echarif commited on
Commit
bb6f86b
·
verified ·
1 Parent(s): 9f6f2ae

Initial model upload

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +5 -0
  2. README.md +60 -0
  3. adapter_config.json +39 -0
  4. adapter_model.safetensors +3 -0
  5. all_results.json +8 -0
  6. checkpoint-1000/README.md +202 -0
  7. checkpoint-1000/adapter_config.json +39 -0
  8. checkpoint-1000/adapter_model.safetensors +3 -0
  9. checkpoint-1000/optimizer.pt +3 -0
  10. checkpoint-1000/rng_state.pth +3 -0
  11. checkpoint-1000/scaler.pt +3 -0
  12. checkpoint-1000/scheduler.pt +3 -0
  13. checkpoint-1000/special_tokens_map.json +26 -0
  14. checkpoint-1000/tokenizer.json +3 -0
  15. checkpoint-1000/tokenizer_config.json +2069 -0
  16. checkpoint-1000/trainer_state.json +1434 -0
  17. checkpoint-1000/training_args.bin +3 -0
  18. checkpoint-1500/README.md +202 -0
  19. checkpoint-1500/adapter_config.json +39 -0
  20. checkpoint-1500/adapter_model.safetensors +3 -0
  21. checkpoint-1500/optimizer.pt +3 -0
  22. checkpoint-1500/rng_state.pth +3 -0
  23. checkpoint-1500/scaler.pt +3 -0
  24. checkpoint-1500/scheduler.pt +3 -0
  25. checkpoint-1500/special_tokens_map.json +26 -0
  26. checkpoint-1500/tokenizer.json +3 -0
  27. checkpoint-1500/tokenizer_config.json +2069 -0
  28. checkpoint-1500/trainer_state.json +2134 -0
  29. checkpoint-1500/training_args.bin +3 -0
  30. checkpoint-1610/README.md +202 -0
  31. checkpoint-1610/adapter_config.json +39 -0
  32. checkpoint-1610/adapter_model.safetensors +3 -0
  33. checkpoint-1610/optimizer.pt +3 -0
  34. checkpoint-1610/rng_state.pth +3 -0
  35. checkpoint-1610/scaler.pt +3 -0
  36. checkpoint-1610/scheduler.pt +3 -0
  37. checkpoint-1610/special_tokens_map.json +26 -0
  38. checkpoint-1610/tokenizer.json +3 -0
  39. checkpoint-1610/tokenizer_config.json +2069 -0
  40. checkpoint-1610/trainer_state.json +2288 -0
  41. checkpoint-1610/training_args.bin +3 -0
  42. checkpoint-500/README.md +202 -0
  43. checkpoint-500/adapter_config.json +39 -0
  44. checkpoint-500/adapter_model.safetensors +3 -0
  45. checkpoint-500/optimizer.pt +3 -0
  46. checkpoint-500/rng_state.pth +3 -0
  47. checkpoint-500/scaler.pt +3 -0
  48. checkpoint-500/scheduler.pt +3 -0
  49. checkpoint-500/special_tokens_map.json +26 -0
  50. checkpoint-500/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-1610/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: meta-llama/Llama-3.2-1B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: models
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # models
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the chatbot_enseignement_train dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 8
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 5
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - PEFT 0.15.2
57
+ - Transformers 4.51.3
58
+ - Pytorch 2.6.0+cu124
59
+ - Datasets 3.6.0
60
+ - Tokenizers 0.21.1
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "k_proj",
31
+ "up_proj",
32
+ "down_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef1c63beed69b42dc1dd6c20a47e30f47118e4d534fb1e93ba1ba7fb89daa41
3
+ size 180385008
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.986046511627907,
3
+ "total_flos": 2.716595267862528e+16,
4
+ "train_loss": 0.07186344412404187,
5
+ "train_runtime": 2691.5003,
6
+ "train_samples_per_second": 4.793,
7
+ "train_steps_per_second": 0.598
8
+ }
checkpoint-1000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-1B-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 0.15.2
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "k_proj",
31
+ "up_proj",
32
+ "down_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c827921e3882affa1e03fbf30154344d64f00d4a5b4b93a0876bf30c7892452a
3
+ size 180385008
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab9c309c8b189753d4a69b285c4090c6d5488e8da0e73fb6fc7c53264b8e85f
3
+ size 360899194
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
+ size 14244
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
3
+ size 988
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d97ef84420284ef4cf547b2cff09567de7530834150c63652d78030648f77b
3
+ size 1064
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
checkpoint-1000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|eom_id|>"
2054
+ ],
2055
+ "bos_token": "<|begin_of_text|>",
2056
+ "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",
2057
+ "clean_up_tokenization_spaces": true,
2058
+ "eos_token": "<|eot_id|>",
2059
+ "extra_special_tokens": {},
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 131072,
2065
+ "pad_token": "<|eot_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizer"
2069
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.096124031007752,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015503875968992248,
14
+ "grad_norm": 2.5634377002716064,
15
+ "learning_rate": 1.2422360248447205e-06,
16
+ "loss": 2.2423,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.031007751937984496,
21
+ "grad_norm": 1.774464726448059,
22
+ "learning_rate": 2.7950310559006214e-06,
23
+ "loss": 2.0959,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.046511627906976744,
28
+ "grad_norm": 2.2086267471313477,
29
+ "learning_rate": 4.347826086956522e-06,
30
+ "loss": 1.7507,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06201550387596899,
35
+ "grad_norm": 1.5988163948059082,
36
+ "learning_rate": 5.900621118012423e-06,
37
+ "loss": 1.4298,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07751937984496124,
42
+ "grad_norm": 1.3644428253173828,
43
+ "learning_rate": 7.453416149068324e-06,
44
+ "loss": 0.9425,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09302325581395349,
49
+ "grad_norm": 1.1469796895980835,
50
+ "learning_rate": 9.006211180124225e-06,
51
+ "loss": 0.6502,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.10852713178294573,
56
+ "grad_norm": 1.8373690843582153,
57
+ "learning_rate": 1.0559006211180125e-05,
58
+ "loss": 0.6724,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12403100775193798,
63
+ "grad_norm": 1.116761565208435,
64
+ "learning_rate": 1.2111801242236026e-05,
65
+ "loss": 0.4023,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.13953488372093023,
70
+ "grad_norm": 0.7392648458480835,
71
+ "learning_rate": 1.3664596273291926e-05,
72
+ "loss": 0.3874,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15503875968992248,
77
+ "grad_norm": 0.9391402006149292,
78
+ "learning_rate": 1.5217391304347828e-05,
79
+ "loss": 0.3164,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17054263565891473,
84
+ "grad_norm": 0.9636594653129578,
85
+ "learning_rate": 1.6770186335403728e-05,
86
+ "loss": 0.1785,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.18604651162790697,
91
+ "grad_norm": 0.6391934156417847,
92
+ "learning_rate": 1.8322981366459628e-05,
93
+ "loss": 0.1778,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20155038759689922,
98
+ "grad_norm": 0.5561841726303101,
99
+ "learning_rate": 1.9875776397515528e-05,
100
+ "loss": 0.2703,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.21705426356589147,
105
+ "grad_norm": 0.49807441234588623,
106
+ "learning_rate": 2.1428571428571428e-05,
107
+ "loss": 0.1875,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.23255813953488372,
112
+ "grad_norm": 1.2350372076034546,
113
+ "learning_rate": 2.2981366459627328e-05,
114
+ "loss": 0.3248,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.24806201550387597,
119
+ "grad_norm": 0.6338334083557129,
120
+ "learning_rate": 2.453416149068323e-05,
121
+ "loss": 0.1297,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.26356589147286824,
126
+ "grad_norm": 0.6853603720664978,
127
+ "learning_rate": 2.608695652173913e-05,
128
+ "loss": 0.1357,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.27906976744186046,
133
+ "grad_norm": 1.0921283960342407,
134
+ "learning_rate": 2.7639751552795035e-05,
135
+ "loss": 0.1418,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.29457364341085274,
140
+ "grad_norm": 0.7996405363082886,
141
+ "learning_rate": 2.919254658385093e-05,
142
+ "loss": 0.1293,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.31007751937984496,
147
+ "grad_norm": 0.4951094388961792,
148
+ "learning_rate": 3.074534161490684e-05,
149
+ "loss": 0.1783,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.32558139534883723,
154
+ "grad_norm": 0.3423459231853485,
155
+ "learning_rate": 3.2298136645962735e-05,
156
+ "loss": 0.0996,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.34108527131782945,
161
+ "grad_norm": 0.6147115230560303,
162
+ "learning_rate": 3.385093167701863e-05,
163
+ "loss": 0.1909,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.35658914728682173,
168
+ "grad_norm": 0.6499375104904175,
169
+ "learning_rate": 3.5403726708074535e-05,
170
+ "loss": 0.1572,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.37209302325581395,
175
+ "grad_norm": 0.274794340133667,
176
+ "learning_rate": 3.695652173913043e-05,
177
+ "loss": 0.1313,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.3875968992248062,
182
+ "grad_norm": 0.44879093766212463,
183
+ "learning_rate": 3.8509316770186335e-05,
184
+ "loss": 0.1141,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.40310077519379844,
189
+ "grad_norm": 0.3992724120616913,
190
+ "learning_rate": 4.006211180124224e-05,
191
+ "loss": 0.1539,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4186046511627907,
196
+ "grad_norm": 0.28350868821144104,
197
+ "learning_rate": 4.161490683229814e-05,
198
+ "loss": 0.0857,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.43410852713178294,
203
+ "grad_norm": 0.5912169814109802,
204
+ "learning_rate": 4.316770186335404e-05,
205
+ "loss": 0.1939,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4496124031007752,
210
+ "grad_norm": 0.35334816575050354,
211
+ "learning_rate": 4.472049689440994e-05,
212
+ "loss": 0.1149,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.46511627906976744,
217
+ "grad_norm": 0.7359523177146912,
218
+ "learning_rate": 4.627329192546584e-05,
219
+ "loss": 0.1193,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.4806201550387597,
224
+ "grad_norm": 0.43439972400665283,
225
+ "learning_rate": 4.782608695652174e-05,
226
+ "loss": 0.1049,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.49612403100775193,
231
+ "grad_norm": 0.4149303734302521,
232
+ "learning_rate": 4.937888198757764e-05,
233
+ "loss": 0.1168,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5116279069767442,
238
+ "grad_norm": 0.38137003779411316,
239
+ "learning_rate": 4.999947117257964e-05,
240
+ "loss": 0.122,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5271317829457365,
245
+ "grad_norm": 0.6025403738021851,
246
+ "learning_rate": 4.999623953047522e-05,
247
+ "loss": 0.1107,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5426356589147286,
252
+ "grad_norm": 0.6327984929084778,
253
+ "learning_rate": 4.999007041858851e-05,
254
+ "loss": 0.0855,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5581395348837209,
259
+ "grad_norm": 0.5637001991271973,
260
+ "learning_rate": 4.998096456189175e-05,
261
+ "loss": 0.0993,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5736434108527132,
266
+ "grad_norm": 0.2784324586391449,
267
+ "learning_rate": 4.996892303047306e-05,
268
+ "loss": 0.0716,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5891472868217055,
273
+ "grad_norm": 0.6117509603500366,
274
+ "learning_rate": 4.995394723941068e-05,
275
+ "loss": 0.0693,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6046511627906976,
280
+ "grad_norm": 1.3043673038482666,
281
+ "learning_rate": 4.993603894860669e-05,
282
+ "loss": 0.1016,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6201550387596899,
287
+ "grad_norm": 0.44789212942123413,
288
+ "learning_rate": 4.991520026258015e-05,
289
+ "loss": 0.0891,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6356589147286822,
294
+ "grad_norm": 1.85973060131073,
295
+ "learning_rate": 4.989143363021987e-05,
296
+ "loss": 0.1393,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6511627906976745,
301
+ "grad_norm": 1.2061032056808472,
302
+ "learning_rate": 4.9864741844496506e-05,
303
+ "loss": 0.116,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6666666666666666,
308
+ "grad_norm": 0.3840301036834717,
309
+ "learning_rate": 4.983512804213447e-05,
310
+ "loss": 0.0952,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6821705426356589,
315
+ "grad_norm": 0.4879723787307739,
316
+ "learning_rate": 4.9802595703243205e-05,
317
+ "loss": 0.128,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.6976744186046512,
322
+ "grad_norm": 0.4783574938774109,
323
+ "learning_rate": 4.976714865090827e-05,
324
+ "loss": 0.0783,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7131782945736435,
329
+ "grad_norm": 0.4228968620300293,
330
+ "learning_rate": 4.9728791050742064e-05,
331
+ "loss": 0.1176,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7286821705426356,
336
+ "grad_norm": 0.18757346272468567,
337
+ "learning_rate": 4.9687527410394275e-05,
338
+ "loss": 0.0872,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7441860465116279,
343
+ "grad_norm": 0.4684408903121948,
344
+ "learning_rate": 4.964336257902217e-05,
345
+ "loss": 0.0753,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7596899224806202,
350
+ "grad_norm": 0.7171066403388977,
351
+ "learning_rate": 4.9596301746720734e-05,
352
+ "loss": 0.0988,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7751937984496124,
357
+ "grad_norm": 0.5907664895057678,
358
+ "learning_rate": 4.9546350443912783e-05,
359
+ "loss": 0.1172,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.7906976744186046,
364
+ "grad_norm": 0.8421684503555298,
365
+ "learning_rate": 4.9493514540698963e-05,
366
+ "loss": 0.0771,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8062015503875969,
371
+ "grad_norm": 0.2831384837627411,
372
+ "learning_rate": 4.9437800246168025e-05,
373
+ "loss": 0.1212,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8217054263565892,
378
+ "grad_norm": 0.4991057217121124,
379
+ "learning_rate": 4.937921410766707e-05,
380
+ "loss": 0.0837,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8372093023255814,
385
+ "grad_norm": 0.5720856189727783,
386
+ "learning_rate": 4.931776301003217e-05,
387
+ "loss": 0.1615,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8527131782945736,
392
+ "grad_norm": 0.48435062170028687,
393
+ "learning_rate": 4.9253454174779265e-05,
394
+ "loss": 0.0872,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8682170542635659,
399
+ "grad_norm": 0.2810228765010834,
400
+ "learning_rate": 4.9186295159255537e-05,
401
+ "loss": 0.0886,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8837209302325582,
406
+ "grad_norm": 0.8470152616500854,
407
+ "learning_rate": 4.9116293855751285e-05,
408
+ "loss": 0.1107,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.8992248062015504,
413
+ "grad_norm": 0.26309266686439514,
414
+ "learning_rate": 4.9043458490572444e-05,
415
+ "loss": 0.0861,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9147286821705426,
420
+ "grad_norm": 0.4955242872238159,
421
+ "learning_rate": 4.896779762307389e-05,
422
+ "loss": 0.0548,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9302325581395349,
427
+ "grad_norm": 0.5125411152839661,
428
+ "learning_rate": 4.888932014465352e-05,
429
+ "loss": 0.0456,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9457364341085271,
434
+ "grad_norm": 0.4470186233520508,
435
+ "learning_rate": 4.880803527770742e-05,
436
+ "loss": 0.0909,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9612403100775194,
441
+ "grad_norm": 0.22464849054813385,
442
+ "learning_rate": 4.872395257454605e-05,
443
+ "loss": 0.0722,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9767441860465116,
448
+ "grad_norm": 0.1867540031671524,
449
+ "learning_rate": 4.86370819162717e-05,
450
+ "loss": 0.0497,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.9922480620155039,
455
+ "grad_norm": 0.1916547268629074,
456
+ "learning_rate": 4.8547433511617305e-05,
457
+ "loss": 0.0698,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.006201550387597,
462
+ "grad_norm": 0.1836194545030594,
463
+ "learning_rate": 4.845501789574674e-05,
464
+ "loss": 0.0563,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0217054263565892,
469
+ "grad_norm": 0.4584813416004181,
470
+ "learning_rate": 4.835984592901678e-05,
471
+ "loss": 0.0489,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0372093023255813,
476
+ "grad_norm": 0.06475898623466492,
477
+ "learning_rate": 4.826192879570078e-05,
478
+ "loss": 0.0526,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0527131782945736,
483
+ "grad_norm": 0.1889159232378006,
484
+ "learning_rate": 4.8161278002674424e-05,
485
+ "loss": 0.0363,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0682170542635658,
490
+ "grad_norm": 0.5690692663192749,
491
+ "learning_rate": 4.80579053780634e-05,
492
+ "loss": 0.0791,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.083720930232558,
497
+ "grad_norm": 0.13445481657981873,
498
+ "learning_rate": 4.795182306985343e-05,
499
+ "loss": 0.0595,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.0992248062015504,
504
+ "grad_norm": 0.357576847076416,
505
+ "learning_rate": 4.7843043544462696e-05,
506
+ "loss": 0.0516,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1147286821705427,
511
+ "grad_norm": 0.16702419519424438,
512
+ "learning_rate": 4.773157958527681e-05,
513
+ "loss": 0.0454,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.130232558139535,
518
+ "grad_norm": 0.23175758123397827,
519
+ "learning_rate": 4.7617444291146565e-05,
520
+ "loss": 0.0378,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1457364341085272,
525
+ "grad_norm": 0.28666743636131287,
526
+ "learning_rate": 4.750065107484859e-05,
527
+ "loss": 0.069,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1612403100775195,
532
+ "grad_norm": 0.2496625781059265,
533
+ "learning_rate": 4.738121366150916e-05,
534
+ "loss": 0.0654,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.1767441860465115,
539
+ "grad_norm": 0.20519720017910004,
540
+ "learning_rate": 4.725914608699122e-05,
541
+ "loss": 0.0576,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.1922480620155038,
546
+ "grad_norm": 0.2702353894710541,
547
+ "learning_rate": 4.7134462696245e-05,
548
+ "loss": 0.0387,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.207751937984496,
553
+ "grad_norm": 0.45655345916748047,
554
+ "learning_rate": 4.700717814162218e-05,
555
+ "loss": 0.0628,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.2232558139534884,
560
+ "grad_norm": 0.2866630554199219,
561
+ "learning_rate": 4.6877307381154044e-05,
562
+ "loss": 0.0596,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2387596899224806,
567
+ "grad_norm": 0.17983689904212952,
568
+ "learning_rate": 4.674486567679367e-05,
569
+ "loss": 0.0376,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.254263565891473,
574
+ "grad_norm": 0.09354360401630402,
575
+ "learning_rate": 4.660986859262236e-05,
576
+ "loss": 0.032,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2697674418604652,
581
+ "grad_norm": 0.3007808327674866,
582
+ "learning_rate": 4.647233199302064e-05,
583
+ "loss": 0.0429,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.2852713178294572,
588
+ "grad_norm": 0.5735777616500854,
589
+ "learning_rate": 4.6332272040803895e-05,
590
+ "loss": 0.0498,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3007751937984495,
595
+ "grad_norm": 0.21312487125396729,
596
+ "learning_rate": 4.618970519532303e-05,
597
+ "loss": 0.0398,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3162790697674418,
602
+ "grad_norm": 0.348650723695755,
603
+ "learning_rate": 4.6044648210530175e-05,
604
+ "loss": 0.0429,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.331782945736434,
609
+ "grad_norm": 0.6043110489845276,
610
+ "learning_rate": 4.589711813300983e-05,
611
+ "loss": 0.0664,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3472868217054264,
616
+ "grad_norm": 0.14238876104354858,
617
+ "learning_rate": 4.574713229997563e-05,
618
+ "loss": 0.0478,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3627906976744186,
623
+ "grad_norm": 0.47702425718307495,
624
+ "learning_rate": 4.559470833723292e-05,
625
+ "loss": 0.0528,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.378294573643411,
630
+ "grad_norm": 0.16487376391887665,
631
+ "learning_rate": 4.5439864157107434e-05,
632
+ "loss": 0.0435,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.3937984496124032,
637
+ "grad_norm": 0.0906042605638504,
638
+ "learning_rate": 4.528261795634032e-05,
639
+ "loss": 0.0337,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.4093023255813955,
644
+ "grad_norm": 0.2174687385559082,
645
+ "learning_rate": 4.5122988213949676e-05,
646
+ "loss": 0.0514,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4248062015503877,
651
+ "grad_norm": 0.08279066532850266,
652
+ "learning_rate": 4.496099368905902e-05,
653
+ "loss": 0.0229,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4403100775193798,
658
+ "grad_norm": 0.19147436320781708,
659
+ "learning_rate": 4.4796653418692745e-05,
660
+ "loss": 0.0347,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.455813953488372,
665
+ "grad_norm": 0.15159855782985687,
666
+ "learning_rate": 4.4629986715538976e-05,
667
+ "loss": 0.0295,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.4713178294573643,
672
+ "grad_norm": 0.3000525236129761,
673
+ "learning_rate": 4.4461013165679986e-05,
674
+ "loss": 0.0405,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.4868217054263566,
679
+ "grad_norm": 0.16434980928897858,
680
+ "learning_rate": 4.428975262629055e-05,
681
+ "loss": 0.0341,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5023255813953489,
686
+ "grad_norm": 0.06991487741470337,
687
+ "learning_rate": 4.411622522330435e-05,
688
+ "loss": 0.0404,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.517829457364341,
693
+ "grad_norm": 0.15435563027858734,
694
+ "learning_rate": 4.39404513490489e-05,
695
+ "loss": 0.0539,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5333333333333332,
700
+ "grad_norm": 0.1697537750005722,
701
+ "learning_rate": 4.376245165984903e-05,
702
+ "loss": 0.0555,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5488372093023255,
707
+ "grad_norm": 0.3248571455478668,
708
+ "learning_rate": 4.358224707359955e-05,
709
+ "loss": 0.0403,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5643410852713178,
714
+ "grad_norm": 0.06237597391009331,
715
+ "learning_rate": 4.3399858767306936e-05,
716
+ "loss": 0.0318,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.57984496124031,
721
+ "grad_norm": 0.34228137135505676,
722
+ "learning_rate": 4.321530817460073e-05,
723
+ "loss": 0.0509,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.5953488372093023,
728
+ "grad_norm": 0.45852935314178467,
729
+ "learning_rate": 4.302861698321478e-05,
730
+ "loss": 0.0418,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6108527131782946,
735
+ "grad_norm": 0.14077672362327576,
736
+ "learning_rate": 4.283980713243847e-05,
737
+ "loss": 0.026,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6263565891472869,
742
+ "grad_norm": 0.13448594510555267,
743
+ "learning_rate": 4.264890081053859e-05,
744
+ "loss": 0.0429,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6418604651162791,
749
+ "grad_norm": 0.0402817465364933,
750
+ "learning_rate": 4.245592045215182e-05,
751
+ "loss": 0.0252,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6573643410852714,
756
+ "grad_norm": 0.25280848145484924,
757
+ "learning_rate": 4.226088873564825e-05,
758
+ "loss": 0.0353,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.6728682170542637,
763
+ "grad_norm": 0.12823021411895752,
764
+ "learning_rate": 4.206382858046636e-05,
765
+ "loss": 0.038,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.688372093023256,
770
+ "grad_norm": 0.08113641291856766,
771
+ "learning_rate": 4.1864763144419536e-05,
772
+ "loss": 0.035,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.703875968992248,
777
+ "grad_norm": 0.27006813883781433,
778
+ "learning_rate": 4.166371582097476e-05,
779
+ "loss": 0.0439,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7193798449612403,
784
+ "grad_norm": 0.2137015163898468,
785
+ "learning_rate": 4.146071023650335e-05,
786
+ "loss": 0.0552,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7348837209302326,
791
+ "grad_norm": 0.35401883721351624,
792
+ "learning_rate": 4.1255770247504576e-05,
793
+ "loss": 0.0259,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7503875968992249,
798
+ "grad_norm": 0.4056580066680908,
799
+ "learning_rate": 4.10489199378021e-05,
800
+ "loss": 0.0419,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.765891472868217,
805
+ "grad_norm": 0.11533407121896744,
806
+ "learning_rate": 4.0840183615713714e-05,
807
+ "loss": 0.0311,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.7813953488372092,
812
+ "grad_norm": 0.1366463154554367,
813
+ "learning_rate": 4.0629585811194726e-05,
814
+ "loss": 0.0449,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.7968992248062015,
819
+ "grad_norm": 0.2846928536891937,
820
+ "learning_rate": 4.041715127295529e-05,
821
+ "loss": 0.0607,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8124031007751937,
826
+ "grad_norm": 0.2537185847759247,
827
+ "learning_rate": 4.020290496555202e-05,
828
+ "loss": 0.0482,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.827906976744186,
833
+ "grad_norm": 0.11237087100744247,
834
+ "learning_rate": 3.9986872066454226e-05,
835
+ "loss": 0.0374,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8434108527131783,
840
+ "grad_norm": 0.25917041301727295,
841
+ "learning_rate": 3.976907796308519e-05,
842
+ "loss": 0.059,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8589147286821706,
847
+ "grad_norm": 0.16126245260238647,
848
+ "learning_rate": 3.954954824983867e-05,
849
+ "loss": 0.0313,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.8744186046511628,
854
+ "grad_norm": 0.17019878327846527,
855
+ "learning_rate": 3.9328308725071204e-05,
856
+ "loss": 0.0397,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.889922480620155,
861
+ "grad_norm": 0.21204759180545807,
862
+ "learning_rate": 3.9105385388070305e-05,
863
+ "loss": 0.0414,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9054263565891474,
868
+ "grad_norm": 0.20105929672718048,
869
+ "learning_rate": 3.8880804435999164e-05,
870
+ "loss": 0.0341,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9209302325581397,
875
+ "grad_norm": 0.11282369494438171,
876
+ "learning_rate": 3.8654592260818045e-05,
877
+ "loss": 0.0323,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.936434108527132,
882
+ "grad_norm": 0.1675432175397873,
883
+ "learning_rate": 3.842677544618279e-05,
884
+ "loss": 0.027,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.951937984496124,
889
+ "grad_norm": 0.2266375571489334,
890
+ "learning_rate": 3.819738076432081e-05,
891
+ "loss": 0.0214,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.9674418604651163,
896
+ "grad_norm": 0.1010638102889061,
897
+ "learning_rate": 3.7966435172884885e-05,
898
+ "loss": 0.0435,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.9829457364341085,
903
+ "grad_norm": 0.11044441908597946,
904
+ "learning_rate": 3.77339658117852e-05,
905
+ "loss": 0.0243,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 1.9984496124031008,
910
+ "grad_norm": 0.050437528640031815,
911
+ "learning_rate": 3.7500000000000003e-05,
912
+ "loss": 0.0423,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.012403100775194,
917
+ "grad_norm": 0.08492262661457062,
918
+ "learning_rate": 3.726456523236511e-05,
919
+ "loss": 0.0266,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.027906976744186,
924
+ "grad_norm": 0.12510479986667633,
925
+ "learning_rate": 3.7027689176342855e-05,
926
+ "loss": 0.0364,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.0434108527131785,
931
+ "grad_norm": 0.191548690199852,
932
+ "learning_rate": 3.67893996687707e-05,
933
+ "loss": 0.0293,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.0589147286821707,
938
+ "grad_norm": 0.2661445140838623,
939
+ "learning_rate": 3.6549724712589905e-05,
940
+ "loss": 0.0298,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.0744186046511626,
945
+ "grad_norm": 0.3290082514286041,
946
+ "learning_rate": 3.6308692473554814e-05,
947
+ "loss": 0.0196,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.089922480620155,
952
+ "grad_norm": 0.2585301697254181,
953
+ "learning_rate": 3.60663312769228e-05,
954
+ "loss": 0.0281,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.105426356589147,
959
+ "grad_norm": 0.23062346875667572,
960
+ "learning_rate": 3.5822669604125684e-05,
961
+ "loss": 0.0228,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1209302325581394,
966
+ "grad_norm": 0.10087283700704575,
967
+ "learning_rate": 3.557773608942262e-05,
968
+ "loss": 0.0292,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.1364341085271317,
973
+ "grad_norm": 0.15738359093666077,
974
+ "learning_rate": 3.533155951653516e-05,
975
+ "loss": 0.0418,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.151937984496124,
980
+ "grad_norm": 0.13803963363170624,
981
+ "learning_rate": 3.508416881526464e-05,
982
+ "loss": 0.0287,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.167441860465116,
987
+ "grad_norm": 0.19056080281734467,
988
+ "learning_rate": 3.483559305809248e-05,
989
+ "loss": 0.0332,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.1829457364341085,
994
+ "grad_norm": 0.18886078894138336,
995
+ "learning_rate": 3.4585861456763686e-05,
996
+ "loss": 0.0352,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.1984496124031008,
1001
+ "grad_norm": 0.2717881202697754,
1002
+ "learning_rate": 3.4335003358853996e-05,
1003
+ "loss": 0.0264,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.213953488372093,
1008
+ "grad_norm": 0.1758740395307541,
1009
+ "learning_rate": 3.408304824432104e-05,
1010
+ "loss": 0.0248,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.2294573643410853,
1015
+ "grad_norm": 0.22997550666332245,
1016
+ "learning_rate": 3.383002572203995e-05,
1017
+ "loss": 0.0306,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2449612403100776,
1022
+ "grad_norm": 0.11724910885095596,
1023
+ "learning_rate": 3.357596552632388e-05,
1024
+ "loss": 0.028,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.26046511627907,
1029
+ "grad_norm": 0.22709335386753082,
1030
+ "learning_rate": 3.332089751342968e-05,
1031
+ "loss": 0.024,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.275968992248062,
1036
+ "grad_norm": 0.27800169587135315,
1037
+ "learning_rate": 3.3064851658049314e-05,
1038
+ "loss": 0.0202,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.2914728682170544,
1043
+ "grad_norm": 0.17299439013004303,
1044
+ "learning_rate": 3.280785804978735e-05,
1045
+ "loss": 0.0189,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.3069767441860467,
1050
+ "grad_norm": 0.1307191699743271,
1051
+ "learning_rate": 3.2549946889624926e-05,
1052
+ "loss": 0.0357,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.322480620155039,
1057
+ "grad_norm": 0.10246355831623077,
1058
+ "learning_rate": 3.2291148486370626e-05,
1059
+ "loss": 0.0224,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3379844961240313,
1064
+ "grad_norm": 0.3734508752822876,
1065
+ "learning_rate": 3.2031493253098724e-05,
1066
+ "loss": 0.0233,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.353488372093023,
1071
+ "grad_norm": 0.13778243958950043,
1072
+ "learning_rate": 3.177101170357513e-05,
1073
+ "loss": 0.0219,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.3689922480620154,
1078
+ "grad_norm": 0.17842572927474976,
1079
+ "learning_rate": 3.150973444867151e-05,
1080
+ "loss": 0.0302,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.3844961240310076,
1085
+ "grad_norm": 0.16797401010990143,
1086
+ "learning_rate": 3.124769219276803e-05,
1087
+ "loss": 0.0492,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4,
1092
+ "grad_norm": 0.1816670447587967,
1093
+ "learning_rate": 3.0984915730145046e-05,
1094
+ "loss": 0.0208,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.415503875968992,
1099
+ "grad_norm": 0.07712769508361816,
1100
+ "learning_rate": 3.072143594136433e-05,
1101
+ "loss": 0.0156,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.4310077519379845,
1106
+ "grad_norm": 0.06302152574062347,
1107
+ "learning_rate": 3.045728378964004e-05,
1108
+ "loss": 0.0212,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.4465116279069767,
1113
+ "grad_norm": 0.11739777028560638,
1114
+ "learning_rate": 3.0192490317200058e-05,
1115
+ "loss": 0.0246,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.462015503875969,
1120
+ "grad_norm": 0.18686673045158386,
1121
+ "learning_rate": 2.9927086641637997e-05,
1122
+ "loss": 0.0166,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.4775193798449613,
1127
+ "grad_norm": 0.1006050631403923,
1128
+ "learning_rate": 2.9661103952256396e-05,
1129
+ "loss": 0.0209,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.4930232558139536,
1134
+ "grad_norm": 0.17344793677330017,
1135
+ "learning_rate": 2.9394573506401467e-05,
1136
+ "loss": 0.0205,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.508527131782946,
1141
+ "grad_norm": 0.08328920602798462,
1142
+ "learning_rate": 2.9127526625789808e-05,
1143
+ "loss": 0.0208,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.524031007751938,
1148
+ "grad_norm": 0.36139625310897827,
1149
+ "learning_rate": 2.885999469282761e-05,
1150
+ "loss": 0.0246,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.5395348837209304,
1155
+ "grad_norm": 0.22528782486915588,
1156
+ "learning_rate": 2.8592009146922704e-05,
1157
+ "loss": 0.0258,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.5550387596899222,
1162
+ "grad_norm": 0.2691043019294739,
1163
+ "learning_rate": 2.8323601480789928e-05,
1164
+ "loss": 0.0203,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.5705426356589145,
1169
+ "grad_norm": 0.1831626147031784,
1170
+ "learning_rate": 2.805480323675016e-05,
1171
+ "loss": 0.0274,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.5860465116279068,
1176
+ "grad_norm": 0.20435118675231934,
1177
+ "learning_rate": 2.7785646003023656e-05,
1178
+ "loss": 0.0217,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.601550387596899,
1183
+ "grad_norm": 0.1789761781692505,
1184
+ "learning_rate": 2.7516161410017844e-05,
1185
+ "loss": 0.0191,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6170542635658913,
1190
+ "grad_norm": 0.08747836202383041,
1191
+ "learning_rate": 2.7246381126610272e-05,
1192
+ "loss": 0.0233,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.6325581395348836,
1197
+ "grad_norm": 0.30709850788116455,
1198
+ "learning_rate": 2.697633685642697e-05,
1199
+ "loss": 0.0252,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.648062015503876,
1204
+ "grad_norm": 0.11726944893598557,
1205
+ "learning_rate": 2.6706060334116777e-05,
1206
+ "loss": 0.0233,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.663565891472868,
1211
+ "grad_norm": 0.06737342476844788,
1212
+ "learning_rate": 2.6435583321621966e-05,
1213
+ "loss": 0.0129,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.6790697674418604,
1218
+ "grad_norm": 0.09594861418008804,
1219
+ "learning_rate": 2.6164937604445705e-05,
1220
+ "loss": 0.021,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.6945736434108527,
1225
+ "grad_norm": 0.12169867008924484,
1226
+ "learning_rate": 2.5894154987916764e-05,
1227
+ "loss": 0.023,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.710077519379845,
1232
+ "grad_norm": 0.22493800520896912,
1233
+ "learning_rate": 2.5623267293451826e-05,
1234
+ "loss": 0.0167,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.7255813953488373,
1239
+ "grad_norm": 0.23264090716838837,
1240
+ "learning_rate": 2.5352306354815953e-05,
1241
+ "loss": 0.0222,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.7410852713178295,
1246
+ "grad_norm": 0.29153597354888916,
1247
+ "learning_rate": 2.5081304014381614e-05,
1248
+ "loss": 0.0208,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.756589147286822,
1253
+ "grad_norm": 0.11771135032176971,
1254
+ "learning_rate": 2.4810292119386675e-05,
1255
+ "loss": 0.0186,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.772093023255814,
1260
+ "grad_norm": 0.33184051513671875,
1261
+ "learning_rate": 2.4539302518191802e-05,
1262
+ "loss": 0.0177,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.7875968992248064,
1267
+ "grad_norm": 0.2414429783821106,
1268
+ "learning_rate": 2.426836705653782e-05,
1269
+ "loss": 0.0198,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8031007751937986,
1274
+ "grad_norm": 0.11880580335855484,
1275
+ "learning_rate": 2.3997517573803187e-05,
1276
+ "loss": 0.0188,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.818604651162791,
1281
+ "grad_norm": 0.05161415413022041,
1282
+ "learning_rate": 2.3726785899262493e-05,
1283
+ "loss": 0.0131,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.834108527131783,
1288
+ "grad_norm": 0.09770730137825012,
1289
+ "learning_rate": 2.34562038483459e-05,
1290
+ "loss": 0.0129,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.8496124031007755,
1295
+ "grad_norm": 0.27657774090766907,
1296
+ "learning_rate": 2.318580321890032e-05,
1297
+ "loss": 0.0242,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.8651162790697673,
1302
+ "grad_norm": 0.1245102509856224,
1303
+ "learning_rate": 2.2915615787452666e-05,
1304
+ "loss": 0.0182,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.8806201550387596,
1309
+ "grad_norm": 0.095403291285038,
1310
+ "learning_rate": 2.264567330547557e-05,
1311
+ "loss": 0.0229,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.896124031007752,
1316
+ "grad_norm": 0.09689685702323914,
1317
+ "learning_rate": 2.2376007495656084e-05,
1318
+ "loss": 0.02,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.911627906976744,
1323
+ "grad_norm": 0.07814809679985046,
1324
+ "learning_rate": 2.2106650048167697e-05,
1325
+ "loss": 0.0296,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.9271317829457364,
1330
+ "grad_norm": 0.18573637306690216,
1331
+ "learning_rate": 2.1837632616946266e-05,
1332
+ "loss": 0.0191,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.9426356589147287,
1337
+ "grad_norm": 0.16544780135154724,
1338
+ "learning_rate": 2.1568986815970126e-05,
1339
+ "loss": 0.0262,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.958139534883721,
1344
+ "grad_norm": 0.06749454140663147,
1345
+ "learning_rate": 2.1300744215544967e-05,
1346
+ "loss": 0.0178,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.973643410852713,
1351
+ "grad_norm": 0.1645621359348297,
1352
+ "learning_rate": 2.1032936338593718e-05,
1353
+ "loss": 0.017,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.9891472868217055,
1358
+ "grad_norm": 0.14035086333751678,
1359
+ "learning_rate": 2.0765594656952198e-05,
1360
+ "loss": 0.0269,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 3.0031007751937984,
1365
+ "grad_norm": 0.07817042618989944,
1366
+ "learning_rate": 2.0498750587670572e-05,
1367
+ "loss": 0.0183,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 3.0186046511627906,
1372
+ "grad_norm": 0.0851919949054718,
1373
+ "learning_rate": 2.0232435489321354e-05,
1374
+ "loss": 0.0115,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 3.034108527131783,
1379
+ "grad_norm": 0.07319127768278122,
1380
+ "learning_rate": 1.9966680658314273e-05,
1381
+ "loss": 0.0186,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 3.049612403100775,
1386
+ "grad_norm": 0.05918855220079422,
1387
+ "learning_rate": 1.970151732521842e-05,
1388
+ "loss": 0.0137,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 3.0651162790697675,
1393
+ "grad_norm": 0.09402059018611908,
1394
+ "learning_rate": 1.9436976651092144e-05,
1395
+ "loss": 0.0216,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 3.0806201550387597,
1400
+ "grad_norm": 0.15518927574157715,
1401
+ "learning_rate": 1.917308972382109e-05,
1402
+ "loss": 0.0164,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 3.096124031007752,
1407
+ "grad_norm": 0.17928968369960785,
1408
+ "learning_rate": 1.89098875544649e-05,
1409
+ "loss": 0.0153,
1410
+ "step": 1000
1411
+ }
1412
+ ],
1413
+ "logging_steps": 5,
1414
+ "max_steps": 1610,
1415
+ "num_input_tokens_seen": 0,
1416
+ "num_train_epochs": 5,
1417
+ "save_steps": 500,
1418
+ "stateful_callbacks": {
1419
+ "TrainerControl": {
1420
+ "args": {
1421
+ "should_epoch_stop": false,
1422
+ "should_evaluate": false,
1423
+ "should_log": false,
1424
+ "should_save": true,
1425
+ "should_training_stop": false
1426
+ },
1427
+ "attributes": {}
1428
+ }
1429
+ },
1430
+ "total_flos": 1.686138310950912e+16,
1431
+ "train_batch_size": 2,
1432
+ "trial_name": null,
1433
+ "trial_params": null
1434
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc429601d1d23ce75bcf84e7e4ed5fc0ae418d073e5933d8bb8717ac0faf730
3
+ size 5688
checkpoint-1500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-1B-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 0.15.2
checkpoint-1500/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "k_proj",
31
+ "up_proj",
32
+ "down_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-1500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34887dc91c196cbe622389714f8082f1aed5f9d8b5adcf2c9b549ec4a63f8658
3
+ size 180385008
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f1855615184b58778c1075b66068027d19fb04ad043decf737b8d0c0ce0aa84
3
+ size 360899194
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
3
+ size 14244
checkpoint-1500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a4b6e0ef05ca249f2d6b7f9f3ad1dff81e55842a962df795bb9740c17c8e92
3
+ size 988
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c58b0a34317bc16485e30e76a0870fd61f7d7086be9d0d74b9ddb18e98eaac3
3
+ size 1064
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
checkpoint-1500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|eom_id|>"
2054
+ ],
2055
+ "bos_token": "<|begin_of_text|>",
2056
+ "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",
2057
+ "clean_up_tokenization_spaces": true,
2058
+ "eos_token": "<|eot_id|>",
2059
+ "extra_special_tokens": {},
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 131072,
2065
+ "pad_token": "<|eot_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizer"
2069
+ }
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,2134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.644961240310078,
6
+ "eval_steps": 500,
7
+ "global_step": 1500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015503875968992248,
14
+ "grad_norm": 2.5634377002716064,
15
+ "learning_rate": 1.2422360248447205e-06,
16
+ "loss": 2.2423,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.031007751937984496,
21
+ "grad_norm": 1.774464726448059,
22
+ "learning_rate": 2.7950310559006214e-06,
23
+ "loss": 2.0959,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.046511627906976744,
28
+ "grad_norm": 2.2086267471313477,
29
+ "learning_rate": 4.347826086956522e-06,
30
+ "loss": 1.7507,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06201550387596899,
35
+ "grad_norm": 1.5988163948059082,
36
+ "learning_rate": 5.900621118012423e-06,
37
+ "loss": 1.4298,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07751937984496124,
42
+ "grad_norm": 1.3644428253173828,
43
+ "learning_rate": 7.453416149068324e-06,
44
+ "loss": 0.9425,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09302325581395349,
49
+ "grad_norm": 1.1469796895980835,
50
+ "learning_rate": 9.006211180124225e-06,
51
+ "loss": 0.6502,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.10852713178294573,
56
+ "grad_norm": 1.8373690843582153,
57
+ "learning_rate": 1.0559006211180125e-05,
58
+ "loss": 0.6724,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12403100775193798,
63
+ "grad_norm": 1.116761565208435,
64
+ "learning_rate": 1.2111801242236026e-05,
65
+ "loss": 0.4023,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.13953488372093023,
70
+ "grad_norm": 0.7392648458480835,
71
+ "learning_rate": 1.3664596273291926e-05,
72
+ "loss": 0.3874,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15503875968992248,
77
+ "grad_norm": 0.9391402006149292,
78
+ "learning_rate": 1.5217391304347828e-05,
79
+ "loss": 0.3164,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17054263565891473,
84
+ "grad_norm": 0.9636594653129578,
85
+ "learning_rate": 1.6770186335403728e-05,
86
+ "loss": 0.1785,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.18604651162790697,
91
+ "grad_norm": 0.6391934156417847,
92
+ "learning_rate": 1.8322981366459628e-05,
93
+ "loss": 0.1778,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20155038759689922,
98
+ "grad_norm": 0.5561841726303101,
99
+ "learning_rate": 1.9875776397515528e-05,
100
+ "loss": 0.2703,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.21705426356589147,
105
+ "grad_norm": 0.49807441234588623,
106
+ "learning_rate": 2.1428571428571428e-05,
107
+ "loss": 0.1875,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.23255813953488372,
112
+ "grad_norm": 1.2350372076034546,
113
+ "learning_rate": 2.2981366459627328e-05,
114
+ "loss": 0.3248,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.24806201550387597,
119
+ "grad_norm": 0.6338334083557129,
120
+ "learning_rate": 2.453416149068323e-05,
121
+ "loss": 0.1297,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.26356589147286824,
126
+ "grad_norm": 0.6853603720664978,
127
+ "learning_rate": 2.608695652173913e-05,
128
+ "loss": 0.1357,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.27906976744186046,
133
+ "grad_norm": 1.0921283960342407,
134
+ "learning_rate": 2.7639751552795035e-05,
135
+ "loss": 0.1418,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.29457364341085274,
140
+ "grad_norm": 0.7996405363082886,
141
+ "learning_rate": 2.919254658385093e-05,
142
+ "loss": 0.1293,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.31007751937984496,
147
+ "grad_norm": 0.4951094388961792,
148
+ "learning_rate": 3.074534161490684e-05,
149
+ "loss": 0.1783,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.32558139534883723,
154
+ "grad_norm": 0.3423459231853485,
155
+ "learning_rate": 3.2298136645962735e-05,
156
+ "loss": 0.0996,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.34108527131782945,
161
+ "grad_norm": 0.6147115230560303,
162
+ "learning_rate": 3.385093167701863e-05,
163
+ "loss": 0.1909,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.35658914728682173,
168
+ "grad_norm": 0.6499375104904175,
169
+ "learning_rate": 3.5403726708074535e-05,
170
+ "loss": 0.1572,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.37209302325581395,
175
+ "grad_norm": 0.274794340133667,
176
+ "learning_rate": 3.695652173913043e-05,
177
+ "loss": 0.1313,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.3875968992248062,
182
+ "grad_norm": 0.44879093766212463,
183
+ "learning_rate": 3.8509316770186335e-05,
184
+ "loss": 0.1141,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.40310077519379844,
189
+ "grad_norm": 0.3992724120616913,
190
+ "learning_rate": 4.006211180124224e-05,
191
+ "loss": 0.1539,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4186046511627907,
196
+ "grad_norm": 0.28350868821144104,
197
+ "learning_rate": 4.161490683229814e-05,
198
+ "loss": 0.0857,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.43410852713178294,
203
+ "grad_norm": 0.5912169814109802,
204
+ "learning_rate": 4.316770186335404e-05,
205
+ "loss": 0.1939,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4496124031007752,
210
+ "grad_norm": 0.35334816575050354,
211
+ "learning_rate": 4.472049689440994e-05,
212
+ "loss": 0.1149,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.46511627906976744,
217
+ "grad_norm": 0.7359523177146912,
218
+ "learning_rate": 4.627329192546584e-05,
219
+ "loss": 0.1193,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.4806201550387597,
224
+ "grad_norm": 0.43439972400665283,
225
+ "learning_rate": 4.782608695652174e-05,
226
+ "loss": 0.1049,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.49612403100775193,
231
+ "grad_norm": 0.4149303734302521,
232
+ "learning_rate": 4.937888198757764e-05,
233
+ "loss": 0.1168,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5116279069767442,
238
+ "grad_norm": 0.38137003779411316,
239
+ "learning_rate": 4.999947117257964e-05,
240
+ "loss": 0.122,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5271317829457365,
245
+ "grad_norm": 0.6025403738021851,
246
+ "learning_rate": 4.999623953047522e-05,
247
+ "loss": 0.1107,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5426356589147286,
252
+ "grad_norm": 0.6327984929084778,
253
+ "learning_rate": 4.999007041858851e-05,
254
+ "loss": 0.0855,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5581395348837209,
259
+ "grad_norm": 0.5637001991271973,
260
+ "learning_rate": 4.998096456189175e-05,
261
+ "loss": 0.0993,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5736434108527132,
266
+ "grad_norm": 0.2784324586391449,
267
+ "learning_rate": 4.996892303047306e-05,
268
+ "loss": 0.0716,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5891472868217055,
273
+ "grad_norm": 0.6117509603500366,
274
+ "learning_rate": 4.995394723941068e-05,
275
+ "loss": 0.0693,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6046511627906976,
280
+ "grad_norm": 1.3043673038482666,
281
+ "learning_rate": 4.993603894860669e-05,
282
+ "loss": 0.1016,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6201550387596899,
287
+ "grad_norm": 0.44789212942123413,
288
+ "learning_rate": 4.991520026258015e-05,
289
+ "loss": 0.0891,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6356589147286822,
294
+ "grad_norm": 1.85973060131073,
295
+ "learning_rate": 4.989143363021987e-05,
296
+ "loss": 0.1393,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6511627906976745,
301
+ "grad_norm": 1.2061032056808472,
302
+ "learning_rate": 4.9864741844496506e-05,
303
+ "loss": 0.116,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6666666666666666,
308
+ "grad_norm": 0.3840301036834717,
309
+ "learning_rate": 4.983512804213447e-05,
310
+ "loss": 0.0952,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6821705426356589,
315
+ "grad_norm": 0.4879723787307739,
316
+ "learning_rate": 4.9802595703243205e-05,
317
+ "loss": 0.128,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.6976744186046512,
322
+ "grad_norm": 0.4783574938774109,
323
+ "learning_rate": 4.976714865090827e-05,
324
+ "loss": 0.0783,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7131782945736435,
329
+ "grad_norm": 0.4228968620300293,
330
+ "learning_rate": 4.9728791050742064e-05,
331
+ "loss": 0.1176,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7286821705426356,
336
+ "grad_norm": 0.18757346272468567,
337
+ "learning_rate": 4.9687527410394275e-05,
338
+ "loss": 0.0872,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7441860465116279,
343
+ "grad_norm": 0.4684408903121948,
344
+ "learning_rate": 4.964336257902217e-05,
345
+ "loss": 0.0753,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7596899224806202,
350
+ "grad_norm": 0.7171066403388977,
351
+ "learning_rate": 4.9596301746720734e-05,
352
+ "loss": 0.0988,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7751937984496124,
357
+ "grad_norm": 0.5907664895057678,
358
+ "learning_rate": 4.9546350443912783e-05,
359
+ "loss": 0.1172,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.7906976744186046,
364
+ "grad_norm": 0.8421684503555298,
365
+ "learning_rate": 4.9493514540698963e-05,
366
+ "loss": 0.0771,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8062015503875969,
371
+ "grad_norm": 0.2831384837627411,
372
+ "learning_rate": 4.9437800246168025e-05,
373
+ "loss": 0.1212,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8217054263565892,
378
+ "grad_norm": 0.4991057217121124,
379
+ "learning_rate": 4.937921410766707e-05,
380
+ "loss": 0.0837,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8372093023255814,
385
+ "grad_norm": 0.5720856189727783,
386
+ "learning_rate": 4.931776301003217e-05,
387
+ "loss": 0.1615,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8527131782945736,
392
+ "grad_norm": 0.48435062170028687,
393
+ "learning_rate": 4.9253454174779265e-05,
394
+ "loss": 0.0872,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8682170542635659,
399
+ "grad_norm": 0.2810228765010834,
400
+ "learning_rate": 4.9186295159255537e-05,
401
+ "loss": 0.0886,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8837209302325582,
406
+ "grad_norm": 0.8470152616500854,
407
+ "learning_rate": 4.9116293855751285e-05,
408
+ "loss": 0.1107,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.8992248062015504,
413
+ "grad_norm": 0.26309266686439514,
414
+ "learning_rate": 4.9043458490572444e-05,
415
+ "loss": 0.0861,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9147286821705426,
420
+ "grad_norm": 0.4955242872238159,
421
+ "learning_rate": 4.896779762307389e-05,
422
+ "loss": 0.0548,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9302325581395349,
427
+ "grad_norm": 0.5125411152839661,
428
+ "learning_rate": 4.888932014465352e-05,
429
+ "loss": 0.0456,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9457364341085271,
434
+ "grad_norm": 0.4470186233520508,
435
+ "learning_rate": 4.880803527770742e-05,
436
+ "loss": 0.0909,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9612403100775194,
441
+ "grad_norm": 0.22464849054813385,
442
+ "learning_rate": 4.872395257454605e-05,
443
+ "loss": 0.0722,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9767441860465116,
448
+ "grad_norm": 0.1867540031671524,
449
+ "learning_rate": 4.86370819162717e-05,
450
+ "loss": 0.0497,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.9922480620155039,
455
+ "grad_norm": 0.1916547268629074,
456
+ "learning_rate": 4.8547433511617305e-05,
457
+ "loss": 0.0698,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.006201550387597,
462
+ "grad_norm": 0.1836194545030594,
463
+ "learning_rate": 4.845501789574674e-05,
464
+ "loss": 0.0563,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0217054263565892,
469
+ "grad_norm": 0.4584813416004181,
470
+ "learning_rate": 4.835984592901678e-05,
471
+ "loss": 0.0489,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0372093023255813,
476
+ "grad_norm": 0.06475898623466492,
477
+ "learning_rate": 4.826192879570078e-05,
478
+ "loss": 0.0526,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0527131782945736,
483
+ "grad_norm": 0.1889159232378006,
484
+ "learning_rate": 4.8161278002674424e-05,
485
+ "loss": 0.0363,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0682170542635658,
490
+ "grad_norm": 0.5690692663192749,
491
+ "learning_rate": 4.80579053780634e-05,
492
+ "loss": 0.0791,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.083720930232558,
497
+ "grad_norm": 0.13445481657981873,
498
+ "learning_rate": 4.795182306985343e-05,
499
+ "loss": 0.0595,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.0992248062015504,
504
+ "grad_norm": 0.357576847076416,
505
+ "learning_rate": 4.7843043544462696e-05,
506
+ "loss": 0.0516,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1147286821705427,
511
+ "grad_norm": 0.16702419519424438,
512
+ "learning_rate": 4.773157958527681e-05,
513
+ "loss": 0.0454,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.130232558139535,
518
+ "grad_norm": 0.23175758123397827,
519
+ "learning_rate": 4.7617444291146565e-05,
520
+ "loss": 0.0378,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1457364341085272,
525
+ "grad_norm": 0.28666743636131287,
526
+ "learning_rate": 4.750065107484859e-05,
527
+ "loss": 0.069,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1612403100775195,
532
+ "grad_norm": 0.2496625781059265,
533
+ "learning_rate": 4.738121366150916e-05,
534
+ "loss": 0.0654,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.1767441860465115,
539
+ "grad_norm": 0.20519720017910004,
540
+ "learning_rate": 4.725914608699122e-05,
541
+ "loss": 0.0576,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.1922480620155038,
546
+ "grad_norm": 0.2702353894710541,
547
+ "learning_rate": 4.7134462696245e-05,
548
+ "loss": 0.0387,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.207751937984496,
553
+ "grad_norm": 0.45655345916748047,
554
+ "learning_rate": 4.700717814162218e-05,
555
+ "loss": 0.0628,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.2232558139534884,
560
+ "grad_norm": 0.2866630554199219,
561
+ "learning_rate": 4.6877307381154044e-05,
562
+ "loss": 0.0596,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2387596899224806,
567
+ "grad_norm": 0.17983689904212952,
568
+ "learning_rate": 4.674486567679367e-05,
569
+ "loss": 0.0376,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.254263565891473,
574
+ "grad_norm": 0.09354360401630402,
575
+ "learning_rate": 4.660986859262236e-05,
576
+ "loss": 0.032,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2697674418604652,
581
+ "grad_norm": 0.3007808327674866,
582
+ "learning_rate": 4.647233199302064e-05,
583
+ "loss": 0.0429,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.2852713178294572,
588
+ "grad_norm": 0.5735777616500854,
589
+ "learning_rate": 4.6332272040803895e-05,
590
+ "loss": 0.0498,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3007751937984495,
595
+ "grad_norm": 0.21312487125396729,
596
+ "learning_rate": 4.618970519532303e-05,
597
+ "loss": 0.0398,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3162790697674418,
602
+ "grad_norm": 0.348650723695755,
603
+ "learning_rate": 4.6044648210530175e-05,
604
+ "loss": 0.0429,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.331782945736434,
609
+ "grad_norm": 0.6043110489845276,
610
+ "learning_rate": 4.589711813300983e-05,
611
+ "loss": 0.0664,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3472868217054264,
616
+ "grad_norm": 0.14238876104354858,
617
+ "learning_rate": 4.574713229997563e-05,
618
+ "loss": 0.0478,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3627906976744186,
623
+ "grad_norm": 0.47702425718307495,
624
+ "learning_rate": 4.559470833723292e-05,
625
+ "loss": 0.0528,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.378294573643411,
630
+ "grad_norm": 0.16487376391887665,
631
+ "learning_rate": 4.5439864157107434e-05,
632
+ "loss": 0.0435,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.3937984496124032,
637
+ "grad_norm": 0.0906042605638504,
638
+ "learning_rate": 4.528261795634032e-05,
639
+ "loss": 0.0337,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.4093023255813955,
644
+ "grad_norm": 0.2174687385559082,
645
+ "learning_rate": 4.5122988213949676e-05,
646
+ "loss": 0.0514,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4248062015503877,
651
+ "grad_norm": 0.08279066532850266,
652
+ "learning_rate": 4.496099368905902e-05,
653
+ "loss": 0.0229,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4403100775193798,
658
+ "grad_norm": 0.19147436320781708,
659
+ "learning_rate": 4.4796653418692745e-05,
660
+ "loss": 0.0347,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.455813953488372,
665
+ "grad_norm": 0.15159855782985687,
666
+ "learning_rate": 4.4629986715538976e-05,
667
+ "loss": 0.0295,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.4713178294573643,
672
+ "grad_norm": 0.3000525236129761,
673
+ "learning_rate": 4.4461013165679986e-05,
674
+ "loss": 0.0405,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.4868217054263566,
679
+ "grad_norm": 0.16434980928897858,
680
+ "learning_rate": 4.428975262629055e-05,
681
+ "loss": 0.0341,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5023255813953489,
686
+ "grad_norm": 0.06991487741470337,
687
+ "learning_rate": 4.411622522330435e-05,
688
+ "loss": 0.0404,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.517829457364341,
693
+ "grad_norm": 0.15435563027858734,
694
+ "learning_rate": 4.39404513490489e-05,
695
+ "loss": 0.0539,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5333333333333332,
700
+ "grad_norm": 0.1697537750005722,
701
+ "learning_rate": 4.376245165984903e-05,
702
+ "loss": 0.0555,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5488372093023255,
707
+ "grad_norm": 0.3248571455478668,
708
+ "learning_rate": 4.358224707359955e-05,
709
+ "loss": 0.0403,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5643410852713178,
714
+ "grad_norm": 0.06237597391009331,
715
+ "learning_rate": 4.3399858767306936e-05,
716
+ "loss": 0.0318,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.57984496124031,
721
+ "grad_norm": 0.34228137135505676,
722
+ "learning_rate": 4.321530817460073e-05,
723
+ "loss": 0.0509,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.5953488372093023,
728
+ "grad_norm": 0.45852935314178467,
729
+ "learning_rate": 4.302861698321478e-05,
730
+ "loss": 0.0418,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6108527131782946,
735
+ "grad_norm": 0.14077672362327576,
736
+ "learning_rate": 4.283980713243847e-05,
737
+ "loss": 0.026,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6263565891472869,
742
+ "grad_norm": 0.13448594510555267,
743
+ "learning_rate": 4.264890081053859e-05,
744
+ "loss": 0.0429,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6418604651162791,
749
+ "grad_norm": 0.0402817465364933,
750
+ "learning_rate": 4.245592045215182e-05,
751
+ "loss": 0.0252,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6573643410852714,
756
+ "grad_norm": 0.25280848145484924,
757
+ "learning_rate": 4.226088873564825e-05,
758
+ "loss": 0.0353,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.6728682170542637,
763
+ "grad_norm": 0.12823021411895752,
764
+ "learning_rate": 4.206382858046636e-05,
765
+ "loss": 0.038,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.688372093023256,
770
+ "grad_norm": 0.08113641291856766,
771
+ "learning_rate": 4.1864763144419536e-05,
772
+ "loss": 0.035,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.703875968992248,
777
+ "grad_norm": 0.27006813883781433,
778
+ "learning_rate": 4.166371582097476e-05,
779
+ "loss": 0.0439,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7193798449612403,
784
+ "grad_norm": 0.2137015163898468,
785
+ "learning_rate": 4.146071023650335e-05,
786
+ "loss": 0.0552,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7348837209302326,
791
+ "grad_norm": 0.35401883721351624,
792
+ "learning_rate": 4.1255770247504576e-05,
793
+ "loss": 0.0259,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7503875968992249,
798
+ "grad_norm": 0.4056580066680908,
799
+ "learning_rate": 4.10489199378021e-05,
800
+ "loss": 0.0419,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.765891472868217,
805
+ "grad_norm": 0.11533407121896744,
806
+ "learning_rate": 4.0840183615713714e-05,
807
+ "loss": 0.0311,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.7813953488372092,
812
+ "grad_norm": 0.1366463154554367,
813
+ "learning_rate": 4.0629585811194726e-05,
814
+ "loss": 0.0449,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.7968992248062015,
819
+ "grad_norm": 0.2846928536891937,
820
+ "learning_rate": 4.041715127295529e-05,
821
+ "loss": 0.0607,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8124031007751937,
826
+ "grad_norm": 0.2537185847759247,
827
+ "learning_rate": 4.020290496555202e-05,
828
+ "loss": 0.0482,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.827906976744186,
833
+ "grad_norm": 0.11237087100744247,
834
+ "learning_rate": 3.9986872066454226e-05,
835
+ "loss": 0.0374,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8434108527131783,
840
+ "grad_norm": 0.25917041301727295,
841
+ "learning_rate": 3.976907796308519e-05,
842
+ "loss": 0.059,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8589147286821706,
847
+ "grad_norm": 0.16126245260238647,
848
+ "learning_rate": 3.954954824983867e-05,
849
+ "loss": 0.0313,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.8744186046511628,
854
+ "grad_norm": 0.17019878327846527,
855
+ "learning_rate": 3.9328308725071204e-05,
856
+ "loss": 0.0397,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.889922480620155,
861
+ "grad_norm": 0.21204759180545807,
862
+ "learning_rate": 3.9105385388070305e-05,
863
+ "loss": 0.0414,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9054263565891474,
868
+ "grad_norm": 0.20105929672718048,
869
+ "learning_rate": 3.8880804435999164e-05,
870
+ "loss": 0.0341,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9209302325581397,
875
+ "grad_norm": 0.11282369494438171,
876
+ "learning_rate": 3.8654592260818045e-05,
877
+ "loss": 0.0323,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.936434108527132,
882
+ "grad_norm": 0.1675432175397873,
883
+ "learning_rate": 3.842677544618279e-05,
884
+ "loss": 0.027,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.951937984496124,
889
+ "grad_norm": 0.2266375571489334,
890
+ "learning_rate": 3.819738076432081e-05,
891
+ "loss": 0.0214,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.9674418604651163,
896
+ "grad_norm": 0.1010638102889061,
897
+ "learning_rate": 3.7966435172884885e-05,
898
+ "loss": 0.0435,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.9829457364341085,
903
+ "grad_norm": 0.11044441908597946,
904
+ "learning_rate": 3.77339658117852e-05,
905
+ "loss": 0.0243,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 1.9984496124031008,
910
+ "grad_norm": 0.050437528640031815,
911
+ "learning_rate": 3.7500000000000003e-05,
912
+ "loss": 0.0423,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.012403100775194,
917
+ "grad_norm": 0.08492262661457062,
918
+ "learning_rate": 3.726456523236511e-05,
919
+ "loss": 0.0266,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.027906976744186,
924
+ "grad_norm": 0.12510479986667633,
925
+ "learning_rate": 3.7027689176342855e-05,
926
+ "loss": 0.0364,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.0434108527131785,
931
+ "grad_norm": 0.191548690199852,
932
+ "learning_rate": 3.67893996687707e-05,
933
+ "loss": 0.0293,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.0589147286821707,
938
+ "grad_norm": 0.2661445140838623,
939
+ "learning_rate": 3.6549724712589905e-05,
940
+ "loss": 0.0298,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.0744186046511626,
945
+ "grad_norm": 0.3290082514286041,
946
+ "learning_rate": 3.6308692473554814e-05,
947
+ "loss": 0.0196,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.089922480620155,
952
+ "grad_norm": 0.2585301697254181,
953
+ "learning_rate": 3.60663312769228e-05,
954
+ "loss": 0.0281,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.105426356589147,
959
+ "grad_norm": 0.23062346875667572,
960
+ "learning_rate": 3.5822669604125684e-05,
961
+ "loss": 0.0228,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1209302325581394,
966
+ "grad_norm": 0.10087283700704575,
967
+ "learning_rate": 3.557773608942262e-05,
968
+ "loss": 0.0292,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.1364341085271317,
973
+ "grad_norm": 0.15738359093666077,
974
+ "learning_rate": 3.533155951653516e-05,
975
+ "loss": 0.0418,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.151937984496124,
980
+ "grad_norm": 0.13803963363170624,
981
+ "learning_rate": 3.508416881526464e-05,
982
+ "loss": 0.0287,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.167441860465116,
987
+ "grad_norm": 0.19056080281734467,
988
+ "learning_rate": 3.483559305809248e-05,
989
+ "loss": 0.0332,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.1829457364341085,
994
+ "grad_norm": 0.18886078894138336,
995
+ "learning_rate": 3.4585861456763686e-05,
996
+ "loss": 0.0352,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.1984496124031008,
1001
+ "grad_norm": 0.2717881202697754,
1002
+ "learning_rate": 3.4335003358853996e-05,
1003
+ "loss": 0.0264,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.213953488372093,
1008
+ "grad_norm": 0.1758740395307541,
1009
+ "learning_rate": 3.408304824432104e-05,
1010
+ "loss": 0.0248,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.2294573643410853,
1015
+ "grad_norm": 0.22997550666332245,
1016
+ "learning_rate": 3.383002572203995e-05,
1017
+ "loss": 0.0306,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2449612403100776,
1022
+ "grad_norm": 0.11724910885095596,
1023
+ "learning_rate": 3.357596552632388e-05,
1024
+ "loss": 0.028,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.26046511627907,
1029
+ "grad_norm": 0.22709335386753082,
1030
+ "learning_rate": 3.332089751342968e-05,
1031
+ "loss": 0.024,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.275968992248062,
1036
+ "grad_norm": 0.27800169587135315,
1037
+ "learning_rate": 3.3064851658049314e-05,
1038
+ "loss": 0.0202,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.2914728682170544,
1043
+ "grad_norm": 0.17299439013004303,
1044
+ "learning_rate": 3.280785804978735e-05,
1045
+ "loss": 0.0189,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.3069767441860467,
1050
+ "grad_norm": 0.1307191699743271,
1051
+ "learning_rate": 3.2549946889624926e-05,
1052
+ "loss": 0.0357,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.322480620155039,
1057
+ "grad_norm": 0.10246355831623077,
1058
+ "learning_rate": 3.2291148486370626e-05,
1059
+ "loss": 0.0224,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3379844961240313,
1064
+ "grad_norm": 0.3734508752822876,
1065
+ "learning_rate": 3.2031493253098724e-05,
1066
+ "loss": 0.0233,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.353488372093023,
1071
+ "grad_norm": 0.13778243958950043,
1072
+ "learning_rate": 3.177101170357513e-05,
1073
+ "loss": 0.0219,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.3689922480620154,
1078
+ "grad_norm": 0.17842572927474976,
1079
+ "learning_rate": 3.150973444867151e-05,
1080
+ "loss": 0.0302,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.3844961240310076,
1085
+ "grad_norm": 0.16797401010990143,
1086
+ "learning_rate": 3.124769219276803e-05,
1087
+ "loss": 0.0492,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4,
1092
+ "grad_norm": 0.1816670447587967,
1093
+ "learning_rate": 3.0984915730145046e-05,
1094
+ "loss": 0.0208,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.415503875968992,
1099
+ "grad_norm": 0.07712769508361816,
1100
+ "learning_rate": 3.072143594136433e-05,
1101
+ "loss": 0.0156,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.4310077519379845,
1106
+ "grad_norm": 0.06302152574062347,
1107
+ "learning_rate": 3.045728378964004e-05,
1108
+ "loss": 0.0212,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.4465116279069767,
1113
+ "grad_norm": 0.11739777028560638,
1114
+ "learning_rate": 3.0192490317200058e-05,
1115
+ "loss": 0.0246,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.462015503875969,
1120
+ "grad_norm": 0.18686673045158386,
1121
+ "learning_rate": 2.9927086641637997e-05,
1122
+ "loss": 0.0166,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.4775193798449613,
1127
+ "grad_norm": 0.1006050631403923,
1128
+ "learning_rate": 2.9661103952256396e-05,
1129
+ "loss": 0.0209,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.4930232558139536,
1134
+ "grad_norm": 0.17344793677330017,
1135
+ "learning_rate": 2.9394573506401467e-05,
1136
+ "loss": 0.0205,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.508527131782946,
1141
+ "grad_norm": 0.08328920602798462,
1142
+ "learning_rate": 2.9127526625789808e-05,
1143
+ "loss": 0.0208,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.524031007751938,
1148
+ "grad_norm": 0.36139625310897827,
1149
+ "learning_rate": 2.885999469282761e-05,
1150
+ "loss": 0.0246,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.5395348837209304,
1155
+ "grad_norm": 0.22528782486915588,
1156
+ "learning_rate": 2.8592009146922704e-05,
1157
+ "loss": 0.0258,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.5550387596899222,
1162
+ "grad_norm": 0.2691043019294739,
1163
+ "learning_rate": 2.8323601480789928e-05,
1164
+ "loss": 0.0203,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.5705426356589145,
1169
+ "grad_norm": 0.1831626147031784,
1170
+ "learning_rate": 2.805480323675016e-05,
1171
+ "loss": 0.0274,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.5860465116279068,
1176
+ "grad_norm": 0.20435118675231934,
1177
+ "learning_rate": 2.7785646003023656e-05,
1178
+ "loss": 0.0217,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.601550387596899,
1183
+ "grad_norm": 0.1789761781692505,
1184
+ "learning_rate": 2.7516161410017844e-05,
1185
+ "loss": 0.0191,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6170542635658913,
1190
+ "grad_norm": 0.08747836202383041,
1191
+ "learning_rate": 2.7246381126610272e-05,
1192
+ "loss": 0.0233,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.6325581395348836,
1197
+ "grad_norm": 0.30709850788116455,
1198
+ "learning_rate": 2.697633685642697e-05,
1199
+ "loss": 0.0252,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.648062015503876,
1204
+ "grad_norm": 0.11726944893598557,
1205
+ "learning_rate": 2.6706060334116777e-05,
1206
+ "loss": 0.0233,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.663565891472868,
1211
+ "grad_norm": 0.06737342476844788,
1212
+ "learning_rate": 2.6435583321621966e-05,
1213
+ "loss": 0.0129,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.6790697674418604,
1218
+ "grad_norm": 0.09594861418008804,
1219
+ "learning_rate": 2.6164937604445705e-05,
1220
+ "loss": 0.021,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.6945736434108527,
1225
+ "grad_norm": 0.12169867008924484,
1226
+ "learning_rate": 2.5894154987916764e-05,
1227
+ "loss": 0.023,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.710077519379845,
1232
+ "grad_norm": 0.22493800520896912,
1233
+ "learning_rate": 2.5623267293451826e-05,
1234
+ "loss": 0.0167,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.7255813953488373,
1239
+ "grad_norm": 0.23264090716838837,
1240
+ "learning_rate": 2.5352306354815953e-05,
1241
+ "loss": 0.0222,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.7410852713178295,
1246
+ "grad_norm": 0.29153597354888916,
1247
+ "learning_rate": 2.5081304014381614e-05,
1248
+ "loss": 0.0208,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.756589147286822,
1253
+ "grad_norm": 0.11771135032176971,
1254
+ "learning_rate": 2.4810292119386675e-05,
1255
+ "loss": 0.0186,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.772093023255814,
1260
+ "grad_norm": 0.33184051513671875,
1261
+ "learning_rate": 2.4539302518191802e-05,
1262
+ "loss": 0.0177,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.7875968992248064,
1267
+ "grad_norm": 0.2414429783821106,
1268
+ "learning_rate": 2.426836705653782e-05,
1269
+ "loss": 0.0198,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8031007751937986,
1274
+ "grad_norm": 0.11880580335855484,
1275
+ "learning_rate": 2.3997517573803187e-05,
1276
+ "loss": 0.0188,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.818604651162791,
1281
+ "grad_norm": 0.05161415413022041,
1282
+ "learning_rate": 2.3726785899262493e-05,
1283
+ "loss": 0.0131,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.834108527131783,
1288
+ "grad_norm": 0.09770730137825012,
1289
+ "learning_rate": 2.34562038483459e-05,
1290
+ "loss": 0.0129,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.8496124031007755,
1295
+ "grad_norm": 0.27657774090766907,
1296
+ "learning_rate": 2.318580321890032e-05,
1297
+ "loss": 0.0242,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.8651162790697673,
1302
+ "grad_norm": 0.1245102509856224,
1303
+ "learning_rate": 2.2915615787452666e-05,
1304
+ "loss": 0.0182,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.8806201550387596,
1309
+ "grad_norm": 0.095403291285038,
1310
+ "learning_rate": 2.264567330547557e-05,
1311
+ "loss": 0.0229,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.896124031007752,
1316
+ "grad_norm": 0.09689685702323914,
1317
+ "learning_rate": 2.2376007495656084e-05,
1318
+ "loss": 0.02,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.911627906976744,
1323
+ "grad_norm": 0.07814809679985046,
1324
+ "learning_rate": 2.2106650048167697e-05,
1325
+ "loss": 0.0296,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.9271317829457364,
1330
+ "grad_norm": 0.18573637306690216,
1331
+ "learning_rate": 2.1837632616946266e-05,
1332
+ "loss": 0.0191,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.9426356589147287,
1337
+ "grad_norm": 0.16544780135154724,
1338
+ "learning_rate": 2.1568986815970126e-05,
1339
+ "loss": 0.0262,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.958139534883721,
1344
+ "grad_norm": 0.06749454140663147,
1345
+ "learning_rate": 2.1300744215544967e-05,
1346
+ "loss": 0.0178,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.973643410852713,
1351
+ "grad_norm": 0.1645621359348297,
1352
+ "learning_rate": 2.1032936338593718e-05,
1353
+ "loss": 0.017,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.9891472868217055,
1358
+ "grad_norm": 0.14035086333751678,
1359
+ "learning_rate": 2.0765594656952198e-05,
1360
+ "loss": 0.0269,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 3.0031007751937984,
1365
+ "grad_norm": 0.07817042618989944,
1366
+ "learning_rate": 2.0498750587670572e-05,
1367
+ "loss": 0.0183,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 3.0186046511627906,
1372
+ "grad_norm": 0.0851919949054718,
1373
+ "learning_rate": 2.0232435489321354e-05,
1374
+ "loss": 0.0115,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 3.034108527131783,
1379
+ "grad_norm": 0.07319127768278122,
1380
+ "learning_rate": 1.9966680658314273e-05,
1381
+ "loss": 0.0186,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 3.049612403100775,
1386
+ "grad_norm": 0.05918855220079422,
1387
+ "learning_rate": 1.970151732521842e-05,
1388
+ "loss": 0.0137,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 3.0651162790697675,
1393
+ "grad_norm": 0.09402059018611908,
1394
+ "learning_rate": 1.9436976651092144e-05,
1395
+ "loss": 0.0216,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 3.0806201550387597,
1400
+ "grad_norm": 0.15518927574157715,
1401
+ "learning_rate": 1.917308972382109e-05,
1402
+ "loss": 0.0164,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 3.096124031007752,
1407
+ "grad_norm": 0.17928968369960785,
1408
+ "learning_rate": 1.89098875544649e-05,
1409
+ "loss": 0.0153,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 3.1116279069767443,
1414
+ "grad_norm": 0.20205701887607574,
1415
+ "learning_rate": 1.8647401073612892e-05,
1416
+ "loss": 0.0143,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 3.1271317829457366,
1421
+ "grad_norm": 0.023780664429068565,
1422
+ "learning_rate": 1.8385661127749166e-05,
1423
+ "loss": 0.0138,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 3.142635658914729,
1428
+ "grad_norm": 0.16407065093517303,
1429
+ "learning_rate": 1.8124698475627696e-05,
1430
+ "loss": 0.0164,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 3.158139534883721,
1435
+ "grad_norm": 0.05904044210910797,
1436
+ "learning_rate": 1.7864543784657643e-05,
1437
+ "loss": 0.0127,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 3.173643410852713,
1442
+ "grad_norm": 0.07115277647972107,
1443
+ "learning_rate": 1.7605227627299413e-05,
1444
+ "loss": 0.0127,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 3.1891472868217052,
1449
+ "grad_norm": 0.3148862421512604,
1450
+ "learning_rate": 1.73467804774719e-05,
1451
+ "loss": 0.0174,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 3.2046511627906975,
1456
+ "grad_norm": 0.1581067591905594,
1457
+ "learning_rate": 1.7089232706971313e-05,
1458
+ "loss": 0.0148,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 3.22015503875969,
1463
+ "grad_norm": 0.17511816322803497,
1464
+ "learning_rate": 1.6832614581901986e-05,
1465
+ "loss": 0.0193,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 3.235658914728682,
1470
+ "grad_norm": 0.07704796642065048,
1471
+ "learning_rate": 1.6576956259119576e-05,
1472
+ "loss": 0.0114,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 3.2511627906976743,
1477
+ "grad_norm": 0.08784597367048264,
1478
+ "learning_rate": 1.6322287782687197e-05,
1479
+ "loss": 0.0116,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 3.2666666666666666,
1484
+ "grad_norm": 0.0565035343170166,
1485
+ "learning_rate": 1.6068639080344708e-05,
1486
+ "loss": 0.0159,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 3.282170542635659,
1491
+ "grad_norm": 0.15565626323223114,
1492
+ "learning_rate": 1.5816039959991712e-05,
1493
+ "loss": 0.015,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 3.297674418604651,
1498
+ "grad_norm": 0.06181817501783371,
1499
+ "learning_rate": 1.5564520106184644e-05,
1500
+ "loss": 0.0169,
1501
+ "step": 1065
1502
+ },
1503
+ {
1504
+ "epoch": 3.3131782945736434,
1505
+ "grad_norm": 0.15954700112342834,
1506
+ "learning_rate": 1.531410907664834e-05,
1507
+ "loss": 0.0147,
1508
+ "step": 1070
1509
+ },
1510
+ {
1511
+ "epoch": 3.3286821705426357,
1512
+ "grad_norm": 0.0700472965836525,
1513
+ "learning_rate": 1.5064836298802551e-05,
1514
+ "loss": 0.0156,
1515
+ "step": 1075
1516
+ },
1517
+ {
1518
+ "epoch": 3.344186046511628,
1519
+ "grad_norm": 0.028587840497493744,
1520
+ "learning_rate": 1.4816731066303686e-05,
1521
+ "loss": 0.0116,
1522
+ "step": 1080
1523
+ },
1524
+ {
1525
+ "epoch": 3.3596899224806203,
1526
+ "grad_norm": 0.11734448373317719,
1527
+ "learning_rate": 1.456982253560235e-05,
1528
+ "loss": 0.0179,
1529
+ "step": 1085
1530
+ },
1531
+ {
1532
+ "epoch": 3.3751937984496125,
1533
+ "grad_norm": 0.046429798007011414,
1534
+ "learning_rate": 1.4324139722516982e-05,
1535
+ "loss": 0.011,
1536
+ "step": 1090
1537
+ },
1538
+ {
1539
+ "epoch": 3.390697674418605,
1540
+ "grad_norm": 0.18383632600307465,
1541
+ "learning_rate": 1.4079711498824027e-05,
1542
+ "loss": 0.0125,
1543
+ "step": 1095
1544
+ },
1545
+ {
1546
+ "epoch": 3.406201550387597,
1547
+ "grad_norm": 0.3278388977050781,
1548
+ "learning_rate": 1.3836566588864999e-05,
1549
+ "loss": 0.0157,
1550
+ "step": 1100
1551
+ },
1552
+ {
1553
+ "epoch": 3.4217054263565894,
1554
+ "grad_norm": 0.18710392713546753,
1555
+ "learning_rate": 1.3594733566170926e-05,
1556
+ "loss": 0.0148,
1557
+ "step": 1105
1558
+ },
1559
+ {
1560
+ "epoch": 3.4372093023255816,
1561
+ "grad_norm": 0.04076448082923889,
1562
+ "learning_rate": 1.3354240850104476e-05,
1563
+ "loss": 0.0077,
1564
+ "step": 1110
1565
+ },
1566
+ {
1567
+ "epoch": 3.4527131782945735,
1568
+ "grad_norm": 0.06835182756185532,
1569
+ "learning_rate": 1.3115116702520219e-05,
1570
+ "loss": 0.0172,
1571
+ "step": 1115
1572
+ },
1573
+ {
1574
+ "epoch": 3.4682170542635657,
1575
+ "grad_norm": 0.07915415614843369,
1576
+ "learning_rate": 1.2877389224443365e-05,
1577
+ "loss": 0.0091,
1578
+ "step": 1120
1579
+ },
1580
+ {
1581
+ "epoch": 3.483720930232558,
1582
+ "grad_norm": 0.04475206881761551,
1583
+ "learning_rate": 1.2641086352767506e-05,
1584
+ "loss": 0.015,
1585
+ "step": 1125
1586
+ },
1587
+ {
1588
+ "epoch": 3.4992248062015503,
1589
+ "grad_norm": 0.025727396830916405,
1590
+ "learning_rate": 1.2406235856971487e-05,
1591
+ "loss": 0.0117,
1592
+ "step": 1130
1593
+ },
1594
+ {
1595
+ "epoch": 3.5147286821705426,
1596
+ "grad_norm": 0.3452167510986328,
1597
+ "learning_rate": 1.2172865335856066e-05,
1598
+ "loss": 0.0115,
1599
+ "step": 1135
1600
+ },
1601
+ {
1602
+ "epoch": 3.530232558139535,
1603
+ "grad_norm": 0.2533954977989197,
1604
+ "learning_rate": 1.1941002214300606e-05,
1605
+ "loss": 0.0174,
1606
+ "step": 1140
1607
+ },
1608
+ {
1609
+ "epoch": 3.545736434108527,
1610
+ "grad_norm": 0.11330398172140121,
1611
+ "learning_rate": 1.1710673740040232e-05,
1612
+ "loss": 0.0119,
1613
+ "step": 1145
1614
+ },
1615
+ {
1616
+ "epoch": 3.5612403100775194,
1617
+ "grad_norm": 0.07775407284498215,
1618
+ "learning_rate": 1.1481906980463709e-05,
1619
+ "loss": 0.0093,
1620
+ "step": 1150
1621
+ },
1622
+ {
1623
+ "epoch": 3.5767441860465117,
1624
+ "grad_norm": 0.14502529799938202,
1625
+ "learning_rate": 1.1254728819432595e-05,
1626
+ "loss": 0.0137,
1627
+ "step": 1155
1628
+ },
1629
+ {
1630
+ "epoch": 3.592248062015504,
1631
+ "grad_norm": 0.05564185976982117,
1632
+ "learning_rate": 1.1029165954121983e-05,
1633
+ "loss": 0.0116,
1634
+ "step": 1160
1635
+ },
1636
+ {
1637
+ "epoch": 3.6077519379844962,
1638
+ "grad_norm": 0.07241734862327576,
1639
+ "learning_rate": 1.0805244891883113e-05,
1640
+ "loss": 0.0095,
1641
+ "step": 1165
1642
+ },
1643
+ {
1644
+ "epoch": 3.6232558139534885,
1645
+ "grad_norm": 0.05909044295549393,
1646
+ "learning_rate": 1.0582991947128324e-05,
1647
+ "loss": 0.0088,
1648
+ "step": 1170
1649
+ },
1650
+ {
1651
+ "epoch": 3.6387596899224808,
1652
+ "grad_norm": 0.12203407287597656,
1653
+ "learning_rate": 1.036243323823868e-05,
1654
+ "loss": 0.0157,
1655
+ "step": 1175
1656
+ },
1657
+ {
1658
+ "epoch": 3.6542635658914726,
1659
+ "grad_norm": 0.15194092690944672,
1660
+ "learning_rate": 1.0143594684494634e-05,
1661
+ "loss": 0.0116,
1662
+ "step": 1180
1663
+ },
1664
+ {
1665
+ "epoch": 3.669767441860465,
1666
+ "grad_norm": 0.06669194251298904,
1667
+ "learning_rate": 9.926502003030075e-06,
1668
+ "loss": 0.0136,
1669
+ "step": 1185
1670
+ },
1671
+ {
1672
+ "epoch": 3.685271317829457,
1673
+ "grad_norm": 0.07091967761516571,
1674
+ "learning_rate": 9.711180705810156e-06,
1675
+ "loss": 0.0164,
1676
+ "step": 1190
1677
+ },
1678
+ {
1679
+ "epoch": 3.7007751937984494,
1680
+ "grad_norm": 0.0350261889398098,
1681
+ "learning_rate": 9.4976560966332e-06,
1682
+ "loss": 0.0128,
1683
+ "step": 1195
1684
+ },
1685
+ {
1686
+ "epoch": 3.7162790697674417,
1687
+ "grad_norm": 0.09878349304199219,
1688
+ "learning_rate": 9.285953268157116e-06,
1689
+ "loss": 0.0127,
1690
+ "step": 1200
1691
+ },
1692
+ {
1693
+ "epoch": 3.731782945736434,
1694
+ "grad_norm": 0.1007269099354744,
1695
+ "learning_rate": 9.076097098950543e-06,
1696
+ "loss": 0.0087,
1697
+ "step": 1205
1698
+ },
1699
+ {
1700
+ "epoch": 3.7472868217054263,
1701
+ "grad_norm": 0.07725387811660767,
1702
+ "learning_rate": 8.868112250569288e-06,
1703
+ "loss": 0.014,
1704
+ "step": 1210
1705
+ },
1706
+ {
1707
+ "epoch": 3.7627906976744185,
1708
+ "grad_norm": 0.07512272149324417,
1709
+ "learning_rate": 8.662023164658125e-06,
1710
+ "loss": 0.0121,
1711
+ "step": 1215
1712
+ },
1713
+ {
1714
+ "epoch": 3.778294573643411,
1715
+ "grad_norm": 0.05582176521420479,
1716
+ "learning_rate": 8.45785406007852e-06,
1717
+ "loss": 0.0153,
1718
+ "step": 1220
1719
+ },
1720
+ {
1721
+ "epoch": 3.793798449612403,
1722
+ "grad_norm": 0.1534244567155838,
1723
+ "learning_rate": 8.2556289300625e-06,
1724
+ "loss": 0.0151,
1725
+ "step": 1225
1726
+ },
1727
+ {
1728
+ "epoch": 3.8093023255813954,
1729
+ "grad_norm": 0.042408719658851624,
1730
+ "learning_rate": 8.055371539393081e-06,
1731
+ "loss": 0.0108,
1732
+ "step": 1230
1733
+ },
1734
+ {
1735
+ "epoch": 3.8248062015503876,
1736
+ "grad_norm": 0.062217891216278076,
1737
+ "learning_rate": 7.857105421611515e-06,
1738
+ "loss": 0.0136,
1739
+ "step": 1235
1740
+ },
1741
+ {
1742
+ "epoch": 3.84031007751938,
1743
+ "grad_norm": 0.09418876469135284,
1744
+ "learning_rate": 7.660853876251684e-06,
1745
+ "loss": 0.0116,
1746
+ "step": 1240
1747
+ },
1748
+ {
1749
+ "epoch": 3.855813953488372,
1750
+ "grad_norm": 0.06122265383601189,
1751
+ "learning_rate": 7.4666399661020126e-06,
1752
+ "loss": 0.0103,
1753
+ "step": 1245
1754
+ },
1755
+ {
1756
+ "epoch": 3.8713178294573645,
1757
+ "grad_norm": 0.06508161127567291,
1758
+ "learning_rate": 7.274486514495268e-06,
1759
+ "loss": 0.0094,
1760
+ "step": 1250
1761
+ },
1762
+ {
1763
+ "epoch": 3.8868217054263567,
1764
+ "grad_norm": 0.122026726603508,
1765
+ "learning_rate": 7.08441610262639e-06,
1766
+ "loss": 0.0105,
1767
+ "step": 1255
1768
+ },
1769
+ {
1770
+ "epoch": 3.902325581395349,
1771
+ "grad_norm": 0.09518284350633621,
1772
+ "learning_rate": 6.896451066898846e-06,
1773
+ "loss": 0.0105,
1774
+ "step": 1260
1775
+ },
1776
+ {
1777
+ "epoch": 3.9178294573643413,
1778
+ "grad_norm": 0.3977924883365631,
1779
+ "learning_rate": 6.710613496299739e-06,
1780
+ "loss": 0.0171,
1781
+ "step": 1265
1782
+ },
1783
+ {
1784
+ "epoch": 3.9333333333333336,
1785
+ "grad_norm": 0.2375529408454895,
1786
+ "learning_rate": 6.526925229803982e-06,
1787
+ "loss": 0.0155,
1788
+ "step": 1270
1789
+ },
1790
+ {
1791
+ "epoch": 3.948837209302326,
1792
+ "grad_norm": 0.15753792226314545,
1793
+ "learning_rate": 6.3454078538078635e-06,
1794
+ "loss": 0.0101,
1795
+ "step": 1275
1796
+ },
1797
+ {
1798
+ "epoch": 3.9643410852713177,
1799
+ "grad_norm": 0.13304033875465393,
1800
+ "learning_rate": 6.166082699592288e-06,
1801
+ "loss": 0.0137,
1802
+ "step": 1280
1803
+ },
1804
+ {
1805
+ "epoch": 3.97984496124031,
1806
+ "grad_norm": 0.11497492343187332,
1807
+ "learning_rate": 5.988970840815994e-06,
1808
+ "loss": 0.0129,
1809
+ "step": 1285
1810
+ },
1811
+ {
1812
+ "epoch": 3.9953488372093022,
1813
+ "grad_norm": 0.052612703293561935,
1814
+ "learning_rate": 5.8140930910390715e-06,
1815
+ "loss": 0.0132,
1816
+ "step": 1290
1817
+ },
1818
+ {
1819
+ "epoch": 4.0093023255813955,
1820
+ "grad_norm": 0.0735371857881546,
1821
+ "learning_rate": 5.64147000127698e-06,
1822
+ "loss": 0.0111,
1823
+ "step": 1295
1824
+ },
1825
+ {
1826
+ "epoch": 4.024806201550388,
1827
+ "grad_norm": 0.08621438592672348,
1828
+ "learning_rate": 5.471121857585543e-06,
1829
+ "loss": 0.01,
1830
+ "step": 1300
1831
+ },
1832
+ {
1833
+ "epoch": 4.04031007751938,
1834
+ "grad_norm": 0.03453483060002327,
1835
+ "learning_rate": 5.30306867867692e-06,
1836
+ "loss": 0.0067,
1837
+ "step": 1305
1838
+ },
1839
+ {
1840
+ "epoch": 4.055813953488372,
1841
+ "grad_norm": 0.02685674838721752,
1842
+ "learning_rate": 5.13733021356714e-06,
1843
+ "loss": 0.0087,
1844
+ "step": 1310
1845
+ },
1846
+ {
1847
+ "epoch": 4.071317829457365,
1848
+ "grad_norm": 0.05555293336510658,
1849
+ "learning_rate": 4.973925939255209e-06,
1850
+ "loss": 0.0067,
1851
+ "step": 1315
1852
+ },
1853
+ {
1854
+ "epoch": 4.086821705426357,
1855
+ "grad_norm": 0.058123618364334106,
1856
+ "learning_rate": 4.812875058434315e-06,
1857
+ "loss": 0.0102,
1858
+ "step": 1320
1859
+ },
1860
+ {
1861
+ "epoch": 4.102325581395349,
1862
+ "grad_norm": 0.026801196858286858,
1863
+ "learning_rate": 4.654196497235139e-06,
1864
+ "loss": 0.0071,
1865
+ "step": 1325
1866
+ },
1867
+ {
1868
+ "epoch": 4.1178294573643415,
1869
+ "grad_norm": 0.053194936364889145,
1870
+ "learning_rate": 4.4979089030017216e-06,
1871
+ "loss": 0.0086,
1872
+ "step": 1330
1873
+ },
1874
+ {
1875
+ "epoch": 4.133333333333334,
1876
+ "grad_norm": 0.11018364131450653,
1877
+ "learning_rate": 4.344030642100133e-06,
1878
+ "loss": 0.011,
1879
+ "step": 1335
1880
+ },
1881
+ {
1882
+ "epoch": 4.148837209302325,
1883
+ "grad_norm": 0.05405386909842491,
1884
+ "learning_rate": 4.192579797760085e-06,
1885
+ "loss": 0.0102,
1886
+ "step": 1340
1887
+ },
1888
+ {
1889
+ "epoch": 4.164341085271317,
1890
+ "grad_norm": 0.05461077392101288,
1891
+ "learning_rate": 4.043574167949893e-06,
1892
+ "loss": 0.0104,
1893
+ "step": 1345
1894
+ },
1895
+ {
1896
+ "epoch": 4.17984496124031,
1897
+ "grad_norm": 0.0669790729880333,
1898
+ "learning_rate": 3.897031263284867e-06,
1899
+ "loss": 0.0075,
1900
+ "step": 1350
1901
+ },
1902
+ {
1903
+ "epoch": 4.195348837209302,
1904
+ "grad_norm": 0.04254228249192238,
1905
+ "learning_rate": 3.752968304969576e-06,
1906
+ "loss": 0.0079,
1907
+ "step": 1355
1908
+ },
1909
+ {
1910
+ "epoch": 4.210852713178294,
1911
+ "grad_norm": 0.06297585368156433,
1912
+ "learning_rate": 3.6114022227740433e-06,
1913
+ "loss": 0.0109,
1914
+ "step": 1360
1915
+ },
1916
+ {
1917
+ "epoch": 4.2263565891472865,
1918
+ "grad_norm": 0.07878061383962631,
1919
+ "learning_rate": 3.4723496530442352e-06,
1920
+ "loss": 0.0092,
1921
+ "step": 1365
1922
+ },
1923
+ {
1924
+ "epoch": 4.241860465116279,
1925
+ "grad_norm": 0.11867242306470871,
1926
+ "learning_rate": 3.335826936747011e-06,
1927
+ "loss": 0.0092,
1928
+ "step": 1370
1929
+ },
1930
+ {
1931
+ "epoch": 4.257364341085271,
1932
+ "grad_norm": 0.10879813879728317,
1933
+ "learning_rate": 3.201850117549787e-06,
1934
+ "loss": 0.009,
1935
+ "step": 1375
1936
+ },
1937
+ {
1938
+ "epoch": 4.272868217054263,
1939
+ "grad_norm": 0.05206475034356117,
1940
+ "learning_rate": 3.0704349399351435e-06,
1941
+ "loss": 0.0099,
1942
+ "step": 1380
1943
+ },
1944
+ {
1945
+ "epoch": 4.288372093023256,
1946
+ "grad_norm": 0.06414878368377686,
1947
+ "learning_rate": 2.941596847350597e-06,
1948
+ "loss": 0.0076,
1949
+ "step": 1385
1950
+ },
1951
+ {
1952
+ "epoch": 4.303875968992248,
1953
+ "grad_norm": 0.09740181267261505,
1954
+ "learning_rate": 2.8153509803937274e-06,
1955
+ "loss": 0.0081,
1956
+ "step": 1390
1957
+ },
1958
+ {
1959
+ "epoch": 4.31937984496124,
1960
+ "grad_norm": 0.055816520005464554,
1961
+ "learning_rate": 2.691712175032912e-06,
1962
+ "loss": 0.0085,
1963
+ "step": 1395
1964
+ },
1965
+ {
1966
+ "epoch": 4.334883720930232,
1967
+ "grad_norm": 0.08039291948080063,
1968
+ "learning_rate": 2.5706949608638704e-06,
1969
+ "loss": 0.0096,
1970
+ "step": 1400
1971
+ },
1972
+ {
1973
+ "epoch": 4.350387596899225,
1974
+ "grad_norm": 0.06461725383996964,
1975
+ "learning_rate": 2.4523135594021585e-06,
1976
+ "loss": 0.0082,
1977
+ "step": 1405
1978
+ },
1979
+ {
1980
+ "epoch": 4.365891472868217,
1981
+ "grad_norm": 0.03589886054396629,
1982
+ "learning_rate": 2.336581882411967e-06,
1983
+ "loss": 0.0064,
1984
+ "step": 1410
1985
+ },
1986
+ {
1987
+ "epoch": 4.381395348837209,
1988
+ "grad_norm": 0.0716664046049118,
1989
+ "learning_rate": 2.2235135302712095e-06,
1990
+ "loss": 0.0093,
1991
+ "step": 1415
1992
+ },
1993
+ {
1994
+ "epoch": 4.3968992248062015,
1995
+ "grad_norm": 0.07864725589752197,
1996
+ "learning_rate": 2.113121790373257e-06,
1997
+ "loss": 0.0091,
1998
+ "step": 1420
1999
+ },
2000
+ {
2001
+ "epoch": 4.412403100775194,
2002
+ "grad_norm": 0.0717134103178978,
2003
+ "learning_rate": 2.005419635565481e-06,
2004
+ "loss": 0.0081,
2005
+ "step": 1425
2006
+ },
2007
+ {
2008
+ "epoch": 4.427906976744186,
2009
+ "grad_norm": 0.11225301772356033,
2010
+ "learning_rate": 1.900419722624705e-06,
2011
+ "loss": 0.0085,
2012
+ "step": 1430
2013
+ },
2014
+ {
2015
+ "epoch": 4.443410852713178,
2016
+ "grad_norm": 0.06452286243438721,
2017
+ "learning_rate": 1.7981343907698484e-06,
2018
+ "loss": 0.0102,
2019
+ "step": 1435
2020
+ },
2021
+ {
2022
+ "epoch": 4.458914728682171,
2023
+ "grad_norm": 0.08178742229938507,
2024
+ "learning_rate": 1.6985756602118236e-06,
2025
+ "loss": 0.0096,
2026
+ "step": 1440
2027
+ },
2028
+ {
2029
+ "epoch": 4.474418604651163,
2030
+ "grad_norm": 0.055801451206207275,
2031
+ "learning_rate": 1.6017552307410033e-06,
2032
+ "loss": 0.0073,
2033
+ "step": 1445
2034
+ },
2035
+ {
2036
+ "epoch": 4.489922480620155,
2037
+ "grad_norm": 0.11048652976751328,
2038
+ "learning_rate": 1.5076844803522922e-06,
2039
+ "loss": 0.0095,
2040
+ "step": 1450
2041
+ },
2042
+ {
2043
+ "epoch": 4.5054263565891475,
2044
+ "grad_norm": 0.06384676694869995,
2045
+ "learning_rate": 1.4163744639080101e-06,
2046
+ "loss": 0.0077,
2047
+ "step": 1455
2048
+ },
2049
+ {
2050
+ "epoch": 4.52093023255814,
2051
+ "grad_norm": 0.05776697397232056,
2052
+ "learning_rate": 1.3278359118387845e-06,
2053
+ "loss": 0.0095,
2054
+ "step": 1460
2055
+ },
2056
+ {
2057
+ "epoch": 4.536434108527132,
2058
+ "grad_norm": 0.055965911597013474,
2059
+ "learning_rate": 1.2420792288825312e-06,
2060
+ "loss": 0.0108,
2061
+ "step": 1465
2062
+ },
2063
+ {
2064
+ "epoch": 4.551937984496124,
2065
+ "grad_norm": 0.06405636668205261,
2066
+ "learning_rate": 1.1591144928617375e-06,
2067
+ "loss": 0.0074,
2068
+ "step": 1470
2069
+ },
2070
+ {
2071
+ "epoch": 4.567441860465117,
2072
+ "grad_norm": 0.03841257467865944,
2073
+ "learning_rate": 1.0789514534991497e-06,
2074
+ "loss": 0.0073,
2075
+ "step": 1475
2076
+ },
2077
+ {
2078
+ "epoch": 4.582945736434109,
2079
+ "grad_norm": 0.0615706592798233,
2080
+ "learning_rate": 1.0015995312720127e-06,
2081
+ "loss": 0.0066,
2082
+ "step": 1480
2083
+ },
2084
+ {
2085
+ "epoch": 4.598449612403101,
2086
+ "grad_norm": 0.037747208029031754,
2087
+ "learning_rate": 9.270678163050217e-07,
2088
+ "loss": 0.0082,
2089
+ "step": 1485
2090
+ },
2091
+ {
2092
+ "epoch": 4.613953488372093,
2093
+ "grad_norm": 0.04813956841826439,
2094
+ "learning_rate": 8.553650673020608e-07,
2095
+ "loss": 0.0089,
2096
+ "step": 1490
2097
+ },
2098
+ {
2099
+ "epoch": 4.629457364341086,
2100
+ "grad_norm": 0.06449221074581146,
2101
+ "learning_rate": 7.864997105169497e-07,
2102
+ "loss": 0.0074,
2103
+ "step": 1495
2104
+ },
2105
+ {
2106
+ "epoch": 4.644961240310078,
2107
+ "grad_norm": 0.1142016053199768,
2108
+ "learning_rate": 7.204798387631773e-07,
2109
+ "loss": 0.009,
2110
+ "step": 1500
2111
+ }
2112
+ ],
2113
+ "logging_steps": 5,
2114
+ "max_steps": 1610,
2115
+ "num_input_tokens_seen": 0,
2116
+ "num_train_epochs": 5,
2117
+ "save_steps": 500,
2118
+ "stateful_callbacks": {
2119
+ "TrainerControl": {
2120
+ "args": {
2121
+ "should_epoch_stop": false,
2122
+ "should_evaluate": false,
2123
+ "should_log": false,
2124
+ "should_save": true,
2125
+ "should_training_stop": false
2126
+ },
2127
+ "attributes": {}
2128
+ }
2129
+ },
2130
+ "total_flos": 2.531573029699584e+16,
2131
+ "train_batch_size": 2,
2132
+ "trial_name": null,
2133
+ "trial_params": null
2134
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc429601d1d23ce75bcf84e7e4ed5fc0ae418d073e5933d8bb8717ac0faf730
3
+ size 5688
checkpoint-1610/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-1B-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 0.15.2
checkpoint-1610/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "k_proj",
31
+ "up_proj",
32
+ "down_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-1610/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef1c63beed69b42dc1dd6c20a47e30f47118e4d534fb1e93ba1ba7fb89daa41
3
+ size 180385008
checkpoint-1610/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab2da32633a7613cf4ba994267ce1db3ba1cc6804d95bd0349c6a4e6db63fa8
3
+ size 360899194
checkpoint-1610/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
3
+ size 14244
checkpoint-1610/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9e3e37a36a4dc60de774807b2074b816981368511fe16bbf5c80dfbfb4a3026
3
+ size 988
checkpoint-1610/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa84fdb6a391eba451b6140040529ccc03f0cb6689d7c0409c8fea703be0a634
3
+ size 1064
checkpoint-1610/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
checkpoint-1610/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-1610/tokenizer_config.json ADDED
@@ -0,0 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|eom_id|>"
2054
+ ],
2055
+ "bos_token": "<|begin_of_text|>",
2056
+ "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",
2057
+ "clean_up_tokenization_spaces": true,
2058
+ "eos_token": "<|eot_id|>",
2059
+ "extra_special_tokens": {},
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 131072,
2065
+ "pad_token": "<|eot_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizer"
2069
+ }
checkpoint-1610/trainer_state.json ADDED
@@ -0,0 +1,2288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.986046511627907,
6
+ "eval_steps": 500,
7
+ "global_step": 1610,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015503875968992248,
14
+ "grad_norm": 2.5634377002716064,
15
+ "learning_rate": 1.2422360248447205e-06,
16
+ "loss": 2.2423,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.031007751937984496,
21
+ "grad_norm": 1.774464726448059,
22
+ "learning_rate": 2.7950310559006214e-06,
23
+ "loss": 2.0959,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.046511627906976744,
28
+ "grad_norm": 2.2086267471313477,
29
+ "learning_rate": 4.347826086956522e-06,
30
+ "loss": 1.7507,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06201550387596899,
35
+ "grad_norm": 1.5988163948059082,
36
+ "learning_rate": 5.900621118012423e-06,
37
+ "loss": 1.4298,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07751937984496124,
42
+ "grad_norm": 1.3644428253173828,
43
+ "learning_rate": 7.453416149068324e-06,
44
+ "loss": 0.9425,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09302325581395349,
49
+ "grad_norm": 1.1469796895980835,
50
+ "learning_rate": 9.006211180124225e-06,
51
+ "loss": 0.6502,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.10852713178294573,
56
+ "grad_norm": 1.8373690843582153,
57
+ "learning_rate": 1.0559006211180125e-05,
58
+ "loss": 0.6724,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12403100775193798,
63
+ "grad_norm": 1.116761565208435,
64
+ "learning_rate": 1.2111801242236026e-05,
65
+ "loss": 0.4023,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.13953488372093023,
70
+ "grad_norm": 0.7392648458480835,
71
+ "learning_rate": 1.3664596273291926e-05,
72
+ "loss": 0.3874,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15503875968992248,
77
+ "grad_norm": 0.9391402006149292,
78
+ "learning_rate": 1.5217391304347828e-05,
79
+ "loss": 0.3164,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17054263565891473,
84
+ "grad_norm": 0.9636594653129578,
85
+ "learning_rate": 1.6770186335403728e-05,
86
+ "loss": 0.1785,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.18604651162790697,
91
+ "grad_norm": 0.6391934156417847,
92
+ "learning_rate": 1.8322981366459628e-05,
93
+ "loss": 0.1778,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20155038759689922,
98
+ "grad_norm": 0.5561841726303101,
99
+ "learning_rate": 1.9875776397515528e-05,
100
+ "loss": 0.2703,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.21705426356589147,
105
+ "grad_norm": 0.49807441234588623,
106
+ "learning_rate": 2.1428571428571428e-05,
107
+ "loss": 0.1875,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.23255813953488372,
112
+ "grad_norm": 1.2350372076034546,
113
+ "learning_rate": 2.2981366459627328e-05,
114
+ "loss": 0.3248,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.24806201550387597,
119
+ "grad_norm": 0.6338334083557129,
120
+ "learning_rate": 2.453416149068323e-05,
121
+ "loss": 0.1297,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.26356589147286824,
126
+ "grad_norm": 0.6853603720664978,
127
+ "learning_rate": 2.608695652173913e-05,
128
+ "loss": 0.1357,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.27906976744186046,
133
+ "grad_norm": 1.0921283960342407,
134
+ "learning_rate": 2.7639751552795035e-05,
135
+ "loss": 0.1418,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.29457364341085274,
140
+ "grad_norm": 0.7996405363082886,
141
+ "learning_rate": 2.919254658385093e-05,
142
+ "loss": 0.1293,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.31007751937984496,
147
+ "grad_norm": 0.4951094388961792,
148
+ "learning_rate": 3.074534161490684e-05,
149
+ "loss": 0.1783,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.32558139534883723,
154
+ "grad_norm": 0.3423459231853485,
155
+ "learning_rate": 3.2298136645962735e-05,
156
+ "loss": 0.0996,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.34108527131782945,
161
+ "grad_norm": 0.6147115230560303,
162
+ "learning_rate": 3.385093167701863e-05,
163
+ "loss": 0.1909,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.35658914728682173,
168
+ "grad_norm": 0.6499375104904175,
169
+ "learning_rate": 3.5403726708074535e-05,
170
+ "loss": 0.1572,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.37209302325581395,
175
+ "grad_norm": 0.274794340133667,
176
+ "learning_rate": 3.695652173913043e-05,
177
+ "loss": 0.1313,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.3875968992248062,
182
+ "grad_norm": 0.44879093766212463,
183
+ "learning_rate": 3.8509316770186335e-05,
184
+ "loss": 0.1141,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.40310077519379844,
189
+ "grad_norm": 0.3992724120616913,
190
+ "learning_rate": 4.006211180124224e-05,
191
+ "loss": 0.1539,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4186046511627907,
196
+ "grad_norm": 0.28350868821144104,
197
+ "learning_rate": 4.161490683229814e-05,
198
+ "loss": 0.0857,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.43410852713178294,
203
+ "grad_norm": 0.5912169814109802,
204
+ "learning_rate": 4.316770186335404e-05,
205
+ "loss": 0.1939,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4496124031007752,
210
+ "grad_norm": 0.35334816575050354,
211
+ "learning_rate": 4.472049689440994e-05,
212
+ "loss": 0.1149,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.46511627906976744,
217
+ "grad_norm": 0.7359523177146912,
218
+ "learning_rate": 4.627329192546584e-05,
219
+ "loss": 0.1193,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.4806201550387597,
224
+ "grad_norm": 0.43439972400665283,
225
+ "learning_rate": 4.782608695652174e-05,
226
+ "loss": 0.1049,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.49612403100775193,
231
+ "grad_norm": 0.4149303734302521,
232
+ "learning_rate": 4.937888198757764e-05,
233
+ "loss": 0.1168,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5116279069767442,
238
+ "grad_norm": 0.38137003779411316,
239
+ "learning_rate": 4.999947117257964e-05,
240
+ "loss": 0.122,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5271317829457365,
245
+ "grad_norm": 0.6025403738021851,
246
+ "learning_rate": 4.999623953047522e-05,
247
+ "loss": 0.1107,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5426356589147286,
252
+ "grad_norm": 0.6327984929084778,
253
+ "learning_rate": 4.999007041858851e-05,
254
+ "loss": 0.0855,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5581395348837209,
259
+ "grad_norm": 0.5637001991271973,
260
+ "learning_rate": 4.998096456189175e-05,
261
+ "loss": 0.0993,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5736434108527132,
266
+ "grad_norm": 0.2784324586391449,
267
+ "learning_rate": 4.996892303047306e-05,
268
+ "loss": 0.0716,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5891472868217055,
273
+ "grad_norm": 0.6117509603500366,
274
+ "learning_rate": 4.995394723941068e-05,
275
+ "loss": 0.0693,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6046511627906976,
280
+ "grad_norm": 1.3043673038482666,
281
+ "learning_rate": 4.993603894860669e-05,
282
+ "loss": 0.1016,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6201550387596899,
287
+ "grad_norm": 0.44789212942123413,
288
+ "learning_rate": 4.991520026258015e-05,
289
+ "loss": 0.0891,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6356589147286822,
294
+ "grad_norm": 1.85973060131073,
295
+ "learning_rate": 4.989143363021987e-05,
296
+ "loss": 0.1393,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6511627906976745,
301
+ "grad_norm": 1.2061032056808472,
302
+ "learning_rate": 4.9864741844496506e-05,
303
+ "loss": 0.116,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6666666666666666,
308
+ "grad_norm": 0.3840301036834717,
309
+ "learning_rate": 4.983512804213447e-05,
310
+ "loss": 0.0952,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6821705426356589,
315
+ "grad_norm": 0.4879723787307739,
316
+ "learning_rate": 4.9802595703243205e-05,
317
+ "loss": 0.128,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.6976744186046512,
322
+ "grad_norm": 0.4783574938774109,
323
+ "learning_rate": 4.976714865090827e-05,
324
+ "loss": 0.0783,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7131782945736435,
329
+ "grad_norm": 0.4228968620300293,
330
+ "learning_rate": 4.9728791050742064e-05,
331
+ "loss": 0.1176,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7286821705426356,
336
+ "grad_norm": 0.18757346272468567,
337
+ "learning_rate": 4.9687527410394275e-05,
338
+ "loss": 0.0872,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7441860465116279,
343
+ "grad_norm": 0.4684408903121948,
344
+ "learning_rate": 4.964336257902217e-05,
345
+ "loss": 0.0753,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7596899224806202,
350
+ "grad_norm": 0.7171066403388977,
351
+ "learning_rate": 4.9596301746720734e-05,
352
+ "loss": 0.0988,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7751937984496124,
357
+ "grad_norm": 0.5907664895057678,
358
+ "learning_rate": 4.9546350443912783e-05,
359
+ "loss": 0.1172,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.7906976744186046,
364
+ "grad_norm": 0.8421684503555298,
365
+ "learning_rate": 4.9493514540698963e-05,
366
+ "loss": 0.0771,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8062015503875969,
371
+ "grad_norm": 0.2831384837627411,
372
+ "learning_rate": 4.9437800246168025e-05,
373
+ "loss": 0.1212,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8217054263565892,
378
+ "grad_norm": 0.4991057217121124,
379
+ "learning_rate": 4.937921410766707e-05,
380
+ "loss": 0.0837,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8372093023255814,
385
+ "grad_norm": 0.5720856189727783,
386
+ "learning_rate": 4.931776301003217e-05,
387
+ "loss": 0.1615,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8527131782945736,
392
+ "grad_norm": 0.48435062170028687,
393
+ "learning_rate": 4.9253454174779265e-05,
394
+ "loss": 0.0872,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8682170542635659,
399
+ "grad_norm": 0.2810228765010834,
400
+ "learning_rate": 4.9186295159255537e-05,
401
+ "loss": 0.0886,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8837209302325582,
406
+ "grad_norm": 0.8470152616500854,
407
+ "learning_rate": 4.9116293855751285e-05,
408
+ "loss": 0.1107,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.8992248062015504,
413
+ "grad_norm": 0.26309266686439514,
414
+ "learning_rate": 4.9043458490572444e-05,
415
+ "loss": 0.0861,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9147286821705426,
420
+ "grad_norm": 0.4955242872238159,
421
+ "learning_rate": 4.896779762307389e-05,
422
+ "loss": 0.0548,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9302325581395349,
427
+ "grad_norm": 0.5125411152839661,
428
+ "learning_rate": 4.888932014465352e-05,
429
+ "loss": 0.0456,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9457364341085271,
434
+ "grad_norm": 0.4470186233520508,
435
+ "learning_rate": 4.880803527770742e-05,
436
+ "loss": 0.0909,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9612403100775194,
441
+ "grad_norm": 0.22464849054813385,
442
+ "learning_rate": 4.872395257454605e-05,
443
+ "loss": 0.0722,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9767441860465116,
448
+ "grad_norm": 0.1867540031671524,
449
+ "learning_rate": 4.86370819162717e-05,
450
+ "loss": 0.0497,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.9922480620155039,
455
+ "grad_norm": 0.1916547268629074,
456
+ "learning_rate": 4.8547433511617305e-05,
457
+ "loss": 0.0698,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.006201550387597,
462
+ "grad_norm": 0.1836194545030594,
463
+ "learning_rate": 4.845501789574674e-05,
464
+ "loss": 0.0563,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0217054263565892,
469
+ "grad_norm": 0.4584813416004181,
470
+ "learning_rate": 4.835984592901678e-05,
471
+ "loss": 0.0489,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0372093023255813,
476
+ "grad_norm": 0.06475898623466492,
477
+ "learning_rate": 4.826192879570078e-05,
478
+ "loss": 0.0526,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0527131782945736,
483
+ "grad_norm": 0.1889159232378006,
484
+ "learning_rate": 4.8161278002674424e-05,
485
+ "loss": 0.0363,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0682170542635658,
490
+ "grad_norm": 0.5690692663192749,
491
+ "learning_rate": 4.80579053780634e-05,
492
+ "loss": 0.0791,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.083720930232558,
497
+ "grad_norm": 0.13445481657981873,
498
+ "learning_rate": 4.795182306985343e-05,
499
+ "loss": 0.0595,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.0992248062015504,
504
+ "grad_norm": 0.357576847076416,
505
+ "learning_rate": 4.7843043544462696e-05,
506
+ "loss": 0.0516,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1147286821705427,
511
+ "grad_norm": 0.16702419519424438,
512
+ "learning_rate": 4.773157958527681e-05,
513
+ "loss": 0.0454,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.130232558139535,
518
+ "grad_norm": 0.23175758123397827,
519
+ "learning_rate": 4.7617444291146565e-05,
520
+ "loss": 0.0378,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1457364341085272,
525
+ "grad_norm": 0.28666743636131287,
526
+ "learning_rate": 4.750065107484859e-05,
527
+ "loss": 0.069,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1612403100775195,
532
+ "grad_norm": 0.2496625781059265,
533
+ "learning_rate": 4.738121366150916e-05,
534
+ "loss": 0.0654,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.1767441860465115,
539
+ "grad_norm": 0.20519720017910004,
540
+ "learning_rate": 4.725914608699122e-05,
541
+ "loss": 0.0576,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.1922480620155038,
546
+ "grad_norm": 0.2702353894710541,
547
+ "learning_rate": 4.7134462696245e-05,
548
+ "loss": 0.0387,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.207751937984496,
553
+ "grad_norm": 0.45655345916748047,
554
+ "learning_rate": 4.700717814162218e-05,
555
+ "loss": 0.0628,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.2232558139534884,
560
+ "grad_norm": 0.2866630554199219,
561
+ "learning_rate": 4.6877307381154044e-05,
562
+ "loss": 0.0596,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2387596899224806,
567
+ "grad_norm": 0.17983689904212952,
568
+ "learning_rate": 4.674486567679367e-05,
569
+ "loss": 0.0376,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.254263565891473,
574
+ "grad_norm": 0.09354360401630402,
575
+ "learning_rate": 4.660986859262236e-05,
576
+ "loss": 0.032,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2697674418604652,
581
+ "grad_norm": 0.3007808327674866,
582
+ "learning_rate": 4.647233199302064e-05,
583
+ "loss": 0.0429,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.2852713178294572,
588
+ "grad_norm": 0.5735777616500854,
589
+ "learning_rate": 4.6332272040803895e-05,
590
+ "loss": 0.0498,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3007751937984495,
595
+ "grad_norm": 0.21312487125396729,
596
+ "learning_rate": 4.618970519532303e-05,
597
+ "loss": 0.0398,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3162790697674418,
602
+ "grad_norm": 0.348650723695755,
603
+ "learning_rate": 4.6044648210530175e-05,
604
+ "loss": 0.0429,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.331782945736434,
609
+ "grad_norm": 0.6043110489845276,
610
+ "learning_rate": 4.589711813300983e-05,
611
+ "loss": 0.0664,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3472868217054264,
616
+ "grad_norm": 0.14238876104354858,
617
+ "learning_rate": 4.574713229997563e-05,
618
+ "loss": 0.0478,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3627906976744186,
623
+ "grad_norm": 0.47702425718307495,
624
+ "learning_rate": 4.559470833723292e-05,
625
+ "loss": 0.0528,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.378294573643411,
630
+ "grad_norm": 0.16487376391887665,
631
+ "learning_rate": 4.5439864157107434e-05,
632
+ "loss": 0.0435,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.3937984496124032,
637
+ "grad_norm": 0.0906042605638504,
638
+ "learning_rate": 4.528261795634032e-05,
639
+ "loss": 0.0337,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.4093023255813955,
644
+ "grad_norm": 0.2174687385559082,
645
+ "learning_rate": 4.5122988213949676e-05,
646
+ "loss": 0.0514,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4248062015503877,
651
+ "grad_norm": 0.08279066532850266,
652
+ "learning_rate": 4.496099368905902e-05,
653
+ "loss": 0.0229,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4403100775193798,
658
+ "grad_norm": 0.19147436320781708,
659
+ "learning_rate": 4.4796653418692745e-05,
660
+ "loss": 0.0347,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.455813953488372,
665
+ "grad_norm": 0.15159855782985687,
666
+ "learning_rate": 4.4629986715538976e-05,
667
+ "loss": 0.0295,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.4713178294573643,
672
+ "grad_norm": 0.3000525236129761,
673
+ "learning_rate": 4.4461013165679986e-05,
674
+ "loss": 0.0405,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.4868217054263566,
679
+ "grad_norm": 0.16434980928897858,
680
+ "learning_rate": 4.428975262629055e-05,
681
+ "loss": 0.0341,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5023255813953489,
686
+ "grad_norm": 0.06991487741470337,
687
+ "learning_rate": 4.411622522330435e-05,
688
+ "loss": 0.0404,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.517829457364341,
693
+ "grad_norm": 0.15435563027858734,
694
+ "learning_rate": 4.39404513490489e-05,
695
+ "loss": 0.0539,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5333333333333332,
700
+ "grad_norm": 0.1697537750005722,
701
+ "learning_rate": 4.376245165984903e-05,
702
+ "loss": 0.0555,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5488372093023255,
707
+ "grad_norm": 0.3248571455478668,
708
+ "learning_rate": 4.358224707359955e-05,
709
+ "loss": 0.0403,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5643410852713178,
714
+ "grad_norm": 0.06237597391009331,
715
+ "learning_rate": 4.3399858767306936e-05,
716
+ "loss": 0.0318,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.57984496124031,
721
+ "grad_norm": 0.34228137135505676,
722
+ "learning_rate": 4.321530817460073e-05,
723
+ "loss": 0.0509,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.5953488372093023,
728
+ "grad_norm": 0.45852935314178467,
729
+ "learning_rate": 4.302861698321478e-05,
730
+ "loss": 0.0418,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6108527131782946,
735
+ "grad_norm": 0.14077672362327576,
736
+ "learning_rate": 4.283980713243847e-05,
737
+ "loss": 0.026,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6263565891472869,
742
+ "grad_norm": 0.13448594510555267,
743
+ "learning_rate": 4.264890081053859e-05,
744
+ "loss": 0.0429,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6418604651162791,
749
+ "grad_norm": 0.0402817465364933,
750
+ "learning_rate": 4.245592045215182e-05,
751
+ "loss": 0.0252,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6573643410852714,
756
+ "grad_norm": 0.25280848145484924,
757
+ "learning_rate": 4.226088873564825e-05,
758
+ "loss": 0.0353,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.6728682170542637,
763
+ "grad_norm": 0.12823021411895752,
764
+ "learning_rate": 4.206382858046636e-05,
765
+ "loss": 0.038,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.688372093023256,
770
+ "grad_norm": 0.08113641291856766,
771
+ "learning_rate": 4.1864763144419536e-05,
772
+ "loss": 0.035,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.703875968992248,
777
+ "grad_norm": 0.27006813883781433,
778
+ "learning_rate": 4.166371582097476e-05,
779
+ "loss": 0.0439,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7193798449612403,
784
+ "grad_norm": 0.2137015163898468,
785
+ "learning_rate": 4.146071023650335e-05,
786
+ "loss": 0.0552,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7348837209302326,
791
+ "grad_norm": 0.35401883721351624,
792
+ "learning_rate": 4.1255770247504576e-05,
793
+ "loss": 0.0259,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7503875968992249,
798
+ "grad_norm": 0.4056580066680908,
799
+ "learning_rate": 4.10489199378021e-05,
800
+ "loss": 0.0419,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.765891472868217,
805
+ "grad_norm": 0.11533407121896744,
806
+ "learning_rate": 4.0840183615713714e-05,
807
+ "loss": 0.0311,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.7813953488372092,
812
+ "grad_norm": 0.1366463154554367,
813
+ "learning_rate": 4.0629585811194726e-05,
814
+ "loss": 0.0449,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.7968992248062015,
819
+ "grad_norm": 0.2846928536891937,
820
+ "learning_rate": 4.041715127295529e-05,
821
+ "loss": 0.0607,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8124031007751937,
826
+ "grad_norm": 0.2537185847759247,
827
+ "learning_rate": 4.020290496555202e-05,
828
+ "loss": 0.0482,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.827906976744186,
833
+ "grad_norm": 0.11237087100744247,
834
+ "learning_rate": 3.9986872066454226e-05,
835
+ "loss": 0.0374,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8434108527131783,
840
+ "grad_norm": 0.25917041301727295,
841
+ "learning_rate": 3.976907796308519e-05,
842
+ "loss": 0.059,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8589147286821706,
847
+ "grad_norm": 0.16126245260238647,
848
+ "learning_rate": 3.954954824983867e-05,
849
+ "loss": 0.0313,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.8744186046511628,
854
+ "grad_norm": 0.17019878327846527,
855
+ "learning_rate": 3.9328308725071204e-05,
856
+ "loss": 0.0397,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.889922480620155,
861
+ "grad_norm": 0.21204759180545807,
862
+ "learning_rate": 3.9105385388070305e-05,
863
+ "loss": 0.0414,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9054263565891474,
868
+ "grad_norm": 0.20105929672718048,
869
+ "learning_rate": 3.8880804435999164e-05,
870
+ "loss": 0.0341,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9209302325581397,
875
+ "grad_norm": 0.11282369494438171,
876
+ "learning_rate": 3.8654592260818045e-05,
877
+ "loss": 0.0323,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.936434108527132,
882
+ "grad_norm": 0.1675432175397873,
883
+ "learning_rate": 3.842677544618279e-05,
884
+ "loss": 0.027,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.951937984496124,
889
+ "grad_norm": 0.2266375571489334,
890
+ "learning_rate": 3.819738076432081e-05,
891
+ "loss": 0.0214,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.9674418604651163,
896
+ "grad_norm": 0.1010638102889061,
897
+ "learning_rate": 3.7966435172884885e-05,
898
+ "loss": 0.0435,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.9829457364341085,
903
+ "grad_norm": 0.11044441908597946,
904
+ "learning_rate": 3.77339658117852e-05,
905
+ "loss": 0.0243,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 1.9984496124031008,
910
+ "grad_norm": 0.050437528640031815,
911
+ "learning_rate": 3.7500000000000003e-05,
912
+ "loss": 0.0423,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.012403100775194,
917
+ "grad_norm": 0.08492262661457062,
918
+ "learning_rate": 3.726456523236511e-05,
919
+ "loss": 0.0266,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.027906976744186,
924
+ "grad_norm": 0.12510479986667633,
925
+ "learning_rate": 3.7027689176342855e-05,
926
+ "loss": 0.0364,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.0434108527131785,
931
+ "grad_norm": 0.191548690199852,
932
+ "learning_rate": 3.67893996687707e-05,
933
+ "loss": 0.0293,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.0589147286821707,
938
+ "grad_norm": 0.2661445140838623,
939
+ "learning_rate": 3.6549724712589905e-05,
940
+ "loss": 0.0298,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.0744186046511626,
945
+ "grad_norm": 0.3290082514286041,
946
+ "learning_rate": 3.6308692473554814e-05,
947
+ "loss": 0.0196,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.089922480620155,
952
+ "grad_norm": 0.2585301697254181,
953
+ "learning_rate": 3.60663312769228e-05,
954
+ "loss": 0.0281,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.105426356589147,
959
+ "grad_norm": 0.23062346875667572,
960
+ "learning_rate": 3.5822669604125684e-05,
961
+ "loss": 0.0228,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1209302325581394,
966
+ "grad_norm": 0.10087283700704575,
967
+ "learning_rate": 3.557773608942262e-05,
968
+ "loss": 0.0292,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.1364341085271317,
973
+ "grad_norm": 0.15738359093666077,
974
+ "learning_rate": 3.533155951653516e-05,
975
+ "loss": 0.0418,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.151937984496124,
980
+ "grad_norm": 0.13803963363170624,
981
+ "learning_rate": 3.508416881526464e-05,
982
+ "loss": 0.0287,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.167441860465116,
987
+ "grad_norm": 0.19056080281734467,
988
+ "learning_rate": 3.483559305809248e-05,
989
+ "loss": 0.0332,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.1829457364341085,
994
+ "grad_norm": 0.18886078894138336,
995
+ "learning_rate": 3.4585861456763686e-05,
996
+ "loss": 0.0352,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.1984496124031008,
1001
+ "grad_norm": 0.2717881202697754,
1002
+ "learning_rate": 3.4335003358853996e-05,
1003
+ "loss": 0.0264,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.213953488372093,
1008
+ "grad_norm": 0.1758740395307541,
1009
+ "learning_rate": 3.408304824432104e-05,
1010
+ "loss": 0.0248,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.2294573643410853,
1015
+ "grad_norm": 0.22997550666332245,
1016
+ "learning_rate": 3.383002572203995e-05,
1017
+ "loss": 0.0306,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2449612403100776,
1022
+ "grad_norm": 0.11724910885095596,
1023
+ "learning_rate": 3.357596552632388e-05,
1024
+ "loss": 0.028,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.26046511627907,
1029
+ "grad_norm": 0.22709335386753082,
1030
+ "learning_rate": 3.332089751342968e-05,
1031
+ "loss": 0.024,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.275968992248062,
1036
+ "grad_norm": 0.27800169587135315,
1037
+ "learning_rate": 3.3064851658049314e-05,
1038
+ "loss": 0.0202,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.2914728682170544,
1043
+ "grad_norm": 0.17299439013004303,
1044
+ "learning_rate": 3.280785804978735e-05,
1045
+ "loss": 0.0189,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.3069767441860467,
1050
+ "grad_norm": 0.1307191699743271,
1051
+ "learning_rate": 3.2549946889624926e-05,
1052
+ "loss": 0.0357,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.322480620155039,
1057
+ "grad_norm": 0.10246355831623077,
1058
+ "learning_rate": 3.2291148486370626e-05,
1059
+ "loss": 0.0224,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3379844961240313,
1064
+ "grad_norm": 0.3734508752822876,
1065
+ "learning_rate": 3.2031493253098724e-05,
1066
+ "loss": 0.0233,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.353488372093023,
1071
+ "grad_norm": 0.13778243958950043,
1072
+ "learning_rate": 3.177101170357513e-05,
1073
+ "loss": 0.0219,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.3689922480620154,
1078
+ "grad_norm": 0.17842572927474976,
1079
+ "learning_rate": 3.150973444867151e-05,
1080
+ "loss": 0.0302,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.3844961240310076,
1085
+ "grad_norm": 0.16797401010990143,
1086
+ "learning_rate": 3.124769219276803e-05,
1087
+ "loss": 0.0492,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4,
1092
+ "grad_norm": 0.1816670447587967,
1093
+ "learning_rate": 3.0984915730145046e-05,
1094
+ "loss": 0.0208,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.415503875968992,
1099
+ "grad_norm": 0.07712769508361816,
1100
+ "learning_rate": 3.072143594136433e-05,
1101
+ "loss": 0.0156,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.4310077519379845,
1106
+ "grad_norm": 0.06302152574062347,
1107
+ "learning_rate": 3.045728378964004e-05,
1108
+ "loss": 0.0212,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.4465116279069767,
1113
+ "grad_norm": 0.11739777028560638,
1114
+ "learning_rate": 3.0192490317200058e-05,
1115
+ "loss": 0.0246,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.462015503875969,
1120
+ "grad_norm": 0.18686673045158386,
1121
+ "learning_rate": 2.9927086641637997e-05,
1122
+ "loss": 0.0166,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.4775193798449613,
1127
+ "grad_norm": 0.1006050631403923,
1128
+ "learning_rate": 2.9661103952256396e-05,
1129
+ "loss": 0.0209,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.4930232558139536,
1134
+ "grad_norm": 0.17344793677330017,
1135
+ "learning_rate": 2.9394573506401467e-05,
1136
+ "loss": 0.0205,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.508527131782946,
1141
+ "grad_norm": 0.08328920602798462,
1142
+ "learning_rate": 2.9127526625789808e-05,
1143
+ "loss": 0.0208,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.524031007751938,
1148
+ "grad_norm": 0.36139625310897827,
1149
+ "learning_rate": 2.885999469282761e-05,
1150
+ "loss": 0.0246,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.5395348837209304,
1155
+ "grad_norm": 0.22528782486915588,
1156
+ "learning_rate": 2.8592009146922704e-05,
1157
+ "loss": 0.0258,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.5550387596899222,
1162
+ "grad_norm": 0.2691043019294739,
1163
+ "learning_rate": 2.8323601480789928e-05,
1164
+ "loss": 0.0203,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.5705426356589145,
1169
+ "grad_norm": 0.1831626147031784,
1170
+ "learning_rate": 2.805480323675016e-05,
1171
+ "loss": 0.0274,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.5860465116279068,
1176
+ "grad_norm": 0.20435118675231934,
1177
+ "learning_rate": 2.7785646003023656e-05,
1178
+ "loss": 0.0217,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.601550387596899,
1183
+ "grad_norm": 0.1789761781692505,
1184
+ "learning_rate": 2.7516161410017844e-05,
1185
+ "loss": 0.0191,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6170542635658913,
1190
+ "grad_norm": 0.08747836202383041,
1191
+ "learning_rate": 2.7246381126610272e-05,
1192
+ "loss": 0.0233,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.6325581395348836,
1197
+ "grad_norm": 0.30709850788116455,
1198
+ "learning_rate": 2.697633685642697e-05,
1199
+ "loss": 0.0252,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.648062015503876,
1204
+ "grad_norm": 0.11726944893598557,
1205
+ "learning_rate": 2.6706060334116777e-05,
1206
+ "loss": 0.0233,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.663565891472868,
1211
+ "grad_norm": 0.06737342476844788,
1212
+ "learning_rate": 2.6435583321621966e-05,
1213
+ "loss": 0.0129,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.6790697674418604,
1218
+ "grad_norm": 0.09594861418008804,
1219
+ "learning_rate": 2.6164937604445705e-05,
1220
+ "loss": 0.021,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.6945736434108527,
1225
+ "grad_norm": 0.12169867008924484,
1226
+ "learning_rate": 2.5894154987916764e-05,
1227
+ "loss": 0.023,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.710077519379845,
1232
+ "grad_norm": 0.22493800520896912,
1233
+ "learning_rate": 2.5623267293451826e-05,
1234
+ "loss": 0.0167,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.7255813953488373,
1239
+ "grad_norm": 0.23264090716838837,
1240
+ "learning_rate": 2.5352306354815953e-05,
1241
+ "loss": 0.0222,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.7410852713178295,
1246
+ "grad_norm": 0.29153597354888916,
1247
+ "learning_rate": 2.5081304014381614e-05,
1248
+ "loss": 0.0208,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.756589147286822,
1253
+ "grad_norm": 0.11771135032176971,
1254
+ "learning_rate": 2.4810292119386675e-05,
1255
+ "loss": 0.0186,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.772093023255814,
1260
+ "grad_norm": 0.33184051513671875,
1261
+ "learning_rate": 2.4539302518191802e-05,
1262
+ "loss": 0.0177,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.7875968992248064,
1267
+ "grad_norm": 0.2414429783821106,
1268
+ "learning_rate": 2.426836705653782e-05,
1269
+ "loss": 0.0198,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8031007751937986,
1274
+ "grad_norm": 0.11880580335855484,
1275
+ "learning_rate": 2.3997517573803187e-05,
1276
+ "loss": 0.0188,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.818604651162791,
1281
+ "grad_norm": 0.05161415413022041,
1282
+ "learning_rate": 2.3726785899262493e-05,
1283
+ "loss": 0.0131,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.834108527131783,
1288
+ "grad_norm": 0.09770730137825012,
1289
+ "learning_rate": 2.34562038483459e-05,
1290
+ "loss": 0.0129,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.8496124031007755,
1295
+ "grad_norm": 0.27657774090766907,
1296
+ "learning_rate": 2.318580321890032e-05,
1297
+ "loss": 0.0242,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.8651162790697673,
1302
+ "grad_norm": 0.1245102509856224,
1303
+ "learning_rate": 2.2915615787452666e-05,
1304
+ "loss": 0.0182,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.8806201550387596,
1309
+ "grad_norm": 0.095403291285038,
1310
+ "learning_rate": 2.264567330547557e-05,
1311
+ "loss": 0.0229,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.896124031007752,
1316
+ "grad_norm": 0.09689685702323914,
1317
+ "learning_rate": 2.2376007495656084e-05,
1318
+ "loss": 0.02,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.911627906976744,
1323
+ "grad_norm": 0.07814809679985046,
1324
+ "learning_rate": 2.2106650048167697e-05,
1325
+ "loss": 0.0296,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.9271317829457364,
1330
+ "grad_norm": 0.18573637306690216,
1331
+ "learning_rate": 2.1837632616946266e-05,
1332
+ "loss": 0.0191,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.9426356589147287,
1337
+ "grad_norm": 0.16544780135154724,
1338
+ "learning_rate": 2.1568986815970126e-05,
1339
+ "loss": 0.0262,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.958139534883721,
1344
+ "grad_norm": 0.06749454140663147,
1345
+ "learning_rate": 2.1300744215544967e-05,
1346
+ "loss": 0.0178,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.973643410852713,
1351
+ "grad_norm": 0.1645621359348297,
1352
+ "learning_rate": 2.1032936338593718e-05,
1353
+ "loss": 0.017,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.9891472868217055,
1358
+ "grad_norm": 0.14035086333751678,
1359
+ "learning_rate": 2.0765594656952198e-05,
1360
+ "loss": 0.0269,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 3.0031007751937984,
1365
+ "grad_norm": 0.07817042618989944,
1366
+ "learning_rate": 2.0498750587670572e-05,
1367
+ "loss": 0.0183,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 3.0186046511627906,
1372
+ "grad_norm": 0.0851919949054718,
1373
+ "learning_rate": 2.0232435489321354e-05,
1374
+ "loss": 0.0115,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 3.034108527131783,
1379
+ "grad_norm": 0.07319127768278122,
1380
+ "learning_rate": 1.9966680658314273e-05,
1381
+ "loss": 0.0186,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 3.049612403100775,
1386
+ "grad_norm": 0.05918855220079422,
1387
+ "learning_rate": 1.970151732521842e-05,
1388
+ "loss": 0.0137,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 3.0651162790697675,
1393
+ "grad_norm": 0.09402059018611908,
1394
+ "learning_rate": 1.9436976651092144e-05,
1395
+ "loss": 0.0216,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 3.0806201550387597,
1400
+ "grad_norm": 0.15518927574157715,
1401
+ "learning_rate": 1.917308972382109e-05,
1402
+ "loss": 0.0164,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 3.096124031007752,
1407
+ "grad_norm": 0.17928968369960785,
1408
+ "learning_rate": 1.89098875544649e-05,
1409
+ "loss": 0.0153,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 3.1116279069767443,
1414
+ "grad_norm": 0.20205701887607574,
1415
+ "learning_rate": 1.8647401073612892e-05,
1416
+ "loss": 0.0143,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 3.1271317829457366,
1421
+ "grad_norm": 0.023780664429068565,
1422
+ "learning_rate": 1.8385661127749166e-05,
1423
+ "loss": 0.0138,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 3.142635658914729,
1428
+ "grad_norm": 0.16407065093517303,
1429
+ "learning_rate": 1.8124698475627696e-05,
1430
+ "loss": 0.0164,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 3.158139534883721,
1435
+ "grad_norm": 0.05904044210910797,
1436
+ "learning_rate": 1.7864543784657643e-05,
1437
+ "loss": 0.0127,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 3.173643410852713,
1442
+ "grad_norm": 0.07115277647972107,
1443
+ "learning_rate": 1.7605227627299413e-05,
1444
+ "loss": 0.0127,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 3.1891472868217052,
1449
+ "grad_norm": 0.3148862421512604,
1450
+ "learning_rate": 1.73467804774719e-05,
1451
+ "loss": 0.0174,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 3.2046511627906975,
1456
+ "grad_norm": 0.1581067591905594,
1457
+ "learning_rate": 1.7089232706971313e-05,
1458
+ "loss": 0.0148,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 3.22015503875969,
1463
+ "grad_norm": 0.17511816322803497,
1464
+ "learning_rate": 1.6832614581901986e-05,
1465
+ "loss": 0.0193,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 3.235658914728682,
1470
+ "grad_norm": 0.07704796642065048,
1471
+ "learning_rate": 1.6576956259119576e-05,
1472
+ "loss": 0.0114,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 3.2511627906976743,
1477
+ "grad_norm": 0.08784597367048264,
1478
+ "learning_rate": 1.6322287782687197e-05,
1479
+ "loss": 0.0116,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 3.2666666666666666,
1484
+ "grad_norm": 0.0565035343170166,
1485
+ "learning_rate": 1.6068639080344708e-05,
1486
+ "loss": 0.0159,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 3.282170542635659,
1491
+ "grad_norm": 0.15565626323223114,
1492
+ "learning_rate": 1.5816039959991712e-05,
1493
+ "loss": 0.015,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 3.297674418604651,
1498
+ "grad_norm": 0.06181817501783371,
1499
+ "learning_rate": 1.5564520106184644e-05,
1500
+ "loss": 0.0169,
1501
+ "step": 1065
1502
+ },
1503
+ {
1504
+ "epoch": 3.3131782945736434,
1505
+ "grad_norm": 0.15954700112342834,
1506
+ "learning_rate": 1.531410907664834e-05,
1507
+ "loss": 0.0147,
1508
+ "step": 1070
1509
+ },
1510
+ {
1511
+ "epoch": 3.3286821705426357,
1512
+ "grad_norm": 0.0700472965836525,
1513
+ "learning_rate": 1.5064836298802551e-05,
1514
+ "loss": 0.0156,
1515
+ "step": 1075
1516
+ },
1517
+ {
1518
+ "epoch": 3.344186046511628,
1519
+ "grad_norm": 0.028587840497493744,
1520
+ "learning_rate": 1.4816731066303686e-05,
1521
+ "loss": 0.0116,
1522
+ "step": 1080
1523
+ },
1524
+ {
1525
+ "epoch": 3.3596899224806203,
1526
+ "grad_norm": 0.11734448373317719,
1527
+ "learning_rate": 1.456982253560235e-05,
1528
+ "loss": 0.0179,
1529
+ "step": 1085
1530
+ },
1531
+ {
1532
+ "epoch": 3.3751937984496125,
1533
+ "grad_norm": 0.046429798007011414,
1534
+ "learning_rate": 1.4324139722516982e-05,
1535
+ "loss": 0.011,
1536
+ "step": 1090
1537
+ },
1538
+ {
1539
+ "epoch": 3.390697674418605,
1540
+ "grad_norm": 0.18383632600307465,
1541
+ "learning_rate": 1.4079711498824027e-05,
1542
+ "loss": 0.0125,
1543
+ "step": 1095
1544
+ },
1545
+ {
1546
+ "epoch": 3.406201550387597,
1547
+ "grad_norm": 0.3278388977050781,
1548
+ "learning_rate": 1.3836566588864999e-05,
1549
+ "loss": 0.0157,
1550
+ "step": 1100
1551
+ },
1552
+ {
1553
+ "epoch": 3.4217054263565894,
1554
+ "grad_norm": 0.18710392713546753,
1555
+ "learning_rate": 1.3594733566170926e-05,
1556
+ "loss": 0.0148,
1557
+ "step": 1105
1558
+ },
1559
+ {
1560
+ "epoch": 3.4372093023255816,
1561
+ "grad_norm": 0.04076448082923889,
1562
+ "learning_rate": 1.3354240850104476e-05,
1563
+ "loss": 0.0077,
1564
+ "step": 1110
1565
+ },
1566
+ {
1567
+ "epoch": 3.4527131782945735,
1568
+ "grad_norm": 0.06835182756185532,
1569
+ "learning_rate": 1.3115116702520219e-05,
1570
+ "loss": 0.0172,
1571
+ "step": 1115
1572
+ },
1573
+ {
1574
+ "epoch": 3.4682170542635657,
1575
+ "grad_norm": 0.07915415614843369,
1576
+ "learning_rate": 1.2877389224443365e-05,
1577
+ "loss": 0.0091,
1578
+ "step": 1120
1579
+ },
1580
+ {
1581
+ "epoch": 3.483720930232558,
1582
+ "grad_norm": 0.04475206881761551,
1583
+ "learning_rate": 1.2641086352767506e-05,
1584
+ "loss": 0.015,
1585
+ "step": 1125
1586
+ },
1587
+ {
1588
+ "epoch": 3.4992248062015503,
1589
+ "grad_norm": 0.025727396830916405,
1590
+ "learning_rate": 1.2406235856971487e-05,
1591
+ "loss": 0.0117,
1592
+ "step": 1130
1593
+ },
1594
+ {
1595
+ "epoch": 3.5147286821705426,
1596
+ "grad_norm": 0.3452167510986328,
1597
+ "learning_rate": 1.2172865335856066e-05,
1598
+ "loss": 0.0115,
1599
+ "step": 1135
1600
+ },
1601
+ {
1602
+ "epoch": 3.530232558139535,
1603
+ "grad_norm": 0.2533954977989197,
1604
+ "learning_rate": 1.1941002214300606e-05,
1605
+ "loss": 0.0174,
1606
+ "step": 1140
1607
+ },
1608
+ {
1609
+ "epoch": 3.545736434108527,
1610
+ "grad_norm": 0.11330398172140121,
1611
+ "learning_rate": 1.1710673740040232e-05,
1612
+ "loss": 0.0119,
1613
+ "step": 1145
1614
+ },
1615
+ {
1616
+ "epoch": 3.5612403100775194,
1617
+ "grad_norm": 0.07775407284498215,
1618
+ "learning_rate": 1.1481906980463709e-05,
1619
+ "loss": 0.0093,
1620
+ "step": 1150
1621
+ },
1622
+ {
1623
+ "epoch": 3.5767441860465117,
1624
+ "grad_norm": 0.14502529799938202,
1625
+ "learning_rate": 1.1254728819432595e-05,
1626
+ "loss": 0.0137,
1627
+ "step": 1155
1628
+ },
1629
+ {
1630
+ "epoch": 3.592248062015504,
1631
+ "grad_norm": 0.05564185976982117,
1632
+ "learning_rate": 1.1029165954121983e-05,
1633
+ "loss": 0.0116,
1634
+ "step": 1160
1635
+ },
1636
+ {
1637
+ "epoch": 3.6077519379844962,
1638
+ "grad_norm": 0.07241734862327576,
1639
+ "learning_rate": 1.0805244891883113e-05,
1640
+ "loss": 0.0095,
1641
+ "step": 1165
1642
+ },
1643
+ {
1644
+ "epoch": 3.6232558139534885,
1645
+ "grad_norm": 0.05909044295549393,
1646
+ "learning_rate": 1.0582991947128324e-05,
1647
+ "loss": 0.0088,
1648
+ "step": 1170
1649
+ },
1650
+ {
1651
+ "epoch": 3.6387596899224808,
1652
+ "grad_norm": 0.12203407287597656,
1653
+ "learning_rate": 1.036243323823868e-05,
1654
+ "loss": 0.0157,
1655
+ "step": 1175
1656
+ },
1657
+ {
1658
+ "epoch": 3.6542635658914726,
1659
+ "grad_norm": 0.15194092690944672,
1660
+ "learning_rate": 1.0143594684494634e-05,
1661
+ "loss": 0.0116,
1662
+ "step": 1180
1663
+ },
1664
+ {
1665
+ "epoch": 3.669767441860465,
1666
+ "grad_norm": 0.06669194251298904,
1667
+ "learning_rate": 9.926502003030075e-06,
1668
+ "loss": 0.0136,
1669
+ "step": 1185
1670
+ },
1671
+ {
1672
+ "epoch": 3.685271317829457,
1673
+ "grad_norm": 0.07091967761516571,
1674
+ "learning_rate": 9.711180705810156e-06,
1675
+ "loss": 0.0164,
1676
+ "step": 1190
1677
+ },
1678
+ {
1679
+ "epoch": 3.7007751937984494,
1680
+ "grad_norm": 0.0350261889398098,
1681
+ "learning_rate": 9.4976560966332e-06,
1682
+ "loss": 0.0128,
1683
+ "step": 1195
1684
+ },
1685
+ {
1686
+ "epoch": 3.7162790697674417,
1687
+ "grad_norm": 0.09878349304199219,
1688
+ "learning_rate": 9.285953268157116e-06,
1689
+ "loss": 0.0127,
1690
+ "step": 1200
1691
+ },
1692
+ {
1693
+ "epoch": 3.731782945736434,
1694
+ "grad_norm": 0.1007269099354744,
1695
+ "learning_rate": 9.076097098950543e-06,
1696
+ "loss": 0.0087,
1697
+ "step": 1205
1698
+ },
1699
+ {
1700
+ "epoch": 3.7472868217054263,
1701
+ "grad_norm": 0.07725387811660767,
1702
+ "learning_rate": 8.868112250569288e-06,
1703
+ "loss": 0.014,
1704
+ "step": 1210
1705
+ },
1706
+ {
1707
+ "epoch": 3.7627906976744185,
1708
+ "grad_norm": 0.07512272149324417,
1709
+ "learning_rate": 8.662023164658125e-06,
1710
+ "loss": 0.0121,
1711
+ "step": 1215
1712
+ },
1713
+ {
1714
+ "epoch": 3.778294573643411,
1715
+ "grad_norm": 0.05582176521420479,
1716
+ "learning_rate": 8.45785406007852e-06,
1717
+ "loss": 0.0153,
1718
+ "step": 1220
1719
+ },
1720
+ {
1721
+ "epoch": 3.793798449612403,
1722
+ "grad_norm": 0.1534244567155838,
1723
+ "learning_rate": 8.2556289300625e-06,
1724
+ "loss": 0.0151,
1725
+ "step": 1225
1726
+ },
1727
+ {
1728
+ "epoch": 3.8093023255813954,
1729
+ "grad_norm": 0.042408719658851624,
1730
+ "learning_rate": 8.055371539393081e-06,
1731
+ "loss": 0.0108,
1732
+ "step": 1230
1733
+ },
1734
+ {
1735
+ "epoch": 3.8248062015503876,
1736
+ "grad_norm": 0.062217891216278076,
1737
+ "learning_rate": 7.857105421611515e-06,
1738
+ "loss": 0.0136,
1739
+ "step": 1235
1740
+ },
1741
+ {
1742
+ "epoch": 3.84031007751938,
1743
+ "grad_norm": 0.09418876469135284,
1744
+ "learning_rate": 7.660853876251684e-06,
1745
+ "loss": 0.0116,
1746
+ "step": 1240
1747
+ },
1748
+ {
1749
+ "epoch": 3.855813953488372,
1750
+ "grad_norm": 0.06122265383601189,
1751
+ "learning_rate": 7.4666399661020126e-06,
1752
+ "loss": 0.0103,
1753
+ "step": 1245
1754
+ },
1755
+ {
1756
+ "epoch": 3.8713178294573645,
1757
+ "grad_norm": 0.06508161127567291,
1758
+ "learning_rate": 7.274486514495268e-06,
1759
+ "loss": 0.0094,
1760
+ "step": 1250
1761
+ },
1762
+ {
1763
+ "epoch": 3.8868217054263567,
1764
+ "grad_norm": 0.122026726603508,
1765
+ "learning_rate": 7.08441610262639e-06,
1766
+ "loss": 0.0105,
1767
+ "step": 1255
1768
+ },
1769
+ {
1770
+ "epoch": 3.902325581395349,
1771
+ "grad_norm": 0.09518284350633621,
1772
+ "learning_rate": 6.896451066898846e-06,
1773
+ "loss": 0.0105,
1774
+ "step": 1260
1775
+ },
1776
+ {
1777
+ "epoch": 3.9178294573643413,
1778
+ "grad_norm": 0.3977924883365631,
1779
+ "learning_rate": 6.710613496299739e-06,
1780
+ "loss": 0.0171,
1781
+ "step": 1265
1782
+ },
1783
+ {
1784
+ "epoch": 3.9333333333333336,
1785
+ "grad_norm": 0.2375529408454895,
1786
+ "learning_rate": 6.526925229803982e-06,
1787
+ "loss": 0.0155,
1788
+ "step": 1270
1789
+ },
1790
+ {
1791
+ "epoch": 3.948837209302326,
1792
+ "grad_norm": 0.15753792226314545,
1793
+ "learning_rate": 6.3454078538078635e-06,
1794
+ "loss": 0.0101,
1795
+ "step": 1275
1796
+ },
1797
+ {
1798
+ "epoch": 3.9643410852713177,
1799
+ "grad_norm": 0.13304033875465393,
1800
+ "learning_rate": 6.166082699592288e-06,
1801
+ "loss": 0.0137,
1802
+ "step": 1280
1803
+ },
1804
+ {
1805
+ "epoch": 3.97984496124031,
1806
+ "grad_norm": 0.11497492343187332,
1807
+ "learning_rate": 5.988970840815994e-06,
1808
+ "loss": 0.0129,
1809
+ "step": 1285
1810
+ },
1811
+ {
1812
+ "epoch": 3.9953488372093022,
1813
+ "grad_norm": 0.052612703293561935,
1814
+ "learning_rate": 5.8140930910390715e-06,
1815
+ "loss": 0.0132,
1816
+ "step": 1290
1817
+ },
1818
+ {
1819
+ "epoch": 4.0093023255813955,
1820
+ "grad_norm": 0.0735371857881546,
1821
+ "learning_rate": 5.64147000127698e-06,
1822
+ "loss": 0.0111,
1823
+ "step": 1295
1824
+ },
1825
+ {
1826
+ "epoch": 4.024806201550388,
1827
+ "grad_norm": 0.08621438592672348,
1828
+ "learning_rate": 5.471121857585543e-06,
1829
+ "loss": 0.01,
1830
+ "step": 1300
1831
+ },
1832
+ {
1833
+ "epoch": 4.04031007751938,
1834
+ "grad_norm": 0.03453483060002327,
1835
+ "learning_rate": 5.30306867867692e-06,
1836
+ "loss": 0.0067,
1837
+ "step": 1305
1838
+ },
1839
+ {
1840
+ "epoch": 4.055813953488372,
1841
+ "grad_norm": 0.02685674838721752,
1842
+ "learning_rate": 5.13733021356714e-06,
1843
+ "loss": 0.0087,
1844
+ "step": 1310
1845
+ },
1846
+ {
1847
+ "epoch": 4.071317829457365,
1848
+ "grad_norm": 0.05555293336510658,
1849
+ "learning_rate": 4.973925939255209e-06,
1850
+ "loss": 0.0067,
1851
+ "step": 1315
1852
+ },
1853
+ {
1854
+ "epoch": 4.086821705426357,
1855
+ "grad_norm": 0.058123618364334106,
1856
+ "learning_rate": 4.812875058434315e-06,
1857
+ "loss": 0.0102,
1858
+ "step": 1320
1859
+ },
1860
+ {
1861
+ "epoch": 4.102325581395349,
1862
+ "grad_norm": 0.026801196858286858,
1863
+ "learning_rate": 4.654196497235139e-06,
1864
+ "loss": 0.0071,
1865
+ "step": 1325
1866
+ },
1867
+ {
1868
+ "epoch": 4.1178294573643415,
1869
+ "grad_norm": 0.053194936364889145,
1870
+ "learning_rate": 4.4979089030017216e-06,
1871
+ "loss": 0.0086,
1872
+ "step": 1330
1873
+ },
1874
+ {
1875
+ "epoch": 4.133333333333334,
1876
+ "grad_norm": 0.11018364131450653,
1877
+ "learning_rate": 4.344030642100133e-06,
1878
+ "loss": 0.011,
1879
+ "step": 1335
1880
+ },
1881
+ {
1882
+ "epoch": 4.148837209302325,
1883
+ "grad_norm": 0.05405386909842491,
1884
+ "learning_rate": 4.192579797760085e-06,
1885
+ "loss": 0.0102,
1886
+ "step": 1340
1887
+ },
1888
+ {
1889
+ "epoch": 4.164341085271317,
1890
+ "grad_norm": 0.05461077392101288,
1891
+ "learning_rate": 4.043574167949893e-06,
1892
+ "loss": 0.0104,
1893
+ "step": 1345
1894
+ },
1895
+ {
1896
+ "epoch": 4.17984496124031,
1897
+ "grad_norm": 0.0669790729880333,
1898
+ "learning_rate": 3.897031263284867e-06,
1899
+ "loss": 0.0075,
1900
+ "step": 1350
1901
+ },
1902
+ {
1903
+ "epoch": 4.195348837209302,
1904
+ "grad_norm": 0.04254228249192238,
1905
+ "learning_rate": 3.752968304969576e-06,
1906
+ "loss": 0.0079,
1907
+ "step": 1355
1908
+ },
1909
+ {
1910
+ "epoch": 4.210852713178294,
1911
+ "grad_norm": 0.06297585368156433,
1912
+ "learning_rate": 3.6114022227740433e-06,
1913
+ "loss": 0.0109,
1914
+ "step": 1360
1915
+ },
1916
+ {
1917
+ "epoch": 4.2263565891472865,
1918
+ "grad_norm": 0.07878061383962631,
1919
+ "learning_rate": 3.4723496530442352e-06,
1920
+ "loss": 0.0092,
1921
+ "step": 1365
1922
+ },
1923
+ {
1924
+ "epoch": 4.241860465116279,
1925
+ "grad_norm": 0.11867242306470871,
1926
+ "learning_rate": 3.335826936747011e-06,
1927
+ "loss": 0.0092,
1928
+ "step": 1370
1929
+ },
1930
+ {
1931
+ "epoch": 4.257364341085271,
1932
+ "grad_norm": 0.10879813879728317,
1933
+ "learning_rate": 3.201850117549787e-06,
1934
+ "loss": 0.009,
1935
+ "step": 1375
1936
+ },
1937
+ {
1938
+ "epoch": 4.272868217054263,
1939
+ "grad_norm": 0.05206475034356117,
1940
+ "learning_rate": 3.0704349399351435e-06,
1941
+ "loss": 0.0099,
1942
+ "step": 1380
1943
+ },
1944
+ {
1945
+ "epoch": 4.288372093023256,
1946
+ "grad_norm": 0.06414878368377686,
1947
+ "learning_rate": 2.941596847350597e-06,
1948
+ "loss": 0.0076,
1949
+ "step": 1385
1950
+ },
1951
+ {
1952
+ "epoch": 4.303875968992248,
1953
+ "grad_norm": 0.09740181267261505,
1954
+ "learning_rate": 2.8153509803937274e-06,
1955
+ "loss": 0.0081,
1956
+ "step": 1390
1957
+ },
1958
+ {
1959
+ "epoch": 4.31937984496124,
1960
+ "grad_norm": 0.055816520005464554,
1961
+ "learning_rate": 2.691712175032912e-06,
1962
+ "loss": 0.0085,
1963
+ "step": 1395
1964
+ },
1965
+ {
1966
+ "epoch": 4.334883720930232,
1967
+ "grad_norm": 0.08039291948080063,
1968
+ "learning_rate": 2.5706949608638704e-06,
1969
+ "loss": 0.0096,
1970
+ "step": 1400
1971
+ },
1972
+ {
1973
+ "epoch": 4.350387596899225,
1974
+ "grad_norm": 0.06461725383996964,
1975
+ "learning_rate": 2.4523135594021585e-06,
1976
+ "loss": 0.0082,
1977
+ "step": 1405
1978
+ },
1979
+ {
1980
+ "epoch": 4.365891472868217,
1981
+ "grad_norm": 0.03589886054396629,
1982
+ "learning_rate": 2.336581882411967e-06,
1983
+ "loss": 0.0064,
1984
+ "step": 1410
1985
+ },
1986
+ {
1987
+ "epoch": 4.381395348837209,
1988
+ "grad_norm": 0.0716664046049118,
1989
+ "learning_rate": 2.2235135302712095e-06,
1990
+ "loss": 0.0093,
1991
+ "step": 1415
1992
+ },
1993
+ {
1994
+ "epoch": 4.3968992248062015,
1995
+ "grad_norm": 0.07864725589752197,
1996
+ "learning_rate": 2.113121790373257e-06,
1997
+ "loss": 0.0091,
1998
+ "step": 1420
1999
+ },
2000
+ {
2001
+ "epoch": 4.412403100775194,
2002
+ "grad_norm": 0.0717134103178978,
2003
+ "learning_rate": 2.005419635565481e-06,
2004
+ "loss": 0.0081,
2005
+ "step": 1425
2006
+ },
2007
+ {
2008
+ "epoch": 4.427906976744186,
2009
+ "grad_norm": 0.11225301772356033,
2010
+ "learning_rate": 1.900419722624705e-06,
2011
+ "loss": 0.0085,
2012
+ "step": 1430
2013
+ },
2014
+ {
2015
+ "epoch": 4.443410852713178,
2016
+ "grad_norm": 0.06452286243438721,
2017
+ "learning_rate": 1.7981343907698484e-06,
2018
+ "loss": 0.0102,
2019
+ "step": 1435
2020
+ },
2021
+ {
2022
+ "epoch": 4.458914728682171,
2023
+ "grad_norm": 0.08178742229938507,
2024
+ "learning_rate": 1.6985756602118236e-06,
2025
+ "loss": 0.0096,
2026
+ "step": 1440
2027
+ },
2028
+ {
2029
+ "epoch": 4.474418604651163,
2030
+ "grad_norm": 0.055801451206207275,
2031
+ "learning_rate": 1.6017552307410033e-06,
2032
+ "loss": 0.0073,
2033
+ "step": 1445
2034
+ },
2035
+ {
2036
+ "epoch": 4.489922480620155,
2037
+ "grad_norm": 0.11048652976751328,
2038
+ "learning_rate": 1.5076844803522922e-06,
2039
+ "loss": 0.0095,
2040
+ "step": 1450
2041
+ },
2042
+ {
2043
+ "epoch": 4.5054263565891475,
2044
+ "grad_norm": 0.06384676694869995,
2045
+ "learning_rate": 1.4163744639080101e-06,
2046
+ "loss": 0.0077,
2047
+ "step": 1455
2048
+ },
2049
+ {
2050
+ "epoch": 4.52093023255814,
2051
+ "grad_norm": 0.05776697397232056,
2052
+ "learning_rate": 1.3278359118387845e-06,
2053
+ "loss": 0.0095,
2054
+ "step": 1460
2055
+ },
2056
+ {
2057
+ "epoch": 4.536434108527132,
2058
+ "grad_norm": 0.055965911597013474,
2059
+ "learning_rate": 1.2420792288825312e-06,
2060
+ "loss": 0.0108,
2061
+ "step": 1465
2062
+ },
2063
+ {
2064
+ "epoch": 4.551937984496124,
2065
+ "grad_norm": 0.06405636668205261,
2066
+ "learning_rate": 1.1591144928617375e-06,
2067
+ "loss": 0.0074,
2068
+ "step": 1470
2069
+ },
2070
+ {
2071
+ "epoch": 4.567441860465117,
2072
+ "grad_norm": 0.03841257467865944,
2073
+ "learning_rate": 1.0789514534991497e-06,
2074
+ "loss": 0.0073,
2075
+ "step": 1475
2076
+ },
2077
+ {
2078
+ "epoch": 4.582945736434109,
2079
+ "grad_norm": 0.0615706592798233,
2080
+ "learning_rate": 1.0015995312720127e-06,
2081
+ "loss": 0.0066,
2082
+ "step": 1480
2083
+ },
2084
+ {
2085
+ "epoch": 4.598449612403101,
2086
+ "grad_norm": 0.037747208029031754,
2087
+ "learning_rate": 9.270678163050217e-07,
2088
+ "loss": 0.0082,
2089
+ "step": 1485
2090
+ },
2091
+ {
2092
+ "epoch": 4.613953488372093,
2093
+ "grad_norm": 0.04813956841826439,
2094
+ "learning_rate": 8.553650673020608e-07,
2095
+ "loss": 0.0089,
2096
+ "step": 1490
2097
+ },
2098
+ {
2099
+ "epoch": 4.629457364341086,
2100
+ "grad_norm": 0.06449221074581146,
2101
+ "learning_rate": 7.864997105169497e-07,
2102
+ "loss": 0.0074,
2103
+ "step": 1495
2104
+ },
2105
+ {
2106
+ "epoch": 4.644961240310078,
2107
+ "grad_norm": 0.1142016053199768,
2108
+ "learning_rate": 7.204798387631773e-07,
2109
+ "loss": 0.009,
2110
+ "step": 1500
2111
+ },
2112
+ {
2113
+ "epoch": 4.66046511627907,
2114
+ "grad_norm": 0.037693146616220474,
2115
+ "learning_rate": 6.573132104628954e-07,
2116
+ "loss": 0.01,
2117
+ "step": 1505
2118
+ },
2119
+ {
2120
+ "epoch": 4.6759689922480625,
2121
+ "grad_norm": 0.06647146493196487,
2122
+ "learning_rate": 5.970072487351458e-07,
2123
+ "loss": 0.0098,
2124
+ "step": 1510
2125
+ },
2126
+ {
2127
+ "epoch": 4.691472868217054,
2128
+ "grad_norm": 0.05509454756975174,
2129
+ "learning_rate": 5.395690405235493e-07,
2130
+ "loss": 0.0072,
2131
+ "step": 1515
2132
+ },
2133
+ {
2134
+ "epoch": 4.706976744186046,
2135
+ "grad_norm": 0.04223225638270378,
2136
+ "learning_rate": 4.850053357634693e-07,
2137
+ "loss": 0.0091,
2138
+ "step": 1520
2139
+ },
2140
+ {
2141
+ "epoch": 4.7224806201550384,
2142
+ "grad_norm": 0.1627756506204605,
2143
+ "learning_rate": 4.333225465887658e-07,
2144
+ "loss": 0.0108,
2145
+ "step": 1525
2146
+ },
2147
+ {
2148
+ "epoch": 4.737984496124031,
2149
+ "grad_norm": 0.0994868054986,
2150
+ "learning_rate": 3.845267465782759e-07,
2151
+ "loss": 0.0088,
2152
+ "step": 1530
2153
+ },
2154
+ {
2155
+ "epoch": 4.753488372093023,
2156
+ "grad_norm": 0.1813383400440216,
2157
+ "learning_rate": 3.386236700420708e-07,
2158
+ "loss": 0.0098,
2159
+ "step": 1535
2160
+ },
2161
+ {
2162
+ "epoch": 4.768992248062015,
2163
+ "grad_norm": 0.06936731189489365,
2164
+ "learning_rate": 2.9561871134757e-07,
2165
+ "loss": 0.0076,
2166
+ "step": 1540
2167
+ },
2168
+ {
2169
+ "epoch": 4.7844961240310075,
2170
+ "grad_norm": 0.06031731516122818,
2171
+ "learning_rate": 2.5551692428563143e-07,
2172
+ "loss": 0.0086,
2173
+ "step": 1545
2174
+ },
2175
+ {
2176
+ "epoch": 4.8,
2177
+ "grad_norm": 0.05364159867167473,
2178
+ "learning_rate": 2.183230214766241e-07,
2179
+ "loss": 0.0081,
2180
+ "step": 1550
2181
+ },
2182
+ {
2183
+ "epoch": 4.815503875968992,
2184
+ "grad_norm": 0.06721718609333038,
2185
+ "learning_rate": 1.8404137381664022e-07,
2186
+ "loss": 0.0127,
2187
+ "step": 1555
2188
+ },
2189
+ {
2190
+ "epoch": 4.831007751937984,
2191
+ "grad_norm": 0.11584588885307312,
2192
+ "learning_rate": 1.526760099638286e-07,
2193
+ "loss": 0.0084,
2194
+ "step": 1560
2195
+ },
2196
+ {
2197
+ "epoch": 4.846511627906977,
2198
+ "grad_norm": 0.03231743723154068,
2199
+ "learning_rate": 1.2423061586496477e-07,
2200
+ "loss": 0.0075,
2201
+ "step": 1565
2202
+ },
2203
+ {
2204
+ "epoch": 4.862015503875969,
2205
+ "grad_norm": 0.04497898742556572,
2206
+ "learning_rate": 9.870853432229488e-08,
2207
+ "loss": 0.009,
2208
+ "step": 1570
2209
+ },
2210
+ {
2211
+ "epoch": 4.877519379844961,
2212
+ "grad_norm": 0.052457842975854874,
2213
+ "learning_rate": 7.611276460069428e-08,
2214
+ "loss": 0.01,
2215
+ "step": 1575
2216
+ },
2217
+ {
2218
+ "epoch": 4.8930232558139535,
2219
+ "grad_norm": 0.08025941997766495,
2220
+ "learning_rate": 5.644596207521335e-08,
2221
+ "loss": 0.0113,
2222
+ "step": 1580
2223
+ },
2224
+ {
2225
+ "epoch": 4.908527131782946,
2226
+ "grad_norm": 0.09332724660634995,
2227
+ "learning_rate": 3.97104379190244e-08,
2228
+ "loss": 0.0088,
2229
+ "step": 1585
2230
+ },
2231
+ {
2232
+ "epoch": 4.924031007751938,
2233
+ "grad_norm": 0.08747787028551102,
2234
+ "learning_rate": 2.590815883181108e-08,
2235
+ "loss": 0.0126,
2236
+ "step": 1590
2237
+ },
2238
+ {
2239
+ "epoch": 4.93953488372093,
2240
+ "grad_norm": 0.2842964231967926,
2241
+ "learning_rate": 1.5040746808664407e-08,
2242
+ "loss": 0.0105,
2243
+ "step": 1595
2244
+ },
2245
+ {
2246
+ "epoch": 4.955038759689923,
2247
+ "grad_norm": 0.07913018018007278,
2248
+ "learning_rate": 7.1094789494602355e-09,
2249
+ "loss": 0.0122,
2250
+ "step": 1600
2251
+ },
2252
+ {
2253
+ "epoch": 4.970542635658915,
2254
+ "grad_norm": 0.07465241849422455,
2255
+ "learning_rate": 2.1152873087848525e-09,
2256
+ "loss": 0.0076,
2257
+ "step": 1605
2258
+ },
2259
+ {
2260
+ "epoch": 4.986046511627907,
2261
+ "grad_norm": 0.12626029551029205,
2262
+ "learning_rate": 5.875878640038135e-11,
2263
+ "loss": 0.0095,
2264
+ "step": 1610
2265
+ }
2266
+ ],
2267
+ "logging_steps": 5,
2268
+ "max_steps": 1610,
2269
+ "num_input_tokens_seen": 0,
2270
+ "num_train_epochs": 5,
2271
+ "save_steps": 500,
2272
+ "stateful_callbacks": {
2273
+ "TrainerControl": {
2274
+ "args": {
2275
+ "should_epoch_stop": false,
2276
+ "should_evaluate": false,
2277
+ "should_log": false,
2278
+ "should_save": true,
2279
+ "should_training_stop": true
2280
+ },
2281
+ "attributes": {}
2282
+ }
2283
+ },
2284
+ "total_flos": 2.716595267862528e+16,
2285
+ "train_batch_size": 2,
2286
+ "trial_name": null,
2287
+ "trial_params": null
2288
+ }
checkpoint-1610/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc429601d1d23ce75bcf84e7e4ed5fc0ae418d073e5933d8bb8717ac0faf730
3
+ size 5688
checkpoint-500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-1B-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 0.15.2
checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "k_proj",
31
+ "up_proj",
32
+ "down_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc306b4eb63f7882f26260252352abe8a246563664f56058bb7404e95a43aeb2
3
+ size 180385008
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e18340be5ff6d1390976ca28a65a3d3c3fac96491a757471219f4df27a4181
3
+ size 360899194
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
3
+ size 988
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84072ec1be49a4c5d3e3f22ccb582e0b4cda85bf83afeb28f14ea1a2cd65496
3
+ size 1064
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920