epoch": 0.2888955762864881,
211
+ "grad_norm": 0.259765625,
212
+ "learning_rate": 4.8128342245989304e-05,
213
+ "logps_logqs/chosen": 0.1172843724489212,
214
+ "logqs/chosen": -0.8963316679000854,
215
+ "logqs/rejected": -0.8776806592941284,
216
+ "logqs_logps/rejected": 0.09663058817386627,
217
+ "loss": 0.4024,
218
+ "step": 180
219
+ },
220
+ {
221
+ "epoch": 0.30494533052462636,
222
+ "grad_norm": 0.28125,
223
+ "learning_rate": 4.9999607536612036e-05,
224
+ "logps_logqs/chosen": 0.11222084611654282,
225
+ "logqs/chosen": -0.8948033452033997,
226
+ "logqs/rejected": -0.8878369331359863,
227
+ "logqs_logps/rejected": 0.09515221416950226,
228
+ "loss": 0.4028,
229
+ "step": 190
230
+ },
231
+ {
232
+ "epoch": 0.32099508476276456,
233
+ "grad_norm": 0.271484375,
234
+ "learning_rate": 4.9992630752499945e-05,
235
+ "logps_logqs/chosen": 0.10836397111415863,
236
+ "logqs/chosen": -0.8886402249336243,
237
+ "logqs/rejected": -0.8636736869812012,
238
+ "logqs_logps/rejected": 0.09533380717039108,
239
+ "loss": 0.3895,
240
+ "step": 200
241
+ },
242
+ {
243
+ "epoch": 0.3370448390009028,
244
+ "grad_norm": 0.267578125,
245
+ "learning_rate": 4.997693536122969e-05,
246
+ "logps_logqs/chosen": 0.10845750570297241,
247
+ "logqs/chosen": -0.8758543729782104,
248
+ "logqs/rejected": -0.8861125707626343,
249
+ "logqs_logps/rejected": 0.09698913246393204,
250
+ "loss": 0.3905,
251
+ "step": 210
252
+ },
253
+ {
254
+ "epoch": 0.353094593239041,
255
+ "grad_norm": 0.255859375,
256
+ "learning_rate": 4.995252683809324e-05,
257
+ "logps_logqs/chosen": 0.103293776512146,
258
+ "logqs/chosen": -0.8651936650276184,
259
+ "logqs/rejected": -0.8593576550483704,
260
+ "logqs_logps/rejected": 0.09784064441919327,
261
+ "loss": 0.3843,
262
+ "step": 220
263
+ },
264
+ {
265
+ "epoch": 0.3691443474771793,
266
+ "grad_norm": 0.26953125,
267
+ "learning_rate": 4.9919413697933496e-05,
268
+ "logps_logqs/chosen": 0.10118403285741806,
269
+ "logqs/chosen": -0.8709210157394409,
270
+ "logqs/rejected": -0.8462339639663696,
271
+ "logqs_logps/rejected": 0.09881097078323364,
272
+ "loss": 0.3841,
273
+ "step": 230
274
+ },
275
+ {
276
+ "epoch": 0.3851941017153175,
277
+ "grad_norm": 0.265625,
278
+ "learning_rate": 4.987760749217389e-05,
279
+ "logps_logqs/chosen": 0.10117912292480469,
280
+ "logqs/chosen": -0.8689754605293274,
281
+ "logqs/rejected": -0.8683704137802124,
282
+ "logqs_logps/rejected": 0.09666574746370316,
283
+ "loss": 0.3777,
284
+ "step": 240
285
+ },
286
+ {
287
+ "epoch": 0.4012438559534557,
288
+ "grad_norm": 0.302734375,
289
+ "learning_rate": 4.982712280478875e-05,
290
+ "logps_logqs/chosen": 0.09455956518650055,
291
+ "logqs/chosen": -0.8457688093185425,
292
+ "logqs/rejected": -0.8621484637260437,
293
+ "logqs_logps/rejected": 0.09776864945888519,
294
+ "loss": 0.3765,
295
+ "step": 250
296
+ },
297
+ {
298
+ "epoch": 0.41729361019159394,
299
+ "grad_norm": 0.2578125,
300
+ "learning_rate": 4.976797724721567e-05,
301
+ "logps_logqs/chosen": 0.09175171703100204,
302
+ "logqs/chosen": -0.8432157635688782,
303
+ "logqs/rejected": -0.8678897023200989,
304
+ "logqs_logps/rejected": 0.09698458015918732,
305
+ "loss": 0.3688,
306
+ "step": 260
307
+ },
308
+ {
309
+ "epoch": 0.43334336442973215,
310
+ "grad_norm": 0.283203125,
311
+ "learning_rate": 4.9700191452211806e-05,
312
+ "logps_logqs/chosen": 0.09448465704917908,
313
+ "logqs/chosen": -0.84539395570755,
314
+ "logqs/rejected": -0.8683292269706726,
315
+ "logqs_logps/rejected": 0.09693001210689545,
316
+ "loss": 0.3716,
317
+ "step": 270
318
+ },
319
+ {
320
+ "epoch": 0.4493931186678704,
321
+ "grad_norm": 0.28125,
322
+ "learning_rate": 4.9623789066656276e-05,
323
+ "logps_logqs/chosen": 0.09571119397878647,
324
+ "logqs/chosen": -0.8593363761901855,
325
+ "logqs/rejected": -0.8565343618392944,
326
+ "logqs_logps/rejected": 0.09683676809072495,
327
+ "loss": 0.3735,
328
+ "step": 280
329
+ },
330
+ {
331
+ "epoch": 0.4654428729060086,
332
+ "grad_norm": 0.31640625,
333
+ "learning_rate": 4.953879674330093e-05,
334
+ "logps_logqs/chosen": 0.09770174324512482,
335
+ "logqs/chosen": -0.8558902740478516,
336
+ "logqs/rejected": -0.8663812875747681,
337
+ "logqs_logps/rejected": 0.09595683217048645,
338
+ "loss": 0.3673,
339
+ "step": 290
340
+ },
341
+ {
342
+ "epoch": 0.48149262714414687,
343
+ "grad_norm": 0.287109375,
344
+ "learning_rate": 4.944524413147263e-05,
345
+ "logps_logqs/chosen": 0.09066566079854965,
346
+ "logqs/chosen": -0.8534440994262695,
347
+ "logqs/rejected": -0.8585640788078308,
348
+ "logqs_logps/rejected": 0.09527692943811417,
349
+ "loss": 0.3652,
350
+ "step": 300
351
+ },
352
+ {
353
+ "epoch": 0.49754238138228507,
354
+ "grad_norm": 0.2578125,
355
+ "learning_rate": 4.934316386673022e-05,
356
+ "logps_logqs/chosen": 0.09241481125354767,
357
+ "logqs/chosen": -0.8291435241699219,
358
+ "logqs/rejected": -0.8762058019638062,
359
+ "logqs_logps/rejected": 0.09554027765989304,
360
+ "loss": 0.3615,
361
+ "step": 310
362
+ },
363
+ {
364
+ "epoch": 0.5135921356204233,
365
+ "grad_norm": 0.28515625,
366
+ "learning_rate": 4.923259155947964e-05,
367
+ "logps_logqs/chosen": 0.09071577340364456,
368
+ "logqs/chosen": -0.8484598398208618,
369
+ "logqs/rejected": -0.8865866661071777,
370
+ "logqs_logps/rejected": 0.09390830993652344,
371
+ "loss": 0.3638,
372
+ "step": 320
373
+ },
374
+ {
375
+ "epoch": 0.5296418898585615,
376
+ "grad_norm": 0.306640625,
377
+ "learning_rate": 4.911356578255139e-05,
378
+ "logps_logqs/chosen": 0.09064419567584991,
379
+ "logqs/chosen": -0.8393951654434204,
380
+ "logqs/rejected": -0.8594444990158081,
381
+ "logqs_logps/rejected": 0.09380849450826645,
382
+ "loss": 0.3604,
383
+ "step": 330
384
+ },
385
+ {
386
+ "epoch": 0.5456916440966998,
387
+ "grad_norm": 0.291015625,
388
+ "learning_rate": 4.898612805774447e-05,
389
+ "logps_logqs/chosen": 0.08888660371303558,
390
+ "logqs/chosen": -0.8379303216934204,
391
+ "logqs/rejected": -0.8894745707511902,
392
+ "logqs_logps/rejected": 0.09310872852802277,
393
+ "loss": 0.3628,
394
+ "step": 340
395
+ },
396
+ {
397
+ "epoch": 0.561741398334838,
398
+ "grad_norm": 0.263671875,
399
+ "learning_rate": 4.885032284134165e-05,
400
+ "logps_logqs/chosen": 0.088349848985672,
401
+ "logqs/chosen": -0.8371356129646301,
402
+ "logqs/rejected": -0.8821464776992798,
403
+ "logqs_logps/rejected": 0.09222712367773056,
404
+ "loss": 0.3579,
405
+ "step": 350
406
+ },
407
+ {
408
+ "epoch": 0.5777911525729762,
409
+ "grad_norm": 0.30078125,
410
+ "learning_rate": 4.8706197508600984e-05,
411
+ "logps_logqs/chosen": 0.08849716186523438,
412
+ "logqs/chosen": -0.8537057638168335,
413
+ "logqs/rejected": -0.8783435821533203,
414
+ "logqs_logps/rejected": 0.0930907279253006,
415
+ "loss": 0.3601,
416
+ "step": 360
417
+ },
418
+ {
419
+ "epoch": 0.5938409068111145,
420
+ "grad_norm": 0.263671875,
421
+ "learning_rate": 4.855380233722915e-05,
422
+ "logps_logqs/chosen": 0.08889272809028625,
423
+ "logqs/chosen": -0.8391559720039368,
424
+ "logqs/rejected": -0.861327052116394,
425
+ "logqs_logps/rejected": 0.09380140900611877,
426
+ "loss": 0.3576,
427
+ "step": 370
428
+ },
429
+ {
430
+ "epoch": 0.6098906610492527,
431
+ "grad_norm": 0.25390625,
432
+ "learning_rate": 4.839319048984217e-05,
433
+ "logps_logqs/chosen": 0.08648727834224701,
434
+ "logqs/chosen": -0.8195026516914368,
435
+ "logqs/rejected": -0.8793449401855469,
436
+ "logqs_logps/rejected": 0.09177446365356445,
437
+ "loss": 0.3512,
438
+ "step": 380
439
+ },
440
+ {
441
+ "epoch": 0.6259404152873909,
442
+ "grad_norm": 0.30859375,
443
+ "learning_rate": 4.822441799541979e-05,
444
+ "logps_logqs/chosen": 0.08833304047584534,
445
+ "logqs/chosen": -0.8366491198539734,
446
+ "logqs/rejected": -0.8869533538818359,
447
+ "logqs_logps/rejected": 0.09127027541399002,
448
+ "loss": 0.351,
449
+ "step": 390
450
+ },
451
+ {
452
+ "epoch": 0.6419901695255291,
453
+ "grad_norm": 0.287109375,
454
+ "learning_rate": 4.8047543729759936e-05,
455
+ "logps_logqs/chosen": 0.08663193136453629,
456
+ "logqs/chosen": -0.824337363243103,
457
+ "logqs/rejected": -0.8671427965164185,
458
+ "logqs_logps/rejected": 0.09136663377285004,
459
+ "loss": 0.3509,
460
+ "step": 400
461
+ },
462
+ {
463
+ "epoch": 0.6580399237636674,
464
+ "grad_norm": 0.275390625,
465
+ "learning_rate": 4.786262939494007e-05,
466
+ "logps_logqs/chosen": 0.0892716497182846,
467
+ "logqs/chosen": -0.8378982543945312,
468
+ "logqs/rejected": -0.9046772718429565,
469
+ "logqs_logps/rejected": 0.09127910435199738,
470
+ "loss": 0.3563,
471
+ "step": 410
472
+ },
473
+ {
474
+ "epoch": 0.6740896780018056,
475
+ "grad_norm": 0.275390625,
476
+ "learning_rate": 4.766973949779261e-05,
477
+ "logps_logqs/chosen": 0.08481737226247787,
478
+ "logqs/chosen": -0.8248282670974731,
479
+ "logqs/rejected": -0.8802385330200195,
480
+ "logqs_logps/rejected": 0.09057352691888809,
481
+ "loss": 0.3503,
482
+ "step": 420
483
+ },
484
+ {
485
+ "epoch": 0.6901394322399438,
486
+ "grad_norm": 0.32421875,
487
+ "learning_rate": 4.746894132740186e-05,
488
+ "logps_logqs/chosen": 0.08275488764047623,
489
+ "logqs/chosen": -0.8119369745254517,
490
+ "logqs/rejected": -0.8782287836074829,
491
+ "logqs_logps/rejected": 0.09131704270839691,
492
+ "loss": 0.3472,
493
+ "step": 430
494
+ },
495
+ {
496
+ "epoch": 0.706189186478082,
497
+ "grad_norm": 0.267578125,
498
+ "learning_rate": 4.726030493163044e-05,
499
+ "logps_logqs/chosen": 0.08377610146999359,
500
+ "logqs/chosen": -0.8197402954101562,
501
+ "logqs/rejected": -0.8705655932426453,
502
+ "logqs_logps/rejected": 0.09147749096155167,
503
+ "loss": 0.3497,
504
+ "step": 440
505
+ },
506
+ {
507
+ "epoch": 0.7222389407162203,
508
+ "grad_norm": 0.283203125,
509
+ "learning_rate": 4.7043903092683314e-05,
510
+ "logps_logqs/chosen": 0.08348951488733292,
511
+ "logqs/chosen": -0.8285576701164246,
512
+ "logqs/rejected": -0.8908966183662415,
513
+ "logqs_logps/rejected": 0.08978553861379623,
514
+ "loss": 0.3513,
515
+ "step": 450
516
+ },
517
+ {
518
+ "epoch": 0.7382886949543586,
519
+ "grad_norm": 0.275390625,
520
+ "learning_rate": 4.6819811301717885e-05,
521
+ "logps_logqs/chosen": 0.08379025757312775,
522
+ "logqs/chosen": -0.8281780481338501,
523
+ "logqs/rejected": -0.8864878416061401,
524
+ "logqs_logps/rejected": 0.09138767421245575,
525
+ "loss": 0.349,
526
+ "step": 460
527
+ },
528
+ {
529
+ "epoch": 0.7543384491924967,
530
+ "grad_norm": 0.28125,
531
+ "learning_rate": 4.6588107732509134e-05,
532
+ "logps_logqs/chosen": 0.08411180227994919,
533
+ "logqs/chosen": -0.8280686140060425,
534
+ "logqs/rejected": -0.8841449618339539,
535
+ "logqs_logps/rejected": 0.09198630601167679,
536
+ "loss": 0.3487,
537
+ "step": 470
538
+ },
539
+ {
540
+ "epoch": 0.770388203430635,
541
+ "grad_norm": 0.3046875,
542
+ "learning_rate": 4.634887321417895e-05,
543
+ "logps_logqs/chosen": 0.08379300683736801,
544
+ "logqs/chosen": -0.8192381858825684,
545
+ "logqs/rejected": -0.8699550628662109,
546
+ "logqs_logps/rejected": 0.09246320277452469,
547
+ "loss": 0.3488,
548
+ "step": 480
549
+ },
550
+ {
551
+ "epoch": 0.7864379576687732,
552
+ "grad_norm": 0.283203125,
553
+ "learning_rate": 4.6102191202999065e-05,
554
+ "logps_logqs/chosen": 0.0825960636138916,
555
+ "logqs/chosen": -0.8156631588935852,
556
+ "logqs/rejected": -0.8777653574943542,
557
+ "logqs_logps/rejected": 0.08903246372938156,
558
+ "loss": 0.3441,
559
+ "step": 490
560
+ },
561
+ {
562
+ "epoch": 0.8024877119069114,
563
+ "grad_norm": 0.259765625,
564
+ "learning_rate": 4.5848147753277656e-05,
565
+ "logps_logqs/chosen": 0.08584129810333252,
566
+ "logqs/chosen": -0.8234313130378723,
567
+ "logqs/rejected": -0.8765767216682434,
568
+ "logqs_logps/rejected": 0.08872086554765701,
569
+ "loss": 0.3405,
570
+ "step": 500
571
+ },
572
+ {
573
+ "epoch": 0.8185374661450496,
574
+ "grad_norm": 0.275390625,
575
+ "learning_rate": 4.5586831487339485e-05,
576
+ "logps_logqs/chosen": 0.0830707997083664,
577
+ "logqs/chosen": -0.8339930772781372,
578
+ "logqs/rejected": -0.8920092582702637,
579
+ "logqs_logps/rejected": 0.0881909504532814,
580
+ "loss": 0.3472,
581
+ "step": 510
582
+ },
583
+ {
584
+ "epoch": 0.8345872203831879,
585
+ "grad_norm": 0.271484375,
586
+ "learning_rate": 4.531833356461027e-05,
587
+ "logps_logqs/chosen": 0.08575956523418427,
588
+ "logqs/chosen": -0.8362727165222168,
589
+ "logqs/rejected": -0.9038101434707642,
590
+ "logqs_logps/rejected": 0.08844949305057526,
591
+ "loss": 0.3426,
592
+ "step": 520
593
+ },
594
+ {
595
+ "epoch": 0.8506369746213261,
596
+ "grad_norm": 0.259765625,
597
+ "learning_rate": 4.5042747649816006e-05,
598
+ "logps_logqs/chosen": 0.08415627479553223,
599
+ "logqs/chosen": -0.8301606178283691,
600
+ "logqs/rejected": -0.8767345547676086,
601
+ "logqs_logps/rejected": 0.090895876288414,
602
+ "loss": 0.3377,
603
+ "step": 530
604
+ },
605
+ {
606
+ "epoch": 0.8666867288594643,
607
+ "grad_norm": 0.2734375,
608
+ "learning_rate": 4.476016988030826e-05,
609
+ "logps_logqs/chosen": 0.08037060499191284,
610
+ "logqs/chosen": -0.8235775232315063,
611
+ "logqs/rejected": -0.903292179107666,
612
+ "logqs_logps/rejected": 0.08936522901058197,
613
+ "loss": 0.3414,
614
+ "step": 540
615
+ },
616
+ {
617
+ "epoch": 0.8827364830976026,
618
+ "grad_norm": 0.255859375,
619
+ "learning_rate": 4.447069883252696e-05,
620
+ "logps_logqs/chosen": 0.08378899097442627,
621
+ "logqs/chosen": -0.81104576587677,
622
+ "logqs/rejected": -0.8723270297050476,
623
+ "logqs_logps/rejected": 0.08844035863876343,
624
+ "loss": 0.3385,
625
+ "step": 550
626
+ },
627
+ {
628
+ "epoch": 0.8987862373357408,
629
+ "grad_norm": 0.28125,
630
+ "learning_rate": 4.417443548761227e-05,
631
+ "logps_logqs/chosen": 0.08536671847105026,
632
+ "logqs/chosen": -0.8402923345565796,
633
+ "logqs/rejected": -0.915910542011261,
634
+ "logqs_logps/rejected": 0.08888525515794754,
635
+ "loss": 0.3445,
636
+ "step": 560
637
+ },
638
+ {
639
+ "epoch": 0.9148359915738791,
640
+ "grad_norm": 0.294921875,
641
+ "learning_rate": 4.387148319617763e-05,
642
+ "logps_logqs/chosen": 0.08296655118465424,
643
+ "logqs/chosen": -0.8120464086532593,
644
+ "logqs/rejected": -0.8686345219612122,
645
+ "logqs_logps/rejected": 0.08868331462144852,
646
+ "loss": 0.3372,
647
+ "step": 570
648
+ },
649
+ {
650
+ "epoch": 0.9308857458120172,
651
+ "grad_norm": 0.283203125,
652
+ "learning_rate": 4.356194764225618e-05,
653
+ "logps_logqs/chosen": 0.08104117959737778,
654
+ "logqs/chosen": -0.8216385841369629,
655
+ "logqs/rejected": -0.8963106274604797,
656
+ "logqs_logps/rejected": 0.08660975098609924,
657
+ "loss": 0.3355,
658
+ "step": 580
659
+ },
660
+ {
661
+ "epoch": 0.9469355000501555,
662
+ "grad_norm": 0.296875,
663
+ "learning_rate": 4.3245936806433205e-05,
664
+ "logps_logqs/chosen": 0.07939769327640533,
665
+ "logqs/chosen": -0.8180539011955261,
666
+ "logqs/rejected": -0.8782569766044617,
667
+ "logqs_logps/rejected": 0.08691652119159698,
668
+ "loss": 0.3356,
669
+ "step": 590
670
+ },
671
+ {
672
+ "epoch": 0.9629852542882937,
673
+ "grad_norm": 0.30078125,
674
+ "learning_rate": 4.292356092817739e-05,
675
+ "logps_logqs/chosen": 0.08429218828678131,
676
+ "logqs/chosen": -0.8148031234741211,
677
+ "logqs/rejected": -0.8775607943534851,
678
+ "logqs_logps/rejected": 0.08722598850727081,
679
+ "loss": 0.3346,
680
+ "step": 600
681
+ },
682
+ {
683
+ "epoch": 0.979035008526432,
684
+ "grad_norm": 0.265625,
685
+ "learning_rate": 4.259493246738409e-05,
686
+ "logps_logqs/chosen": 0.0812491774559021,
687
+ "logqs/chosen": -0.8289790153503418,
688
+ "logqs/rejected": -0.8987892866134644,
689
+ "logqs_logps/rejected": 0.08712317794561386,
690
+ "loss": 0.3364,
691
+ "step": 610
692
+ },
693
+ {
694
+ "epoch": 0.9950847627645701,
695
+ "grad_norm": 0.302734375,
696
+ "learning_rate": 4.226016606514411e-05,
697
+ "logps_logqs/chosen": 0.0814874917268753,
698
+ "logqs/chosen": -0.8087742924690247,
699
+ "logqs/rejected": -0.8908030390739441,
700
+ "logqs_logps/rejected": 0.0876212790608406,
701
+ "loss": 0.3389,
702
+ "step": 620
703
+ },
704
+ {
705
+ "epoch": 1.0111345170027084,
706
+ "grad_norm": 0.26953125,
707
+ "learning_rate": 4.191937850375136e-05,
708
+ "logps_logqs/chosen": 0.07808364927768707,
709
+ "logqs/chosen": -0.8158828616142273,
710
+ "logqs/rejected": -0.8890725374221802,
711
+ "logqs_logps/rejected": 0.08443473279476166,
712
+ "loss": 0.3268,
713
+ "step": 630
714
+ },
715
+ {
716
+ "epoch": 1.0271842712408465,
717
+ "grad_norm": 0.283203125,
718
+ "learning_rate": 4.157268866596381e-05,
719
+ "logps_logqs/chosen": 0.0806763619184494,
720
+ "logqs/chosen": -0.8284119367599487,
721
+ "logqs/rejected": -0.8865575790405273,
722
+ "logqs_logps/rejected": 0.0866897776722908,
723
+ "loss": 0.3295,
724
+ "step": 640
725
+ },
726
+ {
727
+ "epoch": 1.043234025478985,
728
+ "grad_norm": 0.279296875,
729
+ "learning_rate": 4.1220217493531494e-05,
730
+ "logps_logqs/chosen": 0.07972967624664307,
731
+ "logqs/chosen": -0.8299144506454468,
732
+ "logqs/rejected": -0.8995611071586609,
733
+ "logqs_logps/rejected": 0.08687488734722137,
734
+ "loss": 0.3302,
735
+ "step": 650
736
+ },
737
+ {
738
+ "epoch": 1.059283779717123,
739
+ "grad_norm": 0.283203125,
740
+ "learning_rate": 4.086208794500637e-05,
741
+ "logps_logqs/chosen": 0.07892154902219772,
742
+ "logqs/chosen": -0.813999354839325,
743
+ "logqs/rejected": -0.9233400225639343,
744
+ "logqs_logps/rejected": 0.08419923484325409,
745
+ "loss": 0.325,
746
+ "step": 660
747
+ },
748
+ {
749
+ "epoch": 1.0753335339552612,
750
+ "grad_norm": 0.2490234375,
751
+ "learning_rate": 4.049842495284858e-05,
752
+ "logps_logqs/chosen": 0.07649672031402588,
753
+ "logqs/chosen": -0.7998867034912109,
754
+ "logqs/rejected": -0.8894570469856262,
755
+ "logqs_logps/rejected": 0.08604138344526291,
756
+ "loss": 0.327,
757
+ "step": 670
758
+ },
759
+ {
760
+ "epoch": 1.0913832881933996,
761
+ "grad_norm": 0.259765625,
762
+ "learning_rate": 4.012935537984414e-05,
763
+ "logps_logqs/chosen": 0.07958203554153442,
764
+ "logqs/chosen": -0.7970592379570007,
765
+ "logqs/rejected": -0.88422030210495,
766
+ "logqs_logps/rejected": 0.08651049435138702,
767
+ "loss": 0.3246,
768
+ "step": 680
769
+ },
770
+ {
771
+ "epoch": 1.1074330424315377,
772
+ "grad_norm": 0.267578125,
773
+ "learning_rate": 3.9755007974849135e-05,
774
+ "logps_logqs/chosen": 0.076724112033844,
775
+ "logqs/chosen": -0.817238986492157,
776
+ "logqs/rejected": -0.8899539113044739,
777
+ "logqs_logps/rejected": 0.08536411821842194,
778
+ "loss": 0.3296,
779
+ "step": 690
780
+ },
781
+ {
782
+ "epoch": 1.123482796669676,
783
+ "grad_norm": 0.2578125,
784
+ "learning_rate": 3.93755133278762e-05,
785
+ "logps_logqs/chosen": 0.07787708938121796,
786
+ "logqs/chosen": -0.8070911169052124,
787
+ "logqs/rejected": -0.8890964388847351,
788
+ "logqs_logps/rejected": 0.08466648310422897,
789
+ "loss": 0.3256,
790
+ "step": 700
791
+ },
792
+ {
793
+ "epoch": 1.1395325509078142,
794
+ "grad_norm": 0.2578125,
795
+ "learning_rate": 3.899100382453845e-05,
796
+ "logps_logqs/chosen": 0.07550434023141861,
797
+ "logqs/chosen": -0.7925726771354675,
798
+ "logqs/rejected": -0.8927756547927856,
799
+ "logqs_logps/rejected": 0.08544447273015976,
800
+ "loss": 0.3244,
801
+ "step": 710
802
+ },
803
+ {
804
+ "epoch": 1.1555823051459524,
805
+ "grad_norm": 0.263671875,
806
+ "learning_rate": 3.8601613599867156e-05,
807
+ "logps_logqs/chosen": 0.07930372655391693,
808
+ "logqs/chosen": -0.8030117154121399,
809
+ "logqs/rejected": -0.878372848033905,
810
+ "logqs_logps/rejected": 0.08530044555664062,
811
+ "loss": 0.3244,
812
+ "step": 720
813
+ },
814
+ {
815
+ "epoch": 1.1716320593840908,
816
+ "grad_norm": 0.265625,
817
+ "learning_rate": 3.8207478491519216e-05,
818
+ "logps_logqs/chosen": 0.07744885236024857,
819
+ "logqs/chosen": -0.8023334741592407,
820
+ "logqs/rejected": -0.8822676539421082,
821
+ "logqs_logps/rejected": 0.08438443392515182,
822
+ "loss": 0.3258,
823
+ "step": 730
824
+ },
825
+ {
826
+ "epoch": 1.187681813622229,
827
+ "grad_norm": 0.27734375,
828
+ "learning_rate": 3.780873599239044e-05,
829
+ "logps_logqs/chosen": 0.07315745949745178,
830
+ "logqs/chosen": -0.8033607602119446,
831
+ "logqs/rejected": -0.8938726186752319,
832
+ "logqs_logps/rejected": 0.08519093692302704,
833
+ "loss": 0.327,
834
+ "step": 740
835
+ },
836
+ {
837
+ "epoch": 1.203731567860367,
838
+ "grad_norm": 0.27734375,
839
+ "learning_rate": 3.740552520265167e-05,
840
+ "logps_logqs/chosen": 0.0805806964635849,
841
+ "logqs/chosen": -0.8070894479751587,
842
+ "logqs/rejected": -0.8942106366157532,
843
+ "logqs_logps/rejected": 0.0853462964296341,
844
+ "loss": 0.3277,
845
+ "step": 750
846
+ },
847
+ {
848
+ "epoch": 1.2197813220985054,
849
+ "grad_norm": 0.2578125,
850
+ "learning_rate": 3.699798678122403e-05,
851
+ "logps_logqs/chosen": 0.08243963867425919,
852
+ "logqs/chosen": -0.8198779225349426,
853
+ "logqs/rejected": -0.9114899635314941,
854
+ "logqs_logps/rejected": 0.08301108330488205,
855
+ "loss": 0.3246,
856
+ "step": 760
857
+ },
858
+ {
859
+ "epoch": 1.2358310763366436,
860
+ "grad_norm": 0.24609375,
861
+ "learning_rate": 3.6586262896710476e-05,
862
+ "logps_logqs/chosen": 0.07522697746753693,
863
+ "logqs/chosen": -0.7997868657112122,
864
+ "logqs/rejected": -0.8849021792411804,
865
+ "logqs_logps/rejected": 0.08433938026428223,
866
+ "loss": 0.3225,
867
+ "step": 770
868
+ },
869
+ {
870
+ "epoch": 1.2518808305747817,
871
+ "grad_norm": 0.2578125,
872
+ "learning_rate": 3.61704971778007e-05,
873
+ "logps_logqs/chosen": 0.07380663603544235,
874
+ "logqs/chosen": -0.7977632284164429,
875
+ "logqs/rejected": -0.9076175689697266,
876
+ "logqs_logps/rejected": 0.08456581830978394,
877
+ "loss": 0.3231,
878
+ "step": 780
879
+ },
880
+ {
881
+ "epoch": 1.26793058481292,
882
+ "grad_norm": 0.267578125,
883
+ "learning_rate": 3.575083466316664e-05,
884
+ "logps_logqs/chosen": 0.07891708612442017,
885
+ "logqs/chosen": -0.82396399974823,
886
+ "logqs/rejected": -0.8780908584594727,
887
+ "logqs_logps/rejected": 0.08443116396665573,
888
+ "loss": 0.3279,
889
+ "step": 790
890
+ },
891
+ {
892
+ "epoch": 1.2839803390510582,
893
+ "grad_norm": 0.265625,
894
+ "learning_rate": 3.532742175086621e-05,
895
+ "logps_logqs/chosen": 0.0780521035194397,
896
+ "logqs/chosen": -0.8043760061264038,
897
+ "logqs/rejected": -0.874092698097229,
898
+ "logqs_logps/rejected": 0.08614115417003632,
899
+ "loss": 0.3218,
900
+ "step": 800
901
+ },
902
+ {
903
+ "epoch": 1.3000300932891964,
904
+ "grad_norm": 0.2470703125,
905
+ "learning_rate": 3.490040614727272e-05,
906
+ "logps_logqs/chosen": 0.07666923850774765,
907
+ "logqs/chosen": -0.8054482340812683,
908
+ "logqs/rejected": -0.8948068618774414,
909
+ "logqs_logps/rejected": 0.08540605008602142,
910
+ "loss": 0.3189,
911
+ "step": 810
912
+ },
913
+ {
914
+ "epoch": 1.3160798475273348,
915
+ "grad_norm": 0.26953125,
916
+ "learning_rate": 3.446993681554797e-05,
917
+ "logps_logqs/chosen": 0.07618199288845062,
918
+ "logqs/chosen": -0.7989985942840576,
919
+ "logqs/rejected": -0.9127970933914185,
920
+ "logqs_logps/rejected": 0.08587857335805893,
921
+ "loss": 0.3221,
922
+ "step": 820
923
+ },
924
+ {
925
+ "epoch": 1.332129601765473,
926
+ "grad_norm": 0.263671875,
927
+ "learning_rate": 3.403616392367681e-05,
928
+ "logps_logqs/chosen": 0.0786433070898056,
929
+ "logqs/chosen": -0.8273786306381226,
930
+ "logqs/rejected": -0.9085508584976196,
931
+ "logqs_logps/rejected": 0.08382102847099304,
932
+ "loss": 0.3242,
933
+ "step": 830
934
+ },
935
+ {
936
+ "epoch": 1.3481793560036113,
937
+ "grad_norm": 0.28125,
938
+ "learning_rate": 3.3599238792081575e-05,
939
+ "logps_logqs/chosen": 0.08081017434597015,
940
+ "logqs/chosen": -0.8143576383590698,
941
+ "logqs/rejected": -0.8868357539176941,
942
+ "logqs_logps/rejected": 0.08583888411521912,
943
+ "loss": 0.3232,
944
+ "step": 840
945
+ },
946
+ {
947
+ "epoch": 1.3642291102417494,
948
+ "grad_norm": 0.30859375,
949
+ "learning_rate": 3.315931384083431e-05,
950
+ "logps_logqs/chosen": 0.07726846635341644,
951
+ "logqs/chosen": -0.8076990842819214,
952
+ "logqs/rejected": -0.9137754440307617,
953
+ "logqs_logps/rejected": 0.08542170375585556,
954
+ "loss": 0.3269,
955
+ "step": 850
956
+ },
957
+ {
958
+ "epoch": 1.3802788644798878,
959
+ "grad_norm": 0.271484375,
960
+ "learning_rate": 3.2716542536485474e-05,
961
+ "logps_logqs/chosen": 0.07718624174594879,
962
+ "logqs/chosen": -0.8211753964424133,
963
+ "logqs/rejected": -0.9037491083145142,
964
+ "logqs_logps/rejected": 0.08567257225513458,
965
+ "loss": 0.3245,
966
+ "step": 860
967
+ },
968
+ {
969
+ "epoch": 1.396328618718026,
970
+ "grad_norm": 0.259765625,
971
+ "learning_rate": 3.2271079338527626e-05,
972
+ "logps_logqs/chosen": 0.07549947500228882,
973
+ "logqs/chosen": -0.8031107187271118,
974
+ "logqs/rejected": -0.904284656047821,
975
+ "logqs_logps/rejected": 0.08366312086582184,
976
+ "loss": 0.3196,
977
+ "step": 870
978
+ },
979
+ {
980
+ "epoch": 1.412378372956164,
981
+ "grad_norm": 0.263671875,
982
+ "learning_rate": 3.1823079645512655e-05,
983
+ "logps_logqs/chosen": 0.07497793436050415,
984
+ "logqs/chosen": -0.8042508959770203,
985
+ "logqs/rejected": -0.9088570475578308,
986
+ "logqs_logps/rejected": 0.08382809907197952,
987
+ "loss": 0.321,
988
+ "step": 880
989
+ },
990
+ {
991
+ "epoch": 1.4284281271943025,
992
+ "grad_norm": 0.2421875,
993
+ "learning_rate": 3.137269974084139e-05,
994
+ "logps_logqs/chosen": 0.07816600799560547,
995
+ "logqs/chosen": -0.8011495471000671,
996
+ "logqs/rejected": -0.9165712594985962,
997
+ "logqs_logps/rejected": 0.08399650454521179,
998
+ "loss": 0.3214,
999
+ "step": 890
1000
+ },
1001
+ {
1002
+ "epoch": 1.4444778814324406,
1003
+ "grad_norm": 0.248046875,
1004
+ "learning_rate": 3.092009673824469e-05,
1005
+ "logps_logqs/chosen": 0.0796435996890068,
1006
+ "logqs/chosen": -0.8250038027763367,
1007
+ "logqs/rejected": -0.894701361656189,
1008
+ "logqs_logps/rejected": 0.0849834531545639,
1009
+ "loss": 0.3299,
1010
+ "step": 900
1011
+ },
1012
+ {
1013
+ "epoch": 1.4605276356705787,
1014
+ "grad_norm": 0.26953125,
1015
+ "learning_rate": 3.0465428526974665e-05,
1016
+ "logps_logqs/chosen": 0.0747985765337944,
1017
+ "logqs/chosen": -0.7987441420555115,
1018
+ "logqs/rejected": -0.8858783841133118,
1019
+ "logqs_logps/rejected": 0.08518994599580765,
1020
+ "loss": 0.3198,
1021
+ "step": 910
1022
+ },
1023
+ {
1024
+ "epoch": 1.4765773899087171,
1025
+ "grad_norm": 0.25390625,
1026
+ "learning_rate": 3.000885371672554e-05,
1027
+ "logps_logqs/chosen": 0.0736977607011795,
1028
+ "logqs/chosen": -0.796042799949646,
1029
+ "logqs/rejected": -0.8840726017951965,
1030
+ "logqs_logps/rejected": 0.08356060087680817,
1031
+ "loss": 0.3189,
1032
+ "step": 920
1033
+ },
1034
+ {
1035
+ "epoch": 1.4926271441468553,
1036
+ "grad_norm": 0.2333984375,
1037
+ "learning_rate": 2.9550531582303082e-05,
1038
+ "logps_logqs/chosen": 0.07697046548128128,
1039
+ "logqs/chosen": -0.8012852668762207,
1040
+ "logqs/rejected": -0.8978139758110046,
1041
+ "logqs_logps/rejected": 0.08473887294530869,
1042
+ "loss": 0.3234,
1043
+ "step": 930
1044
+ },
1045
+ {
1046
+ "epoch": 1.5086768983849934,
1047
+ "grad_norm": 0.26171875,
1048
+ "learning_rate": 2.909062200806208e-05,
1049
+ "logps_logqs/chosen": 0.07491417229175568,
1050
+ "logqs/chosen": -0.8042458295822144,
1051
+ "logqs/rejected": -0.9043086767196655,
1052
+ "logqs_logps/rejected": 0.08307308703660965,
1053
+ "loss": 0.3185,
1054
+ "step": 940
1055
+ },
1056
+ {
1057
+ "epoch": 1.5247266526231318,
1058
+ "grad_norm": 0.24609375,
1059
+ "learning_rate": 2.8629285432131083e-05,
1060
+ "logps_logqs/chosen": 0.07444656640291214,
1061
+ "logqs/chosen": -0.7999377250671387,
1062
+ "logqs/rejected": -0.8958683013916016,
1063
+ "logqs_logps/rejected": 0.08302817493677139,
1064
+ "loss": 0.3192,
1065
+ "step": 950
1066
+ },
1067
+ {
1068
+ "epoch": 1.54077640686127,
1069
+ "grad_norm": 0.248046875,
1070
+ "learning_rate": 2.8166682790444116e-05,
1071
+ "logps_logqs/chosen": 0.0736972838640213,
1072
+ "logqs/chosen": -0.8029756546020508,
1073
+ "logqs/rejected": -0.9172306060791016,
1074
+ "logqs_logps/rejected": 0.08177176862955093,
1075
+ "loss": 0.3192,
1076
+ "step": 960
1077
+ },
1078
+ {
1079
+ "epoch": 1.556826161099408,
1080
+ "grad_norm": 0.2578125,
1081
+ "learning_rate": 2.7702975460598547e-05,
1082
+ "logps_logqs/chosen": 0.07327345758676529,
1083
+ "logqs/chosen": -0.7889487147331238,
1084
+ "logqs/rejected": -0.8995023965835571,
1085
+ "logqs_logps/rejected": 0.08234850317239761,
1086
+ "loss": 0.3179,
1087
+ "step": 970
1088
+ },
1089
+ {
1090
+ "epoch": 1.5728759153375464,
1091
+ "grad_norm": 0.263671875,
1092
+ "learning_rate": 2.723832520555905e-05,
1093
+ "logps_logqs/chosen": 0.07713175565004349,
1094
+ "logqs/chosen": -0.809069037437439,
1095
+ "logqs/rejected": -0.9176934957504272,
1096
+ "logqs_logps/rejected": 0.08256009966135025,
1097
+ "loss": 0.3216,
1098
+ "step": 980
1099
+ },
1100
+ {
1101
+ "epoch": 1.5889256695756846,
1102
+ "grad_norm": 0.240234375,
1103
+ "learning_rate": 2.677289411722702e-05,
1104
+ "logps_logqs/chosen": 0.07451427727937698,
1105
+ "logqs/chosen": -0.8091384172439575,
1106
+ "logqs/rejected": -0.9061697721481323,
1107
+ "logqs_logps/rejected": 0.08387144654989243,
1108
+ "loss": 0.3227,
1109
+ "step": 990
1110
+ },
1111
+ {
1112
+ "epoch": 1.6049754238138227,
1113
+ "grad_norm": 0.259765625,
1114
+ "learning_rate": 2.63068445598953e-05,
1115
+ "logps_logqs/chosen": 0.07487618923187256,
1116
+ "logqs/chosen": -0.8033574819564819,
1117
+ "logqs/rejected": -0.9179302453994751,
1118
+ "logqs_logps/rejected": 0.08198346197605133,
1119
+ "loss": 0.3233,
1120
+ "step": 1000
1121
+ },
1122
+ {
1123
+ "epoch": 1.6210251780519611,
1124
+ "grad_norm": 0.251953125,
1125
+ "learning_rate": 2.5840339113607854e-05,
1126
+ "logps_logqs/chosen": 0.07482868432998657,
1127
+ "logqs/chosen": -0.7901092767715454,
1128
+ "logqs/rejected": -0.8936401605606079,
1129
+ "logqs_logps/rejected": 0.08298007398843765,
1130
+ "loss": 0.32,
1131
+ "step": 1010
1132
+ },
1133
+ {
1134
+ "epoch": 1.6370749322900993,
1135
+ "grad_norm": 0.2578125,
1136
+ "learning_rate": 2.53735405174442e-05,
1137
+ "logps_logqs/chosen": 0.07392865419387817,
1138
+ "logqs/chosen": -0.7897070646286011,
1139
+ "logqs/rejected": -0.9076752662658691,
1140
+ "logqs_logps/rejected": 0.08304780721664429,
1141
+ "loss": 0.3197,
1142
+ "step": 1020
1143
+ },
1144
+ {
1145
+ "epoch": 1.6531246865282374,
1146
+ "grad_norm": 0.25390625,
1147
+ "learning_rate": 2.490661161274835e-05,
1148
+ "logps_logqs/chosen": 0.07797589153051376,
1149
+ "logqs/chosen": -0.8021060824394226,
1150
+ "logqs/rejected": -0.9039047360420227,
1151
+ "logqs_logps/rejected": 0.08419740200042725,
1152
+ "loss": 0.3199,
1153
+ "step": 1030
1154
+ },
1155
+ {
1156
+ "epoch": 1.6691744407663758,
1157
+ "grad_norm": 0.25390625,
1158
+ "learning_rate": 2.443971528632205e-05,
1159
+ "logps_logqs/chosen": 0.07501687109470367,
1160
+ "logqs/chosen": -0.8008750081062317,
1161
+ "logqs/rejected": -0.8964029550552368,
1162
+ "logqs_logps/rejected": 0.08230260759592056,
1163
+ "loss": 0.3169,
1164
+ "step": 1040
1165
+ },
1166
+ {
1167
+ "epoch": 1.6852241950045141,
1168
+ "grad_norm": 0.251953125,
1169
+ "learning_rate": 2.3973014413602238e-05,
1170
+ "logps_logqs/chosen": 0.07347197085618973,
1171
+ "logqs/chosen": -0.8004202842712402,
1172
+ "logqs/rejected": -0.8897308111190796,
1173
+ "logqs_logps/rejected": 0.08417828381061554,
1174
+ "loss": 0.3197,
1175
+ "step": 1050
1176
+ },
1177
+ {
1178
+ "epoch": 1.701273949242652,
1179
+ "grad_norm": 0.25390625,
1180
+ "learning_rate": 2.3506671801842364e-05,
1181
+ "logps_logqs/chosen": 0.07608149200677872,
1182
+ "logqs/chosen": -0.8141935467720032,
1183
+ "logqs/rejected": -0.9073457717895508,
1184
+ "logqs_logps/rejected": 0.08230859041213989,
1185
+ "loss": 0.3193,
1186
+ "step": 1060
1187
+ },
1188
+ {
1189
+ "epoch": 1.7173237034807904,
1190
+ "grad_norm": 0.251953125,
1191
+ "learning_rate": 2.3040850133317597e-05,
1192
+ "logps_logqs/chosen": 0.07689784467220306,
1193
+ "logqs/chosen": -0.8076275587081909,
1194
+ "logqs/rejected": -0.9122416377067566,
1195
+ "logqs_logps/rejected": 0.08308029919862747,
1196
+ "loss": 0.3223,
1197
+ "step": 1070
1198
+ },
1199
+ {
1200
+ "epoch": 1.7333734577189288,
1201
+ "grad_norm": 0.2412109375,
1202
+ "learning_rate": 2.2575711908573548e-05,
1203
+ "logps_logqs/chosen": 0.07234277576208115,
1204
+ "logqs/chosen": -0.7936676740646362,
1205
+ "logqs/rejected": -0.9038996696472168,
1206
+ "logqs_logps/rejected": 0.08316074311733246,
1207
+ "loss": 0.3167,
1208
+ "step": 1080
1209
+ },
1210
+ {
1211
+ "epoch": 1.749423211957067,
1212
+ "grad_norm": 0.251953125,
1213
+ "learning_rate": 2.2111419389738435e-05,
1214
+ "logps_logqs/chosen": 0.07605086266994476,
1215
+ "logqs/chosen": -0.8008819818496704,
1216
+ "logqs/rejected": -0.8876243829727173,
1217
+ "logqs_logps/rejected": 0.08395352214574814,
1218
+ "loss": 0.3169,
1219
+ "step": 1090
1220
+ },
1221
+ {
1222
+ "epoch": 1.765472966195205,
1223
+ "grad_norm": 0.244140625,
1224
+ "learning_rate": 2.1648134543918423e-05,
1225
+ "logps_logqs/chosen": 0.07533862441778183,
1226
+ "logqs/chosen": -0.7902143597602844,
1227
+ "logqs/rejected": -0.8612885475158691,
1228
+ "logqs_logps/rejected": 0.0841139703989029,
1229
+ "loss": 0.3174,
1230
+ "step": 1100
1231
+ },
1232
+ {
1233
+ "epoch": 1.7815227204333435,
1234
+ "grad_norm": 0.2373046875,
1235
+ "learning_rate": 2.1186018986695842e-05,
1236
+ "logps_logqs/chosen": 0.07465896010398865,
1237
+ "logqs/chosen": -0.8092859387397766,
1238
+ "logqs/rejected": -0.9027106165885925,
1239
+ "logqs_logps/rejected": 0.08286880701780319,
1240
+ "loss": 0.3181,
1241
+ "step": 1110
1242
+ },
1243
+ {
1244
+ "epoch": 1.7975724746714816,
1245
+ "grad_norm": 0.2431640625,
1246
+ "learning_rate": 2.0725233925750063e-05,
1247
+ "logps_logqs/chosen": 0.0745125412940979,
1248
+ "logqs/chosen": -0.8020778894424438,
1249
+ "logqs/rejected": -0.8988272547721863,
1250
+ "logqs_logps/rejected": 0.082740917801857,
1251
+ "loss": 0.3153,
1252
+ "step": 1120
1253
+ },
1254
+ {
1255
+ "epoch": 1.8136222289096198,
1256
+ "grad_norm": 0.26171875,
1257
+ "learning_rate": 2.026594010462068e-05,
1258
+ "logps_logqs/chosen": 0.07593352347612381,
1259
+ "logqs/chosen": -0.8027118444442749,
1260
+ "logqs/rejected": -0.9119024276733398,
1261
+ "logqs_logps/rejected": 0.08280286937952042,
1262
+ "loss": 0.3207,
1263
+ "step": 1130
1264
+ },
1265
+ {
1266
+ "epoch": 1.8296719831477581,
1267
+ "grad_norm": 0.251953125,
1268
+ "learning_rate": 1.980829774663256e-05,
1269
+ "logps_logqs/chosen": 0.07631193101406097,
1270
+ "logqs/chosen": -0.8121039271354675,
1271
+ "logqs/rejected": -0.908685028553009,
1272
+ "logqs_logps/rejected": 0.08407546579837799,
1273
+ "loss": 0.3198,
1274
+ "step": 1140
1275
+ },
1276
+ {
1277
+ "epoch": 1.8457217373858963,
1278
+ "grad_norm": 0.2431640625,
1279
+ "learning_rate": 1.9352466499002422e-05,
1280
+ "logps_logqs/chosen": 0.07544290274381638,
1281
+ "logqs/chosen": -0.8096615076065063,
1282
+ "logqs/rejected": -0.9020143747329712,
1283
+ "logqs_logps/rejected": 0.08248680830001831,
1284
+ "loss": 0.3198,
1285
+ "step": 1150
1286
+ },
1287
+ {
1288
+ "epoch": 1.8617714916240344,
1289
+ "grad_norm": 0.2353515625,
1290
+ "learning_rate": 1.8898605377146383e-05,
1291
+ "logps_logqs/chosen": 0.07422982156276703,
1292
+ "logqs/chosen": -0.8104985952377319,
1293
+ "logqs/rejected": -0.9090179204940796,
1294
+ "logqs_logps/rejected": 0.08247785270214081,
1295
+ "loss": 0.3183,
1296
+ "step": 1160
1297
+ },
1298
+ {
1299
+ "epoch": 1.8778212458621728,
1300
+ "grad_norm": 0.271484375,
1301
+ "learning_rate": 1.8446872709207847e-05,
1302
+ "logps_logqs/chosen": 0.07435441762208939,
1303
+ "logqs/chosen": -0.8137333989143372,
1304
+ "logqs/rejected": -0.9299784898757935,
1305
+ "logqs_logps/rejected": 0.08275195211172104,
1306
+ "loss": 0.3227,
1307
+ "step": 1170
1308
+ },
1309
+ {
1310
+ "epoch": 1.893871000100311,
1311
+ "grad_norm": 0.23828125,
1312
+ "learning_rate": 1.799742608082519e-05,
1313
+ "logps_logqs/chosen": 0.0697832927107811,
1314
+ "logqs/chosen": -0.7819542288780212,
1315
+ "logqs/rejected": -0.8906014561653137,
1316
+ "logqs_logps/rejected": 0.08177825063467026,
1317
+ "loss": 0.312,
1318
+ "step": 1180
1319
+ },
1320
+ {
1321
+ "epoch": 1.909920754338449,
1322
+ "grad_norm": 0.255859375,
1323
+ "learning_rate": 1.7550422280158513e-05,
1324
+ "logps_logqs/chosen": 0.07729648053646088,
1325
+ "logqs/chosen": -0.8102595210075378,
1326
+ "logqs/rejected": -0.904281497001648,
1327
+ "logqs_logps/rejected": 0.0822812020778656,
1328
+ "loss": 0.3192,
1329
+ "step": 1190
1330
+ },
1331
+ {
1332
+ "epoch": 1.9259705085765875,
1333
+ "grad_norm": 0.2451171875,
1334
+ "learning_rate": 1.7106017243194487e-05,
1335
+ "logps_logqs/chosen": 0.07507346570491791,
1336
+ "logqs/chosen": -0.7959727048873901,
1337
+ "logqs/rejected": -0.9095916748046875,
1338
+ "logqs_logps/rejected": 0.08093559741973877,
1339
+ "loss": 0.3228,
1340
+ "step": 1200
1341
+ },
1342
+ {
1343
+ "epoch": 1.9420202628147256,
1344
+ "grad_norm": 0.251953125,
1345
+ "learning_rate": 1.6664365999348594e-05,
1346
+ "logps_logqs/chosen": 0.07413261383771896,
1347
+ "logqs/chosen": -0.7935149073600769,
1348
+ "logqs/rejected": -0.8980931043624878,
1349
+ "logqs_logps/rejected": 0.08442027121782303,
1350
+ "loss": 0.3173,
1351
+ "step": 1210
1352
+ },
1353
+ {
1354
+ "epoch": 1.9580700170528638,
1355
+ "grad_norm": 0.2421875,
1356
+ "learning_rate": 1.6225622617383494e-05,
1357
+ "logps_logqs/chosen": 0.07162965834140778,
1358
+ "logqs/chosen": -0.7896697521209717,
1359
+ "logqs/rejected": -0.8827974200248718,
1360
+ "logqs_logps/rejected": 0.08332808315753937,
1361
+ "loss": 0.3138,
1362
+ "step": 1220
1363
+ },
1364
+ {
1365
+ "epoch": 1.9741197712910021,
1366
+ "grad_norm": 0.2451171875,
1367
+ "learning_rate": 1.578994015166263e-05,
1368
+ "logps_logqs/chosen": 0.07460381835699081,
1369
+ "logqs/chosen": -0.8117923736572266,
1370
+ "logqs/rejected": -0.9152690172195435,
1371
+ "logqs_logps/rejected": 0.0810333639383316,
1372
+ "loss": 0.3209,
1373
+ "step": 1230
1374
+ },
1375
+ {
1376
+ "epoch": 1.9901695255291403,
1377
+ "grad_norm": 0.2431640625,
1378
+ "learning_rate": 1.535747058875765e-05,
1379
+ "logps_logqs/chosen": 0.07367164641618729,
1380
+ "logqs/chosen": -0.7960913777351379,
1381
+ "logqs/rejected": -0.8929139375686646,
1382
+ "logqs_logps/rejected": 0.08183646202087402,
1383
+ "loss": 0.3162,
1384
+ "step": 1240
1385
+ },
1386
+ {
1387
+ "epoch": 2.0062192797672784,
1388
+ "grad_norm": 0.2333984375,
1389
+ "learning_rate": 1.4928364794428307e-05,
1390
+ "logps_logqs/chosen": 0.07295754551887512,
1391
+ "logqs/chosen": -0.8024552464485168,
1392
+ "logqs/rejected": -0.918504536151886,
1393
+ "logqs_logps/rejected": 0.08203531801700592,
1394
+ "loss": 0.314,
1395
+ "step": 1250
1396
+ },
1397
+ {
1398
+ "epoch": 2.022269034005417,
1399
+ "grad_norm": 0.232421875,
1400
+ "learning_rate": 1.4502772460993385e-05,
1401
+ "logps_logqs/chosen": 0.073900006711483,
1402
+ "logqs/chosen": -0.7975751757621765,
1403
+ "logqs/rejected": -0.9003852605819702,
1404
+ "logqs_logps/rejected": 0.08287613093852997,
1405
+ "loss": 0.3139,
1406
+ "step": 1260
1407
+ },
1408
+ {
1409
+ "epoch": 2.038318788243555,
1410
+ "grad_norm": 0.2333984375,
1411
+ "learning_rate": 1.4080842055110993e-05,
1412
+ "logps_logqs/chosen": 0.07410914450883865,
1413
+ "logqs/chosen": -0.789171040058136,
1414
+ "logqs/rejected": -0.8948004841804504,
1415
+ "logqs_logps/rejected": 0.08315090835094452,
1416
+ "loss": 0.315,
1417
+ "step": 1270
1418
+ },
1419
+ {
1420
+ "epoch": 2.054368542481693,
1421
+ "grad_norm": 0.2353515625,
1422
+ "learning_rate": 1.3662720765986341e-05,
1423
+ "logps_logqs/chosen": 0.0750800222158432,
1424
+ "logqs/chosen": -0.8148080706596375,
1425
+ "logqs/rejected": -0.9173944592475891,
1426
+ "logqs_logps/rejected": 0.08202828466892242,
1427
+ "loss": 0.3141,
1428
+ "step": 1280
1429
+ },
1430
+ {
1431
+ "epoch": 2.0704182967198315,
1432
+ "grad_norm": 0.244140625,
1433
+ "learning_rate": 1.3248554454025275e-05,
1434
+ "logps_logqs/chosen": 0.07371431589126587,
1435
+ "logqs/chosen": -0.7904887795448303,
1436
+ "logqs/rejected": -0.892736554145813,
1437
+ "logqs_logps/rejected": 0.08251521736383438,
1438
+ "loss": 0.3121,
1439
+ "step": 1290
1440
+ },
1441
+ {
1442
+ "epoch": 2.08646805095797,
1443
+ "grad_norm": 0.236328125,
1444
+ "learning_rate": 1.2838487599951243e-05,
1445
+ "logps_logqs/chosen": 0.07491550594568253,
1446
+ "logqs/chosen": -0.8070290684700012,
1447
+ "logqs/rejected": -0.8995240926742554,
1448
+ "logqs_logps/rejected": 0.08239687979221344,
1449
+ "loss": 0.3139,
1450
+ "step": 1300
1451
+ },
1452
+ {
1453
+ "epoch": 2.1025178051961078,
1454
+ "grad_norm": 0.2353515625,
1455
+ "learning_rate": 1.2432663254403638e-05,
1456
+ "logps_logqs/chosen": 0.07226058095693588,
1457
+ "logqs/chosen": -0.8035115003585815,
1458
+ "logqs/rejected": -0.8938866853713989,
1459
+ "logqs_logps/rejected": 0.08264483511447906,
1460
+ "loss": 0.3162,
1461
+ "step": 1310
1462
+ },
1463
+ {
1464
+ "epoch": 2.118567559434246,
1465
+ "grad_norm": 0.232421875,
1466
+ "learning_rate": 1.2031222988034967e-05,
1467
+ "logps_logqs/chosen": 0.07458813488483429,
1468
+ "logqs/chosen": -0.7981353998184204,
1469
+ "logqs/rejected": -0.8914963006973267,
1470
+ "logqs_logps/rejected": 0.08298441767692566,
1471
+ "loss": 0.3121,
1472
+ "step": 1320
1473
+ },
1474
+ {
1475
+ "epoch": 2.1346173136723845,
1476
+ "grad_norm": 0.2255859375,
1477
+ "learning_rate": 1.1634306842124423e-05,
1478
+ "logps_logqs/chosen": 0.07301259785890579,
1479
+ "logqs/chosen": -0.7957206964492798,
1480
+ "logqs/rejected": -0.9006513357162476,
1481
+ "logqs_logps/rejected": 0.08207239955663681,
1482
+ "loss": 0.3104,
1483
+ "step": 1330
1484
+ },
1485
+ {
1486
+ "epoch": 2.1506670679105224,
1487
+ "grad_norm": 0.2412109375,
1488
+ "learning_rate": 1.1242053279724762e-05,
1489
+ "logps_logqs/chosen": 0.07079671323299408,
1490
+ "logqs/chosen": -0.7900751233100891,
1491
+ "logqs/rejected": -0.9003415107727051,
1492
+ "logqs_logps/rejected": 0.08099430054426193,
1493
+ "loss": 0.3096,
1494
+ "step": 1340
1495
+ },
1496
+ {
1497
+ "epoch": 2.166716822148661,
1498
+ "grad_norm": 0.2265625,
1499
+ "learning_rate": 1.0854599137359953e-05,
1500
+ "logps_logqs/chosen": 0.07582630217075348,
1501
+ "logqs/chosen": -0.8164023160934448,
1502
+ "logqs/rejected": -0.9069350361824036,
1503
+ "logqs_logps/rejected": 0.08237835019826889,
1504
+ "loss": 0.3158,
1505
+ "step": 1350
1506
+ },
1507
+ {
1508
+ "epoch": 2.182766576386799,
1509
+ "grad_norm": 0.2255859375,
1510
+ "learning_rate": 1.0472079577290111e-05,
1511
+ "logps_logqs/chosen": 0.07026050239801407,
1512
+ "logqs/chosen": -0.7865276336669922,
1513
+ "logqs/rejected": -0.9271472096443176,
1514
+ "logqs_logps/rejected": 0.08012039959430695,
1515
+ "loss": 0.3125,
1516
+ "step": 1360
1517
+ },
1518
+ {
1519
+ "epoch": 2.198816330624937,
1520
+ "grad_norm": 0.2314453125,
1521
+ "learning_rate": 1.009462804036059e-05,
1522
+ "logps_logqs/chosen": 0.07350893318653107,
1523
+ "logqs/chosen": -0.7845043540000916,
1524
+ "logqs/rejected": -0.8784573674201965,
1525
+ "logqs_logps/rejected": 0.08172748982906342,
1526
+ "loss": 0.3118,
1527
+ "step": 1370
1528
+ },
1529
+ {
1530
+ "epoch": 2.2148660848630755,
1531
+ "grad_norm": 0.23828125,
1532
+ "learning_rate": 9.722376199451436e-06,
1533
+ "logps_logqs/chosen": 0.07753650844097137,
1534
+ "logqs/chosen": -0.8113786578178406,
1535
+ "logqs/rejected": -0.895952582359314,
1536
+ "logqs_logps/rejected": 0.08141981810331345,
1537
+ "loss": 0.3144,
1538
+ "step": 1380
1539
+ },
1540
+ {
1541
+ "epoch": 2.230915839101214,
1542
+ "grad_norm": 0.23046875,
1543
+ "learning_rate": 9.35545391354378e-06,
1544
+ "logps_logqs/chosen": 0.07038865983486176,
1545
+ "logqs/chosen": -0.7959168553352356,
1546
+ "logqs/rejected": -0.8996925354003906,
1547
+ "logqs_logps/rejected": 0.08161251246929169,
1548
+ "loss": 0.3102,
1549
+ "step": 1390
1550
+ },
1551
+ {
1552
+ "epoch": 2.246965593339352,
1553
+ "grad_norm": 0.2314453125,
1554
+ "learning_rate": 8.993989182418824e-06,
1555
+ "logps_logqs/chosen": 0.0729217380285263,
1556
+ "logqs/chosen": -0.8092435598373413,
1557
+ "logqs/rejected": -0.8962046504020691,
1558
+ "logqs_logps/rejected": 0.08081961423158646,
1559
+ "loss": 0.3126,
1560
+ "step": 1400
1561
+ },
1562
+ {
1563
+ "epoch": 2.26301534757749,
1564
+ "grad_norm": 0.236328125,
1565
+ "learning_rate": 8.63810810200556e-06,
1566
+ "logps_logqs/chosen": 0.07263143360614777,
1567
+ "logqs/chosen": -0.7884143590927124,
1568
+ "logqs/rejected": -0.9198802709579468,
1569
+ "logqs_logps/rejected": 0.08146072924137115,
1570
+ "loss": 0.3116,
1571
+ "step": 1410
1572
+ },
1573
+ {
1574
+ "epoch": 2.2790651018156285,
1575
+ "grad_norm": 0.23046875,
1576
+ "learning_rate": 8.287934820392498e-06,
1577
+ "logps_logqs/chosen": 0.07447274029254913,
1578
+ "logqs/chosen": -0.8072949647903442,
1579
+ "logqs/rejected": -0.9363552927970886,
1580
+ "logqs_logps/rejected": 0.08067592978477478,
1581
+ "loss": 0.3122,
1582
+ "step": 1420
1583
+ },
1584
+ {
1585
+ "epoch": 2.295114856053767,
1586
+ "grad_norm": 0.2275390625,
1587
+ "learning_rate": 7.943591494519016e-06,
1588
+ "logps_logqs/chosen": 0.0729929506778717,
1589
+ "logqs/chosen": -0.8074385523796082,
1590
+ "logqs/rejected": -0.9285086393356323,
1591
+ "logqs_logps/rejected": 0.08008907735347748,
1592
+ "loss": 0.314,
1593
+ "step": 1430
1594
+ },
1595
+ {
1596
+ "epoch": 2.311164610291905,
1597
+ "grad_norm": 0.2197265625,
1598
+ "learning_rate": 7.60519824756124e-06,
1599
+ "logps_logqs/chosen": 0.07292158156633377,
1600
+ "logqs/chosen": -0.7946223616600037,
1601
+ "logqs/rejected": -0.9008995890617371,
1602
+ "logqs_logps/rejected": 0.08113256096839905,
1603
+ "loss": 0.3134,
1604
+ "step": 1440
1605
+ },
1606
+ {
1607
+ "epoch": 2.327214364530043,
1608
+ "grad_norm": 0.23046875,
1609
+ "learning_rate": 7.272873127027449e-06,
1610
+ "logps_logqs/chosen": 0.07243537902832031,
1611
+ "logqs/chosen": -0.7918037176132202,
1612
+ "logqs/rejected": -0.8832144737243652,
1613
+ "logqs_logps/rejected": 0.08229474723339081,
1614
+ "loss": 0.3128,
1615
+ "step": 1450
1616
+ },
1617
+ {
1618
+ "epoch": 2.3432641187681815,
1619
+ "grad_norm": 0.23046875,
1620
+ "learning_rate": 6.946732063577488e-06,
1621
+ "logps_logqs/chosen": 0.07624879479408264,
1622
+ "logqs/chosen": -0.8100885152816772,
1623
+ "logqs/rejected": -0.8934513330459595,
1624
+ "logqs_logps/rejected": 0.0827435851097107,
1625
+ "loss": 0.3115,
1626
+ "step": 1460
1627
+ },
1628
+ {
1629
+ "epoch": 2.3593138730063195,
1630
+ "grad_norm": 0.2314453125,
1631
+ "learning_rate": 6.6268888305807296e-06,
1632
+ "logps_logqs/chosen": 0.07390271872282028,
1633
+ "logqs/chosen": -0.792887806892395,
1634
+ "logqs/rejected": -0.8847257494926453,
1635
+ "logqs_logps/rejected": 0.08261798322200775,
1636
+ "loss": 0.3104,
1637
+ "step": 1470
1638
+ },
1639
+ {
1640
+ "epoch": 2.375363627244458,
1641
+ "grad_norm": 0.228515625,
1642
+ "learning_rate": 6.313455004426577e-06,
1643
+ "logps_logqs/chosen": 0.07358037680387497,
1644
+ "logqs/chosen": -0.7838066816329956,
1645
+ "logqs/rejected": -0.9078797101974487,
1646
+ "logqs_logps/rejected": 0.08071611076593399,
1647
+ "loss": 0.3106,
1648
+ "step": 1480
1649
+ },
1650
+ {
1651
+ "epoch": 2.391413381482596,
1652
+ "grad_norm": 0.2373046875,
1653
+ "learning_rate": 6.0065399256013204e-06,
1654
+ "logps_logqs/chosen": 0.078421950340271,
1655
+ "logqs/chosen": -0.8123919367790222,
1656
+ "logqs/rejected": -0.8939984440803528,
1657
+ "logqs_logps/rejected": 0.08118218928575516,
1658
+ "loss": 0.3169,
1659
+ "step": 1490
1660
+ },
1661
+ {
1662
+ "epoch": 2.407463135720734,
1663
+ "grad_norm": 0.228515625,
1664
+ "learning_rate": 5.7062506605450454e-06,
1665
+ "logps_logqs/chosen": 0.07398053258657455,
1666
+ "logqs/chosen": -0.8026934862136841,
1667
+ "logqs/rejected": -0.8954586982727051,
1668
+ "logqs_logps/rejected": 0.08243472129106522,
1669
+ "loss": 0.3147,
1670
+ "step": 1500
1671
+ },
1672
+ {
1673
+ "epoch": 2.4235128899588725,
1674
+ "grad_norm": 0.2333984375,
1675
+ "learning_rate": 5.412691964301827e-06,
1676
+ "logps_logqs/chosen": 0.07238447666168213,
1677
+ "logqs/chosen": -0.8131697773933411,
1678
+ "logqs/rejected": -0.9339205622673035,
1679
+ "logqs_logps/rejected": 0.08201464265584946,
1680
+ "loss": 0.3136,
1681
+ "step": 1510
1682
+ },
1683
+ {
1684
+ "epoch": 2.439562644197011,
1685
+ "grad_norm": 0.2353515625,
1686
+ "learning_rate": 5.125966243976218e-06,
1687
+ "logps_logqs/chosen": 0.07509394735097885,
1688
+ "logqs/chosen": -0.78544682264328,
1689
+ "logqs/rejected": -0.8901753425598145,
1690
+ "logqs_logps/rejected": 0.08143877983093262,
1691
+ "loss": 0.311,
1692
+ "step": 1520
1693
+ },
1694
+ {
1695
+ "epoch": 2.455612398435149,
1696
+ "grad_norm": 0.232421875,
1697
+ "learning_rate": 4.846173523008824e-06,
1698
+ "logps_logqs/chosen": 0.07063795626163483,
1699
+ "logqs/chosen": -0.7890464067459106,
1700
+ "logqs/rejected": -0.9245685338973999,
1701
+ "logqs_logps/rejected": 0.08157093822956085,
1702
+ "loss": 0.3102,
1703
+ "step": 1530
1704
+ },
1705
+ {
1706
+ "epoch": 2.471662152673287,
1707
+ "grad_norm": 0.2236328125,
1708
+ "learning_rate": 4.573411406283409e-06,
1709
+ "logps_logqs/chosen": 0.07790166139602661,
1710
+ "logqs/chosen": -0.8271121978759766,
1711
+ "logqs/rejected": -0.9096291661262512,
1712
+ "logqs_logps/rejected": 0.08363105356693268,
1713
+ "loss": 0.3189,
1714
+ "step": 1540
1715
+ },
1716
+ {
1717
+ "epoch": 2.4877119069114255,
1718
+ "grad_norm": 0.2275390625,
1719
+ "learning_rate": 4.307775046077739e-06,
1720
+ "logps_logqs/chosen": 0.07722210884094238,
1721
+ "logqs/chosen": -0.8067975044250488,
1722
+ "logqs/rejected": -0.905848503112793,
1723
+ "logqs_logps/rejected": 0.08417145162820816,
1724
+ "loss": 0.3166,
1725
+ "step": 1550
1726
+ },
1727
+ {
1728
+ "epoch": 2.5037616611495634,
1729
+ "grad_norm": 0.232421875,
1730
+ "learning_rate": 4.049357108869964e-06,
1731
+ "logps_logqs/chosen": 0.07566576451063156,
1732
+ "logqs/chosen": -0.807111918926239,
1733
+ "logqs/rejected": -0.896578311920166,
1734
+ "logqs_logps/rejected": 0.08398713916540146,
1735
+ "loss": 0.3156,
1736
+ "step": 1560
1737
+ },
1738
+ {
1739
+ "epoch": 2.519811415387702,
1740
+ "grad_norm": 0.236328125,
1741
+ "learning_rate": 3.798247743012201e-06,
1742
+ "logps_logqs/chosen": 0.07113765180110931,
1743
+ "logqs/chosen": -0.8036268949508667,
1744
+ "logqs/rejected": -0.9011009335517883,
1745
+ "logqs_logps/rejected": 0.08287129551172256,
1746
+ "loss": 0.3125,
1747
+ "step": 1570
1748
+ },
1749
+ {
1750
+ "epoch": 2.53586116962584,
1751
+ "grad_norm": 0.2275390625,
1752
+ "learning_rate": 3.554534547282512e-06,
1753
+ "logps_logqs/chosen": 0.07366280257701874,
1754
+ "logqs/chosen": -0.7989723086357117,
1755
+ "logqs/rejected": -0.884625256061554,
1756
+ "logqs_logps/rejected": 0.08136685937643051,
1757
+ "loss": 0.3152,
1758
+ "step": 1580
1759
+ },
1760
+ {
1761
+ "epoch": 2.5519109238639786,
1762
+ "grad_norm": 0.232421875,
1763
+ "learning_rate": 3.318302540326343e-06,
1764
+ "logps_logqs/chosen": 0.07400309294462204,
1765
+ "logqs/chosen": -0.8105365633964539,
1766
+ "logqs/rejected": -0.9077731966972351,
1767
+ "logqs_logps/rejected": 0.0812162458896637,
1768
+ "loss": 0.3164,
1769
+ "step": 1590
1770
+ },
1771
+ {
1772
+ "epoch": 2.5679606781021165,
1773
+ "grad_norm": 0.2265625,
1774
+ "learning_rate": 3.089634130998026e-06,
1775
+ "logps_logqs/chosen": 0.07428063452243805,
1776
+ "logqs/chosen": -0.8025354146957397,
1777
+ "logqs/rejected": -0.9122070074081421,
1778
+ "logqs_logps/rejected": 0.08231757581233978,
1779
+ "loss": 0.313,
1780
+ "step": 1600
1781
+ },
1782
+ {
1783
+ "epoch": 2.584010432340255,
1784
+ "grad_norm": 0.2275390625,
1785
+ "learning_rate": 2.8686090896126587e-06,
1786
+ "logps_logqs/chosen": 0.07186438143253326,
1787
+ "logqs/chosen": -0.7830988168716431,
1788
+ "logqs/rejected": -0.8839938044548035,
1789
+ "logqs_logps/rejected": 0.08267438411712646,
1790
+ "loss": 0.3066,
1791
+ "step": 1610
1792
+ },
1793
+ {
1794
+ "epoch": 2.6000601865783928,
1795
+ "grad_norm": 0.2255859375,
1796
+ "learning_rate": 2.655304520118482e-06,
1797
+ "logps_logqs/chosen": 0.07159160077571869,
1798
+ "logqs/chosen": -0.7976843118667603,
1799
+ "logqs/rejected": -0.9096366167068481,
1800
+ "logqs_logps/rejected": 0.08025567978620529,
1801
+ "loss": 0.3097,
1802
+ "step": 1620
1803
+ },
1804
+ {
1805
+ "epoch": 2.616109940816531,
1806
+ "grad_norm": 0.2333984375,
1807
+ "learning_rate": 2.44979483319939e-06,
1808
+ "logps_logqs/chosen": 0.07347805052995682,
1809
+ "logqs/chosen": -0.7938045263290405,
1810
+ "logqs/rejected": -0.890743613243103,
1811
+ "logqs_logps/rejected": 0.08207173645496368,
1812
+ "loss": 0.3107,
1813
+ "step": 1630
1814
+ },
1815
+ {
1816
+ "epoch": 2.6321596950546695,
1817
+ "grad_norm": 0.220703125,
1818
+ "learning_rate": 2.252151720316964e-06,
1819
+ "logps_logqs/chosen": 0.07434280216693878,
1820
+ "logqs/chosen": -0.8010244369506836,
1821
+ "logqs/rejected": -0.8791995048522949,
1822
+ "logqs_logps/rejected": 0.08244656026363373,
1823
+ "loss": 0.3125,
1824
+ "step": 1640
1825
+ },
1826
+ {
1827
+ "epoch": 2.648209449292808,
1828
+ "grad_norm": 0.2236328125,
1829
+ "learning_rate": 2.0624441287011213e-06,
1830
+ "logps_logqs/chosen": 0.07119563221931458,
1831
+ "logqs/chosen": -0.7902050018310547,
1832
+ "logqs/rejected": -0.8934162855148315,
1833
+ "logqs_logps/rejected": 0.08073534816503525,
1834
+ "loss": 0.3096,
1835
+ "step": 1650
1836
+ },
1837
+ {
1838
+ "epoch": 2.664259203530946,
1839
+ "grad_norm": 0.2265625,
1840
+ "learning_rate": 1.8807382372980687e-06,
1841
+ "logps_logqs/chosen": 0.07328217476606369,
1842
+ "logqs/chosen": -0.799074113368988,
1843
+ "logqs/rejected": -0.9103049039840698,
1844
+ "logqs_logps/rejected": 0.08119536936283112,
1845
+ "loss": 0.3127,
1846
+ "step": 1660
1847
+ },
1848
+ {
1849
+ "epoch": 2.680308957769084,
1850
+ "grad_norm": 0.234375,
1851
+ "learning_rate": 1.7070974336839796e-06,
1852
+ "logps_logqs/chosen": 0.07554595172405243,
1853
+ "logqs/chosen": -0.8031436800956726,
1854
+ "logqs/rejected": -0.8931919932365417,
1855
+ "logqs_logps/rejected": 0.08214543014764786,
1856
+ "loss": 0.311,
1857
+ "step": 1670
1858
+ },
1859
+ {
1860
+ "epoch": 2.6963587120072225,
1861
+ "grad_norm": 0.23046875,
1862
+ "learning_rate": 1.541582291952401e-06,
1863
+ "logps_logqs/chosen": 0.07754793018102646,
1864
+ "logqs/chosen": -0.8299878835678101,
1865
+ "logqs/rejected": -0.9271092414855957,
1866
+ "logqs_logps/rejected": 0.08218444138765335,
1867
+ "loss": 0.3161,
1868
+ "step": 1680
1869
+ },
1870
+ {
1871
+ "epoch": 2.7124084662453605,
1872
+ "grad_norm": 0.2236328125,
1873
+ "learning_rate": 1.38425055158318e-06,
1874
+ "logps_logqs/chosen": 0.07421831786632538,
1875
+ "logqs/chosen": -0.811480700969696,
1876
+ "logqs/rejected": -0.9157323837280273,
1877
+ "logqs_logps/rejected": 0.08171753585338593,
1878
+ "loss": 0.3117,
1879
+ "step": 1690
1880
+ },
1881
+ {
1882
+ "epoch": 2.728458220483499,
1883
+ "grad_norm": 0.2255859375,
1884
+ "learning_rate": 1.235157097300188e-06,
1885
+ "logps_logqs/chosen": 0.07626229524612427,
1886
+ "logqs/chosen": -0.8032703399658203,
1887
+ "logqs/rejected": -0.8930376172065735,
1888
+ "logqs_logps/rejected": 0.08358137309551239,
1889
+ "loss": 0.3111,
1890
+ "step": 1700
1891
+ },
1892
+ {
1893
+ "epoch": 2.744507974721637,
1894
+ "grad_norm": 0.2177734375,
1895
+ "learning_rate": 1.0943539399249635e-06,
1896
+ "logps_logqs/chosen": 0.07090778648853302,
1897
+ "logqs/chosen": -0.7999089956283569,
1898
+ "logqs/rejected": -0.8964935541152954,
1899
+ "logqs_logps/rejected": 0.0812908187508583,
1900
+ "loss": 0.3113,
1901
+ "step": 1710
1902
+ },
1903
+ {
1904
+ "epoch": 2.7605577289597756,
1905
+ "grad_norm": 0.2197265625,
1906
+ "learning_rate": 9.618901982328704e-07,
1907
+ "logps_logqs/chosen": 0.07075212895870209,
1908
+ "logqs/chosen": -0.7851020693778992,
1909
+ "logqs/rejected": -0.8868266940116882,
1910
+ "logqs_logps/rejected": 0.08196558058261871,
1911
+ "loss": 0.3124,
1912
+ "step": 1720
1913
+ },
1914
+ {
1915
+ "epoch": 2.7766074831979135,
1916
+ "grad_norm": 0.224609375,
1917
+ "learning_rate": 8.378120818181707e-07,
1918
+ "logps_logqs/chosen": 0.07225438952445984,
1919
+ "logqs/chosen": -0.7922335863113403,
1920
+ "logqs/rejected": -0.8811353445053101,
1921
+ "logqs_logps/rejected": 0.08280298858880997,
1922
+ "loss": 0.3075,
1923
+ "step": 1730
1924
+ },
1925
+ {
1926
+ "epoch": 2.792657237436052,
1927
+ "grad_norm": 0.2236328125,
1928
+ "learning_rate": 7.221628749739223e-07,
1929
+ "logps_logqs/chosen": 0.07148848474025726,
1930
+ "logqs/chosen": -0.7962485551834106,
1931
+ "logqs/rejected": -0.8903713226318359,
1932
+ "logqs_logps/rejected": 0.08183252066373825,
1933
+ "loss": 0.3099,
1934
+ "step": 1740
1935
+ },
1936
+ {
1937
+ "epoch": 2.80870699167419,
1938
+ "grad_norm": 0.232421875,
1939
+ "learning_rate": 6.149829215924025e-07,
1940
+ "logps_logqs/chosen": 0.07041052728891373,
1941
+ "logqs/chosen": -0.7954488396644592,
1942
+ "logqs/rejected": -0.8928369283676147,
1943
+ "logqs_logps/rejected": 0.08137312531471252,
1944
+ "loss": 0.3116,
1945
+ "step": 1750
1946
+ },
1947
+ {
1948
+ "epoch": 2.824756745912328,
1949
+ "grad_norm": 0.22265625,
1950
+ "learning_rate": 5.163096110912368e-07,
1951
+ "logps_logqs/chosen": 0.07447172701358795,
1952
+ "logqs/chosen": -0.819632351398468,
1953
+ "logqs/rejected": -0.9202129244804382,
1954
+ "logqs_logps/rejected": 0.08205995708703995,
1955
+ "loss": 0.3152,
1956
+ "step": 1760
1957
+ },
1958
+ {
1959
+ "epoch": 2.8408065001504665,
1960
+ "grad_norm": 0.2265625,
1961
+ "learning_rate": 4.261773653702089e-07,
1962
+ "logps_logqs/chosen": 0.07548446953296661,
1963
+ "logqs/chosen": -0.819521427154541,
1964
+ "logqs/rejected": -0.9065629243850708,
1965
+ "logqs_logps/rejected": 0.08328162133693695,
1966
+ "loss": 0.3148,
1967
+ "step": 1770
1968
+ },
1969
+ {
1970
+ "epoch": 2.856856254388605,
1971
+ "grad_norm": 0.2236328125,
1972
+ "learning_rate": 3.4461762680329803e-07,
1973
+ "logps_logqs/chosen": 0.07317046076059341,
1974
+ "logqs/chosen": -0.7897886633872986,
1975
+ "logqs/rejected": -0.9044450521469116,
1976
+ "logqs_logps/rejected": 0.08158095180988312,
1977
+ "loss": 0.3104,
1978
+ "step": 1780
1979
+ },
1980
+ {
1981
+ "epoch": 2.872906008626743,
1982
+ "grad_norm": 0.2314453125,
1983
+ "learning_rate": 2.716588472700815e-07,
1984
+ "logps_logqs/chosen": 0.0730937272310257,
1985
+ "logqs/chosen": -0.7850784063339233,
1986
+ "logqs/rejected": -0.9064621925354004,
1987
+ "logqs_logps/rejected": 0.08220399916172028,
1988
+ "loss": 0.3095,
1989
+ "step": 1790
1990
+ },
1991
+ {
1992
+ "epoch": 2.888955762864881,
1993
+ "grad_norm": 0.2275390625,
1994
+ "learning_rate": 2.0732647823038243e-07,
1995
+ "logps_logqs/chosen": 0.07006161659955978,
1996
+ "logqs/chosen": -0.7867298722267151,
1997
+ "logqs/rejected": -0.9106978178024292,
1998
+ "logqs_logps/rejected": 0.08103770762681961,
1999
+ "loss": 0.3086,
2000
+ "step": 1800
2001
+ },
2002
+ {
2003
+ "epoch": 2.905005517103019,
2004
+ "grad_norm": 0.2216796875,
2005
+ "learning_rate": 1.5164296184560222e-07,
2006
+ "logps_logqs/chosen": 0.0730353370308876,
2007
+ "logqs/chosen": -0.784963846206665,
2008
+ "logqs/rejected": -0.895187258720398,
2009
+ "logqs_logps/rejected": 0.08217376470565796,
2010
+ "loss": 0.3121,
2011
+ "step": 1810
2012
+ },
2013
+ {
2014
+ "epoch": 2.9210552713411575,
2015
+ "grad_norm": 0.2333984375,
2016
+ "learning_rate": 1.0462772314983882e-07,
2017
+ "logps_logqs/chosen": 0.07322341203689575,
2018
+ "logqs/chosen": -0.8064349293708801,
2019
+ "logqs/rejected": -0.9101492166519165,
2020
+ "logqs_logps/rejected": 0.08088482171297073,
2021
+ "loss": 0.3163,
2022
+ "step": 1820
2023
+ },
2024
+ {
2025
+ "epoch": 2.937105025579296,
2026
+ "grad_norm": 0.2255859375,
2027
+ "learning_rate": 6.62971632735182e-08,
2028
+ "logps_logqs/chosen": 0.07244640588760376,
2029
+ "logqs/chosen": -0.8047133684158325,
2030
+ "logqs/rejected": -0.9275949597358704,
2031
+ "logqs_logps/rejected": 0.08042384684085846,
2032
+ "loss": 0.3157,
2033
+ "step": 1830
2034
+ },
2035
+ {
2036
+ "epoch": 2.9531547798174342,
2037
+ "grad_norm": 0.2216796875,
2038
+ "learning_rate": 3.666465372190453e-08,
2039
+ "logps_logqs/chosen": 0.07384280860424042,
2040
+ "logqs/chosen": -0.7898183465003967,
2041
+ "logqs/rejected": -0.9135943651199341,
2042
+ "logqs_logps/rejected": 0.08159508556127548,
2043
+ "loss": 0.3114,
2044
+ "step": 1840
2045
+ },
2046
+ {
2047
+ "epoch": 2.969204534055572,
2048
+ "grad_norm": 0.232421875,
2049
+ "learning_rate": 1.57405317104925e-08,
2050
+ "logps_logqs/chosen": 0.07507185637950897,
2051
+ "logqs/chosen": -0.7989250421524048,
2052
+ "logqs/rejected": -0.9065110087394714,
2053
+ "logqs_logps/rejected": 0.08292163163423538,
2054
+ "loss": 0.3158,
2055
+ "step": 1850
2056
+ },
2057
+ {
2058
+ "epoch": 2.9852542882937105,
2059
+ "grad_norm": 0.2265625,
2060
+ "learning_rate": 3.532096558903075e-09,
2061
+ "logps_logqs/chosen": 0.07044342905282974,
2062
+ "logqs/chosen": -0.7936350107192993,
2063
+ "logqs/rejected": -0.9102191925048828,
2064
+ "logqs_logps/rejected": 0.08065608888864517,
2065
+ "loss": 0.3091,
2066
+ "step": 1860
2067
+ }
2068
+ ],
2069
+ "logging_steps": 10,
2070
+ "max_steps": 1869,
2071
+ "num_input_tokens_seen": 0,
2072
+ "num_train_epochs": 3,
2073
+ "save_steps": 500,
2074
+ "stateful_callbacks": {
2075
+ "TrainerControl": {
2076
+ "args": {
2077
+ "should_epoch_stop": false,
2078
+ "should_evaluate": false,
2079
+ "should_log": false,
2080
+ "should_save": true,
2081
+ "should_training_stop": true
2082
+ },
2083
+ "attributes": {}
2084
+ }
2085
+ },
2086
+ "total_flos": 0.0,
2087
+ "train_batch_size": 1,
2088
+ "trial_name": null,
2089
+ "trial_params": null
2090
+ }
llama-3.2-3B-it-distillm2/checkpoint-1869/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78b07454d6b5f6bc3c6b2f835896f1156e52af7ea02a80bb43990ec5e410f1c
3
+ size 6840
llama-3.2-3B-it-distillm2/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
llama-3.2-3B-it-distillm2/eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.999699067108035,
3
+ "eval_logps_logqs/chosen": 0.095769964158535,
4
+ "eval_logqs/chosen": -0.8354007601737976,
5
+ "eval_logqs/rejected": -0.7743091583251953,
6
+ "eval_logqs_logps/rejected": 0.09668296575546265,
7
+ "eval_loss": 0.34429532289505005,
8
+ "eval_runtime": 1.1616,
9
+ "eval_samples": 10,
10
+ "eval_samples_per_second": 8.609,
11
+ "eval_steps_per_second": 2.583
12
+ }
llama-3.2-3B-it-distillm2/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
llama-3.2-3B-it-distillm2/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
llama-3.2-3B-it-distillm2/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
llama-3.2-3B-it-distillm2/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.999699067108035,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.347557685507881,
5
+ "train_runtime": 42290.5207,
6
+ "train_samples": 79751,
7
+ "train_samples_per_second": 5.657,
8
+ "train_steps_per_second": 0.044
9
+ }
llama-3.2-3B-it-distillm2/trainer_state.json ADDED
@@ -0,0 +1,2099 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.999699067108035,
5
+ "eval_steps": 10000000,
6
+ "global_step": 1869,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0016049754238138228,
13
+ "grad_norm": 0.90625,
14
+ "learning_rate": 2.6737967914438503e-07,
15
+ "logps_logqs/chosen": 0.2574678659439087,
16
+ "logqs/chosen": -1.2981349229812622,
17
+ "logqs/rejected": -0.7383479475975037,
18
+ "logqs_logps/rejected": 0.1667567938566208,
19
+ "loss": 0.7904,
20
+ "step": 1
21
+ },
22
+ {
23
+ "epoch": 0.016049754238138227,
24
+ "grad_norm": 0.796875,
25
+ "learning_rate": 2.6737967914438504e-06,
26
+ "logps_logqs/chosen": 0.261772096157074,
27
+ "logqs/chosen": -1.3397735357284546,
28
+ "logqs/rejected": -0.7105537056922913,
29
+ "logqs_logps/rejected": 0.16120129823684692,
30
+ "loss": 0.7608,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.032099508476276455,
35
+ "grad_norm": 0.69140625,
36
+ "learning_rate": 5.347593582887701e-06,
37
+ "logps_logqs/chosen": 0.2507140040397644,
38
+ "logqs/chosen": -1.3112075328826904,
39
+ "logqs/rejected": -0.7247480750083923,
40
+ "logqs_logps/rejected": 0.1601167917251587,
41
+ "loss": 0.7473,
42
+ "step": 20
43
+ },
44
+ {
45
+ "epoch": 0.048149262714414685,
46
+ "grad_norm": 0.5625,
47
+ "learning_rate": 8.02139037433155e-06,
48
+ "logps_logqs/chosen": 0.23428936302661896,
49
+ "logqs/chosen": -1.2722276449203491,
50
+ "logqs/rejected": -0.7449068427085876,
51
+ "logqs_logps/rejected": 0.1634160578250885,
52
+ "loss": 0.7145,
53
+ "step": 30
54
+ },
55
+ {
56
+ "epoch": 0.06419901695255291,
57
+ "grad_norm": 0.494140625,
58
+ "learning_rate": 1.0695187165775402e-05,
59
+ "logps_logqs/chosen": 0.22127564251422882,
60
+ "logqs/chosen": -1.2067252397537231,
61
+ "logqs/rejected": -0.7258399724960327,
62
+ "logqs_logps/rejected": 0.16167941689491272,
63
+ "loss": 0.6827,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 0.08024877119069114,
68
+ "grad_norm": 0.40625,
69
+ "learning_rate": 1.3368983957219252e-05,
70
+ "logps_logqs/chosen": 0.20441269874572754,
71
+ "logqs/chosen": -1.144487977027893,
72
+ "logqs/rejected": -0.7239223718643188,
73
+ "logqs_logps/rejected": 0.16194146871566772,
74
+ "loss": 0.6414,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.09629852542882937,
79
+ "grad_norm": 0.921875,
80
+ "learning_rate": 1.60427807486631e-05,
81
+ "logps_logqs/chosen": 0.19416597485542297,
82
+ "logqs/chosen": -1.1013798713684082,
83
+ "logqs/rejected": -0.7783336639404297,
84
+ "logqs_logps/rejected": 0.1327773630619049,
85
+ "loss": 0.5906,
86
+ "step": 60
87
+ },
88
+ {
89
+ "epoch": 0.1123482796669676,
90
+ "grad_norm": 0.294921875,
91
+ "learning_rate": 1.8716577540106954e-05,
92
+ "logps_logqs/chosen": 0.20319707691669464,
93
+ "logqs/chosen": -1.1499295234680176,
94
+ "logqs/rejected": -0.9546529650688171,
95
+ "logqs_logps/rejected": 0.07568300515413284,
96
+ "loss": 0.5474,
97
+ "step": 70
98
+ },
99
+ {
100
+ "epoch": 0.12839803390510582,
101
+ "grad_norm": 0.296875,
102
+ "learning_rate": 2.1390374331550803e-05,
103
+ "logps_logqs/chosen": 0.2029210776090622,
104
+ "logqs/chosen": -1.1514651775360107,
105
+ "logqs/rejected": -0.9666783213615417,
106
+ "logqs_logps/rejected": 0.07000944763422012,
107
+ "loss": 0.5267,
108
+ "step": 80
109
+ },
110
+ {
111
+ "epoch": 0.14444778814324405,
112
+ "grad_norm": 0.2158203125,
113
+ "learning_rate": 2.4064171122994652e-05,
114
+ "logps_logqs/chosen": 0.19126488268375397,
115
+ "logqs/chosen": -1.1015961170196533,
116
+ "logqs/rejected": -0.9495261907577515,
117
+ "logqs_logps/rejected": 0.07096932828426361,
118
+ "loss": 0.505,
119
+ "step": 90
120
+ },
121
+ {
122
+ "epoch": 0.16049754238138228,
123
+ "grad_norm": 0.228515625,
124
+ "learning_rate": 2.6737967914438505e-05,
125
+ "logps_logqs/chosen": 0.17442497611045837,
126
+ "logqs/chosen": -1.0466772317886353,
127
+ "logqs/rejected": -0.9257510304450989,
128
+ "logqs_logps/rejected": 0.07788076251745224,
129
+ "loss": 0.4811,
130
+ "step": 100
131
+ },
132
+ {
133
+ "epoch": 0.1765472966195205,
134
+ "grad_norm": 0.2373046875,
135
+ "learning_rate": 2.9411764705882354e-05,
136
+ "logps_logqs/chosen": 0.16078680753707886,
137
+ "logqs/chosen": -1.029247522354126,
138
+ "logqs/rejected": -0.8865665197372437,
139
+ "logqs_logps/rejected": 0.09497503191232681,
140
+ "loss": 0.4736,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.19259705085765874,
145
+ "grad_norm": 0.22265625,
146
+ "learning_rate": 3.20855614973262e-05,
147
+ "logps_logqs/chosen": 0.1526278555393219,
148
+ "logqs/chosen": -0.9959474802017212,
149
+ "logqs/rejected": -0.8694570660591125,
150
+ "logqs_logps/rejected": 0.09631417691707611,
151
+ "loss": 0.4569,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.20864680509579697,
156
+ "grad_norm": 0.216796875,
157
+ "learning_rate": 3.4759358288770055e-05,
158
+ "logps_logqs/chosen": 0.14035369455814362,
159
+ "logqs/chosen": -0.9707647562026978,
160
+ "logqs/rejected": -0.8952853083610535,
161
+ "logqs_logps/rejected": 0.09752343595027924,
162
+ "loss": 0.4462,
163
+ "step": 130
164
+ },
165
+ {
166
+ "epoch": 0.2246965593339352,
167
+ "grad_norm": 0.21875,
168
+ "learning_rate": 3.743315508021391e-05,
169
+ "logps_logqs/chosen": 0.13420596718788147,
170
+ "logqs/chosen": -0.9546219706535339,
171
+ "logqs/rejected": -0.8874092102050781,
172
+ "logqs_logps/rejected": 0.09715182334184647,
173
+ "loss": 0.4316,
174
+ "step": 140
175
+ },
176
+ {
177
+ "epoch": 0.24074631357207343,
178
+ "grad_norm": 0.2451171875,
179
+ "learning_rate": 4.0106951871657754e-05,
180
+ "logps_logqs/chosen": 0.12938353419303894,
181
+ "logqs/chosen": -0.9377857446670532,
182
+ "logqs/rejected": -0.8700798749923706,
183
+ "logqs_logps/rejected": 0.09673669189214706,
184
+ "loss": 0.4268,
185
+ "step": 150
186
+ },
187
+ {
188
+ "epoch": 0.25679606781021164,
189
+ "grad_norm": 0.2255859375,
190
+ "learning_rate": 4.2780748663101606e-05,
191
+ "logps_logqs/chosen": 0.12080077081918716,
192
+ "logqs/chosen": -0.9156932830810547,
193
+ "logqs/rejected": -0.8663859367370605,
194
+ "logqs_logps/rejected": 0.09702957421541214,
195
+ "loss": 0.4138,
196
+ "step": 160
197
+ },
198
+ {
199
+ "epoch": 0.2728458220483499,
200
+ "grad_norm": 0.267578125,
201
+ "learning_rate": 4.545454545454546e-05,
202
+ "logps_logqs/chosen": 0.1205262765288353,
203
+ "logqs/chosen": -0.9165436625480652,
204
+ "logqs/rejected": -0.8856159448623657,
205
+ "logqs_logps/rejected": 0.09857054054737091,
206
+ "loss": 0.4114,
207
+ "step": 170
208
+ },
209
+ {
210
+ "epoch": 0.2888955762864881,
211
+ "grad_norm": 0.259765625,
212
+ "learning_rate": 4.8128342245989304e-05,
213
+ "logps_logqs/chosen": 0.1172843724489212,
214
+ "logqs/chosen": -0.8963316679000854,
215
+ "logqs/rejected": -0.8776806592941284,
216
+ "logqs_logps/rejected": 0.09663058817386627,
217
+ "loss": 0.4024,
218
+ "step": 180
219
+ },
220
+ {
221
+ "epoch": 0.30494533052462636,
222
+ "grad_norm": 0.28125,
223
+ "learning_rate": 4.9999607536612036e-05,
224
+ "logps_logqs/chosen": 0.11222084611654282,
225
+ "logqs/chosen": -0.8948033452033997,
226
+ "logqs/rejected": -0.8878369331359863,
227
+ "logqs_logps/rejected": 0.09515221416950226,
228
+ "loss": 0.4028,
229
+ "step": 190
230
+ },
231
+ {
232
+ "epoch": 0.32099508476276456,
233
+ "grad_norm": 0.271484375,
234
+ "learning_rate": 4.9992630752499945e-05,
235
+ "logps_logqs/chosen": 0.10836397111415863,
236
+ "logqs/chosen": -0.8886402249336243,
237
+ "logqs/rejected": -0.8636736869812012,
238
+ "logqs_logps/rejected": 0.09533380717039108,
239
+ "loss": 0.3895,
240
+ "step": 200
241
+ },
242
+ {
243
+ "epoch": 0.3370448390009028,
244
+ "grad_norm": 0.267578125,
245
+ "learning_rate": 4.997693536122969e-05,
246
+ "logps_logqs/chosen": 0.10845750570297241,
247
+ "logqs/chosen": -0.8758543729782104,
248
+ "logqs/rejected": -0.8861125707626343,
249
+ "logqs_logps/rejected": 0.09698913246393204,
250
+ "loss": 0.3905,
251
+ "step": 210
252
+ },
253
+ {
254
+ "epoch": 0.353094593239041,
255
+ "grad_norm": 0.255859375,
256
+ "learning_rate": 4.995252683809324e-05,
257
+ "logps_logqs/chosen": 0.103293776512146,
258
+ "logqs/chosen": -0.8651936650276184,
259
+ "logqs/rejected": -0.8593576550483704,
260
+ "logqs_logps/rejected": 0.09784064441919327,
261
+ "loss": 0.3843,
262
+ "step": 220
263
+ },
264
+ {
265
+ "epoch": 0.3691443474771793,
266
+ "grad_norm": 0.26953125,
267
+ "learning_rate": 4.9919413697933496e-05,
268
+ "logps_logqs/chosen": 0.10118403285741806,
269
+ "logqs/chosen": -0.8709210157394409,
270
+ "logqs/rejected": -0.8462339639663696,
271
+ "logqs_logps/rejected": 0.09881097078323364,
272
+ "loss": 0.3841,
273
+ "step": 230
274
+ },
275
+ {
276
+ "epoch": 0.3851941017153175,
277
+ "grad_norm": 0.265625,
278
+ "learning_rate": 4.987760749217389e-05,
279
+ "logps_logqs/chosen": 0.10117912292480469,
280
+ "logqs/chosen": -0.8689754605293274,
281
+ "logqs/rejected": -0.8683704137802124,
282
+ "logqs_logps/rejected": 0.09666574746370316,
283
+ "loss": 0.3777,
284
+ "step": 240
285
+ },
286
+ {
287
+ "epoch": 0.4012438559534557,
288
+ "grad_norm": 0.302734375,
289
+ "learning_rate": 4.982712280478875e-05,
290
+ "logps_logqs/chosen": 0.09455956518650055,
291
+ "logqs/chosen": -0.8457688093185425,
292
+ "logqs/rejected": -0.8621484637260437,
293
+ "logqs_logps/rejected": 0.09776864945888519,
294
+ "loss": 0.3765,
295
+ "step": 250
296
+ },
297
+ {
298
+ "epoch": 0.41729361019159394,
299
+ "grad_norm": 0.2578125,
300
+ "learning_rate": 4.976797724721567e-05,
301
+ "logps_logqs/chosen": 0.09175171703100204,
302
+ "logqs/chosen": -0.8432157635688782,
303
+ "logqs/rejected": -0.8678897023200989,
304
+ "logqs_logps/rejected": 0.09698458015918732,
305
+ "loss": 0.3688,
306
+ "step": 260
307
+ },
308
+ {
309
+ "epoch": 0.43334336442973215,
310
+ "grad_norm": 0.283203125,
311
+ "learning_rate": 4.9700191452211806e-05,
312
+ "logps_logqs/chosen": 0.09448465704917908,
313
+ "logqs/chosen": -0.84539395570755,
314
+ "logqs/rejected": -0.8683292269706726,
315
+ "logqs_logps/rejected": 0.09693001210689545,
316
+ "loss": 0.3716,
317
+ "step": 270
318
+ },
319
+ {
320
+ "epoch": 0.4493931186678704,
321
+ "grad_norm": 0.28125,
322
+ "learning_rate": 4.9623789066656276e-05,
323
+ "logps_logqs/chosen": 0.09571119397878647,
324
+ "logqs/chosen": -0.8593363761901855,
325
+ "logqs/rejected": -0.8565343618392944,
326
+ "logqs_logps/rejected": 0.09683676809072495,
327
+ "loss": 0.3735,
328
+ "step": 280
329
+ },
330
+ {
331
+ "epoch": 0.4654428729060086,
332
+ "grad_norm": 0.31640625,
333
+ "learning_rate": 4.953879674330093e-05,
334
+ "logps_logqs/chosen": 0.09770174324512482,
335
+ "logqs/chosen": -0.8558902740478516,
336
+ "logqs/rejected": -0.8663812875747681,
337
+ "logqs_logps/rejected": 0.09595683217048645,
338
+ "loss": 0.3673,
339
+ "step": 290
340
+ },
341
+ {
342
+ "epoch": 0.48149262714414687,
343
+ "grad_norm": 0.287109375,
344
+ "learning_rate": 4.944524413147263e-05,
345
+ "logps_logqs/chosen": 0.09066566079854965,
346
+ "logqs/chosen": -0.8534440994262695,
347
+ "logqs/rejected": -0.8585640788078308,
348
+ "logqs_logps/rejected": 0.09527692943811417,
349
+ "loss": 0.3652,
350
+ "step": 300
351
+ },
352
+ {
353
+ "epoch": 0.49754238138228507,
354
+ "grad_norm": 0.2578125,
355
+ "learning_rate": 4.934316386673022e-05,
356
+ "logps_logqs/chosen": 0.09241481125354767,
357
+ "logqs/chosen": -0.8291435241699219,
358
+ "logqs/rejected": -0.8762058019638062,
359
+ "logqs_logps/rejected": 0.09554027765989304,
360
+ "loss": 0.3615,
361
+ "step": 310
362
+ },
363
+ {
364
+ "epoch": 0.5135921356204233,
365
+ "grad_norm": 0.28515625,
366
+ "learning_rate": 4.923259155947964e-05,
367
+ "logps_logqs/chosen": 0.09071577340364456,
368
+ "logqs/chosen": -0.8484598398208618,
369
+ "logqs/rejected": -0.8865866661071777,
370
+ "logqs_logps/rejected": 0.09390830993652344,
371
+ "loss": 0.3638,
372
+ "step": 320
373
+ },
374
+ {
375
+ "epoch": 0.5296418898585615,
376
+ "grad_norm": 0.306640625,
377
+ "learning_rate": 4.911356578255139e-05,
378
+ "logps_logqs/chosen": 0.09064419567584991,
379
+ "logqs/chosen": -0.8393951654434204,
380
+ "logqs/rejected": -0.8594444990158081,
381
+ "logqs_logps/rejected": 0.09380849450826645,
382
+ "loss": 0.3604,
383
+ "step": 330
384
+ },
385
+ {
386
+ "epoch": 0.5456916440966998,
387
+ "grad_norm": 0.291015625,
388
+ "learning_rate": 4.898612805774447e-05,
389
+ "logps_logqs/chosen": 0.08888660371303558,
390
+ "logqs/chosen": -0.8379303216934204,
391
+ "logqs/rejected": -0.8894745707511902,
392
+ "logqs_logps/rejected": 0.09310872852802277,
393
+ "loss": 0.3628,
394
+ "step": 340
395
+ },
396
+ {
397
+ "epoch": 0.561741398334838,
398
+ "grad_norm": 0.263671875,
399
+ "learning_rate": 4.885032284134165e-05,
400
+ "logps_logqs/chosen": 0.088349848985672,
401
+ "logqs/chosen": -0.8371356129646301,
402
+ "logqs/rejected": -0.8821464776992798,
403
+ "logqs_logps/rejected": 0.09222712367773056,
404
+ "loss": 0.3579,
405
+ "step": 350
406
+ },
407
+ {
408
+ "epoch": 0.5777911525729762,
409
+ "grad_norm": 0.30078125,
410
+ "learning_rate": 4.8706197508600984e-05,
411
+ "logps_logqs/chosen": 0.08849716186523438,
412
+ "logqs/chosen": -0.8537057638168335,
413
+ "logqs/rejected": -0.8783435821533203,
414
+ "logqs_logps/rejected": 0.0930907279253006,
415
+ "loss": 0.3601,
416
+ "step": 360
417
+ },
418
+ {
419
+ "epoch": 0.5938409068111145,
420
+ "grad_norm": 0.263671875,
421
+ "learning_rate": 4.855380233722915e-05,
422
+ "logps_logqs/chosen": 0.08889272809028625,
423
+ "logqs/chosen": -0.8391559720039368,
424
+ "logqs/rejected": -0.861327052116394,
425
+ "logqs_logps/rejected": 0.09380140900611877,
426
+ "loss": 0.3576,
427
+ "step": 370
428
+ },
429
+ {
430
+ "epoch": 0.6098906610492527,
431
+ "grad_norm": 0.25390625,
432
+ "learning_rate": 4.839319048984217e-05,
433
+ "logps_logqs/chosen": 0.08648727834224701,
434
+ "logqs/chosen": -0.8195026516914368,
435
+ "logqs/rejected": -0.8793449401855469,
436
+ "logqs_logps/rejected": 0.09177446365356445,
437
+ "loss": 0.3512,
438
+ "step": 380
439
+ },
440
+ {
441
+ "epoch": 0.6259404152873909,
442
+ "grad_norm": 0.30859375,
443
+ "learning_rate": 4.822441799541979e-05,
444
+ "logps_logqs/chosen": 0.08833304047584534,
445
+ "logqs/chosen": -0.8366491198539734,
446
+ "logqs/rejected": -0.8869533538818359,
447
+ "logqs_logps/rejected": 0.09127027541399002,
448
+ "loss": 0.351,
449
+ "step": 390
450
+ },
451
+ {
452
+ "epoch": 0.6419901695255291,
453
+ "grad_norm": 0.287109375,
454
+ "learning_rate": 4.8047543729759936e-05,
455
+ "logps_logqs/chosen": 0.08663193136453629,
456
+ "logqs/chosen": -0.824337363243103,
457
+ "logqs/rejected": -0.8671427965164185,
458
+ "logqs_logps/rejected": 0.09136663377285004,
459
+ "loss": 0.3509,
460
+ "step": 400
461
+ },
462
+ {
463
+ "epoch": 0.6580399237636674,
464
+ "grad_norm": 0.275390625,
465
+ "learning_rate": 4.786262939494007e-05,
466
+ "logps_logqs/chosen": 0.0892716497182846,
467
+ "logqs/chosen": -0.8378982543945312,
468
+ "logqs/rejected": -0.9046772718429565,
469
+ "logqs_logps/rejected": 0.09127910435199738,
470
+ "loss": 0.3563,
471
+ "step": 410
472
+ },
473
+ {
474
+ "epoch": 0.6740896780018056,
475
+ "grad_norm": 0.275390625,
476
+ "learning_rate": 4.766973949779261e-05,
477
+ "logps_logqs/chosen": 0.08481737226247787,
478
+ "logqs/chosen": -0.8248282670974731,
479
+ "logqs/rejected": -0.8802385330200195,
480
+ "logqs_logps/rejected": 0.09057352691888809,
481
+ "loss": 0.3503,
482
+ "step": 420
483
+ },
484
+ {
485
+ "epoch": 0.6901394322399438,
486
+ "grad_norm": 0.32421875,
487
+ "learning_rate": 4.746894132740186e-05,
488
+ "logps_logqs/chosen": 0.08275488764047623,
489
+ "logqs/chosen": -0.8119369745254517,
490
+ "logqs/rejected": -0.8782287836074829,
491
+ "logqs_logps/rejected": 0.09131704270839691,
492
+ "loss": 0.3472,
493
+ "step": 430
494
+ },
495
+ {
496
+ "epoch": 0.706189186478082,
497
+ "grad_norm": 0.267578125,
498
+ "learning_rate": 4.726030493163044e-05,
499
+ "logps_logqs/chosen": 0.08377610146999359,
500
+ "logqs/chosen": -0.8197402954101562,
501
+ "logqs/rejected": -0.8705655932426453,
502
+ "logqs_logps/rejected": 0.09147749096155167,
503
+ "loss": 0.3497,
504
+ "step": 440
505
+ },
506
+ {
507
+ "epoch": 0.7222389407162203,
508
+ "grad_norm": 0.283203125,
509
+ "learning_rate": 4.7043903092683314e-05,
510
+ "logps_logqs/chosen": 0.08348951488733292,
511
+ "logqs/chosen": -0.8285576701164246,
512
+ "logqs/rejected": -0.8908966183662415,
513
+ "logqs_logps/rejected": 0.08978553861379623,
514
+ "loss": 0.3513,
515
+ "step": 450
516
+ },
517
+ {
518
+ "epoch": 0.7382886949543586,
519
+ "grad_norm": 0.275390625,
520
+ "learning_rate": 4.6819811301717885e-05,
521
+ "logps_logqs/chosen": 0.08379025757312775,
522
+ "logqs/chosen": -0.8281780481338501,
523
+ "logqs/rejected": -0.8864878416061401,
524
+ "logqs_logps/rejected": 0.09138767421245575,
525
+ "loss": 0.349,
526
+ "step": 460
527
+ },
528
+ {
529
+ "epoch": 0.7543384491924967,
530
+ "grad_norm": 0.28125,
531
+ "learning_rate": 4.6588107732509134e-05,
532
+ "logps_logqs/chosen": 0.08411180227994919,
533
+ "logqs/chosen": -0.8280686140060425,
534
+ "logqs/rejected": -0.8841449618339539,
535
+ "logqs_logps/rejected": 0.09198630601167679,
536
+ "loss": 0.3487,
537
+ "step": 470
538
+ },
539
+ {
540
+ "epoch": 0.770388203430635,
541
+ "grad_norm": 0.3046875,
542
+ "learning_rate": 4.634887321417895e-05,
543
+ "logps_logqs/chosen": 0.08379300683736801,
544
+ "logqs/chosen": -0.8192381858825684,
545
+ "logqs/rejected": -0.8699550628662109,
546
+ "logqs_logps/rejected": 0.09246320277452469,
547
+ "loss": 0.3488,
548
+ "step": 480
549
+ },
550
+ {
551
+ "epoch": 0.7864379576687732,
552
+ "grad_norm": 0.283203125,
553
+ "learning_rate": 4.6102191202999065e-05,
554
+ "logps_logqs/chosen": 0.0825960636138916,
555
+ "logqs/chosen": -0.8156631588935852,
556
+ "logqs/rejected": -0.8777653574943542,
557
+ "logqs_logps/rejected": 0.08903246372938156,
558
+ "loss": 0.3441,
559
+ "step": 490
560
+ },
561
+ {
562
+ "epoch": 0.8024877119069114,
563
+ "grad_norm": 0.259765625,
564
+ "learning_rate": 4.5848147753277656e-05,
565
+ "logps_logqs/chosen": 0.08584129810333252,
566
+ "logqs/chosen": -0.8234313130378723,
567
+ "logqs/rejected": -0.8765767216682434,
568
+ "logqs_logps/rejected": 0.08872086554765701,
569
+ "loss": 0.3405,
570
+ "step": 500
571
+ },
572
+ {
573
+ "epoch": 0.8185374661450496,
574
+ "grad_norm": 0.275390625,
575
+ "learning_rate": 4.5586831487339485e-05,
576
+ "logps_logqs/chosen": 0.0830707997083664,
577
+ "logqs/chosen": -0.8339930772781372,
578
+ "logqs/rejected": -0.8920092582702637,
579
+ "logqs_logps/rejected": 0.0881909504532814,
580
+ "loss": 0.3472,
581
+ "step": 510
582
+ },
583
+ {
584
+ "epoch": 0.8345872203831879,
585
+ "grad_norm": 0.271484375,
586
+ "learning_rate": 4.531833356461027e-05,
587
+ "logps_logqs/chosen": 0.08575956523418427,
588
+ "logqs/chosen": -0.8362727165222168,
589
+ "logqs/rejected": -0.9038101434707642,
590
+ "logqs_logps/rejected": 0.08844949305057526,
591
+ "loss": 0.3426,
592
+ "step": 520
593
+ },
594
+ {
595
+ "epoch": 0.8506369746213261,
596
+ "grad_norm": 0.259765625,
597
+ "learning_rate": 4.5042747649816006e-05,
598
+ "logps_logqs/chosen": 0.08415627479553223,
599
+ "logqs/chosen": -0.8301606178283691,
600
+ "logqs/rejected": -0.8767345547676086,
601
+ "logqs_logps/rejected": 0.090895876288414,
602
+ "loss": 0.3377,
603
+ "step": 530
604
+ },
605
+ {
606
+ "epoch": 0.8666867288594643,
607
+ "grad_norm": 0.2734375,
608
+ "learning_rate": 4.476016988030826e-05,
609
+ "logps_logqs/chosen": 0.08037060499191284,
610
+ "logqs/chosen": -0.8235775232315063,
611
+ "logqs/rejected": -0.903292179107666,
612
+ "logqs_logps/rejected": 0.08936522901058197,
613
+ "loss": 0.3414,
614
+ "step": 540
615
+ },
616
+ {
617
+ "epoch": 0.8827364830976026,
618
+ "grad_norm": 0.255859375,
619
+ "learning_rate": 4.447069883252696e-05,
620
+ "logps_logqs/chosen": 0.08378899097442627,
621
+ "logqs/chosen": -0.81104576587677,
622
+ "logqs/rejected": -0.8723270297050476,
623
+ "logqs_logps/rejected": 0.08844035863876343,
624
+ "loss": 0.3385,
625
+ "step": 550
626
+ },
627
+ {
628
+ "epoch": 0.8987862373357408,
629
+ "grad_norm": 0.28125,
630
+ "learning_rate": 4.417443548761227e-05,
631
+ "logps_logqs/chosen": 0.08536671847105026,
632
+ "logqs/chosen": -0.8402923345565796,
633
+ "logqs/rejected": -0.915910542011261,
634
+ "logqs_logps/rejected": 0.08888525515794754,
635
+ "loss": 0.3445,
636
+ "step": 560
637
+ },
638
+ {
639
+ "epoch": 0.9148359915738791,
640
+ "grad_norm": 0.294921875,
641
+ "learning_rate": 4.387148319617763e-05,
642
+ "logps_logqs/chosen": 0.08296655118465424,
643
+ "logqs/chosen": -0.8120464086532593,
644
+ "logqs/rejected": -0.8686345219612122,
645
+ "logqs_logps/rejected": 0.08868331462144852,
646
+ "loss": 0.3372,
647
+ "step": 570
648
+ },
649
+ {
650
+ "epoch": 0.9308857458120172,
651
+ "grad_norm": 0.283203125,
652
+ "learning_rate": 4.356194764225618e-05,
653
+ "logps_logqs/chosen": 0.08104117959737778,
654
+ "logqs/chosen": -0.8216385841369629,
655
+ "logqs/rejected": -0.8963106274604797,
656
+ "logqs_logps/rejected": 0.08660975098609924,
657
+ "loss": 0.3355,
658
+ "step": 580
659
+ },
660
+ {
661
+ "epoch": 0.9469355000501555,
662
+ "grad_norm": 0.296875,
663
+ "learning_rate": 4.3245936806433205e-05,
664
+ "logps_logqs/chosen": 0.07939769327640533,
665
+ "logqs/chosen": -0.8180539011955261,
666
+ "logqs/rejected": -0.8782569766044617,
667
+ "logqs_logps/rejected": 0.08691652119159698,
668
+ "loss": 0.3356,
669
+ "step": 590
670
+ },
671
+ {
672
+ "epoch": 0.9629852542882937,
673
+ "grad_norm": 0.30078125,
674
+ "learning_rate": 4.292356092817739e-05,
675
+ "logps_logqs/chosen": 0.08429218828678131,
676
+ "logqs/chosen": -0.8148031234741211,
677
+ "logqs/rejected": -0.8775607943534851,
678
+ "logqs_logps/rejected": 0.08722598850727081,
679
+ "loss": 0.3346,
680
+ "step": 600
681
+ },
682
+ {
683
+ "epoch": 0.979035008526432,
684
+ "grad_norm": 0.265625,
685
+ "learning_rate": 4.259493246738409e-05,
686
+ "logps_logqs/chosen": 0.0812491774559021,
687
+ "logqs/chosen": -0.8289790153503418,
688
+ "logqs/rejected": -0.8987892866134644,
689
+ "logqs_logps/rejected": 0.08712317794561386,
690
+ "loss": 0.3364,
691
+ "step": 610
692
+ },
693
+ {
694
+ "epoch": 0.9950847627645701,
695
+ "grad_norm": 0.302734375,
696
+ "learning_rate": 4.226016606514411e-05,
697
+ "logps_logqs/chosen": 0.0814874917268753,
698
+ "logqs/chosen": -0.8087742924690247,
699
+ "logqs/rejected": -0.8908030390739441,
700
+ "logqs_logps/rejected": 0.0876212790608406,
701
+ "loss": 0.3389,
702
+ "step": 620
703
+ },
704
+ {
705
+ "epoch": 1.0111345170027084,
706
+ "grad_norm": 0.26953125,
707
+ "learning_rate": 4.191937850375136e-05,
708
+ "logps_logqs/chosen": 0.07808364927768707,
709
+ "logqs/chosen": -0.8158828616142273,
710
+ "logqs/rejected": -0.8890725374221802,
711
+ "logqs_logps/rejected": 0.08443473279476166,
712
+ "loss": 0.3268,
713
+ "step": 630
714
+ },
715
+ {
716
+ "epoch": 1.0271842712408465,
717
+ "grad_norm": 0.283203125,
718
+ "learning_rate": 4.157268866596381e-05,
719
+ "logps_logqs/chosen": 0.0806763619184494,
720
+ "logqs/chosen": -0.8284119367599487,
721
+ "logqs/rejected": -0.8865575790405273,
722
+ "logqs_logps/rejected": 0.0866897776722908,
723
+ "loss": 0.3295,
724
+ "step": 640
725
+ },
726
+ {
727
+ "epoch": 1.043234025478985,
728
+ "grad_norm": 0.279296875,
729
+ "learning_rate": 4.1220217493531494e-05,
730
+ "logps_logqs/chosen": 0.07972967624664307,
731
+ "logqs/chosen": -0.8299144506454468,
732
+ "logqs/rejected": -0.8995611071586609,
733
+ "logqs_logps/rejected": 0.08687488734722137,
734
+ "loss": 0.3302,
735
+ "step": 650
736
+ },
737
+ {
738
+ "epoch": 1.059283779717123,
739
+ "grad_norm": 0.283203125,
740
+ "learning_rate": 4.086208794500637e-05,
741
+ "logps_logqs/chosen": 0.07892154902219772,
742
+ "logqs/chosen": -0.813999354839325,
743
+ "logqs/rejected": -0.9233400225639343,
744
+ "logqs_logps/rejected": 0.08419923484325409,
745
+ "loss": 0.325,
746
+ "step": 660
747
+ },
748
+ {
749
+ "epoch": 1.0753335339552612,
750
+ "grad_norm": 0.2490234375,
751
+ "learning_rate": 4.049842495284858e-05,
752
+ "logps_logqs/chosen": 0.07649672031402588,
753
+ "logqs/chosen": -0.7998867034912109,
754
+ "logqs/rejected": -0.8894570469856262,
755
+ "logqs_logps/rejected": 0.08604138344526291,
756
+ "loss": 0.327,
757
+ "step": 670
758
+ },
759
+ {
760
+ "epoch": 1.0913832881933996,
761
+ "grad_norm": 0.259765625,
762
+ "learning_rate": 4.012935537984414e-05,
763
+ "logps_logqs/chosen": 0.07958203554153442,
764
+ "logqs/chosen": -0.7970592379570007,
765
+ "logqs/rejected": -0.88422030210495,
766
+ "logqs_logps/rejected": 0.08651049435138702,
767
+ "loss": 0.3246,
768
+ "step": 680
769
+ },
770
+ {
771
+ "epoch": 1.1074330424315377,
772
+ "grad_norm": 0.267578125,
773
+ "learning_rate": 3.9755007974849135e-05,
774
+ "logps_logqs/chosen": 0.076724112033844,
775
+ "logqs/chosen": -0.817238986492157,
776
+ "logqs/rejected": -0.8899539113044739,
777
+ "logqs_logps/rejected": 0.08536411821842194,
778
+ "loss": 0.3296,
779
+ "step": 690
780
+ },
781
+ {
782
+ "epoch": 1.123482796669676,
783
+ "grad_norm": 0.2578125,
784
+ "learning_rate": 3.93755133278762e-05,
785
+ "logps_logqs/chosen": 0.07787708938121796,
786
+ "logqs/chosen": -0.8070911169052124,
787
+ "logqs/rejected": -0.8890964388847351,
788
+ "logqs_logps/rejected": 0.08466648310422897,
789
+ "loss": 0.3256,
790
+ "step": 700
791
+ },
792
+ {
793
+ "epoch": 1.1395325509078142,
794
+ "grad_norm": 0.2578125,
795
+ "learning_rate": 3.899100382453845e-05,
796
+ "logps_logqs/chosen": 0.07550434023141861,
797
+ "logqs/chosen": -0.7925726771354675,
798
+ "logqs/rejected": -0.8927756547927856,
799
+ "logqs_logps/rejected": 0.08544447273015976,
800
+ "loss": 0.3244,
801
+ "step": 710
802
+ },
803
+ {
804
+ "epoch": 1.1555823051459524,
805
+ "grad_norm": 0.263671875,
806
+ "learning_rate": 3.8601613599867156e-05,
807
+ "logps_logqs/chosen": 0.07930372655391693,
808
+ "logqs/chosen": -0.8030117154121399,
809
+ "logqs/rejected": -0.878372848033905,
810
+ "logqs_logps/rejected": 0.08530044555664062,
811
+ "loss": 0.3244,
812
+ "step": 720
813
+ },
814
+ {
815
+ "epoch": 1.1716320593840908,
816
+ "grad_norm": 0.265625,
817
+ "learning_rate": 3.8207478491519216e-05,
818
+ "logps_logqs/chosen": 0.07744885236024857,
819
+ "logqs/chosen": -0.8023334741592407,
820
+ "logqs/rejected": -0.8822676539421082,
821
+ "logqs_logps/rejected": 0.08438443392515182,
822
+ "loss": 0.3258,
823
+ "step": 730
824
+ },
825
+ {
826
+ "epoch": 1.187681813622229,
827
+ "grad_norm": 0.27734375,
828
+ "learning_rate": 3.780873599239044e-05,
829
+ "logps_logqs/chosen": 0.07315745949745178,
830
+ "logqs/chosen": -0.8033607602119446,
831
+ "logqs/rejected": -0.8938726186752319,
832
+ "logqs_logps/rejected": 0.08519093692302704,
833
+ "loss": 0.327,
834
+ "step": 740
835
+ },
836
+ {
837
+ "epoch": 1.203731567860367,
838
+ "grad_norm": 0.27734375,
839
+ "learning_rate": 3.740552520265167e-05,
840
+ "logps_logqs/chosen": 0.0805806964635849,
841
+ "logqs/chosen": -0.8070894479751587,
842
+ "logqs/rejected": -0.8942106366157532,
843
+ "logqs_logps/rejected": 0.0853462964296341,
844
+ "loss": 0.3277,
845
+ "step": 750
846
+ },
847
+ {
848
+ "epoch": 1.2197813220985054,
849
+ "grad_norm": 0.2578125,
850
+ "learning_rate": 3.699798678122403e-05,
851
+ "logps_logqs/chosen": 0.08243963867425919,
852
+ "logqs/chosen": -0.8198779225349426,
853
+ "logqs/rejected": -0.9114899635314941,
854
+ "logqs_logps/rejected": 0.08301108330488205,
855
+ "loss": 0.3246,
856
+ "step": 760
857
+ },
858
+ {
859
+ "epoch": 1.2358310763366436,
860
+ "grad_norm": 0.24609375,
861
+ "learning_rate": 3.6586262896710476e-05,
862
+ "logps_logqs/chosen": 0.07522697746753693,
863
+ "logqs/chosen": -0.7997868657112122,
864
+ "logqs/rejected": -0.8849021792411804,
865
+ "logqs_logps/rejected": 0.08433938026428223,
866
+ "loss": 0.3225,
867
+ "step": 770
868
+ },
869
+ {
870
+ "epoch": 1.2518808305747817,
871
+ "grad_norm": 0.2578125,
872
+ "learning_rate": 3.61704971778007e-05,
873
+ "logps_logqs/chosen": 0.07380663603544235,
874
+ "logqs/chosen": -0.7977632284164429,
875
+ "logqs/rejected": -0.9076175689697266,
876
+ "logqs_logps/rejected": 0.08456581830978394,
877
+ "loss": 0.3231,
878
+ "step": 780
879
+ },
880
+ {
881
+ "epoch": 1.26793058481292,
882
+ "grad_norm": 0.267578125,
883
+ "learning_rate": 3.575083466316664e-05,
884
+ "logps_logqs/chosen": 0.07891708612442017,
885
+ "logqs/chosen": -0.82396399974823,
886
+ "logqs/rejected": -0.8780908584594727,
887
+ "logqs_logps/rejected": 0.08443116396665573,
888
+ "loss": 0.3279,
889
+ "step": 790
890
+ },
891
+ {
892
+ "epoch": 1.2839803390510582,
893
+ "grad_norm": 0.265625,
894
+ "learning_rate": 3.532742175086621e-05,
895
+ "logps_logqs/chosen": 0.0780521035194397,
896
+ "logqs/chosen": -0.8043760061264038,
897
+ "logqs/rejected": -0.874092698097229,
898
+ "logqs_logps/rejected": 0.08614115417003632,
899
+ "loss": 0.3218,
900
+ "step": 800
901
+ },
902
+ {
903
+ "epoch": 1.3000300932891964,
904
+ "grad_norm": 0.2470703125,
905
+ "learning_rate": 3.490040614727272e-05,
906
+ "logps_logqs/chosen": 0.07666923850774765,
907
+ "logqs/chosen": -0.8054482340812683,
908
+ "logqs/rejected": -0.8948068618774414,
909
+ "logqs_logps/rejected": 0.08540605008602142,
910
+ "loss": 0.3189,
911
+ "step": 810
912
+ },
913
+ {
914
+ "epoch": 1.3160798475273348,
915
+ "grad_norm": 0.26953125,
916
+ "learning_rate": 3.446993681554797e-05,
917
+ "logps_logqs/chosen": 0.07618199288845062,
918
+ "logqs/chosen": -0.7989985942840576,
919
+ "logqs/rejected": -0.9127970933914185,
920
+ "logqs_logps/rejected": 0.08587857335805893,
921
+ "loss": 0.3221,
922
+ "step": 820
923
+ },
924
+ {
925
+ "epoch": 1.332129601765473,
926
+ "grad_norm": 0.263671875,
927
+ "learning_rate": 3.403616392367681e-05,
928
+ "logps_logqs/chosen": 0.0786433070898056,
929
+ "logqs/chosen": -0.8273786306381226,
930
+ "logqs/rejected": -0.9085508584976196,
931
+ "logqs_logps/rejected": 0.08382102847099304,
932
+ "loss": 0.3242,
933
+ "step": 830
934
+ },
935
+ {
936
+ "epoch": 1.3481793560036113,
937
+ "grad_norm": 0.28125,
938
+ "learning_rate": 3.3599238792081575e-05,
939
+ "logps_logqs/chosen": 0.08081017434597015,
940
+ "logqs/chosen": -0.8143576383590698,
941
+ "logqs/rejected": -0.8868357539176941,
942
+ "logqs_logps/rejected": 0.08583888411521912,
943
+ "loss": 0.3232,
944
+ "step": 840
945
+ },
946
+ {
947
+ "epoch": 1.3642291102417494,
948
+ "grad_norm": 0.30859375,
949
+ "learning_rate": 3.315931384083431e-05,
950
+ "logps_logqs/chosen": 0.07726846635341644,
951
+ "logqs/chosen": -0.8076990842819214,
952
+ "logqs/rejected": -0.9137754440307617,
953
+ "logqs_logps/rejected": 0.08542170375585556,
954
+ "loss": 0.3269,
955
+ "step": 850
956
+ },
957
+ {
958
+ "epoch": 1.3802788644798878,
959
+ "grad_norm": 0.271484375,
960
+ "learning_rate": 3.2716542536485474e-05,
961
+ "logps_logqs/chosen": 0.07718624174594879,
962
+ "logqs/chosen": -0.8211753964424133,
963
+ "logqs/rejected": -0.9037491083145142,
964
+ "logqs_logps/rejected": 0.08567257225513458,
965
+ "loss": 0.3245,
966
+ "step": 860
967
+ },
968
+ {
969
+ "epoch": 1.396328618718026,
970
+ "grad_norm": 0.259765625,
971
+ "learning_rate": 3.2271079338527626e-05,
972
+ "logps_logqs/chosen": 0.07549947500228882,
973
+ "logqs/chosen": -0.8031107187271118,
974
+ "logqs/rejected": -0.904284656047821,
975
+ "logqs_logps/rejected": 0.08366312086582184,
976
+ "loss": 0.3196,
977
+ "step": 870
978
+ },
979
+ {
980
+ "epoch": 1.412378372956164,
981
+ "grad_norm": 0.263671875,
982
+ "learning_rate": 3.1823079645512655e-05,
983
+ "logps_logqs/chosen": 0.07497793436050415,
984
+ "logqs/chosen": -0.8042508959770203,
985
+ "logqs/rejected": -0.9088570475578308,
986
+ "logqs_logps/rejected": 0.08382809907197952,
987
+ "loss": 0.321,
988
+ "step": 880
989
+ },
990
+ {
991
+ "epoch": 1.4284281271943025,
992
+ "grad_norm": 0.2421875,
993
+ "learning_rate": 3.137269974084139e-05,
994
+ "logps_logqs/chosen": 0.07816600799560547,
995
+ "logqs/chosen": -0.8011495471000671,
996
+ "logqs/rejected": -0.9165712594985962,
997
+ "logqs_logps/rejected": 0.08399650454521179,
998
+ "loss": 0.3214,
999
+ "step": 890
1000
+ },
1001
+ {
1002
+ "epoch": 1.4444778814324406,
1003
+ "grad_norm": 0.248046875,
1004
+ "learning_rate": 3.092009673824469e-05,
1005
+ "logps_logqs/chosen": 0.0796435996890068,
1006
+ "logqs/chosen": -0.8250038027763367,
1007
+ "logqs/rejected": -0.894701361656189,
1008
+ "logqs_logps/rejected": 0.0849834531545639,
1009
+ "loss": 0.3299,
1010
+ "step": 900
1011
+ },
1012
+ {
1013
+ "epoch": 1.4605276356705787,
1014
+ "grad_norm": 0.26953125,
1015
+ "learning_rate": 3.0465428526974665e-05,
1016
+ "logps_logqs/chosen": 0.0747985765337944,
1017
+ "logqs/chosen": -0.7987441420555115,
1018
+ "logqs/rejected": -0.8858783841133118,
1019
+ "logqs_logps/rejected": 0.08518994599580765,
1020
+ "loss": 0.3198,
1021
+ "step": 910
1022
+ },
1023
+ {
1024
+ "epoch": 1.4765773899087171,
1025
+ "grad_norm": 0.25390625,
1026
+ "learning_rate": 3.000885371672554e-05,
1027
+ "logps_logqs/chosen": 0.0736977607011795,
1028
+ "logqs/chosen": -0.796042799949646,
1029
+ "logqs/rejected": -0.8840726017951965,
1030
+ "logqs_logps/rejected": 0.08356060087680817,
1031
+ "loss": 0.3189,
1032
+ "step": 920
1033
+ },
1034
+ {
1035
+ "epoch": 1.4926271441468553,
1036
+ "grad_norm": 0.2333984375,
1037
+ "learning_rate": 2.9550531582303082e-05,
1038
+ "logps_logqs/chosen": 0.07697046548128128,
1039
+ "logqs/chosen": -0.8012852668762207,
1040
+ "logqs/rejected": -0.8978139758110046,
1041
+ "logqs_logps/rejected": 0.08473887294530869,
1042
+ "loss": 0.3234,
1043
+ "step": 930
1044
+ },
1045
+ {
1046
+ "epoch": 1.5086768983849934,
1047
+ "grad_norm": 0.26171875,
1048
+ "learning_rate": 2.909062200806208e-05,
1049
+ "logps_logqs/chosen": 0.07491417229175568,
1050
+ "logqs/chosen": -0.8042458295822144,
1051
+ "logqs/rejected": -0.9043086767196655,
1052
+ "logqs_logps/rejected": 0.08307308703660965,
1053
+ "loss": 0.3185,
1054
+ "step": 940
1055
+ },
1056
+ {
1057
+ "epoch": 1.5247266526231318,
1058
+ "grad_norm": 0.24609375,
1059
+ "learning_rate": 2.8629285432131083e-05,
1060
+ "logps_logqs/chosen": 0.07444656640291214,
1061
+ "logqs/chosen": -0.7999377250671387,
1062
+ "logqs/rejected": -0.8958683013916016,
1063
+ "logqs_logps/rejected": 0.08302817493677139,
1064
+ "loss": 0.3192,
1065
+ "step": 950
1066
+ },
1067
+ {
1068
+ "epoch": 1.54077640686127,
1069
+ "grad_norm": 0.248046875,
1070
+ "learning_rate": 2.8166682790444116e-05,
1071
+ "logps_logqs/chosen": 0.0736972838640213,
1072
+ "logqs/chosen": -0.8029756546020508,
1073
+ "logqs/rejected": -0.9172306060791016,
1074
+ "logqs_logps/rejected": 0.08177176862955093,
1075
+ "loss": 0.3192,
1076
+ "step": 960
1077
+ },
1078
+ {
1079
+ "epoch": 1.556826161099408,
1080
+ "grad_norm": 0.2578125,
1081
+ "learning_rate": 2.7702975460598547e-05,
1082
+ "logps_logqs/chosen": 0.07327345758676529,
1083
+ "logqs/chosen": -0.7889487147331238,
1084
+ "logqs/rejected": -0.8995023965835571,
1085
+ "logqs_logps/rejected": 0.08234850317239761,
1086
+ "loss": 0.3179,
1087
+ "step": 970
1088
+ },
1089
+ {
1090
+ "epoch": 1.5728759153375464,
1091
+ "grad_norm": 0.263671875,
1092
+ "learning_rate": 2.723832520555905e-05,
1093
+ "logps_logqs/chosen": 0.07713175565004349,
1094
+ "logqs/chosen": -0.809069037437439,
1095
+ "logqs/rejected": -0.9176934957504272,
1096
+ "logqs_logps/rejected": 0.08256009966135025,
1097
+ "loss": 0.3216,
1098
+ "step": 980
1099
+ },
1100
+ {
1101
+ "epoch": 1.5889256695756846,
1102
+ "grad_norm": 0.240234375,
1103
+ "learning_rate": 2.677289411722702e-05,
1104
+ "logps_logqs/chosen": 0.07451427727937698,
1105
+ "logqs/chosen": -0.8091384172439575,
1106
+ "logqs/rejected": -0.9061697721481323,
1107
+ "logqs_logps/rejected": 0.08387144654989243,
1108
+ "loss": 0.3227,
1109
+ "step": 990
1110
+ },
1111
+ {
1112
+ "epoch": 1.6049754238138227,
1113
+ "grad_norm": 0.259765625,
1114
+ "learning_rate": 2.63068445598953e-05,
1115
+ "logps_logqs/chosen": 0.07487618923187256,
1116
+ "logqs/chosen": -0.8033574819564819,
1117
+ "logqs/rejected": -0.9179302453994751,
1118
+ "logqs_logps/rejected": 0.08198346197605133,
1119
+ "loss": 0.3233,
1120
+ "step": 1000
1121
+ },
1122
+ {
1123
+ "epoch": 1.6210251780519611,
1124
+ "grad_norm": 0.251953125,
1125
+ "learning_rate": 2.5840339113607854e-05,
1126
+ "logps_logqs/chosen": 0.07482868432998657,
1127
+ "logqs/chosen": -0.7901092767715454,
1128
+ "logqs/rejected": -0.8936401605606079,
1129
+ "logqs_logps/rejected": 0.08298007398843765,
1130
+ "loss": 0.32,
1131
+ "step": 1010
1132
+ },
1133
+ {
1134
+ "epoch": 1.6370749322900993,
1135
+ "grad_norm": 0.2578125,
1136
+ "learning_rate": 2.53735405174442e-05,
1137
+ "logps_logqs/chosen": 0.07392865419387817,
1138
+ "logqs/chosen": -0.7897070646286011,
1139
+ "logqs/rejected": -0.9076752662658691,
1140
+ "logqs_logps/rejected": 0.08304780721664429,
1141
+ "loss": 0.3197,
1142
+ "step": 1020
1143
+ },
1144
+ {
1145
+ "epoch": 1.6531246865282374,
1146
+ "grad_norm": 0.25390625,
1147
+ "learning_rate": 2.490661161274835e-05,
1148
+ "logps_logqs/chosen": 0.07797589153051376,
1149
+ "logqs/chosen": -0.8021060824394226,
1150
+ "logqs/rejected": -0.9039047360420227,
1151
+ "logqs_logps/rejected": 0.08419740200042725,
1152
+ "loss": 0.3199,
1153
+ "step": 1030
1154
+ },
1155
+ {
1156
+ "epoch": 1.6691744407663758,
1157
+ "grad_norm": 0.25390625,
1158
+ "learning_rate": 2.443971528632205e-05,
1159
+ "logps_logqs/chosen": 0.07501687109470367,
1160
+ "logqs/chosen": -0.8008750081062317,
1161
+ "logqs/rejected": -0.8964029550552368,
1162
+ "logqs_logps/rejected": 0.08230260759592056,
1163
+ "loss": 0.3169,
1164
+ "step": 1040
1165
+ },
1166
+ {
1167
+ "epoch": 1.6852241950045141,
1168
+ "grad_norm": 0.251953125,
1169
+ "learning_rate": 2.3973014413602238e-05,
1170
+ "logps_logqs/chosen": 0.07347197085618973,
1171
+ "logqs/chosen": -0.8004202842712402,
1172
+ "logqs/rejected": -0.8897308111190796,
1173
+ "logqs_logps/rejected": 0.08417828381061554,
1174
+ "loss": 0.3197,
1175
+ "step": 1050
1176
+ },
1177
+ {
1178
+ "epoch": 1.701273949242652,
1179
+ "grad_norm": 0.25390625,
1180
+ "learning_rate": 2.3506671801842364e-05,
1181
+ "logps_logqs/chosen": 0.07608149200677872,
1182
+ "logqs/chosen": -0.8141935467720032,
1183
+ "logqs/rejected": -0.9073457717895508,
1184
+ "logqs_logps/rejected": 0.08230859041213989,
1185
+ "loss": 0.3193,
1186
+ "step": 1060
1187
+ },
1188
+ {
1189
+ "epoch": 1.7173237034807904,
1190
+ "grad_norm": 0.251953125,
1191
+ "learning_rate": 2.3040850133317597e-05,
1192
+ "logps_logqs/chosen": 0.07689784467220306,
1193
+ "logqs/chosen": -0.8076275587081909,
1194
+ "logqs/rejected": -0.9122416377067566,
1195
+ "logqs_logps/rejected": 0.08308029919862747,
1196
+ "loss": 0.3223,
1197
+ "step": 1070
1198
+ },
1199
+ {
1200
+ "epoch": 1.7333734577189288,
1201
+ "grad_norm": 0.2412109375,
1202
+ "learning_rate": 2.2575711908573548e-05,
1203
+ "logps_logqs/chosen": 0.07234277576208115,
1204
+ "logqs/chosen": -0.7936676740646362,
1205
+ "logqs/rejected": -0.9038996696472168,
1206
+ "logqs_logps/rejected": 0.08316074311733246,
1207
+ "loss": 0.3167,
1208
+ "step": 1080
1209
+ },
1210
+ {
1211
+ "epoch": 1.749423211957067,
1212
+ "grad_norm": 0.251953125,
1213
+ "learning_rate": 2.2111419389738435e-05,
1214
+ "logps_logqs/chosen": 0.07605086266994476,
1215
+ "logqs/chosen": -0.8008819818496704,
1216
+ "logqs/rejected": -0.8876243829727173,
1217
+ "logqs_logps/rejected": 0.08395352214574814,
1218
+ "loss": 0.3169,
1219
+ "step": 1090
1220
+ },
1221
+ {
1222
+ "epoch": 1.765472966195205,
1223
+ "grad_norm": 0.244140625,
1224
+ "learning_rate": 2.1648134543918423e-05,
1225
+ "logps_logqs/chosen": 0.07533862441778183,
1226
+ "logqs/chosen": -0.7902143597602844,
1227
+ "logqs/rejected": -0.8612885475158691,
1228
+ "logqs_logps/rejected": 0.0841139703989029,
1229
+ "loss": 0.3174,
1230
+ "step": 1100
1231
+ },
1232
+ {
1233
+ "epoch": 1.7815227204333435,
1234
+ "grad_norm": 0.2373046875,
1235
+ "learning_rate": 2.1186018986695842e-05,
1236
+ "logps_logqs/chosen": 0.07465896010398865,
1237
+ "logqs/chosen": -0.8092859387397766,
1238
+ "logqs/rejected": -0.9027106165885925,
1239
+ "logqs_logps/rejected": 0.08286880701780319,
1240
+ "loss": 0.3181,
1241
+ "step": 1110
1242
+ },
1243
+ {
1244
+ "epoch": 1.7975724746714816,
1245
+ "grad_norm": 0.2431640625,
1246
+ "learning_rate": 2.0725233925750063e-05,
1247
+ "logps_logqs/chosen": 0.0745125412940979,
1248
+ "logqs/chosen": -0.8020778894424438,
1249
+ "logqs/rejected": -0.8988272547721863,
1250
+ "logqs_logps/rejected": 0.082740917801857,
1251
+ "loss": 0.3153,
1252
+ "step": 1120
1253
+ },
1254
+ {
1255
+ "epoch": 1.8136222289096198,
1256
+ "grad_norm": 0.26171875,
1257
+ "learning_rate": 2.026594010462068e-05,
1258
+ "logps_logqs/chosen": 0.07593352347612381,
1259
+ "logqs/chosen": -0.8027118444442749,
1260
+ "logqs/rejected": -0.9119024276733398,
1261
+ "logqs_logps/rejected": 0.08280286937952042,
1262
+ "loss": 0.3207,
1263
+ "step": 1130
1264
+ },
1265
+ {
1266
+ "epoch": 1.8296719831477581,
1267
+ "grad_norm": 0.251953125,
1268
+ "learning_rate": 1.980829774663256e-05,
1269
+ "logps_logqs/chosen": 0.07631193101406097,
1270
+ "logqs/chosen": -0.8121039271354675,
1271
+ "logqs/rejected": -0.908685028553009,
1272
+ "logqs_logps/rejected": 0.08407546579837799,
1273
+ "loss": 0.3198,
1274
+ "step": 1140
1275
+ },
1276
+ {
1277
+ "epoch": 1.8457217373858963,
1278
+ "grad_norm": 0.2431640625,
1279
+ "learning_rate": 1.9352466499002422e-05,
1280
+ "logps_logqs/chosen": 0.07544290274381638,
1281
+ "logqs/chosen": -0.8096615076065063,
1282
+ "logqs/rejected": -0.9020143747329712,
1283
+ "logqs_logps/rejected": 0.08248680830001831,
1284
+ "loss": 0.3198,
1285
+ "step": 1150
1286
+ },
1287
+ {
1288
+ "epoch": 1.8617714916240344,
1289
+ "grad_norm": 0.2353515625,
1290
+ "learning_rate": 1.8898605377146383e-05,
1291
+ "logps_logqs/chosen": 0.07422982156276703,
1292
+ "logqs/chosen": -0.8104985952377319,
1293
+ "logqs/rejected": -0.9090179204940796,
1294
+ "logqs_logps/rejected": 0.08247785270214081,
1295
+ "loss": 0.3183,
1296
+ "step": 1160
1297
+ },
1298
+ {
1299
+ "epoch": 1.8778212458621728,
1300
+ "grad_norm": 0.271484375,
1301
+ "learning_rate": 1.8446872709207847e-05,
1302
+ "logps_logqs/chosen": 0.07435441762208939,
1303
+ "logqs/chosen": -0.8137333989143372,
1304
+ "logqs/rejected": -0.9299784898757935,
1305
+ "logqs_logps/rejected": 0.08275195211172104,
1306
+ "loss": 0.3227,
1307
+ "step": 1170
1308
+ },
1309
+ {
1310
+ "epoch": 1.893871000100311,
1311
+ "grad_norm": 0.23828125,
1312
+ "learning_rate": 1.799742608082519e-05,
1313
+ "logps_logqs/chosen": 0.0697832927107811,
1314
+ "logqs/chosen": -0.7819542288780212,
1315
+ "logqs/rejected": -0.8906014561653137,
1316
+ "logqs_logps/rejected": 0.08177825063467026,
1317
+ "loss": 0.312,
1318
+ "step": 1180
1319
+ },
1320
+ {
1321
+ "epoch": 1.909920754338449,
1322
+ "grad_norm": 0.255859375,
1323
+ "learning_rate": 1.7550422280158513e-05,
1324
+ "logps_logqs/chosen": 0.07729648053646088,
1325
+ "logqs/chosen": -0.8102595210075378,
1326
+ "logqs/rejected": -0.904281497001648,
1327
+ "logqs_logps/rejected": 0.0822812020778656,
1328
+ "loss": 0.3192,
1329
+ "step": 1190
1330
+ },
1331
+ {
1332
+ "epoch": 1.9259705085765875,
1333
+ "grad_norm": 0.2451171875,
1334
+ "learning_rate": 1.7106017243194487e-05,
1335
+ "logps_logqs/chosen": 0.07507346570491791,
1336
+ "logqs/chosen": -0.7959727048873901,
1337
+ "logqs/rejected": -0.9095916748046875,
1338
+ "logqs_logps/rejected": 0.08093559741973877,
1339
+ "loss": 0.3228,
1340
+ "step": 1200
1341
+ },
1342
+ {
1343
+ "epoch": 1.9420202628147256,
1344
+ "grad_norm": 0.251953125,
1345
+ "learning_rate": 1.6664365999348594e-05,
1346
+ "logps_logqs/chosen": 0.07413261383771896,
1347
+ "logqs/chosen": -0.7935149073600769,
1348
+ "logqs/rejected": -0.8980931043624878,
1349
+ "logqs_logps/rejected": 0.08442027121782303,
1350
+ "loss": 0.3173,
1351
+ "step": 1210
1352
+ },
1353
+ {
1354
+ "epoch": 1.9580700170528638,
1355
+ "grad_norm": 0.2421875,
1356
+ "learning_rate": 1.6225622617383494e-05,
1357
+ "logps_logqs/chosen": 0.07162965834140778,
1358
+ "logqs/chosen": -0.7896697521209717,
1359
+ "logqs/rejected": -0.8827974200248718,
1360
+ "logqs_logps/rejected": 0.08332808315753937,
1361
+ "loss": 0.3138,
1362
+ "step": 1220
1363
+ },
1364
+ {
1365
+ "epoch": 1.9741197712910021,
1366
+ "grad_norm": 0.2451171875,
1367
+ "learning_rate": 1.578994015166263e-05,
1368
+ "logps_logqs/chosen": 0.07460381835699081,
1369
+ "logqs/chosen": -0.8117923736572266,
1370
+ "logqs/rejected": -0.9152690172195435,
1371
+ "logqs_logps/rejected": 0.0810333639383316,
1372
+ "loss": 0.3209,
1373
+ "step": 1230
1374
+ },
1375
+ {
1376
+ "epoch": 1.9901695255291403,
1377
+ "grad_norm": 0.2431640625,
1378
+ "learning_rate": 1.535747058875765e-05,
1379
+ "logps_logqs/chosen": 0.07367164641618729,
1380
+ "logqs/chosen": -0.7960913777351379,
1381
+ "logqs/rejected": -0.8929139375686646,
1382
+ "logqs_logps/rejected": 0.08183646202087402,
1383
+ "loss": 0.3162,
1384
+ "step": 1240
1385
+ },
1386
+ {
1387
+ "epoch": 2.0062192797672784,
1388
+ "grad_norm": 0.2333984375,
1389
+ "learning_rate": 1.4928364794428307e-05,
1390
+ "logps_logqs/chosen": 0.07295754551887512,
1391
+ "logqs/chosen": -0.8024552464485168,
1392
+ "logqs/rejected": -0.918504536151886,
1393
+ "logqs_logps/rejected": 0.08203531801700592,
1394
+ "loss": 0.314,
1395
+ "step": 1250
1396
+ },
1397
+ {
1398
+ "epoch": 2.022269034005417,
1399
+ "grad_norm": 0.232421875,
1400
+ "learning_rate": 1.4502772460993385e-05,
1401
+ "logps_logqs/chosen": 0.073900006711483,
1402
+ "logqs/chosen": -0.7975751757621765,
1403
+ "logqs/rejected": -0.9003852605819702,
1404
+ "logqs_logps/rejected": 0.08287613093852997,
1405
+ "loss": 0.3139,
1406
+ "step": 1260
1407
+ },
1408
+ {
1409
+ "epoch": 2.038318788243555,
1410
+ "grad_norm": 0.2333984375,
1411
+ "learning_rate": 1.4080842055110993e-05,
1412
+ "logps_logqs/chosen": 0.07410914450883865,
1413
+ "logqs/chosen": -0.789171040058136,
1414
+ "logqs/rejected": -0.8948004841804504,
1415
+ "logqs_logps/rejected": 0.08315090835094452,
1416
+ "loss": 0.315,
1417
+ "step": 1270
1418
+ },
1419
+ {
1420
+ "epoch": 2.054368542481693,
1421
+ "grad_norm": 0.2353515625,
1422
+ "learning_rate": 1.3662720765986341e-05,
1423
+ "logps_logqs/chosen": 0.0750800222158432,
1424
+ "logqs/chosen": -0.8148080706596375,
1425
+ "logqs/rejected": -0.9173944592475891,
1426
+ "logqs_logps/rejected": 0.08202828466892242,
1427
+ "loss": 0.3141,
1428
+ "step": 1280
1429
+ },
1430
+ {
1431
+ "epoch": 2.0704182967198315,
1432
+ "grad_norm": 0.244140625,
1433
+ "learning_rate": 1.3248554454025275e-05,
1434
+ "logps_logqs/chosen": 0.07371431589126587,
1435
+ "logqs/chosen": -0.7904887795448303,
1436
+ "logqs/rejected": -0.892736554145813,
1437
+ "logqs_logps/rejected": 0.08251521736383438,
1438
+ "loss": 0.3121,
1439
+ "step": 1290
1440
+ },
1441
+ {
1442
+ "epoch": 2.08646805095797,
1443
+ "grad_norm": 0.236328125,
1444
+ "learning_rate": 1.2838487599951243e-05,
1445
+ "logps_logqs/chosen": 0.07491550594568253,
1446
+ "logqs/chosen": -0.8070290684700012,
1447
+ "logqs/rejected": -0.8995240926742554,
1448
+ "logqs_logps/rejected": 0.08239687979221344,
1449
+ "loss": 0.3139,
1450
+ "step": 1300
1451
+ },
1452
+ {
1453
+ "epoch": 2.1025178051961078,
1454
+ "grad_norm": 0.2353515625,
1455
+ "learning_rate": 1.2432663254403638e-05,
1456
+ "logps_logqs/chosen": 0.07226058095693588,
1457
+ "logqs/chosen": -0.8035115003585815,
1458
+ "logqs/rejected": -0.8938866853713989,
1459
+ "logqs_logps/rejected": 0.08264483511447906,
1460
+ "loss": 0.3162,
1461
+ "step": 1310
1462
+ },
1463
+ {
1464
+ "epoch": 2.118567559434246,
1465
+ "grad_norm": 0.232421875,
1466
+ "learning_rate": 1.2031222988034967e-05,
1467
+ "logps_logqs/chosen": 0.07458813488483429,
1468
+ "logqs/chosen": -0.7981353998184204,
1469
+ "logqs/rejected": -0.8914963006973267,
1470
+ "logqs_logps/rejected": 0.08298441767692566,
1471
+ "loss": 0.3121,
1472
+ "step": 1320
1473
+ },
1474
+ {
1475
+ "epoch": 2.1346173136723845,
1476
+ "grad_norm": 0.2255859375,
1477
+ "learning_rate": 1.1634306842124423e-05,
1478
+ "logps_logqs/chosen": 0.07301259785890579,
1479
+ "logqs/chosen": -0.7957206964492798,
1480
+ "logqs/rejected": -0.9006513357162476,
1481
+ "logqs_logps/rejected": 0.08207239955663681,
1482
+ "loss": 0.3104,
1483
+ "step": 1330
1484
+ },
1485
+ {
1486
+ "epoch": 2.1506670679105224,
1487
+ "grad_norm": 0.2412109375,
1488
+ "learning_rate": 1.1242053279724762e-05,
1489
+ "logps_logqs/chosen": 0.07079671323299408,
1490
+ "logqs/chosen": -0.7900751233100891,
1491
+ "logqs/rejected": -0.9003415107727051,
1492
+ "logqs_logps/rejected": 0.08099430054426193,
1493
+ "loss": 0.3096,
1494
+ "step": 1340
1495
+ },
1496
+ {
1497
+ "epoch": 2.166716822148661,
1498
+ "grad_norm": 0.2265625,
1499
+ "learning_rate": 1.0854599137359953e-05,
1500
+ "logps_logqs/chosen": 0.07582630217075348,
1501
+ "logqs/chosen": -0.8164023160934448,
1502
+ "logqs/rejected": -0.9069350361824036,
1503
+ "logqs_logps/rejected": 0.08237835019826889,
1504
+ "loss": 0.3158,
1505
+ "step": 1350
1506
+ },
1507
+ {
1508
+ "epoch": 2.182766576386799,
1509
+ "grad_norm": 0.2255859375,
1510
+ "learning_rate": 1.0472079577290111e-05,
1511
+ "logps_logqs/chosen": 0.07026050239801407,
1512
+ "logqs/chosen": -0.7865276336669922,
1513
+ "logqs/rejected": -0.9271472096443176,
1514
+ "logqs_logps/rejected": 0.08012039959430695,
1515
+ "loss": 0.3125,
1516
+ "step": 1360
1517
+ },
1518
+ {
1519
+ "epoch": 2.198816330624937,
1520
+ "grad_norm": 0.2314453125,
1521
+ "learning_rate": 1.009462804036059e-05,
1522
+ "logps_logqs/chosen": 0.07350893318653107,
1523
+ "logqs/chosen": -0.7845043540000916,
1524
+ "logqs/rejected": -0.8784573674201965,
1525
+ "logqs_logps/rejected": 0.08172748982906342,
1526
+ "loss": 0.3118,
1527
+ "step": 1370
1528
+ },
1529
+ {
1530
+ "epoch": 2.2148660848630755,
1531
+ "grad_norm": 0.23828125,
1532
+ "learning_rate": 9.722376199451436e-06,
1533
+ "logps_logqs/chosen": 0.07753650844097137,
1534
+ "logqs/chosen": -0.8113786578178406,
1535
+ "logqs/rejected": -0.895952582359314,
1536
+ "logqs_logps/rejected": 0.08141981810331345,
1537
+ "loss": 0.3144,
1538
+ "step": 1380
1539
+ },
1540
+ {
1541
+ "epoch": 2.230915839101214,
1542
+ "grad_norm": 0.23046875,
1543
+ "learning_rate": 9.35545391354378e-06,
1544
+ "logps_logqs/chosen": 0.07038865983486176,
1545
+ "logqs/chosen": -0.7959168553352356,
1546
+ "logqs/rejected": -0.8996925354003906,
1547
+ "logqs_logps/rejected": 0.08161251246929169,
1548
+ "loss": 0.3102,
1549
+ "step": 1390
1550
+ },
1551
+ {
1552
+ "epoch": 2.246965593339352,
1553
+ "grad_norm": 0.2314453125,
1554
+ "learning_rate": 8.993989182418824e-06,
1555
+ "logps_logqs/chosen": 0.0729217380285263,
1556
+ "logqs/chosen": -0.8092435598373413,
1557
+ "logqs/rejected": -0.8962046504020691,
1558
+ "logqs_logps/rejected": 0.08081961423158646,
1559
+ "loss": 0.3126,
1560
+ "step": 1400
1561
+ },
1562
+ {
1563
+ "epoch": 2.26301534757749,
1564
+ "grad_norm": 0.236328125,
1565
+ "learning_rate": 8.63810810200556e-06,
1566
+ "logps_logqs/chosen": 0.07263143360614777,
1567
+ "logqs/chosen": -0.7884143590927124,
1568
+ "logqs/rejected": -0.9198802709579468,
1569
+ "logqs_logps/rejected": 0.08146072924137115,
1570
+ "loss": 0.3116,
1571
+ "step": 1410
1572
+ },
1573
+ {
1574
+ "epoch": 2.2790651018156285,
1575
+ "grad_norm": 0.23046875,
1576
+ "learning_rate": 8.287934820392498e-06,
1577
+ "logps_logqs/chosen": 0.07447274029254913,
1578
+ "logqs/chosen": -0.8072949647903442,
1579
+ "logqs/rejected": -0.9363552927970886,
1580
+ "logqs_logps/rejected": 0.08067592978477478,
1581
+ "loss": 0.3122,
1582
+ "step": 1420
1583
+ },
1584
+ {
1585
+ "epoch": 2.295114856053767,
1586
+ "grad_norm": 0.2275390625,
1587
+ "learning_rate": 7.943591494519016e-06,
1588
+ "logps_logqs/chosen": 0.0729929506778717,
1589
+ "logqs/chosen": -0.8074385523796082,
1590
+ "logqs/rejected": -0.9285086393356323,
1591
+ "logqs_logps/rejected": 0.08008907735347748,
1592
+ "loss": 0.314,
1593
+ "step": 1430
1594
+ },
1595
+ {
1596
+ "epoch": 2.311164610291905,
1597
+ "grad_norm": 0.2197265625,
1598
+ "learning_rate": 7.60519824756124e-06,
1599
+ "logps_logqs/chosen": 0.07292158156633377,
1600
+ "logqs/chosen": -0.7946223616600037,
1601
+ "logqs/rejected": -0.9008995890617371,
1602
+ "logqs_logps/rejected": 0.08113256096839905,
1603
+ "loss": 0.3134,
1604
+ "step": 1440
1605
+ },
1606
+ {
1607
+ "epoch": 2.327214364530043,
1608
+ "grad_norm": 0.23046875,
1609
+ "learning_rate": 7.272873127027449e-06,
1610
+ "logps_logqs/chosen": 0.07243537902832031,
1611
+ "logqs/chosen": -0.7918037176132202,
1612
+ "logqs/rejected": -0.8832144737243652,
1613
+ "logqs_logps/rejected": 0.08229474723339081,
1614
+ "loss": 0.3128,
1615
+ "step": 1450
1616
+ },
1617
+ {
1618
+ "epoch": 2.3432641187681815,
1619
+ "grad_norm": 0.23046875,
1620
+ "learning_rate": 6.946732063577488e-06,
1621
+ "logps_logqs/chosen": 0.07624879479408264,
1622
+ "logqs/chosen": -0.8100885152816772,
1623
+ "logqs/rejected": -0.8934513330459595,
1624
+ "logqs_logps/rejected": 0.0827435851097107,
1625
+ "loss": 0.3115,
1626
+ "step": 1460
1627
+ },
1628
+ {
1629
+ "epoch": 2.3593138730063195,
1630
+ "grad_norm": 0.2314453125,
1631
+ "learning_rate": 6.6268888305807296e-06,
1632
+ "logps_logqs/chosen": 0.07390271872282028,
1633
+ "logqs/chosen": -0.792887806892395,
1634
+ "logqs/rejected": -0.8847257494926453,
1635
+ "logqs_logps/rejected": 0.08261798322200775,
1636
+ "loss": 0.3104,
1637
+ "step": 1470
1638
+ },
1639
+ {
1640
+ "epoch": 2.375363627244458,
1641
+ "grad_norm": 0.228515625,
1642
+ "learning_rate": 6.313455004426577e-06,
1643
+ "logps_logqs/chosen": 0.07358037680387497,
1644
+ "logqs/chosen": -0.7838066816329956,
1645
+ "logqs/rejected": -0.9078797101974487,
1646
+ "logqs_logps/rejected": 0.08071611076593399,
1647
+ "loss": 0.3106,
1648
+ "step": 1480
1649
+ },
1650
+ {
1651
+ "epoch": 2.391413381482596,
1652
+ "grad_norm": 0.2373046875,
1653
+ "learning_rate": 6.0065399256013204e-06,
1654
+ "logps_logqs/chosen": 0.078421950340271,
1655
+ "logqs/chosen": -0.8123919367790222,
1656
+ "logqs/rejected": -0.8939984440803528,
1657
+ "logqs_logps/rejected": 0.08118218928575516,
1658
+ "loss": 0.3169,
1659
+ "step": 1490
1660
+ },
1661
+ {
1662
+ "epoch": 2.407463135720734,
1663
+ "grad_norm": 0.228515625,
1664
+ "learning_rate": 5.7062506605450454e-06,
1665
+ "logps_logqs/chosen": 0.07398053258657455,
1666
+ "logqs/chosen": -0.8026934862136841,
1667
+ "logqs/rejected": -0.8954586982727051,
1668
+ "logqs_logps/rejected": 0.08243472129106522,
1669
+ "loss": 0.3147,
1670
+ "step": 1500
1671
+ },
1672
+ {
1673
+ "epoch": 2.4235128899588725,
1674
+ "grad_norm": 0.2333984375,
1675
+ "learning_rate": 5.412691964301827e-06,
1676
+ "logps_logqs/chosen": 0.07238447666168213,
1677
+ "logqs/chosen": -0.8131697773933411,
1678
+ "logqs/rejected": -0.9339205622673035,
1679
+ "logqs_logps/rejected": 0.08201464265584946,
1680
+ "loss": 0.3136,
1681
+ "step": 1510
1682
+ },
1683
+ {
1684
+ "epoch": 2.439562644197011,
1685
+ "grad_norm": 0.2353515625,
1686
+ "learning_rate": 5.125966243976218e-06,
1687
+ "logps_logqs/chosen": 0.07509394735097885,
1688
+ "logqs/chosen": -0.78544682264328,
1689
+ "logqs/rejected": -0.8901753425598145,
1690
+ "logqs_logps/rejected": 0.08143877983093262,
1691
+ "loss": 0.311,
1692
+ "step": 1520
1693
+ },
1694
+ {
1695
+ "epoch": 2.455612398435149,
1696
+ "grad_norm": 0.232421875,
1697
+ "learning_rate": 4.846173523008824e-06,
1698
+ "logps_logqs/chosen": 0.07063795626163483,
1699
+ "logqs/chosen": -0.7890464067459106,
1700
+ "logqs/rejected": -0.9245685338973999,
1701
+ "logqs_logps/rejected": 0.08157093822956085,
1702
+ "loss": 0.3102,
1703
+ "step": 1530
1704
+ },
1705
+ {
1706
+ "epoch": 2.471662152673287,
1707
+ "grad_norm": 0.2236328125,
1708
+ "learning_rate": 4.573411406283409e-06,
1709
+ "logps_logqs/chosen": 0.07790166139602661,
1710
+ "logqs/chosen": -0.8271121978759766,
1711
+ "logqs/rejected": -0.9096291661262512,
1712
+ "logqs_logps/rejected": 0.08363105356693268,
1713
+ "loss": 0.3189,
1714
+ "step": 1540
1715
+ },
1716
+ {
1717
+ "epoch": 2.4877119069114255,
1718
+ "grad_norm": 0.2275390625,
1719
+ "learning_rate": 4.307775046077739e-06,
1720
+ "logps_logqs/chosen": 0.07722210884094238,
1721
+ "logqs/chosen": -0.8067975044250488,
1722
+ "logqs/rejected": -0.905848503112793,
1723
+ "logqs_logps/rejected": 0.08417145162820816,
1724
+ "loss": 0.3166,
1725
+ "step": 1550
1726
+ },
1727
+ {
1728
+ "epoch": 2.5037616611495634,
1729
+ "grad_norm": 0.232421875,
1730
+ "learning_rate": 4.049357108869964e-06,
1731
+ "logps_logqs/chosen": 0.07566576451063156,
1732
+ "logqs/chosen": -0.807111918926239,
1733
+ "logqs/rejected": -0.896578311920166,
1734
+ "logqs_logps/rejected": 0.08398713916540146,
1735
+ "loss": 0.3156,
1736
+ "step": 1560
1737
+ },
1738
+ {
1739
+ "epoch": 2.519811415387702,
1740
+ "grad_norm": 0.236328125,
1741
+ "learning_rate": 3.798247743012201e-06,
1742
+ "logps_logqs/chosen": 0.07113765180110931,
1743
+ "logqs/chosen": -0.8036268949508667,
1744
+ "logqs/rejected": -0.9011009335517883,
1745
+ "logqs_logps/rejected": 0.08287129551172256,
1746
+ "loss": 0.3125,
1747
+ "step": 1570
1748
+ },
1749
+ {
1750
+ "epoch": 2.53586116962584,
1751
+ "grad_norm": 0.2275390625,
1752
+ "learning_rate": 3.554534547282512e-06,
1753
+ "logps_logqs/chosen": 0.07366280257701874,
1754
+ "logqs/chosen": -0.7989723086357117,
1755
+ "logqs/rejected": -0.884625256061554,
1756
+ "logqs_logps/rejected": 0.08136685937643051,
1757
+ "loss": 0.3152,
1758
+ "step": 1580
1759
+ },
1760
+ {
1761
+ "epoch": 2.5519109238639786,
1762
+ "grad_norm": 0.232421875,
1763
+ "learning_rate": 3.318302540326343e-06,
1764
+ "logps_logqs/chosen": 0.07400309294462204,
1765
+ "logqs/chosen": -0.8105365633964539,
1766
+ "logqs/rejected": -0.9077731966972351,
1767
+ "logqs_logps/rejected": 0.0812162458896637,
1768
+ "loss": 0.3164,
1769
+ "step": 1590
1770
+ },
1771
+ {
1772
+ "epoch": 2.5679606781021165,
1773
+ "grad_norm": 0.2265625,
1774
+ "learning_rate": 3.089634130998026e-06,
1775
+ "logps_logqs/chosen": 0.07428063452243805,
1776
+ "logqs/chosen": -0.8025354146957397,
1777
+ "logqs/rejected": -0.9122070074081421,
1778
+ "logqs_logps/rejected": 0.08231757581233978,
1779
+ "loss": 0.313,
1780
+ "step": 1600
1781
+ },
1782
+ {
1783
+ "epoch": 2.584010432340255,
1784
+ "grad_norm": 0.2275390625,
1785
+ "learning_rate": 2.8686090896126587e-06,
1786
+ "logps_logqs/chosen": 0.07186438143253326,
1787
+ "logqs/chosen": -0.7830988168716431,
1788
+ "logqs/rejected": -0.8839938044548035,
1789
+ "logqs_logps/rejected": 0.08267438411712646,
1790
+ "loss": 0.3066,
1791
+ "step": 1610
1792
+ },
1793
+ {
1794
+ "epoch": 2.6000601865783928,
1795
+ "grad_norm": 0.2255859375,
1796
+ "learning_rate": 2.655304520118482e-06,
1797
+ "logps_logqs/chosen": 0.07159160077571869,
1798
+ "logqs/chosen": -0.7976843118667603,
1799
+ "logqs/rejected": -0.9096366167068481,
1800
+ "logqs_logps/rejected": 0.08025567978620529,
1801
+ "loss": 0.3097,
1802
+ "step": 1620
1803
+ },
1804
+ {
1805
+ "epoch": 2.616109940816531,
1806
+ "grad_norm": 0.2333984375,
1807
+ "learning_rate": 2.44979483319939e-06,
1808
+ "logps_logqs/chosen": 0.07347805052995682,
1809
+ "logqs/chosen": -0.7938045263290405,
1810
+ "logqs/rejected": -0.890743613243103,
1811
+ "logqs_logps/rejected": 0.08207173645496368,
1812
+ "loss": 0.3107,
1813
+ "step": 1630
1814
+ },
1815
+ {
1816
+ "epoch": 2.6321596950546695,
1817
+ "grad_norm": 0.220703125,
1818
+ "learning_rate": 2.252151720316964e-06,
1819
+ "logps_logqs/chosen": 0.07434280216693878,
1820
+ "logqs/chosen": -0.8010244369506836,
1821
+ "logqs/rejected": -0.8791995048522949,
1822
+ "logqs_logps/rejected": 0.08244656026363373,
1823
+ "loss": 0.3125,
1824
+ "step": 1640
1825
+ },
1826
+ {
1827
+ "epoch": 2.648209449292808,
1828
+ "grad_norm": 0.2236328125,
1829
+ "learning_rate": 2.0624441287011213e-06,
1830
+ "logps_logqs/chosen": 0.07119563221931458,
1831
+ "logqs/chosen": -0.7902050018310547,
1832
+ "logqs/rejected": -0.8934162855148315,
1833
+ "logqs_logps/rejected": 0.08073534816503525,
1834
+ "loss": 0.3096,
1835
+ "step": 1650
1836
+ },
1837
+ {
1838
+ "epoch": 2.664259203530946,
1839
+ "grad_norm": 0.2265625,
1840
+ "learning_rate": 1.8807382372980687e-06,
1841
+ "logps_logqs/chosen": 0.07328217476606369,
1842
+ "logqs/chosen": -0.799074113368988,
1843
+ "logqs/rejected": -0.9103049039840698,
1844
+ "logqs_logps/rejected": 0.08119536936283112,
1845
+ "loss": 0.3127,
1846
+ "step": 1660
1847
+ },
1848
+ {
1849
+ "epoch": 2.680308957769084,
1850
+ "grad_norm": 0.234375,
1851
+ "learning_rate": 1.7070974336839796e-06,
1852
+ "logps_logqs/chosen": 0.07554595172405243,
1853
+ "logqs/chosen": -0.8031436800956726,
1854
+ "logqs/rejected": -0.8931919932365417,
1855
+ "logqs_logps/rejected": 0.08214543014764786,
1856
+ "loss": 0.311,
1857
+ "step": 1670
1858
+ },
1859
+ {
1860
+ "epoch": 2.6963587120072225,
1861
+ "grad_norm": 0.23046875,
1862
+ "learning_rate": 1.541582291952401e-06,
1863
+ "logps_logqs/chosen": 0.07754793018102646,
1864
+ "logqs/chosen": -0.8299878835678101,
1865
+ "logqs/rejected": -0.9271092414855957,
1866
+ "logqs_logps/rejected": 0.08218444138765335,
1867
+ "loss": 0.3161,
1868
+ "step": 1680
1869
+ },
1870
+ {
1871
+ "epoch": 2.7124084662453605,
1872
+ "grad_norm": 0.2236328125,
1873
+ "learning_rate": 1.38425055158318e-06,
1874
+ "logps_logqs/chosen": 0.07421831786632538,
1875
+ "logqs/chosen": -0.811480700969696,
1876
+ "logqs/rejected": -0.9157323837280273,
1877
+ "logqs_logps/rejected": 0.08171753585338593,
1878
+ "loss": 0.3117,
1879
+ "step": 1690
1880
+ },
1881
+ {
1882
+ "epoch": 2.728458220483499,
1883
+ "grad_norm": 0.2255859375,
1884
+ "learning_rate": 1.235157097300188e-06,
1885
+ "logps_logqs/chosen": 0.07626229524612427,
1886
+ "logqs/chosen": -0.8032703399658203,
1887
+ "logqs/rejected": -0.8930376172065735,
1888
+ "logqs_logps/rejected": 0.08358137309551239,
1889
+ "loss": 0.3111,
1890
+ "step": 1700
1891
+ },
1892
+ {
1893
+ "epoch": 2.744507974721637,
1894
+ "grad_norm": 0.2177734375,
1895
+ "learning_rate": 1.0943539399249635e-06,
1896
+ "logps_logqs/chosen": 0.07090778648853302,
1897
+ "logqs/chosen": -0.7999089956283569,
1898
+ "logqs/rejected": -0.8964935541152954,
1899
+ "logqs_logps/rejected": 0.0812908187508583,
1900
+ "loss": 0.3113,
1901
+ "step": 1710
1902
+ },
1903
+ {
1904
+ "epoch": 2.7605577289597756,
1905
+ "grad_norm": 0.2197265625,
1906
+ "learning_rate": 9.618901982328704e-07,
1907
+ "logps_logqs/chosen": 0.07075212895870209,
1908
+ "logqs/chosen": -0.7851020693778992,
1909
+ "logqs/rejected": -0.8868266940116882,
1910
+ "logqs_logps/rejected": 0.08196558058261871,
1911
+ "loss": 0.3124,
1912
+ "step": 1720
1913
+ },
1914
+ {
1915
+ "epoch": 2.7766074831979135,
1916
+ "grad_norm": 0.224609375,
1917
+ "learning_rate": 8.378120818181707e-07,
1918
+ "logps_logqs/chosen": 0.07225438952445984,
1919
+ "logqs/chosen": -0.7922335863113403,
1920
+ "logqs/rejected": -0.8811353445053101,
1921
+ "logqs_logps/rejected": 0.08280298858880997,
1922
+ "loss": 0.3075,
1923
+ "step": 1730
1924
+ },
1925
+ {
1926
+ "epoch": 2.792657237436052,
1927
+ "grad_norm": 0.2236328125,
1928
+ "learning_rate": 7.221628749739223e-07,
1929
+ "logps_logqs/chosen": 0.07148848474025726,
1930
+ "logqs/chosen": -0.7962485551834106,
1931
+ "logqs/rejected": -0.8903713226318359,
1932
+ "logqs_logps/rejected": 0.08183252066373825,
1933
+ "loss": 0.3099,
1934
+ "step": 1740
1935
+ },
1936
+ {
1937
+ "epoch": 2.80870699167419,
1938
+ "grad_norm": 0.232421875,
1939
+ "learning_rate": 6.149829215924025e-07,
1940
+ "logps_logqs/chosen": 0.07041052728891373,
1941
+ "logqs/chosen": -0.7954488396644592,
1942
+ "logqs/rejected": -0.8928369283676147,
1943
+ "logqs_logps/rejected": 0.08137312531471252,
1944
+ "loss": 0.3116,
1945
+ "step": 1750
1946
+ },
1947
+ {
1948
+ "epoch": 2.824756745912328,
1949
+ "grad_norm": 0.22265625,
1950
+ "learning_rate": 5.163096110912368e-07,
1951
+ "logps_logqs/chosen": 0.07447172701358795,
1952
+ "logqs/chosen": -0.819632351398468,
1953
+ "logqs/rejected": -0.9202129244804382,
1954
+ "logqs_logps/rejected": 0.08205995708703995,
1955
+ "loss": 0.3152,
1956
+ "step": 1760
1957
+ },
1958
+ {
1959
+ "epoch": 2.8408065001504665,
1960
+ "grad_norm": 0.2265625,
1961
+ "learning_rate": 4.261773653702089e-07,
1962
+ "logps_logqs/chosen": 0.07548446953296661,
1963
+ "logqs/chosen": -0.819521427154541,
1964
+ "logqs/rejected": -0.9065629243850708,
1965
+ "logqs_logps/rejected": 0.08328162133693695,
1966
+ "loss": 0.3148,
1967
+ "step": 1770
1968
+ },
1969
+ {
1970
+ "epoch": 2.856856254388605,
1971
+ "grad_norm": 0.2236328125,
1972
+ "learning_rate": 3.4461762680329803e-07,
1973
+ "logps_logqs/chosen": 0.07317046076059341,
1974
+ "logqs/chosen": -0.7897886633872986,
1975
+ "logqs/rejected": -0.9044450521469116,
1976
+ "logqs_logps/rejected": 0.08158095180988312,
1977
+ "loss": 0.3104,
1978
+ "step": 1780
1979
+ },
1980
+ {
1981
+ "epoch": 2.872906008626743,
1982
+ "grad_norm": 0.2314453125,
1983
+ "learning_rate": 2.716588472700815e-07,
1984
+ "logps_logqs/chosen": 0.0730937272310257,
1985
+ "logqs/chosen": -0.7850784063339233,
1986
+ "logqs/rejected": -0.9064621925354004,
1987
+ "logqs_logps/rejected": 0.08220399916172028,
1988
+ "loss": 0.3095,
1989
+ "step": 1790
1990
+ },
1991
+ {
1992
+ "epoch": 2.888955762864881,
1993
+ "grad_norm": 0.2275390625,
1994
+ "learning_rate": 2.0732647823038243e-07,
1995
+ "logps_logqs/chosen": 0.07006161659955978,
1996
+ "logqs/chosen": -0.7867298722267151,
1997
+ "logqs/rejected": -0.9106978178024292,
1998
+ "logqs_logps/rejected": 0.08103770762681961,
1999
+ "loss": 0.3086,
2000
+ "step": 1800
2001
+ },
2002
+ {
2003
+ "epoch": 2.905005517103019,
2004
+ "grad_norm": 0.2216796875,
2005
+ "learning_rate": 1.5164296184560222e-07,
2006
+ "logps_logqs/chosen": 0.0730353370308876,
2007
+ "logqs/chosen": -0.784963846206665,
2008
+ "logqs/rejected": -0.895187258720398,
2009
+ "logqs_logps/rejected": 0.08217376470565796,
2010
+ "loss": 0.3121,
2011
+ "step": 1810
2012
+ },
2013
+ {
2014
+ "epoch": 2.9210552713411575,
2015
+ "grad_norm": 0.2333984375,
2016
+ "learning_rate": 1.0462772314983882e-07,
2017
+ "logps_logqs/chosen": 0.07322341203689575,
2018
+ "logqs/chosen": -0.8064349293708801,
2019
+ "logqs/rejected": -0.9101492166519165,
2020
+ "logqs_logps/rejected": 0.08088482171297073,
2021
+ "loss": 0.3163,
2022
+ "step": 1820
2023
+ },
2024
+ {
2025
+ "epoch": 2.937105025579296,
2026
+ "grad_norm": 0.2255859375,
2027
+ "learning_rate": 6.62971632735182e-08,
2028
+ "logps_logqs/chosen": 0.07244640588760376,
2029
+ "logqs/chosen": -0.8047133684158325,
2030
+ "logqs/rejected": -0.9275949597358704,
2031
+ "logqs_logps/rejected": 0.08042384684085846,
2032
+ "loss": 0.3157,
2033
+ "step": 1830
2034
+ },
2035
+ {
2036
+ "epoch": 2.9531547798174342,
2037
+ "grad_norm": 0.2216796875,
2038
+ "learning_rate": 3.666465372190453e-08,
2039
+ "logps_logqs/chosen": 0.07384280860424042,
2040
+ "logqs/chosen": -0.7898183465003967,
2041
+ "logqs/rejected": -0.9135943651199341,
2042
+ "logqs_logps/rejected": 0.08159508556127548,
2043
+ "loss": 0.3114,
2044
+ "step": 1840
2045
+ },
2046
+ {
2047
+ "epoch": 2.969204534055572,
2048
+ "grad_norm": 0.232421875,
2049
+ "learning_rate": 1.57405317104925e-08,
2050
+ "logps_logqs/chosen": 0.07507185637950897,
2051
+ "logqs/chosen": -0.7989250421524048,
2052
+ "logqs/rejected": -0.9065110087394714,
2053
+ "logqs_logps/rejected": 0.08292163163423538,
2054
+ "loss": 0.3158,
2055
+ "step": 1850
2056
+ },
2057
+ {
2058
+ "epoch": 2.9852542882937105,
2059
+ "grad_norm": 0.2265625,
2060
+ "learning_rate": 3.532096558903075e-09,
2061
+ "logps_logqs/chosen": 0.07044342905282974,
2062
+ "logqs/chosen": -0.7936350107192993,
2063
+ "logqs/rejected": -0.9102191925048828,
2064
+ "logqs_logps/rejected": 0.08065608888864517,
2065
+ "loss": 0.3091,
2066
+ "step": 1860
2067
+ },
2068
+ {
2069
+ "epoch": 2.999699067108035,
2070
+ "step": 1869,
2071
+ "total_flos": 0.0,
2072
+ "train_loss": 0.347557685507881,
2073
+ "train_runtime": 42290.5207,
2074
+ "train_samples_per_second": 5.657,
2075
+ "train_steps_per_second": 0.044
2076
+ }
2077
+ ],
2078
+ "logging_steps": 10,
2079
+ "max_steps": 1869,
2080
+ "num_input_tokens_seen": 0,
2081
+ "num_train_epochs": 3,
2082
+ "save_steps": 500,
2083
+ "stateful_callbacks": {
2084
+ "TrainerControl": {
2085
+ "args": {
2086
+ "should_epoch_stop": false,
2087
+ "should_evaluate": false,
2088
+ "should_log": false,
2089
+ "should_save": true,
2090
+ "should_training_stop": true
2091
+ },
2092
+ "attributes": {}
2093
+ }
2094
+ },
2095
+ "total_flos": 0.0,
2096
+ "train_batch_size": 1,
2097
+ "trial_name": null,
2098
+ "trial_params": null
2099
+ }
llama-3.2-3B-it-distillm2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78b07454d6b5f6bc3c6b2f835896f1156e52af7ea02a80bb43990ec5e410f1c
3
+ size 6840
logs/distillm_2_qwen2.5_1.5b_1e.log CHANGED
The diff for this file is too large to render. See raw diff
 
logs/distillm_2_qwen2.5_1.5b_it.log CHANGED
The diff for this file is too large to render. See raw diff
 
logs/llama3.2_3b_it_distillm_2.log CHANGED
@@ -975,4 +975,194 @@ Deprecated positional argument(s) used in DPOTrainer, please use the DPOConfig t
975
 
976
  88%|████████▊ | 1640/1869 [10:18:12<1:26:05, 22.56s/it]
977
  88%|████████▊ | 1641/1869 [10:18:35<1:25:57, 22.62s/it]
978
  88%|████████▊ | 1642/1869 [10:18:58<1:25:19, 22.55s/it]
979
  88%|████████▊ | 1643/1869 [10:19:20<1:25:16, 22.64s/it]
980
  88%|████████▊ | 1644/1869 [10:19:43<1:24:39, 22.57s/it]
981
  88%|████████▊ | 1645/1869 [10:20:06<1:24:26, 22.62s/it]
982
  88%|████████▊ | 1646/1869 [10:20:28<1:24:06, 22.63s/it]
983
  88%|████████▊ | 1647/1869 [10:20:51<1:23:45, 22.64s/it]
984
  88%|████████▊ | 1648/1869 [10:21:13<1:23:23, 22.64s/it]
985
  88%|████████▊ | 1649/1869 [10:21:36<1:23:06, 22.67s/it]
986
  88%|████████▊ | 1650/1869 [10:21:59<1:22:34, 22.62s/it]
987
 
988
 
989
  88%|████████▊ | 1650/1869 [10:21:59<1:22:34, 22.62s/it]
990
  88%|████████▊ | 1651/1869 [10:22:22<1:22:29, 22.70s/it]
991
  88%|████████▊ | 1652/1869 [10:22:44<1:22:15, 22.74s/it]
992
  88%|████████▊ | 1653/1869 [10:23:07<1:22:05, 22.80s/it]
993
  88%|████████▊ | 1654/1869 [10:23:30<1:21:42, 22.80s/it]
994
  89%|████████▊ | 1655/1869 [10:23:53<1:21:11, 22.76s/it]
995
  89%|████████▊ | 1656/1869 [10:24:15<1:20:33, 22.69s/it]
996
  89%|████████▊ | 1657/1869 [10:24:38<1:19:51, 22.60s/it]
997
  89%|████████▊ | 1658/1869 [10:25:01<1:19:36, 22.64s/it]
998
  89%|████████▉ | 1659/1869 [10:25:23<1:19:06, 22.60s/it]
999
  89%|████████▉ | 1660/1869 [10:25:46<1:18:38, 22.58s/it]
1000
 
1001
 
1002
  89%|████████▉ | 1660/1869 [10:25:46<1:18:38, 22.58s/it]
1003
  89%|████████▉ | 1661/1869 [10:26:08<1:18:16, 22.58s/it]
1004
  89%|████████▉ | 1662/1869 [10:26:30<1:17:33, 22.48s/it]
1005
  89%|████████▉ | 1663/1869 [10:26:53<1:17:09, 22.47s/it]
1006
  89%|████████▉ | 1664/1869 [10:27:15<1:16:46, 22.47s/it]
1007
  89%|████████▉ | 1665/1869 [10:27:38<1:16:10, 22.40s/it]
1008
  89%|████████▉ | 1666/1869 [10:28:00<1:15:23, 22.28s/it]
1009
  89%|████████▉ | 1667/1869 [10:28:23<1:15:51, 22.53s/it]
1010
  89%|████████▉ | 1668/1869 [10:28:46<1:16:10, 22.74s/it]
1011
  89%|████████▉ | 1669/1869 [10:29:09<1:16:09, 22.85s/it]
1012
  89%|████████▉ | 1670/1869 [10:29:32<1:16:00, 22.92s/it]
1013
 
1014
-
1015
  89%|████████▉ | 1670/1869 [10:29:32<1:16:00, 22.92s/it]
 
1016
  89%|████████▉ | 1670/1869 [10:29:32<1:16:00, 22.92s/it]
1017
  89%|████████▉ | 1671/1869 [10:29:55<1:15:22, 22.84s/it]
1018
  89%|████████▉ | 1672/1869 [10:30:17<1:14:45, 22.77s/it]
1019
  90%|████████▉ | 1673/1869 [10:30:40<1:14:16, 22.74s/it]
1020
  90%|████████▉ | 1674/1869 [10:31:03<1:13:57, 22.76s/it]
1021
  90%|████████▉ | 1675/1869 [10:31:26<1:13:39, 22.78s/it]
1022
  90%|████████▉ | 1676/1869 [10:31:48<1:13:14, 22.77s/it]
1023
  90%|████████▉ | 1677/1869 [10:32:11<1:13:10, 22.87s/it]
1024
  90%|████████▉ | 1678/1869 [10:32:35<1:13:03, 22.95s/it]
1025
  90%|████████▉ | 1679/1869 [10:32:57<1:12:30, 22.90s/it]
1026
  90%|████████▉ | 1680/1869 [10:33:20<1:12:01, 22.86s/it]
1027
 
 
1028
  90%|████████▉ | 1680/1869 [10:33:20<1:12:01, 22.86s/it]
1029
  90%|████████▉ | 1681/1869 [10:33:43<1:11:42, 22.89s/it]
1030
  90%|████████▉ | 1682/1869 [10:34:06<1:11:02, 22.79s/it]
1031
  90%|█████████ | 1683/1869 [10:34:29<1:10:46, 22.83s/it]
1032
  90%|████████�� | 1684/1869 [10:34:51<1:10:09, 22.75s/it]
1033
  90%|█████████ | 1685/1869 [10:35:14<1:09:56, 22.81s/it]
1034
  90%|█████████ | 1686/1869 [10:35:37<1:09:20, 22.73s/it]
1035
  90%|█████████ | 1687/1869 [10:35:59<1:08:44, 22.66s/it]
1036
  90%|█████████ | 1688/1869 [10:36:22<1:08:15, 22.63s/it]
1037
  90%|█████████ | 1689/1869 [10:36:45<1:08:29, 22.83s/it]
1038
  90%|█████████ | 1690/1869 [10:37:08<1:08:23, 22.92s/it]
1039
 
 
1040
  90%|█████████ | 1690/1869 [10:37:08<1:08:23, 22.92s/it]
1041
  90%|█████████ | 1691/1869 [10:37:31<1:08:09, 22.97s/it]
1042
  91%|█████████ | 1692/1869 [10:37:55<1:08:06, 23.09s/it]
1043
  91%|█████████ | 1693/1869 [10:38:17<1:07:00, 22.85s/it]
1044
  91%|█████████ | 1694/1869 [10:38:39<1:06:02, 22.64s/it]
1045
  91%|█████████ | 1695/1869 [10:39:01<1:05:28, 22.58s/it]
1046
  91%|█████████ | 1696/1869 [10:39:23<1:04:35, 22.40s/it]
1047
  91%|█████████ | 1697/1869 [10:39:46<1:04:06, 22.36s/it]
1048
  91%|█████████ | 1698/1869 [10:40:08<1:03:20, 22.23s/it]
1049
  91%|█████████ | 1699/1869 [10:40:30<1:02:45, 22.15s/it]
1050
  91%|█████████ | 1700/1869 [10:40:52<1:02:40, 22.25s/it]
1051
 
 
1052
  91%|█████████ | 1700/1869 [10:40:52<1:02:40, 22.25s/it]
1053
  91%|█████████ | 1701/1869 [10:41:14<1:02:16, 22.24s/it]
1054
  91%|█████████ | 1702/1869 [10:41:37<1:01:53, 22.24s/it]
1055
  91%|█████████ | 1703/1869 [10:41:59<1:01:45, 22.32s/it]
1056
  91%|█████████ | 1704/1869 [10:42:22<1:01:42, 22.44s/it]
1057
  91%|█████████ | 1705/1869 [10:42:45<1:01:35, 22.53s/it]
1058
  91%|█████████▏| 1706/1869 [10:43:07<1:01:16, 22.56s/it]
1059
  91%|█████████▏| 1707/1869 [10:43:30<1:01:17, 22.70s/it]
1060
  91%|█████████▏| 1708/1869 [10:43:53<1:00:52, 22.68s/it]
1061
  91%|█████████▏| 1709/1869 [10:44:15<1:00:13, 22.58s/it]
1062
  91%|█████████▏| 1710/1869 [10:44:37<59:33, 22.47s/it]
1063
 
 
1064
  91%|█████████▏| 1710/1869 [10:44:37<59:33, 22.47s/it]
1065
  92%|█████████▏| 1711/1869 [10:45:00<59:26, 22.57s/it]
1066
  92%|█████████▏| 1712/1869 [10:45:23<59:29, 22.73s/it]
1067
  92%|█████████▏| 1713/1869 [10:45:46<59:06, 22.74s/it]
1068
  92%|█████████▏| 1714/1869 [10:46:09<58:39, 22.71s/it]
1069
  92%|█████████▏| 1715/1869 [10:46:32<58:23, 22.75s/it]
1070
  92%|█████████▏| 1716/1869 [10:46:55<58:15, 22.85s/it]
1071
  92%|█████████▏| 1717/1869 [10:47:17<57:41, 22.77s/it]
1072
  92%|█████████▏| 1718/1869 [10:47:40<57:03, 22.67s/it]
1073
  92%|█████████▏| 1719/1869 [10:48:03<56:48, 22.72s/it]
1074
  92%|█████████▏| 1720/1869 [10:48:25<56:22, 22.70s/it]
1075
 
 
1076
  92%|█████████▏| 1720/1869 [10:48:25<56:22, 22.70s/it]
1077
  92%|█████████▏| 1721/1869 [10:48:48<56:14, 22.80s/it]
1078
  92%|█████████▏| 1722/1869 [10:49:11<55:45, 22.76s/it]
1079
  92%|█████████▏| 1723/1869 [10:49:34<55:39, 22.88s/it]
1080
  92%|█████████▏| 1724/1869 [10:49:57<55:14, 22.86s/it]
1081
  92%|█████████▏| 1725/1869 [10:50:19<54:36, 22.75s/it]
1082
  92%|█████████▏| 1726/1869 [10:50:41<53:40, 22.52s/it]
1083
  92%|█████████▏| 1727/1869 [10:51:03<53:00, 22.40s/it]
1084
  92%|█████████▏| 1728/1869 [10:51:26<52:40, 22.42s/it]
1085
  93%|█████████▎| 1729/1869 [10:51:48<52:07, 22.34s/it]
1086
  93%|█████████▎| 1730/1869 [10:52:10<51:35, 22.27s/it]
1087
 
 
1088
  93%|█████████▎| 1730/1869 [10:52:10<51:35, 22.27s/it]
1089
  93%|█████████▎| 1731/1869 [10:52:32<51:08, 22.23s/it]
1090
  93%|█████████▎| 1732/1869 [10:52:55<51:12, 22.43s/it]
1091
  93%|█████████▎| 1733/1869 [10:53:18<51:06, 22.55s/it]
1092
  93%|█████████▎| 1734/1869 [10:53:41<51:01, 22.68s/it]
1093
  93%|█████████▎| 1735/1869 [10:54:04<50:46, 22.73s/it]
1094
  93%|█████████▎| 1736/1869 [10:54:27<50:39, 22.86s/it]
1095
  93%|█████████▎| 1737/1869 [10:54:50<50:18, 22.87s/it]
1096
  93%|█████████▎| 1738/1869 [10:55:13<49:53, 22.85s/it]
1097
  93%|█████████▎| 1739/1869 [10:55:36<49:33, 22.88s/it]
1098
  93%|█████████▎| 1740/1869 [10:55:58<49:05, 22.83s/it]
1099
 
 
1100
  93%|█████████▎| 1740/1869 [10:55:58<49:05, 22.83s/it]
1101
  93%|█████████▎| 1741/1869 [10:56:21<48:45, 22.86s/it]
1102
  93%|█████████▎| 1742/1869 [10:56:44<48:17, 22.81s/it]
1103
  93%|█████████▎| 1743/1869 [10:57:07<47:58, 22.85s/it]
1104
  93%|█████████▎| 1744/1869 [10:57:30<47:35, 22.84s/it]
1105
  93%|█████████▎| 1745/1869 [10:57:52<47:02, 22.76s/it]
1106
  93%|█████████▎| 1746/1869 [10:58:15<46:46, 22.82s/it]
1107
  93%|█████████▎| 1747/1869 [10:58:38<46:14, 22.74s/it]
1108
  94%|█████████▎| 1748/1869 [10:59:01<45:54, 22.76s/it]
1109
  94%|█████████▎| 1749/1869 [10:59:23<45:28, 22.73s/it]
1110
  94%|█████████▎| 1750/1869 [10:59:46<45:11, 22.79s/it]
1111
 
 
1112
  94%|█████████▎| 1750/1869 [10:59:46<45:11, 22.79s/it]
1113
  94%|█████████▎| 1751/1869 [11:00:09<44:48, 22.78s/it]
1114
  94%|█████████▎| 1752/1869 [11:00:32<44:16, 22.71s/it]
1115
  94%|█████████▍| 1753/1869 [11:00:55<44:07, 22.82s/it]
1116
  94%|█████████▍| 1754/1869 [11:01:17<43:43, 22.81s/it]
1117
  94%|█████████▍| 1755/1869 [11:01:40<43:22, 22.82s/it]
1118
  94%|█████████▍| 1756/1869 [11:02:03<42:46, 22.71s/it]
1119
  94%|█████████▍| 1757/1869 [11:02:25<42:22, 22.70s/it]
1120
  94%|█████████▍| 1758/1869 [11:02:48<41:59, 22.70s/it]
1121
  94%|█████████▍| 1759/1869 [11:03:11<41:51, 22.83s/it]
1122
  94%|█████████▍| 1760/1869 [11:03:34<41:20, 22.75s/it]
1123
 
 
1124
  94%|█████████▍| 1760/1869 [11:03:34<41:20, 22.75s/it]
1125
  94%|█████████▍| 1761/1869 [11:03:57<40:58, 22.76s/it]
1126
  94%|█████████▍| 1762/1869 [11:04:20<40:41, 22.82s/it]
1127
  94%|█████████▍| 1763/1869 [11:04:43<40:32, 22.95s/it]
1128
  94%|█████████▍| 1764/1869 [11:05:06<40:04, 22.90s/it]
1129
  94%|█████████▍| 1765/1869 [11:05:28<39:40, 22.89s/it]
1130
  94%|█████████▍| 1766/1869 [11:05:51<39:12, 22.84s/it]
1131
  95%|█████████▍| 1767/1869 [11:06:14<38:42, 22.77s/it]
1132
  95%|█████████▍| 1768/1869 [11:06:36<38:15, 22.72s/it]
1133
  95%|█████████▍| 1769/1869 [11:06:59<37:54, 22.74s/it]
1134
  95%|█████████▍| 1770/1869 [11:07:22<37:30, 22.74s/it]
1135
 
 
1136
  95%|█████████▍| 1770/1869 [11:07:22<37:30, 22.74s/it]
1137
  95%|█████████▍| 1771/1869 [11:07:45<37:18, 22.84s/it]
1138
  95%|█████████▍| 1772/1869 [11:08:08<36:53, 22.82s/it]
1139
  95%|█████████▍| 1773/1869 [11:08:31<36:38, 22.90s/it]
1140
  95%|█████████▍| 1774/1869 [11:08:54<36:22, 22.97s/it]
1141
  95%|█████████▍| 1775/1869 [11:09:17<35:55, 22.93s/it]
1142
  95%|█████████▌| 1776/1869 [11:09:40<35:31, 22.92s/it]
1143
  95%|█████████▌| 1777/1869 [11:10:02<34:57, 22.80s/it]
1144
  95%|█████████▌| 1778/1869 [11:10:25<34:24, 22.69s/it]
1145
  95%|█████████▌| 1779/1869 [11:10:47<34:03, 22.71s/it]
1146
  95%|█████████▌| 1780/1869 [11:11:10<33:37, 22.66s/it]
1147
 
 
1148
  95%|█████████▌| 1780/1869 [11:11:10<33:37, 22.66s/it]
1149
  95%|█████████▌| 1781/1869 [11:11:33<33:13, 22.65s/it]
1150
  95%|█████████▌| 1782/1869 [11:11:55<32:46, 22.60s/it]
1151
  95%|█████████▌| 1783/1869 [11:12:18<32:21, 22.58s/it]
1152
  95%|█████████▌| 1784/1869 [11:12:40<32:03, 22.63s/it]
1153
  96%|█████████▌| 1785/1869 [11:13:03<31:44, 22.68s/it]
1154
  96%|█████████▌| 1786/1869 [11:13:26<31:16, 22.61s/it]
1155
  96%|█████████▌| 1787/1869 [11:13:49<31:03, 22.73s/it]
1156
  96%|█████████▌| 1788/1869 [11:14:12<30:55, 22.91s/it]
1157
  96%|█████████▌| 1789/1869 [11:14:35<30:40, 23.00s/it]
1158
  96%|█████████▌| 1790/1869 [11:14:58<30:06, 22.87s/it]
1159
 
 
1160
  96%|█████████▌| 1790/1869 [11:14:58<30:06, 22.87s/it]
1161
  96%|█████████▌| 1791/1869 [11:15:20<29:34, 22.75s/it]
1162
  96%|█████████▌| 1792/1869 [11:15:43<29:10, 22.73s/it]
1163
  96%|█████████▌| 1793/1869 [11:16:06<28:53, 22.81s/it]
1164
  96%|█████████▌| 1794/1869 [11:16:29<28:30, 22.81s/it]
1165
  96%|█████████▌| 1795/1869 [11:16:51<28:07, 22.80s/it]
1166
  96%|█████████▌| 1796/1869 [11:17:14<27:47, 22.84s/it]
1167
  96%|█████████▌| 1797/1869 [11:17:37<27:21, 22.79s/it]
1168
  96%|█████████▌| 1798/1869 [11:18:00<26:53, 22.73s/it]
1169
  96%|█████████▋| 1799/1869 [11:18:22<26:30, 22.73s/it]
1170
  96%|█████████▋| 1800/1869 [11:18:45<26:09, 22.74s/it]
1171
 
 
1172
  96%|█████████▋| 1800/1869 [11:18:45<26:09, 22.74s/it]
1173
  96%|█████████▋| 1801/1869 [11:19:08<25:48, 22.77s/it]
1174
  96%|█████████▋| 1802/1869 [11:19:31<25:28, 22.82s/it]
1175
  96%|█████████▋| 1803/1869 [11:19:54<25:14, 22.95s/it]
1176
  97%|█████████▋| 1804/1869 [11:20:17<24:45, 22.85s/it]
1177
  97%|█████████▋| 1805/1869 [11:20:39<24:11, 22.69s/it]
1178
  97%|█████████▋| 1806/1869 [11:21:02<23:47, 22.66s/it]
1179
  97%|█████████▋| 1807/1869 [11:21:25<23:30, 22.75s/it]
1180
  97%|█████████▋| 1808/1869 [11:21:47<23:08, 22.76s/it]
1181
  97%|█████████▋| 1809/1869 [11:22:10<22:43, 22.73s/it]
1182
  97%|█████████▋| 1810/1869 [11:22:33<22:21, 22.73s/it]
1183
 
 
1184
  97%|█████████▋| 1810/1869 [11:22:33<22:21, 22.73s/it]
1185
  97%|█████████▋| 1811/1869 [11:22:55<21:53, 22.64s/it]
1186
  97%|█████████▋| 1812/1869 [11:23:18<21:31, 22.66s/it]
1187
  97%|█████████▋| 1813/1869 [11:23:41<21:09, 22.66s/it]
1188
  97%|█████████▋| 1814/1869 [11:24:03<20:43, 22.61s/it]
1189
  97%|█████████▋| 1815/1869 [11:24:26<20:22, 22.64s/it]
1190
  97%|█████████▋| 1816/1869 [11:24:49<20:01, 22.66s/it]
1191
  97%|█████████▋| 1817/1869 [11:25:11<19:35, 22.61s/it]
1192
  97%|█████████▋| 1818/1869 [11:25:33<19:08, 22.52s/it]
1193
  97%|█████████▋| 1819/1869 [11:25:56<18:44, 22.50s/it]
1194
  97%|█████████▋| 1820/1869 [11:26:18<18:23, 22.51s/it]
1195
 
 
1196
  97%|█████████▋| 1820/1869 [11:26:18<18:23, 22.51s/it]
1197
  97%|█████████▋| 1821/1869 [11:26:41<17:58, 22.48s/it]
1198
  97%|█████████▋| 1822/1869 [11:27:03<17:29, 22.34s/it]
1199
  98%|█████████▊| 1823/1869 [11:27:25<17:08, 22.36s/it]
1200
  98%|█████████▊| 1824/1869 [11:27:48<16:46, 22.37s/it]
1201
  98%|█████████▊| 1825/1869 [11:28:10<16:21, 22.30s/it]
1202
  98%|█████████▊| 1826/1869 [11:28:32<15:57, 22.28s/it]
1203
  98%|█████████▊| 1827/1869 [11:28:55<15:40, 22.40s/it]
1204
  98%|█████████▊| 1828/1869 [11:29:17<15:18, 22.40s/it]
1205
  98%|█████████▊| 1829/1869 [11:29:39<14:53, 22.35s/it]
1206
  98%|█████████▊| 1830/1869 [11:30:01<14:30, 22.33s/it]
1207
 
 
1208
  98%|█████████▊| 1830/1869 [11:30:01<14:30, 22.33s/it]
1209
  98%|█████████▊| 1831/1869 [11:30:24<14:14, 22.48s/it]
1210
  98%|█████████▊| 1832/1869 [11:30:47<13:53, 22.54s/it]
1211
  98%|█████████▊| 1833/1869 [11:31:10<13:34, 22.61s/it]
1212
  98%|█████████▊| 1834/1869 [11:31:32<13:11, 22.62s/it]
1213
  98%|█████████▊| 1835/1869 [11:31:55<12:49, 22.62s/it]
1214
  98%|█████████▊| 1836/1869 [11:32:18<12:25, 22.58s/it]
1215
  98%|█████████▊| 1837/1869 [11:32:40<12:06, 22.70s/it]
1216
  98%|█████████▊| 1838/1869 [11:33:03<11:45, 22.75s/it]
1217
  98%|█████████▊| 1839/1869 [11:33:26<11:25, 22.85s/it]
1218
  98%|█████████▊| 1840/1869 [11:33:50<11:05, 22.96s/it]
1219
 
 
1220
  98%|█████████▊| 1840/1869 [11:33:50<11:05, 22.96s/it]
1221
  99%|█████████▊| 1841/1869 [11:34:12<10:40, 22.89s/it]
1222
  99%|█████████▊| 1842/1869 [11:34:35<10:14, 22.74s/it]
1223
  99%|█████████▊| 1843/1869 [11:34:58<09:51, 22.76s/it]
1224
  99%|█████████▊| 1844/1869 [11:35:21<09:31, 22.84s/it]
1225
  99%|█████████▊| 1845/1869 [11:35:43<09:07, 22.83s/it]
1226
  99%|█████████▉| 1846/1869 [11:36:06<08:46, 22.88s/it]
1227
  99%|█████████▉| 1847/1869 [11:36:29<08:23, 22.87s/it]
1228
  99%|█████████▉| 1848/1869 [11:36:52<08:01, 22.91s/it]
1229
  99%|█████████▉| 1849/1869 [11:37:15<07:38, 22.92s/it]
1230
  99%|█████████▉| 1850/1869 [11:37:38<07:15, 22.93s/it]
1231
 
 
1232
  99%|█████████▉| 1850/1869 [11:37:38<07:15, 22.93s/it]
1233
  99%|█████████▉| 1851/1869 [11:38:01<06:53, 22.97s/it]
1234
  99%|█████████▉| 1852/1869 [11:38:24<06:30, 22.94s/it]
1235
  99%|█████████▉| 1853/1869 [11:38:47<06:06, 22.90s/it]
1236
  99%|█████████▉| 1854/1869 [11:39:10<05:43, 22.90s/it]
1237
  99%|█████████▉| 1855/1869 [11:39:33<05:20, 22.88s/it]
1238
  99%|█████████▉| 1856/1869 [11:39:56<04:57, 22.90s/it]
1239
  99%|█████████▉| 1857/1869 [11:40:19<04:35, 22.95s/it]
1240
  99%|█████████▉| 1858/1869 [11:40:42<04:12, 22.95s/it]
1241
  99%|█████████▉| 1859/1869 [11:41:05<03:49, 22.97s/it]
1242
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1243
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1244
  0%| | 0/3 [00:00<?, ?it/s]
1245
  67%|██████▋ | 2/3 [00:00<00:00, 5.96it/s]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
975
 
976
  88%|████████▊ | 1640/1869 [10:18:12<1:26:05, 22.56s/it]
977
  88%|████████▊ | 1641/1869 [10:18:35<1:25:57, 22.62s/it]
978
  88%|████████▊ | 1642/1869 [10:18:58<1:25:19, 22.55s/it]
979
  88%|████████▊ | 1643/1869 [10:19:20<1:25:16, 22.64s/it]
980
  88%|████████▊ | 1644/1869 [10:19:43<1:24:39, 22.57s/it]
981
  88%|████████▊ | 1645/1869 [10:20:06<1:24:26, 22.62s/it]
982
  88%|████████▊ | 1646/1869 [10:20:28<1:24:06, 22.63s/it]
983
  88%|████████▊ | 1647/1869 [10:20:51<1:23:45, 22.64s/it]
984
  88%|████████▊ | 1648/1869 [10:21:13<1:23:23, 22.64s/it]
985
  88%|████████▊ | 1649/1869 [10:21:36<1:23:06, 22.67s/it]
986
  88%|████████▊ | 1650/1869 [10:21:59<1:22:34, 22.62s/it]
987
 
988
 
989
  88%|████████▊ | 1650/1869 [10:21:59<1:22:34, 22.62s/it]
990
  88%|████████▊ | 1651/1869 [10:22:22<1:22:29, 22.70s/it]
991
  88%|████████▊ | 1652/1869 [10:22:44<1:22:15, 22.74s/it]
992
  88%|████████▊ | 1653/1869 [10:23:07<1:22:05, 22.80s/it]
993
  88%|████████▊ | 1654/1869 [10:23:30<1:21:42, 22.80s/it]
994
  89%|████████▊ | 1655/1869 [10:23:53<1:21:11, 22.76s/it]
995
  89%|████████▊ | 1656/1869 [10:24:15<1:20:33, 22.69s/it]
996
  89%|████████▊ | 1657/1869 [10:24:38<1:19:51, 22.60s/it]
997
  89%|████████▊ | 1658/1869 [10:25:01<1:19:36, 22.64s/it]
998
  89%|████████▉ | 1659/1869 [10:25:23<1:19:06, 22.60s/it]
999
  89%|████████▉ | 1660/1869 [10:25:46<1:18:38, 22.58s/it]
1000
 
1001
 
1002
  89%|████████▉ | 1660/1869 [10:25:46<1:18:38, 22.58s/it]
1003
  89%|████████▉ | 1661/1869 [10:26:08<1:18:16, 22.58s/it]
1004
  89%|████████▉ | 1662/1869 [10:26:30<1:17:33, 22.48s/it]
1005
  89%|████████▉ | 1663/1869 [10:26:53<1:17:09, 22.47s/it]
1006
  89%|████████▉ | 1664/1869 [10:27:15<1:16:46, 22.47s/it]
1007
  89%|████████▉ | 1665/1869 [10:27:38<1:16:10, 22.40s/it]
1008
  89%|████████▉ | 1666/1869 [10:28:00<1:15:23, 22.28s/it]
1009
  89%|████████▉ | 1667/1869 [10:28:23<1:15:51, 22.53s/it]
1010
  89%|████████▉ | 1668/1869 [10:28:46<1:16:10, 22.74s/it]
1011
  89%|████████▉ | 1669/1869 [10:29:09<1:16:09, 22.85s/it]
1012
  89%|████████▉ | 1670/1869 [10:29:32<1:16:00, 22.92s/it]
1013
 
 
1014
  89%|████████▉ | 1670/1869 [10:29:32<1:16:00, 22.92s/it]
1015
+
1016
  89%|████████▉ | 1670/1869 [10:29:32<1:16:00, 22.92s/it]
1017
  89%|████████▉ | 1671/1869 [10:29:55<1:15:22, 22.84s/it]
1018
  89%|████████▉ | 1672/1869 [10:30:17<1:14:45, 22.77s/it]
1019
  90%|████████▉ | 1673/1869 [10:30:40<1:14:16, 22.74s/it]
1020
  90%|████████▉ | 1674/1869 [10:31:03<1:13:57, 22.76s/it]
1021
  90%|████████▉ | 1675/1869 [10:31:26<1:13:39, 22.78s/it]
1022
  90%|████████▉ | 1676/1869 [10:31:48<1:13:14, 22.77s/it]
1023
  90%|████████▉ | 1677/1869 [10:32:11<1:13:10, 22.87s/it]
1024
  90%|████████▉ | 1678/1869 [10:32:35<1:13:03, 22.95s/it]
1025
  90%|████████▉ | 1679/1869 [10:32:57<1:12:30, 22.90s/it]
1026
  90%|████████▉ | 1680/1869 [10:33:20<1:12:01, 22.86s/it]
1027
 
1028
+
1029
  90%|████████▉ | 1680/1869 [10:33:20<1:12:01, 22.86s/it]
1030
  90%|████████▉ | 1681/1869 [10:33:43<1:11:42, 22.89s/it]
1031
  90%|████████▉ | 1682/1869 [10:34:06<1:11:02, 22.79s/it]
1032
  90%|█████████ | 1683/1869 [10:34:29<1:10:46, 22.83s/it]
1033
  90%|████████�� | 1684/1869 [10:34:51<1:10:09, 22.75s/it]
1034
  90%|█████████ | 1685/1869 [10:35:14<1:09:56, 22.81s/it]
1035
  90%|█████████ | 1686/1869 [10:35:37<1:09:20, 22.73s/it]
1036
  90%|█████████ | 1687/1869 [10:35:59<1:08:44, 22.66s/it]
1037
  90%|█████████ | 1688/1869 [10:36:22<1:08:15, 22.63s/it]
1038
  90%|█████████ | 1689/1869 [10:36:45<1:08:29, 22.83s/it]
1039
  90%|█████████ | 1690/1869 [10:37:08<1:08:23, 22.92s/it]
1040
 
1041
+
1042
  90%|█████████ | 1690/1869 [10:37:08<1:08:23, 22.92s/it]
1043
  90%|█████████ | 1691/1869 [10:37:31<1:08:09, 22.97s/it]
1044
  91%|█████████ | 1692/1869 [10:37:55<1:08:06, 23.09s/it]
1045
  91%|█████████ | 1693/1869 [10:38:17<1:07:00, 22.85s/it]
1046
  91%|█████████ | 1694/1869 [10:38:39<1:06:02, 22.64s/it]
1047
  91%|█████████ | 1695/1869 [10:39:01<1:05:28, 22.58s/it]
1048
  91%|█████████ | 1696/1869 [10:39:23<1:04:35, 22.40s/it]
1049
  91%|█████████ | 1697/1869 [10:39:46<1:04:06, 22.36s/it]
1050
  91%|█████████ | 1698/1869 [10:40:08<1:03:20, 22.23s/it]
1051
  91%|█████████ | 1699/1869 [10:40:30<1:02:45, 22.15s/it]
1052
  91%|█████████ | 1700/1869 [10:40:52<1:02:40, 22.25s/it]
1053
 
1054
+
1055
  91%|█████████ | 1700/1869 [10:40:52<1:02:40, 22.25s/it]
1056
  91%|█████████ | 1701/1869 [10:41:14<1:02:16, 22.24s/it]
1057
  91%|█████████ | 1702/1869 [10:41:37<1:01:53, 22.24s/it]
1058
  91%|█████████ | 1703/1869 [10:41:59<1:01:45, 22.32s/it]
1059
  91%|█████████ | 1704/1869 [10:42:22<1:01:42, 22.44s/it]
1060
  91%|█████████ | 1705/1869 [10:42:45<1:01:35, 22.53s/it]
1061
  91%|█████████▏| 1706/1869 [10:43:07<1:01:16, 22.56s/it]
1062
  91%|█████████▏| 1707/1869 [10:43:30<1:01:17, 22.70s/it]
1063
  91%|█████████▏| 1708/1869 [10:43:53<1:00:52, 22.68s/it]
1064
  91%|█████████▏| 1709/1869 [10:44:15<1:00:13, 22.58s/it]
1065
  91%|█████████▏| 1710/1869 [10:44:37<59:33, 22.47s/it]
1066
 
1067
+
1068
  91%|█████████▏| 1710/1869 [10:44:37<59:33, 22.47s/it]
1069
  92%|█████████▏| 1711/1869 [10:45:00<59:26, 22.57s/it]
1070
  92%|█████████▏| 1712/1869 [10:45:23<59:29, 22.73s/it]
1071
  92%|█████████▏| 1713/1869 [10:45:46<59:06, 22.74s/it]
1072
  92%|█████████▏| 1714/1869 [10:46:09<58:39, 22.71s/it]
1073
  92%|█████████▏| 1715/1869 [10:46:32<58:23, 22.75s/it]
1074
  92%|█████████▏| 1716/1869 [10:46:55<58:15, 22.85s/it]
1075
  92%|█████████▏| 1717/1869 [10:47:17<57:41, 22.77s/it]
1076
  92%|█████████▏| 1718/1869 [10:47:40<57:03, 22.67s/it]
1077
  92%|█████████▏| 1719/1869 [10:48:03<56:48, 22.72s/it]
1078
  92%|█████████▏| 1720/1869 [10:48:25<56:22, 22.70s/it]
1079
 
1080
+
1081
  92%|█████████▏| 1720/1869 [10:48:25<56:22, 22.70s/it]
1082
  92%|█████████▏| 1721/1869 [10:48:48<56:14, 22.80s/it]
1083
  92%|█████████▏| 1722/1869 [10:49:11<55:45, 22.76s/it]
1084
  92%|█████████▏| 1723/1869 [10:49:34<55:39, 22.88s/it]
1085
  92%|█████████▏| 1724/1869 [10:49:57<55:14, 22.86s/it]
1086
  92%|█████████▏| 1725/1869 [10:50:19<54:36, 22.75s/it]
1087
  92%|█████████▏| 1726/1869 [10:50:41<53:40, 22.52s/it]
1088
  92%|█████████▏| 1727/1869 [10:51:03<53:00, 22.40s/it]
1089
  92%|█████████▏| 1728/1869 [10:51:26<52:40, 22.42s/it]
1090
  93%|█████████▎| 1729/1869 [10:51:48<52:07, 22.34s/it]
1091
  93%|█████████▎| 1730/1869 [10:52:10<51:35, 22.27s/it]
1092
 
1093
+
1094
  93%|█████████▎| 1730/1869 [10:52:10<51:35, 22.27s/it]
1095
  93%|█████████▎| 1731/1869 [10:52:32<51:08, 22.23s/it]
1096
  93%|█████████▎| 1732/1869 [10:52:55<51:12, 22.43s/it]
1097
  93%|█████████▎| 1733/1869 [10:53:18<51:06, 22.55s/it]
1098
  93%|█████████▎| 1734/1869 [10:53:41<51:01, 22.68s/it]
1099
  93%|█████████▎| 1735/1869 [10:54:04<50:46, 22.73s/it]
1100
  93%|█████████▎| 1736/1869 [10:54:27<50:39, 22.86s/it]
1101
  93%|█████████▎| 1737/1869 [10:54:50<50:18, 22.87s/it]
1102
  93%|█████████▎| 1738/1869 [10:55:13<49:53, 22.85s/it]
1103
  93%|█████████▎| 1739/1869 [10:55:36<49:33, 22.88s/it]
1104
  93%|█████████▎| 1740/1869 [10:55:58<49:05, 22.83s/it]
1105
 
1106
+
1107
  93%|█████████▎| 1740/1869 [10:55:58<49:05, 22.83s/it]
1108
  93%|█████████▎| 1741/1869 [10:56:21<48:45, 22.86s/it]
1109
  93%|█████████▎| 1742/1869 [10:56:44<48:17, 22.81s/it]
1110
  93%|█████████▎| 1743/1869 [10:57:07<47:58, 22.85s/it]
1111
  93%|█████████▎| 1744/1869 [10:57:30<47:35, 22.84s/it]
1112
  93%|█████████▎| 1745/1869 [10:57:52<47:02, 22.76s/it]
1113
  93%|█████████▎| 1746/1869 [10:58:15<46:46, 22.82s/it]
1114
  93%|█████████▎| 1747/1869 [10:58:38<46:14, 22.74s/it]
1115
  94%|█████████▎| 1748/1869 [10:59:01<45:54, 22.76s/it]
1116
  94%|█████████▎| 1749/1869 [10:59:23<45:28, 22.73s/it]
1117
  94%|█████████▎| 1750/1869 [10:59:46<45:11, 22.79s/it]
1118
 
1119
+
1120
  94%|█████████▎| 1750/1869 [10:59:46<45:11, 22.79s/it]
1121
  94%|█████████▎| 1751/1869 [11:00:09<44:48, 22.78s/it]
1122
  94%|█████████▎| 1752/1869 [11:00:32<44:16, 22.71s/it]
1123
  94%|█████████▍| 1753/1869 [11:00:55<44:07, 22.82s/it]
1124
  94%|█████████▍| 1754/1869 [11:01:17<43:43, 22.81s/it]
1125
  94%|█████████▍| 1755/1869 [11:01:40<43:22, 22.82s/it]
1126
  94%|█████████▍| 1756/1869 [11:02:03<42:46, 22.71s/it]
1127
  94%|█████████▍| 1757/1869 [11:02:25<42:22, 22.70s/it]
1128
  94%|█████████▍| 1758/1869 [11:02:48<41:59, 22.70s/it]
1129
  94%|█████████▍| 1759/1869 [11:03:11<41:51, 22.83s/it]
1130
  94%|█████████▍| 1760/1869 [11:03:34<41:20, 22.75s/it]
1131
 
1132
+
1133
  94%|█████████▍| 1760/1869 [11:03:34<41:20, 22.75s/it]
1134
  94%|█████████▍| 1761/1869 [11:03:57<40:58, 22.76s/it]
1135
  94%|█████████▍| 1762/1869 [11:04:20<40:41, 22.82s/it]
1136
  94%|█████████▍| 1763/1869 [11:04:43<40:32, 22.95s/it]
1137
  94%|█████████▍| 1764/1869 [11:05:06<40:04, 22.90s/it]
1138
  94%|█████████▍| 1765/1869 [11:05:28<39:40, 22.89s/it]
1139
  94%|█████████▍| 1766/1869 [11:05:51<39:12, 22.84s/it]
1140
  95%|█████████▍| 1767/1869 [11:06:14<38:42, 22.77s/it]
1141
  95%|█████████▍| 1768/1869 [11:06:36<38:15, 22.72s/it]
1142
  95%|█████████▍| 1769/1869 [11:06:59<37:54, 22.74s/it]
1143
  95%|█████████▍| 1770/1869 [11:07:22<37:30, 22.74s/it]
1144
 
1145
+
1146
  95%|█████████▍| 1770/1869 [11:07:22<37:30, 22.74s/it]
1147
  95%|█████████▍| 1771/1869 [11:07:45<37:18, 22.84s/it]
1148
  95%|█████████▍| 1772/1869 [11:08:08<36:53, 22.82s/it]
1149
  95%|█████████▍| 1773/1869 [11:08:31<36:38, 22.90s/it]
1150
  95%|█████████▍| 1774/1869 [11:08:54<36:22, 22.97s/it]
1151
  95%|█████████▍| 1775/1869 [11:09:17<35:55, 22.93s/it]
1152
  95%|█████████▌| 1776/1869 [11:09:40<35:31, 22.92s/it]
1153
  95%|█████████▌| 1777/1869 [11:10:02<34:57, 22.80s/it]
1154
  95%|█████████▌| 1778/1869 [11:10:25<34:24, 22.69s/it]
1155
  95%|█████████▌| 1779/1869 [11:10:47<34:03, 22.71s/it]
1156
  95%|█████████▌| 1780/1869 [11:11:10<33:37, 22.66s/it]
1157
 
1158
+
1159
  95%|█████████▌| 1780/1869 [11:11:10<33:37, 22.66s/it]
1160
  95%|█████████▌| 1781/1869 [11:11:33<33:13, 22.65s/it]
1161
  95%|█████████▌| 1782/1869 [11:11:55<32:46, 22.60s/it]
1162
  95%|█████████▌| 1783/1869 [11:12:18<32:21, 22.58s/it]
1163
  95%|█████████▌| 1784/1869 [11:12:40<32:03, 22.63s/it]
1164
  96%|█████████▌| 1785/1869 [11:13:03<31:44, 22.68s/it]
1165
  96%|█████████▌| 1786/1869 [11:13:26<31:16, 22.61s/it]
1166
  96%|█████████▌| 1787/1869 [11:13:49<31:03, 22.73s/it]
1167
  96%|█████████▌| 1788/1869 [11:14:12<30:55, 22.91s/it]
1168
  96%|█████████▌| 1789/1869 [11:14:35<30:40, 23.00s/it]
1169
  96%|█████████▌| 1790/1869 [11:14:58<30:06, 22.87s/it]
1170
 
1171
+
1172
  96%|█████████▌| 1790/1869 [11:14:58<30:06, 22.87s/it]
1173
  96%|█████████▌| 1791/1869 [11:15:20<29:34, 22.75s/it]
1174
  96%|█████████▌| 1792/1869 [11:15:43<29:10, 22.73s/it]
1175
  96%|█████████▌| 1793/1869 [11:16:06<28:53, 22.81s/it]
1176
  96%|█████████▌| 1794/1869 [11:16:29<28:30, 22.81s/it]
1177
  96%|█████████▌| 1795/1869 [11:16:51<28:07, 22.80s/it]
1178
  96%|█████████▌| 1796/1869 [11:17:14<27:47, 22.84s/it]
1179
  96%|█████████▌| 1797/1869 [11:17:37<27:21, 22.79s/it]
1180
  96%|█████████▌| 1798/1869 [11:18:00<26:53, 22.73s/it]
1181
  96%|█████████▋| 1799/1869 [11:18:22<26:30, 22.73s/it]
1182
  96%|█████████▋| 1800/1869 [11:18:45<26:09, 22.74s/it]
1183
 
1184
+
1185
  96%|█████████▋| 1800/1869 [11:18:45<26:09, 22.74s/it]
1186
  96%|█████████▋| 1801/1869 [11:19:08<25:48, 22.77s/it]
1187
  96%|█████████▋| 1802/1869 [11:19:31<25:28, 22.82s/it]
1188
  96%|█████████▋| 1803/1869 [11:19:54<25:14, 22.95s/it]
1189
  97%|█████████▋| 1804/1869 [11:20:17<24:45, 22.85s/it]
1190
  97%|█████████▋| 1805/1869 [11:20:39<24:11, 22.69s/it]
1191
  97%|█████████▋| 1806/1869 [11:21:02<23:47, 22.66s/it]
1192
  97%|█████████▋| 1807/1869 [11:21:25<23:30, 22.75s/it]
1193
  97%|█████████▋| 1808/1869 [11:21:47<23:08, 22.76s/it]
1194
  97%|█████████▋| 1809/1869 [11:22:10<22:43, 22.73s/it]
1195
  97%|█████████▋| 1810/1869 [11:22:33<22:21, 22.73s/it]
1196
 
1197
+
1198
  97%|█████████▋| 1810/1869 [11:22:33<22:21, 22.73s/it]
1199
  97%|█████████▋| 1811/1869 [11:22:55<21:53, 22.64s/it]
1200
  97%|█████████▋| 1812/1869 [11:23:18<21:31, 22.66s/it]
1201
  97%|█████████▋| 1813/1869 [11:23:41<21:09, 22.66s/it]
1202
  97%|█████████▋| 1814/1869 [11:24:03<20:43, 22.61s/it]
1203
  97%|█████████▋| 1815/1869 [11:24:26<20:22, 22.64s/it]
1204
  97%|█████████▋| 1816/1869 [11:24:49<20:01, 22.66s/it]
1205
  97%|█████████▋| 1817/1869 [11:25:11<19:35, 22.61s/it]
1206
  97%|█████████▋| 1818/1869 [11:25:33<19:08, 22.52s/it]
1207
  97%|█████████▋| 1819/1869 [11:25:56<18:44, 22.50s/it]
1208
  97%|█████████▋| 1820/1869 [11:26:18<18:23, 22.51s/it]
1209
 
1210
+
1211
  97%|█████████▋| 1820/1869 [11:26:18<18:23, 22.51s/it]
1212
  97%|█████████▋| 1821/1869 [11:26:41<17:58, 22.48s/it]
1213
  97%|█████████▋| 1822/1869 [11:27:03<17:29, 22.34s/it]
1214
  98%|█████████▊| 1823/1869 [11:27:25<17:08, 22.36s/it]
1215
  98%|█████████▊| 1824/1869 [11:27:48<16:46, 22.37s/it]
1216
  98%|█████████▊| 1825/1869 [11:28:10<16:21, 22.30s/it]
1217
  98%|█████████▊| 1826/1869 [11:28:32<15:57, 22.28s/it]
1218
  98%|█████████▊| 1827/1869 [11:28:55<15:40, 22.40s/it]
1219
  98%|█████████▊| 1828/1869 [11:29:17<15:18, 22.40s/it]
1220
  98%|█████████▊| 1829/1869 [11:29:39<14:53, 22.35s/it]
1221
  98%|█████████▊| 1830/1869 [11:30:01<14:30, 22.33s/it]
1222
 
1223
+
1224
  98%|█████████▊| 1830/1869 [11:30:01<14:30, 22.33s/it]
1225
  98%|█████████▊| 1831/1869 [11:30:24<14:14, 22.48s/it]
1226
  98%|█████████▊| 1832/1869 [11:30:47<13:53, 22.54s/it]
1227
  98%|█████████▊| 1833/1869 [11:31:10<13:34, 22.61s/it]
1228
  98%|█████████▊| 1834/1869 [11:31:32<13:11, 22.62s/it]
1229
  98%|█████████▊| 1835/1869 [11:31:55<12:49, 22.62s/it]
1230
  98%|█████████▊| 1836/1869 [11:32:18<12:25, 22.58s/it]
1231
  98%|█████████▊| 1837/1869 [11:32:40<12:06, 22.70s/it]
1232
  98%|█████████▊| 1838/1869 [11:33:03<11:45, 22.75s/it]
1233
  98%|█████████▊| 1839/1869 [11:33:26<11:25, 22.85s/it]
1234
  98%|█████████▊| 1840/1869 [11:33:50<11:05, 22.96s/it]
1235
 
1236
+
1237
  98%|█████████▊| 1840/1869 [11:33:50<11:05, 22.96s/it]
1238
  99%|█████████▊| 1841/1869 [11:34:12<10:40, 22.89s/it]
1239
  99%|█████████▊| 1842/1869 [11:34:35<10:14, 22.74s/it]
1240
  99%|█████████▊| 1843/1869 [11:34:58<09:51, 22.76s/it]
1241
  99%|█████████▊| 1844/1869 [11:35:21<09:31, 22.84s/it]
1242
  99%|█████████▊| 1845/1869 [11:35:43<09:07, 22.83s/it]
1243
  99%|█████████▉| 1846/1869 [11:36:06<08:46, 22.88s/it]
1244
  99%|█████████▉| 1847/1869 [11:36:29<08:23, 22.87s/it]
1245
  99%|█████████▉| 1848/1869 [11:36:52<08:01, 22.91s/it]
1246
  99%|█████████▉| 1849/1869 [11:37:15<07:38, 22.92s/it]
1247
  99%|█████████▉| 1850/1869 [11:37:38<07:15, 22.93s/it]
1248
 
1249
+
1250
  99%|█████████▉| 1850/1869 [11:37:38<07:15, 22.93s/it]
1251
  99%|█████████▉| 1851/1869 [11:38:01<06:53, 22.97s/it]
1252
  99%|█████████▉| 1852/1869 [11:38:24<06:30, 22.94s/it]
1253
  99%|█████████▉| 1853/1869 [11:38:47<06:06, 22.90s/it]
1254
  99%|█████████▉| 1854/1869 [11:39:10<05:43, 22.90s/it]
1255
  99%|█████████▉| 1855/1869 [11:39:33<05:20, 22.88s/it]
1256
  99%|█████████▉| 1856/1869 [11:39:56<04:57, 22.90s/it]
1257
  99%|█████████▉| 1857/1869 [11:40:19<04:35, 22.95s/it]
1258
  99%|█████████▉| 1858/1869 [11:40:42<04:12, 22.95s/it]
1259
  99%|█████████▉| 1859/1869 [11:41:05<03:49, 22.97s/it]
1260
 
1261
+
1262
+ [INFO|configuration_utils.py:675] 2026-05-11 05:05:14,127 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--meta-llama--Llama-3.2-3B-Instruct/snapshots/0cb88a4f764b7a12671c53f0838cd831a0843b95/config.json
1263
+ [INFO|configuration_utils.py:742] 2026-05-11 05:05:14,128 >> Model config LlamaConfig {
1264
+ "architectures": [
1265
+ "LlamaForCausalLM"
1266
+ ],
1267
+ "attention_bias": false,
1268
+ "attention_dropout": 0.0,
1269
+ "bos_token_id": 128000,
1270
+ "eos_token_id": [
1271
+ 128001,
1272
+ 128008,
1273
+ 128009
1274
+ ],
1275
+ "head_dim": 128,
1276
+ "hidden_act": "silu",
1277
+ "hidden_size": 3072,
1278
+ "initializer_range": 0.02,
1279
+ "intermediate_size": 8192,
1280
+ "max_position_embeddings": 131072,
1281
+ "mlp_bias": false,
1282
+ "model_type": "llama",
1283
+ "num_attention_heads": 24,
1284
+ "num_hidden_layers": 28,
1285
+ "num_key_value_heads": 8,
1286
+ "pretraining_tp": 1,
1287
+ "rms_norm_eps": 1e-05,
1288
+ "rope_scaling": {
1289
+ "factor": 32.0,
1290
+ "high_freq_factor": 4.0,
1291
+ "low_freq_factor": 1.0,
1292
+ "original_max_position_embeddings": 8192,
1293
+ "rope_type": "llama3"
1294
+ },
1295
+ "rope_theta": 500000.0,
1296
+ "tie_word_embeddings": true,
1297
+ "torch_dtype": "bfloat16",
1298
+ "transformers_version": "4.45.2",
1299
+ "use_cache": true,
1300
+ "vocab_size": 128256
1301
+ }
1302
+
1303
+ [INFO|tokenization_utils_base.py:2641] 2026-05-11 05:05:14,204 >> tokenizer config file saved in ./outputs/llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer_config.json
1304
+ [INFO|tokenization_utils_base.py:2650] 2026-05-11 05:05:14,204 >> Special tokens file saved in ./outputs/llama-3.2-3B-it-distillm2/checkpoint-1869/special_tokens_map.json
1305
+ [INFO|trainer.py:3705] 2026-05-11 05:05:14,346 >> Saving model checkpoint to ./outputs/llama-3.2-3B-it-distillm2/checkpoint-1869
1306
+ [INFO|configuration_utils.py:675] 2026-05-11 05:05:14,637 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--meta-llama--Llama-3.2-3B-Instruct/snapshots/0cb88a4f764b7a12671c53f0838cd831a0843b95/config.json
1307
+ [INFO|configuration_utils.py:742] 2026-05-11 05:05:14,638 >> Model config LlamaConfig {
1308
+ "architectures": [
1309
+ "LlamaForCausalLM"
1310
+ ],
1311
+ "attention_bias": false,
1312
+ "attention_dropout": 0.0,
1313
+ "bos_token_id": 128000,
1314
+ "eos_token_id": [
1315
+ 128001,
1316
+ 128008,
1317
+ 128009
1318
+ ],
1319
+ "head_dim": 128,
1320
+ "hidden_act": "silu",
1321
+ "hidden_size": 3072,
1322
+ "initializer_range": 0.02,
1323
+ "intermediate_size": 8192,
1324
+ "max_position_embeddings": 131072,
1325
+ "mlp_bias": false,
1326
+ "model_type": "llama",
1327
+ "num_attention_heads": 24,
1328
+ "num_hidden_layers": 28,
1329
+ "num_key_value_heads": 8,
1330
+ "pretraining_tp": 1,
1331
+ "rms_norm_eps": 1e-05,
1332
+ "rope_scaling": {
1333
+ "factor": 32.0,
1334
+ "high_freq_factor": 4.0,
1335
+ "low_freq_factor": 1.0,
1336
+ "original_max_position_embeddings": 8192,
1337
+ "rope_type": "llama3"
1338
+ },
1339
+ "rope_theta": 500000.0,
1340
+ "tie_word_embeddings": true,
1341
+ "torch_dtype": "bfloat16",
1342
+ "transformers_version": "4.45.2",
1343
+ "use_cache": true,
1344
+ "vocab_size": 128256
1345
+ }
1346
+
1347
+ [INFO|tokenization_utils_base.py:2641] 2026-05-11 05:05:14,757 >> tokenizer config file saved in ./outputs/llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer_config.json
1348
+ [INFO|tokenization_utils_base.py:2650] 2026-05-11 05:05:14,758 >> Special tokens file saved in ./outputs/llama-3.2-3B-it-distillm2/checkpoint-1869/special_tokens_map.json
1349
+ [INFO|trainer.py:2505] 2026-05-11 05:05:14,881 >>
1350
+
1351
+ Training completed. Do not forget to share your model on huggingface.co/models =)
1352
+
1353
+
1354
+
1355
 
1356
+
1357
+ ***** train metrics *****
1358
+ epoch = 2.9997
1359
+ total_flos = 0GF
1360
+ train_loss = 0.3476
1361
+ train_runtime = 11:44:50.52
1362
+ train_samples = 79751
1363
+ train_samples_per_second = 5.657
1364
+ train_steps_per_second = 0.044
1365
+ 2026-05-11 05:05:14 - INFO - __main__ - *** Training complete ***
1366
+ 2026-05-11 05:05:14 - INFO - __main__ - *** Save model ***
1367
+ [INFO|trainer.py:3705] 2026-05-11 05:05:14,888 >> Saving model checkpoint to ./outputs/llama-3.2-3B-it-distillm2
1368
+ [INFO|configuration_utils.py:675] 2026-05-11 05:05:15,185 >> loading configuration file config.json from cache at /home/ubuntu/.cache/huggingface/hub/models--meta-llama--Llama-3.2-3B-Instruct/snapshots/0cb88a4f764b7a12671c53f0838cd831a0843b95/config.json
1369
+ [INFO|configuration_utils.py:742] 2026-05-11 05:05:15,185 >> Model config LlamaConfig {
1370
+ "architectures": [
1371
+ "LlamaForCausalLM"
1372
+ ],
1373
+ "attention_bias": false,
1374
+ "attention_dropout": 0.0,
1375
+ "bos_token_id": 128000,
1376
+ "eos_token_id": [
1377
+ 128001,
1378
+ 128008,
1379
+ 128009
1380
+ ],
1381
+ "head_dim": 128,
1382
+ "hidden_act": "silu",
1383
+ "hidden_size": 3072,
1384
+ "initializer_range": 0.02,
1385
+ "intermediate_size": 8192,
1386
+ "max_position_embeddings": 131072,
1387
+ "mlp_bias": false,
1388
+ "model_type": "llama",
1389
+ "num_attention_heads": 24,
1390
+ "num_hidden_layers": 28,
1391
+ "num_key_value_heads": 8,
1392
+ "pretraining_tp": 1,
1393
+ "rms_norm_eps": 1e-05,
1394
+ "rope_scaling": {
1395
+ "factor": 32.0,
1396
+ "high_freq_factor": 4.0,
1397
+ "low_freq_factor": 1.0,
1398
+ "original_max_position_embeddings": 8192,
1399
+ "rope_type": "llama3"
1400
+ },
1401
+ "rope_theta": 500000.0,
1402
+ "tie_word_embeddings": true,
1403
+ "torch_dtype": "bfloat16",
1404
+ "transformers_version": "4.45.2",
1405
+ "use_cache": true,
1406
+ "vocab_size": 128256
1407
+ }
1408
+
1409
+ [INFO|tokenization_utils_base.py:2641] 2026-05-11 05:05:15,261 >> tokenizer config file saved in ./outputs/llama-3.2-3B-it-distillm2/tokenizer_config.json
1410
+ [INFO|tokenization_utils_base.py:2650] 2026-05-11 05:05:15,261 >> Special tokens file saved in ./outputs/llama-3.2-3B-it-distillm2/special_tokens_map.json
1411
+ 2026-05-11 05:05:15 - INFO - __main__ - Model saved to ./outputs/llama-3.2-3B-it-distillm2
1412
+ [INFO|modelcard.py:449] 2026-05-11 05:05:15,530 >> Dropping the following result as it does not have all the necessary fields:
1413
+ {'dataset': {'name': 'data/reformatted/distill-deepSeek-R1-Distill-Llama-8B', 'type': 'data/reformatted/distill-deepSeek-R1-Distill-Llama-8B'}}
1414
+ [INFO|configuration_utils.py:410] 2026-05-11 05:05:15,538 >> Configuration saved in ./outputs/llama-3.2-3B-it-distillm2/config.json
1415
+ 2026-05-11 05:05:15 - INFO - __main__ - *** Evaluate ***
1416
+ [INFO|trainer.py:4021] 2026-05-11 05:05:15,542 >>
1417
+ ***** Running Evaluation *****
1418
+ [INFO|trainer.py:4023] 2026-05-11 05:05:15,542 >> Num examples = 10
1419
+ [INFO|trainer.py:4026] 2026-05-11 05:05:15,542 >> Batch size = 2
1420
+
1421
  0%| | 0/3 [00:00<?, ?it/s]
1422
  67%|██████▋ | 2/3 [00:00<00:00, 5.96it/s]
1423
+ ***** eval metrics *****
1424
+ epoch = 2.9997
1425
+ eval_logps_logqs/chosen = 0.0958
1426
+ eval_logqs/chosen = -0.8354
1427
+ eval_logqs/rejected = -0.7743
1428
+ eval_logqs_logps/rejected = 0.0967
1429
+ eval_loss = 0.3443
1430
+ eval_runtime = 0:00:01.16
1431
+ eval_samples = 10
1432
+ eval_samples_per_second = 8.609
1433
+ eval_steps_per_second = 2.583
1434
+ 2026-05-11 05:05:16 - INFO - __main__ - *** Training complete! ***
1435
+ [rank0]:[W511 05:05:17.401351081 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
qwen2.5-1.5B-it-distillm2-1epoch/README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-1.5B-Instruct
5
+ tags:
6
+ - alignment-handbook
7
+ - generated_from_trainer
8
+ datasets:
9
+ - data/reformatted/distill-qwen2.5-14B-Instruct
10
+ model-index:
11
+ - name: qwen2.5-1.5B-it-distillm2-1epoch
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # qwen2.5-1.5B-it-distillm2-1epoch
19
+
20
+ This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the data/reformatted/distill-qwen2.5-14B-Instruct dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 2
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 2
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 1
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.45.2
60
+ - Pytorch 2.5.1+cu124
61
+ - Datasets 4.8.5
62
+ - Tokenizers 0.20.3
qwen2.5-1.5B-it-distillm2-1epoch/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5-1.5B-it-distillm2-1epoch/all_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9998996890360117,
3
+ "eval_logps_logqs/chosen": 0.05957354977726936,
4
+ "eval_logqs/chosen": -0.9947950839996338,
5
+ "eval_logqs/rejected": -0.9651834964752197,
6
+ "eval_logqs_logps/rejected": 0.04703126847743988,
7
+ "eval_loss": 0.18548408150672913,
8
+ "eval_runtime": 1.047,
9
+ "eval_samples": 10,
10
+ "eval_samples_per_second": 9.551,
11
+ "eval_steps_per_second": 2.865,
12
+ "total_flos": 0.0,
13
+ "train_loss": 0.2227630860637126,
14
+ "train_runtime": 7975.4099,
15
+ "train_samples": 79751,
16
+ "train_samples_per_second": 10.0,
17
+ "train_steps_per_second": 0.312
18
+ }
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.45.2",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.45.2"
14
+ }
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ff145d45e5491c4cb2f9b91b392fa1d4980c8caf0c065acd5d8e83f7ad1bf6
3
+ size 3087935634
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "bos_token": "<|endoftext|>",
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": "<|endoftext|>",
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 2048,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/trainer_state.json ADDED
@@ -0,0 +1,2783 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9998996890360117,
5
+ "eval_steps": 10000000,
6
+ "global_step": 2492,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0004012438559534557,
13
+ "grad_norm": 7.4375,
14
+ "learning_rate": 2.0000000000000002e-07,
15
+ "logps_logqs/chosen": 0.04569786787033081,
16
+ "logqs/chosen": -0.7619987726211548,
17
+ "logqs/rejected": -0.6922895908355713,
18
+ "logqs_logps/rejected": 0.12882234156131744,
19
+ "loss": 0.4402,
20
+ "step": 1
21
+ },
22
+ {
23
+ "epoch": 0.004012438559534557,
24
+ "grad_norm": 8.1875,
25
+ "learning_rate": 2.0000000000000003e-06,
26
+ "logps_logqs/chosen": 0.05236833542585373,
27
+ "logqs/chosen": -0.7575697302818298,
28
+ "logqs/rejected": -0.7214224338531494,
29
+ "logqs_logps/rejected": 0.13564398884773254,
30
+ "loss": 0.4632,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.008024877119069114,
35
+ "grad_norm": 3.5625,
36
+ "learning_rate": 4.000000000000001e-06,
37
+ "logps_logqs/chosen": 0.03725143522024155,
38
+ "logqs/chosen": -0.7332857847213745,
39
+ "logqs/rejected": -0.6967843770980835,
40
+ "logqs_logps/rejected": 0.15449675917625427,
41
+ "loss": 0.437,
42
+ "step": 20
43
+ },
44
+ {
45
+ "epoch": 0.012037315678603671,
46
+ "grad_norm": 2.65625,
47
+ "learning_rate": 6e-06,
48
+ "logps_logqs/chosen": 0.024129396304488182,
49
+ "logqs/chosen": -0.6929070353507996,
50
+ "logqs/rejected": -0.6931973695755005,
51
+ "logqs_logps/rejected": 0.14559319615364075,
52
+ "loss": 0.3924,
53
+ "step": 30
54
+ },
55
+ {
56
+ "epoch": 0.016049754238138227,
57
+ "grad_norm": 1.9296875,
58
+ "learning_rate": 8.000000000000001e-06,
59
+ "logps_logqs/chosen": 0.04635835438966751,
60
+ "logqs/chosen": -0.7109580039978027,
61
+ "logqs/rejected": -0.7326062917709351,
62
+ "logqs_logps/rejected": 0.11042358726263046,
63
+ "loss": 0.3376,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 0.020062192797672785,
68
+ "grad_norm": 1.359375,
69
+ "learning_rate": 1e-05,
70
+ "logps_logqs/chosen": 0.06155390664935112,
71
+ "logqs/chosen": -0.7556450963020325,
72
+ "logqs/rejected": -0.7544510364532471,
73
+ "logqs_logps/rejected": 0.0817796066403389,
74
+ "loss": 0.3119,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.024074631357207343,
79
+ "grad_norm": 1.9609375,
80
+ "learning_rate": 1.2e-05,
81
+ "logps_logqs/chosen": 0.04699297621846199,
82
+ "logqs/chosen": -0.7331749796867371,
83
+ "logqs/rejected": -0.7754837870597839,
84
+ "logqs_logps/rejected": 0.09542788565158844,
85
+ "loss": 0.3021,
86
+ "step": 60
87
+ },
88
+ {
89
+ "epoch": 0.0280870699167419,
90
+ "grad_norm": 2.1875,
91
+ "learning_rate": 1.4000000000000001e-05,
92
+ "logps_logqs/chosen": 0.04325335472822189,
93
+ "logqs/chosen": -0.7399210333824158,
94
+ "logqs/rejected": -0.8113678097724915,
95
+ "logqs_logps/rejected": 0.09601923078298569,
96
+ "loss": 0.3056,
97
+ "step": 70
98
+ },
99
+ {
100
+ "epoch": 0.032099508476276455,
101
+ "grad_norm": 1.40625,
102
+ "learning_rate": 1.6000000000000003e-05,
103
+ "logps_logqs/chosen": 0.05340943485498428,
104
+ "logqs/chosen": -0.7167432904243469,
105
+ "logqs/rejected": -0.733643651008606,
106
+ "logqs_logps/rejected": 0.08651523292064667,
107
+ "loss": 0.2901,
108
+ "step": 80
109
+ },
110
+ {
111
+ "epoch": 0.03611194703581101,
112
+ "grad_norm": 1.9140625,
113
+ "learning_rate": 1.8e-05,
114
+ "logps_logqs/chosen": 0.05581357330083847,
115
+ "logqs/chosen": -0.7287663221359253,
116
+ "logqs/rejected": -0.80914705991745,
117
+ "logqs_logps/rejected": 0.08022361993789673,
118
+ "loss": 0.2872,
119
+ "step": 90
120
+ },
121
+ {
122
+ "epoch": 0.04012438559534557,
123
+ "grad_norm": 1.484375,
124
+ "learning_rate": 2e-05,
125
+ "logps_logqs/chosen": 0.060486920177936554,
126
+ "logqs/chosen": -0.7507224082946777,
127
+ "logqs/rejected": -0.7546180486679077,
128
+ "logqs_logps/rejected": 0.08861987292766571,
129
+ "loss": 0.2874,
130
+ "step": 100
131
+ },
132
+ {
133
+ "epoch": 0.04413682415488013,
134
+ "grad_norm": 1.625,
135
+ "learning_rate": 2.2000000000000003e-05,
136
+ "logps_logqs/chosen": 0.05298670381307602,
137
+ "logqs/chosen": -0.7025843262672424,
138
+ "logqs/rejected": -0.8093870282173157,
139
+ "logqs_logps/rejected": 0.09236426651477814,
140
+ "loss": 0.284,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.048149262714414685,
145
+ "grad_norm": 1.3671875,
146
+ "learning_rate": 2.4e-05,
147
+ "logps_logqs/chosen": 0.0429534837603569,
148
+ "logqs/chosen": -0.7203501462936401,
149
+ "logqs/rejected": -0.7625126838684082,
150
+ "logqs_logps/rejected": 0.09294354915618896,
151
+ "loss": 0.2814,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.05216170127394924,
156
+ "grad_norm": 1.4375,
157
+ "learning_rate": 2.6000000000000002e-05,
158
+ "logps_logqs/chosen": 0.04513775557279587,
159
+ "logqs/chosen": -0.7521069645881653,
160
+ "logqs/rejected": -0.8475151062011719,
161
+ "logqs_logps/rejected": 0.08711571246385574,
162
+ "loss": 0.2738,
163
+ "step": 130
164
+ },
165
+ {
166
+ "epoch": 0.0561741398334838,
167
+ "grad_norm": 1.2578125,
168
+ "learning_rate": 2.8000000000000003e-05,
169
+ "logps_logqs/chosen": 0.05815966799855232,
170
+ "logqs/chosen": -0.7234808206558228,
171
+ "logqs/rejected": -0.7618853449821472,
172
+ "logqs_logps/rejected": 0.08775873482227325,
173
+ "loss": 0.2716,
174
+ "step": 140
175
+ },
176
+ {
177
+ "epoch": 0.06018657839301836,
178
+ "grad_norm": 1.2421875,
179
+ "learning_rate": 3e-05,
180
+ "logps_logqs/chosen": 0.04522830247879028,
181
+ "logqs/chosen": -0.7279343008995056,
182
+ "logqs/rejected": -0.7802385091781616,
183
+ "logqs_logps/rejected": 0.08993647247552872,
184
+ "loss": 0.2844,
185
+ "step": 150
186
+ },
187
+ {
188
+ "epoch": 0.06419901695255291,
189
+ "grad_norm": 4.8125,
190
+ "learning_rate": 3.2000000000000005e-05,
191
+ "logps_logqs/chosen": 0.04608219116926193,
192
+ "logqs/chosen": -0.7237873077392578,
193
+ "logqs/rejected": -0.8180141448974609,
194
+ "logqs_logps/rejected": 0.09209342300891876,
195
+ "loss": 0.2734,
196
+ "step": 160
197
+ },
198
+ {
199
+ "epoch": 0.06821145551208747,
200
+ "grad_norm": 1.625,
201
+ "learning_rate": 3.4000000000000007e-05,
202
+ "logps_logqs/chosen": 0.0829857811331749,
203
+ "logqs/chosen": -0.834354043006897,
204
+ "logqs/rejected": -0.9757483601570129,
205
+ "logqs_logps/rejected": 0.05420444533228874,
206
+ "loss": 0.2608,
207
+ "step": 170
208
+ },
209
+ {
210
+ "epoch": 0.07222389407162202,
211
+ "grad_norm": 1.59375,
212
+ "learning_rate": 3.6e-05,
213
+ "logps_logqs/chosen": 0.07175259292125702,
214
+ "logqs/chosen": -0.8033750653266907,
215
+ "logqs/rejected": -0.9368761777877808,
216
+ "logqs_logps/rejected": 0.05796421319246292,
217
+ "loss": 0.2532,
218
+ "step": 180
219
+ },
220
+ {
221
+ "epoch": 0.07623633263115659,
222
+ "grad_norm": 1.171875,
223
+ "learning_rate": 3.8e-05,
224
+ "logps_logqs/chosen": 0.07778682559728622,
225
+ "logqs/chosen": -0.7997792959213257,
226
+ "logqs/rejected": -0.9281190633773804,
227
+ "logqs_logps/rejected": 0.05667818337678909,
228
+ "loss": 0.2451,
229
+ "step": 190
230
+ },
231
+ {
232
+ "epoch": 0.08024877119069114,
233
+ "grad_norm": 1.515625,
234
+ "learning_rate": 4e-05,
235
+ "logps_logqs/chosen": 0.07711273431777954,
236
+ "logqs/chosen": -0.7552299499511719,
237
+ "logqs/rejected": -0.8450819849967957,
238
+ "logqs_logps/rejected": 0.047475770115852356,
239
+ "loss": 0.2445,
240
+ "step": 200
241
+ },
242
+ {
243
+ "epoch": 0.0842612097502257,
244
+ "grad_norm": 1.2421875,
245
+ "learning_rate": 4.2e-05,
246
+ "logps_logqs/chosen": 0.07256797701120377,
247
+ "logqs/chosen": -0.7694905996322632,
248
+ "logqs/rejected": -0.9085494875907898,
249
+ "logqs_logps/rejected": 0.04616270214319229,
250
+ "loss": 0.2415,
251
+ "step": 210
252
+ },
253
+ {
254
+ "epoch": 0.08827364830976026,
255
+ "grad_norm": 1.359375,
256
+ "learning_rate": 4.4000000000000006e-05,
257
+ "logps_logqs/chosen": 0.07909471541643143,
258
+ "logqs/chosen": -0.7777330875396729,
259
+ "logqs/rejected": -0.9235789179801941,
260
+ "logqs_logps/rejected": 0.04829848185181618,
261
+ "loss": 0.2477,
262
+ "step": 220
263
+ },
264
+ {
265
+ "epoch": 0.09228608686929482,
266
+ "grad_norm": 1.6484375,
267
+ "learning_rate": 4.600000000000001e-05,
268
+ "logps_logqs/chosen": 0.07866504043340683,
269
+ "logqs/chosen": -0.8106803894042969,
270
+ "logqs/rejected": -0.851120114326477,
271
+ "logqs_logps/rejected": 0.04576503112912178,
272
+ "loss": 0.2416,
273
+ "step": 230
274
+ },
275
+ {
276
+ "epoch": 0.09629852542882937,
277
+ "grad_norm": 1.3671875,
278
+ "learning_rate": 4.8e-05,
279
+ "logps_logqs/chosen": 0.08257119357585907,
280
+ "logqs/chosen": -0.8273600339889526,
281
+ "logqs/rejected": -0.9416961669921875,
282
+ "logqs_logps/rejected": 0.03500179573893547,
283
+ "loss": 0.2464,
284
+ "step": 240
285
+ },
286
+ {
287
+ "epoch": 0.10031096398836392,
288
+ "grad_norm": 1.2578125,
289
+ "learning_rate": 5e-05,
290
+ "logps_logqs/chosen": 0.07746388763189316,
291
+ "logqs/chosen": -0.8364149332046509,
292
+ "logqs/rejected": -0.9234830737113953,
293
+ "logqs_logps/rejected": 0.0357363224029541,
294
+ "loss": 0.249,
295
+ "step": 250
296
+ },
297
+ {
298
+ "epoch": 0.10432340254789849,
299
+ "grad_norm": 1.734375,
300
+ "learning_rate": 4.999754567859088e-05,
301
+ "logps_logqs/chosen": 0.07921982556581497,
302
+ "logqs/chosen": -0.8031741976737976,
303
+ "logqs/rejected": -0.9179041981697083,
304
+ "logqs_logps/rejected": 0.040028877556324005,
305
+ "loss": 0.254,
306
+ "step": 260
307
+ },
308
+ {
309
+ "epoch": 0.10833584110743304,
310
+ "grad_norm": 1.375,
311
+ "learning_rate": 4.9990183196258985e-05,
312
+ "logps_logqs/chosen": 0.07431423664093018,
313
+ "logqs/chosen": -0.8124697804450989,
314
+ "logqs/rejected": -1.044480323791504,
315
+ "logqs_logps/rejected": 0.03857969120144844,
316
+ "loss": 0.2526,
317
+ "step": 270
318
+ },
319
+ {
320
+ "epoch": 0.1123482796669676,
321
+ "grad_norm": 1.2578125,
322
+ "learning_rate": 4.997791399859618e-05,
323
+ "logps_logqs/chosen": 0.07444961369037628,
324
+ "logqs/chosen": -0.7750430107116699,
325
+ "logqs/rejected": -0.9249812364578247,
326
+ "logqs_logps/rejected": 0.043836839497089386,
327
+ "loss": 0.2466,
328
+ "step": 280
329
+ },
330
+ {
331
+ "epoch": 0.11636071822650215,
332
+ "grad_norm": 1.234375,
333
+ "learning_rate": 4.9960740494606804e-05,
334
+ "logps_logqs/chosen": 0.0844290554523468,
335
+ "logqs/chosen": -0.8090071678161621,
336
+ "logqs/rejected": -0.9015344381332397,
337
+ "logqs_logps/rejected": 0.04431484267115593,
338
+ "loss": 0.2518,
339
+ "step": 290
340
+ },
341
+ {
342
+ "epoch": 0.12037315678603672,
343
+ "grad_norm": 1.2109375,
344
+ "learning_rate": 4.993866605623476e-05,
345
+ "logps_logqs/chosen": 0.08662852644920349,
346
+ "logqs/chosen": -0.8766249418258667,
347
+ "logqs/rejected": -0.9904054403305054,
348
+ "logqs_logps/rejected": 0.03374750539660454,
349
+ "loss": 0.259,
350
+ "step": 300
351
+ },
352
+ {
353
+ "epoch": 0.12438559534557127,
354
+ "grad_norm": 1.1875,
355
+ "learning_rate": 4.9911695017701354e-05,
356
+ "logps_logqs/chosen": 0.06808570772409439,
357
+ "logqs/chosen": -0.7952664494514465,
358
+ "logqs/rejected": -1.0071316957473755,
359
+ "logqs_logps/rejected": 0.0351722352206707,
360
+ "loss": 0.2404,
361
+ "step": 310
362
+ },
363
+ {
364
+ "epoch": 0.12839803390510582,
365
+ "grad_norm": 1.25,
366
+ "learning_rate": 4.9879832674654394e-05,
367
+ "logps_logqs/chosen": 0.07012389600276947,
368
+ "logqs/chosen": -0.7575680017471313,
369
+ "logqs/rejected": -0.8348391652107239,
370
+ "logqs_logps/rejected": 0.04610547423362732,
371
+ "loss": 0.2475,
372
+ "step": 320
373
+ },
374
+ {
375
+ "epoch": 0.13241047246464038,
376
+ "grad_norm": 1.125,
377
+ "learning_rate": 4.984308528312833e-05,
378
+ "logps_logqs/chosen": 0.07651235163211823,
379
+ "logqs/chosen": -0.8075329661369324,
380
+ "logqs/rejected": -0.8980422019958496,
381
+ "logqs_logps/rejected": 0.05326312780380249,
382
+ "loss": 0.2557,
383
+ "step": 330
384
+ },
385
+ {
386
+ "epoch": 0.13642291102417495,
387
+ "grad_norm": 0.9375,
388
+ "learning_rate": 4.980146005831593e-05,
389
+ "logps_logqs/chosen": 0.07402589172124863,
390
+ "logqs/chosen": -0.7595754265785217,
391
+ "logqs/rejected": -0.8438477516174316,
392
+ "logqs_logps/rejected": 0.0414380244910717,
393
+ "loss": 0.2352,
394
+ "step": 340
395
+ },
396
+ {
397
+ "epoch": 0.1404353495837095,
398
+ "grad_norm": 1.03125,
399
+ "learning_rate": 4.975496517315164e-05,
400
+ "logps_logqs/chosen": 0.08224797248840332,
401
+ "logqs/chosen": -0.8209888339042664,
402
+ "logqs/rejected": -0.9319378137588501,
403
+ "logqs_logps/rejected": 0.040799789130687714,
404
+ "loss": 0.2447,
405
+ "step": 350
406
+ },
407
+ {
408
+ "epoch": 0.14444778814324405,
409
+ "grad_norm": 0.8984375,
410
+ "learning_rate": 4.9703609756706825e-05,
411
+ "logps_logqs/chosen": 0.06839220225811005,
412
+ "logqs/chosen": -0.7235757112503052,
413
+ "logqs/rejected": -0.8419008255004883,
414
+ "logqs_logps/rejected": 0.042561449110507965,
415
+ "loss": 0.2358,
416
+ "step": 360
417
+ },
418
+ {
419
+ "epoch": 0.1484602267027786,
420
+ "grad_norm": 1.0546875,
421
+ "learning_rate": 4.964740389239732e-05,
422
+ "logps_logqs/chosen": 0.06623891741037369,
423
+ "logqs/chosen": -0.7539215683937073,
424
+ "logqs/rejected": -0.9607669115066528,
425
+ "logqs_logps/rejected": 0.04915183037519455,
426
+ "loss": 0.239,
427
+ "step": 370
428
+ },
429
+ {
430
+ "epoch": 0.15247266526231318,
431
+ "grad_norm": 1.0390625,
432
+ "learning_rate": 4.958635861600363e-05,
433
+ "logps_logqs/chosen": 0.07241146266460419,
434
+ "logqs/chosen": -0.7943685054779053,
435
+ "logqs/rejected": -0.893652617931366,
436
+ "logqs_logps/rejected": 0.04425416141748428,
437
+ "loss": 0.2338,
438
+ "step": 380
439
+ },
440
+ {
441
+ "epoch": 0.15648510382184772,
442
+ "grad_norm": 1.3828125,
443
+ "learning_rate": 4.9520485913504034e-05,
444
+ "logps_logqs/chosen": 0.08117856085300446,
445
+ "logqs/chosen": -0.8306816816329956,
446
+ "logqs/rejected": -0.9850896596908569,
447
+ "logqs_logps/rejected": 0.0467182882130146,
448
+ "loss": 0.2507,
449
+ "step": 390
450
+ },
451
+ {
452
+ "epoch": 0.16049754238138228,
453
+ "grad_norm": 1.1328125,
454
+ "learning_rate": 4.944979871872126e-05,
455
+ "logps_logqs/chosen": 0.07253263145685196,
456
+ "logqs/chosen": -0.7571657299995422,
457
+ "logqs/rejected": -0.8560029864311218,
458
+ "logqs_logps/rejected": 0.04899878054857254,
459
+ "loss": 0.2395,
460
+ "step": 400
461
+ },
462
+ {
463
+ "epoch": 0.16450998094091684,
464
+ "grad_norm": 1.0,
465
+ "learning_rate": 4.937431091078297e-05,
466
+ "logps_logqs/chosen": 0.07146044075489044,
467
+ "logqs/chosen": -0.780661404132843,
468
+ "logqs/rejected": -0.8788405656814575,
469
+ "logqs_logps/rejected": 0.045706409960985184,
470
+ "loss": 0.2476,
471
+ "step": 410
472
+ },
473
+ {
474
+ "epoch": 0.1685224195004514,
475
+ "grad_norm": 1.171875,
476
+ "learning_rate": 4.929403731139659e-05,
477
+ "logps_logqs/chosen": 0.06834863871335983,
478
+ "logqs/chosen": -0.7439772486686707,
479
+ "logqs/rejected": -0.8892331123352051,
480
+ "logqs_logps/rejected": 0.04937626048922539,
481
+ "loss": 0.2396,
482
+ "step": 420
483
+ },
484
+ {
485
+ "epoch": 0.17253485805998595,
486
+ "grad_norm": 1.265625,
487
+ "learning_rate": 4.920899368193923e-05,
488
+ "logps_logqs/chosen": 0.07205794751644135,
489
+ "logqs/chosen": -0.7703086137771606,
490
+ "logqs/rejected": -0.924181342124939,
491
+ "logqs_logps/rejected": 0.04389696940779686,
492
+ "loss": 0.2415,
493
+ "step": 430
494
+ },
495
+ {
496
+ "epoch": 0.1765472966195205,
497
+ "grad_norm": 1.0546875,
498
+ "learning_rate": 4.91191967203629e-05,
499
+ "logps_logqs/chosen": 0.07142455875873566,
500
+ "logqs/chosen": -0.774928092956543,
501
+ "logqs/rejected": -0.8973848223686218,
502
+ "logqs_logps/rejected": 0.05115640163421631,
503
+ "loss": 0.2429,
504
+ "step": 440
505
+ },
506
+ {
507
+ "epoch": 0.18055973517905508,
508
+ "grad_norm": 1.203125,
509
+ "learning_rate": 4.902466405791604e-05,
510
+ "logps_logqs/chosen": 0.0635933205485344,
511
+ "logqs/chosen": -0.7374957799911499,
512
+ "logqs/rejected": -0.8527389764785767,
513
+ "logqs_logps/rejected": 0.04913189262151718,
514
+ "loss": 0.2389,
515
+ "step": 450
516
+ },
517
+ {
518
+ "epoch": 0.18457217373858964,
519
+ "grad_norm": 1.0703125,
520
+ "learning_rate": 4.8925414255681634e-05,
521
+ "logps_logqs/chosen": 0.07408438622951508,
522
+ "logqs/chosen": -0.7961963415145874,
523
+ "logqs/rejected": -0.891047477722168,
524
+ "logqs_logps/rejected": 0.047257475554943085,
525
+ "loss": 0.244,
526
+ "step": 460
527
+ },
528
+ {
529
+ "epoch": 0.18858461229812418,
530
+ "grad_norm": 1.0625,
531
+ "learning_rate": 4.8821466800932834e-05,
532
+ "logps_logqs/chosen": 0.07002029567956924,
533
+ "logqs/chosen": -0.7757862210273743,
534
+ "logqs/rejected": -0.9203861355781555,
535
+ "logqs_logps/rejected": 0.04404062032699585,
536
+ "loss": 0.2403,
537
+ "step": 470
538
+ },
539
+ {
540
+ "epoch": 0.19259705085765874,
541
+ "grad_norm": 1.0703125,
542
+ "learning_rate": 4.8712842103306734e-05,
543
+ "logps_logqs/chosen": 0.0644606500864029,
544
+ "logqs/chosen": -0.7633457779884338,
545
+ "logqs/rejected": -0.8767465353012085,
546
+ "logqs_logps/rejected": 0.056550778448581696,
547
+ "loss": 0.2414,
548
+ "step": 480
549
+ },
550
+ {
551
+ "epoch": 0.1966094894171933,
552
+ "grad_norm": 1.046875,
553
+ "learning_rate": 4.859956149079699e-05,
554
+ "logps_logqs/chosen": 0.06858934462070465,
555
+ "logqs/chosen": -0.7749469876289368,
556
+ "logqs/rejected": -0.9290539622306824,
557
+ "logqs_logps/rejected": 0.048794034868478775,
558
+ "loss": 0.2352,
559
+ "step": 490
560
+ },
561
+ {
562
+ "epoch": 0.20062192797672784,
563
+ "grad_norm": 1.0859375,
564
+ "learning_rate": 4.8481647205566245e-05,
565
+ "logps_logqs/chosen": 0.07484981417655945,
566
+ "logqs/chosen": -0.7901949286460876,
567
+ "logqs/rejected": -0.9649750590324402,
568
+ "logqs_logps/rejected": 0.039597224444150925,
569
+ "loss": 0.2426,
570
+ "step": 500
571
+ },
572
+ {
573
+ "epoch": 0.2046343665362624,
574
+ "grad_norm": 1.078125,
575
+ "learning_rate": 4.835912239957884e-05,
576
+ "logps_logqs/chosen": 0.07183913886547089,
577
+ "logqs/chosen": -0.8072341084480286,
578
+ "logqs/rejected": -0.949781596660614,
579
+ "logqs_logps/rejected": 0.04103394225239754,
580
+ "loss": 0.2461,
581
+ "step": 510
582
+ },
583
+ {
584
+ "epoch": 0.20864680509579697,
585
+ "grad_norm": 1.03125,
586
+ "learning_rate": 4.8232011130055145e-05,
587
+ "logps_logqs/chosen": 0.07492522150278091,
588
+ "logqs/chosen": -0.7984409928321838,
589
+ "logqs/rejected": -0.9403228759765625,
590
+ "logqs_logps/rejected": 0.04501514509320259,
591
+ "loss": 0.2399,
592
+ "step": 520
593
+ },
594
+ {
595
+ "epoch": 0.21265924365533154,
596
+ "grad_norm": 0.984375,
597
+ "learning_rate": 4.8100338354747964e-05,
598
+ "logps_logqs/chosen": 0.06418637186288834,
599
+ "logqs/chosen": -0.7536183595657349,
600
+ "logqs/rejected": -0.9021707773208618,
601
+ "logqs_logps/rejected": 0.0469144806265831,
602
+ "loss": 0.2232,
603
+ "step": 530
604
+ },
605
+ {
606
+ "epoch": 0.21667168221486607,
607
+ "grad_norm": 0.98828125,
608
+ "learning_rate": 4.796412992704221e-05,
609
+ "logps_logqs/chosen": 0.07294625043869019,
610
+ "logqs/chosen": -0.817304790019989,
611
+ "logqs/rejected": -1.0015363693237305,
612
+ "logqs_logps/rejected": 0.03600292652845383,
613
+ "loss": 0.2425,
614
+ "step": 540
615
+ },
616
+ {
617
+ "epoch": 0.22068412077440064,
618
+ "grad_norm": 2.171875,
619
+ "learning_rate": 4.7823412590878725e-05,
620
+ "logps_logqs/chosen": 0.06552080065011978,
621
+ "logqs/chosen": -0.757979691028595,
622
+ "logqs/rejected": -0.9391049146652222,
623
+ "logqs_logps/rejected": 0.04227089509367943,
624
+ "loss": 0.2345,
625
+ "step": 550
626
+ },
627
+ {
628
+ "epoch": 0.2246965593339352,
629
+ "grad_norm": 0.94921875,
630
+ "learning_rate": 4.767821397550314e-05,
631
+ "logps_logqs/chosen": 0.07307900488376617,
632
+ "logqs/chosen": -0.7912179231643677,
633
+ "logqs/rejected": -0.9022812843322754,
634
+ "logqs_logps/rejected": 0.04547736793756485,
635
+ "loss": 0.2293,
636
+ "step": 560
637
+ },
638
+ {
639
+ "epoch": 0.22870899789346977,
640
+ "grad_norm": 0.90234375,
641
+ "learning_rate": 4.75285625900411e-05,
642
+ "logps_logqs/chosen": 0.06120596081018448,
643
+ "logqs/chosen": -0.7520848512649536,
644
+ "logqs/rejected": -0.8490988612174988,
645
+ "logqs_logps/rejected": 0.04672159627079964,
646
+ "loss": 0.2196,
647
+ "step": 570
648
+ },
649
+ {
650
+ "epoch": 0.2327214364530043,
651
+ "grad_norm": 0.9140625,
652
+ "learning_rate": 4.7374487817900526e-05,
653
+ "logps_logqs/chosen": 0.07047772407531738,
654
+ "logqs/chosen": -0.7582333087921143,
655
+ "logqs/rejected": -0.9080425500869751,
656
+ "logqs_logps/rejected": 0.043630070984363556,
657
+ "loss": 0.233,
658
+ "step": 580
659
+ },
660
+ {
661
+ "epoch": 0.23673387501253887,
662
+ "grad_norm": 1.0390625,
663
+ "learning_rate": 4.721601991100239e-05,
664
+ "logps_logqs/chosen": 0.07312636077404022,
665
+ "logqs/chosen": -0.8173810839653015,
666
+ "logqs/rejected": -0.9898309707641602,
667
+ "logqs_logps/rejected": 0.038896821439266205,
668
+ "loss": 0.2466,
669
+ "step": 590
670
+ },
671
+ {
672
+ "epoch": 0.24074631357207343,
673
+ "grad_norm": 1.0625,
674
+ "learning_rate": 4.70531899838408e-05,
675
+ "logps_logqs/chosen": 0.08125702291727066,
676
+ "logqs/chosen": -0.815421462059021,
677
+ "logqs/rejected": -0.9149931073188782,
678
+ "logqs_logps/rejected": 0.039436694234609604,
679
+ "loss": 0.2358,
680
+ "step": 600
681
+ },
682
+ {
683
+ "epoch": 0.244758752131608,
684
+ "grad_norm": 0.9765625,
685
+ "learning_rate": 4.688603000737386e-05,
686
+ "logps_logqs/chosen": 0.07415197044610977,
687
+ "logqs/chosen": -0.765034556388855,
688
+ "logqs/rejected": -0.8983548879623413,
689
+ "logqs_logps/rejected": 0.036344725638628006,
690
+ "loss": 0.2262,
691
+ "step": 610
692
+ },
693
+ {
694
+ "epoch": 0.24877119069114254,
695
+ "grad_norm": 1.0078125,
696
+ "learning_rate": 4.67145728027463e-05,
697
+ "logps_logqs/chosen": 0.06661795824766159,
698
+ "logqs/chosen": -0.7819303274154663,
699
+ "logqs/rejected": -0.9227293133735657,
700
+ "logqs_logps/rejected": 0.04116612672805786,
701
+ "loss": 0.2231,
702
+ "step": 620
703
+ },
704
+ {
705
+ "epoch": 0.2527836292506771,
706
+ "grad_norm": 1.34375,
707
+ "learning_rate": 4.653885203484515e-05,
708
+ "logps_logqs/chosen": 0.07415126264095306,
709
+ "logqs/chosen": -0.8002082705497742,
710
+ "logqs/rejected": -0.9249210357666016,
711
+ "logqs_logps/rejected": 0.0376618318259716,
712
+ "loss": 0.2299,
713
+ "step": 630
714
+ },
715
+ {
716
+ "epoch": 0.25679606781021164,
717
+ "grad_norm": 1.0703125,
718
+ "learning_rate": 4.635890220568984e-05,
719
+ "logps_logqs/chosen": 0.07411129772663116,
720
+ "logqs/chosen": -0.7709895372390747,
721
+ "logqs/rejected": -0.9492446780204773,
722
+ "logqs_logps/rejected": 0.036350082606077194,
723
+ "loss": 0.2301,
724
+ "step": 640
725
+ },
726
+ {
727
+ "epoch": 0.26080850636974623,
728
+ "grad_norm": 0.92578125,
729
+ "learning_rate": 4.6174758647657826e-05,
730
+ "logps_logqs/chosen": 0.07068853080272675,
731
+ "logqs/chosen": -0.8123248815536499,
732
+ "logqs/rejected": -0.8981572985649109,
733
+ "logqs_logps/rejected": 0.03915414959192276,
734
+ "loss": 0.2292,
735
+ "step": 650
736
+ },
737
+ {
738
+ "epoch": 0.26482094492928077,
739
+ "grad_norm": 1.03125,
740
+ "learning_rate": 4.598645751654724e-05,
741
+ "logps_logqs/chosen": 0.07326103746891022,
742
+ "logqs/chosen": -0.8222491145133972,
743
+ "logqs/rejected": -0.9678870439529419,
744
+ "logqs_logps/rejected": 0.0360921174287796,
745
+ "loss": 0.2451,
746
+ "step": 660
747
+ },
748
+ {
749
+ "epoch": 0.2688333834888153,
750
+ "grad_norm": 0.98828125,
751
+ "learning_rate": 4.579403578447791e-05,
752
+ "logps_logqs/chosen": 0.06781081855297089,
753
+ "logqs/chosen": -0.7649012804031372,
754
+ "logqs/rejected": -0.870588481426239,
755
+ "logqs_logps/rejected": 0.03709111362695694,
756
+ "loss": 0.2284,
757
+ "step": 670
758
+ },
759
+ {
760
+ "epoch": 0.2728458220483499,
761
+ "grad_norm": 0.921875,
762
+ "learning_rate": 4.559753123263193e-05,
763
+ "logps_logqs/chosen": 0.06727007776498795,
764
+ "logqs/chosen": -0.7720677256584167,
765
+ "logqs/rejected": -0.9267464876174927,
766
+ "logqs_logps/rejected": 0.041538018733263016,
767
+ "loss": 0.232,
768
+ "step": 680
769
+ },
770
+ {
771
+ "epoch": 0.27685826060788443,
772
+ "grad_norm": 0.96484375,
773
+ "learning_rate": 4.53969824438356e-05,
774
+ "logps_logqs/chosen": 0.07148684561252594,
775
+ "logqs/chosen": -0.7559467554092407,
776
+ "logqs/rejected": -0.9380974769592285,
777
+ "logqs_logps/rejected": 0.04005631059408188,
778
+ "loss": 0.2274,
779
+ "step": 690
780
+ },
781
+ {
782
+ "epoch": 0.280870699167419,
783
+ "grad_norm": 1.140625,
784
+ "learning_rate": 4.51924287949838e-05,
785
+ "logps_logqs/chosen": 0.06440640985965729,
786
+ "logqs/chosen": -0.7269574403762817,
787
+ "logqs/rejected": -0.8716470003128052,
788
+ "logqs_logps/rejected": 0.041931308805942535,
789
+ "loss": 0.2209,
790
+ "step": 700
791
+ },
792
+ {
793
+ "epoch": 0.28488313772695356,
794
+ "grad_norm": 0.96484375,
795
+ "learning_rate": 4.49839104493085e-05,
796
+ "logps_logqs/chosen": 0.06912580877542496,
797
+ "logqs/chosen": -0.7862259149551392,
798
+ "logqs/rejected": -0.888696551322937,
799
+ "logqs_logps/rejected": 0.04150567576289177,
800
+ "loss": 0.227,
801
+ "step": 710
802
+ },
803
+ {
804
+ "epoch": 0.2888955762864881,
805
+ "grad_norm": 1.2578125,
806
+ "learning_rate": 4.47714683484929e-05,
807
+ "logps_logqs/chosen": 0.07041208446025848,
808
+ "logqs/chosen": -0.7624860405921936,
809
+ "logqs/rejected": -0.8739960789680481,
810
+ "logqs_logps/rejected": 0.0403289757668972,
811
+ "loss": 0.2293,
812
+ "step": 720
813
+ },
814
+ {
815
+ "epoch": 0.2929080148460227,
816
+ "grad_norm": 1.1953125,
817
+ "learning_rate": 4.455514420463269e-05,
818
+ "logps_logqs/chosen": 0.06653012335300446,
819
+ "logqs/chosen": -0.7875178456306458,
820
+ "logqs/rejected": -0.8743432760238647,
821
+ "logqs_logps/rejected": 0.04233306646347046,
822
+ "loss": 0.2308,
823
+ "step": 730
824
+ },
825
+ {
826
+ "epoch": 0.2969204534055572,
827
+ "grad_norm": 0.90234375,
828
+ "learning_rate": 4.433498049204609e-05,
829
+ "logps_logqs/chosen": 0.06754721701145172,
830
+ "logqs/chosen": -0.7811694741249084,
831
+ "logqs/rejected": -0.9393448829650879,
832
+ "logqs_logps/rejected": 0.04023420438170433,
833
+ "loss": 0.2258,
834
+ "step": 740
835
+ },
836
+ {
837
+ "epoch": 0.30093289196509176,
838
+ "grad_norm": 1.09375,
839
+ "learning_rate": 4.4111020438934153e-05,
840
+ "logps_logqs/chosen": 0.06672672927379608,
841
+ "logqs/chosen": -0.8131230473518372,
842
+ "logqs/rejected": -0.9676214456558228,
843
+ "logqs_logps/rejected": 0.03876449912786484,
844
+ "loss": 0.2357,
845
+ "step": 750
846
+ },
847
+ {
848
+ "epoch": 0.30494533052462636,
849
+ "grad_norm": 1.09375,
850
+ "learning_rate": 4.388330801889314e-05,
851
+ "logps_logqs/chosen": 0.07214461266994476,
852
+ "logqs/chosen": -0.7811805009841919,
853
+ "logqs/rejected": -0.891452968120575,
854
+ "logqs_logps/rejected": 0.047579459846019745,
855
+ "loss": 0.2377,
856
+ "step": 760
857
+ },
858
+ {
859
+ "epoch": 0.3089577690841609,
860
+ "grad_norm": 1.046875,
861
+ "learning_rate": 4.365188794228045e-05,
862
+ "logps_logqs/chosen": 0.06557562947273254,
863
+ "logqs/chosen": -0.7820721864700317,
864
+ "logqs/rejected": -0.924803614616394,
865
+ "logqs_logps/rejected": 0.04372669756412506,
866
+ "loss": 0.2302,
867
+ "step": 770
868
+ },
869
+ {
870
+ "epoch": 0.31297020764369543,
871
+ "grad_norm": 1.015625,
872
+ "learning_rate": 4.341680564743599e-05,
873
+ "logps_logqs/chosen": 0.07139238715171814,
874
+ "logqs/chosen": -0.7355774641036987,
875
+ "logqs/rejected": -0.8488505482673645,
876
+ "logqs_logps/rejected": 0.04906998202204704,
877
+ "loss": 0.2185,
878
+ "step": 780
879
+ },
880
+ {
881
+ "epoch": 0.31698264620323,
882
+ "grad_norm": 1.0859375,
883
+ "learning_rate": 4.317810729176047e-05,
884
+ "logps_logqs/chosen": 0.062024809420108795,
885
+ "logqs/chosen": -0.7930202484130859,
886
+ "logqs/rejected": -0.9120181202888489,
887
+ "logqs_logps/rejected": 0.03688317909836769,
888
+ "loss": 0.2227,
889
+ "step": 790
890
+ },
891
+ {
892
+ "epoch": 0.32099508476276456,
893
+ "grad_norm": 0.97265625,
894
+ "learning_rate": 4.293583974265266e-05,
895
+ "logps_logqs/chosen": 0.06941133737564087,
896
+ "logqs/chosen": -0.7975060939788818,
897
+ "logqs/rejected": -0.8955381512641907,
898
+ "logqs_logps/rejected": 0.039408259093761444,
899
+ "loss": 0.2187,
900
+ "step": 800
901
+ },
902
+ {
903
+ "epoch": 0.32500752332229915,
904
+ "grad_norm": 1.03125,
905
+ "learning_rate": 4.269005056830717e-05,
906
+ "logps_logqs/chosen": 0.07276356965303421,
907
+ "logqs/chosen": -0.7674018740653992,
908
+ "logqs/rejected": -0.9420695304870605,
909
+ "logqs_logps/rejected": 0.039966169744729996,
910
+ "loss": 0.2275,
911
+ "step": 810
912
+ },
913
+ {
914
+ "epoch": 0.3290199618818337,
915
+ "grad_norm": 0.9375,
916
+ "learning_rate": 4.2440788028374624e-05,
917
+ "logps_logqs/chosen": 0.07384312152862549,
918
+ "logqs/chosen": -0.7966219782829285,
919
+ "logqs/rejected": -0.9411764144897461,
920
+ "logqs_logps/rejected": 0.036322906613349915,
921
+ "loss": 0.2367,
922
+ "step": 820
923
+ },
924
+ {
925
+ "epoch": 0.3330324004413682,
926
+ "grad_norm": 1.03125,
927
+ "learning_rate": 4.218810106448606e-05,
928
+ "logps_logqs/chosen": 0.06529523432254791,
929
+ "logqs/chosen": -0.7632766366004944,
930
+ "logqs/rejected": -0.9264775514602661,
931
+ "logqs_logps/rejected": 0.040053799748420715,
932
+ "loss": 0.2152,
933
+ "step": 830
934
+ },
935
+ {
936
+ "epoch": 0.3370448390009028,
937
+ "grad_norm": 1.0234375,
938
+ "learning_rate": 4.193203929064353e-05,
939
+ "logps_logqs/chosen": 0.06620033085346222,
940
+ "logqs/chosen": -0.7850610017776489,
941
+ "logqs/rejected": -0.896354079246521,
942
+ "logqs_logps/rejected": 0.040085501968860626,
943
+ "loss": 0.2181,
944
+ "step": 840
945
+ },
946
+ {
947
+ "epoch": 0.34105727756043736,
948
+ "grad_norm": 0.84375,
949
+ "learning_rate": 4.16726529834785e-05,
950
+ "logps_logqs/chosen": 0.0637274831533432,
951
+ "logqs/chosen": -0.768839955329895,
952
+ "logqs/rejected": -0.9418250918388367,
953
+ "logqs_logps/rejected": 0.03641074150800705,
954
+ "loss": 0.2162,
955
+ "step": 850
956
+ },
957
+ {
958
+ "epoch": 0.3450697161199719,
959
+ "grad_norm": 1.1640625,
960
+ "learning_rate": 4.140999307238033e-05,
961
+ "logps_logqs/chosen": 0.06885053962469101,
962
+ "logqs/chosen": -0.7867051362991333,
963
+ "logqs/rejected": -0.9046538472175598,
964
+ "logqs_logps/rejected": 0.04814887046813965,
965
+ "loss": 0.2268,
966
+ "step": 860
967
+ },
968
+ {
969
+ "epoch": 0.3490821546795065,
970
+ "grad_norm": 1.0234375,
971
+ "learning_rate": 4.114411112949647e-05,
972
+ "logps_logqs/chosen": 0.06477545201778412,
973
+ "logqs/chosen": -0.7621933817863464,
974
+ "logqs/rejected": -0.9573066830635071,
975
+ "logqs_logps/rejected": 0.04498199373483658,
976
+ "loss": 0.2217,
977
+ "step": 870
978
+ },
979
+ {
980
+ "epoch": 0.353094593239041,
981
+ "grad_norm": 0.96484375,
982
+ "learning_rate": 4.08750593596065e-05,
983
+ "logps_logqs/chosen": 0.07505324482917786,
984
+ "logqs/chosen": -0.7968708276748657,
985
+ "logqs/rejected": -0.8728815317153931,
986
+ "logqs_logps/rejected": 0.04394535347819328,
987
+ "loss": 0.2298,
988
+ "step": 880
989
+ },
990
+ {
991
+ "epoch": 0.35710703179857556,
992
+ "grad_norm": 0.9296875,
993
+ "learning_rate": 4.060289058987193e-05,
994
+ "logps_logqs/chosen": 0.0760955736041069,
995
+ "logqs/chosen": -0.7982200384140015,
996
+ "logqs/rejected": -0.9353931546211243,
997
+ "logqs_logps/rejected": 0.04747863858938217,
998
+ "loss": 0.2368,
999
+ "step": 890
1000
+ },
1001
+ {
1002
+ "epoch": 0.36111947035811015,
1003
+ "grad_norm": 1.0703125,
1004
+ "learning_rate": 4.032765825946385e-05,
1005
+ "logps_logqs/chosen": 0.061619557440280914,
1006
+ "logqs/chosen": -0.7349200248718262,
1007
+ "logqs/rejected": -0.8901300430297852,
1008
+ "logqs_logps/rejected": 0.03812010958790779,
1009
+ "loss": 0.2231,
1010
+ "step": 900
1011
+ },
1012
+ {
1013
+ "epoch": 0.3651319089176447,
1014
+ "grad_norm": 0.89453125,
1015
+ "learning_rate": 4.004941640907033e-05,
1016
+ "logps_logqs/chosen": 0.07090075314044952,
1017
+ "logqs/chosen": -0.7767890095710754,
1018
+ "logqs/rejected": -0.881528377532959,
1019
+ "logqs_logps/rejected": 0.04279327765107155,
1020
+ "loss": 0.2177,
1021
+ "step": 910
1022
+ },
1023
+ {
1024
+ "epoch": 0.3691443474771793,
1025
+ "grad_norm": 0.95703125,
1026
+ "learning_rate": 3.97682196702858e-05,
1027
+ "logps_logqs/chosen": 0.07161594927310944,
1028
+ "logqs/chosen": -0.7564586400985718,
1029
+ "logqs/rejected": -0.8816903829574585,
1030
+ "logqs_logps/rejected": 0.045852385461330414,
1031
+ "loss": 0.2223,
1032
+ "step": 920
1033
+ },
1034
+ {
1035
+ "epoch": 0.3731567860367138,
1036
+ "grad_norm": 0.86328125,
1037
+ "learning_rate": 3.9484123254884364e-05,
1038
+ "logps_logqs/chosen": 0.0665770024061203,
1039
+ "logqs/chosen": -0.7706209421157837,
1040
+ "logqs/rejected": -0.9511642456054688,
1041
+ "logqs_logps/rejected": 0.04237721115350723,
1042
+ "loss": 0.223,
1043
+ "step": 930
1044
+ },
1045
+ {
1046
+ "epoch": 0.37716922459624835,
1047
+ "grad_norm": 1.234375,
1048
+ "learning_rate": 3.919718294397917e-05,
1049
+ "logps_logqs/chosen": 0.0625394806265831,
1050
+ "logqs/chosen": -0.7470197677612305,
1051
+ "logqs/rejected": -0.9170467257499695,
1052
+ "logqs_logps/rejected": 0.039193086326122284,
1053
+ "loss": 0.2152,
1054
+ "step": 940
1055
+ },
1056
+ {
1057
+ "epoch": 0.38118166315578295,
1058
+ "grad_norm": 1.0234375,
1059
+ "learning_rate": 3.890745507707009e-05,
1060
+ "logps_logqs/chosen": 0.07387630641460419,
1061
+ "logqs/chosen": -0.8002737760543823,
1062
+ "logqs/rejected": -0.9207932353019714,
1063
+ "logqs_logps/rejected": 0.042600203305482864,
1064
+ "loss": 0.2218,
1065
+ "step": 950
1066
+ },
1067
+ {
1068
+ "epoch": 0.3851941017153175,
1069
+ "grad_norm": 0.921875,
1070
+ "learning_rate": 3.861499654098164e-05,
1071
+ "logps_logqs/chosen": 0.06455671042203903,
1072
+ "logqs/chosen": -0.7371721267700195,
1073
+ "logqs/rejected": -0.9134686589241028,
1074
+ "logqs_logps/rejected": 0.04233291745185852,
1075
+ "loss": 0.2122,
1076
+ "step": 960
1077
+ },
1078
+ {
1079
+ "epoch": 0.389206540274852,
1080
+ "grad_norm": 0.953125,
1081
+ "learning_rate": 3.831986475869354e-05,
1082
+ "logps_logqs/chosen": 0.06445468217134476,
1083
+ "logqs/chosen": -0.8044613599777222,
1084
+ "logqs/rejected": -1.0282663106918335,
1085
+ "logqs_logps/rejected": 0.038126152008771896,
1086
+ "loss": 0.224,
1087
+ "step": 970
1088
+ },
1089
+ {
1090
+ "epoch": 0.3932189788343866,
1091
+ "grad_norm": 1.03125,
1092
+ "learning_rate": 3.802211767806592e-05,
1093
+ "logps_logqs/chosen": 0.06315324455499649,
1094
+ "logqs/chosen": -0.755436897277832,
1095
+ "logqs/rejected": -0.892535388469696,
1096
+ "logqs_logps/rejected": 0.03698495030403137,
1097
+ "loss": 0.21,
1098
+ "step": 980
1099
+ },
1100
+ {
1101
+ "epoch": 0.39723141739392115,
1102
+ "grad_norm": 1.0078125,
1103
+ "learning_rate": 3.772181376046154e-05,
1104
+ "logps_logqs/chosen": 0.06318236142396927,
1105
+ "logqs/chosen": -0.779813289642334,
1106
+ "logqs/rejected": -0.9424177408218384,
1107
+ "logqs_logps/rejected": 0.04168635606765747,
1108
+ "loss": 0.2229,
1109
+ "step": 990
1110
+ },
1111
+ {
1112
+ "epoch": 0.4012438559534557,
1113
+ "grad_norm": 0.91015625,
1114
+ "learning_rate": 3.741901196926715e-05,
1115
+ "logps_logqs/chosen": 0.06805428117513657,
1116
+ "logqs/chosen": -0.7568292021751404,
1117
+ "logqs/rejected": -0.9653108716011047,
1118
+ "logqs_logps/rejected": 0.048825882375240326,
1119
+ "loss": 0.2281,
1120
+ "step": 1000
1121
+ },
1122
+ {
1123
+ "epoch": 0.4052562945129903,
1124
+ "grad_norm": 0.9609375,
1125
+ "learning_rate": 3.711377175831626e-05,
1126
+ "logps_logqs/chosen": 0.06242173910140991,
1127
+ "logqs/chosen": -0.7545310258865356,
1128
+ "logqs/rejected": -0.8632828593254089,
1129
+ "logqs_logps/rejected": 0.04335509240627289,
1130
+ "loss": 0.2093,
1131
+ "step": 1010
1132
+ },
1133
+ {
1134
+ "epoch": 0.4092687330725248,
1135
+ "grad_norm": 1.0078125,
1136
+ "learning_rate": 3.6806153060215625e-05,
1137
+ "logps_logqs/chosen": 0.06218956038355827,
1138
+ "logqs/chosen": -0.7818590402603149,
1139
+ "logqs/rejected": -0.9333481788635254,
1140
+ "logqs_logps/rejected": 0.04040559381246567,
1141
+ "loss": 0.2171,
1142
+ "step": 1020
1143
+ },
1144
+ {
1145
+ "epoch": 0.4132811716320594,
1146
+ "grad_norm": 0.84765625,
1147
+ "learning_rate": 3.649621627457779e-05,
1148
+ "logps_logqs/chosen": 0.06417541205883026,
1149
+ "logqs/chosen": -0.756496787071228,
1150
+ "logqs/rejected": -0.8772870898246765,
1151
+ "logqs_logps/rejected": 0.044820256531238556,
1152
+ "loss": 0.2066,
1153
+ "step": 1030
1154
+ },
1155
+ {
1156
+ "epoch": 0.41729361019159394,
1157
+ "grad_norm": 0.90625,
1158
+ "learning_rate": 3.618402225616182e-05,
1159
+ "logps_logqs/chosen": 0.06157483905553818,
1160
+ "logqs/chosen": -0.7702164649963379,
1161
+ "logqs/rejected": -0.8873571157455444,
1162
+ "logqs_logps/rejected": 0.040025461465120316,
1163
+ "loss": 0.2119,
1164
+ "step": 1040
1165
+ },
1166
+ {
1167
+ "epoch": 0.4213060487511285,
1168
+ "grad_norm": 1.015625,
1169
+ "learning_rate": 3.586963230292478e-05,
1170
+ "logps_logqs/chosen": 0.06648336350917816,
1171
+ "logqs/chosen": -0.7476903200149536,
1172
+ "logqs/rejected": -0.9481046795845032,
1173
+ "logqs_logps/rejected": 0.040808893740177155,
1174
+ "loss": 0.2153,
1175
+ "step": 1050
1176
+ },
1177
+ {
1178
+ "epoch": 0.4253184873106631,
1179
+ "grad_norm": 0.86328125,
1180
+ "learning_rate": 3.5553108143986106e-05,
1181
+ "logps_logqs/chosen": 0.06893102824687958,
1182
+ "logqs/chosen": -0.8103592991828918,
1183
+ "logqs/rejected": -0.959617018699646,
1184
+ "logqs_logps/rejected": 0.03886875510215759,
1185
+ "loss": 0.2252,
1186
+ "step": 1060
1187
+ },
1188
+ {
1189
+ "epoch": 0.4293309258701976,
1190
+ "grad_norm": 0.94140625,
1191
+ "learning_rate": 3.5234511927507386e-05,
1192
+ "logps_logqs/chosen": 0.06997676193714142,
1193
+ "logqs/chosen": -0.7442790269851685,
1194
+ "logqs/rejected": -0.8467389941215515,
1195
+ "logqs_logps/rejected": 0.0434083454310894,
1196
+ "loss": 0.2061,
1197
+ "step": 1070
1198
+ },
1199
+ {
1200
+ "epoch": 0.43334336442973215,
1201
+ "grad_norm": 1.0078125,
1202
+ "learning_rate": 3.4913906208489816e-05,
1203
+ "logps_logqs/chosen": 0.06593279540538788,
1204
+ "logqs/chosen": -0.794285237789154,
1205
+ "logqs/rejected": -0.942711353302002,
1206
+ "logqs_logps/rejected": 0.03897419571876526,
1207
+ "loss": 0.2152,
1208
+ "step": 1080
1209
+ },
1210
+ {
1211
+ "epoch": 0.43735580298926674,
1212
+ "grad_norm": 0.90234375,
1213
+ "learning_rate": 3.4591353936491804e-05,
1214
+ "logps_logqs/chosen": 0.06674528867006302,
1215
+ "logqs/chosen": -0.7946367263793945,
1216
+ "logqs/rejected": -0.8623877763748169,
1217
+ "logqs_logps/rejected": 0.04701145738363266,
1218
+ "loss": 0.2179,
1219
+ "step": 1090
1220
+ },
1221
+ {
1222
+ "epoch": 0.4413682415488013,
1223
+ "grad_norm": 0.984375,
1224
+ "learning_rate": 3.4266918443269083e-05,
1225
+ "logps_logqs/chosen": 0.07212932407855988,
1226
+ "logqs/chosen": -0.8063435554504395,
1227
+ "logqs/rejected": -0.9033867716789246,
1228
+ "logqs_logps/rejected": 0.0527394600212574,
1229
+ "loss": 0.229,
1230
+ "step": 1100
1231
+ },
1232
+ {
1233
+ "epoch": 0.4453806801083358,
1234
+ "grad_norm": 0.94921875,
1235
+ "learning_rate": 3.3940663430339816e-05,
1236
+ "logps_logqs/chosen": 0.0656530112028122,
1237
+ "logqs/chosen": -0.7609381675720215,
1238
+ "logqs/rejected": -0.8543895483016968,
1239
+ "logqs_logps/rejected": 0.04062092304229736,
1240
+ "loss": 0.2046,
1241
+ "step": 1110
1242
+ },
1243
+ {
1244
+ "epoch": 0.4493931186678704,
1245
+ "grad_norm": 0.87890625,
1246
+ "learning_rate": 3.361265295647703e-05,
1247
+ "logps_logqs/chosen": 0.0694454088807106,
1248
+ "logqs/chosen": -0.7907551527023315,
1249
+ "logqs/rejected": -0.9830646514892578,
1250
+ "logqs_logps/rejected": 0.04873238503932953,
1251
+ "loss": 0.229,
1252
+ "step": 1120
1253
+ },
1254
+ {
1255
+ "epoch": 0.45340555722740494,
1256
+ "grad_norm": 0.94140625,
1257
+ "learning_rate": 3.328295142513101e-05,
1258
+ "logps_logqs/chosen": 0.06491965055465698,
1259
+ "logqs/chosen": -0.7659338712692261,
1260
+ "logqs/rejected": -0.858781635761261,
1261
+ "logqs_logps/rejected": 0.04801768809556961,
1262
+ "loss": 0.2131,
1263
+ "step": 1130
1264
+ },
1265
+ {
1266
+ "epoch": 0.45741799578693954,
1267
+ "grad_norm": 0.96484375,
1268
+ "learning_rate": 3.295162357178392e-05,
1269
+ "logps_logqs/chosen": 0.06826496124267578,
1270
+ "logqs/chosen": -0.7904923558235168,
1271
+ "logqs/rejected": -0.9123312830924988,
1272
+ "logqs_logps/rejected": 0.0476931631565094,
1273
+ "loss": 0.2244,
1274
+ "step": 1140
1275
+ },
1276
+ {
1277
+ "epoch": 0.46143043434647407,
1278
+ "grad_norm": 0.91796875,
1279
+ "learning_rate": 3.2618734451239265e-05,
1280
+ "logps_logqs/chosen": 0.066849485039711,
1281
+ "logqs/chosen": -0.7713029980659485,
1282
+ "logqs/rejected": -0.8515326380729675,
1283
+ "logqs_logps/rejected": 0.037967417389154434,
1284
+ "loss": 0.2025,
1285
+ "step": 1150
1286
+ },
1287
+ {
1288
+ "epoch": 0.4654428729060086,
1289
+ "grad_norm": 1.0546875,
1290
+ "learning_rate": 3.2284349424848686e-05,
1291
+ "logps_logqs/chosen": 0.061885617673397064,
1292
+ "logqs/chosen": -0.7651118636131287,
1293
+ "logqs/rejected": -0.9462388753890991,
1294
+ "logqs_logps/rejected": 0.04066777601838112,
1295
+ "loss": 0.2073,
1296
+ "step": 1160
1297
+ },
1298
+ {
1299
+ "epoch": 0.4694553114655432,
1300
+ "grad_norm": 0.8515625,
1301
+ "learning_rate": 3.19485341476785e-05,
1302
+ "logps_logqs/chosen": 0.06695061177015305,
1303
+ "logqs/chosen": -0.7339809536933899,
1304
+ "logqs/rejected": -0.8749481439590454,
1305
+ "logqs_logps/rejected": 0.04051825404167175,
1306
+ "loss": 0.2124,
1307
+ "step": 1170
1308
+ },
1309
+ {
1310
+ "epoch": 0.47346775002507774,
1311
+ "grad_norm": 0.94921875,
1312
+ "learning_rate": 3.161135455561867e-05,
1313
+ "logps_logqs/chosen": 0.05254195258021355,
1314
+ "logqs/chosen": -0.7602388262748718,
1315
+ "logqs/rejected": -0.9050895571708679,
1316
+ "logqs_logps/rejected": 0.041042499244213104,
1317
+ "loss": 0.2066,
1318
+ "step": 1180
1319
+ },
1320
+ {
1321
+ "epoch": 0.4774801885846123,
1322
+ "grad_norm": 0.95703125,
1323
+ "learning_rate": 3.127287685243649e-05,
1324
+ "logps_logqs/chosen": 0.0691223293542862,
1325
+ "logqs/chosen": -0.767509400844574,
1326
+ "logqs/rejected": -0.9097784161567688,
1327
+ "logqs_logps/rejected": 0.04124459624290466,
1328
+ "loss": 0.2114,
1329
+ "step": 1190
1330
+ },
1331
+ {
1332
+ "epoch": 0.48149262714414687,
1333
+ "grad_norm": 0.984375,
1334
+ "learning_rate": 3.093316749677788e-05,
1335
+ "logps_logqs/chosen": 0.07016964256763458,
1336
+ "logqs/chosen": -0.8034747242927551,
1337
+ "logqs/rejected": -0.9332574605941772,
1338
+ "logqs_logps/rejected": 0.04192311316728592,
1339
+ "loss": 0.2191,
1340
+ "step": 1200
1341
+ },
1342
+ {
1343
+ "epoch": 0.4855050657036814,
1344
+ "grad_norm": 1.0078125,
1345
+ "learning_rate": 3.059229318911834e-05,
1346
+ "logps_logqs/chosen": 0.06674963980913162,
1347
+ "logqs/chosen": -0.8160765767097473,
1348
+ "logqs/rejected": -0.9725866317749023,
1349
+ "logqs_logps/rejected": 0.036663301289081573,
1350
+ "loss": 0.2146,
1351
+ "step": 1210
1352
+ },
1353
+ {
1354
+ "epoch": 0.489517504263216,
1355
+ "grad_norm": 0.859375,
1356
+ "learning_rate": 3.0250320858666808e-05,
1357
+ "logps_logqs/chosen": 0.05871901661157608,
1358
+ "logqs/chosen": -0.7368924617767334,
1359
+ "logqs/rejected": -0.9339553713798523,
1360
+ "logqs_logps/rejected": 0.0406537726521492,
1361
+ "loss": 0.203,
1362
+ "step": 1220
1363
+ },
1364
+ {
1365
+ "epoch": 0.49352994282275053,
1366
+ "grad_norm": 0.80859375,
1367
+ "learning_rate": 2.9907317650224202e-05,
1368
+ "logps_logqs/chosen": 0.06281201541423798,
1369
+ "logqs/chosen": -0.7343816757202148,
1370
+ "logqs/rejected": -0.832353949546814,
1371
+ "logqs_logps/rejected": 0.04407534375786781,
1372
+ "loss": 0.2028,
1373
+ "step": 1230
1374
+ },
1375
+ {
1376
+ "epoch": 0.49754238138228507,
1377
+ "grad_norm": 0.88671875,
1378
+ "learning_rate": 2.9563350910999987e-05,
1379
+ "logps_logqs/chosen": 0.06290856003761292,
1380
+ "logqs/chosen": -0.767212986946106,
1381
+ "logqs/rejected": -0.8938047289848328,
1382
+ "logqs_logps/rejected": 0.04681697487831116,
1383
+ "loss": 0.208,
1384
+ "step": 1240
1385
+ },
1386
+ {
1387
+ "epoch": 0.5015548199418196,
1388
+ "grad_norm": 0.87890625,
1389
+ "learning_rate": 2.9218488177388708e-05,
1390
+ "logps_logqs/chosen": 0.05903799459338188,
1391
+ "logqs/chosen": -0.764884352684021,
1392
+ "logqs/rejected": -0.980311393737793,
1393
+ "logqs_logps/rejected": 0.03830552473664284,
1394
+ "loss": 0.2067,
1395
+ "step": 1250
1396
+ },
1397
+ {
1398
+ "epoch": 0.5055672585013542,
1399
+ "grad_norm": 1.0078125,
1400
+ "learning_rate": 2.8872797161709592e-05,
1401
+ "logps_logqs/chosen": 0.0676959678530693,
1402
+ "logqs/chosen": -0.8294798135757446,
1403
+ "logqs/rejected": -1.0086824893951416,
1404
+ "logqs_logps/rejected": 0.04707977548241615,
1405
+ "loss": 0.2281,
1406
+ "step": 1260
1407
+ },
1408
+ {
1409
+ "epoch": 0.5095796970608888,
1410
+ "grad_norm": 0.91796875,
1411
+ "learning_rate": 2.8526345738911514e-05,
1412
+ "logps_logqs/chosen": 0.06489823758602142,
1413
+ "logqs/chosen": -0.7817304730415344,
1414
+ "logqs/rejected": -0.964560866355896,
1415
+ "logqs_logps/rejected": 0.033502064645290375,
1416
+ "loss": 0.2112,
1417
+ "step": 1270
1418
+ },
1419
+ {
1420
+ "epoch": 0.5135921356204233,
1421
+ "grad_norm": 1.0625,
1422
+ "learning_rate": 2.817920193324598e-05,
1423
+ "logps_logqs/chosen": 0.06510399281978607,
1424
+ "logqs/chosen": -0.7938090562820435,
1425
+ "logqs/rejected": -0.9560580253601074,
1426
+ "logqs_logps/rejected": 0.036699842661619186,
1427
+ "loss": 0.2083,
1428
+ "step": 1280
1429
+ },
1430
+ {
1431
+ "epoch": 0.5176045741799579,
1432
+ "grad_norm": 0.91015625,
1433
+ "learning_rate": 2.7831433904910966e-05,
1434
+ "logps_logqs/chosen": 0.06948190927505493,
1435
+ "logqs/chosen": -0.786105751991272,
1436
+ "logqs/rejected": -1.0199264287948608,
1437
+ "logqs_logps/rejected": 0.04138697311282158,
1438
+ "loss": 0.2193,
1439
+ "step": 1290
1440
+ },
1441
+ {
1442
+ "epoch": 0.5216170127394925,
1443
+ "grad_norm": 0.921875,
1444
+ "learning_rate": 2.7483109936667833e-05,
1445
+ "logps_logqs/chosen": 0.05654798075556755,
1446
+ "logqs/chosen": -0.7541887164115906,
1447
+ "logqs/rejected": -0.9388119578361511,
1448
+ "logqs_logps/rejected": 0.0368928536772728,
1449
+ "loss": 0.206,
1450
+ "step": 1300
1451
+ },
1452
+ {
1453
+ "epoch": 0.5256294512990269,
1454
+ "grad_norm": 0.75390625,
1455
+ "learning_rate": 2.7134298420434405e-05,
1456
+ "logps_logqs/chosen": 0.06768162548542023,
1457
+ "logqs/chosen": -0.751132607460022,
1458
+ "logqs/rejected": -0.9309018850326538,
1459
+ "logqs_logps/rejected": 0.040372543036937714,
1460
+ "loss": 0.2047,
1461
+ "step": 1310
1462
+ },
1463
+ {
1464
+ "epoch": 0.5296418898585615,
1465
+ "grad_norm": 0.90234375,
1466
+ "learning_rate": 2.6785067843856437e-05,
1467
+ "logps_logqs/chosen": 0.0685514509677887,
1468
+ "logqs/chosen": -0.7638227343559265,
1469
+ "logqs/rejected": -0.9002357721328735,
1470
+ "logqs_logps/rejected": 0.04437505453824997,
1471
+ "loss": 0.208,
1472
+ "step": 1320
1473
+ },
1474
+ {
1475
+ "epoch": 0.5336543284180961,
1476
+ "grad_norm": 0.88671875,
1477
+ "learning_rate": 2.6435486776860397e-05,
1478
+ "logps_logqs/chosen": 0.06796412169933319,
1479
+ "logqs/chosen": -0.7779960632324219,
1480
+ "logqs/rejected": -0.8985629081726074,
1481
+ "logqs_logps/rejected": 0.04421251639723778,
1482
+ "loss": 0.2105,
1483
+ "step": 1330
1484
+ },
1485
+ {
1486
+ "epoch": 0.5376667669776306,
1487
+ "grad_norm": 1.03125,
1488
+ "learning_rate": 2.608562385819004e-05,
1489
+ "logps_logqs/chosen": 0.07138559222221375,
1490
+ "logqs/chosen": -0.7967632412910461,
1491
+ "logqs/rejected": -0.961688220500946,
1492
+ "logqs_logps/rejected": 0.04707226902246475,
1493
+ "loss": 0.2143,
1494
+ "step": 1340
1495
+ },
1496
+ {
1497
+ "epoch": 0.5416792055371652,
1498
+ "grad_norm": 0.8671875,
1499
+ "learning_rate": 2.5735547781929486e-05,
1500
+ "logps_logqs/chosen": 0.06736733019351959,
1501
+ "logqs/chosen": -0.786482036113739,
1502
+ "logqs/rejected": -0.9260354042053223,
1503
+ "logqs_logps/rejected": 0.040234483778476715,
1504
+ "loss": 0.2095,
1505
+ "step": 1350
1506
+ },
1507
+ {
1508
+ "epoch": 0.5456916440966998,
1509
+ "grad_norm": 1.0546875,
1510
+ "learning_rate": 2.5385327284015442e-05,
1511
+ "logps_logqs/chosen": 0.05687067657709122,
1512
+ "logqs/chosen": -0.7579948902130127,
1513
+ "logqs/rejected": -0.8798167109489441,
1514
+ "logqs_logps/rejected": 0.04075098782777786,
1515
+ "loss": 0.211,
1516
+ "step": 1360
1517
+ },
1518
+ {
1519
+ "epoch": 0.5497040826562343,
1520
+ "grad_norm": 0.7734375,
1521
+ "learning_rate": 2.5035031128741186e-05,
1522
+ "logps_logqs/chosen": 0.054413218051195145,
1523
+ "logqs/chosen": -0.7419102191925049,
1524
+ "logqs/rejected": -0.9421182870864868,
1525
+ "logqs_logps/rejected": 0.04363472759723663,
1526
+ "loss": 0.1988,
1527
+ "step": 1370
1528
+ },
1529
+ {
1530
+ "epoch": 0.5537165212157689,
1531
+ "grad_norm": 0.99609375,
1532
+ "learning_rate": 2.468472809525499e-05,
1533
+ "logps_logqs/chosen": 0.0663304477930069,
1534
+ "logqs/chosen": -0.7536656856536865,
1535
+ "logqs/rejected": -0.8601825833320618,
1536
+ "logqs_logps/rejected": 0.04670237749814987,
1537
+ "loss": 0.2015,
1538
+ "step": 1380
1539
+ },
1540
+ {
1541
+ "epoch": 0.5577289597753035,
1542
+ "grad_norm": 1.0546875,
1543
+ "learning_rate": 2.433448696405563e-05,
1544
+ "logps_logqs/chosen": 0.0683605819940567,
1545
+ "logqs/chosen": -0.7921854853630066,
1546
+ "logqs/rejected": -0.9560282826423645,
1547
+ "logqs_logps/rejected": 0.04194676876068115,
1548
+ "loss": 0.2153,
1549
+ "step": 1390
1550
+ },
1551
+ {
1552
+ "epoch": 0.561741398334838,
1553
+ "grad_norm": 0.875,
1554
+ "learning_rate": 2.3984376503487657e-05,
1555
+ "logps_logqs/chosen": 0.059657491743564606,
1556
+ "logqs/chosen": -0.7732149362564087,
1557
+ "logqs/rejected": -0.9037120938301086,
1558
+ "logqs_logps/rejected": 0.047056883573532104,
1559
+ "loss": 0.2059,
1560
+ "step": 1400
1561
+ },
1562
+ {
1563
+ "epoch": 0.5657538368943725,
1564
+ "grad_norm": 1.1015625,
1565
+ "learning_rate": 2.363446545623896e-05,
1566
+ "logps_logqs/chosen": 0.06571358442306519,
1567
+ "logqs/chosen": -0.7903417348861694,
1568
+ "logqs/rejected": -0.8886157870292664,
1569
+ "logqs_logps/rejected": 0.044423289597034454,
1570
+ "loss": 0.2137,
1571
+ "step": 1410
1572
+ },
1573
+ {
1574
+ "epoch": 0.5697662754539071,
1575
+ "grad_norm": 0.7734375,
1576
+ "learning_rate": 2.3284822525843513e-05,
1577
+ "logps_logqs/chosen": 0.06020021438598633,
1578
+ "logqs/chosen": -0.774948239326477,
1579
+ "logqs/rejected": -0.8824418783187866,
1580
+ "logqs_logps/rejected": 0.047613807022571564,
1581
+ "loss": 0.2102,
1582
+ "step": 1420
1583
+ },
1584
+ {
1585
+ "epoch": 0.5737787140134417,
1586
+ "grad_norm": 0.93359375,
1587
+ "learning_rate": 2.2935516363191693e-05,
1588
+ "logps_logqs/chosen": 0.05629735440015793,
1589
+ "logqs/chosen": -0.7801834940910339,
1590
+ "logqs/rejected": -0.9769400358200073,
1591
+ "logqs_logps/rejected": 0.04005488008260727,
1592
+ "loss": 0.1992,
1593
+ "step": 1430
1594
+ },
1595
+ {
1596
+ "epoch": 0.5777911525729762,
1597
+ "grad_norm": 0.9765625,
1598
+ "learning_rate": 2.2586615553050958e-05,
1599
+ "logps_logqs/chosen": 0.06125611066818237,
1600
+ "logqs/chosen": -0.7764580845832825,
1601
+ "logqs/rejected": -0.9078529477119446,
1602
+ "logqs_logps/rejected": 0.047422997653484344,
1603
+ "loss": 0.2102,
1604
+ "step": 1440
1605
+ },
1606
+ {
1607
+ "epoch": 0.5818035911325108,
1608
+ "grad_norm": 1.0390625,
1609
+ "learning_rate": 2.2238188600599557e-05,
1610
+ "logps_logqs/chosen": 0.06047336012125015,
1611
+ "logqs/chosen": -0.7722862958908081,
1612
+ "logqs/rejected": -0.9338611364364624,
1613
+ "logqs_logps/rejected": 0.04897394776344299,
1614
+ "loss": 0.2118,
1615
+ "step": 1450
1616
+ },
1617
+ {
1618
+ "epoch": 0.5858160296920454,
1619
+ "grad_norm": 0.8046875,
1620
+ "learning_rate": 2.1890303917975793e-05,
1621
+ "logps_logqs/chosen": 0.06230146437883377,
1622
+ "logqs/chosen": -0.7600993514060974,
1623
+ "logqs/rejected": -0.894098162651062,
1624
+ "logqs_logps/rejected": 0.04384886845946312,
1625
+ "loss": 0.2098,
1626
+ "step": 1460
1627
+ },
1628
+ {
1629
+ "epoch": 0.5898284682515799,
1630
+ "grad_norm": 1.0703125,
1631
+ "learning_rate": 2.1543029810845636e-05,
1632
+ "logps_logqs/chosen": 0.0581694059073925,
1633
+ "logqs/chosen": -0.7508013248443604,
1634
+ "logqs/rejected": -0.8761455416679382,
1635
+ "logqs_logps/rejected": 0.047836847603321075,
1636
+ "loss": 0.2022,
1637
+ "step": 1470
1638
+ },
1639
+ {
1640
+ "epoch": 0.5938409068111145,
1641
+ "grad_norm": 0.9609375,
1642
+ "learning_rate": 2.1196434464991143e-05,
1643
+ "logps_logqs/chosen": 0.0635426789522171,
1644
+ "logqs/chosen": -0.729708731174469,
1645
+ "logqs/rejected": -0.9138385653495789,
1646
+ "logqs_logps/rejected": 0.04027016833424568,
1647
+ "loss": 0.2025,
1648
+ "step": 1480
1649
+ },
1650
+ {
1651
+ "epoch": 0.597853345370649,
1652
+ "grad_norm": 0.86328125,
1653
+ "learning_rate": 2.085058593292254e-05,
1654
+ "logps_logqs/chosen": 0.06386588513851166,
1655
+ "logqs/chosen": -0.7314515709877014,
1656
+ "logqs/rejected": -0.920465350151062,
1657
+ "logqs_logps/rejected": 0.044058460742235184,
1658
+ "loss": 0.201,
1659
+ "step": 1490
1660
+ },
1661
+ {
1662
+ "epoch": 0.6018657839301835,
1663
+ "grad_norm": 0.953125,
1664
+ "learning_rate": 2.0505552120516347e-05,
1665
+ "logps_logqs/chosen": 0.059891510754823685,
1666
+ "logqs/chosen": -0.772852897644043,
1667
+ "logqs/rejected": -0.9922389984130859,
1668
+ "logqs_logps/rejected": 0.038037288933992386,
1669
+ "loss": 0.2087,
1670
+ "step": 1500
1671
+ },
1672
+ {
1673
+ "epoch": 0.6058782224897181,
1674
+ "grad_norm": 0.97265625,
1675
+ "learning_rate": 2.0161400773682387e-05,
1676
+ "logps_logqs/chosen": 0.06451881676912308,
1677
+ "logqs/chosen": -0.7392505407333374,
1678
+ "logqs/rejected": -0.8385832905769348,
1679
+ "logqs_logps/rejected": 0.04175102710723877,
1680
+ "loss": 0.1949,
1681
+ "step": 1510
1682
+ },
1683
+ {
1684
+ "epoch": 0.6098906610492527,
1685
+ "grad_norm": 0.82421875,
1686
+ "learning_rate": 1.9818199465062122e-05,
1687
+ "logps_logqs/chosen": 0.057556964457035065,
1688
+ "logqs/chosen": -0.7747632265090942,
1689
+ "logqs/rejected": -0.9425610303878784,
1690
+ "logqs_logps/rejected": 0.04500174522399902,
1691
+ "loss": 0.1981,
1692
+ "step": 1520
1693
+ },
1694
+ {
1695
+ "epoch": 0.6139030996087872,
1696
+ "grad_norm": 0.953125,
1697
+ "learning_rate": 1.947601558076112e-05,
1698
+ "logps_logqs/chosen": 0.06366400420665741,
1699
+ "logqs/chosen": -0.7735481262207031,
1700
+ "logqs/rejected": -0.9604089856147766,
1701
+ "logqs_logps/rejected": 0.03997362032532692,
1702
+ "loss": 0.2085,
1703
+ "step": 1530
1704
+ },
1705
+ {
1706
+ "epoch": 0.6179155381683218,
1707
+ "grad_norm": 0.8359375,
1708
+ "learning_rate": 1.913491630711803e-05,
1709
+ "logps_logqs/chosen": 0.059332527220249176,
1710
+ "logqs/chosen": -0.7706314921379089,
1711
+ "logqs/rejected": -0.9478508234024048,
1712
+ "logqs_logps/rejected": 0.04246944189071655,
1713
+ "loss": 0.2092,
1714
+ "step": 1540
1715
+ },
1716
+ {
1717
+ "epoch": 0.6219279767278564,
1718
+ "grad_norm": 1.015625,
1719
+ "learning_rate": 1.8794968617512827e-05,
1720
+ "logps_logqs/chosen": 0.059884555637836456,
1721
+ "logqs/chosen": -0.7863162755966187,
1722
+ "logqs/rejected": -0.9061921238899231,
1723
+ "logqs_logps/rejected": 0.040217991918325424,
1724
+ "loss": 0.2126,
1725
+ "step": 1550
1726
+ },
1727
+ {
1728
+ "epoch": 0.6259404152873909,
1729
+ "grad_norm": 0.97265625,
1730
+ "learning_rate": 1.8456239259216935e-05,
1731
+ "logps_logqs/chosen": 0.06425374746322632,
1732
+ "logqs/chosen": -0.8034299612045288,
1733
+ "logqs/rejected": -0.9601300358772278,
1734
+ "logqs_logps/rejected": 0.041518889367580414,
1735
+ "loss": 0.208,
1736
+ "step": 1560
1737
+ },
1738
+ {
1739
+ "epoch": 0.6299528538469255,
1740
+ "grad_norm": 0.90234375,
1741
+ "learning_rate": 1.8118794740287626e-05,
1742
+ "logps_logqs/chosen": 0.06399701535701752,
1743
+ "logqs/chosen": -0.7407925724983215,
1744
+ "logqs/rejected": -0.9087139964103699,
1745
+ "logqs_logps/rejected": 0.04571211710572243,
1746
+ "loss": 0.2112,
1747
+ "step": 1570
1748
+ },
1749
+ {
1750
+ "epoch": 0.63396529240646,
1751
+ "grad_norm": 0.91015625,
1752
+ "learning_rate": 1.778270131650948e-05,
1753
+ "logps_logqs/chosen": 0.0619058683514595,
1754
+ "logqs/chosen": -0.7647662162780762,
1755
+ "logqs/rejected": -0.8764744997024536,
1756
+ "logqs_logps/rejected": 0.047727279365062714,
1757
+ "loss": 0.2061,
1758
+ "step": 1580
1759
+ },
1760
+ {
1761
+ "epoch": 0.6379777309659946,
1762
+ "grad_norm": 0.78515625,
1763
+ "learning_rate": 1.7448024978385323e-05,
1764
+ "logps_logqs/chosen": 0.05647442862391472,
1765
+ "logqs/chosen": -0.6957526803016663,
1766
+ "logqs/rejected": -0.862210750579834,
1767
+ "logqs_logps/rejected": 0.04325004667043686,
1768
+ "loss": 0.1936,
1769
+ "step": 1590
1770
+ },
1771
+ {
1772
+ "epoch": 0.6419901695255291,
1773
+ "grad_norm": 0.828125,
1774
+ "learning_rate": 1.7114831438179304e-05,
1775
+ "logps_logqs/chosen": 0.05817713588476181,
1776
+ "logqs/chosen": -0.8131221532821655,
1777
+ "logqs/rejected": -0.9595745801925659,
1778
+ "logqs_logps/rejected": 0.04276737570762634,
1779
+ "loss": 0.2054,
1780
+ "step": 1600
1781
+ },
1782
+ {
1783
+ "epoch": 0.6460026080850637,
1784
+ "grad_norm": 1.125,
1785
+ "learning_rate": 1.678318611701456e-05,
1786
+ "logps_logqs/chosen": 0.059329450130462646,
1787
+ "logqs/chosen": -0.7848485708236694,
1788
+ "logqs/rejected": -0.9603179693222046,
1789
+ "logqs_logps/rejected": 0.04404183477163315,
1790
+ "loss": 0.2073,
1791
+ "step": 1610
1792
+ },
1793
+ {
1794
+ "epoch": 0.6500150466445983,
1795
+ "grad_norm": 0.875,
1796
+ "learning_rate": 1.6453154132028036e-05,
1797
+ "logps_logqs/chosen": 0.06459563970565796,
1798
+ "logqs/chosen": -0.7197882533073425,
1799
+ "logqs/rejected": -0.8624848127365112,
1800
+ "logqs_logps/rejected": 0.04526801407337189,
1801
+ "loss": 0.1997,
1802
+ "step": 1620
1803
+ },
1804
+ {
1805
+ "epoch": 0.6540274852041328,
1806
+ "grad_norm": 1.0,
1807
+ "learning_rate": 1.6124800283585047e-05,
1808
+ "logps_logqs/chosen": 0.06266516447067261,
1809
+ "logqs/chosen": -0.7793084383010864,
1810
+ "logqs/rejected": -0.9734363555908203,
1811
+ "logqs_logps/rejected": 0.03937797620892525,
1812
+ "loss": 0.2166,
1813
+ "step": 1630
1814
+ },
1815
+ {
1816
+ "epoch": 0.6580399237636674,
1817
+ "grad_norm": 1.015625,
1818
+ "learning_rate": 1.5798189042556e-05,
1819
+ "logps_logqs/chosen": 0.06362553685903549,
1820
+ "logqs/chosen": -0.8266116976737976,
1821
+ "logqs/rejected": -0.9903604388237,
1822
+ "logqs_logps/rejected": 0.044061560183763504,
1823
+ "loss": 0.2128,
1824
+ "step": 1640
1825
+ },
1826
+ {
1827
+ "epoch": 0.662052362323202,
1828
+ "grad_norm": 0.8984375,
1829
+ "learning_rate": 1.547338453765781e-05,
1830
+ "logps_logqs/chosen": 0.06749062240123749,
1831
+ "logqs/chosen": -0.7770861983299255,
1832
+ "logqs/rejected": -0.9624859094619751,
1833
+ "logqs_logps/rejected": 0.0393180288374424,
1834
+ "loss": 0.203,
1835
+ "step": 1650
1836
+ },
1837
+ {
1838
+ "epoch": 0.6660648008827365,
1839
+ "grad_norm": 1.03125,
1840
+ "learning_rate": 1.5150450542862465e-05,
1841
+ "logps_logqs/chosen": 0.05758975073695183,
1842
+ "logqs/chosen": -0.7523698806762695,
1843
+ "logqs/rejected": -0.8969352841377258,
1844
+ "logqs_logps/rejected": 0.040392350405454636,
1845
+ "loss": 0.2035,
1846
+ "step": 1660
1847
+ },
1848
+ {
1849
+ "epoch": 0.670077239442271,
1850
+ "grad_norm": 1.1484375,
1851
+ "learning_rate": 1.482945046487535e-05,
1852
+ "logps_logqs/chosen": 0.061460964381694794,
1853
+ "logqs/chosen": -0.770228385925293,
1854
+ "logqs/rejected": -0.9278268814086914,
1855
+ "logqs_logps/rejected": 0.04707395285367966,
1856
+ "loss": 0.2084,
1857
+ "step": 1670
1858
+ },
1859
+ {
1860
+ "epoch": 0.6740896780018056,
1861
+ "grad_norm": 0.79296875,
1862
+ "learning_rate": 1.4510447330685572e-05,
1863
+ "logps_logqs/chosen": 0.061688266694545746,
1864
+ "logqs/chosen": -0.7408064603805542,
1865
+ "logqs/rejected": -0.8874767422676086,
1866
+ "logqs_logps/rejected": 0.04055311530828476,
1867
+ "loss": 0.1933,
1868
+ "step": 1680
1869
+ },
1870
+ {
1871
+ "epoch": 0.6781021165613401,
1872
+ "grad_norm": 0.84765625,
1873
+ "learning_rate": 1.4193503775190869e-05,
1874
+ "logps_logqs/chosen": 0.06273935735225677,
1875
+ "logqs/chosen": -0.7087291479110718,
1876
+ "logqs/rejected": -0.9201680421829224,
1877
+ "logqs_logps/rejected": 0.04273274913430214,
1878
+ "loss": 0.1981,
1879
+ "step": 1690
1880
+ },
1881
+ {
1882
+ "epoch": 0.6821145551208747,
1883
+ "grad_norm": 0.859375,
1884
+ "learning_rate": 1.3878682028899542e-05,
1885
+ "logps_logqs/chosen": 0.05558650940656662,
1886
+ "logqs/chosen": -0.759759783744812,
1887
+ "logqs/rejected": -0.9058607220649719,
1888
+ "logqs_logps/rejected": 0.04389805346727371,
1889
+ "loss": 0.1978,
1890
+ "step": 1700
1891
+ },
1892
+ {
1893
+ "epoch": 0.6861269936804093,
1894
+ "grad_norm": 0.84375,
1895
+ "learning_rate": 1.3566043905711739e-05,
1896
+ "logps_logqs/chosen": 0.06162220984697342,
1897
+ "logqs/chosen": -0.7727446556091309,
1898
+ "logqs/rejected": -0.8560484647750854,
1899
+ "logqs_logps/rejected": 0.046323083341121674,
1900
+ "loss": 0.1981,
1901
+ "step": 1710
1902
+ },
1903
+ {
1904
+ "epoch": 0.6901394322399438,
1905
+ "grad_norm": 0.98828125,
1906
+ "learning_rate": 1.3255650790782593e-05,
1907
+ "logps_logqs/chosen": 0.06615598499774933,
1908
+ "logqs/chosen": -0.7760972380638123,
1909
+ "logqs/rejected": -0.9352099299430847,
1910
+ "logqs_logps/rejected": 0.036824874579906464,
1911
+ "loss": 0.2053,
1912
+ "step": 1720
1913
+ },
1914
+ {
1915
+ "epoch": 0.6941518707994784,
1916
+ "grad_norm": 1.078125,
1917
+ "learning_rate": 1.2947563628469487e-05,
1918
+ "logps_logqs/chosen": 0.06651194393634796,
1919
+ "logqs/chosen": -0.7634227871894836,
1920
+ "logqs/rejected": -0.8523470759391785,
1921
+ "logqs_logps/rejected": 0.0407404787838459,
1922
+ "loss": 0.201,
1923
+ "step": 1730
1924
+ },
1925
+ {
1926
+ "epoch": 0.698164309359013,
1927
+ "grad_norm": 0.9375,
1928
+ "learning_rate": 1.2641842910365882e-05,
1929
+ "logps_logqs/chosen": 0.06568791717290878,
1930
+ "logqs/chosen": -0.7720048427581787,
1931
+ "logqs/rejected": -0.8878447413444519,
1932
+ "logqs_logps/rejected": 0.04862860590219498,
1933
+ "loss": 0.2112,
1934
+ "step": 1740
1935
+ },
1936
+ {
1937
+ "epoch": 0.7021767479185475,
1938
+ "grad_norm": 0.84375,
1939
+ "learning_rate": 1.2338548663424063e-05,
1940
+ "logps_logqs/chosen": 0.06173808500170708,
1941
+ "logqs/chosen": -0.7485703229904175,
1942
+ "logqs/rejected": -0.9079939126968384,
1943
+ "logqs_logps/rejected": 0.039516132324934006,
1944
+ "loss": 0.1972,
1945
+ "step": 1750
1946
+ },
1947
+ {
1948
+ "epoch": 0.706189186478082,
1949
+ "grad_norm": 0.828125,
1950
+ "learning_rate": 1.2037740438169118e-05,
1951
+ "logps_logqs/chosen": 0.05886746197938919,
1952
+ "logqs/chosen": -0.7420176267623901,
1953
+ "logqs/rejected": -0.86164790391922,
1954
+ "logqs_logps/rejected": 0.04042860120534897,
1955
+ "loss": 0.1986,
1956
+ "step": 1760
1957
+ },
1958
+ {
1959
+ "epoch": 0.7102016250376166,
1960
+ "grad_norm": 0.89453125,
1961
+ "learning_rate": 1.173947729700644e-05,
1962
+ "logps_logqs/chosen": 0.06122485548257828,
1963
+ "logqs/chosen": -0.7482978701591492,
1964
+ "logqs/rejected": -0.8508716821670532,
1965
+ "logqs_logps/rejected": 0.04005607217550278,
1966
+ "loss": 0.2006,
1967
+ "step": 1770
1968
+ },
1969
+ {
1970
+ "epoch": 0.7142140635971511,
1971
+ "grad_norm": 0.9296875,
1972
+ "learning_rate": 1.1443817802625045e-05,
1973
+ "logps_logqs/chosen": 0.06048593670129776,
1974
+ "logqs/chosen": -0.7596639394760132,
1975
+ "logqs/rejected": -0.943291187286377,
1976
+ "logqs_logps/rejected": 0.03989649564027786,
1977
+ "loss": 0.1975,
1978
+ "step": 1780
1979
+ },
1980
+ {
1981
+ "epoch": 0.7182265021566857,
1982
+ "grad_norm": 0.828125,
1983
+ "learning_rate": 1.1150820006499102e-05,
1984
+ "logps_logqs/chosen": 0.06095385551452637,
1985
+ "logqs/chosen": -0.8086657524108887,
1986
+ "logqs/rejected": -0.9322345852851868,
1987
+ "logqs_logps/rejected": 0.03858863189816475,
1988
+ "loss": 0.2043,
1989
+ "step": 1790
1990
+ },
1991
+ {
1992
+ "epoch": 0.7222389407162203,
1993
+ "grad_norm": 0.8984375,
1994
+ "learning_rate": 1.0860541437489704e-05,
1995
+ "logps_logqs/chosen": 0.06901264935731888,
1996
+ "logqs/chosen": -0.796691358089447,
1997
+ "logqs/rejected": -0.9594961404800415,
1998
+ "logqs_logps/rejected": 0.04785243421792984,
1999
+ "loss": 0.2166,
2000
+ "step": 1800
2001
+ },
2002
+ {
2003
+ "epoch": 0.7262513792757549,
2004
+ "grad_norm": 0.7890625,
2005
+ "learning_rate": 1.0573039090549374e-05,
2006
+ "logps_logqs/chosen": 0.06223682314157486,
2007
+ "logqs/chosen": -0.7634943723678589,
2008
+ "logqs/rejected": -0.9174191355705261,
2009
+ "logqs_logps/rejected": 0.03920085355639458,
2010
+ "loss": 0.1951,
2011
+ "step": 1810
2012
+ },
2013
+ {
2014
+ "epoch": 0.7302638178352894,
2015
+ "grad_norm": 0.94921875,
2016
+ "learning_rate": 1.0288369415531335e-05,
2017
+ "logps_logqs/chosen": 0.0662630945444107,
2018
+ "logqs/chosen": -0.7865787148475647,
2019
+ "logqs/rejected": -0.9215148091316223,
2020
+ "logqs_logps/rejected": 0.04244377464056015,
2021
+ "loss": 0.2054,
2022
+ "step": 1820
2023
+ },
2024
+ {
2025
+ "epoch": 0.734276256394824,
2026
+ "grad_norm": 0.890625,
2027
+ "learning_rate": 1.0006588306105832e-05,
2028
+ "logps_logqs/chosen": 0.0686667412519455,
2029
+ "logqs/chosen": -0.8002827763557434,
2030
+ "logqs/rejected": -0.9347888827323914,
2031
+ "logqs_logps/rejected": 0.046215157955884933,
2032
+ "loss": 0.2087,
2033
+ "step": 1830
2034
+ },
2035
+ {
2036
+ "epoch": 0.7382886949543586,
2037
+ "grad_norm": 0.84765625,
2038
+ "learning_rate": 9.727751088785622e-06,
2039
+ "logps_logqs/chosen": 0.06760746985673904,
2040
+ "logqs/chosen": -0.7690545320510864,
2041
+ "logqs/rejected": -0.9443781971931458,
2042
+ "logqs_logps/rejected": 0.038559213280677795,
2043
+ "loss": 0.2029,
2044
+ "step": 1840
2045
+ },
2046
+ {
2047
+ "epoch": 0.742301133513893,
2048
+ "grad_norm": 0.88671875,
2049
+ "learning_rate": 9.451912512062863e-06,
2050
+ "logps_logqs/chosen": 0.06737495958805084,
2051
+ "logqs/chosen": -0.7588866949081421,
2052
+ "logqs/rejected": -0.8812012672424316,
2053
+ "logqs_logps/rejected": 0.04380820319056511,
2054
+ "loss": 0.2055,
2055
+ "step": 1850
2056
+ },
2057
+ {
2058
+ "epoch": 0.7463135720734276,
2059
+ "grad_norm": 0.92578125,
2060
+ "learning_rate": 9.179126735659513e-06,
2061
+ "logps_logqs/chosen": 0.06551609933376312,
2062
+ "logqs/chosen": -0.7602046728134155,
2063
+ "logqs/rejected": -0.8694095611572266,
2064
+ "logqs_logps/rejected": 0.042011164128780365,
2065
+ "loss": 0.2,
2066
+ "step": 1860
2067
+ },
2068
+ {
2069
+ "epoch": 0.7503260106329622,
2070
+ "grad_norm": 0.87109375,
2071
+ "learning_rate": 8.909447319893268e-06,
2072
+ "logps_logqs/chosen": 0.06104401499032974,
2073
+ "logqs/chosen": -0.7819545865058899,
2074
+ "logqs/rejected": -0.9451535940170288,
2075
+ "logqs_logps/rejected": 0.042893193662166595,
2076
+ "loss": 0.2034,
2077
+ "step": 1870
2078
+ },
2079
+ {
2080
+ "epoch": 0.7543384491924967,
2081
+ "grad_norm": 0.828125,
2082
+ "learning_rate": 8.642927215161221e-06,
2083
+ "logps_logqs/chosen": 0.05745772644877434,
2084
+ "logqs/chosen": -0.7933343648910522,
2085
+ "logqs/rejected": -0.9668875932693481,
2086
+ "logqs_logps/rejected": 0.042098429054021835,
2087
+ "loss": 0.2053,
2088
+ "step": 1880
2089
+ },
2090
+ {
2091
+ "epoch": 0.7583508877520313,
2092
+ "grad_norm": 0.77734375,
2093
+ "learning_rate": 8.379618751543275e-06,
2094
+ "logps_logqs/chosen": 0.06059462949633598,
2095
+ "logqs/chosen": -0.7289972305297852,
2096
+ "logqs/rejected": -0.8890076875686646,
2097
+ "logqs_logps/rejected": 0.043808337301015854,
2098
+ "loss": 0.1994,
2099
+ "step": 1890
2100
+ },
2101
+ {
2102
+ "epoch": 0.7623633263115659,
2103
+ "grad_norm": 0.86328125,
2104
+ "learning_rate": 8.119573628527406e-06,
2105
+ "logps_logqs/chosen": 0.06398828327655792,
2106
+ "logqs/chosen": -0.7545658349990845,
2107
+ "logqs/rejected": -0.8651827573776245,
2108
+ "logqs_logps/rejected": 0.04523858055472374,
2109
+ "loss": 0.207,
2110
+ "step": 1900
2111
+ },
2112
+ {
2113
+ "epoch": 0.7663757648711004,
2114
+ "grad_norm": 0.8125,
2115
+ "learning_rate": 7.862842904858633e-06,
2116
+ "logps_logqs/chosen": 0.05899987369775772,
2117
+ "logqs/chosen": -0.7348795533180237,
2118
+ "logqs/rejected": -0.9609573483467102,
2119
+ "logqs_logps/rejected": 0.03890888765454292,
2120
+ "loss": 0.199,
2121
+ "step": 1910
2122
+ },
2123
+ {
2124
+ "epoch": 0.770388203430635,
2125
+ "grad_norm": 0.88671875,
2126
+ "learning_rate": 7.609476988513875e-06,
2127
+ "logps_logqs/chosen": 0.06505165994167328,
2128
+ "logqs/chosen": -0.7714970707893372,
2129
+ "logqs/rejected": -0.8944205045700073,
2130
+ "logqs_logps/rejected": 0.042544566094875336,
2131
+ "loss": 0.2085,
2132
+ "step": 1920
2133
+ },
2134
+ {
2135
+ "epoch": 0.7744006419901696,
2136
+ "grad_norm": 0.828125,
2137
+ "learning_rate": 7.359525626804545e-06,
2138
+ "logps_logqs/chosen": 0.06677477806806564,
2139
+ "logqs/chosen": -0.7985670566558838,
2140
+ "logqs/rejected": -0.9588406682014465,
2141
+ "logqs_logps/rejected": 0.03549560531973839,
2142
+ "loss": 0.2021,
2143
+ "step": 1930
2144
+ },
2145
+ {
2146
+ "epoch": 0.778413080549704,
2147
+ "grad_norm": 0.83984375,
2148
+ "learning_rate": 7.113037896608923e-06,
2149
+ "logps_logqs/chosen": 0.05854114890098572,
2150
+ "logqs/chosen": -0.7753890752792358,
2151
+ "logqs/rejected": -0.9235790371894836,
2152
+ "logqs_logps/rejected": 0.04000157117843628,
2153
+ "loss": 0.1948,
2154
+ "step": 1940
2155
+ },
2156
+ {
2157
+ "epoch": 0.7824255191092386,
2158
+ "grad_norm": 0.984375,
2159
+ "learning_rate": 6.870062194736057e-06,
2160
+ "logps_logqs/chosen": 0.06045924499630928,
2161
+ "logqs/chosen": -0.8043012619018555,
2162
+ "logqs/rejected": -0.9698446989059448,
2163
+ "logqs_logps/rejected": 0.042726777493953705,
2164
+ "loss": 0.2069,
2165
+ "step": 1950
2166
+ },
2167
+ {
2168
+ "epoch": 0.7864379576687732,
2169
+ "grad_norm": 0.99609375,
2170
+ "learning_rate": 6.6306462284233234e-06,
2171
+ "logps_logqs/chosen": 0.05968203395605087,
2172
+ "logqs/chosen": -0.7555102705955505,
2173
+ "logqs/rejected": -0.9313309788703918,
2174
+ "logqs_logps/rejected": 0.04395302012562752,
2175
+ "loss": 0.1983,
2176
+ "step": 1960
2177
+ },
2178
+ {
2179
+ "epoch": 0.7904503962283077,
2180
+ "grad_norm": 0.890625,
2181
+ "learning_rate": 6.394837005969251e-06,
2182
+ "logps_logqs/chosen": 0.054263245314359665,
2183
+ "logqs/chosen": -0.7649015188217163,
2184
+ "logqs/rejected": -0.9770067930221558,
2185
+ "logqs_logps/rejected": 0.039296168833971024,
2186
+ "loss": 0.1991,
2187
+ "step": 1970
2188
+ },
2189
+ {
2190
+ "epoch": 0.7944628347878423,
2191
+ "grad_norm": 0.9140625,
2192
+ "learning_rate": 6.162680827503705e-06,
2193
+ "logps_logqs/chosen": 0.06627397239208221,
2194
+ "logqs/chosen": -0.759872317314148,
2195
+ "logqs/rejected": -0.9354902505874634,
2196
+ "logqs_logps/rejected": 0.04396883398294449,
2197
+ "loss": 0.205,
2198
+ "step": 1980
2199
+ },
2200
+ {
2201
+ "epoch": 0.7984752733473769,
2202
+ "grad_norm": 0.75390625,
2203
+ "learning_rate": 5.934223275897e-06,
2204
+ "logps_logqs/chosen": 0.05789231136441231,
2205
+ "logqs/chosen": -0.7570023536682129,
2206
+ "logqs/rejected": -0.9084933996200562,
2207
+ "logqs_logps/rejected": 0.034562643617391586,
2208
+ "loss": 0.1977,
2209
+ "step": 1990
2210
+ },
2211
+ {
2212
+ "epoch": 0.8024877119069114,
2213
+ "grad_norm": 0.9921875,
2214
+ "learning_rate": 5.709509207809946e-06,
2215
+ "logps_logqs/chosen": 0.05983500927686691,
2216
+ "logqs/chosen": -0.7238153219223022,
2217
+ "logqs/rejected": -0.8950502276420593,
2218
+ "logqs_logps/rejected": 0.043728940188884735,
2219
+ "loss": 0.204,
2220
+ "step": 2000
2221
+ },
2222
+ {
2223
+ "epoch": 0.806500150466446,
2224
+ "grad_norm": 0.7734375,
2225
+ "learning_rate": 5.4885827448863865e-06,
2226
+ "logps_logqs/chosen": 0.06219662353396416,
2227
+ "logqs/chosen": -0.7557579278945923,
2228
+ "logqs/rejected": -0.9043906927108765,
2229
+ "logqs_logps/rejected": 0.04098309203982353,
2230
+ "loss": 0.2037,
2231
+ "step": 2010
2232
+ },
2233
+ {
2234
+ "epoch": 0.8105125890259806,
2235
+ "grad_norm": 1.0078125,
2236
+ "learning_rate": 5.271487265090163e-06,
2237
+ "logps_logqs/chosen": 0.06002221629023552,
2238
+ "logqs/chosen": -0.7607712149620056,
2239
+ "logqs/rejected": -0.9396473169326782,
2240
+ "logqs_logps/rejected": 0.04222804307937622,
2241
+ "loss": 0.2034,
2242
+ "step": 2020
2243
+ },
2244
+ {
2245
+ "epoch": 0.8145250275855151,
2246
+ "grad_norm": 1.046875,
2247
+ "learning_rate": 5.058265394187969e-06,
2248
+ "logps_logqs/chosen": 0.06274767965078354,
2249
+ "logqs/chosen": -0.7671214938163757,
2250
+ "logqs/rejected": -0.9004543423652649,
2251
+ "logqs_logps/rejected": 0.046913545578718185,
2252
+ "loss": 0.2041,
2253
+ "step": 2030
2254
+ },
2255
+ {
2256
+ "epoch": 0.8185374661450496,
2257
+ "grad_norm": 1.0546875,
2258
+ "learning_rate": 4.848958997380035e-06,
2259
+ "logps_logqs/chosen": 0.06094413250684738,
2260
+ "logqs/chosen": -0.7989168167114258,
2261
+ "logqs/rejected": -0.9816246032714844,
2262
+ "logqs_logps/rejected": 0.042406968772411346,
2263
+ "loss": 0.2054,
2264
+ "step": 2040
2265
+ },
2266
+ {
2267
+ "epoch": 0.8225499047045842,
2268
+ "grad_norm": 0.67578125,
2269
+ "learning_rate": 4.643609171080002e-06,
2270
+ "logps_logqs/chosen": 0.05818860977888107,
2271
+ "logqs/chosen": -0.7579581141471863,
2272
+ "logqs/rejected": -0.9492076635360718,
2273
+ "logqs_logps/rejected": 0.041138358414173126,
2274
+ "loss": 0.1991,
2275
+ "step": 2050
2276
+ },
2277
+ {
2278
+ "epoch": 0.8265623432641188,
2279
+ "grad_norm": 0.84375,
2280
+ "learning_rate": 4.44225623484589e-06,
2281
+ "logps_logqs/chosen": 0.061229269951581955,
2282
+ "logqs/chosen": -0.7763658761978149,
2283
+ "logqs/rejected": -0.9214930534362793,
2284
+ "logqs_logps/rejected": 0.04326833412051201,
2285
+ "loss": 0.2105,
2286
+ "step": 2060
2287
+ },
2288
+ {
2289
+ "epoch": 0.8305747818236533,
2290
+ "grad_norm": 0.9609375,
2291
+ "learning_rate": 4.244939723463468e-06,
2292
+ "logps_logqs/chosen": 0.061605095863342285,
2293
+ "logqs/chosen": -0.7827211022377014,
2294
+ "logqs/rejected": -1.016422152519226,
2295
+ "logqs_logps/rejected": 0.04850704222917557,
2296
+ "loss": 0.2028,
2297
+ "step": 2070
2298
+ },
2299
+ {
2300
+ "epoch": 0.8345872203831879,
2301
+ "grad_norm": 1.0546875,
2302
+ "learning_rate": 4.051698379183791e-06,
2303
+ "logps_logqs/chosen": 0.059653230011463165,
2304
+ "logqs/chosen": -0.7364221811294556,
2305
+ "logqs/rejected": -0.9126985669136047,
2306
+ "logqs_logps/rejected": 0.04395602270960808,
2307
+ "loss": 0.2077,
2308
+ "step": 2080
2309
+ },
2310
+ {
2311
+ "epoch": 0.8385996589427225,
2312
+ "grad_norm": 0.875,
2313
+ "learning_rate": 3.862570144116334e-06,
2314
+ "logps_logqs/chosen": 0.06163454055786133,
2315
+ "logqs/chosen": -0.7645280361175537,
2316
+ "logqs/rejected": -1.0081186294555664,
2317
+ "logqs_logps/rejected": 0.04180619865655899,
2318
+ "loss": 0.202,
2319
+ "step": 2090
2320
+ },
2321
+ {
2322
+ "epoch": 0.842612097502257,
2323
+ "grad_norm": 0.9375,
2324
+ "learning_rate": 3.677592152779216e-06,
2325
+ "logps_logqs/chosen": 0.060922086238861084,
2326
+ "logqs/chosen": -0.7481504082679749,
2327
+ "logqs/rejected": -0.900185227394104,
2328
+ "logqs_logps/rejected": 0.04749513044953346,
2329
+ "loss": 0.2071,
2330
+ "step": 2100
2331
+ },
2332
+ {
2333
+ "epoch": 0.8466245360617916,
2334
+ "grad_norm": 0.97265625,
2335
+ "learning_rate": 3.4968007248079777e-06,
2336
+ "logps_logqs/chosen": 0.06403280794620514,
2337
+ "logqs/chosen": -0.7176480293273926,
2338
+ "logqs/rejected": -0.8989812731742859,
2339
+ "logqs_logps/rejected": 0.04769695922732353,
2340
+ "loss": 0.2051,
2341
+ "step": 2110
2342
+ },
2343
+ {
2344
+ "epoch": 0.8506369746213261,
2345
+ "grad_norm": 0.8828125,
2346
+ "learning_rate": 3.3202313578243995e-06,
2347
+ "logps_logqs/chosen": 0.05457407236099243,
2348
+ "logqs/chosen": -0.7609150409698486,
2349
+ "logqs/rejected": -0.9247547388076782,
2350
+ "logqs_logps/rejected": 0.04001811891794205,
2351
+ "loss": 0.202,
2352
+ "step": 2120
2353
+ },
2354
+ {
2355
+ "epoch": 0.8546494131808606,
2356
+ "grad_norm": 1.046875,
2357
+ "learning_rate": 3.1479187204666886e-06,
2358
+ "logps_logqs/chosen": 0.05928390100598335,
2359
+ "logqs/chosen": -0.764100193977356,
2360
+ "logqs/rejected": -0.9366759061813354,
2361
+ "logqs_logps/rejected": 0.03913865610957146,
2362
+ "loss": 0.2027,
2363
+ "step": 2130
2364
+ },
2365
+ {
2366
+ "epoch": 0.8586618517403952,
2367
+ "grad_norm": 0.90234375,
2368
+ "learning_rate": 2.9798966455824474e-06,
2369
+ "logps_logqs/chosen": 0.06238958239555359,
2370
+ "logqs/chosen": -0.7486379742622375,
2371
+ "logqs/rejected": -0.9404671788215637,
2372
+ "logqs_logps/rejected": 0.04445621743798256,
2373
+ "loss": 0.2009,
2374
+ "step": 2140
2375
+ },
2376
+ {
2377
+ "epoch": 0.8626742902999298,
2378
+ "grad_norm": 0.90625,
2379
+ "learning_rate": 2.8161981235857143e-06,
2380
+ "logps_logqs/chosen": 0.05766347795724869,
2381
+ "logqs/chosen": -0.8047393560409546,
2382
+ "logqs/rejected": -0.9559482336044312,
2383
+ "logqs_logps/rejected": 0.043215952813625336,
2384
+ "loss": 0.202,
2385
+ "step": 2150
2386
+ },
2387
+ {
2388
+ "epoch": 0.8666867288594643,
2389
+ "grad_norm": 0.8984375,
2390
+ "learning_rate": 2.656855295979463e-06,
2391
+ "logps_logqs/chosen": 0.06472580134868622,
2392
+ "logqs/chosen": -0.737873911857605,
2393
+ "logqs/rejected": -0.8887351751327515,
2394
+ "logqs_logps/rejected": 0.043567948043346405,
2395
+ "loss": 0.2042,
2396
+ "step": 2160
2397
+ },
2398
+ {
2399
+ "epoch": 0.8706991674189989,
2400
+ "grad_norm": 1.0234375,
2401
+ "learning_rate": 2.5018994490447506e-06,
2402
+ "logps_logqs/chosen": 0.06504198163747787,
2403
+ "logqs/chosen": -0.7585901618003845,
2404
+ "logqs/rejected": -0.93121337890625,
2405
+ "logqs_logps/rejected": 0.048323631286621094,
2406
+ "loss": 0.2037,
2407
+ "step": 2170
2408
+ },
2409
+ {
2410
+ "epoch": 0.8747116059785335,
2411
+ "grad_norm": 0.9375,
2412
+ "learning_rate": 2.3513610076977914e-06,
2413
+ "logps_logqs/chosen": 0.05999793857336044,
2414
+ "logqs/chosen": -0.7390618920326233,
2415
+ "logqs/rejected": -0.9315282702445984,
2416
+ "logqs_logps/rejected": 0.04710640385746956,
2417
+ "loss": 0.2065,
2418
+ "step": 2180
2419
+ },
2420
+ {
2421
+ "epoch": 0.878724044538068,
2422
+ "grad_norm": 1.0546875,
2423
+ "learning_rate": 2.2052695295161406e-06,
2424
+ "logps_logqs/chosen": 0.06420952826738358,
2425
+ "logqs/chosen": -0.7469607591629028,
2426
+ "logqs/rejected": -0.8542912602424622,
2427
+ "logqs_logps/rejected": 0.04820626974105835,
2428
+ "loss": 0.2034,
2429
+ "step": 2190
2430
+ },
2431
+ {
2432
+ "epoch": 0.8827364830976026,
2433
+ "grad_norm": 0.87890625,
2434
+ "learning_rate": 2.0636536989351974e-06,
2435
+ "logps_logqs/chosen": 0.06679137796163559,
2436
+ "logqs/chosen": -0.7580717206001282,
2437
+ "logqs/rejected": -0.8642162084579468,
2438
+ "logqs_logps/rejected": 0.042508114129304886,
2439
+ "loss": 0.2008,
2440
+ "step": 2200
2441
+ },
2442
+ {
2443
+ "epoch": 0.8867489216571371,
2444
+ "grad_norm": 0.91015625,
2445
+ "learning_rate": 1.9265413216161597e-06,
2446
+ "logps_logqs/chosen": 0.06721115857362747,
2447
+ "logqs/chosen": -0.7631017565727234,
2448
+ "logqs/rejected": -0.9131069183349609,
2449
+ "logqs_logps/rejected": 0.04944468289613724,
2450
+ "loss": 0.2065,
2451
+ "step": 2210
2452
+ },
2453
+ {
2454
+ "epoch": 0.8907613602166716,
2455
+ "grad_norm": 0.83984375,
2456
+ "learning_rate": 1.7939593189864795e-06,
2457
+ "logps_logqs/chosen": 0.061406660825014114,
2458
+ "logqs/chosen": -0.7838734984397888,
2459
+ "logqs/rejected": -0.9089409708976746,
2460
+ "logqs_logps/rejected": 0.04142575338482857,
2461
+ "loss": 0.1987,
2462
+ "step": 2220
2463
+ },
2464
+ {
2465
+ "epoch": 0.8947737987762062,
2466
+ "grad_norm": 0.96484375,
2467
+ "learning_rate": 1.6659337229539524e-06,
2468
+ "logps_logqs/chosen": 0.0574992373585701,
2469
+ "logqs/chosen": -0.74857097864151,
2470
+ "logqs/rejected": -0.9218307733535767,
2471
+ "logqs_logps/rejected": 0.045242272317409515,
2472
+ "loss": 0.2061,
2473
+ "step": 2230
2474
+ },
2475
+ {
2476
+ "epoch": 0.8987862373357408,
2477
+ "grad_norm": 0.953125,
2478
+ "learning_rate": 1.5424896707954773e-06,
2479
+ "logps_logqs/chosen": 0.06686152517795563,
2480
+ "logqs/chosen": -0.8112009167671204,
2481
+ "logqs/rejected": -0.9499409794807434,
2482
+ "logqs_logps/rejected": 0.04503064230084419,
2483
+ "loss": 0.2133,
2484
+ "step": 2240
2485
+ },
2486
+ {
2487
+ "epoch": 0.9027986758952754,
2488
+ "grad_norm": 0.87109375,
2489
+ "learning_rate": 1.4236514002214651e-06,
2490
+ "logps_logqs/chosen": 0.06498394906520844,
2491
+ "logqs/chosen": -0.7638250589370728,
2492
+ "logqs/rejected": -0.8727086782455444,
2493
+ "logqs_logps/rejected": 0.047809042036533356,
2494
+ "loss": 0.2039,
2495
+ "step": 2250
2496
+ },
2497
+ {
2498
+ "epoch": 0.9068111144548099,
2499
+ "grad_norm": 0.8359375,
2500
+ "learning_rate": 1.3094422446168404e-06,
2501
+ "logps_logqs/chosen": 0.05696554109454155,
2502
+ "logqs/chosen": -0.7111738920211792,
2503
+ "logqs/rejected": -0.8518338203430176,
2504
+ "logqs_logps/rejected": 0.044544972479343414,
2505
+ "loss": 0.1983,
2506
+ "step": 2260
2507
+ },
2508
+ {
2509
+ "epoch": 0.9108235530143445,
2510
+ "grad_norm": 0.81640625,
2511
+ "learning_rate": 1.1998846284596688e-06,
2512
+ "logps_logqs/chosen": 0.061489515006542206,
2513
+ "logqs/chosen": -0.7231674194335938,
2514
+ "logqs/rejected": -0.8351476788520813,
2515
+ "logqs_logps/rejected": 0.04788647219538689,
2516
+ "loss": 0.1983,
2517
+ "step": 2270
2518
+ },
2519
+ {
2520
+ "epoch": 0.9148359915738791,
2521
+ "grad_norm": 0.78515625,
2522
+ "learning_rate": 1.0950000629181807e-06,
2523
+ "logps_logqs/chosen": 0.04939153045415878,
2524
+ "logqs/chosen": -0.7786750197410583,
2525
+ "logqs/rejected": -0.8713645935058594,
2526
+ "logqs_logps/rejected": 0.04320090264081955,
2527
+ "loss": 0.2081,
2528
+ "step": 2280
2529
+ },
2530
+ {
2531
+ "epoch": 0.9188484301334136,
2532
+ "grad_norm": 0.953125,
2533
+ "learning_rate": 9.948091416271483e-07,
2534
+ "logps_logqs/chosen": 0.0662379264831543,
2535
+ "logqs/chosen": -0.8300337791442871,
2536
+ "logqs/rejected": -0.9588104486465454,
2537
+ "logqs_logps/rejected": 0.04326099902391434,
2538
+ "loss": 0.2103,
2539
+ "step": 2290
2540
+ },
2541
+ {
2542
+ "epoch": 0.9228608686929481,
2543
+ "grad_norm": 0.79296875,
2544
+ "learning_rate": 8.99331536644421e-07,
2545
+ "logps_logqs/chosen": 0.05675070732831955,
2546
+ "logqs/chosen": -0.7419881224632263,
2547
+ "logqs/rejected": -0.9318987727165222,
2548
+ "logqs_logps/rejected": 0.04274313896894455,
2549
+ "loss": 0.2006,
2550
+ "step": 2300
2551
+ },
2552
+ {
2553
+ "epoch": 0.9268733072524827,
2554
+ "grad_norm": 1.0703125,
2555
+ "learning_rate": 8.085859945883983e-07,
2556
+ "logps_logqs/chosen": 0.05921543762087822,
2557
+ "logqs/chosen": -0.7391059994697571,
2558
+ "logqs/rejected": -0.8634150624275208,
2559
+ "logqs_logps/rejected": 0.04096318036317825,
2560
+ "loss": 0.2,
2561
+ "step": 2310
2562
+ },
2563
+ {
2564
+ "epoch": 0.9308857458120172,
2565
+ "grad_norm": 0.8125,
2566
+ "learning_rate": 7.225903329572181e-07,
2567
+ "logps_logqs/chosen": 0.06639240682125092,
2568
+ "logqs/chosen": -0.7444113492965698,
2569
+ "logqs/rejected": -0.8740445971488953,
2570
+ "logqs_logps/rejected": 0.046740248799324036,
2571
+ "loss": 0.1993,
2572
+ "step": 2320
2573
+ },
2574
+ {
2575
+ "epoch": 0.9348981843715518,
2576
+ "grad_norm": 1.078125,
2577
+ "learning_rate": 6.413614366303472e-07,
2578
+ "logps_logqs/chosen": 0.06109191104769707,
2579
+ "logqs/chosen": -0.7488638162612915,
2580
+ "logqs/rejected": -0.9097427129745483,
2581
+ "logqs_logps/rejected": 0.04230613261461258,
2582
+ "loss": 0.206,
2583
+ "step": 2330
2584
+ },
2585
+ {
2586
+ "epoch": 0.9389106229310864,
2587
+ "grad_norm": 0.84765625,
2588
+ "learning_rate": 5.649152545533332e-07,
2589
+ "logps_logqs/chosen": 0.06688685715198517,
2590
+ "logqs/chosen": -0.7463788986206055,
2591
+ "logqs/rejected": -0.8424680829048157,
2592
+ "logqs_logps/rejected": 0.04632396623492241,
2593
+ "loss": 0.1996,
2594
+ "step": 2340
2595
+ },
2596
+ {
2597
+ "epoch": 0.9429230614906209,
2598
+ "grad_norm": 0.859375,
2599
+ "learning_rate": 4.932667966062815e-07,
2600
+ "logps_logqs/chosen": 0.06688842177391052,
2601
+ "logqs/chosen": -0.7895928621292114,
2602
+ "logqs/rejected": -1.0372272729873657,
2603
+ "logqs_logps/rejected": 0.042335085570812225,
2604
+ "loss": 0.2169,
2605
+ "step": 2350
2606
+ },
2607
+ {
2608
+ "epoch": 0.9469355000501555,
2609
+ "grad_norm": 0.9140625,
2610
+ "learning_rate": 4.2643013065673533e-07,
2611
+ "logps_logqs/chosen": 0.05645795911550522,
2612
+ "logqs/chosen": -0.801129162311554,
2613
+ "logqs/rejected": -0.9468640089035034,
2614
+ "logqs_logps/rejected": 0.04600223898887634,
2615
+ "loss": 0.201,
2616
+ "step": 2360
2617
+ },
2618
+ {
2619
+ "epoch": 0.9509479386096901,
2620
+ "grad_norm": 0.91015625,
2621
+ "learning_rate": 3.6441837979750426e-07,
2622
+ "logps_logqs/chosen": 0.057076144963502884,
2623
+ "logqs/chosen": -0.7397576570510864,
2624
+ "logqs/rejected": -0.928216814994812,
2625
+ "logqs_logps/rejected": 0.045889295637607574,
2626
+ "loss": 0.201,
2627
+ "step": 2370
2628
+ },
2629
+ {
2630
+ "epoch": 0.9549603771692246,
2631
+ "grad_norm": 0.8984375,
2632
+ "learning_rate": 3.07243719770009e-07,
2633
+ "logps_logqs/chosen": 0.05663397163152695,
2634
+ "logqs/chosen": -0.7601091861724854,
2635
+ "logqs/rejected": -0.8796554803848267,
2636
+ "logqs_logps/rejected": 0.0409110002219677,
2637
+ "loss": 0.1985,
2638
+ "step": 2380
2639
+ },
2640
+ {
2641
+ "epoch": 0.9589728157287591,
2642
+ "grad_norm": 0.98046875,
2643
+ "learning_rate": 2.5491737657362127e-07,
2644
+ "logps_logqs/chosen": 0.06481993943452835,
2645
+ "logqs/chosen": -0.7787806391716003,
2646
+ "logqs/rejected": -0.9817843437194824,
2647
+ "logqs_logps/rejected": 0.04762902110815048,
2648
+ "loss": 0.2106,
2649
+ "step": 2390
2650
+ },
2651
+ {
2652
+ "epoch": 0.9629852542882937,
2653
+ "grad_norm": 0.9921875,
2654
+ "learning_rate": 2.0744962426149372e-07,
2655
+ "logps_logqs/chosen": 0.06616654247045517,
2656
+ "logqs/chosen": -0.7752987742424011,
2657
+ "logqs/rejected": -0.8757341504096985,
2658
+ "logqs_logps/rejected": 0.04639893025159836,
2659
+ "loss": 0.2078,
2660
+ "step": 2400
2661
+ },
2662
+ {
2663
+ "epoch": 0.9669976928478282,
2664
+ "grad_norm": 0.984375,
2665
+ "learning_rate": 1.6484978292328479e-07,
2666
+ "logps_logqs/chosen": 0.0615106001496315,
2667
+ "logqs/chosen": -0.7567707300186157,
2668
+ "logqs/rejected": -0.8831803202629089,
2669
+ "logqs_logps/rejected": 0.0448283851146698,
2670
+ "loss": 0.2027,
2671
+ "step": 2410
2672
+ },
2673
+ {
2674
+ "epoch": 0.9710101314073628,
2675
+ "grad_norm": 0.79296875,
2676
+ "learning_rate": 1.2712621685520288e-07,
2677
+ "logps_logqs/chosen": 0.054491542279720306,
2678
+ "logqs/chosen": -0.7399695515632629,
2679
+ "logqs/rejected": -0.915317714214325,
2680
+ "logqs_logps/rejected": 0.03824533894658089,
2681
+ "loss": 0.196,
2682
+ "step": 2420
2683
+ },
2684
+ {
2685
+ "epoch": 0.9750225699668974,
2686
+ "grad_norm": 0.90234375,
2687
+ "learning_rate": 9.42863329177146e-08,
2688
+ "logps_logqs/chosen": 0.06179448962211609,
2689
+ "logqs/chosen": -0.7460163831710815,
2690
+ "logqs/rejected": -0.8711358308792114,
2691
+ "logqs_logps/rejected": 0.04575900733470917,
2692
+ "loss": 0.1979,
2693
+ "step": 2430
2694
+ },
2695
+ {
2696
+ "epoch": 0.979035008526432,
2697
+ "grad_norm": 0.8828125,
2698
+ "learning_rate": 6.633657908123591e-08,
2699
+ "logps_logqs/chosen": 0.05870884656906128,
2700
+ "logqs/chosen": -0.7323063015937805,
2701
+ "logqs/rejected": -0.8580669164657593,
2702
+ "logqs_logps/rejected": 0.04539089277386665,
2703
+ "loss": 0.2049,
2704
+ "step": 2440
2705
+ },
2706
+ {
2707
+ "epoch": 0.9830474470859665,
2708
+ "grad_norm": 0.953125,
2709
+ "learning_rate": 4.328244316011143e-08,
2710
+ "logps_logqs/chosen": 0.054106056690216064,
2711
+ "logqs/chosen": -0.7781955003738403,
2712
+ "logqs/rejected": -1.0293381214141846,
2713
+ "logqs_logps/rejected": 0.043772052973508835,
2714
+ "loss": 0.2009,
2715
+ "step": 2450
2716
+ },
2717
+ {
2718
+ "epoch": 0.9870598856455011,
2719
+ "grad_norm": 0.7578125,
2720
+ "learning_rate": 2.5128451735081936e-08,
2721
+ "logps_logqs/chosen": 0.06501375138759613,
2722
+ "logqs/chosen": -0.7846288681030273,
2723
+ "logqs/rejected": -0.9334620237350464,
2724
+ "logqs_logps/rejected": 0.04351498931646347,
2725
+ "loss": 0.21,
2726
+ "step": 2460
2727
+ },
2728
+ {
2729
+ "epoch": 0.9910723242050357,
2730
+ "grad_norm": 0.796875,
2731
+ "learning_rate": 1.1878169264536999e-08,
2732
+ "logps_logqs/chosen": 0.06218789145350456,
2733
+ "logqs/chosen": -0.73200923204422,
2734
+ "logqs/rejected": -0.8427228927612305,
2735
+ "logqs_logps/rejected": 0.045235030353069305,
2736
+ "loss": 0.203,
2737
+ "step": 2470
2738
+ },
2739
+ {
2740
+ "epoch": 0.9950847627645701,
2741
+ "grad_norm": 0.91796875,
2742
+ "learning_rate": 3.5341973846303445e-09,
2743
+ "logps_logqs/chosen": 0.06000654771924019,
2744
+ "logqs/chosen": -0.7566072940826416,
2745
+ "logqs/rejected": -0.9218905568122864,
2746
+ "logqs_logps/rejected": 0.044534750282764435,
2747
+ "loss": 0.2049,
2748
+ "step": 2480
2749
+ },
2750
+ {
2751
+ "epoch": 0.9990972013241047,
2752
+ "grad_norm": 1.046875,
2753
+ "learning_rate": 9.817439847181753e-11,
2754
+ "logps_logqs/chosen": 0.060572218149900436,
2755
+ "logqs/chosen": -0.7785285115242004,
2756
+ "logqs/rejected": -0.9291244745254517,
2757
+ "logqs_logps/rejected": 0.03921912610530853,
2758
+ "loss": 0.2054,
2759
+ "step": 2490
2760
+ }
2761
+ ],
2762
+ "logging_steps": 10,
2763
+ "max_steps": 2492,
2764
+ "num_input_tokens_seen": 0,
2765
+ "num_train_epochs": 1,
2766
+ "save_steps": 500,
2767
+ "stateful_callbacks": {
2768
+ "TrainerControl": {
2769
+ "args": {
2770
+ "should_epoch_stop": false,
2771
+ "should_evaluate": false,
2772
+ "should_log": false,
2773
+ "should_save": true,
2774
+ "should_training_stop": true
2775
+ },
2776
+ "attributes": {}
2777
+ }
2778
+ },
2779
+ "total_flos": 0.0,
2780
+ "train_batch_size": 2,
2781
+ "trial_name": null,
2782
+ "trial_params": null
2783
+ }
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1161612a2c62499be2c7df457de2b8f9c367b6c35886d6da23351b674ba8c60d
3
+ size 6840
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-1.5B-it-distillm2-1epoch/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.45.2",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
qwen2.5-1.5B-it-distillm2-1epoch/eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9998996890360117,
3
+ "eval_logps_logqs/chosen": 0.05957354977726936,
4
+ "eval_logqs/chosen": -0.9947950839996338,
5
+ "eval_logqs/rejected": -0.9651834964752197,
6
+ "eval_logqs_logps/rejected": 0.04703126847743988,
7
+ "eval_loss": 0.18548408150672913,
8
+ "eval_runtime": 1.047,
9
+ "eval_samples": 10,
10
+ "eval_samples_per_second": 9.551,
11
+ "eval_steps_per_second": 2.865
12
+ }
qwen2.5-1.5B-it-distillm2-1epoch/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.45.2"
14
+ }
qwen2.5-1.5B-it-distillm2-1epoch/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-1.5B-it-distillm2-1epoch/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ff145d45e5491c4cb2f9b91b392fa1d4980c8caf0c065acd5d8e83f7ad1bf6
3
+ size 3087935634
qwen2.5-1.5B-it-distillm2-1epoch/special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "bos_token": "<|endoftext|>",
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
qwen2.5-1.5B-it-distillm2-1epoch/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5-1.5B-it-distillm2-1epoch/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": "<|endoftext|>",
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 2048,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
qwen2.5-1.5B-it-distillm2-1epoch/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9998996890360117,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.2227630860637126,
5
+ "train_runtime": 7975.4099,
6
+ "train_samples": 79751,
7
+ "train_samples_per_second": 10.0,
8
+ "train_steps_per_second": 0.312
9
+ }
qwen2.5-1.5B-it-distillm2-1epoch/trainer_state.json ADDED
@@ -0,0 +1,2792 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9998996890360117,
5
+ "eval_steps": 10000000,
6
+ "global_step": 2492,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0004012438559534557,
13
+ "grad_norm": 7.4375,
14
+ "learning_rate": 2.0000000000000002e-07,
15
+ "logps_logqs/chosen": 0.04569786787033081,
16
+ "logqs/chosen": -0.7619987726211548,
17
+ "logqs/rejected": -0.6922895908355713,
18
+ "logqs_logps/rejected": 0.12882234156131744,
19
+ "loss": 0.4402,
20
+ "step": 1
21
+ },
22
+ {
23
+ "epoch": 0.004012438559534557,
24
+ "grad_norm": 8.1875,
25
+ "learning_rate": 2.0000000000000003e-06,
26
+ "logps_logqs/chosen": 0.05236833542585373,
27
+ "logqs/chosen": -0.7575697302818298,
28
+ "logqs/rejected": -0.7214224338531494,
29
+ "logqs_logps/rejected": 0.13564398884773254,
30
+ "loss": 0.4632,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.008024877119069114,
35
+ "grad_norm": 3.5625,
36
+ "learning_rate": 4.000000000000001e-06,
37
+ "logps_logqs/chosen": 0.03725143522024155,
38
+ "logqs/chosen": -0.7332857847213745,
39
+ "logqs/rejected": -0.6967843770980835,
40
+ "logqs_logps/rejected": 0.15449675917625427,
41
+ "loss": 0.437,
42
+ "step": 20
43
+ },
44
+ {
45
+ "epoch": 0.012037315678603671,
46
+ "grad_norm": 2.65625,
47
+ "learning_rate": 6e-06,
48
+ "logps_logqs/chosen": 0.024129396304488182,
49
+ "logqs/chosen": -0.6929070353507996,
50
+ "logqs/rejected": -0.6931973695755005,
51
+ "logqs_logps/rejected": 0.14559319615364075,
52
+ "loss": 0.3924,
53
+ "step": 30
54
+ },
55
+ {
56
+ "epoch": 0.016049754238138227,
57
+ "grad_norm": 1.9296875,
58
+ "learning_rate": 8.000000000000001e-06,
59
+ "logps_logqs/chosen": 0.04635835438966751,
60
+ "logqs/chosen": -0.7109580039978027,
61
+ "logqs/rejected": -0.7326062917709351,
62
+ "logqs_logps/rejected": 0.11042358726263046,
63
+ "loss": 0.3376,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 0.020062192797672785,
68
+ "grad_norm": 1.359375,
69
+ "learning_rate": 1e-05,
70
+ "logps_logqs/chosen": 0.06155390664935112,
71
+ "logqs/chosen": -0.7556450963020325,
72
+ "logqs/rejected": -0.7544510364532471,
73
+ "logqs_logps/rejected": 0.0817796066403389,
74
+ "loss": 0.3119,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.024074631357207343,
79
+ "grad_norm": 1.9609375,
80
+ "learning_rate": 1.2e-05,
81
+ "logps_logqs/chosen": 0.04699297621846199,
82
+ "logqs/chosen": -0.7331749796867371,
83
+ "logqs/rejected": -0.7754837870597839,
84
+ "logqs_logps/rejected": 0.09542788565158844,
85
+ "loss": 0.3021,
86
+ "step": 60
87
+ },
88
+ {
89
+ "epoch": 0.0280870699167419,
90
+ "grad_norm": 2.1875,
91
+ "learning_rate": 1.4000000000000001e-05,
92
+ "logps_logqs/chosen": 0.04325335472822189,
93
+ "logqs/chosen": -0.7399210333824158,
94
+ "logqs/rejected": -0.8113678097724915,
95
+ "logqs_logps/rejected": 0.09601923078298569,
96
+ "loss": 0.3056,
97
+ "step": 70
98
+ },
99
+ {
100
+ "epoch": 0.032099508476276455,
101
+ "grad_norm": 1.40625,
102
+ "learning_rate": 1.6000000000000003e-05,
103
+ "logps_logqs/chosen": 0.05340943485498428,
104
+ "logqs/chosen": -0.7167432904243469,
105
+ "logqs/rejected": -0.733643651008606,
106
+ "logqs_logps/rejected": 0.08651523292064667,
107
+ "loss": 0.2901,
108
+ "step": 80
109
+ },
110
+ {
111
+ "epoch": 0.03611194703581101,
112
+ "grad_norm": 1.9140625,
113
+ "learning_rate": 1.8e-05,
114
+ "logps_logqs/chosen": 0.05581357330083847,
115
+ "logqs/chosen": -0.7287663221359253,
116
+ "logqs/rejected": -0.80914705991745,
117
+ "logqs_logps/rejected": 0.08022361993789673,
118
+ "loss": 0.2872,
119
+ "step": 90
120
+ },
121
+ {
122
+ "epoch": 0.04012438559534557,
123
+ "grad_norm": 1.484375,
124
+ "learning_rate": 2e-05,
125
+ "logps_logqs/chosen": 0.060486920177936554,
126
+ "logqs/chosen": -0.7507224082946777,
127
+ "logqs/rejected": -0.7546180486679077,
128
+ "logqs_logps/rejected": 0.08861987292766571,
129
+ "loss": 0.2874,
130
+ "step": 100
131
+ },
132
+ {
133
+ "epoch": 0.04413682415488013,
134
+ "grad_norm": 1.625,
135
+ "learning_rate": 2.2000000000000003e-05,
136
+ "logps_logqs/chosen": 0.05298670381307602,
137
+ "logqs/chosen": -0.7025843262672424,
138
+ "logqs/rejected": -0.8093870282173157,
139
+ "logqs_logps/rejected": 0.09236426651477814,
140
+ "loss": 0.284,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.048149262714414685,
145
+ "grad_norm": 1.3671875,
146
+ "learning_rate": 2.4e-05,
147
+ "logps_logqs/chosen": 0.0429534837603569,
148
+ "logqs/chosen": -0.7203501462936401,
149
+ "logqs/rejected": -0.7625126838684082,
150
+ "logqs_logps/rejected": 0.09294354915618896,
151
+ "loss": 0.2814,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.05216170127394924,
156
+ "grad_norm": 1.4375,
157
+ "learning_rate": 2.6000000000000002e-05,
158
+ "logps_logqs/chosen": 0.04513775557279587,
159
+ "logqs/chosen": -0.7521069645881653,
160
+ "logqs/rejected": -0.8475151062011719,
161
+ "logqs_logps/rejected": 0.08711571246385574,
162
+ "loss": 0.2738,
163
+ "step": 130
164
+ },
165
+ {
166
+ "epoch": 0.0561741398334838,
167
+ "grad_norm": 1.2578125,
168
+ "learning_rate": 2.8000000000000003e-05,
169
+ "logps_logqs/chosen": 0.05815966799855232,
170
+ "logqs/chosen": -0.7234808206558228,
171
+ "logqs/rejected": -0.7618853449821472,
172
+ "logqs_logps/rejected": 0.08775873482227325,
173
+ "loss": 0.2716,
174
+ "step": 140
175
+ },
176
+ {
177
+ "epoch": 0.06018657839301836,
178
+ "grad_norm": 1.2421875,
179
+ "learning_rate": 3e-05,
180
+ "logps_logqs/chosen": 0.04522830247879028,
181
+ "logqs/chosen": -0.7279343008995056,
182
+ "logqs/rejected": -0.7802385091781616,
183
+ "logqs_logps/rejected": 0.08993647247552872,
184
+ "loss": 0.2844,
185
+ "step": 150
186
+ },
187
+ {
188
+ "epoch": 0.06419901695255291,
189
+ "grad_norm": 4.8125,
190
+ "learning_rate": 3.2000000000000005e-05,
191
+ "logps_logqs/chosen": 0.04608219116926193,
192
+ "logqs/chosen": -0.7237873077392578,
193
+ "logqs/rejected": -0.8180141448974609,
194
+ "logqs_logps/rejected": 0.09209342300891876,
195
+ "loss": 0.2734,
196
+ "step": 160
197
+ },
198
+ {
199
+ "epoch": 0.06821145551208747,
200
+ "grad_norm": 1.625,
201
+ "learning_rate": 3.4000000000000007e-05,
202
+ "logps_logqs/chosen": 0.0829857811331749,
203
+ "logqs/chosen": -0.834354043006897,
204
+ "logqs/rejected": -0.9757483601570129,
205
+ "logqs_logps/rejected": 0.05420444533228874,
206
+ "loss": 0.2608,
207
+ "step": 170
208
+ },
209
+ {
210
+ "epoch": 0.07222389407162202,
211
+ "grad_norm": 1.59375,
212
+ "learning_rate": 3.6e-05,
213
+ "logps_logqs/chosen": 0.07175259292125702,
214
+ "logqs/chosen": -0.8033750653266907,
215
+ "logqs/rejected": -0.9368761777877808,
216
+ "logqs_logps/rejected": 0.05796421319246292,
217
+ "loss": 0.2532,
218
+ "step": 180
219
+ },
220
+ {
221
+ "epoch": 0.07623633263115659,
222
+ "grad_norm": 1.171875,
223
+ "learning_rate": 3.8e-05,
224
+ "logps_logqs/chosen": 0.07778682559728622,
225
+ "logqs/chosen": -0.7997792959213257,
226
+ "logqs/rejected": -0.9281190633773804,
227
+ "logqs_logps/rejected": 0.05667818337678909,
228
+ "loss": 0.2451,
229
+ "step": 190
230
+ },
231
+ {
232
+ "epoch": 0.08024877119069114,
233
+ "grad_norm": 1.515625,
234
+ "learning_rate": 4e-05,
235
+ "logps_logqs/chosen": 0.07711273431777954,
236
+ "logqs/chosen": -0.7552299499511719,
237
+ "logqs/rejected": -0.8450819849967957,
238
+ "logqs_logps/rejected": 0.047475770115852356,
239
+ "loss": 0.2445,
240
+ "step": 200
241
+ },
242
+ {
243
+ "epoch": 0.0842612097502257,
244
+ "grad_norm": 1.2421875,
245
+ "learning_rate": 4.2e-05,
246
+ "logps_logqs/chosen": 0.07256797701120377,
247
+ "logqs/chosen": -0.7694905996322632,
248
+ "logqs/rejected": -0.9085494875907898,
249
+ "logqs_logps/rejected": 0.04616270214319229,
250
+ "loss": 0.2415,
251
+ "step": 210
252
+ },
253
+ {
254
+ "epoch": 0.08827364830976026,
255
+ "grad_norm": 1.359375,
256
+ "learning_rate": 4.4000000000000006e-05,
257
+ "logps_logqs/chosen": 0.07909471541643143,
258
+ "logqs/chosen": -0.7777330875396729,
259
+ "logqs/rejected": -0.9235789179801941,
260
+ "logqs_logps/rejected": 0.04829848185181618,
261
+ "loss": 0.2477,
262
+ "step": 220
263
+ },
264
+ {
265
+ "epoch": 0.09228608686929482,
266
+ "grad_norm": 1.6484375,
267
+ "learning_rate": 4.600000000000001e-05,
268
+ "logps_logqs/chosen": 0.07866504043340683,
269
+ "logqs/chosen": -0.8106803894042969,
270
+ "logqs/rejected": -0.851120114326477,
271
+ "logqs_logps/rejected": 0.04576503112912178,
272
+ "loss": 0.2416,
273
+ "step": 230
274
+ },
275
+ {
276
+ "epoch": 0.09629852542882937,
277
+ "grad_norm": 1.3671875,
278
+ "learning_rate": 4.8e-05,
279
+ "logps_logqs/chosen": 0.08257119357585907,
280
+ "logqs/chosen": -0.8273600339889526,
281
+ "logqs/rejected": -0.9416961669921875,
282
+ "logqs_logps/rejected": 0.03500179573893547,
283
+ "loss": 0.2464,
284
+ "step": 240
285
+ },
286
+ {
287
+ "epoch": 0.10031096398836392,
288
+ "grad_norm": 1.2578125,
289
+ "learning_rate": 5e-05,
290
+ "logps_logqs/chosen": 0.07746388763189316,
291
+ "logqs/chosen": -0.8364149332046509,
292
+ "logqs/rejected": -0.9234830737113953,
293
+ "logqs_logps/rejected": 0.0357363224029541,
294
+ "loss": 0.249,
295
+ "step": 250
296
+ },
297
+ {
298
+ "epoch": 0.10432340254789849,
299
+ "grad_norm": 1.734375,
300
+ "learning_rate": 4.999754567859088e-05,
301
+ "logps_logqs/chosen": 0.07921982556581497,
302
+ "logqs/chosen": -0.8031741976737976,
303
+ "logqs/rejected": -0.9179041981697083,
304
+ "logqs_logps/rejected": 0.040028877556324005,
305
+ "loss": 0.254,
306
+ "step": 260
307
+ },
308
+ {
309
+ "epoch": 0.10833584110743304,
310
+ "grad_norm": 1.375,
311
+ "learning_rate": 4.9990183196258985e-05,
312
+ "logps_logqs/chosen": 0.07431423664093018,
313
+ "logqs/chosen": -0.8124697804450989,
314
+ "logqs/rejected": -1.044480323791504,
315
+ "logqs_logps/rejected": 0.03857969120144844,
316
+ "loss": 0.2526,
317
+ "step": 270
318
+ },
319
+ {
320
+ "epoch": 0.1123482796669676,
321
+ "grad_norm": 1.2578125,
322
+ "learning_rate": 4.997791399859618e-05,
323
+ "logps_logqs/chosen": 0.07444961369037628,
324
+ "logqs/chosen": -0.7750430107116699,
325
+ "logqs/rejected": -0.9249812364578247,
326
+ "logqs_logps/rejected": 0.043836839497089386,
327
+ "loss": 0.2466,
328
+ "step": 280
329
+ },
330
+ {
331
+ "epoch": 0.11636071822650215,
332
+ "grad_norm": 1.234375,
333
+ "learning_rate": 4.9960740494606804e-05,
334
+ "logps_logqs/chosen": 0.0844290554523468,
335
+ "logqs/chosen": -0.8090071678161621,
336
+ "logqs/rejected": -0.9015344381332397,
337
+ "logqs_logps/rejected": 0.04431484267115593,
338
+ "loss": 0.2518,
339
+ "step": 290
340
+ },
341
+ {
342
+ "epoch": 0.12037315678603672,
343
+ "grad_norm": 1.2109375,
344
+ "learning_rate": 4.993866605623476e-05,
345
+ "logps_logqs/chosen": 0.08662852644920349,
346
+ "logqs/chosen": -0.8766249418258667,
347
+ "logqs/rejected": -0.9904054403305054,
348
+ "logqs_logps/rejected": 0.03374750539660454,
349
+ "loss": 0.259,
350
+ "step": 300
351
+ },
352
+ {
353
+ "epoch": 0.12438559534557127,
354
+ "grad_norm": 1.1875,
355
+ "learning_rate": 4.9911695017701354e-05,
356
+ "logps_logqs/chosen": 0.06808570772409439,
357
+ "logqs/chosen": -0.7952664494514465,
358
+ "logqs/rejected": -1.0071316957473755,
359
+ "logqs_logps/rejected": 0.0351722352206707,
360
+ "loss": 0.2404,
361
+ "step": 310
362
+ },
363
+ {
364
+ "epoch": 0.12839803390510582,
365
+ "grad_norm": 1.25,
366
+ "learning_rate": 4.9879832674654394e-05,
367
+ "logps_logqs/chosen": 0.07012389600276947,
368
+ "logqs/chosen": -0.7575680017471313,
369
+ "logqs/rejected": -0.8348391652107239,
370
+ "logqs_logps/rejected": 0.04610547423362732,
371
+ "loss": 0.2475,
372
+ "step": 320
373
+ },
374
+ {
375
+ "epoch": 0.13241047246464038,
376
+ "grad_norm": 1.125,
377
+ "learning_rate": 4.984308528312833e-05,
378
+ "logps_logqs/chosen": 0.07651235163211823,
379
+ "logqs/chosen": -0.8075329661369324,
380
+ "logqs/rejected": -0.8980422019958496,
381
+ "logqs_logps/rejected": 0.05326312780380249,
382
+ "loss": 0.2557,
383
+ "step": 330
384
+ },
385
+ {
386
+ "epoch": 0.13642291102417495,
387
+ "grad_norm": 0.9375,
388
+ "learning_rate": 4.980146005831593e-05,
389
+ "logps_logqs/chosen": 0.07402589172124863,
390
+ "logqs/chosen": -0.7595754265785217,
391
+ "logqs/rejected": -0.8438477516174316,
392
+ "logqs_logps/rejected": 0.0414380244910717,
393
+ "loss": 0.2352,
394
+ "step": 340
395
+ },
396
+ {
397
+ "epoch": 0.1404353495837095,
398
+ "grad_norm": 1.03125,
399
+ "learning_rate": 4.975496517315164e-05,
400
+ "logps_logqs/chosen": 0.08224797248840332,
401
+ "logqs/chosen": -0.8209888339042664,
402
+ "logqs/rejected": -0.9319378137588501,
403
+ "logqs_logps/rejected": 0.040799789130687714,
404
+ "loss": 0.2447,
405
+ "step": 350
406
+ },
407
+ {
408
+ "epoch": 0.14444778814324405,
409
+ "grad_norm": 0.8984375,
410
+ "learning_rate": 4.9703609756706825e-05,
411
+ "logps_logqs/chosen": 0.06839220225811005,
412
+ "logqs/chosen": -0.7235757112503052,
413
+ "logqs/rejected": -0.8419008255004883,
414
+ "logqs_logps/rejected": 0.042561449110507965,
415
+ "loss": 0.2358,
416
+ "step": 360
417
+ },
418
+ {
419
+ "epoch": 0.1484602267027786,
420
+ "grad_norm": 1.0546875,
421
+ "learning_rate": 4.964740389239732e-05,
422
+ "logps_logqs/chosen": 0.06623891741037369,
423
+ "logqs/chosen": -0.7539215683937073,
424
+ "logqs/rejected": -0.9607669115066528,
425
+ "logqs_logps/rejected": 0.04915183037519455,
426
+ "loss": 0.239,
427
+ "step": 370
428
+ },
429
+ {
430
+ "epoch": 0.15247266526231318,
431
+ "grad_norm": 1.0390625,
432
+ "learning_rate": 4.958635861600363e-05,
433
+ "logps_logqs/chosen": 0.07241146266460419,
434
+ "logqs/chosen": -0.7943685054779053,
435
+ "logqs/rejected": -0.893652617931366,
436
+ "logqs_logps/rejected": 0.04425416141748428,
437
+ "loss": 0.2338,
438
+ "step": 380
439
+ },
440
+ {
441
+ "epoch": 0.15648510382184772,
442
+ "grad_norm": 1.3828125,
443
+ "learning_rate": 4.9520485913504034e-05,
444
+ "logps_logqs/chosen": 0.08117856085300446,
445
+ "logqs/chosen": -0.8306816816329956,
446
+ "logqs/rejected": -0.9850896596908569,
447
+ "logqs_logps/rejected": 0.0467182882130146,
448
+ "loss": 0.2507,
449
+ "step": 390
450
+ },
451
+ {
452
+ "epoch": 0.16049754238138228,
453
+ "grad_norm": 1.1328125,
454
+ "learning_rate": 4.944979871872126e-05,
455
+ "logps_logqs/chosen": 0.07253263145685196,
456
+ "logqs/chosen": -0.7571657299995422,
457
+ "logqs/rejected": -0.8560029864311218,
458
+ "logqs_logps/rejected": 0.04899878054857254,
459
+ "loss": 0.2395,
460
+ "step": 400
461
+ },
462
+ {
463
+ "epoch": 0.16450998094091684,
464
+ "grad_norm": 1.0,
465
+ "learning_rate": 4.937431091078297e-05,
466
+ "logps_logqs/chosen": 0.07146044075489044,
467
+ "logqs/chosen": -0.780661404132843,
468
+ "logqs/rejected": -0.8788405656814575,
469
+ "logqs_logps/rejected": 0.045706409960985184,
470
+ "loss": 0.2476,
471
+ "step": 410
472
+ },
473
+ {
474
+ "epoch": 0.1685224195004514,
475
+ "grad_norm": 1.171875,
476
+ "learning_rate": 4.929403731139659e-05,
477
+ "logps_logqs/chosen": 0.06834863871335983,
478
+ "logqs/chosen": -0.7439772486686707,
479
+ "logqs/rejected": -0.8892331123352051,
480
+ "logqs_logps/rejected": 0.04937626048922539,
481
+ "loss": 0.2396,
482
+ "step": 420
483
+ },
484
+ {
485
+ "epoch": 0.17253485805998595,
486
+ "grad_norm": 1.265625,
487
+ "learning_rate": 4.920899368193923e-05,
488
+ "logps_logqs/chosen": 0.07205794751644135,
489
+ "logqs/chosen": -0.7703086137771606,
490
+ "logqs/rejected": -0.924181342124939,
491
+ "logqs_logps/rejected": 0.04389696940779686,
492
+ "loss": 0.2415,
493
+ "step": 430
494
+ },
495
+ {
496
+ "epoch": 0.1765472966195205,
497
+ "grad_norm": 1.0546875,
498
+ "learning_rate": 4.91191967203629e-05,
499
+ "logps_logqs/chosen": 0.07142455875873566,
500
+ "logqs/chosen": -0.774928092956543,
501
+ "logqs/rejected": -0.8973848223686218,
502
+ "logqs_logps/rejected": 0.05115640163421631,
503
+ "loss": 0.2429,
504
+ "step": 440
505
+ },
506
+ {
507
+ "epoch": 0.18055973517905508,
508
+ "grad_norm": 1.203125,
509
+ "learning_rate": 4.902466405791604e-05,
510
+ "logps_logqs/chosen": 0.0635933205485344,
511
+ "logqs/chosen": -0.7374957799911499,
512
+ "logqs/rejected": -0.8527389764785767,
513
+ "logqs_logps/rejected": 0.04913189262151718,
514
+ "loss": 0.2389,
515
+ "step": 450
516
+ },
517
+ {
518
+ "epoch": 0.18457217373858964,
519
+ "grad_norm": 1.0703125,
520
+ "learning_rate": 4.8925414255681634e-05,
521
+ "logps_logqs/chosen": 0.07408438622951508,
522
+ "logqs/chosen": -0.7961963415145874,
523
+ "logqs/rejected": -0.891047477722168,
524
+ "logqs_logps/rejected": 0.047257475554943085,
525
+ "loss": 0.244,
526
+ "step": 460
527
+ },
528
+ {
529
+ "epoch": 0.18858461229812418,
530
+ "grad_norm": 1.0625,
531
+ "learning_rate": 4.8821466800932834e-05,
532
+ "logps_logqs/chosen": 0.07002029567956924,
533
+ "logqs/chosen": -0.7757862210273743,
534
+ "logqs/rejected": -0.9203861355781555,
535
+ "logqs_logps/rejected": 0.04404062032699585,
536
+ "loss": 0.2403,
537
+ "step": 470
538
+ },
539
+ {
540
+ "epoch": 0.19259705085765874,
541
+ "grad_norm": 1.0703125,
542
+ "learning_rate": 4.8712842103306734e-05,
543
+ "logps_logqs/chosen": 0.0644606500864029,
544
+ "logqs/chosen": -0.7633457779884338,
545
+ "logqs/rejected": -0.8767465353012085,
546
+ "logqs_logps/rejected": 0.056550778448581696,
547
+ "loss": 0.2414,
548
+ "step": 480
549
+ },
550
+ {
551
+ "epoch": 0.1966094894171933,
552
+ "grad_norm": 1.046875,
553
+ "learning_rate": 4.859956149079699e-05,
554
+ "logps_logqs/chosen": 0.06858934462070465,
555
+ "logqs/chosen": -0.7749469876289368,
556
+ "logqs/rejected": -0.9290539622306824,
557
+ "logqs_logps/rejected": 0.048794034868478775,
558
+ "loss": 0.2352,
559
+ "step": 490
560
+ },
561
+ {
562
+ "epoch": 0.20062192797672784,
563
+ "grad_norm": 1.0859375,
564
+ "learning_rate": 4.8481647205566245e-05,
565
+ "logps_logqs/chosen": 0.07484981417655945,
566
+ "logqs/chosen": -0.7901949286460876,
567
+ "logqs/rejected": -0.9649750590324402,
568
+ "logqs_logps/rejected": 0.039597224444150925,
569
+ "loss": 0.2426,
570
+ "step": 500
571
+ },
572
+ {
573
+ "epoch": 0.2046343665362624,
574
+ "grad_norm": 1.078125,
575
+ "learning_rate": 4.835912239957884e-05,
576
+ "logps_logqs/chosen": 0.07183913886547089,
577
+ "logqs/chosen": -0.8072341084480286,
578
+ "logqs/rejected": -0.949781596660614,
579
+ "logqs_logps/rejected": 0.04103394225239754,
580
+ "loss": 0.2461,
581
+ "step": 510
582
+ },
583
+ {
584
+ "epoch": 0.20864680509579697,
585
+ "grad_norm": 1.03125,
586
+ "learning_rate": 4.8232011130055145e-05,
587
+ "logps_logqs/chosen": 0.07492522150278091,
588
+ "logqs/chosen": -0.7984409928321838,
589
+ "logqs/rejected": -0.9403228759765625,
590
+ "logqs_logps/rejected": 0.04501514509320259,
591
+ "loss": 0.2399,
592
+ "step": 520
593
+ },
594
+ {
595
+ "epoch": 0.21265924365533154,
596
+ "grad_norm": 0.984375,
597
+ "learning_rate": 4.8100338354747964e-05,
598
+ "logps_logqs/chosen": 0.06418637186288834,
599
+ "logqs/chosen": -0.7536183595657349,
600
+ "logqs/rejected": -0.9021707773208618,
601
+ "logqs_logps/rejected": 0.0469144806265831,
602
+ "loss": 0.2232,
603
+ "step": 530
604
+ },
605
+ {
606
+ "epoch": 0.21667168221486607,
607
+ "grad_norm": 0.98828125,
608
+ "learning_rate": 4.796412992704221e-05,
609
+ "logps_logqs/chosen": 0.07294625043869019,
610
+ "logqs/chosen": -0.817304790019989,
611
+ "logqs/rejected": -1.0015363693237305,
612
+ "logqs_logps/rejected": 0.03600292652845383,
613
+ "loss": 0.2425,
614
+ "step": 540
615
+ },
616
+ {
617
+ "epoch": 0.22068412077440064,
618
+ "grad_norm": 2.171875,
619
+ "learning_rate": 4.7823412590878725e-05,
620
+ "logps_logqs/chosen": 0.06552080065011978,
621
+ "logqs/chosen": -0.757979691028595,
622
+ "logqs/rejected": -0.9391049146652222,
623
+ "logqs_logps/rejected": 0.04227089509367943,
624
+ "loss": 0.2345,
625
+ "step": 550
626
+ },
627
+ {
628
+ "epoch": 0.2246965593339352,
629
+ "grad_norm": 0.94921875,
630
+ "learning_rate": 4.767821397550314e-05,
631
+ "logps_logqs/chosen": 0.07307900488376617,
632
+ "logqs/chosen": -0.7912179231643677,
633
+ "logqs/rejected": -0.9022812843322754,
634
+ "logqs_logps/rejected": 0.04547736793756485,
635
+ "loss": 0.2293,
636
+ "step": 560
637
+ },
638
+ {
639
+ "epoch": 0.22870899789346977,
640
+ "grad_norm": 0.90234375,
641
+ "learning_rate": 4.75285625900411e-05,
642
+ "logps_logqs/chosen": 0.06120596081018448,
643
+ "logqs/chosen": -0.7520848512649536,
644
+ "logqs/rejected": -0.8490988612174988,
645
+ "logqs_logps/rejected": 0.04672159627079964,
646
+ "loss": 0.2196,
647
+ "step": 570
648
+ },
649
+ {
650
+ "epoch": 0.2327214364530043,
651
+ "grad_norm": 0.9140625,
652
+ "learning_rate": 4.7374487817900526e-05,
653
+ "logps_logqs/chosen": 0.07047772407531738,
654
+ "logqs/chosen": -0.7582333087921143,
655
+ "logqs/rejected": -0.9080425500869751,
656
+ "logqs_logps/rejected": 0.043630070984363556,
657
+ "loss": 0.233,
658
+ "step": 580
659
+ },
660
+ {
661
+ "epoch": 0.23673387501253887,
662
+ "grad_norm": 1.0390625,
663
+ "learning_rate": 4.721601991100239e-05,
664
+ "logps_logqs/chosen": 0.07312636077404022,
665
+ "logqs/chosen": -0.8173810839653015,
666
+ "logqs/rejected": -0.9898309707641602,
667
+ "logqs_logps/rejected": 0.038896821439266205,
668
+ "loss": 0.2466,
669
+ "step": 590
670
+ },
671
+ {
672
+ "epoch": 0.24074631357207343,
673
+ "grad_norm": 1.0625,
674
+ "learning_rate": 4.70531899838408e-05,
675
+ "logps_logqs/chosen": 0.08125702291727066,
676
+ "logqs/chosen": -0.815421462059021,
677
+ "logqs/rejected": -0.9149931073188782,
678
+ "logqs_logps/rejected": 0.039436694234609604,
679
+ "loss": 0.2358,
680
+ "step": 600
681
+ },
682
+ {
683
+ "epoch": 0.244758752131608,
684
+ "grad_norm": 0.9765625,
685
+ "learning_rate": 4.688603000737386e-05,
686
+ "logps_logqs/chosen": 0.07415197044610977,
687
+ "logqs/chosen": -0.765034556388855,
688
+ "logqs/rejected": -0.8983548879623413,
689
+ "logqs_logps/rejected": 0.036344725638628006,
690
+ "loss": 0.2262,
691
+ "step": 610
692
+ },
693
+ {
694
+ "epoch": 0.24877119069114254,
695
+ "grad_norm": 1.0078125,
696
+ "learning_rate": 4.67145728027463e-05,
697
+ "logps_logqs/chosen": 0.06661795824766159,
698
+ "logqs/chosen": -0.7819303274154663,
699
+ "logqs/rejected": -0.9227293133735657,
700
+ "logqs_logps/rejected": 0.04116612672805786,
701
+ "loss": 0.2231,
702
+ "step": 620
703
+ },
704
+ {
705
+ "epoch": 0.2527836292506771,
706
+ "grad_norm": 1.34375,
707
+ "learning_rate": 4.653885203484515e-05,
708
+ "logps_logqs/chosen": 0.07415126264095306,
709
+ "logqs/chosen": -0.8002082705497742,
710
+ "logqs/rejected": -0.9249210357666016,
711
+ "logqs_logps/rejected": 0.0376618318259716,
712
+ "loss": 0.2299,
713
+ "step": 630
714
+ },
715
+ {
716
+ "epoch": 0.25679606781021164,
717
+ "grad_norm": 1.0703125,
718
+ "learning_rate": 4.635890220568984e-05,
719
+ "logps_logqs/chosen": 0.07411129772663116,
720
+ "logqs/chosen": -0.7709895372390747,
721
+ "logqs/rejected": -0.9492446780204773,
722
+ "logqs_logps/rejected": 0.036350082606077194,
723
+ "loss": 0.2301,
724
+ "step": 640
725
+ },
726
+ {
727
+ "epoch": 0.26080850636974623,
728
+ "grad_norm": 0.92578125,
729
+ "learning_rate": 4.6174758647657826e-05,
730
+ "logps_logqs/chosen": 0.07068853080272675,
731
+ "logqs/chosen": -0.8123248815536499,
732
+ "logqs/rejected": -0.8981572985649109,
733
+ "logqs_logps/rejected": 0.03915414959192276,
734
+ "loss": 0.2292,
735
+ "step": 650
736
+ },
737
+ {
738
+ "epoch": 0.26482094492928077,
739
+ "grad_norm": 1.03125,
740
+ "learning_rate": 4.598645751654724e-05,
741
+ "logps_logqs/chosen": 0.07326103746891022,
742
+ "logqs/chosen": -0.8222491145133972,
743
+ "logqs/rejected": -0.9678870439529419,
744
+ "logqs_logps/rejected": 0.0360921174287796,
745
+ "loss": 0.2451,
746
+ "step": 660
747
+ },
748
+ {
749
+ "epoch": 0.2688333834888153,
750
+ "grad_norm": 0.98828125,
751
+ "learning_rate": 4.579403578447791e-05,
752
+ "logps_logqs/chosen": 0.06781081855297089,
753
+ "logqs/chosen": -0.7649012804031372,
754
+ "logqs/rejected": -0.870588481426239,
755
+ "logqs_logps/rejected": 0.03709111362695694,
756
+ "loss": 0.2284,
757
+ "step": 670
758
+ },
759
+ {
760
+ "epoch": 0.2728458220483499,
761
+ "grad_norm": 0.921875,
762
+ "learning_rate": 4.559753123263193e-05,
763
+ "logps_logqs/chosen": 0.06727007776498795,
764
+ "logqs/chosen": -0.7720677256584167,
765
+ "logqs/rejected": -0.9267464876174927,
766
+ "logqs_logps/rejected": 0.041538018733263016,
767
+ "loss": 0.232,
768
+ "step": 680
769
+ },
770
+ {
771
+ "epoch": 0.27685826060788443,
772
+ "grad_norm": 0.96484375,
773
+ "learning_rate": 4.53969824438356e-05,
774
+ "logps_logqs/chosen": 0.07148684561252594,
775
+ "logqs/chosen": -0.7559467554092407,
776
+ "logqs/rejected": -0.9380974769592285,
777
+ "logqs_logps/rejected": 0.04005631059408188,
778
+ "loss": 0.2274,
779
+ "step": 690
780
+ },
781
+ {
782
+ "epoch": 0.280870699167419,
783
+ "grad_norm": 1.140625,
784
+ "learning_rate": 4.51924287949838e-05,
785
+ "logps_logqs/chosen": 0.06440640985965729,
786
+ "logqs/chosen": -0.7269574403762817,
787
+ "logqs/rejected": -0.8716470003128052,
788
+ "logqs_logps/rejected": 0.041931308805942535,
789
+ "loss": 0.2209,
790
+ "step": 700
791
+ },
792
+ {
793
+ "epoch": 0.28488313772695356,
794
+ "grad_norm": 0.96484375,
795
+ "learning_rate": 4.49839104493085e-05,
796
+ "logps_logqs/chosen": 0.06912580877542496,
797
+ "logqs/chosen": -0.7862259149551392,
798
+ "logqs/rejected": -0.888696551322937,
799
+ "logqs_logps/rejected": 0.04150567576289177,
800
+ "loss": 0.227,
801
+ "step": 710
802
+ },
803
+ {
804
+ "epoch": 0.2888955762864881,
805
+ "grad_norm": 1.2578125,
806
+ "learning_rate": 4.47714683484929e-05,
807
+ "logps_logqs/chosen": 0.07041208446025848,
808
+ "logqs/chosen": -0.7624860405921936,
809
+ "logqs/rejected": -0.8739960789680481,
810
+ "logqs_logps/rejected": 0.0403289757668972,
811
+ "loss": 0.2293,
812
+ "step": 720
813
+ },
814
+ {
815
+ "epoch": 0.2929080148460227,
816
+ "grad_norm": 1.1953125,
817
+ "learning_rate": 4.455514420463269e-05,
818
+ "logps_logqs/chosen": 0.06653012335300446,
819
+ "logqs/chosen": -0.7875178456306458,
820
+ "logqs/rejected": -0.8743432760238647,
821
+ "logqs_logps/rejected": 0.04233306646347046,
822
+ "loss": 0.2308,
823
+ "step": 730
824
+ },
825
+ {
826
+ "epoch": 0.2969204534055572,
827
+ "grad_norm": 0.90234375,
828
+ "learning_rate": 4.433498049204609e-05,
829
+ "logps_logqs/chosen": 0.06754721701145172,
830
+ "logqs/chosen": -0.7811694741249084,
831
+ "logqs/rejected": -0.9393448829650879,
832
+ "logqs_logps/rejected": 0.04023420438170433,
833
+ "loss": 0.2258,
834
+ "step": 740
835
+ },
836
+ {
837
+ "epoch": 0.30093289196509176,
838
+ "grad_norm": 1.09375,
839
+ "learning_rate": 4.4111020438934153e-05,
840
+ "logps_logqs/chosen": 0.06672672927379608,
841
+ "logqs/chosen": -0.8131230473518372,
842
+ "logqs/rejected": -0.9676214456558228,
843
+ "logqs_logps/rejected": 0.03876449912786484,
844
+ "loss": 0.2357,
845
+ "step": 750
846
+ },
847
+ {
848
+ "epoch": 0.30494533052462636,
849
+ "grad_norm": 1.09375,
850
+ "learning_rate": 4.388330801889314e-05,
851
+ "logps_logqs/chosen": 0.07214461266994476,
852
+ "logqs/chosen": -0.7811805009841919,
853
+ "logqs/rejected": -0.891452968120575,
854
+ "logqs_logps/rejected": 0.047579459846019745,
855
+ "loss": 0.2377,
856
+ "step": 760
857
+ },
858
+ {
859
+ "epoch": 0.3089577690841609,
860
+ "grad_norm": 1.046875,
861
+ "learning_rate": 4.365188794228045e-05,
862
+ "logps_logqs/chosen": 0.06557562947273254,
863
+ "logqs/chosen": -0.7820721864700317,
864
+ "logqs/rejected": -0.924803614616394,
865
+ "logqs_logps/rejected": 0.04372669756412506,
866
+ "loss": 0.2302,
867
+ "step": 770
868
+ },
869
+ {
870
+ "epoch": 0.31297020764369543,
871
+ "grad_norm": 1.015625,
872
+ "learning_rate": 4.341680564743599e-05,
873
+ "logps_logqs/chosen": 0.07139238715171814,
874
+ "logqs/chosen": -0.7355774641036987,
875
+ "logqs/rejected": -0.8488505482673645,
876
+ "logqs_logps/rejected": 0.04906998202204704,
877
+ "loss": 0.2185,
878
+ "step": 780
879
+ },
880
+ {
881
+ "epoch": 0.31698264620323,
882
+ "grad_norm": 1.0859375,
883
+ "learning_rate": 4.317810729176047e-05,
884
+ "logps_logqs/chosen": 0.062024809420108795,
885
+ "logqs/chosen": -0.7930202484130859,
886
+ "logqs/rejected": -0.9120181202888489,
887
+ "logqs_logps/rejected": 0.03688317909836769,
888
+ "loss": 0.2227,
889
+ "step": 790
890
+ },
891
+ {
892
+ "epoch": 0.32099508476276456,
893
+ "grad_norm": 0.97265625,
894
+ "learning_rate": 4.293583974265266e-05,
895
+ "logps_logqs/chosen": 0.06941133737564087,
896
+ "logqs/chosen": -0.7975060939788818,
897
+ "logqs/rejected": -0.8955381512641907,
898
+ "logqs_logps/rejected": 0.039408259093761444,
899
+ "loss": 0.2187,
900
+ "step": 800
901
+ },
902
+ {
903
+ "epoch": 0.32500752332229915,
904
+ "grad_norm": 1.03125,
905
+ "learning_rate": 4.269005056830717e-05,
906
+ "logps_logqs/chosen": 0.07276356965303421,
907
+ "logqs/chosen": -0.7674018740653992,
908
+ "logqs/rejected": -0.9420695304870605,
909
+ "logqs_logps/rejected": 0.039966169744729996,
910
+ "loss": 0.2275,
911
+ "step": 810
912
+ },
913
+ {
914
+ "epoch": 0.3290199618818337,
915
+ "grad_norm": 0.9375,
916
+ "learning_rate": 4.2440788028374624e-05,
917
+ "logps_logqs/chosen": 0.07384312152862549,
918
+ "logqs/chosen": -0.7966219782829285,
919
+ "logqs/rejected": -0.9411764144897461,
920
+ "logqs_logps/rejected": 0.036322906613349915,
921
+ "loss": 0.2367,
922
+ "step": 820
923
+ },
924
+ {
925
+ "epoch": 0.3330324004413682,
926
+ "grad_norm": 1.03125,
927
+ "learning_rate": 4.218810106448606e-05,
928
+ "logps_logqs/chosen": 0.06529523432254791,
929
+ "logqs/chosen": -0.7632766366004944,
930
+ "logqs/rejected": -0.9264775514602661,
931
+ "logqs_logps/rejected": 0.040053799748420715,
932
+ "loss": 0.2152,
933
+ "step": 830
934
+ },
935
+ {
936
+ "epoch": 0.3370448390009028,
937
+ "grad_norm": 1.0234375,
938
+ "learning_rate": 4.193203929064353e-05,
939
+ "logps_logqs/chosen": 0.06620033085346222,
940
+ "logqs/chosen": -0.7850610017776489,
941
+ "logqs/rejected": -0.896354079246521,
942
+ "logqs_logps/rejected": 0.040085501968860626,
943
+ "loss": 0.2181,
944
+ "step": 840
945
+ },
946
+ {
947
+ "epoch": 0.34105727756043736,
948
+ "grad_norm": 0.84375,
949
+ "learning_rate": 4.16726529834785e-05,
950
+ "logps_logqs/chosen": 0.0637274831533432,
951
+ "logqs/chosen": -0.768839955329895,
952
+ "logqs/rejected": -0.9418250918388367,
953
+ "logqs_logps/rejected": 0.03641074150800705,
954
+ "loss": 0.2162,
955
+ "step": 850
956
+ },
957
+ {
958
+ "epoch": 0.3450697161199719,
959
+ "grad_norm": 1.1640625,
960
+ "learning_rate": 4.140999307238033e-05,
961
+ "logps_logqs/chosen": 0.06885053962469101,
962
+ "logqs/chosen": -0.7867051362991333,
963
+ "logqs/rejected": -0.9046538472175598,
964
+ "logqs_logps/rejected": 0.04814887046813965,
965
+ "loss": 0.2268,
966
+ "step": 860
967
+ },
968
+ {
969
+ "epoch": 0.3490821546795065,
970
+ "grad_norm": 1.0234375,
971
+ "learning_rate": 4.114411112949647e-05,
972
+ "logps_logqs/chosen": 0.06477545201778412,
973
+ "logqs/chosen": -0.7621933817863464,
974
+ "logqs/rejected": -0.9573066830635071,
975
+ "logqs_logps/rejected": 0.04498199373483658,
976
+ "loss": 0.2217,
977
+ "step": 870
978
+ },
979
+ {
980
+ "epoch": 0.353094593239041,
981
+ "grad_norm": 0.96484375,
982
+ "learning_rate": 4.08750593596065e-05,
983
+ "logps_logqs/chosen": 0.07505324482917786,
984
+ "logqs/chosen": -0.7968708276748657,
985
+ "logqs/rejected": -0.8728815317153931,
986
+ "logqs_logps/rejected": 0.04394535347819328,
987
+ "loss": 0.2298,
988
+ "step": 880
989
+ },
990
+ {
991
+ "epoch": 0.35710703179857556,
992
+ "grad_norm": 0.9296875,
993
+ "learning_rate": 4.060289058987193e-05,
994
+ "logps_logqs/chosen": 0.0760955736041069,
995
+ "logqs/chosen": -0.7982200384140015,
996
+ "logqs/rejected": -0.9353931546211243,
997
+ "logqs_logps/rejected": 0.04747863858938217,
998
+ "loss": 0.2368,
999
+ "step": 890
1000
+ },
1001
+ {
1002
+ "epoch": 0.36111947035811015,
1003
+ "grad_norm": 1.0703125,
1004
+ "learning_rate": 4.032765825946385e-05,
1005
+ "logps_logqs/chosen": 0.061619557440280914,
1006
+ "logqs/chosen": -0.7349200248718262,
1007
+ "logqs/rejected": -0.8901300430297852,
1008
+ "logqs_logps/rejected": 0.03812010958790779,
1009
+ "loss": 0.2231,
1010
+ "step": 900
1011
+ },
1012
+ {
1013
+ "epoch": 0.3651319089176447,
1014
+ "grad_norm": 0.89453125,
1015
+ "learning_rate": 4.004941640907033e-05,
1016
+ "logps_logqs/chosen": 0.07090075314044952,
1017
+ "logqs/chosen": -0.7767890095710754,
1018
+ "logqs/rejected": -0.881528377532959,
1019
+ "logqs_logps/rejected": 0.04279327765107155,
1020
+ "loss": 0.2177,
1021
+ "step": 910
1022
+ },
1023
+ {
1024
+ "epoch": 0.3691443474771793,
1025
+ "grad_norm": 0.95703125,
1026
+ "learning_rate": 3.97682196702858e-05,
1027
+ "logps_logqs/chosen": 0.07161594927310944,
1028
+ "logqs/chosen": -0.7564586400985718,
1029
+ "logqs/rejected": -0.8816903829574585,
1030
+ "logqs_logps/rejected": 0.045852385461330414,
1031
+ "loss": 0.2223,
1032
+ "step": 920
1033
+ },
1034
+ {
1035
+ "epoch": 0.3731567860367138,
1036
+ "grad_norm": 0.86328125,
1037
+ "learning_rate": 3.9484123254884364e-05,
1038
+ "logps_logqs/chosen": 0.0665770024061203,
1039
+ "logqs/chosen": -0.7706209421157837,
1040
+ "logqs/rejected": -0.9511642456054688,
1041
+ "logqs_logps/rejected": 0.04237721115350723,
1042
+ "loss": 0.223,
1043
+ "step": 930
1044
+ },
1045
+ {
1046
+ "epoch": 0.37716922459624835,
1047
+ "grad_norm": 1.234375,
1048
+ "learning_rate": 3.919718294397917e-05,
1049
+ "logps_logqs/chosen": 0.0625394806265831,
1050
+ "logqs/chosen": -0.7470197677612305,
1051
+ "logqs/rejected": -0.9170467257499695,
1052
+ "logqs_logps/rejected": 0.039193086326122284,
1053
+ "loss": 0.2152,
1054
+ "step": 940
1055
+ },
1056
+ {
1057
+ "epoch": 0.38118166315578295,
1058
+ "grad_norm": 1.0234375,
1059
+ "learning_rate": 3.890745507707009e-05,
1060
+ "logps_logqs/chosen": 0.07387630641460419,
1061
+ "logqs/chosen": -0.8002737760543823,
1062
+ "logqs/rejected": -0.9207932353019714,
1063
+ "logqs_logps/rejected": 0.042600203305482864,
1064
+ "loss": 0.2218,
1065
+ "step": 950
1066
+ },
1067
+ {
1068
+ "epoch": 0.3851941017153175,
1069
+ "grad_norm": 0.921875,
1070
+ "learning_rate": 3.861499654098164e-05,
1071
+ "logps_logqs/chosen": 0.06455671042203903,
1072
+ "logqs/chosen": -0.7371721267700195,
1073
+ "logqs/rejected": -0.9134686589241028,
1074
+ "logqs_logps/rejected": 0.04233291745185852,
1075
+ "loss": 0.2122,
1076
+ "step": 960
1077
+ },
1078
+ {
1079
+ "epoch": 0.389206540274852,
1080
+ "grad_norm": 0.953125,
1081
+ "learning_rate": 3.831986475869354e-05,
1082
+ "logps_logqs/chosen": 0.06445468217134476,
1083
+ "logqs/chosen": -0.8044613599777222,
1084
+ "logqs/rejected": -1.0282663106918335,
1085
+ "logqs_logps/rejected": 0.038126152008771896,
1086
+ "loss": 0.224,
1087
+ "step": 970
1088
+ },
1089
+ {
1090
+ "epoch": 0.3932189788343866,
1091
+ "grad_norm": 1.03125,
1092
+ "learning_rate": 3.802211767806592e-05,
1093
+ "logps_logqs/chosen": 0.06315324455499649,
1094
+ "logqs/chosen": -0.755436897277832,
1095
+ "logqs/rejected": -0.892535388469696,
1096
+ "logqs_logps/rejected": 0.03698495030403137,
1097
+ "loss": 0.21,
1098
+ "step": 980
1099
+ },
1100
+ {
1101
+ "epoch": 0.39723141739392115,
1102
+ "grad_norm": 1.0078125,
1103
+ "learning_rate": 3.772181376046154e-05,
1104
+ "logps_logqs/chosen": 0.06318236142396927,
1105
+ "logqs/chosen": -0.779813289642334,
1106
+ "logqs/rejected": -0.9424177408218384,
1107
+ "logqs_logps/rejected": 0.04168635606765747,
1108
+ "loss": 0.2229,
1109
+ "step": 990
1110
+ },
1111
+ {
1112
+ "epoch": 0.4012438559534557,
1113
+ "grad_norm": 0.91015625,
1114
+ "learning_rate": 3.741901196926715e-05,
1115
+ "logps_logqs/chosen": 0.06805428117513657,
1116
+ "logqs/chosen": -0.7568292021751404,
1117
+ "logqs/rejected": -0.9653108716011047,
1118
+ "logqs_logps/rejected": 0.048825882375240326,
1119
+ "loss": 0.2281,
1120
+ "step": 1000
1121
+ },
1122
+ {
1123
+ "epoch": 0.4052562945129903,
1124
+ "grad_norm": 0.9609375,
1125
+ "learning_rate": 3.711377175831626e-05,
1126
+ "logps_logqs/chosen": 0.06242173910140991,
1127
+ "logqs/chosen": -0.7545310258865356,
1128
+ "logqs/rejected": -0.8632828593254089,
1129
+ "logqs_logps/rejected": 0.04335509240627289,
1130
+ "loss": 0.2093,
1131
+ "step": 1010
1132
+ },
1133
+ {
1134
+ "epoch": 0.4092687330725248,
1135
+ "grad_norm": 1.0078125,
1136
+ "learning_rate": 3.6806153060215625e-05,
1137
+ "logps_logqs/chosen": 0.06218956038355827,
1138
+ "logqs/chosen": -0.7818590402603149,
1139
+ "logqs/rejected": -0.9333481788635254,
1140
+ "logqs_logps/rejected": 0.04040559381246567,
1141
+ "loss": 0.2171,
1142
+ "step": 1020
1143
+ },
1144
+ {
1145
+ "epoch": 0.4132811716320594,
1146
+ "grad_norm": 0.84765625,
1147
+ "learning_rate": 3.649621627457779e-05,
1148
+ "logps_logqs/chosen": 0.06417541205883026,
1149
+ "logqs/chosen": -0.756496787071228,
1150
+ "logqs/rejected": -0.8772870898246765,
1151
+ "logqs_logps/rejected": 0.044820256531238556,
1152
+ "loss": 0.2066,
1153
+ "step": 1030
1154
+ },
1155
+ {
1156
+ "epoch": 0.41729361019159394,
1157
+ "grad_norm": 0.90625,
1158
+ "learning_rate": 3.618402225616182e-05,
1159
+ "logps_logqs/chosen": 0.06157483905553818,
1160
+ "logqs/chosen": -0.7702164649963379,
1161
+ "logqs/rejected": -0.8873571157455444,
1162
+ "logqs_logps/rejected": 0.040025461465120316,
1163
+ "loss": 0.2119,
1164
+ "step": 1040
1165
+ },
1166
+ {
1167
+ "epoch": 0.4213060487511285,
1168
+ "grad_norm": 1.015625,
1169
+ "learning_rate": 3.586963230292478e-05,
1170
+ "logps_logqs/chosen": 0.06648336350917816,
1171
+ "logqs/chosen": -0.7476903200149536,
1172
+ "logqs/rejected": -0.9481046795845032,
1173
+ "logqs_logps/rejected": 0.040808893740177155,
1174
+ "loss": 0.2153,
1175
+ "step": 1050
1176
+ },
1177
+ {
1178
+ "epoch": 0.4253184873106631,
1179
+ "grad_norm": 0.86328125,
1180
+ "learning_rate": 3.5553108143986106e-05,
1181
+ "logps_logqs/chosen": 0.06893102824687958,
1182
+ "logqs/chosen": -0.8103592991828918,
1183
+ "logqs/rejected": -0.959617018699646,
1184
+ "logqs_logps/rejected": 0.03886875510215759,
1185
+ "loss": 0.2252,
1186
+ "step": 1060
1187
+ },
1188
+ {
1189
+ "epoch": 0.4293309258701976,
1190
+ "grad_norm": 0.94140625,
1191
+ "learning_rate": 3.5234511927507386e-05,
1192
+ "logps_logqs/chosen": 0.06997676193714142,
1193
+ "logqs/chosen": -0.7442790269851685,
1194
+ "logqs/rejected": -0.8467389941215515,
1195
+ "logqs_logps/rejected": 0.0434083454310894,
1196
+ "loss": 0.2061,
1197
+ "step": 1070
1198
+ },
1199
+ {
1200
+ "epoch": 0.43334336442973215,
1201
+ "grad_norm": 1.0078125,
1202
+ "learning_rate": 3.4913906208489816e-05,
1203
+ "logps_logqs/chosen": 0.06593279540538788,
1204
+ "logqs/chosen": -0.794285237789154,
1205
+ "logqs/rejected": -0.942711353302002,
1206
+ "logqs_logps/rejected": 0.03897419571876526,
1207
+ "loss": 0.2152,
1208
+ "step": 1080
1209
+ },
1210
+ {
1211
+ "epoch": 0.43735580298926674,
1212
+ "grad_norm": 0.90234375,
1213
+ "learning_rate": 3.4591353936491804e-05,
1214
+ "logps_logqs/chosen": 0.06674528867006302,
1215
+ "logqs/chosen": -0.7946367263793945,
1216
+ "logqs/rejected": -0.8623877763748169,
1217
+ "logqs_logps/rejected": 0.04701145738363266,
1218
+ "loss": 0.2179,
1219
+ "step": 1090
1220
+ },
1221
+ {
1222
+ "epoch": 0.4413682415488013,
1223
+ "grad_norm": 0.984375,
1224
+ "learning_rate": 3.4266918443269083e-05,
1225
+ "logps_logqs/chosen": 0.07212932407855988,
1226
+ "logqs/chosen": -0.8063435554504395,
1227
+ "logqs/rejected": -0.9033867716789246,
1228
+ "logqs_logps/rejected": 0.0527394600212574,
1229
+ "loss": 0.229,
1230
+ "step": 1100
1231
+ },
1232
+ {
1233
+ "epoch": 0.4453806801083358,
1234
+ "grad_norm": 0.94921875,
1235
+ "learning_rate": 3.3940663430339816e-05,
1236
+ "logps_logqs/chosen": 0.0656530112028122,
1237
+ "logqs/chosen": -0.7609381675720215,
1238
+ "logqs/rejected": -0.8543895483016968,
1239
+ "logqs_logps/rejected": 0.04062092304229736,
1240
+ "loss": 0.2046,
1241
+ "step": 1110
1242
+ },
1243
+ {
1244
+ "epoch": 0.4493931186678704,
1245
+ "grad_norm": 0.87890625,
1246
+ "learning_rate": 3.361265295647703e-05,
1247
+ "logps_logqs/chosen": 0.0694454088807106,
1248
+ "logqs/chosen": -0.7907551527023315,
1249
+ "logqs/rejected": -0.9830646514892578,
1250
+ "logqs_logps/rejected": 0.04873238503932953,
1251
+ "loss": 0.229,
1252
+ "step": 1120
1253
+ },
1254
+ {
1255
+ "epoch": 0.45340555722740494,
1256
+ "grad_norm": 0.94140625,
1257
+ "learning_rate": 3.328295142513101e-05,
1258
+ "logps_logqs/chosen": 0.06491965055465698,
1259
+ "logqs/chosen": -0.7659338712692261,
1260
+ "logqs/rejected": -0.858781635761261,
1261
+ "logqs_logps/rejected": 0.04801768809556961,
1262
+ "loss": 0.2131,
1263
+ "step": 1130
1264
+ },
1265
+ {
1266
+ "epoch": 0.45741799578693954,
1267
+ "grad_norm": 0.96484375,
1268
+ "learning_rate": 3.295162357178392e-05,
1269
+ "logps_logqs/chosen": 0.06826496124267578,
1270
+ "logqs/chosen": -0.7904923558235168,
1271
+ "logqs/rejected": -0.9123312830924988,
1272
+ "logqs_logps/rejected": 0.0476931631565094,
1273
+ "loss": 0.2244,
1274
+ "step": 1140
1275
+ },
1276
+ {
1277
+ "epoch": 0.46143043434647407,
1278
+ "grad_norm": 0.91796875,
1279
+ "learning_rate": 3.2618734451239265e-05,
1280
+ "logps_logqs/chosen": 0.066849485039711,
1281
+ "logqs/chosen": -0.7713029980659485,
1282
+ "logqs/rejected": -0.8515326380729675,
1283
+ "logqs_logps/rejected": 0.037967417389154434,
1284
+ "loss": 0.2025,
1285
+ "step": 1150
1286
+ },
1287
+ {
1288
+ "epoch": 0.4654428729060086,
1289
+ "grad_norm": 1.0546875,
1290
+ "learning_rate": 3.2284349424848686e-05,
1291
+ "logps_logqs/chosen": 0.061885617673397064,
1292
+ "logqs/chosen": -0.7651118636131287,
1293
+ "logqs/rejected": -0.9462388753890991,
1294
+ "logqs_logps/rejected": 0.04066777601838112,
1295
+ "loss": 0.2073,
1296
+ "step": 1160
1297
+ },
1298
+ {
1299
+ "epoch": 0.4694553114655432,
1300
+ "grad_norm": 0.8515625,
1301
+ "learning_rate": 3.19485341476785e-05,
1302
+ "logps_logqs/chosen": 0.06695061177015305,
1303
+ "logqs/chosen": -0.7339809536933899,
1304
+ "logqs/rejected": -0.8749481439590454,
1305
+ "logqs_logps/rejected": 0.04051825404167175,
1306
+ "loss": 0.2124,
1307
+ "step": 1170
1308
+ },
1309
+ {
1310
+ "epoch": 0.47346775002507774,
1311
+ "grad_norm": 0.94921875,
1312
+ "learning_rate": 3.161135455561867e-05,
1313
+ "logps_logqs/chosen": 0.05254195258021355,
1314
+ "logqs/chosen": -0.7602388262748718,
1315
+ "logqs/rejected": -0.9050895571708679,
1316
+ "logqs_logps/rejected": 0.041042499244213104,
1317
+ "loss": 0.2066,
1318
+ "step": 1180
1319
+ },
1320
+ {
1321
+ "epoch": 0.4774801885846123,
1322
+ "grad_norm": 0.95703125,
1323
+ "learning_rate": 3.127287685243649e-05,
1324
+ "logps_logqs/chosen": 0.0691223293542862,
1325
+ "logqs/chosen": -0.767509400844574,
1326
+ "logqs/rejected": -0.9097784161567688,
1327
+ "logqs_logps/rejected": 0.04124459624290466,
1328
+ "loss": 0.2114,
1329
+ "step": 1190
1330
+ },
1331
+ {
1332
+ "epoch": 0.48149262714414687,
1333
+ "grad_norm": 0.984375,
1334
+ "learning_rate": 3.093316749677788e-05,
1335
+ "logps_logqs/chosen": 0.07016964256763458,
1336
+ "logqs/chosen": -0.8034747242927551,
1337
+ "logqs/rejected": -0.9332574605941772,
1338
+ "logqs_logps/rejected": 0.04192311316728592,
1339
+ "loss": 0.2191,
1340
+ "step": 1200
1341
+ },
1342
+ {
1343
+ "epoch": 0.4855050657036814,
1344
+ "grad_norm": 1.0078125,
1345
+ "learning_rate": 3.059229318911834e-05,
1346
+ "logps_logqs/chosen": 0.06674963980913162,
1347
+ "logqs/chosen": -0.8160765767097473,
1348
+ "logqs/rejected": -0.9725866317749023,
1349
+ "logqs_logps/rejected": 0.036663301289081573,
1350
+ "loss": 0.2146,
1351
+ "step": 1210
1352
+ },
1353
+ {
1354
+ "epoch": 0.489517504263216,
1355
+ "grad_norm": 0.859375,
1356
+ "learning_rate": 3.0250320858666808e-05,
1357
+ "logps_logqs/chosen": 0.05871901661157608,
1358
+ "logqs/chosen": -0.7368924617767334,
1359
+ "logqs/rejected": -0.9339553713798523,
1360
+ "logqs_logps/rejected": 0.0406537726521492,
1361
+ "loss": 0.203,
1362
+ "step": 1220
1363
+ },
1364
+ {
1365
+ "epoch": 0.49352994282275053,
1366
+ "grad_norm": 0.80859375,
1367
+ "learning_rate": 2.9907317650224202e-05,
1368
+ "logps_logqs/chosen": 0.06281201541423798,
1369
+ "logqs/chosen": -0.7343816757202148,
1370
+ "logqs/rejected": -0.832353949546814,
1371
+ "logqs_logps/rejected": 0.04407534375786781,
1372
+ "loss": 0.2028,
1373
+ "step": 1230
1374
+ },
1375
+ {
1376
+ "epoch": 0.49754238138228507,
1377
+ "grad_norm": 0.88671875,
1378
+ "learning_rate": 2.9563350910999987e-05,
1379
+ "logps_logqs/chosen": 0.06290856003761292,
1380
+ "logqs/chosen": -0.767212986946106,
1381
+ "logqs/rejected": -0.8938047289848328,
1382
+ "logqs_logps/rejected": 0.04681697487831116,
1383
+ "loss": 0.208,
1384
+ "step": 1240
1385
+ },
1386
+ {
1387
+ "epoch": 0.5015548199418196,
1388
+ "grad_norm": 0.87890625,
1389
+ "learning_rate": 2.9218488177388708e-05,
1390
+ "logps_logqs/chosen": 0.05903799459338188,
1391
+ "logqs/chosen": -0.764884352684021,
1392
+ "logqs/rejected": -0.980311393737793,
1393
+ "logqs_logps/rejected": 0.03830552473664284,
1394
+ "loss": 0.2067,
1395
+ "step": 1250
1396
+ },
1397
+ {
1398
+ "epoch": 0.5055672585013542,
1399
+ "grad_norm": 1.0078125,
1400
+ "learning_rate": 2.8872797161709592e-05,
1401
+ "logps_logqs/chosen": 0.0676959678530693,
1402
+ "logqs/chosen": -0.8294798135757446,
1403
+ "logqs/rejected": -1.0086824893951416,
1404
+ "logqs_logps/rejected": 0.04707977548241615,
1405
+ "loss": 0.2281,
1406
+ "step": 1260
1407
+ },
1408
+ {
1409
+ "epoch": 0.5095796970608888,
1410
+ "grad_norm": 0.91796875,
1411
+ "learning_rate": 2.8526345738911514e-05,
1412
+ "logps_logqs/chosen": 0.06489823758602142,
1413
+ "logqs/chosen": -0.7817304730415344,
1414
+ "logqs/rejected": -0.964560866355896,
1415
+ "logqs_logps/rejected": 0.033502064645290375,
1416
+ "loss": 0.2112,
1417
+ "step": 1270
1418
+ },
1419
+ {
1420
+ "epoch": 0.5135921356204233,
1421
+ "grad_norm": 1.0625,
1422
+ "learning_rate": 2.817920193324598e-05,
1423
+ "logps_logqs/chosen": 0.06510399281978607,
1424
+ "logqs/chosen": -0.7938090562820435,
1425
+ "logqs/rejected": -0.9560580253601074,
1426
+ "logqs_logps/rejected": 0.036699842661619186,
1427
+ "loss": 0.2083,
1428
+ "step": 1280
1429
+ },
1430
+ {
1431
+ "epoch": 0.5176045741799579,
1432
+ "grad_norm": 0.91015625,
1433
+ "learning_rate": 2.7831433904910966e-05,
1434
+ "logps_logqs/chosen": 0.06948190927505493,
1435
+ "logqs/chosen": -0.786105751991272,
1436
+ "logqs/rejected": -1.0199264287948608,
1437
+ "logqs_logps/rejected": 0.04138697311282158,
1438
+ "loss": 0.2193,
1439
+ "step": 1290
1440
+ },
1441
+ {
1442
+ "epoch": 0.5216170127394925,
1443
+ "grad_norm": 0.921875,
1444
+ "learning_rate": 2.7483109936667833e-05,
1445
+ "logps_logqs/chosen": 0.05654798075556755,
1446
+ "logqs/chosen": -0.7541887164115906,
1447
+ "logqs/rejected": -0.9388119578361511,
1448
+ "logqs_logps/rejected": 0.0368928536772728,
1449
+ "loss": 0.206,
1450
+ "step": 1300
1451
+ },
1452
+ {
1453
+ "epoch": 0.5256294512990269,
1454
+ "grad_norm": 0.75390625,
1455
+ "learning_rate": 2.7134298420434405e-05,
1456
+ "logps_logqs/chosen": 0.06768162548542023,
1457
+ "logqs/chosen": -0.751132607460022,
1458
+ "logqs/rejected": -0.9309018850326538,
1459
+ "logqs_logps/rejected": 0.040372543036937714,
1460
+ "loss": 0.2047,
1461
+ "step": 1310
1462
+ },
1463
+ {
1464
+ "epoch": 0.5296418898585615,
1465
+ "grad_norm": 0.90234375,
1466
+ "learning_rate": 2.6785067843856437e-05,
1467
+ "logps_logqs/chosen": 0.0685514509677887,
1468
+ "logqs/chosen": -0.7638227343559265,
1469
+ "logqs/rejected": -0.9002357721328735,
1470
+ "logqs_logps/rejected": 0.04437505453824997,
1471
+ "loss": 0.208,
1472
+ "step": 1320
1473
+ },
1474
+ {
1475
+ "epoch": 0.5336543284180961,
1476
+ "grad_norm": 0.88671875,
1477
+ "learning_rate": 2.6435486776860397e-05,
1478
+ "logps_logqs/chosen": 0.06796412169933319,
1479
+ "logqs/chosen": -0.7779960632324219,
1480
+ "logqs/rejected": -0.8985629081726074,
1481
+ "logqs_logps/rejected": 0.04421251639723778,
1482
+ "loss": 0.2105,
1483
+ "step": 1330
1484
+ },
1485
+ {
1486
+ "epoch": 0.5376667669776306,
1487
+ "grad_norm": 1.03125,
1488
+ "learning_rate": 2.608562385819004e-05,
1489
+ "logps_logqs/chosen": 0.07138559222221375,
1490
+ "logqs/chosen": -0.7967632412910461,
1491
+ "logqs/rejected": -0.961688220500946,
1492
+ "logqs_logps/rejected": 0.04707226902246475,
1493
+ "loss": 0.2143,
1494
+ "step": 1340
1495
+ },
1496
+ {
1497
+ "epoch": 0.5416792055371652,
1498
+ "grad_norm": 0.8671875,
1499
+ "learning_rate": 2.5735547781929486e-05,
1500
+ "logps_logqs/chosen": 0.06736733019351959,
1501
+ "logqs/chosen": -0.786482036113739,
1502
+ "logqs/rejected": -0.9260354042053223,
1503
+ "logqs_logps/rejected": 0.040234483778476715,
1504
+ "loss": 0.2095,
1505
+ "step": 1350
1506
+ },
1507
+ {
1508
+ "epoch": 0.5456916440966998,
1509
+ "grad_norm": 1.0546875,
1510
+ "learning_rate": 2.5385327284015442e-05,
1511
+ "logps_logqs/chosen": 0.05687067657709122,
1512
+ "logqs/chosen": -0.7579948902130127,
1513
+ "logqs/rejected": -0.8798167109489441,
1514
+ "logqs_logps/rejected": 0.04075098782777786,
1515
+ "loss": 0.211,
1516
+ "step": 1360
1517
+ },
1518
+ {
1519
+ "epoch": 0.5497040826562343,
1520
+ "grad_norm": 0.7734375,
1521
+ "learning_rate": 2.5035031128741186e-05,
1522
+ "logps_logqs/chosen": 0.054413218051195145,
1523
+ "logqs/chosen": -0.7419102191925049,
1524
+ "logqs/rejected": -0.9421182870864868,
1525
+ "logqs_logps/rejected": 0.04363472759723663,
1526
+ "loss": 0.1988,
1527
+ "step": 1370
1528
+ },
1529
+ {
1530
+ "epoch": 0.5537165212157689,
1531
+ "grad_norm": 0.99609375,
1532
+ "learning_rate": 2.468472809525499e-05,
1533
+ "logps_logqs/chosen": 0.0663304477930069,
1534
+ "logqs/chosen": -0.7536656856536865,
1535
+ "logqs/rejected": -0.8601825833320618,
1536
+ "logqs_logps/rejected": 0.04670237749814987,
1537
+ "loss": 0.2015,
1538
+ "step": 1380
1539
+ },
1540
+ {
1541
+ "epoch": 0.5577289597753035,
1542
+ "grad_norm": 1.0546875,
1543
+ "learning_rate": 2.433448696405563e-05,
1544
+ "logps_logqs/chosen": 0.0683605819940567,
1545
+ "logqs/chosen": -0.7921854853630066,
1546
+ "logqs/rejected": -0.9560282826423645,
1547
+ "logqs_logps/rejected": 0.04194676876068115,
1548
+ "loss": 0.2153,
1549
+ "step": 1390
1550
+ },
1551
+ {
1552
+ "epoch": 0.561741398334838,
1553
+ "grad_norm": 0.875,
1554
+ "learning_rate": 2.3984376503487657e-05,
1555
+ "logps_logqs/chosen": 0.059657491743564606,
1556
+ "logqs/chosen": -0.7732149362564087,
1557
+ "logqs/rejected": -0.9037120938301086,
1558
+ "logqs_logps/rejected": 0.047056883573532104,
1559
+ "loss": 0.2059,
1560
+ "step": 1400
1561
+ },
1562
+ {
1563
+ "epoch": 0.5657538368943725,
1564
+ "grad_norm": 1.1015625,
1565
+ "learning_rate": 2.363446545623896e-05,
1566
+ "logps_logqs/chosen": 0.06571358442306519,
1567
+ "logqs/chosen": -0.7903417348861694,
1568
+ "logqs/rejected": -0.8886157870292664,
1569
+ "logqs_logps/rejected": 0.044423289597034454,
1570
+ "loss": 0.2137,
1571
+ "step": 1410
1572
+ },
1573
+ {
1574
+ "epoch": 0.5697662754539071,
1575
+ "grad_norm": 0.7734375,
1576
+ "learning_rate": 2.3284822525843513e-05,
1577
+ "logps_logqs/chosen": 0.06020021438598633,
1578
+ "logqs/chosen": -0.774948239326477,
1579
+ "logqs/rejected": -0.8824418783187866,
1580
+ "logqs_logps/rejected": 0.047613807022571564,
1581
+ "loss": 0.2102,
1582
+ "step": 1420
1583
+ },
1584
+ {
1585
+ "epoch": 0.5737787140134417,
1586
+ "grad_norm": 0.93359375,
1587
+ "learning_rate": 2.2935516363191693e-05,
1588
+ "logps_logqs/chosen": 0.05629735440015793,
1589
+ "logqs/chosen": -0.7801834940910339,
1590
+ "logqs/rejected": -0.9769400358200073,
1591
+ "logqs_logps/rejected": 0.04005488008260727,
1592
+ "loss": 0.1992,
1593
+ "step": 1430
1594
+ },
1595
+ {
1596
+ "epoch": 0.5777911525729762,
1597
+ "grad_norm": 0.9765625,
1598
+ "learning_rate": 2.2586615553050958e-05,
1599
+ "logps_logqs/chosen": 0.06125611066818237,
1600
+ "logqs/chosen": -0.7764580845832825,
1601
+ "logqs/rejected": -0.9078529477119446,
1602
+ "logqs_logps/rejected": 0.047422997653484344,
1603
+ "loss": 0.2102,
1604
+ "step": 1440
1605
+ },
1606
+ {
1607
+ "epoch": 0.5818035911325108,
1608
+ "grad_norm": 1.0390625,
1609
+ "learning_rate": 2.2238188600599557e-05,
1610
+ "logps_logqs/chosen": 0.06047336012125015,
1611
+ "logqs/chosen": -0.7722862958908081,
1612
+ "logqs/rejected": -0.9338611364364624,
1613
+ "logqs_logps/rejected": 0.04897394776344299,
1614
+ "loss": 0.2118,
1615
+ "step": 1450
1616
+ },
1617
+ {
1618
+ "epoch": 0.5858160296920454,
1619
+ "grad_norm": 0.8046875,
1620
+ "learning_rate": 2.1890303917975793e-05,
1621
+ "logps_logqs/chosen": 0.06230146437883377,
1622
+ "logqs/chosen": -0.7600993514060974,
1623
+ "logqs/rejected": -0.894098162651062,
1624
+ "logqs_logps/rejected": 0.04384886845946312,
1625
+ "loss": 0.2098,
1626
+ "step": 1460
1627
+ },
1628
+ {
1629
+ "epoch": 0.5898284682515799,
1630
+ "grad_norm": 1.0703125,
1631
+ "learning_rate": 2.1543029810845636e-05,
1632
+ "logps_logqs/chosen": 0.0581694059073925,
1633
+ "logqs/chosen": -0.7508013248443604,
1634
+ "logqs/rejected": -0.8761455416679382,
1635
+ "logqs_logps/rejected": 0.047836847603321075,
1636
+ "loss": 0.2022,
1637
+ "step": 1470
1638
+ },
1639
+ {
1640
+ "epoch": 0.5938409068111145,
1641
+ "grad_norm": 0.9609375,
1642
+ "learning_rate": 2.1196434464991143e-05,
1643
+ "logps_logqs/chosen": 0.0635426789522171,
1644
+ "logqs/chosen": -0.729708731174469,
1645
+ "logqs/rejected": -0.9138385653495789,
1646
+ "logqs_logps/rejected": 0.04027016833424568,
1647
+ "loss": 0.2025,
1648
+ "step": 1480
1649
+ },
1650
+ {
1651
+ "epoch": 0.597853345370649,
1652
+ "grad_norm": 0.86328125,
1653
+ "learning_rate": 2.085058593292254e-05,
1654
+ "logps_logqs/chosen": 0.06386588513851166,
1655
+ "logqs/chosen": -0.7314515709877014,
1656
+ "logqs/rejected": -0.920465350151062,
1657
+ "logqs_logps/rejected": 0.044058460742235184,
1658
+ "loss": 0.201,
1659
+ "step": 1490
1660
+ },
1661
+ {
1662
+ "epoch": 0.6018657839301835,
1663
+ "grad_norm": 0.953125,
1664
+ "learning_rate": 2.0505552120516347e-05,
1665
+ "logps_logqs/chosen": 0.059891510754823685,
1666
+ "logqs/chosen": -0.772852897644043,
1667
+ "logqs/rejected": -0.9922389984130859,
1668
+ "logqs_logps/rejected": 0.038037288933992386,
1669
+ "loss": 0.2087,
1670
+ "step": 1500
1671
+ },
1672
+ {
1673
+ "epoch": 0.6058782224897181,
1674
+ "grad_norm": 0.97265625,
1675
+ "learning_rate": 2.0161400773682387e-05,
1676
+ "logps_logqs/chosen": 0.06451881676912308,
1677
+ "logqs/chosen": -0.7392505407333374,
1678
+ "logqs/rejected": -0.8385832905769348,
1679
+ "logqs_logps/rejected": 0.04175102710723877,
1680
+ "loss": 0.1949,
1681
+ "step": 1510
1682
+ },
1683
+ {
1684
+ "epoch": 0.6098906610492527,
1685
+ "grad_norm": 0.82421875,
1686
+ "learning_rate": 1.9818199465062122e-05,
1687
+ "logps_logqs/chosen": 0.057556964457035065,
1688
+ "logqs/chosen": -0.7747632265090942,
1689
+ "logqs/rejected": -0.9425610303878784,
1690
+ "logqs_logps/rejected": 0.04500174522399902,
1691
+ "loss": 0.1981,
1692
+ "step": 1520
1693
+ },
1694
+ {
1695
+ "epoch": 0.6139030996087872,
1696
+ "grad_norm": 0.953125,
1697
+ "learning_rate": 1.947601558076112e-05,
1698
+ "logps_logqs/chosen": 0.06366400420665741,
1699
+ "logqs/chosen": -0.7735481262207031,
1700
+ "logqs/rejected": -0.9604089856147766,
1701
+ "logqs_logps/rejected": 0.03997362032532692,
1702
+ "loss": 0.2085,
1703
+ "step": 1530
1704
+ },
1705
+ {
1706
+ "epoch": 0.6179155381683218,
1707
+ "grad_norm": 0.8359375,
1708
+ "learning_rate": 1.913491630711803e-05,
1709
+ "logps_logqs/chosen": 0.059332527220249176,
1710
+ "logqs/chosen": -0.7706314921379089,
1711
+ "logqs/rejected": -0.9478508234024048,
1712
+ "logqs_logps/rejected": 0.04246944189071655,
1713
+ "loss": 0.2092,
1714
+ "step": 1540
1715
+ },
1716
+ {
1717
+ "epoch": 0.6219279767278564,
1718
+ "grad_norm": 1.015625,
1719
+ "learning_rate": 1.8794968617512827e-05,
1720
+ "logps_logqs/chosen": 0.059884555637836456,
1721
+ "logqs/chosen": -0.7863162755966187,
1722
+ "logqs/rejected": -0.9061921238899231,
1723
+ "logqs_logps/rejected": 0.040217991918325424,
1724
+ "loss": 0.2126,
1725
+ "step": 1550
1726
+ },
1727
+ {
1728
+ "epoch": 0.6259404152873909,
1729
+ "grad_norm": 0.97265625,
1730
+ "learning_rate": 1.8456239259216935e-05,
1731
+ "logps_logqs/chosen": 0.06425374746322632,
1732
+ "logqs/chosen": -0.8034299612045288,
1733
+ "logqs/rejected": -0.9601300358772278,
1734
+ "logqs_logps/rejected": 0.041518889367580414,
1735
+ "loss": 0.208,
1736
+ "step": 1560
1737
+ },
1738
+ {
1739
+ "epoch": 0.6299528538469255,
1740
+ "grad_norm": 0.90234375,
1741
+ "learning_rate": 1.8118794740287626e-05,
1742
+ "logps_logqs/chosen": 0.06399701535701752,
1743
+ "logqs/chosen": -0.7407925724983215,
1744
+ "logqs/rejected": -0.9087139964103699,
1745
+ "logqs_logps/rejected": 0.04571211710572243,
1746
+ "loss": 0.2112,
1747
+ "step": 1570
1748
+ },
1749
+ {
1750
+ "epoch": 0.63396529240646,
1751
+ "grad_norm": 0.91015625,
1752
+ "learning_rate": 1.778270131650948e-05,
1753
+ "logps_logqs/chosen": 0.0619058683514595,
1754
+ "logqs/chosen": -0.7647662162780762,
1755
+ "logqs/rejected": -0.8764744997024536,
1756
+ "logqs_logps/rejected": 0.047727279365062714,
1757
+ "loss": 0.2061,
1758
+ "step": 1580
1759
+ },
1760
+ {
1761
+ "epoch": 0.6379777309659946,
1762
+ "grad_norm": 0.78515625,
1763
+ "learning_rate": 1.7448024978385323e-05,
1764
+ "logps_logqs/chosen": 0.05647442862391472,
1765
+ "logqs/chosen": -0.6957526803016663,
1766
+ "logqs/rejected": -0.862210750579834,
1767
+ "logqs_logps/rejected": 0.04325004667043686,
1768
+ "loss": 0.1936,
1769
+ "step": 1590
1770
+ },
1771
+ {
1772
+ "epoch": 0.6419901695255291,
1773
+ "grad_norm": 0.828125,
1774
+ "learning_rate": 1.7114831438179304e-05,
1775
+ "logps_logqs/chosen": 0.05817713588476181,
1776
+ "logqs/chosen": -0.8131221532821655,
1777
+ "logqs/rejected": -0.9595745801925659,
1778
+ "logqs_logps/rejected": 0.04276737570762634,
1779
+ "loss": 0.2054,
1780
+ "step": 1600
1781
+ },
1782
+ {
1783
+ "epoch": 0.6460026080850637,
1784
+ "grad_norm": 1.125,
1785
+ "learning_rate": 1.678318611701456e-05,
1786
+ "logps_logqs/chosen": 0.059329450130462646,
1787
+ "logqs/chosen": -0.7848485708236694,
1788
+ "logqs/rejected": -0.9603179693222046,
1789
+ "logqs_logps/rejected": 0.04404183477163315,
1790
+ "loss": 0.2073,
1791
+ "step": 1610
1792
+ },
1793
+ {
1794
+ "epoch": 0.6500150466445983,
1795
+ "grad_norm": 0.875,
1796
+ "learning_rate": 1.6453154132028036e-05,
1797
+ "logps_logqs/chosen": 0.06459563970565796,
1798
+ "logqs/chosen": -0.7197882533073425,
1799
+ "logqs/rejected": -0.8624848127365112,
1800
+ "logqs_logps/rejected": 0.04526801407337189,
1801
+ "loss": 0.1997,
1802
+ "step": 1620
1803
+ },
1804
+ {
1805
+ "epoch": 0.6540274852041328,
1806
+ "grad_norm": 1.0,
1807
+ "learning_rate": 1.6124800283585047e-05,
1808
+ "logps_logqs/chosen": 0.06266516447067261,
1809
+ "logqs/chosen": -0.7793084383010864,
1810
+ "logqs/rejected": -0.9734363555908203,
1811
+ "logqs_logps/rejected": 0.03937797620892525,
1812
+ "loss": 0.2166,
1813
+ "step": 1630
1814
+ },
1815
+ {
1816
+ "epoch": 0.6580399237636674,
1817
+ "grad_norm": 1.015625,
1818
+ "learning_rate": 1.5798189042556e-05,
1819
+ "logps_logqs/chosen": 0.06362553685903549,
1820
+ "logqs/chosen": -0.8266116976737976,
1821
+ "logqs/rejected": -0.9903604388237,
1822
+ "logqs_logps/rejected": 0.044061560183763504,
1823
+ "loss": 0.2128,
1824
+ "step": 1640
1825
+ },
1826
+ {
1827
+ "epoch": 0.662052362323202,
1828
+ "grad_norm": 0.8984375,
1829
+ "learning_rate": 1.547338453765781e-05,
1830
+ "logps_logqs/chosen": 0.06749062240123749,
1831
+ "logqs/chosen": -0.7770861983299255,
1832
+ "logqs/rejected": -0.9624859094619751,
1833
+ "logqs_logps/rejected": 0.0393180288374424,
1834
+ "loss": 0.203,
1835
+ "step": 1650
1836
+ },
1837
+ {
1838
+ "epoch": 0.6660648008827365,
1839
+ "grad_norm": 1.03125,
1840
+ "learning_rate": 1.5150450542862465e-05,
1841
+ "logps_logqs/chosen": 0.05758975073695183,
1842
+ "logqs/chosen": -0.7523698806762695,
1843
+ "logqs/rejected": -0.8969352841377258,
1844
+ "logqs_logps/rejected": 0.040392350405454636,
1845
+ "loss": 0.2035,
1846
+ "step": 1660
1847
+ },
1848
+ {
1849
+ "epoch": 0.670077239442271,
1850
+ "grad_norm": 1.1484375,
1851
+ "learning_rate": 1.482945046487535e-05,
1852
+ "logps_logqs/chosen": 0.061460964381694794,
1853
+ "logqs/chosen": -0.770228385925293,
1854
+ "logqs/rejected": -0.9278268814086914,
1855
+ "logqs_logps/rejected": 0.04707395285367966,
1856
+ "loss": 0.2084,
1857
+ "step": 1670
1858
+ },
1859
+ {
1860
+ "epoch": 0.6740896780018056,
1861
+ "grad_norm": 0.79296875,
1862
+ "learning_rate": 1.4510447330685572e-05,
1863
+ "logps_logqs/chosen": 0.061688266694545746,
1864
+ "logqs/chosen": -0.7408064603805542,
1865
+ "logqs/rejected": -0.8874767422676086,
1866
+ "logqs_logps/rejected": 0.04055311530828476,
1867
+ "loss": 0.1933,
1868
+ "step": 1680
1869
+ },
1870
+ {
1871
+ "epoch": 0.6781021165613401,
1872
+ "grad_norm": 0.84765625,
1873
+ "learning_rate": 1.4193503775190869e-05,
1874
+ "logps_logqs/chosen": 0.06273935735225677,
1875
+ "logqs/chosen": -0.7087291479110718,
1876
+ "logqs/rejected": -0.9201680421829224,
1877
+ "logqs_logps/rejected": 0.04273274913430214,
1878
+ "loss": 0.1981,
1879
+ "step": 1690
1880
+ },
1881
+ {
1882
+ "epoch": 0.6821145551208747,
1883
+ "grad_norm": 0.859375,
1884
+ "learning_rate": 1.3878682028899542e-05,
1885
+ "logps_logqs/chosen": 0.05558650940656662,
1886
+ "logqs/chosen": -0.759759783744812,
1887
+ "logqs/rejected": -0.9058607220649719,
1888
+ "logqs_logps/rejected": 0.04389805346727371,
1889
+ "loss": 0.1978,
1890
+ "step": 1700
1891
+ },
1892
+ {
1893
+ "epoch": 0.6861269936804093,
1894
+ "grad_norm": 0.84375,
1895
+ "learning_rate": 1.3566043905711739e-05,
1896
+ "logps_logqs/chosen": 0.06162220984697342,
1897
+ "logqs/chosen": -0.7727446556091309,
1898
+ "logqs/rejected": -0.8560484647750854,
1899
+ "logqs_logps/rejected": 0.046323083341121674,
1900
+ "loss": 0.1981,
1901
+ "step": 1710
1902
+ },
1903
+ {
1904
+ "epoch": 0.6901394322399438,
1905
+ "grad_norm": 0.98828125,
1906
+ "learning_rate": 1.3255650790782593e-05,
1907
+ "logps_logqs/chosen": 0.06615598499774933,
1908
+ "logqs/chosen": -0.7760972380638123,
1909
+ "logqs/rejected": -0.9352099299430847,
1910
+ "logqs_logps/rejected": 0.036824874579906464,
1911
+ "loss": 0.2053,
1912
+ "step": 1720
1913
+ },
1914
+ {
1915
+ "epoch": 0.6941518707994784,
1916
+ "grad_norm": 1.078125,
1917
+ "learning_rate": 1.2947563628469487e-05,
1918
+ "logps_logqs/chosen": 0.06651194393634796,
1919
+ "logqs/chosen": -0.7634227871894836,
1920
+ "logqs/rejected": -0.8523470759391785,
1921
+ "logqs_logps/rejected": 0.0407404787838459,
1922
+ "loss": 0.201,
1923
+ "step": 1730
1924
+ },
1925
+ {
1926
+ "epoch": 0.698164309359013,
1927
+ "grad_norm": 0.9375,
1928
+ "learning_rate": 1.2641842910365882e-05,
1929
+ "logps_logqs/chosen": 0.06568791717290878,
1930
+ "logqs/chosen": -0.7720048427581787,
1931
+ "logqs/rejected": -0.8878447413444519,
1932
+ "logqs_logps/rejected": 0.04862860590219498,
1933
+ "loss": 0.2112,
1934
+ "step": 1740
1935
+ },
1936
+ {
1937
+ "epoch": 0.7021767479185475,
1938
+ "grad_norm": 0.84375,
1939
+ "learning_rate": 1.2338548663424063e-05,
1940
+ "logps_logqs/chosen": 0.06173808500170708,
1941
+ "logqs/chosen": -0.7485703229904175,
1942
+ "logqs/rejected": -0.9079939126968384,
1943
+ "logqs_logps/rejected": 0.039516132324934006,
1944
+ "loss": 0.1972,
1945
+ "step": 1750
1946
+ },
1947
+ {
1948
+ "epoch": 0.706189186478082,
1949
+ "grad_norm": 0.828125,
1950
+ "learning_rate": 1.2037740438169118e-05,
1951
+ "logps_logqs/chosen": 0.05886746197938919,
1952
+ "logqs/chosen": -0.7420176267623901,
1953
+ "logqs/rejected": -0.86164790391922,
1954
+ "logqs_logps/rejected": 0.04042860120534897,
1955
+ "loss": 0.1986,
1956
+ "step": 1760
1957
+ },
1958
+ {
1959
+ "epoch": 0.7102016250376166,
1960
+ "grad_norm": 0.89453125,
1961
+ "learning_rate": 1.173947729700644e-05,
1962
+ "logps_logqs/chosen": 0.06122485548257828,
1963
+ "logqs/chosen": -0.7482978701591492,
1964
+ "logqs/rejected": -0.8508716821670532,
1965
+ "logqs_logps/rejected": 0.04005607217550278,
1966
+ "loss": 0.2006,
1967
+ "step": 1770
1968
+ },
1969
+ {
1970
+ "epoch": 0.7142140635971511,
1971
+ "grad_norm": 0.9296875,
1972
+ "learning_rate": 1.1443817802625045e-05,
1973
+ "logps_logqs/chosen": 0.06048593670129776,
1974
+ "logqs/chosen": -0.7596639394760132,
1975
+ "logqs/rejected": -0.943291187286377,
1976
+ "logqs_logps/rejected": 0.03989649564027786,
1977
+ "loss": 0.1975,
1978
+ "step": 1780
1979
+ },
1980
+ {
1981
+ "epoch": 0.7182265021566857,
1982
+ "grad_norm": 0.828125,
1983
+ "learning_rate": 1.1150820006499102e-05,
1984
+ "logps_logqs/chosen": 0.06095385551452637,
1985
+ "logqs/chosen": -0.8086657524108887,
1986
+ "logqs/rejected": -0.9322345852851868,
1987
+ "logqs_logps/rejected": 0.03858863189816475,
1988
+ "loss": 0.2043,
1989
+ "step": 1790
1990
+ },
1991
+ {
1992
+ "epoch": 0.7222389407162203,
1993
+ "grad_norm": 0.8984375,
1994
+ "learning_rate": 1.0860541437489704e-05,
1995
+ "logps_logqs/chosen": 0.06901264935731888,
1996
+ "logqs/chosen": -0.796691358089447,
1997
+ "logqs/rejected": -0.9594961404800415,
1998
+ "logqs_logps/rejected": 0.04785243421792984,
1999
+ "loss": 0.2166,
2000
+ "step": 1800
2001
+ },
2002
+ {
2003
+ "epoch": 0.7262513792757549,
2004
+ "grad_norm": 0.7890625,
2005
+ "learning_rate": 1.0573039090549374e-05,
2006
+ "logps_logqs/chosen": 0.06223682314157486,
2007
+ "logqs/chosen": -0.7634943723678589,
2008
+ "logqs/rejected": -0.9174191355705261,
2009
+ "logqs_logps/rejected": 0.03920085355639458,
2010
+ "loss": 0.1951,
2011
+ "step": 1810
2012
+ },
2013
+ {
2014
+ "epoch": 0.7302638178352894,
2015
+ "grad_norm": 0.94921875,
2016
+ "learning_rate": 1.0288369415531335e-05,
2017
+ "logps_logqs/chosen": 0.0662630945444107,
2018
+ "logqs/chosen": -0.7865787148475647,
2019
+ "logqs/rejected": -0.9215148091316223,
2020
+ "logqs_logps/rejected": 0.04244377464056015,
2021
+ "loss": 0.2054,
2022
+ "step": 1820
2023
+ },
2024
+ {
2025
+ "epoch": 0.734276256394824,
2026
+ "grad_norm": 0.890625,
2027
+ "learning_rate": 1.0006588306105832e-05,
2028
+ "logps_logqs/chosen": 0.0686667412519455,
2029
+ "logqs/chosen": -0.8002827763557434,
2030
+ "logqs/rejected": -0.9347888827323914,
2031
+ "logqs_logps/rejected": 0.046215157955884933,
2032
+ "loss": 0.2087,
2033
+ "step": 1830
2034
+ },
2035
+ {
2036
+ "epoch": 0.7382886949543586,
2037
+ "grad_norm": 0.84765625,
2038
+ "learning_rate": 9.727751088785622e-06,
2039
+ "logps_logqs/chosen": 0.06760746985673904,
2040
+ "logqs/chosen": -0.7690545320510864,
2041
+ "logqs/rejected": -0.9443781971931458,
2042
+ "logqs_logps/rejected": 0.038559213280677795,
2043
+ "loss": 0.2029,
2044
+ "step": 1840
2045
+ },
2046
+ {
2047
+ "epoch": 0.742301133513893,
2048
+ "grad_norm": 0.88671875,
2049
+ "learning_rate": 9.451912512062863e-06,
2050
+ "logps_logqs/chosen": 0.06737495958805084,
2051
+ "logqs/chosen": -0.7588866949081421,
2052
+ "logqs/rejected": -0.8812012672424316,
2053
+ "logqs_logps/rejected": 0.04380820319056511,
2054
+ "loss": 0.2055,
2055
+ "step": 1850
2056
+ },
2057
+ {
2058
+ "epoch": 0.7463135720734276,
2059
+ "grad_norm": 0.92578125,
2060
+ "learning_rate": 9.179126735659513e-06,
2061
+ "logps_logqs/chosen": 0.06551609933376312,
2062
+ "logqs/chosen": -0.7602046728134155,
2063
+ "logqs/rejected": -0.8694095611572266,
2064
+ "logqs_logps/rejected": 0.042011164128780365,
2065
+ "loss": 0.2,
2066
+ "step": 1860
2067
+ },
2068
+ {
2069
+ "epoch": 0.7503260106329622,
2070
+ "grad_norm": 0.87109375,
2071
+ "learning_rate": 8.909447319893268e-06,
2072
+ "logps_logqs/chosen": 0.06104401499032974,
2073
+ "logqs/chosen": -0.7819545865058899,
2074
+ "logqs/rejected": -0.9451535940170288,
2075
+ "logqs_logps/rejected": 0.042893193662166595,
2076
+ "loss": 0.2034,
2077
+ "step": 1870
2078
+ },
2079
+ {
2080
+ "epoch": 0.7543384491924967,
2081
+ "grad_norm": 0.828125,
2082
+ "learning_rate": 8.642927215161221e-06,
2083
+ "logps_logqs/chosen": 0.05745772644877434,
2084
+ "logqs/chosen": -0.7933343648910522,
2085
+ "logqs/rejected": -0.9668875932693481,
2086
+ "logqs_logps/rejected": 0.042098429054021835,
2087
+ "loss": 0.2053,
2088
+ "step": 1880
2089
+ },
2090
+ {
2091
+ "epoch": 0.7583508877520313,
2092
+ "grad_norm": 0.77734375,
2093
+ "learning_rate": 8.379618751543275e-06,
2094
+ "logps_logqs/chosen": 0.06059462949633598,
2095
+ "logqs/chosen": -0.7289972305297852,
2096
+ "logqs/rejected": -0.8890076875686646,
2097
+ "logqs_logps/rejected": 0.043808337301015854,
2098
+ "loss": 0.1994,
2099
+ "step": 1890
2100
+ },
2101
+ {
2102
+ "epoch": 0.7623633263115659,
2103
+ "grad_norm": 0.86328125,
2104
+ "learning_rate": 8.119573628527406e-06,
2105
+ "logps_logqs/chosen": 0.06398828327655792,
2106
+ "logqs/chosen": -0.7545658349990845,
2107
+ "logqs/rejected": -0.8651827573776245,
2108
+ "logqs_logps/rejected": 0.04523858055472374,
2109
+ "loss": 0.207,
2110
+ "step": 1900
2111
+ },
2112
+ {
2113
+ "epoch": 0.7663757648711004,
2114
+ "grad_norm": 0.8125,
2115
+ "learning_rate": 7.862842904858633e-06,
2116
+ "logps_logqs/chosen": 0.05899987369775772,
2117
+ "logqs/chosen": -0.7348795533180237,
2118
+ "logqs/rejected": -0.9609573483467102,
2119
+ "logqs_logps/rejected": 0.03890888765454292,
2120
+ "loss": 0.199,
2121
+ "step": 1910
2122
+ },
2123
+ {
2124
+ "epoch": 0.770388203430635,
2125
+ "grad_norm": 0.88671875,
2126
+ "learning_rate": 7.609476988513875e-06,
2127
+ "logps_logqs/chosen": 0.06505165994167328,
2128
+ "logqs/chosen": -0.7714970707893372,
2129
+ "logqs/rejected": -0.8944205045700073,
2130
+ "logqs_logps/rejected": 0.042544566094875336,
2131
+ "loss": 0.2085,
2132
+ "step": 1920
2133
+ },
2134
+ {
2135
+ "epoch": 0.7744006419901696,
2136
+ "grad_norm": 0.828125,
2137
+ "learning_rate": 7.359525626804545e-06,
2138
+ "logps_logqs/chosen": 0.06677477806806564,
2139
+ "logqs/chosen": -0.7985670566558838,
2140
+ "logqs/rejected": -0.9588406682014465,
2141
+ "logqs_logps/rejected": 0.03549560531973839,
2142
+ "loss": 0.2021,
2143
+ "step": 1930
2144
+ },
2145
+ {
2146
+ "epoch": 0.778413080549704,
2147
+ "grad_norm": 0.83984375,
2148
+ "learning_rate": 7.113037896608923e-06,
2149
+ "logps_logqs/chosen": 0.05854114890098572,
2150
+ "logqs/chosen": -0.7753890752792358,
2151
+ "logqs/rejected": -0.9235790371894836,
2152
+ "logqs_logps/rejected": 0.04000157117843628,
2153
+ "loss": 0.1948,
2154
+ "step": 1940
2155
+ },
2156
+ {
2157
+ "epoch": 0.7824255191092386,
2158
+ "grad_norm": 0.984375,
2159
+ "learning_rate": 6.870062194736057e-06,
2160
+ "logps_logqs/chosen": 0.06045924499630928,
2161
+ "logqs/chosen": -0.8043012619018555,
2162
+ "logqs/rejected": -0.9698446989059448,
2163
+ "logqs_logps/rejected": 0.042726777493953705,
2164
+ "loss": 0.2069,
2165
+ "step": 1950
2166
+ },
2167
+ {
2168
+ "epoch": 0.7864379576687732,
2169
+ "grad_norm": 0.99609375,
2170
+ "learning_rate": 6.6306462284233234e-06,
2171
+ "logps_logqs/chosen": 0.05968203395605087,
2172
+ "logqs/chosen": -0.7555102705955505,
2173
+ "logqs/rejected": -0.9313309788703918,
2174
+ "logqs_logps/rejected": 0.04395302012562752,
2175
+ "loss": 0.1983,
2176
+ "step": 1960
2177
+ },
2178
+ {
2179
+ "epoch": 0.7904503962283077,
2180
+ "grad_norm": 0.890625,
2181
+ "learning_rate": 6.394837005969251e-06,
2182
+ "logps_logqs/chosen": 0.054263245314359665,
2183
+ "logqs/chosen": -0.7649015188217163,
2184
+ "logqs/rejected": -0.9770067930221558,
2185
+ "logqs_logps/rejected": 0.039296168833971024,
2186
+ "loss": 0.1991,
2187
+ "step": 1970
2188
+ },
2189
+ {
2190
+ "epoch": 0.7944628347878423,
2191
+ "grad_norm": 0.9140625,
2192
+ "learning_rate": 6.162680827503705e-06,
2193
+ "logps_logqs/chosen": 0.06627397239208221,
2194
+ "logqs/chosen": -0.759872317314148,
2195
+ "logqs/rejected": -0.9354902505874634,
2196
+ "logqs_logps/rejected": 0.04396883398294449,
2197
+ "loss": 0.205,
2198
+ "step": 1980
2199
+ },
2200
+ {
2201
+ "epoch": 0.7984752733473769,
2202
+ "grad_norm": 0.75390625,
2203
+ "learning_rate": 5.934223275897e-06,
2204
+ "logps_logqs/chosen": 0.05789231136441231,
2205
+ "logqs/chosen": -0.7570023536682129,
2206
+ "logqs/rejected": -0.9084933996200562,
2207
+ "logqs_logps/rejected": 0.034562643617391586,
2208
+ "loss": 0.1977,
2209
+ "step": 1990
2210
+ },
2211
+ {
2212
+ "epoch": 0.8024877119069114,
2213
+ "grad_norm": 0.9921875,
2214
+ "learning_rate": 5.709509207809946e-06,
2215
+ "logps_logqs/chosen": 0.05983500927686691,
2216
+ "logqs/chosen": -0.7238153219223022,
2217
+ "logqs/rejected": -0.8950502276420593,
2218
+ "logqs_logps/rejected": 0.043728940188884735,
2219
+ "loss": 0.204,
2220
+ "step": 2000
2221
+ },
2222
+ {
2223
+ "epoch": 0.806500150466446,
2224
+ "grad_norm": 0.7734375,
2225
+ "learning_rate": 5.4885827448863865e-06,
2226
+ "logps_logqs/chosen": 0.06219662353396416,
2227
+ "logqs/chosen": -0.7557579278945923,
2228
+ "logqs/rejected": -0.9043906927108765,
2229
+ "logqs_logps/rejected": 0.04098309203982353,
2230
+ "loss": 0.2037,
2231
+ "step": 2010
2232
+ },
2233
+ {
2234
+ "epoch": 0.8105125890259806,
2235
+ "grad_norm": 1.0078125,
2236
+ "learning_rate": 5.271487265090163e-06,
2237
+ "logps_logqs/chosen": 0.06002221629023552,
2238
+ "logqs/chosen": -0.7607712149620056,
2239
+ "logqs/rejected": -0.9396473169326782,
2240
+ "logqs_logps/rejected": 0.04222804307937622,
2241
+ "loss": 0.2034,
2242
+ "step": 2020
2243
+ },
2244
+ {
2245
+ "epoch": 0.8145250275855151,
2246
+ "grad_norm": 1.046875,
2247
+ "learning_rate": 5.058265394187969e-06,
2248
+ "logps_logqs/chosen": 0.06274767965078354,
2249
+ "logqs/chosen": -0.7671214938163757,
2250
+ "logqs/rejected": -0.9004543423652649,
2251
+ "logqs_logps/rejected": 0.046913545578718185,
2252
+ "loss": 0.2041,
2253
+ "step": 2030
2254
+ },
2255
+ {
2256
+ "epoch": 0.8185374661450496,
2257
+ "grad_norm": 1.0546875,
2258
+ "learning_rate": 4.848958997380035e-06,
2259
+ "logps_logqs/chosen": 0.06094413250684738,
2260
+ "logqs/chosen": -0.7989168167114258,
2261
+ "logqs/rejected": -0.9816246032714844,
2262
+ "logqs_logps/rejected": 0.042406968772411346,
2263
+ "loss": 0.2054,
2264
+ "step": 2040
2265
+ },
2266
+ {
2267
+ "epoch": 0.8225499047045842,
2268
+ "grad_norm": 0.67578125,
2269
+ "learning_rate": 4.643609171080002e-06,
2270
+ "logps_logqs/chosen": 0.05818860977888107,
2271
+ "logqs/chosen": -0.7579581141471863,
2272
+ "logqs/rejected": -0.9492076635360718,
2273
+ "logqs_logps/rejected": 0.041138358414173126,
2274
+ "loss": 0.1991,
2275
+ "step": 2050
2276
+ },
2277
+ {
2278
+ "epoch": 0.8265623432641188,
2279
+ "grad_norm": 0.84375,
2280
+ "learning_rate": 4.44225623484589e-06,
2281
+ "logps_logqs/chosen": 0.061229269951581955,
2282
+ "logqs/chosen": -0.7763658761978149,
2283
+ "logqs/rejected": -0.9214930534362793,
2284
+ "logqs_logps/rejected": 0.04326833412051201,
2285
+ "loss": 0.2105,
2286
+ "step": 2060
2287
+ },
2288
+ {
2289
+ "epoch": 0.8305747818236533,
2290
+ "grad_norm": 0.9609375,
2291
+ "learning_rate": 4.244939723463468e-06,
2292
+ "logps_logqs/chosen": 0.061605095863342285,
2293
+ "logqs/chosen": -0.7827211022377014,
2294
+ "logqs/rejected": -1.016422152519226,
2295
+ "logqs_logps/rejected": 0.04850704222917557,
2296
+ "loss": 0.2028,
2297
+ "step": 2070
2298
+ },
2299
+ {
2300
+ "epoch": 0.8345872203831879,
2301
+ "grad_norm": 1.0546875,
2302
+ "learning_rate": 4.051698379183791e-06,
2303
+ "logps_logqs/chosen": 0.059653230011463165,
2304
+ "logqs/chosen": -0.7364221811294556,
2305
+ "logqs/rejected": -0.9126985669136047,
2306
+ "logqs_logps/rejected": 0.04395602270960808,
2307
+ "loss": 0.2077,
2308
+ "step": 2080
2309
+ },
2310
+ {
2311
+ "epoch": 0.8385996589427225,
2312
+ "grad_norm": 0.875,
2313
+ "learning_rate": 3.862570144116334e-06,
2314
+ "logps_logqs/chosen": 0.06163454055786133,
2315
+ "logqs/chosen": -0.7645280361175537,
2316
+ "logqs/rejected": -1.0081186294555664,
2317
+ "logqs_logps/rejected": 0.04180619865655899,
2318
+ "loss": 0.202,
2319
+ "step": 2090
2320
+ },
2321
+ {
2322
+ "epoch": 0.842612097502257,
2323
+ "grad_norm": 0.9375,
2324
+ "learning_rate": 3.677592152779216e-06,
2325
+ "logps_logqs/chosen": 0.060922086238861084,
2326
+ "logqs/chosen": -0.7481504082679749,
2327
+ "logqs/rejected": -0.900185227394104,
2328
+ "logqs_logps/rejected": 0.04749513044953346,
2329
+ "loss": 0.2071,
2330
+ "step": 2100
2331
+ },
2332
+ {
2333
+ "epoch": 0.8466245360617916,
2334
+ "grad_norm": 0.97265625,
2335
+ "learning_rate": 3.4968007248079777e-06,
2336
+ "logps_logqs/chosen": 0.06403280794620514,
2337
+ "logqs/chosen": -0.7176480293273926,
2338
+ "logqs/rejected": -0.8989812731742859,
2339
+ "logqs_logps/rejected": 0.04769695922732353,
2340
+ "loss": 0.2051,
2341
+ "step": 2110
2342
+ },
2343
+ {
2344
+ "epoch": 0.8506369746213261,
2345
+ "grad_norm": 0.8828125,
2346
+ "learning_rate": 3.3202313578243995e-06,
2347
+ "logps_logqs/chosen": 0.05457407236099243,
2348
+ "logqs/chosen": -0.7609150409698486,
2349
+ "logqs/rejected": -0.9247547388076782,
2350
+ "logqs_logps/rejected": 0.04001811891794205,
2351
+ "loss": 0.202,
2352
+ "step": 2120
2353
+ },
2354
+ {
2355
+ "epoch": 0.8546494131808606,
2356
+ "grad_norm": 1.046875,
2357
+ "learning_rate": 3.1479187204666886e-06,
2358
+ "logps_logqs/chosen": 0.05928390100598335,
2359
+ "logqs/chosen": -0.764100193977356,
2360
+ "logqs/rejected": -0.9366759061813354,
2361
+ "logqs_logps/rejected": 0.03913865610957146,
2362
+ "loss": 0.2027,
2363
+ "step": 2130
2364
+ },
2365
+ {
2366
+ "epoch": 0.8586618517403952,
2367
+ "grad_norm": 0.90234375,
2368
+ "learning_rate": 2.9798966455824474e-06,
2369
+ "logps_logqs/chosen": 0.06238958239555359,
2370
+ "logqs/chosen": -0.7486379742622375,
2371
+ "logqs/rejected": -0.9404671788215637,
2372
+ "logqs_logps/rejected": 0.04445621743798256,
2373
+ "loss": 0.2009,
2374
+ "step": 2140
2375
+ },
2376
+ {
2377
+ "epoch": 0.8626742902999298,
2378
+ "grad_norm": 0.90625,
2379
+ "learning_rate": 2.8161981235857143e-06,
2380
+ "logps_logqs/chosen": 0.05766347795724869,
2381
+ "logqs/chosen": -0.8047393560409546,
2382
+ "logqs/rejected": -0.9559482336044312,
2383
+ "logqs_logps/rejected": 0.043215952813625336,
2384
+ "loss": 0.202,
2385
+ "step": 2150
2386
+ },
2387
+ {
2388
+ "epoch": 0.8666867288594643,
2389
+ "grad_norm": 0.8984375,
2390
+ "learning_rate": 2.656855295979463e-06,
2391
+ "logps_logqs/chosen": 0.06472580134868622,
2392
+ "logqs/chosen": -0.737873911857605,
2393
+ "logqs/rejected": -0.8887351751327515,
2394
+ "logqs_logps/rejected": 0.043567948043346405,
2395
+ "loss": 0.2042,
2396
+ "step": 2160
2397
+ },
2398
+ {
2399
+ "epoch": 0.8706991674189989,
2400
+ "grad_norm": 1.0234375,
2401
+ "learning_rate": 2.5018994490447506e-06,
2402
+ "logps_logqs/chosen": 0.06504198163747787,
2403
+ "logqs/chosen": -0.7585901618003845,
2404
+ "logqs/rejected": -0.93121337890625,
2405
+ "logqs_logps/rejected": 0.048323631286621094,
2406
+ "loss": 0.2037,
2407
+ "step": 2170
2408
+ },
2409
+ {
2410
+ "epoch": 0.8747116059785335,
2411
+ "grad_norm": 0.9375,
2412
+ "learning_rate": 2.3513610076977914e-06,
2413
+ "logps_logqs/chosen": 0.05999793857336044,
2414
+ "logqs/chosen": -0.7390618920326233,
2415
+ "logqs/rejected": -0.9315282702445984,
2416
+ "logqs_logps/rejected": 0.04710640385746956,
2417
+ "loss": 0.2065,
2418
+ "step": 2180
2419
+ },
2420
+ {
2421
+ "epoch": 0.878724044538068,
2422
+ "grad_norm": 1.0546875,
2423
+ "learning_rate": 2.2052695295161406e-06,
2424
+ "logps_logqs/chosen": 0.06420952826738358,
2425
+ "logqs/chosen": -0.7469607591629028,
2426
+ "logqs/rejected": -0.8542912602424622,
2427
+ "logqs_logps/rejected": 0.04820626974105835,
2428
+ "loss": 0.2034,
2429
+ "step": 2190
2430
+ },
2431
+ {
2432
+ "epoch": 0.8827364830976026,
2433
+ "grad_norm": 0.87890625,
2434
+ "learning_rate": 2.0636536989351974e-06,
2435
+ "logps_logqs/chosen": 0.06679137796163559,
2436
+ "logqs/chosen": -0.7580717206001282,
2437
+ "logqs/rejected": -0.8642162084579468,
2438
+ "logqs_logps/rejected": 0.042508114129304886,
2439
+ "loss": 0.2008,
2440
+ "step": 2200
2441
+ },
2442
+ {
2443
+ "epoch": 0.8867489216571371,
2444
+ "grad_norm": 0.91015625,
2445
+ "learning_rate": 1.9265413216161597e-06,
2446
+ "logps_logqs/chosen": 0.06721115857362747,
2447
+ "logqs/chosen": -0.7631017565727234,
2448
+ "logqs/rejected": -0.9131069183349609,
2449
+ "logqs_logps/rejected": 0.04944468289613724,
2450
+ "loss": 0.2065,
2451
+ "step": 2210
2452
+ },
2453
+ {
2454
+ "epoch": 0.8907613602166716,
2455
+ "grad_norm": 0.83984375,
2456
+ "learning_rate": 1.7939593189864795e-06,
2457
+ "logps_logqs/chosen": 0.061406660825014114,
2458
+ "logqs/chosen": -0.7838734984397888,
2459
+ "logqs/rejected": -0.9089409708976746,
2460
+ "logqs_logps/rejected": 0.04142575338482857,
2461
+ "loss": 0.1987,
2462
+ "step": 2220
2463
+ },
2464
+ {
2465
+ "epoch": 0.8947737987762062,
2466
+ "grad_norm": 0.96484375,
2467
+ "learning_rate": 1.6659337229539524e-06,
2468
+ "logps_logqs/chosen": 0.0574992373585701,
2469
+ "logqs/chosen": -0.74857097864151,
2470
+ "logqs/rejected": -0.9218307733535767,
2471
+ "logqs_logps/rejected": 0.045242272317409515,
2472
+ "loss": 0.2061,
2473
+ "step": 2230
2474
+ },
2475
+ {
2476
+ "epoch": 0.8987862373357408,
2477
+ "grad_norm": 0.953125,
2478
+ "learning_rate": 1.5424896707954773e-06,
2479
+ "logps_logqs/chosen": 0.06686152517795563,
2480
+ "logqs/chosen": -0.8112009167671204,
2481
+ "logqs/rejected": -0.9499409794807434,
2482
+ "logqs_logps/rejected": 0.04503064230084419,
2483
+ "loss": 0.2133,
2484
+ "step": 2240
2485
+ },
2486
+ {
2487
+ "epoch": 0.9027986758952754,
2488
+ "grad_norm": 0.87109375,
2489
+ "learning_rate": 1.4236514002214651e-06,
2490
+ "logps_logqs/chosen": 0.06498394906520844,
2491
+ "logqs/chosen": -0.7638250589370728,
2492
+ "logqs/rejected": -0.8727086782455444,
2493
+ "logqs_logps/rejected": 0.047809042036533356,
2494
+ "loss": 0.2039,
2495
+ "step": 2250
2496
+ },
2497
+ {
2498
+ "epoch": 0.9068111144548099,
2499
+ "grad_norm": 0.8359375,
2500
+ "learning_rate": 1.3094422446168404e-06,
2501
+ "logps_logqs/chosen": 0.05696554109454155,
2502
+ "logqs/chosen": -0.7111738920211792,
2503
+ "logqs/rejected": -0.8518338203430176,
2504
+ "logqs_logps/rejected": 0.044544972479343414,
2505
+ "loss": 0.1983,
2506
+ "step": 2260
2507
+ },
2508
+ {
2509
+ "epoch": 0.9108235530143445,
2510
+ "grad_norm": 0.81640625,
2511
+ "learning_rate": 1.1998846284596688e-06,
2512
+ "logps_logqs/chosen": 0.061489515006542206,
2513
+ "logqs/chosen": -0.7231674194335938,
2514
+ "logqs/rejected": -0.8351476788520813,
2515
+ "logqs_logps/rejected": 0.04788647219538689,
2516
+ "loss": 0.1983,
2517
+ "step": 2270
2518
+ },
2519
+ {
2520
+ "epoch": 0.9148359915738791,
2521
+ "grad_norm": 0.78515625,
2522
+ "learning_rate": 1.0950000629181807e-06,
2523
+ "logps_logqs/chosen": 0.04939153045415878,
2524
+ "logqs/chosen": -0.7786750197410583,
2525
+ "logqs/rejected": -0.8713645935058594,
2526
+ "logqs_logps/rejected": 0.04320090264081955,
2527
+ "loss": 0.2081,
2528
+ "step": 2280
2529
+ },
2530
+ {
2531
+ "epoch": 0.9188484301334136,
2532
+ "grad_norm": 0.953125,
2533
+ "learning_rate": 9.948091416271483e-07,
2534
+ "logps_logqs/chosen": 0.0662379264831543,
2535
+ "logqs/chosen": -0.8300337791442871,
2536
+ "logqs/rejected": -0.9588104486465454,
2537
+ "logqs_logps/rejected": 0.04326099902391434,
2538
+ "loss": 0.2103,
2539
+ "step": 2290
2540
+ },
2541
+ {
2542
+ "epoch": 0.9228608686929481,
2543
+ "grad_norm": 0.79296875,
2544
+ "learning_rate": 8.99331536644421e-07,
2545
+ "logps_logqs/chosen": 0.05675070732831955,
2546
+ "logqs/chosen": -0.7419881224632263,
2547
+ "logqs/rejected": -0.9318987727165222,
2548
+ "logqs_logps/rejected": 0.04274313896894455,
2549
+ "loss": 0.2006,
2550
+ "step": 2300
2551
+ },
2552
+ {
2553
+ "epoch": 0.9268733072524827,
2554
+ "grad_norm": 1.0703125,
2555
+ "learning_rate": 8.085859945883983e-07,
2556
+ "logps_logqs/chosen": 0.05921543762087822,
2557
+ "logqs/chosen": -0.7391059994697571,
2558
+ "logqs/rejected": -0.8634150624275208,
2559
+ "logqs_logps/rejected": 0.04096318036317825,
2560
+ "loss": 0.2,
2561
+ "step": 2310
2562
+ },
2563
+ {
2564
+ "epoch": 0.9308857458120172,
2565
+ "grad_norm": 0.8125,
2566
+ "learning_rate": 7.225903329572181e-07,
2567
+ "logps_logqs/chosen": 0.06639240682125092,
2568
+ "logqs/chosen": -0.7444113492965698,
2569
+ "logqs/rejected": -0.8740445971488953,
2570
+ "logqs_logps/rejected": 0.046740248799324036,
2571
+ "loss": 0.1993,
2572
+ "step": 2320
2573
+ },
2574
+ {
2575
+ "epoch": 0.9348981843715518,
2576
+ "grad_norm": 1.078125,
2577
+ "learning_rate": 6.413614366303472e-07,
2578
+ "logps_logqs/chosen": 0.06109191104769707,
2579
+ "logqs/chosen": -0.7488638162612915,
2580
+ "logqs/rejected": -0.9097427129745483,
2581
+ "logqs_logps/rejected": 0.04230613261461258,
2582
+ "loss": 0.206,
2583
+ "step": 2330
2584
+ },
2585
+ {
2586
+ "epoch": 0.9389106229310864,
2587
+ "grad_norm": 0.84765625,
2588
+ "learning_rate": 5.649152545533332e-07,
2589
+ "logps_logqs/chosen": 0.06688685715198517,
2590
+ "logqs/chosen": -0.7463788986206055,
2591
+ "logqs/rejected": -0.8424680829048157,
2592
+ "logqs_logps/rejected": 0.04632396623492241,
2593
+ "loss": 0.1996,
2594
+ "step": 2340
2595
+ },
2596
+ {
2597
+ "epoch": 0.9429230614906209,
2598
+ "grad_norm": 0.859375,
2599
+ "learning_rate": 4.932667966062815e-07,
2600
+ "logps_logqs/chosen": 0.06688842177391052,
2601
+ "logqs/chosen": -0.7895928621292114,
2602
+ "logqs/rejected": -1.0372272729873657,
2603
+ "logqs_logps/rejected": 0.042335085570812225,
2604
+ "loss": 0.2169,
2605
+ "step": 2350
2606
+ },
2607
+ {
2608
+ "epoch": 0.9469355000501555,
2609
+ "grad_norm": 0.9140625,
2610
+ "learning_rate": 4.2643013065673533e-07,
2611
+ "logps_logqs/chosen": 0.05645795911550522,
2612
+ "logqs/chosen": -0.801129162311554,
2613
+ "logqs/rejected": -0.9468640089035034,
2614
+ "logqs_logps/rejected": 0.04600223898887634,
2615
+ "loss": 0.201,
2616
+ "step": 2360
2617
+ },
2618
+ {
2619
+ "epoch": 0.9509479386096901,
2620
+ "grad_norm": 0.91015625,
2621
+ "learning_rate": 3.6441837979750426e-07,
2622
+ "logps_logqs/chosen": 0.057076144963502884,
2623
+ "logqs/chosen": -0.7397576570510864,
2624
+ "logqs/rejected": -0.928216814994812,
2625
+ "logqs_logps/rejected": 0.045889295637607574,
2626
+ "loss": 0.201,
2627
+ "step": 2370
2628
+ },
2629
+ {
2630
+ "epoch": 0.9549603771692246,
2631
+ "grad_norm": 0.8984375,
2632
+ "learning_rate": 3.07243719770009e-07,
2633
+ "logps_logqs/chosen": 0.05663397163152695,
2634
+ "logqs/chosen": -0.7601091861724854,
2635
+ "logqs/rejected": -0.8796554803848267,
2636
+ "logqs_logps/rejected": 0.0409110002219677,
2637
+ "loss": 0.1985,
2638
+ "step": 2380
2639
+ },
2640
+ {
2641
+ "epoch": 0.9589728157287591,
2642
+ "grad_norm": 0.98046875,
2643
+ "learning_rate": 2.5491737657362127e-07,
2644
+ "logps_logqs/chosen": 0.06481993943452835,
2645
+ "logqs/chosen": -0.7787806391716003,
2646
+ "logqs/rejected": -0.9817843437194824,
2647
+ "logqs_logps/rejected": 0.04762902110815048,
2648
+ "loss": 0.2106,
2649
+ "step": 2390
2650
+ },
2651
+ {
2652
+ "epoch": 0.9629852542882937,
2653
+ "grad_norm": 0.9921875,
2654
+ "learning_rate": 2.0744962426149372e-07,
2655
+ "logps_logqs/chosen": 0.06616654247045517,
2656
+ "logqs/chosen": -0.7752987742424011,
2657
+ "logqs/rejected": -0.8757341504096985,
2658
+ "logqs_logps/rejected": 0.04639893025159836,
2659
+ "loss": 0.2078,
2660
+ "step": 2400
2661
+ },
2662
+ {
2663
+ "epoch": 0.9669976928478282,
2664
+ "grad_norm": 0.984375,
2665
+ "learning_rate": 1.6484978292328479e-07,
2666
+ "logps_logqs/chosen": 0.0615106001496315,
2667
+ "logqs/chosen": -0.7567707300186157,
2668
+ "logqs/rejected": -0.8831803202629089,
2669
+ "logqs_logps/rejected": 0.0448283851146698,
2670
+ "loss": 0.2027,
2671
+ "step": 2410
2672
+ },
2673
+ {
2674
+ "epoch": 0.9710101314073628,
2675
+ "grad_norm": 0.79296875,
2676
+ "learning_rate": 1.2712621685520288e-07,
2677
+ "logps_logqs/chosen": 0.054491542279720306,
2678
+ "logqs/chosen": -0.7399695515632629,
2679
+ "logqs/rejected": -0.915317714214325,
2680
+ "logqs_logps/rejected": 0.03824533894658089,
2681
+ "loss": 0.196,
2682
+ "step": 2420
2683
+ },
2684
+ {
2685
+ "epoch": 0.9750225699668974,
2686
+ "grad_norm": 0.90234375,
2687
+ "learning_rate": 9.42863329177146e-08,
2688
+ "logps_logqs/chosen": 0.06179448962211609,
2689
+ "logqs/chosen": -0.7460163831710815,
2690
+ "logqs/rejected": -0.8711358308792114,
2691
+ "logqs_logps/rejected": 0.04575900733470917,
2692
+ "loss": 0.1979,
2693
+ "step": 2430
2694
+ },
2695
+ {
2696
+ "epoch": 0.979035008526432,
2697
+ "grad_norm": 0.8828125,
2698
+ "learning_rate": 6.633657908123591e-08,
2699
+ "logps_logqs/chosen": 0.05870884656906128,
2700
+ "logqs/chosen": -0.7323063015937805,
2701
+ "logqs/rejected": -0.8580669164657593,
2702
+ "logqs_logps/rejected": 0.04539089277386665,
2703
+ "loss": 0.2049,
2704
+ "step": 2440
2705
+ },
2706
+ {
2707
+ "epoch": 0.9830474470859665,
2708
+ "grad_norm": 0.953125,
2709
+ "learning_rate": 4.328244316011143e-08,
2710
+ "logps_logqs/chosen": 0.054106056690216064,
2711
+ "logqs/chosen": -0.7781955003738403,
2712
+ "logqs/rejected": -1.0293381214141846,
2713
+ "logqs_logps/rejected": 0.043772052973508835,
2714
+ "loss": 0.2009,
2715
+ "step": 2450
2716
+ },
2717
+ {
2718
+ "epoch": 0.9870598856455011,
2719
+ "grad_norm": 0.7578125,
2720
+ "learning_rate": 2.5128451735081936e-08,
2721
+ "logps_logqs/chosen": 0.06501375138759613,
2722
+ "logqs/chosen": -0.7846288681030273,
2723
+ "logqs/rejected": -0.9334620237350464,
2724
+ "logqs_logps/rejected": 0.04351498931646347,
2725
+ "loss": 0.21,
2726
+ "step": 2460
2727
+ },
2728
+ {
2729
+ "epoch": 0.9910723242050357,
2730
+ "grad_norm": 0.796875,
2731
+ "learning_rate": 1.1878169264536999e-08,
2732
+ "logps_logqs/chosen": 0.06218789145350456,
2733
+ "logqs/chosen": -0.73200923204422,
2734
+ "logqs/rejected": -0.8427228927612305,
2735
+ "logqs_logps/rejected": 0.045235030353069305,
2736
+ "loss": 0.203,
2737
+ "step": 2470
2738
+ },
2739
+ {
2740
+ "epoch": 0.9950847627645701,
2741
+ "grad_norm": 0.91796875,
2742
+ "learning_rate": 3.5341973846303445e-09,
2743
+ "logps_logqs/chosen": 0.06000654771924019,
2744
+ "logqs/chosen": -0.7566072940826416,
2745
+ "logqs/rejected": -0.9218905568122864,
2746
+ "logqs_logps/rejected": 0.044534750282764435,
2747
+ "loss": 0.2049,
2748
+ "step": 2480
2749
+ },
2750
+ {
2751
+ "epoch": 0.9990972013241047,
2752
+ "grad_norm": 1.046875,
2753
+ "learning_rate": 9.817439847181753e-11,
2754
+ "logps_logqs/chosen": 0.060572218149900436,
2755
+ "logqs/chosen": -0.7785285115242004,
2756
+ "logqs/rejected": -0.9291244745254517,
2757
+ "logqs_logps/rejected": 0.03921912610530853,
2758
+ "loss": 0.2054,
2759
+ "step": 2490
2760
+ },
2761
+ {
2762
+ "epoch": 0.9998996890360117,
2763
+ "step": 2492,
2764
+ "total_flos": 0.0,
2765
+ "train_loss": 0.2227630860637126,
2766
+ "train_runtime": 7975.4099,
2767
+ "train_samples_per_second": 10.0,
2768
+ "train_steps_per_second": 0.312
2769
+ }
2770
+ ],
2771
+ "logging_steps": 10,
2772
+ "max_steps": 2492,
2773
+ "num_input_tokens_seen": 0,
2774
+ "num_train_epochs": 1,
2775
+ "save_steps": 500,
2776
+ "stateful_callbacks": {
2777
+ "TrainerControl": {
2778
+ "args": {
2779
+ "should_epoch_stop": false,
2780
+ "should_evaluate": false,
2781
+ "should_log": false,
2782
+ "should_save": true,
2783
+ "should_training_stop": true
2784
+ },
2785
+ "attributes": {}
2786
+ }
2787
+ },
2788
+ "total_flos": 0.0,
2789
+ "train_batch_size": 2,
2790
+ "trial_name": null,
2791
+ "trial_params": null
2792
+ }
qwen2.5-1.5B-it-distillm2-1epoch/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1161612a2c62499be2c7df457de2b8f9c367b6c35886d6da23351b674ba8c60d
3
+ size 6840
qwen2.5-1.5B-it-distillm2-1epoch/vocab.json ADDED
The diff for this file is too large to render. See raw diff