Hugging Face's logo

kloodia
/
lora-8b-physic

PEFT
TensorBoard
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files
xet
Metrics Community
kloodia commited on
Commit
c4d7b6b
·
verified ·
1 Parent(s): 484865c

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +158 -0
  2. adapter_config.json +34 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-168/README.md +202 -0
  5. checkpoint-168/adapter_config.json +34 -0
  6. checkpoint-168/adapter_model.safetensors +3 -0
  7. checkpoint-168/optimizer.pt +3 -0
  8. checkpoint-168/rng_state_0.pth +3 -0
  9. checkpoint-168/rng_state_1.pth +3 -0
  10. checkpoint-168/rng_state_2.pth +3 -0
  11. checkpoint-168/rng_state_3.pth +3 -0
  12. checkpoint-168/scheduler.pt +3 -0
  13. checkpoint-168/special_tokens_map.json +23 -0
  14. checkpoint-168/tokenizer.json +0 -0
  15. checkpoint-168/tokenizer_config.json +2062 -0
  16. checkpoint-168/trainer_state.json +1237 -0
  17. checkpoint-168/training_args.bin +3 -0
  18. checkpoint-336/README.md +202 -0
  19. checkpoint-336/adapter_config.json +34 -0
  20. checkpoint-336/adapter_model.safetensors +3 -0
  21. checkpoint-336/optimizer.pt +3 -0
  22. checkpoint-336/rng_state_0.pth +3 -0
  23. checkpoint-336/rng_state_1.pth +3 -0
  24. checkpoint-336/rng_state_2.pth +3 -0
  25. checkpoint-336/rng_state_3.pth +3 -0
  26. checkpoint-336/scheduler.pt +3 -0
  27. checkpoint-336/special_tokens_map.json +23 -0
  28. checkpoint-336/tokenizer.json +0 -0
  29. checkpoint-336/tokenizer_config.json +2062 -0
  30. checkpoint-336/trainer_state.json +2445 -0
  31. checkpoint-336/training_args.bin +3 -0
  32. checkpoint-504/README.md +202 -0
  33. checkpoint-504/adapter_config.json +34 -0
  34. checkpoint-504/adapter_model.safetensors +3 -0
  35. checkpoint-504/optimizer.pt +3 -0
  36. checkpoint-504/rng_state_0.pth +3 -0
  37. checkpoint-504/rng_state_1.pth +3 -0
  38. checkpoint-504/rng_state_2.pth +3 -0
  39. checkpoint-504/rng_state_3.pth +3 -0
  40. checkpoint-504/scheduler.pt +3 -0
  41. checkpoint-504/special_tokens_map.json +23 -0
  42. checkpoint-504/tokenizer.json +0 -0
  43. checkpoint-504/tokenizer_config.json +2062 -0
  44. checkpoint-504/trainer_state.json +3653 -0
  45. checkpoint-504/training_args.bin +3 -0
  46. checkpoint-672/README.md +202 -0
  47. checkpoint-672/adapter_config.json +34 -0
  48. checkpoint-672/adapter_model.safetensors +3 -0
  49. checkpoint-672/optimizer.pt +3 -0
  50. checkpoint-672/rng_state_0.pth +3 -0
README.md ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: meta-llama/Meta-Llama-3-8B
7
+ model-index:
8
+ - name: lora-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ base_model: meta-llama/Meta-Llama-3-8B
21
+ model_type: LlamaForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+
24
+ load_in_8bit: true
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: kloodia/raw_physic
30
+ type: oasst
31
+ dataset_prepared_path:
32
+ val_set_size: 0.05
33
+ output_dir: ./lora-out
34
+
35
+ sequence_len: 4096
36
+ sample_packing: true
37
+ pad_to_sequence_len: true
38
+
39
+ adapter: lora
40
+ lora_model_dir:
41
+ lora_r: 32
42
+ lora_alpha: 16
43
+ lora_dropout: 0.05
44
+ lora_target_linear: true
45
+ lora_fan_in_fan_out:
46
+
47
+ wandb_project:
48
+ wandb_entity:
49
+ wandb_watch:
50
+ wandb_name:
51
+ wandb_log_model:
52
+
53
+ gradient_accumulation_steps: 4
54
+ micro_batch_size: 1
55
+ num_epochs: 4
56
+ optimizer: adamw_bnb_8bit
57
+ lr_scheduler: cosine
58
+ learning_rate: 0.0002
59
+
60
+ train_on_inputs: false
61
+ group_by_length: false
62
+ bf16: auto
63
+ fp16:
64
+ tf32: false
65
+
66
+ gradient_checkpointing: true
67
+ early_stopping_patience:
68
+ resume_from_checkpoint:
69
+ local_rank:
70
+ logging_steps: 1
71
+ xformers_attention:
72
+ flash_attention: true
73
+ s2_attention:
74
+
75
+ warmup_steps: 10
76
+ evals_per_epoch: 4
77
+ eval_table_size:
78
+ eval_max_new_tokens: 128
79
+ saves_per_epoch: 1
80
+ debug:
81
+ deepspeed:
82
+ weight_decay: 0.0
83
+ fsdp:
84
+ fsdp_config:
85
+ special_tokens:
86
+ pad_token: <|end_of_text|>
87
+
88
+ ```
89
+
90
+ </details><br>
91
+
92
+ # lora-out
93
+
94
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
95
+ It achieves the following results on the evaluation set:
96
+ - Loss: 0.5060
97
+
98
+ ## Model description
99
+
100
+ More information needed
101
+
102
+ ## Intended uses & limitations
103
+
104
+ More information needed
105
+
106
+ ## Training and evaluation data
107
+
108
+ More information needed
109
+
110
+ ## Training procedure
111
+
112
+ ### Training hyperparameters
113
+
114
+ The following hyperparameters were used during training:
115
+ - learning_rate: 0.0002
116
+ - train_batch_size: 1
117
+ - eval_batch_size: 1
118
+ - seed: 42
119
+ - distributed_type: multi-GPU
120
+ - num_devices: 4
121
+ - gradient_accumulation_steps: 4
122
+ - total_train_batch_size: 16
123
+ - total_eval_batch_size: 4
124
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
125
+ - lr_scheduler_type: cosine
126
+ - lr_scheduler_warmup_steps: 10
127
+ - num_epochs: 4
128
+
129
+ ### Training results
130
+
131
+ | Training Loss | Epoch | Step | Validation Loss |
132
+ |:-------------:|:-----:|:----:|:---------------:|
133
+ | 0.641 | 0.01 | 1 | 0.6417 |
134
+ | 0.5093 | 0.25 | 42 | 0.5260 |
135
+ | 0.4665 | 0.5 | 84 | 0.5118 |
136
+ | 0.4431 | 0.75 | 126 | 0.5043 |
137
+ | 0.4523 | 1.0 | 168 | 0.4985 |
138
+ | 0.4237 | 1.23 | 210 | 0.4985 |
139
+ | 0.4002 | 1.48 | 252 | 0.4976 |
140
+ | 0.3656 | 1.73 | 294 | 0.4955 |
141
+ | 0.3744 | 1.98 | 336 | 0.4942 |
142
+ | 0.3278 | 2.21 | 378 | 0.5012 |
143
+ | 0.344 | 2.46 | 420 | 0.5003 |
144
+ | 0.3216 | 2.71 | 462 | 0.4984 |
145
+ | 0.3371 | 2.96 | 504 | 0.4980 |
146
+ | 0.3243 | 3.19 | 546 | 0.5051 |
147
+ | 0.3184 | 3.44 | 588 | 0.5052 |
148
+ | 0.313 | 3.69 | 630 | 0.5060 |
149
+ | 0.3097 | 3.94 | 672 | 0.5060 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - PEFT 0.10.0
155
+ - Transformers 4.40.0.dev0
156
+ - Pytorch 2.1.2+cu118
157
+ - Datasets 2.15.0
158
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39594e018232eea839d875abb7cf0c016f248f746138eae8b3941d0ed822ad6
3
+ size 335706186
checkpoint-168/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.10.0
checkpoint-168/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-168/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f662fdee8ba25294e3716676018092b8ba0a767e67f02dae288f4ac2628023f
3
+ size 335604696
checkpoint-168/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac1a54617baa3cba24651fd787498e1f5829756cac9e069de6e754e579477dd
3
+ size 168624724
checkpoint-168/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d845548623bea25c8a5f5469cc92866d5116ef64cd129c46199d476564fb5f6c
3
+ size 15024
checkpoint-168/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa7a2c9f68943d771201e61370a572c49184ccff1a53c77ab8758fa0bded89b
3
+ size 15024
checkpoint-168/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779e9d2d68d7b099b7379a93815d6ce97b2d0c7b1cbdb066d316ced7b37c4a01
3
+ size 15024
checkpoint-168/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e9cf5911ed3718ae6c8f8ed0d6cbed3c1e9ee7ee0cce5c3710a840b8d0a858
3
+ size 15024
checkpoint-168/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5692456911a4200a9874d8a5352ce1471b4fcc042a815c644258ca150b926f24
3
+ size 1064
checkpoint-168/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-168/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-168/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-168/trainer_state.json ADDED
@@ -0,0 +1,1237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9970326409495549,
5
+ "eval_steps": 42,
6
+ "global_step": 168,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.0981353223323822,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.641,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "eval_loss": 0.6416735053062439,
21
+ "eval_runtime": 21.4326,
22
+ "eval_samples_per_second": 46.331,
23
+ "eval_steps_per_second": 11.618,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.01,
28
+ "grad_norm": 0.09748291969299316,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.6396,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02,
35
+ "grad_norm": 0.09947647899389267,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.6397,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "grad_norm": 0.09976381808519363,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.6371,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "grad_norm": 0.10493721067905426,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.6491,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.04,
56
+ "grad_norm": 0.1144007071852684,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.6218,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.04,
63
+ "grad_norm": 0.08536222577095032,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.6177,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.05,
70
+ "grad_norm": 0.11926598846912384,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.5861,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.05,
77
+ "grad_norm": 0.15648387372493744,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.6006,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.06,
84
+ "grad_norm": 0.12172720581293106,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.5845,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.07,
91
+ "grad_norm": 0.09348208457231522,
92
+ "learning_rate": 0.0001999988739622358,
93
+ "loss": 0.5471,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.07,
98
+ "grad_norm": 0.07471276819705963,
99
+ "learning_rate": 0.00019999549587430254,
100
+ "loss": 0.578,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.08,
105
+ "grad_norm": 0.07200929522514343,
106
+ "learning_rate": 0.00019998986581227718,
107
+ "loss": 0.5328,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.08,
112
+ "grad_norm": 0.07460763305425644,
113
+ "learning_rate": 0.000199981983902953,
114
+ "loss": 0.5651,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.09,
119
+ "grad_norm": 0.07441641390323639,
120
+ "learning_rate": 0.00019997185032383664,
121
+ "loss": 0.5589,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.09,
126
+ "grad_norm": 0.07513019442558289,
127
+ "learning_rate": 0.00019995946530314385,
128
+ "loss": 0.5736,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.1,
133
+ "grad_norm": 0.06902395933866501,
134
+ "learning_rate": 0.00019994482911979468,
135
+ "loss": 0.556,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.11,
140
+ "grad_norm": 0.07314619421958923,
141
+ "learning_rate": 0.00019992794210340706,
142
+ "loss": 0.5469,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.11,
147
+ "grad_norm": 0.06833848357200623,
148
+ "learning_rate": 0.00019990880463428937,
149
+ "loss": 0.5448,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.12,
154
+ "grad_norm": 0.07301248610019684,
155
+ "learning_rate": 0.00019988741714343177,
156
+ "loss": 0.5612,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.12,
161
+ "grad_norm": 0.07063400000333786,
162
+ "learning_rate": 0.0001998637801124968,
163
+ "loss": 0.5446,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.13,
168
+ "grad_norm": 0.06935883313417435,
169
+ "learning_rate": 0.00019983789407380828,
170
+ "loss": 0.5223,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.14,
175
+ "grad_norm": 0.06576420366764069,
176
+ "learning_rate": 0.00019980975961033924,
177
+ "loss": 0.5351,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.14,
182
+ "grad_norm": 0.07276671379804611,
183
+ "learning_rate": 0.00019977937735569915,
184
+ "loss": 0.5423,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.15,
189
+ "grad_norm": 0.0756976306438446,
190
+ "learning_rate": 0.00019974674799411925,
191
+ "loss": 0.5344,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.15,
196
+ "grad_norm": 0.06945928931236267,
197
+ "learning_rate": 0.00019971187226043745,
198
+ "loss": 0.5198,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.16,
203
+ "grad_norm": 0.06587155908346176,
204
+ "learning_rate": 0.0001996747509400816,
205
+ "loss": 0.5175,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.17,
210
+ "grad_norm": 0.0752682164311409,
211
+ "learning_rate": 0.0001996353848690519,
212
+ "loss": 0.5068,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.17,
217
+ "grad_norm": 0.0740601122379303,
218
+ "learning_rate": 0.00019959377493390196,
219
+ "loss": 0.535,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.18,
224
+ "grad_norm": 0.07076304405927658,
225
+ "learning_rate": 0.00019954992207171898,
226
+ "loss": 0.5079,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.18,
231
+ "grad_norm": 0.0776033028960228,
232
+ "learning_rate": 0.00019950382727010254,
233
+ "loss": 0.5124,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.19,
238
+ "grad_norm": 0.0779872015118599,
239
+ "learning_rate": 0.00019945549156714234,
240
+ "loss": 0.5146,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.2,
245
+ "grad_norm": 0.08037945628166199,
246
+ "learning_rate": 0.00019940491605139498,
247
+ "loss": 0.5189,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.2,
252
+ "grad_norm": 0.06880298256874084,
253
+ "learning_rate": 0.0001993521018618592,
254
+ "loss": 0.506,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.21,
259
+ "grad_norm": 0.0755767747759819,
260
+ "learning_rate": 0.00019929705018795053,
261
+ "loss": 0.4997,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.21,
266
+ "grad_norm": 0.07505559921264648,
267
+ "learning_rate": 0.00019923976226947417,
268
+ "loss": 0.502,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.22,
273
+ "grad_norm": 0.07533205300569534,
274
+ "learning_rate": 0.00019918023939659733,
275
+ "loss": 0.5093,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.23,
280
+ "grad_norm": 0.0748637244105339,
281
+ "learning_rate": 0.0001991184829098201,
282
+ "loss": 0.4976,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.23,
287
+ "grad_norm": 0.076931431889534,
288
+ "learning_rate": 0.00019905449419994518,
289
+ "loss": 0.4992,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.24,
294
+ "grad_norm": 0.07511387020349503,
295
+ "learning_rate": 0.0001989882747080466,
296
+ "loss": 0.5069,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.24,
301
+ "grad_norm": 0.0723625123500824,
302
+ "learning_rate": 0.00019891982592543746,
303
+ "loss": 0.4952,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.25,
308
+ "grad_norm": 0.07320375740528107,
309
+ "learning_rate": 0.00019884914939363588,
310
+ "loss": 0.5093,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.25,
315
+ "eval_loss": 0.5259941220283508,
316
+ "eval_runtime": 21.4684,
317
+ "eval_samples_per_second": 46.254,
318
+ "eval_steps_per_second": 11.598,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.26,
323
+ "grad_norm": 0.07251272350549698,
324
+ "learning_rate": 0.00019877624670433086,
325
+ "loss": 0.4931,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.26,
330
+ "grad_norm": 0.07731667906045914,
331
+ "learning_rate": 0.00019870111949934599,
332
+ "loss": 0.4879,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.27,
337
+ "grad_norm": 0.074358269572258,
338
+ "learning_rate": 0.00019862376947060264,
339
+ "loss": 0.5049,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.27,
344
+ "grad_norm": 0.0808371901512146,
345
+ "learning_rate": 0.0001985441983600819,
346
+ "loss": 0.517,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.28,
351
+ "grad_norm": 0.07559769600629807,
352
+ "learning_rate": 0.00019846240795978528,
353
+ "loss": 0.4834,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.28,
358
+ "grad_norm": 0.07425505667924881,
359
+ "learning_rate": 0.00019837840011169438,
360
+ "loss": 0.5138,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.29,
365
+ "grad_norm": 0.07782939821481705,
366
+ "learning_rate": 0.00019829217670772935,
367
+ "loss": 0.4858,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.3,
372
+ "grad_norm": 0.0754002034664154,
373
+ "learning_rate": 0.00019820373968970642,
374
+ "loss": 0.4941,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3,
379
+ "grad_norm": 0.07364428788423538,
380
+ "learning_rate": 0.000198113091049294,
381
+ "loss": 0.4835,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.31,
386
+ "grad_norm": 0.08309967815876007,
387
+ "learning_rate": 0.00019802023282796796,
388
+ "loss": 0.5237,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.31,
393
+ "grad_norm": 0.07548778504133224,
394
+ "learning_rate": 0.00019792516711696556,
395
+ "loss": 0.4923,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.32,
400
+ "grad_norm": 0.07607278972864151,
401
+ "learning_rate": 0.0001978278960572384,
402
+ "loss": 0.4971,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.33,
407
+ "grad_norm": 0.07432844489812851,
408
+ "learning_rate": 0.00019772842183940422,
409
+ "loss": 0.4874,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.33,
414
+ "grad_norm": 0.077260322868824,
415
+ "learning_rate": 0.00019762674670369755,
416
+ "loss": 0.5067,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.34,
421
+ "grad_norm": 0.08594146370887756,
422
+ "learning_rate": 0.00019752287293991927,
423
+ "loss": 0.4804,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.34,
428
+ "grad_norm": 0.075816310942173,
429
+ "learning_rate": 0.00019741680288738492,
430
+ "loss": 0.4738,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.35,
435
+ "grad_norm": 0.07784326374530792,
436
+ "learning_rate": 0.00019730853893487228,
437
+ "loss": 0.4768,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.36,
442
+ "grad_norm": 0.08903329074382782,
443
+ "learning_rate": 0.00019719808352056724,
444
+ "loss": 0.4773,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.36,
449
+ "grad_norm": 0.07911587506532669,
450
+ "learning_rate": 0.00019708543913200924,
451
+ "loss": 0.4672,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.37,
456
+ "grad_norm": 0.07881385087966919,
457
+ "learning_rate": 0.00019697060830603494,
458
+ "loss": 0.4824,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.37,
463
+ "grad_norm": 0.08292945474386215,
464
+ "learning_rate": 0.00019685359362872125,
465
+ "loss": 0.4814,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.38,
470
+ "grad_norm": 0.08237861096858978,
471
+ "learning_rate": 0.00019673439773532713,
472
+ "loss": 0.486,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.39,
477
+ "grad_norm": 0.07958442717790604,
478
+ "learning_rate": 0.0001966130233102341,
479
+ "loss": 0.4913,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.39,
484
+ "grad_norm": 0.07969169318675995,
485
+ "learning_rate": 0.00019648947308688593,
486
+ "loss": 0.4781,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4,
491
+ "grad_norm": 0.08310563862323761,
492
+ "learning_rate": 0.00019636374984772692,
493
+ "loss": 0.4811,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4,
498
+ "grad_norm": 0.07763976603746414,
499
+ "learning_rate": 0.00019623585642413938,
500
+ "loss": 0.4809,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.41,
505
+ "grad_norm": 0.0927213802933693,
506
+ "learning_rate": 0.00019610579569637982,
507
+ "loss": 0.5019,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.42,
512
+ "grad_norm": 0.08405344933271408,
513
+ "learning_rate": 0.000195973570593514,
514
+ "loss": 0.5001,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.42,
519
+ "grad_norm": 0.07862479984760284,
520
+ "learning_rate": 0.0001958391840933512,
521
+ "loss": 0.4894,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.43,
526
+ "grad_norm": 0.07815296947956085,
527
+ "learning_rate": 0.00019570263922237687,
528
+ "loss": 0.4676,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.43,
533
+ "grad_norm": 0.07999672740697861,
534
+ "learning_rate": 0.00019556393905568458,
535
+ "loss": 0.4857,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.44,
540
+ "grad_norm": 0.08266247063875198,
541
+ "learning_rate": 0.0001954230867169069,
542
+ "loss": 0.4842,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.45,
547
+ "grad_norm": 0.08117777854204178,
548
+ "learning_rate": 0.00019528008537814486,
549
+ "loss": 0.4602,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.45,
554
+ "grad_norm": 0.08203484117984772,
555
+ "learning_rate": 0.00019513493825989664,
556
+ "loss": 0.4761,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.46,
561
+ "grad_norm": 0.07647153735160828,
562
+ "learning_rate": 0.00019498764863098495,
563
+ "loss": 0.4839,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.46,
568
+ "grad_norm": 0.0811714455485344,
569
+ "learning_rate": 0.00019483821980848347,
570
+ "loss": 0.4803,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.47,
575
+ "grad_norm": 0.08266978710889816,
576
+ "learning_rate": 0.00019468665515764215,
577
+ "loss": 0.4665,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.47,
582
+ "grad_norm": 0.07869689911603928,
583
+ "learning_rate": 0.00019453295809181143,
584
+ "loss": 0.4857,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.48,
589
+ "grad_norm": 0.08934654295444489,
590
+ "learning_rate": 0.00019437713207236525,
591
+ "loss": 0.4825,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.49,
596
+ "grad_norm": 0.07842836529016495,
597
+ "learning_rate": 0.00019421918060862333,
598
+ "loss": 0.4609,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.49,
603
+ "grad_norm": 0.08244986832141876,
604
+ "learning_rate": 0.0001940591072577719,
605
+ "loss": 0.4688,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5,
610
+ "grad_norm": 0.07819854468107224,
611
+ "learning_rate": 0.00019389691562478374,
612
+ "loss": 0.4665,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5,
617
+ "eval_loss": 0.5117939114570618,
618
+ "eval_runtime": 21.4742,
619
+ "eval_samples_per_second": 46.242,
620
+ "eval_steps_per_second": 11.595,
621
+ "step": 84
622
+ },
623
+ {
624
+ "epoch": 0.5,
625
+ "grad_norm": 0.0837428942322731,
626
+ "learning_rate": 0.0001937326093623369,
627
+ "loss": 0.4952,
628
+ "step": 85
629
+ },
630
+ {
631
+ "epoch": 0.51,
632
+ "grad_norm": 0.07781701534986496,
633
+ "learning_rate": 0.00019356619217073253,
634
+ "loss": 0.467,
635
+ "step": 86
636
+ },
637
+ {
638
+ "epoch": 0.52,
639
+ "grad_norm": 0.08447270840406418,
640
+ "learning_rate": 0.00019339766779781145,
641
+ "loss": 0.4838,
642
+ "step": 87
643
+ },
644
+ {
645
+ "epoch": 0.52,
646
+ "grad_norm": 0.08231997489929199,
647
+ "learning_rate": 0.00019322704003886987,
648
+ "loss": 0.4611,
649
+ "step": 88
650
+ },
651
+ {
652
+ "epoch": 0.53,
653
+ "grad_norm": 0.08507382869720459,
654
+ "learning_rate": 0.00019305431273657374,
655
+ "loss": 0.4757,
656
+ "step": 89
657
+ },
658
+ {
659
+ "epoch": 0.53,
660
+ "grad_norm": 0.08521989732980728,
661
+ "learning_rate": 0.0001928794897808724,
662
+ "loss": 0.4854,
663
+ "step": 90
664
+ },
665
+ {
666
+ "epoch": 0.54,
667
+ "grad_norm": 0.0963786169886589,
668
+ "learning_rate": 0.00019270257510891082,
669
+ "loss": 0.4505,
670
+ "step": 91
671
+ },
672
+ {
673
+ "epoch": 0.55,
674
+ "grad_norm": 0.08671442419290543,
675
+ "learning_rate": 0.0001925235727049411,
676
+ "loss": 0.4766,
677
+ "step": 92
678
+ },
679
+ {
680
+ "epoch": 0.55,
681
+ "grad_norm": 0.09087081998586655,
682
+ "learning_rate": 0.0001923424866002325,
683
+ "loss": 0.4966,
684
+ "step": 93
685
+ },
686
+ {
687
+ "epoch": 0.56,
688
+ "grad_norm": 0.07899381965398788,
689
+ "learning_rate": 0.00019215932087298092,
690
+ "loss": 0.4638,
691
+ "step": 94
692
+ },
693
+ {
694
+ "epoch": 0.56,
695
+ "grad_norm": 0.09070860594511032,
696
+ "learning_rate": 0.00019197407964821684,
697
+ "loss": 0.4847,
698
+ "step": 95
699
+ },
700
+ {
701
+ "epoch": 0.57,
702
+ "grad_norm": 0.0885949656367302,
703
+ "learning_rate": 0.00019178676709771258,
704
+ "loss": 0.4648,
705
+ "step": 96
706
+ },
707
+ {
708
+ "epoch": 0.58,
709
+ "grad_norm": 0.09253839403390884,
710
+ "learning_rate": 0.00019159738743988825,
711
+ "loss": 0.459,
712
+ "step": 97
713
+ },
714
+ {
715
+ "epoch": 0.58,
716
+ "grad_norm": 0.08571318536996841,
717
+ "learning_rate": 0.00019140594493971674,
718
+ "loss": 0.4797,
719
+ "step": 98
720
+ },
721
+ {
722
+ "epoch": 0.59,
723
+ "grad_norm": 0.07787954807281494,
724
+ "learning_rate": 0.0001912124439086278,
725
+ "loss": 0.4547,
726
+ "step": 99
727
+ },
728
+ {
729
+ "epoch": 0.59,
730
+ "grad_norm": 0.08822935819625854,
731
+ "learning_rate": 0.00019101688870441078,
732
+ "loss": 0.4511,
733
+ "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6,
737
+ "grad_norm": 0.08409956842660904,
738
+ "learning_rate": 0.0001908192837311166,
739
+ "loss": 0.4631,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.61,
744
+ "grad_norm": 0.08279416710138321,
745
+ "learning_rate": 0.00019061963343895846,
746
+ "loss": 0.4696,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.61,
751
+ "grad_norm": 0.09696204960346222,
752
+ "learning_rate": 0.00019041794232421176,
753
+ "loss": 0.4862,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.62,
758
+ "grad_norm": 0.08494329452514648,
759
+ "learning_rate": 0.00019021421492911272,
760
+ "loss": 0.4557,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.62,
765
+ "grad_norm": 0.08702557533979416,
766
+ "learning_rate": 0.00019000845584175616,
767
+ "loss": 0.4693,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.63,
772
+ "grad_norm": 0.09048158675432205,
773
+ "learning_rate": 0.00018980066969599216,
774
+ "loss": 0.4714,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.64,
779
+ "grad_norm": 0.08462114632129669,
780
+ "learning_rate": 0.0001895908611713216,
781
+ "loss": 0.4632,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.64,
786
+ "grad_norm": 0.09956546127796173,
787
+ "learning_rate": 0.00018937903499279102,
788
+ "loss": 0.4638,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.65,
793
+ "grad_norm": 0.08630617707967758,
794
+ "learning_rate": 0.00018916519593088584,
795
+ "loss": 0.4499,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.65,
800
+ "grad_norm": 0.08207620680332184,
801
+ "learning_rate": 0.0001889493488014233,
802
+ "loss": 0.4603,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.66,
807
+ "grad_norm": 0.08473565429449081,
808
+ "learning_rate": 0.00018873149846544376,
809
+ "loss": 0.4571,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.66,
814
+ "grad_norm": 0.08818928152322769,
815
+ "learning_rate": 0.00018851164982910135,
816
+ "loss": 0.4489,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.67,
821
+ "grad_norm": 0.08116699010133743,
822
+ "learning_rate": 0.00018828980784355338,
823
+ "loss": 0.4578,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.68,
828
+ "grad_norm": 0.08832226693630219,
829
+ "learning_rate": 0.00018806597750484897,
830
+ "loss": 0.4719,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.68,
835
+ "grad_norm": 0.08624406903982162,
836
+ "learning_rate": 0.0001878401638538163,
837
+ "loss": 0.4628,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.69,
842
+ "grad_norm": 0.08936543017625809,
843
+ "learning_rate": 0.00018761237197594945,
844
+ "loss": 0.4533,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.69,
849
+ "grad_norm": 0.08579661697149277,
850
+ "learning_rate": 0.00018738260700129354,
851
+ "loss": 0.4772,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7,
856
+ "grad_norm": 0.08271288126707077,
857
+ "learning_rate": 0.0001871508741043293,
858
+ "loss": 0.4773,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.71,
863
+ "grad_norm": 0.08224964886903763,
864
+ "learning_rate": 0.0001869171785038566,
865
+ "loss": 0.4635,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.71,
870
+ "grad_norm": 0.087012380361557,
871
+ "learning_rate": 0.00018668152546287686,
872
+ "loss": 0.4559,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.72,
877
+ "grad_norm": 0.08352699875831604,
878
+ "learning_rate": 0.00018644392028847458,
879
+ "loss": 0.4485,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.72,
884
+ "grad_norm": 0.08281444013118744,
885
+ "learning_rate": 0.00018620436833169772,
886
+ "loss": 0.4393,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.73,
891
+ "grad_norm": 0.08376545459032059,
892
+ "learning_rate": 0.00018596287498743732,
893
+ "loss": 0.4525,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.74,
898
+ "grad_norm": 0.08526434749364853,
899
+ "learning_rate": 0.0001857194456943058,
900
+ "loss": 0.4456,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.74,
905
+ "grad_norm": 0.08151934295892715,
906
+ "learning_rate": 0.0001854740859345148,
907
+ "loss": 0.4576,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.75,
912
+ "grad_norm": 0.08793777972459793,
913
+ "learning_rate": 0.0001852268012337514,
914
+ "loss": 0.4431,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.75,
919
+ "eval_loss": 0.5042669773101807,
920
+ "eval_runtime": 21.4592,
921
+ "eval_samples_per_second": 46.274,
922
+ "eval_steps_per_second": 11.603,
923
+ "step": 126
924
+ },
925
+ {
926
+ "epoch": 0.75,
927
+ "grad_norm": 0.08135095983743668,
928
+ "learning_rate": 0.00018497759716105377,
929
+ "loss": 0.4384,
930
+ "step": 127
931
+ },
932
+ {
933
+ "epoch": 0.76,
934
+ "grad_norm": 0.0917576476931572,
935
+ "learning_rate": 0.0001847264793286859,
936
+ "loss": 0.4687,
937
+ "step": 128
938
+ },
939
+ {
940
+ "epoch": 0.77,
941
+ "grad_norm": 0.08832691609859467,
942
+ "learning_rate": 0.00018447345339201102,
943
+ "loss": 0.4386,
944
+ "step": 129
945
+ },
946
+ {
947
+ "epoch": 0.77,
948
+ "grad_norm": 0.08340886980295181,
949
+ "learning_rate": 0.00018421852504936438,
950
+ "loss": 0.4512,
951
+ "step": 130
952
+ },
953
+ {
954
+ "epoch": 0.78,
955
+ "grad_norm": 0.08589499443769455,
956
+ "learning_rate": 0.00018396170004192475,
957
+ "loss": 0.4387,
958
+ "step": 131
959
+ },
960
+ {
961
+ "epoch": 0.78,
962
+ "grad_norm": 0.08753557503223419,
963
+ "learning_rate": 0.00018370298415358526,
964
+ "loss": 0.4615,
965
+ "step": 132
966
+ },
967
+ {
968
+ "epoch": 0.79,
969
+ "grad_norm": 0.08406232297420502,
970
+ "learning_rate": 0.00018344238321082315,
971
+ "loss": 0.4465,
972
+ "step": 133
973
+ },
974
+ {
975
+ "epoch": 0.8,
976
+ "grad_norm": 0.08514856547117233,
977
+ "learning_rate": 0.0001831799030825685,
978
+ "loss": 0.4516,
979
+ "step": 134
980
+ },
981
+ {
982
+ "epoch": 0.8,
983
+ "grad_norm": 0.09259331226348877,
984
+ "learning_rate": 0.000182915549680072,
985
+ "loss": 0.4387,
986
+ "step": 135
987
+ },
988
+ {
989
+ "epoch": 0.81,
990
+ "grad_norm": 0.08862275630235672,
991
+ "learning_rate": 0.00018264932895677193,
992
+ "loss": 0.4434,
993
+ "step": 136
994
+ },
995
+ {
996
+ "epoch": 0.81,
997
+ "grad_norm": 0.08515379577875137,
998
+ "learning_rate": 0.0001823812469081601,
999
+ "loss": 0.4425,
1000
+ "step": 137
1001
+ },
1002
+ {
1003
+ "epoch": 0.82,
1004
+ "grad_norm": 0.09041007608175278,
1005
+ "learning_rate": 0.00018211130957164668,
1006
+ "loss": 0.4607,
1007
+ "step": 138
1008
+ },
1009
+ {
1010
+ "epoch": 0.82,
1011
+ "grad_norm": 0.08312032371759415,
1012
+ "learning_rate": 0.0001818395230264244,
1013
+ "loss": 0.442,
1014
+ "step": 139
1015
+ },
1016
+ {
1017
+ "epoch": 0.83,
1018
+ "grad_norm": 0.08981412649154663,
1019
+ "learning_rate": 0.00018156589339333152,
1020
+ "loss": 0.4608,
1021
+ "step": 140
1022
+ },
1023
+ {
1024
+ "epoch": 0.84,
1025
+ "grad_norm": 0.08991118520498276,
1026
+ "learning_rate": 0.00018129042683471402,
1027
+ "loss": 0.451,
1028
+ "step": 141
1029
+ },
1030
+ {
1031
+ "epoch": 0.84,
1032
+ "grad_norm": 0.08628728240728378,
1033
+ "learning_rate": 0.00018101312955428692,
1034
+ "loss": 0.4453,
1035
+ "step": 142
1036
+ },
1037
+ {
1038
+ "epoch": 0.85,
1039
+ "grad_norm": 0.08730859309434891,
1040
+ "learning_rate": 0.00018073400779699435,
1041
+ "loss": 0.4485,
1042
+ "step": 143
1043
+ },
1044
+ {
1045
+ "epoch": 0.85,
1046
+ "grad_norm": 0.08489865809679031,
1047
+ "learning_rate": 0.0001804530678488691,
1048
+ "loss": 0.4592,
1049
+ "step": 144
1050
+ },
1051
+ {
1052
+ "epoch": 0.86,
1053
+ "grad_norm": 0.08439410477876663,
1054
+ "learning_rate": 0.00018017031603689102,
1055
+ "loss": 0.4326,
1056
+ "step": 145
1057
+ },
1058
+ {
1059
+ "epoch": 0.87,
1060
+ "grad_norm": 0.09346488118171692,
1061
+ "learning_rate": 0.0001798857587288445,
1062
+ "loss": 0.4484,
1063
+ "step": 146
1064
+ },
1065
+ {
1066
+ "epoch": 0.87,
1067
+ "grad_norm": 0.09130821377038956,
1068
+ "learning_rate": 0.00017959940233317498,
1069
+ "loss": 0.4502,
1070
+ "step": 147
1071
+ },
1072
+ {
1073
+ "epoch": 0.88,
1074
+ "grad_norm": 0.08846256881952286,
1075
+ "learning_rate": 0.0001793112532988448,
1076
+ "loss": 0.4322,
1077
+ "step": 148
1078
+ },
1079
+ {
1080
+ "epoch": 0.88,
1081
+ "grad_norm": 0.09061886370182037,
1082
+ "learning_rate": 0.00017902131811518786,
1083
+ "loss": 0.4437,
1084
+ "step": 149
1085
+ },
1086
+ {
1087
+ "epoch": 0.89,
1088
+ "grad_norm": 0.09259927272796631,
1089
+ "learning_rate": 0.00017872960331176345,
1090
+ "loss": 0.4545,
1091
+ "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.9,
1095
+ "grad_norm": 0.09632189571857452,
1096
+ "learning_rate": 0.00017843611545820926,
1097
+ "loss": 0.4515,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.9,
1102
+ "grad_norm": 0.08714065700769424,
1103
+ "learning_rate": 0.00017814086116409348,
1104
+ "loss": 0.4602,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.91,
1109
+ "grad_norm": 0.09537078440189362,
1110
+ "learning_rate": 0.00017784384707876576,
1111
+ "loss": 0.4482,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.91,
1116
+ "grad_norm": 0.09175322949886322,
1117
+ "learning_rate": 0.00017754507989120764,
1118
+ "loss": 0.4681,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.92,
1123
+ "grad_norm": 0.08962789177894592,
1124
+ "learning_rate": 0.00017724456632988187,
1125
+ "loss": 0.4304,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.93,
1130
+ "grad_norm": 0.09643880277872086,
1131
+ "learning_rate": 0.00017694231316258077,
1132
+ "loss": 0.4532,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.93,
1137
+ "grad_norm": 0.08335065096616745,
1138
+ "learning_rate": 0.00017663832719627402,
1139
+ "loss": 0.4504,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.94,
1144
+ "grad_norm": 0.087184838950634,
1145
+ "learning_rate": 0.0001763326152769551,
1146
+ "loss": 0.4752,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.94,
1151
+ "grad_norm": 0.08858635276556015,
1152
+ "learning_rate": 0.0001760251842894874,
1153
+ "loss": 0.4413,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.95,
1158
+ "grad_norm": 0.08101391792297363,
1159
+ "learning_rate": 0.00017571604115744892,
1160
+ "loss": 0.4465,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.96,
1165
+ "grad_norm": 0.08623132854700089,
1166
+ "learning_rate": 0.0001754051928429765,
1167
+ "loss": 0.4673,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.96,
1172
+ "grad_norm": 0.0922100692987442,
1173
+ "learning_rate": 0.00017509264634660895,
1174
+ "loss": 0.4587,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.97,
1179
+ "grad_norm": 0.08243449032306671,
1180
+ "learning_rate": 0.00017477840870712945,
1181
+ "loss": 0.4368,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.97,
1186
+ "grad_norm": 0.0845554992556572,
1187
+ "learning_rate": 0.00017446248700140693,
1188
+ "loss": 0.4209,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.98,
1193
+ "grad_norm": 0.08277452737092972,
1194
+ "learning_rate": 0.00017414488834423687,
1195
+ "loss": 0.4397,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.99,
1200
+ "grad_norm": 0.0826331302523613,
1201
+ "learning_rate": 0.00017382561988818086,
1202
+ "loss": 0.4333,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.99,
1207
+ "grad_norm": 0.08441821485757828,
1208
+ "learning_rate": 0.0001735046888234057,
1209
+ "loss": 0.4496,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 1.0,
1214
+ "grad_norm": 0.08665426075458527,
1215
+ "learning_rate": 0.00017318210237752136,
1216
+ "loss": 0.4523,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 1.0,
1221
+ "eval_loss": 0.4984985589981079,
1222
+ "eval_runtime": 21.4662,
1223
+ "eval_samples_per_second": 46.259,
1224
+ "eval_steps_per_second": 11.6,
1225
+ "step": 168
1226
+ }
1227
+ ],
1228
+ "logging_steps": 1,
1229
+ "max_steps": 672,
1230
+ "num_input_tokens_seen": 0,
1231
+ "num_train_epochs": 4,
1232
+ "save_steps": 168,
1233
+ "total_flos": 5.013190238546166e+17,
1234
+ "train_batch_size": 1,
1235
+ "trial_name": null,
1236
+ "trial_params": null
1237
+ }
checkpoint-168/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a2f0ef670d0281abf97e6b6a3c9043bd5509665b561215ad64107dc2e4edda
3
+ size 5752
checkpoint-336/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.10.0
checkpoint-336/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-336/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77bc34c48cf6e6ee55d139adad4e7acc7c40a4fd51937697cb6b75ea618bcd41
3
+ size 335604696
checkpoint-336/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043278a490f04262ff3e4e088b017c201430aecdc0cba051df9aaf1f78cedc3e
3
+ size 168625172
checkpoint-336/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aece1990495dd97d31cf17c7a276e7c3abfb9c7cb3bb939a1f7c8e9b6acf9c6d
3
+ size 15024
checkpoint-336/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac8fed5596c818372386f6e5e1fa26f2219086b955afb1d57cc2d9fe9f0900f
3
+ size 15024
checkpoint-336/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6dc2c730c981b20d372233a5e66b5adfb33ae059c0e08b99e397f7f25fddefb
3
+ size 15024
checkpoint-336/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b95557a9cb73274722d1d97ee4bbe9853a09c95dbc9f82283cbe6f32c102ed1
3
+ size 15024
checkpoint-336/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b6cdbafeabb8c06c9fd321b0a85b830ab62bbdbb356c28f295407965ec4de0
3
+ size 1064
checkpoint-336/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-336/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-336/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-336/trainer_state.json ADDED
@@ -0,0 +1,2445 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.979228486646884,
5
+ "eval_steps": 42,
6
+ "global_step": 336,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.0981353223323822,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.641,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "eval_loss": 0.6416735053062439,
21
+ "eval_runtime": 21.4326,
22
+ "eval_samples_per_second": 46.331,
23
+ "eval_steps_per_second": 11.618,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.01,
28
+ "grad_norm": 0.09748291969299316,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.6396,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02,
35
+ "grad_norm": 0.09947647899389267,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.6397,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "grad_norm": 0.09976381808519363,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.6371,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "grad_norm": 0.10493721067905426,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.6491,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.04,
56
+ "grad_norm": 0.1144007071852684,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.6218,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.04,
63
+ "grad_norm": 0.08536222577095032,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.6177,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.05,
70
+ "grad_norm": 0.11926598846912384,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.5861,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.05,
77
+ "grad_norm": 0.15648387372493744,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.6006,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.06,
84
+ "grad_norm": 0.12172720581293106,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.5845,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.07,
91
+ "grad_norm": 0.09348208457231522,
92
+ "learning_rate": 0.0001999988739622358,
93
+ "loss": 0.5471,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.07,
98
+ "grad_norm": 0.07471276819705963,
99
+ "learning_rate": 0.00019999549587430254,
100
+ "loss": 0.578,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.08,
105
+ "grad_norm": 0.07200929522514343,
106
+ "learning_rate": 0.00019998986581227718,
107
+ "loss": 0.5328,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.08,
112
+ "grad_norm": 0.07460763305425644,
113
+ "learning_rate": 0.000199981983902953,
114
+ "loss": 0.5651,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.09,
119
+ "grad_norm": 0.07441641390323639,
120
+ "learning_rate": 0.00019997185032383664,
121
+ "loss": 0.5589,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.09,
126
+ "grad_norm": 0.07513019442558289,
127
+ "learning_rate": 0.00019995946530314385,
128
+ "loss": 0.5736,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.1,
133
+ "grad_norm": 0.06902395933866501,
134
+ "learning_rate": 0.00019994482911979468,
135
+ "loss": 0.556,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.11,
140
+ "grad_norm": 0.07314619421958923,
141
+ "learning_rate": 0.00019992794210340706,
142
+ "loss": 0.5469,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.11,
147
+ "grad_norm": 0.06833848357200623,
148
+ "learning_rate": 0.00019990880463428937,
149
+ "loss": 0.5448,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.12,
154
+ "grad_norm": 0.07301248610019684,
155
+ "learning_rate": 0.00019988741714343177,
156
+ "loss": 0.5612,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.12,
161
+ "grad_norm": 0.07063400000333786,
162
+ "learning_rate": 0.0001998637801124968,
163
+ "loss": 0.5446,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.13,
168
+ "grad_norm": 0.06935883313417435,
169
+ "learning_rate": 0.00019983789407380828,
170
+ "loss": 0.5223,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.14,
175
+ "grad_norm": 0.06576420366764069,
176
+ "learning_rate": 0.00019980975961033924,
177
+ "loss": 0.5351,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.14,
182
+ "grad_norm": 0.07276671379804611,
183
+ "learning_rate": 0.00019977937735569915,
184
+ "loss": 0.5423,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.15,
189
+ "grad_norm": 0.0756976306438446,
190
+ "learning_rate": 0.00019974674799411925,
191
+ "loss": 0.5344,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.15,
196
+ "grad_norm": 0.06945928931236267,
197
+ "learning_rate": 0.00019971187226043745,
198
+ "loss": 0.5198,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.16,
203
+ "grad_norm": 0.06587155908346176,
204
+ "learning_rate": 0.0001996747509400816,
205
+ "loss": 0.5175,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.17,
210
+ "grad_norm": 0.0752682164311409,
211
+ "learning_rate": 0.0001996353848690519,
212
+ "loss": 0.5068,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.17,
217
+ "grad_norm": 0.0740601122379303,
218
+ "learning_rate": 0.00019959377493390196,
219
+ "loss": 0.535,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.18,
224
+ "grad_norm": 0.07076304405927658,
225
+ "learning_rate": 0.00019954992207171898,
226
+ "loss": 0.5079,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.18,
231
+ "grad_norm": 0.0776033028960228,
232
+ "learning_rate": 0.00019950382727010254,
233
+ "loss": 0.5124,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.19,
238
+ "grad_norm": 0.0779872015118599,
239
+ "learning_rate": 0.00019945549156714234,
240
+ "loss": 0.5146,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.2,
245
+ "grad_norm": 0.08037945628166199,
246
+ "learning_rate": 0.00019940491605139498,
247
+ "loss": 0.5189,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.2,
252
+ "grad_norm": 0.06880298256874084,
253
+ "learning_rate": 0.0001993521018618592,
254
+ "loss": 0.506,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.21,
259
+ "grad_norm": 0.0755767747759819,
260
+ "learning_rate": 0.00019929705018795053,
261
+ "loss": 0.4997,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.21,
266
+ "grad_norm": 0.07505559921264648,
267
+ "learning_rate": 0.00019923976226947417,
268
+ "loss": 0.502,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.22,
273
+ "grad_norm": 0.07533205300569534,
274
+ "learning_rate": 0.00019918023939659733,
275
+ "loss": 0.5093,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.23,
280
+ "grad_norm": 0.0748637244105339,
281
+ "learning_rate": 0.0001991184829098201,
282
+ "loss": 0.4976,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.23,
287
+ "grad_norm": 0.076931431889534,
288
+ "learning_rate": 0.00019905449419994518,
289
+ "loss": 0.4992,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.24,
294
+ "grad_norm": 0.07511387020349503,
295
+ "learning_rate": 0.0001989882747080466,
296
+ "loss": 0.5069,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.24,
301
+ "grad_norm": 0.0723625123500824,
302
+ "learning_rate": 0.00019891982592543746,
303
+ "loss": 0.4952,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.25,
308
+ "grad_norm": 0.07320375740528107,
309
+ "learning_rate": 0.00019884914939363588,
310
+ "loss": 0.5093,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.25,
315
+ "eval_loss": 0.5259941220283508,
316
+ "eval_runtime": 21.4684,
317
+ "eval_samples_per_second": 46.254,
318
+ "eval_steps_per_second": 11.598,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.26,
323
+ "grad_norm": 0.07251272350549698,
324
+ "learning_rate": 0.00019877624670433086,
325
+ "loss": 0.4931,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.26,
330
+ "grad_norm": 0.07731667906045914,
331
+ "learning_rate": 0.00019870111949934599,
332
+ "loss": 0.4879,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.27,
337
+ "grad_norm": 0.074358269572258,
338
+ "learning_rate": 0.00019862376947060264,
339
+ "loss": 0.5049,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.27,
344
+ "grad_norm": 0.0808371901512146,
345
+ "learning_rate": 0.0001985441983600819,
346
+ "loss": 0.517,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.28,
351
+ "grad_norm": 0.07559769600629807,
352
+ "learning_rate": 0.00019846240795978528,
353
+ "loss": 0.4834,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.28,
358
+ "grad_norm": 0.07425505667924881,
359
+ "learning_rate": 0.00019837840011169438,
360
+ "loss": 0.5138,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.29,
365
+ "grad_norm": 0.07782939821481705,
366
+ "learning_rate": 0.00019829217670772935,
367
+ "loss": 0.4858,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.3,
372
+ "grad_norm": 0.0754002034664154,
373
+ "learning_rate": 0.00019820373968970642,
374
+ "loss": 0.4941,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3,
379
+ "grad_norm": 0.07364428788423538,
380
+ "learning_rate": 0.000198113091049294,
381
+ "loss": 0.4835,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.31,
386
+ "grad_norm": 0.08309967815876007,
387
+ "learning_rate": 0.00019802023282796796,
388
+ "loss": 0.5237,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.31,
393
+ "grad_norm": 0.07548778504133224,
394
+ "learning_rate": 0.00019792516711696556,
395
+ "loss": 0.4923,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.32,
400
+ "grad_norm": 0.07607278972864151,
401
+ "learning_rate": 0.0001978278960572384,
402
+ "loss": 0.4971,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.33,
407
+ "grad_norm": 0.07432844489812851,
408
+ "learning_rate": 0.00019772842183940422,
409
+ "loss": 0.4874,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.33,
414
+ "grad_norm": 0.077260322868824,
415
+ "learning_rate": 0.00019762674670369755,
416
+ "loss": 0.5067,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.34,
421
+ "grad_norm": 0.08594146370887756,
422
+ "learning_rate": 0.00019752287293991927,
423
+ "loss": 0.4804,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.34,
428
+ "grad_norm": 0.075816310942173,
429
+ "learning_rate": 0.00019741680288738492,
430
+ "loss": 0.4738,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.35,
435
+ "grad_norm": 0.07784326374530792,
436
+ "learning_rate": 0.00019730853893487228,
437
+ "loss": 0.4768,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.36,
442
+ "grad_norm": 0.08903329074382782,
443
+ "learning_rate": 0.00019719808352056724,
444
+ "loss": 0.4773,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.36,
449
+ "grad_norm": 0.07911587506532669,
450
+ "learning_rate": 0.00019708543913200924,
451
+ "loss": 0.4672,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.37,
456
+ "grad_norm": 0.07881385087966919,
457
+ "learning_rate": 0.00019697060830603494,
458
+ "loss": 0.4824,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.37,
463
+ "grad_norm": 0.08292945474386215,
464
+ "learning_rate": 0.00019685359362872125,
465
+ "loss": 0.4814,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.38,
470
+ "grad_norm": 0.08237861096858978,
471
+ "learning_rate": 0.00019673439773532713,
472
+ "loss": 0.486,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.39,
477
+ "grad_norm": 0.07958442717790604,
478
+ "learning_rate": 0.0001966130233102341,
479
+ "loss": 0.4913,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.39,
484
+ "grad_norm": 0.07969169318675995,
485
+ "learning_rate": 0.00019648947308688593,
486
+ "loss": 0.4781,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4,
491
+ "grad_norm": 0.08310563862323761,
492
+ "learning_rate": 0.00019636374984772692,
493
+ "loss": 0.4811,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4,
498
+ "grad_norm": 0.07763976603746414,
499
+ "learning_rate": 0.00019623585642413938,
500
+ "loss": 0.4809,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.41,
505
+ "grad_norm": 0.0927213802933693,
506
+ "learning_rate": 0.00019610579569637982,
507
+ "loss": 0.5019,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.42,
512
+ "grad_norm": 0.08405344933271408,
513
+ "learning_rate": 0.000195973570593514,
514
+ "loss": 0.5001,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.42,
519
+ "grad_norm": 0.07862479984760284,
520
+ "learning_rate": 0.0001958391840933512,
521
+ "loss": 0.4894,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.43,
526
+ "grad_norm": 0.07815296947956085,
527
+ "learning_rate": 0.00019570263922237687,
528
+ "loss": 0.4676,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.43,
533
+ "grad_norm": 0.07999672740697861,
534
+ "learning_rate": 0.00019556393905568458,
535
+ "loss": 0.4857,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.44,
540
+ "grad_norm": 0.08266247063875198,
541
+ "learning_rate": 0.0001954230867169069,
542
+ "loss": 0.4842,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.45,
547
+ "grad_norm": 0.08117777854204178,
548
+ "learning_rate": 0.00019528008537814486,
549
+ "loss": 0.4602,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.45,
554
+ "grad_norm": 0.08203484117984772,
555
+ "learning_rate": 0.00019513493825989664,
556
+ "loss": 0.4761,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.46,
561
+ "grad_norm": 0.07647153735160828,
562
+ "learning_rate": 0.00019498764863098495,
563
+ "loss": 0.4839,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.46,
568
+ "grad_norm": 0.0811714455485344,
569
+ "learning_rate": 0.00019483821980848347,
570
+ "loss": 0.4803,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.47,
575
+ "grad_norm": 0.08266978710889816,
576
+ "learning_rate": 0.00019468665515764215,
577
+ "loss": 0.4665,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.47,
582
+ "grad_norm": 0.07869689911603928,
583
+ "learning_rate": 0.00019453295809181143,
584
+ "loss": 0.4857,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.48,
589
+ "grad_norm": 0.08934654295444489,
590
+ "learning_rate": 0.00019437713207236525,
591
+ "loss": 0.4825,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.49,
596
+ "grad_norm": 0.07842836529016495,
597
+ "learning_rate": 0.00019421918060862333,
598
+ "loss": 0.4609,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.49,
603
+ "grad_norm": 0.08244986832141876,
604
+ "learning_rate": 0.0001940591072577719,
605
+ "loss": 0.4688,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5,
610
+ "grad_norm": 0.07819854468107224,
611
+ "learning_rate": 0.00019389691562478374,
612
+ "loss": 0.4665,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5,
617
+ "eval_loss": 0.5117939114570618,
618
+ "eval_runtime": 21.4742,
619
+ "eval_samples_per_second": 46.242,
620
+ "eval_steps_per_second": 11.595,
621
+ "step": 84
622
+ },
623
+ {
624
+ "epoch": 0.5,
625
+ "grad_norm": 0.0837428942322731,
626
+ "learning_rate": 0.0001937326093623369,
627
+ "loss": 0.4952,
628
+ "step": 85
629
+ },
630
+ {
631
+ "epoch": 0.51,
632
+ "grad_norm": 0.07781701534986496,
633
+ "learning_rate": 0.00019356619217073253,
634
+ "loss": 0.467,
635
+ "step": 86
636
+ },
637
+ {
638
+ "epoch": 0.52,
639
+ "grad_norm": 0.08447270840406418,
640
+ "learning_rate": 0.00019339766779781145,
641
+ "loss": 0.4838,
642
+ "step": 87
643
+ },
644
+ {
645
+ "epoch": 0.52,
646
+ "grad_norm": 0.08231997489929199,
647
+ "learning_rate": 0.00019322704003886987,
648
+ "loss": 0.4611,
649
+ "step": 88
650
+ },
651
+ {
652
+ "epoch": 0.53,
653
+ "grad_norm": 0.08507382869720459,
654
+ "learning_rate": 0.00019305431273657374,
655
+ "loss": 0.4757,
656
+ "step": 89
657
+ },
658
+ {
659
+ "epoch": 0.53,
660
+ "grad_norm": 0.08521989732980728,
661
+ "learning_rate": 0.0001928794897808724,
662
+ "loss": 0.4854,
663
+ "step": 90
664
+ },
665
+ {
666
+ "epoch": 0.54,
667
+ "grad_norm": 0.0963786169886589,
668
+ "learning_rate": 0.00019270257510891082,
669
+ "loss": 0.4505,
670
+ "step": 91
671
+ },
672
+ {
673
+ "epoch": 0.55,
674
+ "grad_norm": 0.08671442419290543,
675
+ "learning_rate": 0.0001925235727049411,
676
+ "loss": 0.4766,
677
+ "step": 92
678
+ },
679
+ {
680
+ "epoch": 0.55,
681
+ "grad_norm": 0.09087081998586655,
682
+ "learning_rate": 0.0001923424866002325,
683
+ "loss": 0.4966,
684
+ "step": 93
685
+ },
686
+ {
687
+ "epoch": 0.56,
688
+ "grad_norm": 0.07899381965398788,
689
+ "learning_rate": 0.00019215932087298092,
690
+ "loss": 0.4638,
691
+ "step": 94
692
+ },
693
+ {
694
+ "epoch": 0.56,
695
+ "grad_norm": 0.09070860594511032,
696
+ "learning_rate": 0.00019197407964821684,
697
+ "loss": 0.4847,
698
+ "step": 95
699
+ },
700
+ {
701
+ "epoch": 0.57,
702
+ "grad_norm": 0.0885949656367302,
703
+ "learning_rate": 0.00019178676709771258,
704
+ "loss": 0.4648,
705
+ "step": 96
706
+ },
707
+ {
708
+ "epoch": 0.58,
709
+ "grad_norm": 0.09253839403390884,
710
+ "learning_rate": 0.00019159738743988825,
711
+ "loss": 0.459,
712
+ "step": 97
713
+ },
714
+ {
715
+ "epoch": 0.58,
716
+ "grad_norm": 0.08571318536996841,
717
+ "learning_rate": 0.00019140594493971674,
718
+ "loss": 0.4797,
719
+ "step": 98
720
+ },
721
+ {
722
+ "epoch": 0.59,
723
+ "grad_norm": 0.07787954807281494,
724
+ "learning_rate": 0.0001912124439086278,
725
+ "loss": 0.4547,
726
+ "step": 99
727
+ },
728
+ {
729
+ "epoch": 0.59,
730
+ "grad_norm": 0.08822935819625854,
731
+ "learning_rate": 0.00019101688870441078,
732
+ "loss": 0.4511,
733
+ "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6,
737
+ "grad_norm": 0.08409956842660904,
738
+ "learning_rate": 0.0001908192837311166,
739
+ "loss": 0.4631,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.61,
744
+ "grad_norm": 0.08279416710138321,
745
+ "learning_rate": 0.00019061963343895846,
746
+ "loss": 0.4696,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.61,
751
+ "grad_norm": 0.09696204960346222,
752
+ "learning_rate": 0.00019041794232421176,
753
+ "loss": 0.4862,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.62,
758
+ "grad_norm": 0.08494329452514648,
759
+ "learning_rate": 0.00019021421492911272,
760
+ "loss": 0.4557,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.62,
765
+ "grad_norm": 0.08702557533979416,
766
+ "learning_rate": 0.00019000845584175616,
767
+ "loss": 0.4693,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.63,
772
+ "grad_norm": 0.09048158675432205,
773
+ "learning_rate": 0.00018980066969599216,
774
+ "loss": 0.4714,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.64,
779
+ "grad_norm": 0.08462114632129669,
780
+ "learning_rate": 0.0001895908611713216,
781
+ "loss": 0.4632,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.64,
786
+ "grad_norm": 0.09956546127796173,
787
+ "learning_rate": 0.00018937903499279102,
788
+ "loss": 0.4638,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.65,
793
+ "grad_norm": 0.08630617707967758,
794
+ "learning_rate": 0.00018916519593088584,
795
+ "loss": 0.4499,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.65,
800
+ "grad_norm": 0.08207620680332184,
801
+ "learning_rate": 0.0001889493488014233,
802
+ "loss": 0.4603,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.66,
807
+ "grad_norm": 0.08473565429449081,
808
+ "learning_rate": 0.00018873149846544376,
809
+ "loss": 0.4571,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.66,
814
+ "grad_norm": 0.08818928152322769,
815
+ "learning_rate": 0.00018851164982910135,
816
+ "loss": 0.4489,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.67,
821
+ "grad_norm": 0.08116699010133743,
822
+ "learning_rate": 0.00018828980784355338,
823
+ "loss": 0.4578,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.68,
828
+ "grad_norm": 0.08832226693630219,
829
+ "learning_rate": 0.00018806597750484897,
830
+ "loss": 0.4719,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.68,
835
+ "grad_norm": 0.08624406903982162,
836
+ "learning_rate": 0.0001878401638538163,
837
+ "loss": 0.4628,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.69,
842
+ "grad_norm": 0.08936543017625809,
843
+ "learning_rate": 0.00018761237197594945,
844
+ "loss": 0.4533,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.69,
849
+ "grad_norm": 0.08579661697149277,
850
+ "learning_rate": 0.00018738260700129354,
851
+ "loss": 0.4772,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7,
856
+ "grad_norm": 0.08271288126707077,
857
+ "learning_rate": 0.0001871508741043293,
858
+ "loss": 0.4773,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.71,
863
+ "grad_norm": 0.08224964886903763,
864
+ "learning_rate": 0.0001869171785038566,
865
+ "loss": 0.4635,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.71,
870
+ "grad_norm": 0.087012380361557,
871
+ "learning_rate": 0.00018668152546287686,
872
+ "loss": 0.4559,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.72,
877
+ "grad_norm": 0.08352699875831604,
878
+ "learning_rate": 0.00018644392028847458,
879
+ "loss": 0.4485,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.72,
884
+ "grad_norm": 0.08281444013118744,
885
+ "learning_rate": 0.00018620436833169772,
886
+ "loss": 0.4393,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.73,
891
+ "grad_norm": 0.08376545459032059,
892
+ "learning_rate": 0.00018596287498743732,
893
+ "loss": 0.4525,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.74,
898
+ "grad_norm": 0.08526434749364853,
899
+ "learning_rate": 0.0001857194456943058,
900
+ "loss": 0.4456,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.74,
905
+ "grad_norm": 0.08151934295892715,
906
+ "learning_rate": 0.0001854740859345148,
907
+ "loss": 0.4576,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.75,
912
+ "grad_norm": 0.08793777972459793,
913
+ "learning_rate": 0.0001852268012337514,
914
+ "loss": 0.4431,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.75,
919
+ "eval_loss": 0.5042669773101807,
920
+ "eval_runtime": 21.4592,
921
+ "eval_samples_per_second": 46.274,
922
+ "eval_steps_per_second": 11.603,
923
+ "step": 126
924
+ },
925
+ {
926
+ "epoch": 0.75,
927
+ "grad_norm": 0.08135095983743668,
928
+ "learning_rate": 0.00018497759716105377,
929
+ "loss": 0.4384,
930
+ "step": 127
931
+ },
932
+ {
933
+ "epoch": 0.76,
934
+ "grad_norm": 0.0917576476931572,
935
+ "learning_rate": 0.0001847264793286859,
936
+ "loss": 0.4687,
937
+ "step": 128
938
+ },
939
+ {
940
+ "epoch": 0.77,
941
+ "grad_norm": 0.08832691609859467,
942
+ "learning_rate": 0.00018447345339201102,
943
+ "loss": 0.4386,
944
+ "step": 129
945
+ },
946
+ {
947
+ "epoch": 0.77,
948
+ "grad_norm": 0.08340886980295181,
949
+ "learning_rate": 0.00018421852504936438,
950
+ "loss": 0.4512,
951
+ "step": 130
952
+ },
953
+ {
954
+ "epoch": 0.78,
955
+ "grad_norm": 0.08589499443769455,
956
+ "learning_rate": 0.00018396170004192475,
957
+ "loss": 0.4387,
958
+ "step": 131
959
+ },
960
+ {
961
+ "epoch": 0.78,
962
+ "grad_norm": 0.08753557503223419,
963
+ "learning_rate": 0.00018370298415358526,
964
+ "loss": 0.4615,
965
+ "step": 132
966
+ },
967
+ {
968
+ "epoch": 0.79,
969
+ "grad_norm": 0.08406232297420502,
970
+ "learning_rate": 0.00018344238321082315,
971
+ "loss": 0.4465,
972
+ "step": 133
973
+ },
974
+ {
975
+ "epoch": 0.8,
976
+ "grad_norm": 0.08514856547117233,
977
+ "learning_rate": 0.0001831799030825685,
978
+ "loss": 0.4516,
979
+ "step": 134
980
+ },
981
+ {
982
+ "epoch": 0.8,
983
+ "grad_norm": 0.09259331226348877,
984
+ "learning_rate": 0.000182915549680072,
985
+ "loss": 0.4387,
986
+ "step": 135
987
+ },
988
+ {
989
+ "epoch": 0.81,
990
+ "grad_norm": 0.08862275630235672,
991
+ "learning_rate": 0.00018264932895677193,
992
+ "loss": 0.4434,
993
+ "step": 136
994
+ },
995
+ {
996
+ "epoch": 0.81,
997
+ "grad_norm": 0.08515379577875137,
998
+ "learning_rate": 0.0001823812469081601,
999
+ "loss": 0.4425,
1000
+ "step": 137
1001
+ },
1002
+ {
1003
+ "epoch": 0.82,
1004
+ "grad_norm": 0.09041007608175278,
1005
+ "learning_rate": 0.00018211130957164668,
1006
+ "loss": 0.4607,
1007
+ "step": 138
1008
+ },
1009
+ {
1010
+ "epoch": 0.82,
1011
+ "grad_norm": 0.08312032371759415,
1012
+ "learning_rate": 0.0001818395230264244,
1013
+ "loss": 0.442,
1014
+ "step": 139
1015
+ },
1016
+ {
1017
+ "epoch": 0.83,
1018
+ "grad_norm": 0.08981412649154663,
1019
+ "learning_rate": 0.00018156589339333152,
1020
+ "loss": 0.4608,
1021
+ "step": 140
1022
+ },
1023
+ {
1024
+ "epoch": 0.84,
1025
+ "grad_norm": 0.08991118520498276,
1026
+ "learning_rate": 0.00018129042683471402,
1027
+ "loss": 0.451,
1028
+ "step": 141
1029
+ },
1030
+ {
1031
+ "epoch": 0.84,
1032
+ "grad_norm": 0.08628728240728378,
1033
+ "learning_rate": 0.00018101312955428692,
1034
+ "loss": 0.4453,
1035
+ "step": 142
1036
+ },
1037
+ {
1038
+ "epoch": 0.85,
1039
+ "grad_norm": 0.08730859309434891,
1040
+ "learning_rate": 0.00018073400779699435,
1041
+ "loss": 0.4485,
1042
+ "step": 143
1043
+ },
1044
+ {
1045
+ "epoch": 0.85,
1046
+ "grad_norm": 0.08489865809679031,
1047
+ "learning_rate": 0.0001804530678488691,
1048
+ "loss": 0.4592,
1049
+ "step": 144
1050
+ },
1051
+ {
1052
+ "epoch": 0.86,
1053
+ "grad_norm": 0.08439410477876663,
1054
+ "learning_rate": 0.00018017031603689102,
1055
+ "loss": 0.4326,
1056
+ "step": 145
1057
+ },
1058
+ {
1059
+ "epoch": 0.87,
1060
+ "grad_norm": 0.09346488118171692,
1061
+ "learning_rate": 0.0001798857587288445,
1062
+ "loss": 0.4484,
1063
+ "step": 146
1064
+ },
1065
+ {
1066
+ "epoch": 0.87,
1067
+ "grad_norm": 0.09130821377038956,
1068
+ "learning_rate": 0.00017959940233317498,
1069
+ "loss": 0.4502,
1070
+ "step": 147
1071
+ },
1072
+ {
1073
+ "epoch": 0.88,
1074
+ "grad_norm": 0.08846256881952286,
1075
+ "learning_rate": 0.0001793112532988448,
1076
+ "loss": 0.4322,
1077
+ "step": 148
1078
+ },
1079
+ {
1080
+ "epoch": 0.88,
1081
+ "grad_norm": 0.09061886370182037,
1082
+ "learning_rate": 0.00017902131811518786,
1083
+ "loss": 0.4437,
1084
+ "step": 149
1085
+ },
1086
+ {
1087
+ "epoch": 0.89,
1088
+ "grad_norm": 0.09259927272796631,
1089
+ "learning_rate": 0.00017872960331176345,
1090
+ "loss": 0.4545,
1091
+ "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.9,
1095
+ "grad_norm": 0.09632189571857452,
1096
+ "learning_rate": 0.00017843611545820926,
1097
+ "loss": 0.4515,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.9,
1102
+ "grad_norm": 0.08714065700769424,
1103
+ "learning_rate": 0.00017814086116409348,
1104
+ "loss": 0.4602,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.91,
1109
+ "grad_norm": 0.09537078440189362,
1110
+ "learning_rate": 0.00017784384707876576,
1111
+ "loss": 0.4482,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.91,
1116
+ "grad_norm": 0.09175322949886322,
1117
+ "learning_rate": 0.00017754507989120764,
1118
+ "loss": 0.4681,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.92,
1123
+ "grad_norm": 0.08962789177894592,
1124
+ "learning_rate": 0.00017724456632988187,
1125
+ "loss": 0.4304,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.93,
1130
+ "grad_norm": 0.09643880277872086,
1131
+ "learning_rate": 0.00017694231316258077,
1132
+ "loss": 0.4532,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.93,
1137
+ "grad_norm": 0.08335065096616745,
1138
+ "learning_rate": 0.00017663832719627402,
1139
+ "loss": 0.4504,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.94,
1144
+ "grad_norm": 0.087184838950634,
1145
+ "learning_rate": 0.0001763326152769551,
1146
+ "loss": 0.4752,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.94,
1151
+ "grad_norm": 0.08858635276556015,
1152
+ "learning_rate": 0.0001760251842894874,
1153
+ "loss": 0.4413,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.95,
1158
+ "grad_norm": 0.08101391792297363,
1159
+ "learning_rate": 0.00017571604115744892,
1160
+ "loss": 0.4465,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.96,
1165
+ "grad_norm": 0.08623132854700089,
1166
+ "learning_rate": 0.0001754051928429765,
1167
+ "loss": 0.4673,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.96,
1172
+ "grad_norm": 0.0922100692987442,
1173
+ "learning_rate": 0.00017509264634660895,
1174
+ "loss": 0.4587,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.97,
1179
+ "grad_norm": 0.08243449032306671,
1180
+ "learning_rate": 0.00017477840870712945,
1181
+ "loss": 0.4368,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.97,
1186
+ "grad_norm": 0.0845554992556572,
1187
+ "learning_rate": 0.00017446248700140693,
1188
+ "loss": 0.4209,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.98,
1193
+ "grad_norm": 0.08277452737092972,
1194
+ "learning_rate": 0.00017414488834423687,
1195
+ "loss": 0.4397,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.99,
1200
+ "grad_norm": 0.0826331302523613,
1201
+ "learning_rate": 0.00017382561988818086,
1202
+ "loss": 0.4333,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.99,
1207
+ "grad_norm": 0.08441821485757828,
1208
+ "learning_rate": 0.0001735046888234057,
1209
+ "loss": 0.4496,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 1.0,
1214
+ "grad_norm": 0.08665426075458527,
1215
+ "learning_rate": 0.00017318210237752136,
1216
+ "loss": 0.4523,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 1.0,
1221
+ "eval_loss": 0.4984985589981079,
1222
+ "eval_runtime": 21.4662,
1223
+ "eval_samples_per_second": 46.259,
1224
+ "eval_steps_per_second": 11.6,
1225
+ "step": 168
1226
+ },
1227
+ {
1228
+ "epoch": 1.0,
1229
+ "grad_norm": 0.08923573791980743,
1230
+ "learning_rate": 0.00017285786781541824,
1231
+ "loss": 0.4735,
1232
+ "step": 169
1233
+ },
1234
+ {
1235
+ "epoch": 1.01,
1236
+ "grad_norm": 0.08524107187986374,
1237
+ "learning_rate": 0.00017253199243910357,
1238
+ "loss": 0.4323,
1239
+ "step": 170
1240
+ },
1241
+ {
1242
+ "epoch": 1.01,
1243
+ "grad_norm": 0.09072479605674744,
1244
+ "learning_rate": 0.00017220448358753692,
1245
+ "loss": 0.4617,
1246
+ "step": 171
1247
+ },
1248
+ {
1249
+ "epoch": 1.01,
1250
+ "grad_norm": 0.08986588567495346,
1251
+ "learning_rate": 0.0001718753486364651,
1252
+ "loss": 0.4264,
1253
+ "step": 172
1254
+ },
1255
+ {
1256
+ "epoch": 1.01,
1257
+ "grad_norm": 0.09549989551305771,
1258
+ "learning_rate": 0.00017154459499825564,
1259
+ "loss": 0.4042,
1260
+ "step": 173
1261
+ },
1262
+ {
1263
+ "epoch": 1.02,
1264
+ "grad_norm": 0.09217043220996857,
1265
+ "learning_rate": 0.0001712122301217304,
1266
+ "loss": 0.4028,
1267
+ "step": 174
1268
+ },
1269
+ {
1270
+ "epoch": 1.02,
1271
+ "grad_norm": 0.10525793582201004,
1272
+ "learning_rate": 0.00017087826149199734,
1273
+ "loss": 0.4176,
1274
+ "step": 175
1275
+ },
1276
+ {
1277
+ "epoch": 1.03,
1278
+ "grad_norm": 0.10329723358154297,
1279
+ "learning_rate": 0.00017054269663028233,
1280
+ "loss": 0.4062,
1281
+ "step": 176
1282
+ },
1283
+ {
1284
+ "epoch": 1.04,
1285
+ "grad_norm": 0.10040964931249619,
1286
+ "learning_rate": 0.00017020554309375946,
1287
+ "loss": 0.4222,
1288
+ "step": 177
1289
+ },
1290
+ {
1291
+ "epoch": 1.04,
1292
+ "grad_norm": 0.10112589597702026,
1293
+ "learning_rate": 0.00016986680847538106,
1294
+ "loss": 0.4058,
1295
+ "step": 178
1296
+ },
1297
+ {
1298
+ "epoch": 1.05,
1299
+ "grad_norm": 0.09155958890914917,
1300
+ "learning_rate": 0.0001695265004037065,
1301
+ "loss": 0.4045,
1302
+ "step": 179
1303
+ },
1304
+ {
1305
+ "epoch": 1.05,
1306
+ "grad_norm": 0.10278405249118805,
1307
+ "learning_rate": 0.00016918462654273063,
1308
+ "loss": 0.4294,
1309
+ "step": 180
1310
+ },
1311
+ {
1312
+ "epoch": 1.06,
1313
+ "grad_norm": 0.10295873880386353,
1314
+ "learning_rate": 0.00016884119459171105,
1315
+ "loss": 0.4025,
1316
+ "step": 181
1317
+ },
1318
+ {
1319
+ "epoch": 1.07,
1320
+ "grad_norm": 0.09759877622127533,
1321
+ "learning_rate": 0.0001684962122849946,
1322
+ "loss": 0.4227,
1323
+ "step": 182
1324
+ },
1325
+ {
1326
+ "epoch": 1.07,
1327
+ "grad_norm": 0.09612429887056351,
1328
+ "learning_rate": 0.00016814968739184343,
1329
+ "loss": 0.3991,
1330
+ "step": 183
1331
+ },
1332
+ {
1333
+ "epoch": 1.08,
1334
+ "grad_norm": 0.09644313901662827,
1335
+ "learning_rate": 0.00016780162771625986,
1336
+ "loss": 0.4271,
1337
+ "step": 184
1338
+ },
1339
+ {
1340
+ "epoch": 1.08,
1341
+ "grad_norm": 0.09357411414384842,
1342
+ "learning_rate": 0.00016745204109681064,
1343
+ "loss": 0.4017,
1344
+ "step": 185
1345
+ },
1346
+ {
1347
+ "epoch": 1.09,
1348
+ "grad_norm": 0.09177077561616898,
1349
+ "learning_rate": 0.00016710093540645056,
1350
+ "loss": 0.386,
1351
+ "step": 186
1352
+ },
1353
+ {
1354
+ "epoch": 1.09,
1355
+ "grad_norm": 0.10068117827177048,
1356
+ "learning_rate": 0.00016674831855234486,
1357
+ "loss": 0.4127,
1358
+ "step": 187
1359
+ },
1360
+ {
1361
+ "epoch": 1.1,
1362
+ "grad_norm": 0.09634707123041153,
1363
+ "learning_rate": 0.00016639419847569147,
1364
+ "loss": 0.403,
1365
+ "step": 188
1366
+ },
1367
+ {
1368
+ "epoch": 1.11,
1369
+ "grad_norm": 0.09533964842557907,
1370
+ "learning_rate": 0.00016603858315154195,
1371
+ "loss": 0.4004,
1372
+ "step": 189
1373
+ },
1374
+ {
1375
+ "epoch": 1.11,
1376
+ "grad_norm": 0.09449424594640732,
1377
+ "learning_rate": 0.00016568148058862197,
1378
+ "loss": 0.4136,
1379
+ "step": 190
1380
+ },
1381
+ {
1382
+ "epoch": 1.12,
1383
+ "grad_norm": 0.09432344883680344,
1384
+ "learning_rate": 0.00016532289882915103,
1385
+ "loss": 0.403,
1386
+ "step": 191
1387
+ },
1388
+ {
1389
+ "epoch": 1.12,
1390
+ "grad_norm": 0.10496091097593307,
1391
+ "learning_rate": 0.00016496284594866113,
1392
+ "loss": 0.423,
1393
+ "step": 192
1394
+ },
1395
+ {
1396
+ "epoch": 1.13,
1397
+ "grad_norm": 0.0957692563533783,
1398
+ "learning_rate": 0.00016460133005581512,
1399
+ "loss": 0.4032,
1400
+ "step": 193
1401
+ },
1402
+ {
1403
+ "epoch": 1.14,
1404
+ "grad_norm": 0.10207226127386093,
1405
+ "learning_rate": 0.0001642383592922239,
1406
+ "loss": 0.4068,
1407
+ "step": 194
1408
+ },
1409
+ {
1410
+ "epoch": 1.14,
1411
+ "grad_norm": 0.10685818642377853,
1412
+ "learning_rate": 0.00016387394183226328,
1413
+ "loss": 0.4194,
1414
+ "step": 195
1415
+ },
1416
+ {
1417
+ "epoch": 1.15,
1418
+ "grad_norm": 0.09566125273704529,
1419
+ "learning_rate": 0.00016350808588288965,
1420
+ "loss": 0.3717,
1421
+ "step": 196
1422
+ },
1423
+ {
1424
+ "epoch": 1.15,
1425
+ "grad_norm": 0.10426433384418488,
1426
+ "learning_rate": 0.0001631407996834553,
1427
+ "loss": 0.4197,
1428
+ "step": 197
1429
+ },
1430
+ {
1431
+ "epoch": 1.16,
1432
+ "grad_norm": 0.09626364707946777,
1433
+ "learning_rate": 0.00016277209150552285,
1434
+ "loss": 0.3965,
1435
+ "step": 198
1436
+ },
1437
+ {
1438
+ "epoch": 1.17,
1439
+ "grad_norm": 0.10416010022163391,
1440
+ "learning_rate": 0.000162401969652679,
1441
+ "loss": 0.4042,
1442
+ "step": 199
1443
+ },
1444
+ {
1445
+ "epoch": 1.17,
1446
+ "grad_norm": 0.11229964345693588,
1447
+ "learning_rate": 0.0001620304424603474,
1448
+ "loss": 0.4039,
1449
+ "step": 200
1450
+ },
1451
+ {
1452
+ "epoch": 1.18,
1453
+ "grad_norm": 0.09705965220928192,
1454
+ "learning_rate": 0.00016165751829560102,
1455
+ "loss": 0.4111,
1456
+ "step": 201
1457
+ },
1458
+ {
1459
+ "epoch": 1.18,
1460
+ "grad_norm": 0.09751327335834503,
1461
+ "learning_rate": 0.00016128320555697364,
1462
+ "loss": 0.4007,
1463
+ "step": 202
1464
+ },
1465
+ {
1466
+ "epoch": 1.19,
1467
+ "grad_norm": 0.09729477018117905,
1468
+ "learning_rate": 0.000160907512674271,
1469
+ "loss": 0.4025,
1470
+ "step": 203
1471
+ },
1472
+ {
1473
+ "epoch": 1.2,
1474
+ "grad_norm": 0.09977483749389648,
1475
+ "learning_rate": 0.00016053044810838046,
1476
+ "loss": 0.4143,
1477
+ "step": 204
1478
+ },
1479
+ {
1480
+ "epoch": 1.2,
1481
+ "grad_norm": 0.10283766686916351,
1482
+ "learning_rate": 0.0001601520203510809,
1483
+ "loss": 0.4093,
1484
+ "step": 205
1485
+ },
1486
+ {
1487
+ "epoch": 1.21,
1488
+ "grad_norm": 0.10398785024881363,
1489
+ "learning_rate": 0.00015977223792485118,
1490
+ "loss": 0.409,
1491
+ "step": 206
1492
+ },
1493
+ {
1494
+ "epoch": 1.21,
1495
+ "grad_norm": 0.10487958043813705,
1496
+ "learning_rate": 0.0001593911093826784,
1497
+ "loss": 0.4102,
1498
+ "step": 207
1499
+ },
1500
+ {
1501
+ "epoch": 1.22,
1502
+ "grad_norm": 0.10372807830572128,
1503
+ "learning_rate": 0.00015900864330786518,
1504
+ "loss": 0.4082,
1505
+ "step": 208
1506
+ },
1507
+ {
1508
+ "epoch": 1.23,
1509
+ "grad_norm": 0.09674819558858871,
1510
+ "learning_rate": 0.00015862484831383644,
1511
+ "loss": 0.4093,
1512
+ "step": 209
1513
+ },
1514
+ {
1515
+ "epoch": 1.23,
1516
+ "grad_norm": 0.09968870133161545,
1517
+ "learning_rate": 0.00015823973304394525,
1518
+ "loss": 0.4237,
1519
+ "step": 210
1520
+ },
1521
+ {
1522
+ "epoch": 1.23,
1523
+ "eval_loss": 0.4985295832157135,
1524
+ "eval_runtime": 21.4597,
1525
+ "eval_samples_per_second": 46.273,
1526
+ "eval_steps_per_second": 11.603,
1527
+ "step": 210
1528
+ },
1529
+ {
1530
+ "epoch": 1.24,
1531
+ "grad_norm": 0.10222364962100983,
1532
+ "learning_rate": 0.00015785330617127842,
1533
+ "loss": 0.4032,
1534
+ "step": 211
1535
+ },
1536
+ {
1537
+ "epoch": 1.24,
1538
+ "grad_norm": 0.09916388243436813,
1539
+ "learning_rate": 0.00015746557639846097,
1540
+ "loss": 0.4113,
1541
+ "step": 212
1542
+ },
1543
+ {
1544
+ "epoch": 1.25,
1545
+ "grad_norm": 0.1033184677362442,
1546
+ "learning_rate": 0.0001570765524574602,
1547
+ "loss": 0.3956,
1548
+ "step": 213
1549
+ },
1550
+ {
1551
+ "epoch": 1.26,
1552
+ "grad_norm": 0.11059914529323578,
1553
+ "learning_rate": 0.00015668624310938913,
1554
+ "loss": 0.404,
1555
+ "step": 214
1556
+ },
1557
+ {
1558
+ "epoch": 1.26,
1559
+ "grad_norm": 0.0982404425740242,
1560
+ "learning_rate": 0.00015629465714430904,
1561
+ "loss": 0.3875,
1562
+ "step": 215
1563
+ },
1564
+ {
1565
+ "epoch": 1.27,
1566
+ "grad_norm": 0.1017359048128128,
1567
+ "learning_rate": 0.0001559018033810316,
1568
+ "loss": 0.4033,
1569
+ "step": 216
1570
+ },
1571
+ {
1572
+ "epoch": 1.27,
1573
+ "grad_norm": 0.1090175062417984,
1574
+ "learning_rate": 0.00015550769066692034,
1575
+ "loss": 0.4084,
1576
+ "step": 217
1577
+ },
1578
+ {
1579
+ "epoch": 1.28,
1580
+ "grad_norm": 0.1041378527879715,
1581
+ "learning_rate": 0.00015511232787769123,
1582
+ "loss": 0.4095,
1583
+ "step": 218
1584
+ },
1585
+ {
1586
+ "epoch": 1.28,
1587
+ "grad_norm": 0.0929458811879158,
1588
+ "learning_rate": 0.00015471572391721284,
1589
+ "loss": 0.3892,
1590
+ "step": 219
1591
+ },
1592
+ {
1593
+ "epoch": 1.29,
1594
+ "grad_norm": 0.10203150659799576,
1595
+ "learning_rate": 0.00015431788771730597,
1596
+ "loss": 0.3967,
1597
+ "step": 220
1598
+ },
1599
+ {
1600
+ "epoch": 1.3,
1601
+ "grad_norm": 0.10682693123817444,
1602
+ "learning_rate": 0.00015391882823754228,
1603
+ "loss": 0.4164,
1604
+ "step": 221
1605
+ },
1606
+ {
1607
+ "epoch": 1.3,
1608
+ "grad_norm": 0.10250475257635117,
1609
+ "learning_rate": 0.00015351855446504268,
1610
+ "loss": 0.402,
1611
+ "step": 222
1612
+ },
1613
+ {
1614
+ "epoch": 1.31,
1615
+ "grad_norm": 0.09453174471855164,
1616
+ "learning_rate": 0.00015311707541427487,
1617
+ "loss": 0.3927,
1618
+ "step": 223
1619
+ },
1620
+ {
1621
+ "epoch": 1.31,
1622
+ "grad_norm": 0.09379514306783676,
1623
+ "learning_rate": 0.00015271440012685025,
1624
+ "loss": 0.3825,
1625
+ "step": 224
1626
+ },
1627
+ {
1628
+ "epoch": 1.32,
1629
+ "grad_norm": 0.09439584612846375,
1630
+ "learning_rate": 0.00015231053767132045,
1631
+ "loss": 0.3798,
1632
+ "step": 225
1633
+ },
1634
+ {
1635
+ "epoch": 1.33,
1636
+ "grad_norm": 0.10218024253845215,
1637
+ "learning_rate": 0.00015190549714297303,
1638
+ "loss": 0.3909,
1639
+ "step": 226
1640
+ },
1641
+ {
1642
+ "epoch": 1.33,
1643
+ "grad_norm": 0.10314662754535675,
1644
+ "learning_rate": 0.00015149928766362657,
1645
+ "loss": 0.4075,
1646
+ "step": 227
1647
+ },
1648
+ {
1649
+ "epoch": 1.34,
1650
+ "grad_norm": 0.10139516741037369,
1651
+ "learning_rate": 0.00015109191838142536,
1652
+ "loss": 0.4125,
1653
+ "step": 228
1654
+ },
1655
+ {
1656
+ "epoch": 1.34,
1657
+ "grad_norm": 0.10410083085298538,
1658
+ "learning_rate": 0.0001506833984706333,
1659
+ "loss": 0.3998,
1660
+ "step": 229
1661
+ },
1662
+ {
1663
+ "epoch": 1.35,
1664
+ "grad_norm": 0.11478332430124283,
1665
+ "learning_rate": 0.00015027373713142735,
1666
+ "loss": 0.4181,
1667
+ "step": 230
1668
+ },
1669
+ {
1670
+ "epoch": 1.36,
1671
+ "grad_norm": 0.10138574987649918,
1672
+ "learning_rate": 0.00014986294358969028,
1673
+ "loss": 0.4152,
1674
+ "step": 231
1675
+ },
1676
+ {
1677
+ "epoch": 1.36,
1678
+ "grad_norm": 0.0989016592502594,
1679
+ "learning_rate": 0.0001494510270968029,
1680
+ "loss": 0.399,
1681
+ "step": 232
1682
+ },
1683
+ {
1684
+ "epoch": 1.37,
1685
+ "grad_norm": 0.10673234611749649,
1686
+ "learning_rate": 0.00014903799692943574,
1687
+ "loss": 0.4246,
1688
+ "step": 233
1689
+ },
1690
+ {
1691
+ "epoch": 1.37,
1692
+ "grad_norm": 0.10326199978590012,
1693
+ "learning_rate": 0.00014862386238934016,
1694
+ "loss": 0.4033,
1695
+ "step": 234
1696
+ },
1697
+ {
1698
+ "epoch": 1.38,
1699
+ "grad_norm": 0.09947673231363297,
1700
+ "learning_rate": 0.00014820863280313873,
1701
+ "loss": 0.3886,
1702
+ "step": 235
1703
+ },
1704
+ {
1705
+ "epoch": 1.39,
1706
+ "grad_norm": 0.09778755158185959,
1707
+ "learning_rate": 0.00014779231752211548,
1708
+ "loss": 0.3934,
1709
+ "step": 236
1710
+ },
1711
+ {
1712
+ "epoch": 1.39,
1713
+ "grad_norm": 0.09947831183671951,
1714
+ "learning_rate": 0.0001473749259220048,
1715
+ "loss": 0.4147,
1716
+ "step": 237
1717
+ },
1718
+ {
1719
+ "epoch": 1.4,
1720
+ "grad_norm": 0.10698696970939636,
1721
+ "learning_rate": 0.00014695646740278085,
1722
+ "loss": 0.3773,
1723
+ "step": 238
1724
+ },
1725
+ {
1726
+ "epoch": 1.4,
1727
+ "grad_norm": 0.09899724274873734,
1728
+ "learning_rate": 0.00014653695138844557,
1729
+ "loss": 0.4005,
1730
+ "step": 239
1731
+ },
1732
+ {
1733
+ "epoch": 1.41,
1734
+ "grad_norm": 0.10226688534021378,
1735
+ "learning_rate": 0.0001461163873268164,
1736
+ "loss": 0.4009,
1737
+ "step": 240
1738
+ },
1739
+ {
1740
+ "epoch": 1.42,
1741
+ "grad_norm": 0.10390684753656387,
1742
+ "learning_rate": 0.0001456947846893137,
1743
+ "loss": 0.4129,
1744
+ "step": 241
1745
+ },
1746
+ {
1747
+ "epoch": 1.42,
1748
+ "grad_norm": 0.09909753501415253,
1749
+ "learning_rate": 0.0001452721529707473,
1750
+ "loss": 0.3773,
1751
+ "step": 242
1752
+ },
1753
+ {
1754
+ "epoch": 1.43,
1755
+ "grad_norm": 0.09814441949129105,
1756
+ "learning_rate": 0.00014484850168910263,
1757
+ "loss": 0.3976,
1758
+ "step": 243
1759
+ },
1760
+ {
1761
+ "epoch": 1.43,
1762
+ "grad_norm": 0.10027995705604553,
1763
+ "learning_rate": 0.00014442384038532665,
1764
+ "loss": 0.3951,
1765
+ "step": 244
1766
+ },
1767
+ {
1768
+ "epoch": 1.44,
1769
+ "grad_norm": 0.0988469123840332,
1770
+ "learning_rate": 0.00014399817862311256,
1771
+ "loss": 0.3734,
1772
+ "step": 245
1773
+ },
1774
+ {
1775
+ "epoch": 1.45,
1776
+ "grad_norm": 0.09742960333824158,
1777
+ "learning_rate": 0.00014357152598868476,
1778
+ "loss": 0.3826,
1779
+ "step": 246
1780
+ },
1781
+ {
1782
+ "epoch": 1.45,
1783
+ "grad_norm": 0.1014707013964653,
1784
+ "learning_rate": 0.00014314389209058286,
1785
+ "loss": 0.4082,
1786
+ "step": 247
1787
+ },
1788
+ {
1789
+ "epoch": 1.46,
1790
+ "grad_norm": 0.10080685466527939,
1791
+ "learning_rate": 0.00014271528655944522,
1792
+ "loss": 0.4104,
1793
+ "step": 248
1794
+ },
1795
+ {
1796
+ "epoch": 1.46,
1797
+ "grad_norm": 0.1009359136223793,
1798
+ "learning_rate": 0.0001422857190477921,
1799
+ "loss": 0.3912,
1800
+ "step": 249
1801
+ },
1802
+ {
1803
+ "epoch": 1.47,
1804
+ "grad_norm": 0.0964767187833786,
1805
+ "learning_rate": 0.0001418551992298083,
1806
+ "loss": 0.3731,
1807
+ "step": 250
1808
+ },
1809
+ {
1810
+ "epoch": 1.47,
1811
+ "grad_norm": 0.09848513454198837,
1812
+ "learning_rate": 0.0001414237368011253,
1813
+ "loss": 0.3891,
1814
+ "step": 251
1815
+ },
1816
+ {
1817
+ "epoch": 1.48,
1818
+ "grad_norm": 0.10232508182525635,
1819
+ "learning_rate": 0.00014099134147860286,
1820
+ "loss": 0.4002,
1821
+ "step": 252
1822
+ },
1823
+ {
1824
+ "epoch": 1.48,
1825
+ "eval_loss": 0.4975546896457672,
1826
+ "eval_runtime": 21.466,
1827
+ "eval_samples_per_second": 46.259,
1828
+ "eval_steps_per_second": 11.6,
1829
+ "step": 252
1830
+ },
1831
+ {
1832
+ "epoch": 1.49,
1833
+ "grad_norm": 0.10712958872318268,
1834
+ "learning_rate": 0.00014055802300011027,
1835
+ "loss": 0.41,
1836
+ "step": 253
1837
+ },
1838
+ {
1839
+ "epoch": 1.49,
1840
+ "grad_norm": 0.10100317001342773,
1841
+ "learning_rate": 0.0001401237911243069,
1842
+ "loss": 0.3954,
1843
+ "step": 254
1844
+ },
1845
+ {
1846
+ "epoch": 1.5,
1847
+ "grad_norm": 0.09532604366540909,
1848
+ "learning_rate": 0.00013968865563042255,
1849
+ "loss": 0.4111,
1850
+ "step": 255
1851
+ },
1852
+ {
1853
+ "epoch": 1.5,
1854
+ "grad_norm": 0.10244431346654892,
1855
+ "learning_rate": 0.00013925262631803723,
1856
+ "loss": 0.4,
1857
+ "step": 256
1858
+ },
1859
+ {
1860
+ "epoch": 1.51,
1861
+ "grad_norm": 0.10212967544794083,
1862
+ "learning_rate": 0.00013881571300686037,
1863
+ "loss": 0.3996,
1864
+ "step": 257
1865
+ },
1866
+ {
1867
+ "epoch": 1.52,
1868
+ "grad_norm": 0.09606331586837769,
1869
+ "learning_rate": 0.0001383779255365097,
1870
+ "loss": 0.3852,
1871
+ "step": 258
1872
+ },
1873
+ {
1874
+ "epoch": 1.52,
1875
+ "grad_norm": 0.10002104192972183,
1876
+ "learning_rate": 0.00013793927376628976,
1877
+ "loss": 0.4126,
1878
+ "step": 259
1879
+ },
1880
+ {
1881
+ "epoch": 1.53,
1882
+ "grad_norm": 0.10387251526117325,
1883
+ "learning_rate": 0.00013749976757496967,
1884
+ "loss": 0.4146,
1885
+ "step": 260
1886
+ },
1887
+ {
1888
+ "epoch": 1.53,
1889
+ "grad_norm": 0.09998749941587448,
1890
+ "learning_rate": 0.00013705941686056086,
1891
+ "loss": 0.4143,
1892
+ "step": 261
1893
+ },
1894
+ {
1895
+ "epoch": 1.54,
1896
+ "grad_norm": 0.09770024567842484,
1897
+ "learning_rate": 0.00013661823154009395,
1898
+ "loss": 0.3719,
1899
+ "step": 262
1900
+ },
1901
+ {
1902
+ "epoch": 1.55,
1903
+ "grad_norm": 0.10180012881755829,
1904
+ "learning_rate": 0.00013617622154939564,
1905
+ "loss": 0.408,
1906
+ "step": 263
1907
+ },
1908
+ {
1909
+ "epoch": 1.55,
1910
+ "grad_norm": 0.10063595324754715,
1911
+ "learning_rate": 0.00013573339684286472,
1912
+ "loss": 0.4007,
1913
+ "step": 264
1914
+ },
1915
+ {
1916
+ "epoch": 1.56,
1917
+ "grad_norm": 0.10153420269489288,
1918
+ "learning_rate": 0.00013528976739324807,
1919
+ "loss": 0.4054,
1920
+ "step": 265
1921
+ },
1922
+ {
1923
+ "epoch": 1.56,
1924
+ "grad_norm": 0.10569385439157486,
1925
+ "learning_rate": 0.0001348453431914159,
1926
+ "loss": 0.4031,
1927
+ "step": 266
1928
+ },
1929
+ {
1930
+ "epoch": 1.57,
1931
+ "grad_norm": 0.10000584274530411,
1932
+ "learning_rate": 0.00013440013424613698,
1933
+ "loss": 0.4018,
1934
+ "step": 267
1935
+ },
1936
+ {
1937
+ "epoch": 1.58,
1938
+ "grad_norm": 0.09948629140853882,
1939
+ "learning_rate": 0.00013395415058385296,
1940
+ "loss": 0.3997,
1941
+ "step": 268
1942
+ },
1943
+ {
1944
+ "epoch": 1.58,
1945
+ "grad_norm": 0.10179516673088074,
1946
+ "learning_rate": 0.00013350740224845278,
1947
+ "loss": 0.3872,
1948
+ "step": 269
1949
+ },
1950
+ {
1951
+ "epoch": 1.59,
1952
+ "grad_norm": 0.0989665687084198,
1953
+ "learning_rate": 0.00013305989930104638,
1954
+ "loss": 0.3672,
1955
+ "step": 270
1956
+ },
1957
+ {
1958
+ "epoch": 1.59,
1959
+ "grad_norm": 0.09988453984260559,
1960
+ "learning_rate": 0.00013261165181973814,
1961
+ "loss": 0.3978,
1962
+ "step": 271
1963
+ },
1964
+ {
1965
+ "epoch": 1.6,
1966
+ "grad_norm": 0.09958979487419128,
1967
+ "learning_rate": 0.00013216266989939988,
1968
+ "loss": 0.3793,
1969
+ "step": 272
1970
+ },
1971
+ {
1972
+ "epoch": 1.61,
1973
+ "grad_norm": 0.10080169141292572,
1974
+ "learning_rate": 0.0001317129636514435,
1975
+ "loss": 0.4012,
1976
+ "step": 273
1977
+ },
1978
+ {
1979
+ "epoch": 1.61,
1980
+ "grad_norm": 0.10148239880800247,
1981
+ "learning_rate": 0.00013126254320359343,
1982
+ "loss": 0.3904,
1983
+ "step": 274
1984
+ },
1985
+ {
1986
+ "epoch": 1.62,
1987
+ "grad_norm": 0.10728135704994202,
1988
+ "learning_rate": 0.00013081141869965835,
1989
+ "loss": 0.393,
1990
+ "step": 275
1991
+ },
1992
+ {
1993
+ "epoch": 1.62,
1994
+ "grad_norm": 0.09917322546243668,
1995
+ "learning_rate": 0.00013035960029930278,
1996
+ "loss": 0.3725,
1997
+ "step": 276
1998
+ },
1999
+ {
2000
+ "epoch": 1.63,
2001
+ "grad_norm": 0.10163102298974991,
2002
+ "learning_rate": 0.00012990709817781837,
2003
+ "loss": 0.406,
2004
+ "step": 277
2005
+ },
2006
+ {
2007
+ "epoch": 1.64,
2008
+ "grad_norm": 0.09815432131290436,
2009
+ "learning_rate": 0.00012945392252589465,
2010
+ "loss": 0.3995,
2011
+ "step": 278
2012
+ },
2013
+ {
2014
+ "epoch": 1.64,
2015
+ "grad_norm": 0.09806889295578003,
2016
+ "learning_rate": 0.0001290000835493896,
2017
+ "loss": 0.3952,
2018
+ "step": 279
2019
+ },
2020
+ {
2021
+ "epoch": 1.65,
2022
+ "grad_norm": 0.09826052933931351,
2023
+ "learning_rate": 0.0001285455914690997,
2024
+ "loss": 0.402,
2025
+ "step": 280
2026
+ },
2027
+ {
2028
+ "epoch": 1.65,
2029
+ "grad_norm": 0.09949176013469696,
2030
+ "learning_rate": 0.0001280904565205299,
2031
+ "loss": 0.3953,
2032
+ "step": 281
2033
+ },
2034
+ {
2035
+ "epoch": 1.66,
2036
+ "grad_norm": 0.10278761386871338,
2037
+ "learning_rate": 0.00012763468895366303,
2038
+ "loss": 0.4091,
2039
+ "step": 282
2040
+ },
2041
+ {
2042
+ "epoch": 1.66,
2043
+ "grad_norm": 0.10104485601186752,
2044
+ "learning_rate": 0.0001271782990327289,
2045
+ "loss": 0.3807,
2046
+ "step": 283
2047
+ },
2048
+ {
2049
+ "epoch": 1.67,
2050
+ "grad_norm": 0.10103065520524979,
2051
+ "learning_rate": 0.0001267212970359732,
2052
+ "loss": 0.4136,
2053
+ "step": 284
2054
+ },
2055
+ {
2056
+ "epoch": 1.68,
2057
+ "grad_norm": 0.10056735575199127,
2058
+ "learning_rate": 0.0001262636932554261,
2059
+ "loss": 0.3834,
2060
+ "step": 285
2061
+ },
2062
+ {
2063
+ "epoch": 1.68,
2064
+ "grad_norm": 0.10619843006134033,
2065
+ "learning_rate": 0.00012580549799667034,
2066
+ "loss": 0.3926,
2067
+ "step": 286
2068
+ },
2069
+ {
2070
+ "epoch": 1.69,
2071
+ "grad_norm": 0.10867036134004593,
2072
+ "learning_rate": 0.00012534672157860928,
2073
+ "loss": 0.4102,
2074
+ "step": 287
2075
+ },
2076
+ {
2077
+ "epoch": 1.69,
2078
+ "grad_norm": 0.10176358371973038,
2079
+ "learning_rate": 0.00012488737433323426,
2080
+ "loss": 0.4013,
2081
+ "step": 288
2082
+ },
2083
+ {
2084
+ "epoch": 1.7,
2085
+ "grad_norm": 0.09872467070817947,
2086
+ "learning_rate": 0.00012442746660539227,
2087
+ "loss": 0.3859,
2088
+ "step": 289
2089
+ },
2090
+ {
2091
+ "epoch": 1.71,
2092
+ "grad_norm": 0.10109713673591614,
2093
+ "learning_rate": 0.00012396700875255264,
2094
+ "loss": 0.3779,
2095
+ "step": 290
2096
+ },
2097
+ {
2098
+ "epoch": 1.71,
2099
+ "grad_norm": 0.10859864950180054,
2100
+ "learning_rate": 0.00012350601114457396,
2101
+ "loss": 0.4023,
2102
+ "step": 291
2103
+ },
2104
+ {
2105
+ "epoch": 1.72,
2106
+ "grad_norm": 0.10092321038246155,
2107
+ "learning_rate": 0.00012304448416347065,
2108
+ "loss": 0.3998,
2109
+ "step": 292
2110
+ },
2111
+ {
2112
+ "epoch": 1.72,
2113
+ "grad_norm": 0.10352278500795364,
2114
+ "learning_rate": 0.0001225824382031789,
2115
+ "loss": 0.4067,
2116
+ "step": 293
2117
+ },
2118
+ {
2119
+ "epoch": 1.73,
2120
+ "grad_norm": 0.1029689610004425,
2121
+ "learning_rate": 0.0001221198836693226,
2122
+ "loss": 0.3656,
2123
+ "step": 294
2124
+ },
2125
+ {
2126
+ "epoch": 1.73,
2127
+ "eval_loss": 0.4955105185508728,
2128
+ "eval_runtime": 21.4362,
2129
+ "eval_samples_per_second": 46.324,
2130
+ "eval_steps_per_second": 11.616,
2131
+ "step": 294
2132
+ },
2133
+ {
2134
+ "epoch": 1.74,
2135
+ "grad_norm": 0.10078923404216766,
2136
+ "learning_rate": 0.00012165683097897931,
2137
+ "loss": 0.4035,
2138
+ "step": 295
2139
+ },
2140
+ {
2141
+ "epoch": 1.74,
2142
+ "grad_norm": 0.1020880788564682,
2143
+ "learning_rate": 0.00012119329056044532,
2144
+ "loss": 0.393,
2145
+ "step": 296
2146
+ },
2147
+ {
2148
+ "epoch": 1.75,
2149
+ "grad_norm": 0.10287690162658691,
2150
+ "learning_rate": 0.00012072927285300098,
2151
+ "loss": 0.4005,
2152
+ "step": 297
2153
+ },
2154
+ {
2155
+ "epoch": 1.75,
2156
+ "grad_norm": 0.10361482948064804,
2157
+ "learning_rate": 0.00012026478830667551,
2158
+ "loss": 0.3885,
2159
+ "step": 298
2160
+ },
2161
+ {
2162
+ "epoch": 1.76,
2163
+ "grad_norm": 0.10416186600923538,
2164
+ "learning_rate": 0.00011979984738201171,
2165
+ "loss": 0.3997,
2166
+ "step": 299
2167
+ },
2168
+ {
2169
+ "epoch": 1.77,
2170
+ "grad_norm": 0.10558196157217026,
2171
+ "learning_rate": 0.00011933446054983035,
2172
+ "loss": 0.4082,
2173
+ "step": 300
2174
+ },
2175
+ {
2176
+ "epoch": 1.77,
2177
+ "grad_norm": 0.10211660712957382,
2178
+ "learning_rate": 0.00011886863829099441,
2179
+ "loss": 0.3798,
2180
+ "step": 301
2181
+ },
2182
+ {
2183
+ "epoch": 1.78,
2184
+ "grad_norm": 0.10305824875831604,
2185
+ "learning_rate": 0.00011840239109617302,
2186
+ "loss": 0.3898,
2187
+ "step": 302
2188
+ },
2189
+ {
2190
+ "epoch": 1.78,
2191
+ "grad_norm": 0.11154858022928238,
2192
+ "learning_rate": 0.0001179357294656051,
2193
+ "loss": 0.3921,
2194
+ "step": 303
2195
+ },
2196
+ {
2197
+ "epoch": 1.79,
2198
+ "grad_norm": 0.1013292595744133,
2199
+ "learning_rate": 0.00011746866390886305,
2200
+ "loss": 0.3808,
2201
+ "step": 304
2202
+ },
2203
+ {
2204
+ "epoch": 1.8,
2205
+ "grad_norm": 0.10282581299543381,
2206
+ "learning_rate": 0.00011700120494461595,
2207
+ "loss": 0.3811,
2208
+ "step": 305
2209
+ },
2210
+ {
2211
+ "epoch": 1.8,
2212
+ "grad_norm": 0.10098174214363098,
2213
+ "learning_rate": 0.0001165333631003928,
2214
+ "loss": 0.3822,
2215
+ "step": 306
2216
+ },
2217
+ {
2218
+ "epoch": 1.81,
2219
+ "grad_norm": 0.10231437534093857,
2220
+ "learning_rate": 0.00011606514891234526,
2221
+ "loss": 0.38,
2222
+ "step": 307
2223
+ },
2224
+ {
2225
+ "epoch": 1.81,
2226
+ "grad_norm": 0.10368547588586807,
2227
+ "learning_rate": 0.00011559657292501042,
2228
+ "loss": 0.3863,
2229
+ "step": 308
2230
+ },
2231
+ {
2232
+ "epoch": 1.82,
2233
+ "grad_norm": 0.10524257272481918,
2234
+ "learning_rate": 0.00011512764569107351,
2235
+ "loss": 0.4024,
2236
+ "step": 309
2237
+ },
2238
+ {
2239
+ "epoch": 1.82,
2240
+ "grad_norm": 0.10808374732732773,
2241
+ "learning_rate": 0.00011465837777113,
2242
+ "loss": 0.4021,
2243
+ "step": 310
2244
+ },
2245
+ {
2246
+ "epoch": 1.83,
2247
+ "grad_norm": 0.10130346566438675,
2248
+ "learning_rate": 0.00011418877973344781,
2249
+ "loss": 0.3857,
2250
+ "step": 311
2251
+ },
2252
+ {
2253
+ "epoch": 1.84,
2254
+ "grad_norm": 0.10113856196403503,
2255
+ "learning_rate": 0.00011371886215372951,
2256
+ "loss": 0.4028,
2257
+ "step": 312
2258
+ },
2259
+ {
2260
+ "epoch": 1.84,
2261
+ "grad_norm": 0.10313602536916733,
2262
+ "learning_rate": 0.00011324863561487383,
2263
+ "loss": 0.3897,
2264
+ "step": 313
2265
+ },
2266
+ {
2267
+ "epoch": 1.85,
2268
+ "grad_norm": 0.0981384888291359,
2269
+ "learning_rate": 0.00011277811070673765,
2270
+ "loss": 0.3798,
2271
+ "step": 314
2272
+ },
2273
+ {
2274
+ "epoch": 1.85,
2275
+ "grad_norm": 0.10432131588459015,
2276
+ "learning_rate": 0.00011230729802589726,
2277
+ "loss": 0.3941,
2278
+ "step": 315
2279
+ },
2280
+ {
2281
+ "epoch": 1.86,
2282
+ "grad_norm": 0.09853876382112503,
2283
+ "learning_rate": 0.00011183620817540986,
2284
+ "loss": 0.3799,
2285
+ "step": 316
2286
+ },
2287
+ {
2288
+ "epoch": 1.87,
2289
+ "grad_norm": 0.10610882192850113,
2290
+ "learning_rate": 0.00011136485176457459,
2291
+ "loss": 0.4034,
2292
+ "step": 317
2293
+ },
2294
+ {
2295
+ "epoch": 1.87,
2296
+ "grad_norm": 0.09782709181308746,
2297
+ "learning_rate": 0.00011089323940869392,
2298
+ "loss": 0.3725,
2299
+ "step": 318
2300
+ },
2301
+ {
2302
+ "epoch": 1.88,
2303
+ "grad_norm": 0.10068295896053314,
2304
+ "learning_rate": 0.0001104213817288343,
2305
+ "loss": 0.3721,
2306
+ "step": 319
2307
+ },
2308
+ {
2309
+ "epoch": 1.88,
2310
+ "grad_norm": 0.10485327988862991,
2311
+ "learning_rate": 0.00010994928935158702,
2312
+ "loss": 0.3832,
2313
+ "step": 320
2314
+ },
2315
+ {
2316
+ "epoch": 1.89,
2317
+ "grad_norm": 0.10914643853902817,
2318
+ "learning_rate": 0.00010947697290882903,
2319
+ "loss": 0.4039,
2320
+ "step": 321
2321
+ },
2322
+ {
2323
+ "epoch": 1.9,
2324
+ "grad_norm": 0.10210110992193222,
2325
+ "learning_rate": 0.00010900444303748332,
2326
+ "loss": 0.3954,
2327
+ "step": 322
2328
+ },
2329
+ {
2330
+ "epoch": 1.9,
2331
+ "grad_norm": 0.09887547791004181,
2332
+ "learning_rate": 0.00010853171037927951,
2333
+ "loss": 0.3711,
2334
+ "step": 323
2335
+ },
2336
+ {
2337
+ "epoch": 1.91,
2338
+ "grad_norm": 0.1009160652756691,
2339
+ "learning_rate": 0.0001080587855805141,
2340
+ "loss": 0.3917,
2341
+ "step": 324
2342
+ },
2343
+ {
2344
+ "epoch": 1.91,
2345
+ "grad_norm": 0.10089701414108276,
2346
+ "learning_rate": 0.00010758567929181074,
2347
+ "loss": 0.388,
2348
+ "step": 325
2349
+ },
2350
+ {
2351
+ "epoch": 1.92,
2352
+ "grad_norm": 0.10800614953041077,
2353
+ "learning_rate": 0.00010711240216788036,
2354
+ "loss": 0.4067,
2355
+ "step": 326
2356
+ },
2357
+ {
2358
+ "epoch": 1.93,
2359
+ "grad_norm": 0.10289803147315979,
2360
+ "learning_rate": 0.00010663896486728133,
2361
+ "loss": 0.3965,
2362
+ "step": 327
2363
+ },
2364
+ {
2365
+ "epoch": 1.93,
2366
+ "grad_norm": 0.10536928474903107,
2367
+ "learning_rate": 0.00010616537805217916,
2368
+ "loss": 0.4033,
2369
+ "step": 328
2370
+ },
2371
+ {
2372
+ "epoch": 1.94,
2373
+ "grad_norm": 0.10302754491567612,
2374
+ "learning_rate": 0.00010569165238810666,
2375
+ "loss": 0.3841,
2376
+ "step": 329
2377
+ },
2378
+ {
2379
+ "epoch": 1.94,
2380
+ "grad_norm": 0.10210216045379639,
2381
+ "learning_rate": 0.00010521779854372353,
2382
+ "loss": 0.4043,
2383
+ "step": 330
2384
+ },
2385
+ {
2386
+ "epoch": 1.95,
2387
+ "grad_norm": 0.10437451303005219,
2388
+ "learning_rate": 0.00010474382719057631,
2389
+ "loss": 0.4065,
2390
+ "step": 331
2391
+ },
2392
+ {
2393
+ "epoch": 1.96,
2394
+ "grad_norm": 0.10098063200712204,
2395
+ "learning_rate": 0.00010426974900285784,
2396
+ "loss": 0.4029,
2397
+ "step": 332
2398
+ },
2399
+ {
2400
+ "epoch": 1.96,
2401
+ "grad_norm": 0.09919014573097229,
2402
+ "learning_rate": 0.00010379557465716696,
2403
+ "loss": 0.3902,
2404
+ "step": 333
2405
+ },
2406
+ {
2407
+ "epoch": 1.97,
2408
+ "grad_norm": 0.09987551718950272,
2409
+ "learning_rate": 0.00010332131483226804,
2410
+ "loss": 0.3901,
2411
+ "step": 334
2412
+ },
2413
+ {
2414
+ "epoch": 1.97,
2415
+ "grad_norm": 0.10001327842473984,
2416
+ "learning_rate": 0.00010284698020885053,
2417
+ "loss": 0.3697,
2418
+ "step": 335
2419
+ },
2420
+ {
2421
+ "epoch": 1.98,
2422
+ "grad_norm": 0.11250711232423782,
2423
+ "learning_rate": 0.00010237258146928848,
2424
+ "loss": 0.3744,
2425
+ "step": 336
2426
+ },
2427
+ {
2428
+ "epoch": 1.98,
2429
+ "eval_loss": 0.4941823482513428,
2430
+ "eval_runtime": 21.4596,
2431
+ "eval_samples_per_second": 46.273,
2432
+ "eval_steps_per_second": 11.603,
2433
+ "step": 336
2434
+ }
2435
+ ],
2436
+ "logging_steps": 1,
2437
+ "max_steps": 672,
2438
+ "num_input_tokens_seen": 0,
2439
+ "num_train_epochs": 4,
2440
+ "save_steps": 168,
2441
+ "total_flos": 1.0026380477092332e+18,
2442
+ "train_batch_size": 1,
2443
+ "trial_name": null,
2444
+ "trial_params": null
2445
+ }
checkpoint-336/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a2f0ef670d0281abf97e6b6a3c9043bd5509665b561215ad64107dc2e4edda
3
+ size 5752
checkpoint-504/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.10.0
checkpoint-504/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-504/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681a9b28a8b0fb51573ae23eb21662971b70b0cda188addda8bdfbfa55f3d729
3
+ size 335604696
checkpoint-504/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834ba47d0ed60ec8ccbb998c6b06bbed853e023179419811f1692b19796d8752
3
+ size 168625172
checkpoint-504/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1287bea6796580c709a78238b0261dae4e34c5184a6c6dbfd67bfc579a9654
3
+ size 15024
checkpoint-504/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c77783ff5d5d2aa23b7417d0675ae0e730606420d0fcb4ca7a09198b2a5a37
3
+ size 15024
checkpoint-504/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8cf7892ffba354540cb4f485bb460e9fd6900ea313beca8c70eec92df4c2878
3
+ size 15024
checkpoint-504/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84675bf8348cf54ca752ef75877e27316c56ac1ea0968df847124976cc07bc8
3
+ size 15024
checkpoint-504/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8295d1008fc7021b42c6546f62a9b803d58c60a7fdacb1d7c560af3b54ecd8b3
3
+ size 1064
checkpoint-504/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-504/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-504/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-504/trainer_state.json ADDED
@@ -0,0 +1,3653 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9599406528189913,
5
+ "eval_steps": 42,
6
+ "global_step": 504,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.0981353223323822,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.641,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "eval_loss": 0.6416735053062439,
21
+ "eval_runtime": 21.4326,
22
+ "eval_samples_per_second": 46.331,
23
+ "eval_steps_per_second": 11.618,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.01,
28
+ "grad_norm": 0.09748291969299316,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.6396,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02,
35
+ "grad_norm": 0.09947647899389267,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.6397,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "grad_norm": 0.09976381808519363,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.6371,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "grad_norm": 0.10493721067905426,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.6491,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.04,
56
+ "grad_norm": 0.1144007071852684,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.6218,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.04,
63
+ "grad_norm": 0.08536222577095032,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.6177,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.05,
70
+ "grad_norm": 0.11926598846912384,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.5861,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.05,
77
+ "grad_norm": 0.15648387372493744,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.6006,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.06,
84
+ "grad_norm": 0.12172720581293106,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.5845,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.07,
91
+ "grad_norm": 0.09348208457231522,
92
+ "learning_rate": 0.0001999988739622358,
93
+ "loss": 0.5471,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.07,
98
+ "grad_norm": 0.07471276819705963,
99
+ "learning_rate": 0.00019999549587430254,
100
+ "loss": 0.578,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.08,
105
+ "grad_norm": 0.07200929522514343,
106
+ "learning_rate": 0.00019998986581227718,
107
+ "loss": 0.5328,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.08,
112
+ "grad_norm": 0.07460763305425644,
113
+ "learning_rate": 0.000199981983902953,
114
+ "loss": 0.5651,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.09,
119
+ "grad_norm": 0.07441641390323639,
120
+ "learning_rate": 0.00019997185032383664,
121
+ "loss": 0.5589,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.09,
126
+ "grad_norm": 0.07513019442558289,
127
+ "learning_rate": 0.00019995946530314385,
128
+ "loss": 0.5736,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.1,
133
+ "grad_norm": 0.06902395933866501,
134
+ "learning_rate": 0.00019994482911979468,
135
+ "loss": 0.556,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.11,
140
+ "grad_norm": 0.07314619421958923,
141
+ "learning_rate": 0.00019992794210340706,
142
+ "loss": 0.5469,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.11,
147
+ "grad_norm": 0.06833848357200623,
148
+ "learning_rate": 0.00019990880463428937,
149
+ "loss": 0.5448,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.12,
154
+ "grad_norm": 0.07301248610019684,
155
+ "learning_rate": 0.00019988741714343177,
156
+ "loss": 0.5612,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.12,
161
+ "grad_norm": 0.07063400000333786,
162
+ "learning_rate": 0.0001998637801124968,
163
+ "loss": 0.5446,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.13,
168
+ "grad_norm": 0.06935883313417435,
169
+ "learning_rate": 0.00019983789407380828,
170
+ "loss": 0.5223,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.14,
175
+ "grad_norm": 0.06576420366764069,
176
+ "learning_rate": 0.00019980975961033924,
177
+ "loss": 0.5351,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.14,
182
+ "grad_norm": 0.07276671379804611,
183
+ "learning_rate": 0.00019977937735569915,
184
+ "loss": 0.5423,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.15,
189
+ "grad_norm": 0.0756976306438446,
190
+ "learning_rate": 0.00019974674799411925,
191
+ "loss": 0.5344,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.15,
196
+ "grad_norm": 0.06945928931236267,
197
+ "learning_rate": 0.00019971187226043745,
198
+ "loss": 0.5198,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.16,
203
+ "grad_norm": 0.06587155908346176,
204
+ "learning_rate": 0.0001996747509400816,
205
+ "loss": 0.5175,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.17,
210
+ "grad_norm": 0.0752682164311409,
211
+ "learning_rate": 0.0001996353848690519,
212
+ "loss": 0.5068,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.17,
217
+ "grad_norm": 0.0740601122379303,
218
+ "learning_rate": 0.00019959377493390196,
219
+ "loss": 0.535,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.18,
224
+ "grad_norm": 0.07076304405927658,
225
+ "learning_rate": 0.00019954992207171898,
226
+ "loss": 0.5079,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.18,
231
+ "grad_norm": 0.0776033028960228,
232
+ "learning_rate": 0.00019950382727010254,
233
+ "loss": 0.5124,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.19,
238
+ "grad_norm": 0.0779872015118599,
239
+ "learning_rate": 0.00019945549156714234,
240
+ "loss": 0.5146,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.2,
245
+ "grad_norm": 0.08037945628166199,
246
+ "learning_rate": 0.00019940491605139498,
247
+ "loss": 0.5189,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.2,
252
+ "grad_norm": 0.06880298256874084,
253
+ "learning_rate": 0.0001993521018618592,
254
+ "loss": 0.506,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.21,
259
+ "grad_norm": 0.0755767747759819,
260
+ "learning_rate": 0.00019929705018795053,
261
+ "loss": 0.4997,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.21,
266
+ "grad_norm": 0.07505559921264648,
267
+ "learning_rate": 0.00019923976226947417,
268
+ "loss": 0.502,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.22,
273
+ "grad_norm": 0.07533205300569534,
274
+ "learning_rate": 0.00019918023939659733,
275
+ "loss": 0.5093,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.23,
280
+ "grad_norm": 0.0748637244105339,
281
+ "learning_rate": 0.0001991184829098201,
282
+ "loss": 0.4976,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.23,
287
+ "grad_norm": 0.076931431889534,
288
+ "learning_rate": 0.00019905449419994518,
289
+ "loss": 0.4992,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.24,
294
+ "grad_norm": 0.07511387020349503,
295
+ "learning_rate": 0.0001989882747080466,
296
+ "loss": 0.5069,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.24,
301
+ "grad_norm": 0.0723625123500824,
302
+ "learning_rate": 0.00019891982592543746,
303
+ "loss": 0.4952,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.25,
308
+ "grad_norm": 0.07320375740528107,
309
+ "learning_rate": 0.00019884914939363588,
310
+ "loss": 0.5093,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.25,
315
+ "eval_loss": 0.5259941220283508,
316
+ "eval_runtime": 21.4684,
317
+ "eval_samples_per_second": 46.254,
318
+ "eval_steps_per_second": 11.598,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.26,
323
+ "grad_norm": 0.07251272350549698,
324
+ "learning_rate": 0.00019877624670433086,
325
+ "loss": 0.4931,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.26,
330
+ "grad_norm": 0.07731667906045914,
331
+ "learning_rate": 0.00019870111949934599,
332
+ "loss": 0.4879,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.27,
337
+ "grad_norm": 0.074358269572258,
338
+ "learning_rate": 0.00019862376947060264,
339
+ "loss": 0.5049,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.27,
344
+ "grad_norm": 0.0808371901512146,
345
+ "learning_rate": 0.0001985441983600819,
346
+ "loss": 0.517,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.28,
351
+ "grad_norm": 0.07559769600629807,
352
+ "learning_rate": 0.00019846240795978528,
353
+ "loss": 0.4834,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.28,
358
+ "grad_norm": 0.07425505667924881,
359
+ "learning_rate": 0.00019837840011169438,
360
+ "loss": 0.5138,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.29,
365
+ "grad_norm": 0.07782939821481705,
366
+ "learning_rate": 0.00019829217670772935,
367
+ "loss": 0.4858,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.3,
372
+ "grad_norm": 0.0754002034664154,
373
+ "learning_rate": 0.00019820373968970642,
374
+ "loss": 0.4941,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3,
379
+ "grad_norm": 0.07364428788423538,
380
+ "learning_rate": 0.000198113091049294,
381
+ "loss": 0.4835,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.31,
386
+ "grad_norm": 0.08309967815876007,
387
+ "learning_rate": 0.00019802023282796796,
388
+ "loss": 0.5237,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.31,
393
+ "grad_norm": 0.07548778504133224,
394
+ "learning_rate": 0.00019792516711696556,
395
+ "loss": 0.4923,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.32,
400
+ "grad_norm": 0.07607278972864151,
401
+ "learning_rate": 0.0001978278960572384,
402
+ "loss": 0.4971,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.33,
407
+ "grad_norm": 0.07432844489812851,
408
+ "learning_rate": 0.00019772842183940422,
409
+ "loss": 0.4874,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.33,
414
+ "grad_norm": 0.077260322868824,
415
+ "learning_rate": 0.00019762674670369755,
416
+ "loss": 0.5067,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.34,
421
+ "grad_norm": 0.08594146370887756,
422
+ "learning_rate": 0.00019752287293991927,
423
+ "loss": 0.4804,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.34,
428
+ "grad_norm": 0.075816310942173,
429
+ "learning_rate": 0.00019741680288738492,
430
+ "loss": 0.4738,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.35,
435
+ "grad_norm": 0.07784326374530792,
436
+ "learning_rate": 0.00019730853893487228,
437
+ "loss": 0.4768,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.36,
442
+ "grad_norm": 0.08903329074382782,
443
+ "learning_rate": 0.00019719808352056724,
444
+ "loss": 0.4773,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.36,
449
+ "grad_norm": 0.07911587506532669,
450
+ "learning_rate": 0.00019708543913200924,
451
+ "loss": 0.4672,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.37,
456
+ "grad_norm": 0.07881385087966919,
457
+ "learning_rate": 0.00019697060830603494,
458
+ "loss": 0.4824,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.37,
463
+ "grad_norm": 0.08292945474386215,
464
+ "learning_rate": 0.00019685359362872125,
465
+ "loss": 0.4814,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.38,
470
+ "grad_norm": 0.08237861096858978,
471
+ "learning_rate": 0.00019673439773532713,
472
+ "loss": 0.486,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.39,
477
+ "grad_norm": 0.07958442717790604,
478
+ "learning_rate": 0.0001966130233102341,
479
+ "loss": 0.4913,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.39,
484
+ "grad_norm": 0.07969169318675995,
485
+ "learning_rate": 0.00019648947308688593,
486
+ "loss": 0.4781,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4,
491
+ "grad_norm": 0.08310563862323761,
492
+ "learning_rate": 0.00019636374984772692,
493
+ "loss": 0.4811,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4,
498
+ "grad_norm": 0.07763976603746414,
499
+ "learning_rate": 0.00019623585642413938,
500
+ "loss": 0.4809,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.41,
505
+ "grad_norm": 0.0927213802933693,
506
+ "learning_rate": 0.00019610579569637982,
507
+ "loss": 0.5019,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.42,
512
+ "grad_norm": 0.08405344933271408,
513
+ "learning_rate": 0.000195973570593514,
514
+ "loss": 0.5001,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.42,
519
+ "grad_norm": 0.07862479984760284,
520
+ "learning_rate": 0.0001958391840933512,
521
+ "loss": 0.4894,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.43,
526
+ "grad_norm": 0.07815296947956085,
527
+ "learning_rate": 0.00019570263922237687,
528
+ "loss": 0.4676,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.43,
533
+ "grad_norm": 0.07999672740697861,
534
+ "learning_rate": 0.00019556393905568458,
535
+ "loss": 0.4857,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.44,
540
+ "grad_norm": 0.08266247063875198,
541
+ "learning_rate": 0.0001954230867169069,
542
+ "loss": 0.4842,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.45,
547
+ "grad_norm": 0.08117777854204178,
548
+ "learning_rate": 0.00019528008537814486,
549
+ "loss": 0.4602,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.45,
554
+ "grad_norm": 0.08203484117984772,
555
+ "learning_rate": 0.00019513493825989664,
556
+ "loss": 0.4761,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.46,
561
+ "grad_norm": 0.07647153735160828,
562
+ "learning_rate": 0.00019498764863098495,
563
+ "loss": 0.4839,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.46,
568
+ "grad_norm": 0.0811714455485344,
569
+ "learning_rate": 0.00019483821980848347,
570
+ "loss": 0.4803,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.47,
575
+ "grad_norm": 0.08266978710889816,
576
+ "learning_rate": 0.00019468665515764215,
577
+ "loss": 0.4665,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.47,
582
+ "grad_norm": 0.07869689911603928,
583
+ "learning_rate": 0.00019453295809181143,
584
+ "loss": 0.4857,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.48,
589
+ "grad_norm": 0.08934654295444489,
590
+ "learning_rate": 0.00019437713207236525,
591
+ "loss": 0.4825,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.49,
596
+ "grad_norm": 0.07842836529016495,
597
+ "learning_rate": 0.00019421918060862333,
598
+ "loss": 0.4609,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.49,
603
+ "grad_norm": 0.08244986832141876,
604
+ "learning_rate": 0.0001940591072577719,
605
+ "loss": 0.4688,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5,
610
+ "grad_norm": 0.07819854468107224,
611
+ "learning_rate": 0.00019389691562478374,
612
+ "loss": 0.4665,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5,
617
+ "eval_loss": 0.5117939114570618,
618
+ "eval_runtime": 21.4742,
619
+ "eval_samples_per_second": 46.242,
620
+ "eval_steps_per_second": 11.595,
621
+ "step": 84
622
+ },
623
+ {
624
+ "epoch": 0.5,
625
+ "grad_norm": 0.0837428942322731,
626
+ "learning_rate": 0.0001937326093623369,
627
+ "loss": 0.4952,
628
+ "step": 85
629
+ },
630
+ {
631
+ "epoch": 0.51,
632
+ "grad_norm": 0.07781701534986496,
633
+ "learning_rate": 0.00019356619217073253,
634
+ "loss": 0.467,
635
+ "step": 86
636
+ },
637
+ {
638
+ "epoch": 0.52,
639
+ "grad_norm": 0.08447270840406418,
640
+ "learning_rate": 0.00019339766779781145,
641
+ "loss": 0.4838,
642
+ "step": 87
643
+ },
644
+ {
645
+ "epoch": 0.52,
646
+ "grad_norm": 0.08231997489929199,
647
+ "learning_rate": 0.00019322704003886987,
648
+ "loss": 0.4611,
649
+ "step": 88
650
+ },
651
+ {
652
+ "epoch": 0.53,
653
+ "grad_norm": 0.08507382869720459,
654
+ "learning_rate": 0.00019305431273657374,
655
+ "loss": 0.4757,
656
+ "step": 89
657
+ },
658
+ {
659
+ "epoch": 0.53,
660
+ "grad_norm": 0.08521989732980728,
661
+ "learning_rate": 0.0001928794897808724,
662
+ "loss": 0.4854,
663
+ "step": 90
664
+ },
665
+ {
666
+ "epoch": 0.54,
667
+ "grad_norm": 0.0963786169886589,
668
+ "learning_rate": 0.00019270257510891082,
669
+ "loss": 0.4505,
670
+ "step": 91
671
+ },
672
+ {
673
+ "epoch": 0.55,
674
+ "grad_norm": 0.08671442419290543,
675
+ "learning_rate": 0.0001925235727049411,
676
+ "loss": 0.4766,
677
+ "step": 92
678
+ },
679
+ {
680
+ "epoch": 0.55,
681
+ "grad_norm": 0.09087081998586655,
682
+ "learning_rate": 0.0001923424866002325,
683
+ "loss": 0.4966,
684
+ "step": 93
685
+ },
686
+ {
687
+ "epoch": 0.56,
688
+ "grad_norm": 0.07899381965398788,
689
+ "learning_rate": 0.00019215932087298092,
690
+ "loss": 0.4638,
691
+ "step": 94
692
+ },
693
+ {
694
+ "epoch": 0.56,
695
+ "grad_norm": 0.09070860594511032,
696
+ "learning_rate": 0.00019197407964821684,
697
+ "loss": 0.4847,
698
+ "step": 95
699
+ },
700
+ {
701
+ "epoch": 0.57,
702
+ "grad_norm": 0.0885949656367302,
703
+ "learning_rate": 0.00019178676709771258,
704
+ "loss": 0.4648,
705
+ "step": 96
706
+ },
707
+ {
708
+ "epoch": 0.58,
709
+ "grad_norm": 0.09253839403390884,
710
+ "learning_rate": 0.00019159738743988825,
711
+ "loss": 0.459,
712
+ "step": 97
713
+ },
714
+ {
715
+ "epoch": 0.58,
716
+ "grad_norm": 0.08571318536996841,
717
+ "learning_rate": 0.00019140594493971674,
718
+ "loss": 0.4797,
719
+ "step": 98
720
+ },
721
+ {
722
+ "epoch": 0.59,
723
+ "grad_norm": 0.07787954807281494,
724
+ "learning_rate": 0.0001912124439086278,
725
+ "loss": 0.4547,
726
+ "step": 99
727
+ },
728
+ {
729
+ "epoch": 0.59,
730
+ "grad_norm": 0.08822935819625854,
731
+ "learning_rate": 0.00019101688870441078,
732
+ "loss": 0.4511,
733
+ "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6,
737
+ "grad_norm": 0.08409956842660904,
738
+ "learning_rate": 0.0001908192837311166,
739
+ "loss": 0.4631,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.61,
744
+ "grad_norm": 0.08279416710138321,
745
+ "learning_rate": 0.00019061963343895846,
746
+ "loss": 0.4696,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.61,
751
+ "grad_norm": 0.09696204960346222,
752
+ "learning_rate": 0.00019041794232421176,
753
+ "loss": 0.4862,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.62,
758
+ "grad_norm": 0.08494329452514648,
759
+ "learning_rate": 0.00019021421492911272,
760
+ "loss": 0.4557,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.62,
765
+ "grad_norm": 0.08702557533979416,
766
+ "learning_rate": 0.00019000845584175616,
767
+ "loss": 0.4693,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.63,
772
+ "grad_norm": 0.09048158675432205,
773
+ "learning_rate": 0.00018980066969599216,
774
+ "loss": 0.4714,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.64,
779
+ "grad_norm": 0.08462114632129669,
780
+ "learning_rate": 0.0001895908611713216,
781
+ "loss": 0.4632,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.64,
786
+ "grad_norm": 0.09956546127796173,
787
+ "learning_rate": 0.00018937903499279102,
788
+ "loss": 0.4638,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.65,
793
+ "grad_norm": 0.08630617707967758,
794
+ "learning_rate": 0.00018916519593088584,
795
+ "loss": 0.4499,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.65,
800
+ "grad_norm": 0.08207620680332184,
801
+ "learning_rate": 0.0001889493488014233,
802
+ "loss": 0.4603,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.66,
807
+ "grad_norm": 0.08473565429449081,
808
+ "learning_rate": 0.00018873149846544376,
809
+ "loss": 0.4571,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.66,
814
+ "grad_norm": 0.08818928152322769,
815
+ "learning_rate": 0.00018851164982910135,
816
+ "loss": 0.4489,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.67,
821
+ "grad_norm": 0.08116699010133743,
822
+ "learning_rate": 0.00018828980784355338,
823
+ "loss": 0.4578,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.68,
828
+ "grad_norm": 0.08832226693630219,
829
+ "learning_rate": 0.00018806597750484897,
830
+ "loss": 0.4719,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.68,
835
+ "grad_norm": 0.08624406903982162,
836
+ "learning_rate": 0.0001878401638538163,
837
+ "loss": 0.4628,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.69,
842
+ "grad_norm": 0.08936543017625809,
843
+ "learning_rate": 0.00018761237197594945,
844
+ "loss": 0.4533,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.69,
849
+ "grad_norm": 0.08579661697149277,
850
+ "learning_rate": 0.00018738260700129354,
851
+ "loss": 0.4772,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7,
856
+ "grad_norm": 0.08271288126707077,
857
+ "learning_rate": 0.0001871508741043293,
858
+ "loss": 0.4773,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.71,
863
+ "grad_norm": 0.08224964886903763,
864
+ "learning_rate": 0.0001869171785038566,
865
+ "loss": 0.4635,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.71,
870
+ "grad_norm": 0.087012380361557,
871
+ "learning_rate": 0.00018668152546287686,
872
+ "loss": 0.4559,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.72,
877
+ "grad_norm": 0.08352699875831604,
878
+ "learning_rate": 0.00018644392028847458,
879
+ "loss": 0.4485,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.72,
884
+ "grad_norm": 0.08281444013118744,
885
+ "learning_rate": 0.00018620436833169772,
886
+ "loss": 0.4393,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.73,
891
+ "grad_norm": 0.08376545459032059,
892
+ "learning_rate": 0.00018596287498743732,
893
+ "loss": 0.4525,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.74,
898
+ "grad_norm": 0.08526434749364853,
899
+ "learning_rate": 0.0001857194456943058,
900
+ "loss": 0.4456,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.74,
905
+ "grad_norm": 0.08151934295892715,
906
+ "learning_rate": 0.0001854740859345148,
907
+ "loss": 0.4576,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.75,
912
+ "grad_norm": 0.08793777972459793,
913
+ "learning_rate": 0.0001852268012337514,
914
+ "loss": 0.4431,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.75,
919
+ "eval_loss": 0.5042669773101807,
920
+ "eval_runtime": 21.4592,
921
+ "eval_samples_per_second": 46.274,
922
+ "eval_steps_per_second": 11.603,
923
+ "step": 126
924
+ },
925
+ {
926
+ "epoch": 0.75,
927
+ "grad_norm": 0.08135095983743668,
928
+ "learning_rate": 0.00018497759716105377,
929
+ "loss": 0.4384,
930
+ "step": 127
931
+ },
932
+ {
933
+ "epoch": 0.76,
934
+ "grad_norm": 0.0917576476931572,
935
+ "learning_rate": 0.0001847264793286859,
936
+ "loss": 0.4687,
937
+ "step": 128
938
+ },
939
+ {
940
+ "epoch": 0.77,
941
+ "grad_norm": 0.08832691609859467,
942
+ "learning_rate": 0.00018447345339201102,
943
+ "loss": 0.4386,
944
+ "step": 129
945
+ },
946
+ {
947
+ "epoch": 0.77,
948
+ "grad_norm": 0.08340886980295181,
949
+ "learning_rate": 0.00018421852504936438,
950
+ "loss": 0.4512,
951
+ "step": 130
952
+ },
953
+ {
954
+ "epoch": 0.78,
955
+ "grad_norm": 0.08589499443769455,
956
+ "learning_rate": 0.00018396170004192475,
957
+ "loss": 0.4387,
958
+ "step": 131
959
+ },
960
+ {
961
+ "epoch": 0.78,
962
+ "grad_norm": 0.08753557503223419,
963
+ "learning_rate": 0.00018370298415358526,
964
+ "loss": 0.4615,
965
+ "step": 132
966
+ },
967
+ {
968
+ "epoch": 0.79,
969
+ "grad_norm": 0.08406232297420502,
970
+ "learning_rate": 0.00018344238321082315,
971
+ "loss": 0.4465,
972
+ "step": 133
973
+ },
974
+ {
975
+ "epoch": 0.8,
976
+ "grad_norm": 0.08514856547117233,
977
+ "learning_rate": 0.0001831799030825685,
978
+ "loss": 0.4516,
979
+ "step": 134
980
+ },
981
+ {
982
+ "epoch": 0.8,
983
+ "grad_norm": 0.09259331226348877,
984
+ "learning_rate": 0.000182915549680072,
985
+ "loss": 0.4387,
986
+ "step": 135
987
+ },
988
+ {
989
+ "epoch": 0.81,
990
+ "grad_norm": 0.08862275630235672,
991
+ "learning_rate": 0.00018264932895677193,
992
+ "loss": 0.4434,
993
+ "step": 136
994
+ },
995
+ {
996
+ "epoch": 0.81,
997
+ "grad_norm": 0.08515379577875137,
998
+ "learning_rate": 0.0001823812469081601,
999
+ "loss": 0.4425,
1000
+ "step": 137
1001
+ },
1002
+ {
1003
+ "epoch": 0.82,
1004
+ "grad_norm": 0.09041007608175278,
1005
+ "learning_rate": 0.00018211130957164668,
1006
+ "loss": 0.4607,
1007
+ "step": 138
1008
+ },
1009
+ {
1010
+ "epoch": 0.82,
1011
+ "grad_norm": 0.08312032371759415,
1012
+ "learning_rate": 0.0001818395230264244,
1013
+ "loss": 0.442,
1014
+ "step": 139
1015
+ },
1016
+ {
1017
+ "epoch": 0.83,
1018
+ "grad_norm": 0.08981412649154663,
1019
+ "learning_rate": 0.00018156589339333152,
1020
+ "loss": 0.4608,
1021
+ "step": 140
1022
+ },
1023
+ {
1024
+ "epoch": 0.84,
1025
+ "grad_norm": 0.08991118520498276,
1026
+ "learning_rate": 0.00018129042683471402,
1027
+ "loss": 0.451,
1028
+ "step": 141
1029
+ },
1030
+ {
1031
+ "epoch": 0.84,
1032
+ "grad_norm": 0.08628728240728378,
1033
+ "learning_rate": 0.00018101312955428692,
1034
+ "loss": 0.4453,
1035
+ "step": 142
1036
+ },
1037
+ {
1038
+ "epoch": 0.85,
1039
+ "grad_norm": 0.08730859309434891,
1040
+ "learning_rate": 0.00018073400779699435,
1041
+ "loss": 0.4485,
1042
+ "step": 143
1043
+ },
1044
+ {
1045
+ "epoch": 0.85,
1046
+ "grad_norm": 0.08489865809679031,
1047
+ "learning_rate": 0.0001804530678488691,
1048
+ "loss": 0.4592,
1049
+ "step": 144
1050
+ },
1051
+ {
1052
+ "epoch": 0.86,
1053
+ "grad_norm": 0.08439410477876663,
1054
+ "learning_rate": 0.00018017031603689102,
1055
+ "loss": 0.4326,
1056
+ "step": 145
1057
+ },
1058
+ {
1059
+ "epoch": 0.87,
1060
+ "grad_norm": 0.09346488118171692,
1061
+ "learning_rate": 0.0001798857587288445,
1062
+ "loss": 0.4484,
1063
+ "step": 146
1064
+ },
1065
+ {
1066
+ "epoch": 0.87,
1067
+ "grad_norm": 0.09130821377038956,
1068
+ "learning_rate": 0.00017959940233317498,
1069
+ "loss": 0.4502,
1070
+ "step": 147
1071
+ },
1072
+ {
1073
+ "epoch": 0.88,
1074
+ "grad_norm": 0.08846256881952286,
1075
+ "learning_rate": 0.0001793112532988448,
1076
+ "loss": 0.4322,
1077
+ "step": 148
1078
+ },
1079
+ {
1080
+ "epoch": 0.88,
1081
+ "grad_norm": 0.09061886370182037,
1082
+ "learning_rate": 0.00017902131811518786,
1083
+ "loss": 0.4437,
1084
+ "step": 149
1085
+ },
1086
+ {
1087
+ "epoch": 0.89,
1088
+ "grad_norm": 0.09259927272796631,
1089
+ "learning_rate": 0.00017872960331176345,
1090
+ "loss": 0.4545,
1091
+ "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.9,
1095
+ "grad_norm": 0.09632189571857452,
1096
+ "learning_rate": 0.00017843611545820926,
1097
+ "loss": 0.4515,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.9,
1102
+ "grad_norm": 0.08714065700769424,
1103
+ "learning_rate": 0.00017814086116409348,
1104
+ "loss": 0.4602,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.91,
1109
+ "grad_norm": 0.09537078440189362,
1110
+ "learning_rate": 0.00017784384707876576,
1111
+ "loss": 0.4482,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.91,
1116
+ "grad_norm": 0.09175322949886322,
1117
+ "learning_rate": 0.00017754507989120764,
1118
+ "loss": 0.4681,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.92,
1123
+ "grad_norm": 0.08962789177894592,
1124
+ "learning_rate": 0.00017724456632988187,
1125
+ "loss": 0.4304,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.93,
1130
+ "grad_norm": 0.09643880277872086,
1131
+ "learning_rate": 0.00017694231316258077,
1132
+ "loss": 0.4532,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.93,
1137
+ "grad_norm": 0.08335065096616745,
1138
+ "learning_rate": 0.00017663832719627402,
1139
+ "loss": 0.4504,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.94,
1144
+ "grad_norm": 0.087184838950634,
1145
+ "learning_rate": 0.0001763326152769551,
1146
+ "loss": 0.4752,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.94,
1151
+ "grad_norm": 0.08858635276556015,
1152
+ "learning_rate": 0.0001760251842894874,
1153
+ "loss": 0.4413,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.95,
1158
+ "grad_norm": 0.08101391792297363,
1159
+ "learning_rate": 0.00017571604115744892,
1160
+ "loss": 0.4465,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.96,
1165
+ "grad_norm": 0.08623132854700089,
1166
+ "learning_rate": 0.0001754051928429765,
1167
+ "loss": 0.4673,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.96,
1172
+ "grad_norm": 0.0922100692987442,
1173
+ "learning_rate": 0.00017509264634660895,
1174
+ "loss": 0.4587,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.97,
1179
+ "grad_norm": 0.08243449032306671,
1180
+ "learning_rate": 0.00017477840870712945,
1181
+ "loss": 0.4368,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.97,
1186
+ "grad_norm": 0.0845554992556572,
1187
+ "learning_rate": 0.00017446248700140693,
1188
+ "loss": 0.4209,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.98,
1193
+ "grad_norm": 0.08277452737092972,
1194
+ "learning_rate": 0.00017414488834423687,
1195
+ "loss": 0.4397,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.99,
1200
+ "grad_norm": 0.0826331302523613,
1201
+ "learning_rate": 0.00017382561988818086,
1202
+ "loss": 0.4333,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.99,
1207
+ "grad_norm": 0.08441821485757828,
1208
+ "learning_rate": 0.0001735046888234057,
1209
+ "loss": 0.4496,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 1.0,
1214
+ "grad_norm": 0.08665426075458527,
1215
+ "learning_rate": 0.00017318210237752136,
1216
+ "loss": 0.4523,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 1.0,
1221
+ "eval_loss": 0.4984985589981079,
1222
+ "eval_runtime": 21.4662,
1223
+ "eval_samples_per_second": 46.259,
1224
+ "eval_steps_per_second": 11.6,
1225
+ "step": 168
1226
+ },
1227
+ {
1228
+ "epoch": 1.0,
1229
+ "grad_norm": 0.08923573791980743,
1230
+ "learning_rate": 0.00017285786781541824,
1231
+ "loss": 0.4735,
1232
+ "step": 169
1233
+ },
1234
+ {
1235
+ "epoch": 1.01,
1236
+ "grad_norm": 0.08524107187986374,
1237
+ "learning_rate": 0.00017253199243910357,
1238
+ "loss": 0.4323,
1239
+ "step": 170
1240
+ },
1241
+ {
1242
+ "epoch": 1.01,
1243
+ "grad_norm": 0.09072479605674744,
1244
+ "learning_rate": 0.00017220448358753692,
1245
+ "loss": 0.4617,
1246
+ "step": 171
1247
+ },
1248
+ {
1249
+ "epoch": 1.01,
1250
+ "grad_norm": 0.08986588567495346,
1251
+ "learning_rate": 0.0001718753486364651,
1252
+ "loss": 0.4264,
1253
+ "step": 172
1254
+ },
1255
+ {
1256
+ "epoch": 1.01,
1257
+ "grad_norm": 0.09549989551305771,
1258
+ "learning_rate": 0.00017154459499825564,
1259
+ "loss": 0.4042,
1260
+ "step": 173
1261
+ },
1262
+ {
1263
+ "epoch": 1.02,
1264
+ "grad_norm": 0.09217043220996857,
1265
+ "learning_rate": 0.0001712122301217304,
1266
+ "loss": 0.4028,
1267
+ "step": 174
1268
+ },
1269
+ {
1270
+ "epoch": 1.02,
1271
+ "grad_norm": 0.10525793582201004,
1272
+ "learning_rate": 0.00017087826149199734,
1273
+ "loss": 0.4176,
1274
+ "step": 175
1275
+ },
1276
+ {
1277
+ "epoch": 1.03,
1278
+ "grad_norm": 0.10329723358154297,
1279
+ "learning_rate": 0.00017054269663028233,
1280
+ "loss": 0.4062,
1281
+ "step": 176
1282
+ },
1283
+ {
1284
+ "epoch": 1.04,
1285
+ "grad_norm": 0.10040964931249619,
1286
+ "learning_rate": 0.00017020554309375946,
1287
+ "loss": 0.4222,
1288
+ "step": 177
1289
+ },
1290
+ {
1291
+ "epoch": 1.04,
1292
+ "grad_norm": 0.10112589597702026,
1293
+ "learning_rate": 0.00016986680847538106,
1294
+ "loss": 0.4058,
1295
+ "step": 178
1296
+ },
1297
+ {
1298
+ "epoch": 1.05,
1299
+ "grad_norm": 0.09155958890914917,
1300
+ "learning_rate": 0.0001695265004037065,
1301
+ "loss": 0.4045,
1302
+ "step": 179
1303
+ },
1304
+ {
1305
+ "epoch": 1.05,
1306
+ "grad_norm": 0.10278405249118805,
1307
+ "learning_rate": 0.00016918462654273063,
1308
+ "loss": 0.4294,
1309
+ "step": 180
1310
+ },
1311
+ {
1312
+ "epoch": 1.06,
1313
+ "grad_norm": 0.10295873880386353,
1314
+ "learning_rate": 0.00016884119459171105,
1315
+ "loss": 0.4025,
1316
+ "step": 181
1317
+ },
1318
+ {
1319
+ "epoch": 1.07,
1320
+ "grad_norm": 0.09759877622127533,
1321
+ "learning_rate": 0.0001684962122849946,
1322
+ "loss": 0.4227,
1323
+ "step": 182
1324
+ },
1325
+ {
1326
+ "epoch": 1.07,
1327
+ "grad_norm": 0.09612429887056351,
1328
+ "learning_rate": 0.00016814968739184343,
1329
+ "loss": 0.3991,
1330
+ "step": 183
1331
+ },
1332
+ {
1333
+ "epoch": 1.08,
1334
+ "grad_norm": 0.09644313901662827,
1335
+ "learning_rate": 0.00016780162771625986,
1336
+ "loss": 0.4271,
1337
+ "step": 184
1338
+ },
1339
+ {
1340
+ "epoch": 1.08,
1341
+ "grad_norm": 0.09357411414384842,
1342
+ "learning_rate": 0.00016745204109681064,
1343
+ "loss": 0.4017,
1344
+ "step": 185
1345
+ },
1346
+ {
1347
+ "epoch": 1.09,
1348
+ "grad_norm": 0.09177077561616898,
1349
+ "learning_rate": 0.00016710093540645056,
1350
+ "loss": 0.386,
1351
+ "step": 186
1352
+ },
1353
+ {
1354
+ "epoch": 1.09,
1355
+ "grad_norm": 0.10068117827177048,
1356
+ "learning_rate": 0.00016674831855234486,
1357
+ "loss": 0.4127,
1358
+ "step": 187
1359
+ },
1360
+ {
1361
+ "epoch": 1.1,
1362
+ "grad_norm": 0.09634707123041153,
1363
+ "learning_rate": 0.00016639419847569147,
1364
+ "loss": 0.403,
1365
+ "step": 188
1366
+ },
1367
+ {
1368
+ "epoch": 1.11,
1369
+ "grad_norm": 0.09533964842557907,
1370
+ "learning_rate": 0.00016603858315154195,
1371
+ "loss": 0.4004,
1372
+ "step": 189
1373
+ },
1374
+ {
1375
+ "epoch": 1.11,
1376
+ "grad_norm": 0.09449424594640732,
1377
+ "learning_rate": 0.00016568148058862197,
1378
+ "loss": 0.4136,
1379
+ "step": 190
1380
+ },
1381
+ {
1382
+ "epoch": 1.12,
1383
+ "grad_norm": 0.09432344883680344,
1384
+ "learning_rate": 0.00016532289882915103,
1385
+ "loss": 0.403,
1386
+ "step": 191
1387
+ },
1388
+ {
1389
+ "epoch": 1.12,
1390
+ "grad_norm": 0.10496091097593307,
1391
+ "learning_rate": 0.00016496284594866113,
1392
+ "loss": 0.423,
1393
+ "step": 192
1394
+ },
1395
+ {
1396
+ "epoch": 1.13,
1397
+ "grad_norm": 0.0957692563533783,
1398
+ "learning_rate": 0.00016460133005581512,
1399
+ "loss": 0.4032,
1400
+ "step": 193
1401
+ },
1402
+ {
1403
+ "epoch": 1.14,
1404
+ "grad_norm": 0.10207226127386093,
1405
+ "learning_rate": 0.0001642383592922239,
1406
+ "loss": 0.4068,
1407
+ "step": 194
1408
+ },
1409
+ {
1410
+ "epoch": 1.14,
1411
+ "grad_norm": 0.10685818642377853,
1412
+ "learning_rate": 0.00016387394183226328,
1413
+ "loss": 0.4194,
1414
+ "step": 195
1415
+ },
1416
+ {
1417
+ "epoch": 1.15,
1418
+ "grad_norm": 0.09566125273704529,
1419
+ "learning_rate": 0.00016350808588288965,
1420
+ "loss": 0.3717,
1421
+ "step": 196
1422
+ },
1423
+ {
1424
+ "epoch": 1.15,
1425
+ "grad_norm": 0.10426433384418488,
1426
+ "learning_rate": 0.0001631407996834553,
1427
+ "loss": 0.4197,
1428
+ "step": 197
1429
+ },
1430
+ {
1431
+ "epoch": 1.16,
1432
+ "grad_norm": 0.09626364707946777,
1433
+ "learning_rate": 0.00016277209150552285,
1434
+ "loss": 0.3965,
1435
+ "step": 198
1436
+ },
1437
+ {
1438
+ "epoch": 1.17,
1439
+ "grad_norm": 0.10416010022163391,
1440
+ "learning_rate": 0.000162401969652679,
1441
+ "loss": 0.4042,
1442
+ "step": 199
1443
+ },
1444
+ {
1445
+ "epoch": 1.17,
1446
+ "grad_norm": 0.11229964345693588,
1447
+ "learning_rate": 0.0001620304424603474,
1448
+ "loss": 0.4039,
1449
+ "step": 200
1450
+ },
1451
+ {
1452
+ "epoch": 1.18,
1453
+ "grad_norm": 0.09705965220928192,
1454
+ "learning_rate": 0.00016165751829560102,
1455
+ "loss": 0.4111,
1456
+ "step": 201
1457
+ },
1458
+ {
1459
+ "epoch": 1.18,
1460
+ "grad_norm": 0.09751327335834503,
1461
+ "learning_rate": 0.00016128320555697364,
1462
+ "loss": 0.4007,
1463
+ "step": 202
1464
+ },
1465
+ {
1466
+ "epoch": 1.19,
1467
+ "grad_norm": 0.09729477018117905,
1468
+ "learning_rate": 0.000160907512674271,
1469
+ "loss": 0.4025,
1470
+ "step": 203
1471
+ },
1472
+ {
1473
+ "epoch": 1.2,
1474
+ "grad_norm": 0.09977483749389648,
1475
+ "learning_rate": 0.00016053044810838046,
1476
+ "loss": 0.4143,
1477
+ "step": 204
1478
+ },
1479
+ {
1480
+ "epoch": 1.2,
1481
+ "grad_norm": 0.10283766686916351,
1482
+ "learning_rate": 0.0001601520203510809,
1483
+ "loss": 0.4093,
1484
+ "step": 205
1485
+ },
1486
+ {
1487
+ "epoch": 1.21,
1488
+ "grad_norm": 0.10398785024881363,
1489
+ "learning_rate": 0.00015977223792485118,
1490
+ "loss": 0.409,
1491
+ "step": 206
1492
+ },
1493
+ {
1494
+ "epoch": 1.21,
1495
+ "grad_norm": 0.10487958043813705,
1496
+ "learning_rate": 0.0001593911093826784,
1497
+ "loss": 0.4102,
1498
+ "step": 207
1499
+ },
1500
+ {
1501
+ "epoch": 1.22,
1502
+ "grad_norm": 0.10372807830572128,
1503
+ "learning_rate": 0.00015900864330786518,
1504
+ "loss": 0.4082,
1505
+ "step": 208
1506
+ },
1507
+ {
1508
+ "epoch": 1.23,
1509
+ "grad_norm": 0.09674819558858871,
1510
+ "learning_rate": 0.00015862484831383644,
1511
+ "loss": 0.4093,
1512
+ "step": 209
1513
+ },
1514
+ {
1515
+ "epoch": 1.23,
1516
+ "grad_norm": 0.09968870133161545,
1517
+ "learning_rate": 0.00015823973304394525,
1518
+ "loss": 0.4237,
1519
+ "step": 210
1520
+ },
1521
+ {
1522
+ "epoch": 1.23,
1523
+ "eval_loss": 0.4985295832157135,
1524
+ "eval_runtime": 21.4597,
1525
+ "eval_samples_per_second": 46.273,
1526
+ "eval_steps_per_second": 11.603,
1527
+ "step": 210
1528
+ },
1529
+ {
1530
+ "epoch": 1.24,
1531
+ "grad_norm": 0.10222364962100983,
1532
+ "learning_rate": 0.00015785330617127842,
1533
+ "loss": 0.4032,
1534
+ "step": 211
1535
+ },
1536
+ {
1537
+ "epoch": 1.24,
1538
+ "grad_norm": 0.09916388243436813,
1539
+ "learning_rate": 0.00015746557639846097,
1540
+ "loss": 0.4113,
1541
+ "step": 212
1542
+ },
1543
+ {
1544
+ "epoch": 1.25,
1545
+ "grad_norm": 0.1033184677362442,
1546
+ "learning_rate": 0.0001570765524574602,
1547
+ "loss": 0.3956,
1548
+ "step": 213
1549
+ },
1550
+ {
1551
+ "epoch": 1.26,
1552
+ "grad_norm": 0.11059914529323578,
1553
+ "learning_rate": 0.00015668624310938913,
1554
+ "loss": 0.404,
1555
+ "step": 214
1556
+ },
1557
+ {
1558
+ "epoch": 1.26,
1559
+ "grad_norm": 0.0982404425740242,
1560
+ "learning_rate": 0.00015629465714430904,
1561
+ "loss": 0.3875,
1562
+ "step": 215
1563
+ },
1564
+ {
1565
+ "epoch": 1.27,
1566
+ "grad_norm": 0.1017359048128128,
1567
+ "learning_rate": 0.0001559018033810316,
1568
+ "loss": 0.4033,
1569
+ "step": 216
1570
+ },
1571
+ {
1572
+ "epoch": 1.27,
1573
+ "grad_norm": 0.1090175062417984,
1574
+ "learning_rate": 0.00015550769066692034,
1575
+ "loss": 0.4084,
1576
+ "step": 217
1577
+ },
1578
+ {
1579
+ "epoch": 1.28,
1580
+ "grad_norm": 0.1041378527879715,
1581
+ "learning_rate": 0.00015511232787769123,
1582
+ "loss": 0.4095,
1583
+ "step": 218
1584
+ },
1585
+ {
1586
+ "epoch": 1.28,
1587
+ "grad_norm": 0.0929458811879158,
1588
+ "learning_rate": 0.00015471572391721284,
1589
+ "loss": 0.3892,
1590
+ "step": 219
1591
+ },
1592
+ {
1593
+ "epoch": 1.29,
1594
+ "grad_norm": 0.10203150659799576,
1595
+ "learning_rate": 0.00015431788771730597,
1596
+ "loss": 0.3967,
1597
+ "step": 220
1598
+ },
1599
+ {
1600
+ "epoch": 1.3,
1601
+ "grad_norm": 0.10682693123817444,
1602
+ "learning_rate": 0.00015391882823754228,
1603
+ "loss": 0.4164,
1604
+ "step": 221
1605
+ },
1606
+ {
1607
+ "epoch": 1.3,
1608
+ "grad_norm": 0.10250475257635117,
1609
+ "learning_rate": 0.00015351855446504268,
1610
+ "loss": 0.402,
1611
+ "step": 222
1612
+ },
1613
+ {
1614
+ "epoch": 1.31,
1615
+ "grad_norm": 0.09453174471855164,
1616
+ "learning_rate": 0.00015311707541427487,
1617
+ "loss": 0.3927,
1618
+ "step": 223
1619
+ },
1620
+ {
1621
+ "epoch": 1.31,
1622
+ "grad_norm": 0.09379514306783676,
1623
+ "learning_rate": 0.00015271440012685025,
1624
+ "loss": 0.3825,
1625
+ "step": 224
1626
+ },
1627
+ {
1628
+ "epoch": 1.32,
1629
+ "grad_norm": 0.09439584612846375,
1630
+ "learning_rate": 0.00015231053767132045,
1631
+ "loss": 0.3798,
1632
+ "step": 225
1633
+ },
1634
+ {
1635
+ "epoch": 1.33,
1636
+ "grad_norm": 0.10218024253845215,
1637
+ "learning_rate": 0.00015190549714297303,
1638
+ "loss": 0.3909,
1639
+ "step": 226
1640
+ },
1641
+ {
1642
+ "epoch": 1.33,
1643
+ "grad_norm": 0.10314662754535675,
1644
+ "learning_rate": 0.00015149928766362657,
1645
+ "loss": 0.4075,
1646
+ "step": 227
1647
+ },
1648
+ {
1649
+ "epoch": 1.34,
1650
+ "grad_norm": 0.10139516741037369,
1651
+ "learning_rate": 0.00015109191838142536,
1652
+ "loss": 0.4125,
1653
+ "step": 228
1654
+ },
1655
+ {
1656
+ "epoch": 1.34,
1657
+ "grad_norm": 0.10410083085298538,
1658
+ "learning_rate": 0.0001506833984706333,
1659
+ "loss": 0.3998,
1660
+ "step": 229
1661
+ },
1662
+ {
1663
+ "epoch": 1.35,
1664
+ "grad_norm": 0.11478332430124283,
1665
+ "learning_rate": 0.00015027373713142735,
1666
+ "loss": 0.4181,
1667
+ "step": 230
1668
+ },
1669
+ {
1670
+ "epoch": 1.36,
1671
+ "grad_norm": 0.10138574987649918,
1672
+ "learning_rate": 0.00014986294358969028,
1673
+ "loss": 0.4152,
1674
+ "step": 231
1675
+ },
1676
+ {
1677
+ "epoch": 1.36,
1678
+ "grad_norm": 0.0989016592502594,
1679
+ "learning_rate": 0.0001494510270968029,
1680
+ "loss": 0.399,
1681
+ "step": 232
1682
+ },
1683
+ {
1684
+ "epoch": 1.37,
1685
+ "grad_norm": 0.10673234611749649,
1686
+ "learning_rate": 0.00014903799692943574,
1687
+ "loss": 0.4246,
1688
+ "step": 233
1689
+ },
1690
+ {
1691
+ "epoch": 1.37,
1692
+ "grad_norm": 0.10326199978590012,
1693
+ "learning_rate": 0.00014862386238934016,
1694
+ "loss": 0.4033,
1695
+ "step": 234
1696
+ },
1697
+ {
1698
+ "epoch": 1.38,
1699
+ "grad_norm": 0.09947673231363297,
1700
+ "learning_rate": 0.00014820863280313873,
1701
+ "loss": 0.3886,
1702
+ "step": 235
1703
+ },
1704
+ {
1705
+ "epoch": 1.39,
1706
+ "grad_norm": 0.09778755158185959,
1707
+ "learning_rate": 0.00014779231752211548,
1708
+ "loss": 0.3934,
1709
+ "step": 236
1710
+ },
1711
+ {
1712
+ "epoch": 1.39,
1713
+ "grad_norm": 0.09947831183671951,
1714
+ "learning_rate": 0.0001473749259220048,
1715
+ "loss": 0.4147,
1716
+ "step": 237
1717
+ },
1718
+ {
1719
+ "epoch": 1.4,
1720
+ "grad_norm": 0.10698696970939636,
1721
+ "learning_rate": 0.00014695646740278085,
1722
+ "loss": 0.3773,
1723
+ "step": 238
1724
+ },
1725
+ {
1726
+ "epoch": 1.4,
1727
+ "grad_norm": 0.09899724274873734,
1728
+ "learning_rate": 0.00014653695138844557,
1729
+ "loss": 0.4005,
1730
+ "step": 239
1731
+ },
1732
+ {
1733
+ "epoch": 1.41,
1734
+ "grad_norm": 0.10226688534021378,
1735
+ "learning_rate": 0.0001461163873268164,
1736
+ "loss": 0.4009,
1737
+ "step": 240
1738
+ },
1739
+ {
1740
+ "epoch": 1.42,
1741
+ "grad_norm": 0.10390684753656387,
1742
+ "learning_rate": 0.0001456947846893137,
1743
+ "loss": 0.4129,
1744
+ "step": 241
1745
+ },
1746
+ {
1747
+ "epoch": 1.42,
1748
+ "grad_norm": 0.09909753501415253,
1749
+ "learning_rate": 0.0001452721529707473,
1750
+ "loss": 0.3773,
1751
+ "step": 242
1752
+ },
1753
+ {
1754
+ "epoch": 1.43,
1755
+ "grad_norm": 0.09814441949129105,
1756
+ "learning_rate": 0.00014484850168910263,
1757
+ "loss": 0.3976,
1758
+ "step": 243
1759
+ },
1760
+ {
1761
+ "epoch": 1.43,
1762
+ "grad_norm": 0.10027995705604553,
1763
+ "learning_rate": 0.00014442384038532665,
1764
+ "loss": 0.3951,
1765
+ "step": 244
1766
+ },
1767
+ {
1768
+ "epoch": 1.44,
1769
+ "grad_norm": 0.0988469123840332,
1770
+ "learning_rate": 0.00014399817862311256,
1771
+ "loss": 0.3734,
1772
+ "step": 245
1773
+ },
1774
+ {
1775
+ "epoch": 1.45,
1776
+ "grad_norm": 0.09742960333824158,
1777
+ "learning_rate": 0.00014357152598868476,
1778
+ "loss": 0.3826,
1779
+ "step": 246
1780
+ },
1781
+ {
1782
+ "epoch": 1.45,
1783
+ "grad_norm": 0.1014707013964653,
1784
+ "learning_rate": 0.00014314389209058286,
1785
+ "loss": 0.4082,
1786
+ "step": 247
1787
+ },
1788
+ {
1789
+ "epoch": 1.46,
1790
+ "grad_norm": 0.10080685466527939,
1791
+ "learning_rate": 0.00014271528655944522,
1792
+ "loss": 0.4104,
1793
+ "step": 248
1794
+ },
1795
+ {
1796
+ "epoch": 1.46,
1797
+ "grad_norm": 0.1009359136223793,
1798
+ "learning_rate": 0.0001422857190477921,
1799
+ "loss": 0.3912,
1800
+ "step": 249
1801
+ },
1802
+ {
1803
+ "epoch": 1.47,
1804
+ "grad_norm": 0.0964767187833786,
1805
+ "learning_rate": 0.0001418551992298083,
1806
+ "loss": 0.3731,
1807
+ "step": 250
1808
+ },
1809
+ {
1810
+ "epoch": 1.47,
1811
+ "grad_norm": 0.09848513454198837,
1812
+ "learning_rate": 0.0001414237368011253,
1813
+ "loss": 0.3891,
1814
+ "step": 251
1815
+ },
1816
+ {
1817
+ "epoch": 1.48,
1818
+ "grad_norm": 0.10232508182525635,
1819
+ "learning_rate": 0.00014099134147860286,
1820
+ "loss": 0.4002,
1821
+ "step": 252
1822
+ },
1823
+ {
1824
+ "epoch": 1.48,
1825
+ "eval_loss": 0.4975546896457672,
1826
+ "eval_runtime": 21.466,
1827
+ "eval_samples_per_second": 46.259,
1828
+ "eval_steps_per_second": 11.6,
1829
+ "step": 252
1830
+ },
1831
+ {
1832
+ "epoch": 1.49,
1833
+ "grad_norm": 0.10712958872318268,
1834
+ "learning_rate": 0.00014055802300011027,
1835
+ "loss": 0.41,
1836
+ "step": 253
1837
+ },
1838
+ {
1839
+ "epoch": 1.49,
1840
+ "grad_norm": 0.10100317001342773,
1841
+ "learning_rate": 0.0001401237911243069,
1842
+ "loss": 0.3954,
1843
+ "step": 254
1844
+ },
1845
+ {
1846
+ "epoch": 1.5,
1847
+ "grad_norm": 0.09532604366540909,
1848
+ "learning_rate": 0.00013968865563042255,
1849
+ "loss": 0.4111,
1850
+ "step": 255
1851
+ },
1852
+ {
1853
+ "epoch": 1.5,
1854
+ "grad_norm": 0.10244431346654892,
1855
+ "learning_rate": 0.00013925262631803723,
1856
+ "loss": 0.4,
1857
+ "step": 256
1858
+ },
1859
+ {
1860
+ "epoch": 1.51,
1861
+ "grad_norm": 0.10212967544794083,
1862
+ "learning_rate": 0.00013881571300686037,
1863
+ "loss": 0.3996,
1864
+ "step": 257
1865
+ },
1866
+ {
1867
+ "epoch": 1.52,
1868
+ "grad_norm": 0.09606331586837769,
1869
+ "learning_rate": 0.0001383779255365097,
1870
+ "loss": 0.3852,
1871
+ "step": 258
1872
+ },
1873
+ {
1874
+ "epoch": 1.52,
1875
+ "grad_norm": 0.10002104192972183,
1876
+ "learning_rate": 0.00013793927376628976,
1877
+ "loss": 0.4126,
1878
+ "step": 259
1879
+ },
1880
+ {
1881
+ "epoch": 1.53,
1882
+ "grad_norm": 0.10387251526117325,
1883
+ "learning_rate": 0.00013749976757496967,
1884
+ "loss": 0.4146,
1885
+ "step": 260
1886
+ },
1887
+ {
1888
+ "epoch": 1.53,
1889
+ "grad_norm": 0.09998749941587448,
1890
+ "learning_rate": 0.00013705941686056086,
1891
+ "loss": 0.4143,
1892
+ "step": 261
1893
+ },
1894
+ {
1895
+ "epoch": 1.54,
1896
+ "grad_norm": 0.09770024567842484,
1897
+ "learning_rate": 0.00013661823154009395,
1898
+ "loss": 0.3719,
1899
+ "step": 262
1900
+ },
1901
+ {
1902
+ "epoch": 1.55,
1903
+ "grad_norm": 0.10180012881755829,
1904
+ "learning_rate": 0.00013617622154939564,
1905
+ "loss": 0.408,
1906
+ "step": 263
1907
+ },
1908
+ {
1909
+ "epoch": 1.55,
1910
+ "grad_norm": 0.10063595324754715,
1911
+ "learning_rate": 0.00013573339684286472,
1912
+ "loss": 0.4007,
1913
+ "step": 264
1914
+ },
1915
+ {
1916
+ "epoch": 1.56,
1917
+ "grad_norm": 0.10153420269489288,
1918
+ "learning_rate": 0.00013528976739324807,
1919
+ "loss": 0.4054,
1920
+ "step": 265
1921
+ },
1922
+ {
1923
+ "epoch": 1.56,
1924
+ "grad_norm": 0.10569385439157486,
1925
+ "learning_rate": 0.0001348453431914159,
1926
+ "loss": 0.4031,
1927
+ "step": 266
1928
+ },
1929
+ {
1930
+ "epoch": 1.57,
1931
+ "grad_norm": 0.10000584274530411,
1932
+ "learning_rate": 0.00013440013424613698,
1933
+ "loss": 0.4018,
1934
+ "step": 267
1935
+ },
1936
+ {
1937
+ "epoch": 1.58,
1938
+ "grad_norm": 0.09948629140853882,
1939
+ "learning_rate": 0.00013395415058385296,
1940
+ "loss": 0.3997,
1941
+ "step": 268
1942
+ },
1943
+ {
1944
+ "epoch": 1.58,
1945
+ "grad_norm": 0.10179516673088074,
1946
+ "learning_rate": 0.00013350740224845278,
1947
+ "loss": 0.3872,
1948
+ "step": 269
1949
+ },
1950
+ {
1951
+ "epoch": 1.59,
1952
+ "grad_norm": 0.0989665687084198,
1953
+ "learning_rate": 0.00013305989930104638,
1954
+ "loss": 0.3672,
1955
+ "step": 270
1956
+ },
1957
+ {
1958
+ "epoch": 1.59,
1959
+ "grad_norm": 0.09988453984260559,
1960
+ "learning_rate": 0.00013261165181973814,
1961
+ "loss": 0.3978,
1962
+ "step": 271
1963
+ },
1964
+ {
1965
+ "epoch": 1.6,
1966
+ "grad_norm": 0.09958979487419128,
1967
+ "learning_rate": 0.00013216266989939988,
1968
+ "loss": 0.3793,
1969
+ "step": 272
1970
+ },
1971
+ {
1972
+ "epoch": 1.61,
1973
+ "grad_norm": 0.10080169141292572,
1974
+ "learning_rate": 0.0001317129636514435,
1975
+ "loss": 0.4012,
1976
+ "step": 273
1977
+ },
1978
+ {
1979
+ "epoch": 1.61,
1980
+ "grad_norm": 0.10148239880800247,
1981
+ "learning_rate": 0.00013126254320359343,
1982
+ "loss": 0.3904,
1983
+ "step": 274
1984
+ },
1985
+ {
1986
+ "epoch": 1.62,
1987
+ "grad_norm": 0.10728135704994202,
1988
+ "learning_rate": 0.00013081141869965835,
1989
+ "loss": 0.393,
1990
+ "step": 275
1991
+ },
1992
+ {
1993
+ "epoch": 1.62,
1994
+ "grad_norm": 0.09917322546243668,
1995
+ "learning_rate": 0.00013035960029930278,
1996
+ "loss": 0.3725,
1997
+ "step": 276
1998
+ },
1999
+ {
2000
+ "epoch": 1.63,
2001
+ "grad_norm": 0.10163102298974991,
2002
+ "learning_rate": 0.00012990709817781837,
2003
+ "loss": 0.406,
2004
+ "step": 277
2005
+ },
2006
+ {
2007
+ "epoch": 1.64,
2008
+ "grad_norm": 0.09815432131290436,
2009
+ "learning_rate": 0.00012945392252589465,
2010
+ "loss": 0.3995,
2011
+ "step": 278
2012
+ },
2013
+ {
2014
+ "epoch": 1.64,
2015
+ "grad_norm": 0.09806889295578003,
2016
+ "learning_rate": 0.0001290000835493896,
2017
+ "loss": 0.3952,
2018
+ "step": 279
2019
+ },
2020
+ {
2021
+ "epoch": 1.65,
2022
+ "grad_norm": 0.09826052933931351,
2023
+ "learning_rate": 0.0001285455914690997,
2024
+ "loss": 0.402,
2025
+ "step": 280
2026
+ },
2027
+ {
2028
+ "epoch": 1.65,
2029
+ "grad_norm": 0.09949176013469696,
2030
+ "learning_rate": 0.0001280904565205299,
2031
+ "loss": 0.3953,
2032
+ "step": 281
2033
+ },
2034
+ {
2035
+ "epoch": 1.66,
2036
+ "grad_norm": 0.10278761386871338,
2037
+ "learning_rate": 0.00012763468895366303,
2038
+ "loss": 0.4091,
2039
+ "step": 282
2040
+ },
2041
+ {
2042
+ "epoch": 1.66,
2043
+ "grad_norm": 0.10104485601186752,
2044
+ "learning_rate": 0.0001271782990327289,
2045
+ "loss": 0.3807,
2046
+ "step": 283
2047
+ },
2048
+ {
2049
+ "epoch": 1.67,
2050
+ "grad_norm": 0.10103065520524979,
2051
+ "learning_rate": 0.0001267212970359732,
2052
+ "loss": 0.4136,
2053
+ "step": 284
2054
+ },
2055
+ {
2056
+ "epoch": 1.68,
2057
+ "grad_norm": 0.10056735575199127,
2058
+ "learning_rate": 0.0001262636932554261,
2059
+ "loss": 0.3834,
2060
+ "step": 285
2061
+ },
2062
+ {
2063
+ "epoch": 1.68,
2064
+ "grad_norm": 0.10619843006134033,
2065
+ "learning_rate": 0.00012580549799667034,
2066
+ "loss": 0.3926,
2067
+ "step": 286
2068
+ },
2069
+ {
2070
+ "epoch": 1.69,
2071
+ "grad_norm": 0.10867036134004593,
2072
+ "learning_rate": 0.00012534672157860928,
2073
+ "loss": 0.4102,
2074
+ "step": 287
2075
+ },
2076
+ {
2077
+ "epoch": 1.69,
2078
+ "grad_norm": 0.10176358371973038,
2079
+ "learning_rate": 0.00012488737433323426,
2080
+ "loss": 0.4013,
2081
+ "step": 288
2082
+ },
2083
+ {
2084
+ "epoch": 1.7,
2085
+ "grad_norm": 0.09872467070817947,
2086
+ "learning_rate": 0.00012442746660539227,
2087
+ "loss": 0.3859,
2088
+ "step": 289
2089
+ },
2090
+ {
2091
+ "epoch": 1.71,
2092
+ "grad_norm": 0.10109713673591614,
2093
+ "learning_rate": 0.00012396700875255264,
2094
+ "loss": 0.3779,
2095
+ "step": 290
2096
+ },
2097
+ {
2098
+ "epoch": 1.71,
2099
+ "grad_norm": 0.10859864950180054,
2100
+ "learning_rate": 0.00012350601114457396,
2101
+ "loss": 0.4023,
2102
+ "step": 291
2103
+ },
2104
+ {
2105
+ "epoch": 1.72,
2106
+ "grad_norm": 0.10092321038246155,
2107
+ "learning_rate": 0.00012304448416347065,
2108
+ "loss": 0.3998,
2109
+ "step": 292
2110
+ },
2111
+ {
2112
+ "epoch": 1.72,
2113
+ "grad_norm": 0.10352278500795364,
2114
+ "learning_rate": 0.0001225824382031789,
2115
+ "loss": 0.4067,
2116
+ "step": 293
2117
+ },
2118
+ {
2119
+ "epoch": 1.73,
2120
+ "grad_norm": 0.1029689610004425,
2121
+ "learning_rate": 0.0001221198836693226,
2122
+ "loss": 0.3656,
2123
+ "step": 294
2124
+ },
2125
+ {
2126
+ "epoch": 1.73,
2127
+ "eval_loss": 0.4955105185508728,
2128
+ "eval_runtime": 21.4362,
2129
+ "eval_samples_per_second": 46.324,
2130
+ "eval_steps_per_second": 11.616,
2131
+ "step": 294
2132
+ },
2133
+ {
2134
+ "epoch": 1.74,
2135
+ "grad_norm": 0.10078923404216766,
2136
+ "learning_rate": 0.00012165683097897931,
2137
+ "loss": 0.4035,
2138
+ "step": 295
2139
+ },
2140
+ {
2141
+ "epoch": 1.74,
2142
+ "grad_norm": 0.1020880788564682,
2143
+ "learning_rate": 0.00012119329056044532,
2144
+ "loss": 0.393,
2145
+ "step": 296
2146
+ },
2147
+ {
2148
+ "epoch": 1.75,
2149
+ "grad_norm": 0.10287690162658691,
2150
+ "learning_rate": 0.00012072927285300098,
2151
+ "loss": 0.4005,
2152
+ "step": 297
2153
+ },
2154
+ {
2155
+ "epoch": 1.75,
2156
+ "grad_norm": 0.10361482948064804,
2157
+ "learning_rate": 0.00012026478830667551,
2158
+ "loss": 0.3885,
2159
+ "step": 298
2160
+ },
2161
+ {
2162
+ "epoch": 1.76,
2163
+ "grad_norm": 0.10416186600923538,
2164
+ "learning_rate": 0.00011979984738201171,
2165
+ "loss": 0.3997,
2166
+ "step": 299
2167
+ },
2168
+ {
2169
+ "epoch": 1.77,
2170
+ "grad_norm": 0.10558196157217026,
2171
+ "learning_rate": 0.00011933446054983035,
2172
+ "loss": 0.4082,
2173
+ "step": 300
2174
+ },
2175
+ {
2176
+ "epoch": 1.77,
2177
+ "grad_norm": 0.10211660712957382,
2178
+ "learning_rate": 0.00011886863829099441,
2179
+ "loss": 0.3798,
2180
+ "step": 301
2181
+ },
2182
+ {
2183
+ "epoch": 1.78,
2184
+ "grad_norm": 0.10305824875831604,
2185
+ "learning_rate": 0.00011840239109617302,
2186
+ "loss": 0.3898,
2187
+ "step": 302
2188
+ },
2189
+ {
2190
+ "epoch": 1.78,
2191
+ "grad_norm": 0.11154858022928238,
2192
+ "learning_rate": 0.0001179357294656051,
2193
+ "loss": 0.3921,
2194
+ "step": 303
2195
+ },
2196
+ {
2197
+ "epoch": 1.79,
2198
+ "grad_norm": 0.1013292595744133,
2199
+ "learning_rate": 0.00011746866390886305,
2200
+ "loss": 0.3808,
2201
+ "step": 304
2202
+ },
2203
+ {
2204
+ "epoch": 1.8,
2205
+ "grad_norm": 0.10282581299543381,
2206
+ "learning_rate": 0.00011700120494461595,
2207
+ "loss": 0.3811,
2208
+ "step": 305
2209
+ },
2210
+ {
2211
+ "epoch": 1.8,
2212
+ "grad_norm": 0.10098174214363098,
2213
+ "learning_rate": 0.0001165333631003928,
2214
+ "loss": 0.3822,
2215
+ "step": 306
2216
+ },
2217
+ {
2218
+ "epoch": 1.81,
2219
+ "grad_norm": 0.10231437534093857,
2220
+ "learning_rate": 0.00011606514891234526,
2221
+ "loss": 0.38,
2222
+ "step": 307
2223
+ },
2224
+ {
2225
+ "epoch": 1.81,
2226
+ "grad_norm": 0.10368547588586807,
2227
+ "learning_rate": 0.00011559657292501042,
2228
+ "loss": 0.3863,
2229
+ "step": 308
2230
+ },
2231
+ {
2232
+ "epoch": 1.82,
2233
+ "grad_norm": 0.10524257272481918,
2234
+ "learning_rate": 0.00011512764569107351,
2235
+ "loss": 0.4024,
2236
+ "step": 309
2237
+ },
2238
+ {
2239
+ "epoch": 1.82,
2240
+ "grad_norm": 0.10808374732732773,
2241
+ "learning_rate": 0.00011465837777113,
2242
+ "loss": 0.4021,
2243
+ "step": 310
2244
+ },
2245
+ {
2246
+ "epoch": 1.83,
2247
+ "grad_norm": 0.10130346566438675,
2248
+ "learning_rate": 0.00011418877973344781,
2249
+ "loss": 0.3857,
2250
+ "step": 311
2251
+ },
2252
+ {
2253
+ "epoch": 1.84,
2254
+ "grad_norm": 0.10113856196403503,
2255
+ "learning_rate": 0.00011371886215372951,
2256
+ "loss": 0.4028,
2257
+ "step": 312
2258
+ },
2259
+ {
2260
+ "epoch": 1.84,
2261
+ "grad_norm": 0.10313602536916733,
2262
+ "learning_rate": 0.00011324863561487383,
2263
+ "loss": 0.3897,
2264
+ "step": 313
2265
+ },
2266
+ {
2267
+ "epoch": 1.85,
2268
+ "grad_norm": 0.0981384888291359,
2269
+ "learning_rate": 0.00011277811070673765,
2270
+ "loss": 0.3798,
2271
+ "step": 314
2272
+ },
2273
+ {
2274
+ "epoch": 1.85,
2275
+ "grad_norm": 0.10432131588459015,
2276
+ "learning_rate": 0.00011230729802589726,
2277
+ "loss": 0.3941,
2278
+ "step": 315
2279
+ },
2280
+ {
2281
+ "epoch": 1.86,
2282
+ "grad_norm": 0.09853876382112503,
2283
+ "learning_rate": 0.00011183620817540986,
2284
+ "loss": 0.3799,
2285
+ "step": 316
2286
+ },
2287
+ {
2288
+ "epoch": 1.87,
2289
+ "grad_norm": 0.10610882192850113,
2290
+ "learning_rate": 0.00011136485176457459,
2291
+ "loss": 0.4034,
2292
+ "step": 317
2293
+ },
2294
+ {
2295
+ "epoch": 1.87,
2296
+ "grad_norm": 0.09782709181308746,
2297
+ "learning_rate": 0.00011089323940869392,
2298
+ "loss": 0.3725,
2299
+ "step": 318
2300
+ },
2301
+ {
2302
+ "epoch": 1.88,
2303
+ "grad_norm": 0.10068295896053314,
2304
+ "learning_rate": 0.0001104213817288343,
2305
+ "loss": 0.3721,
2306
+ "step": 319
2307
+ },
2308
+ {
2309
+ "epoch": 1.88,
2310
+ "grad_norm": 0.10485327988862991,
2311
+ "learning_rate": 0.00010994928935158702,
2312
+ "loss": 0.3832,
2313
+ "step": 320
2314
+ },
2315
+ {
2316
+ "epoch": 1.89,
2317
+ "grad_norm": 0.10914643853902817,
2318
+ "learning_rate": 0.00010947697290882903,
2319
+ "loss": 0.4039,
2320
+ "step": 321
2321
+ },
2322
+ {
2323
+ "epoch": 1.9,
2324
+ "grad_norm": 0.10210110992193222,
2325
+ "learning_rate": 0.00010900444303748332,
2326
+ "loss": 0.3954,
2327
+ "step": 322
2328
+ },
2329
+ {
2330
+ "epoch": 1.9,
2331
+ "grad_norm": 0.09887547791004181,
2332
+ "learning_rate": 0.00010853171037927951,
2333
+ "loss": 0.3711,
2334
+ "step": 323
2335
+ },
2336
+ {
2337
+ "epoch": 1.91,
2338
+ "grad_norm": 0.1009160652756691,
2339
+ "learning_rate": 0.0001080587855805141,
2340
+ "loss": 0.3917,
2341
+ "step": 324
2342
+ },
2343
+ {
2344
+ "epoch": 1.91,
2345
+ "grad_norm": 0.10089701414108276,
2346
+ "learning_rate": 0.00010758567929181074,
2347
+ "loss": 0.388,
2348
+ "step": 325
2349
+ },
2350
+ {
2351
+ "epoch": 1.92,
2352
+ "grad_norm": 0.10800614953041077,
2353
+ "learning_rate": 0.00010711240216788036,
2354
+ "loss": 0.4067,
2355
+ "step": 326
2356
+ },
2357
+ {
2358
+ "epoch": 1.93,
2359
+ "grad_norm": 0.10289803147315979,
2360
+ "learning_rate": 0.00010663896486728133,
2361
+ "loss": 0.3965,
2362
+ "step": 327
2363
+ },
2364
+ {
2365
+ "epoch": 1.93,
2366
+ "grad_norm": 0.10536928474903107,
2367
+ "learning_rate": 0.00010616537805217916,
2368
+ "loss": 0.4033,
2369
+ "step": 328
2370
+ },
2371
+ {
2372
+ "epoch": 1.94,
2373
+ "grad_norm": 0.10302754491567612,
2374
+ "learning_rate": 0.00010569165238810666,
2375
+ "loss": 0.3841,
2376
+ "step": 329
2377
+ },
2378
+ {
2379
+ "epoch": 1.94,
2380
+ "grad_norm": 0.10210216045379639,
2381
+ "learning_rate": 0.00010521779854372353,
2382
+ "loss": 0.4043,
2383
+ "step": 330
2384
+ },
2385
+ {
2386
+ "epoch": 1.95,
2387
+ "grad_norm": 0.10437451303005219,
2388
+ "learning_rate": 0.00010474382719057631,
2389
+ "loss": 0.4065,
2390
+ "step": 331
2391
+ },
2392
+ {
2393
+ "epoch": 1.96,
2394
+ "grad_norm": 0.10098063200712204,
2395
+ "learning_rate": 0.00010426974900285784,
2396
+ "loss": 0.4029,
2397
+ "step": 332
2398
+ },
2399
+ {
2400
+ "epoch": 1.96,
2401
+ "grad_norm": 0.09919014573097229,
2402
+ "learning_rate": 0.00010379557465716696,
2403
+ "loss": 0.3902,
2404
+ "step": 333
2405
+ },
2406
+ {
2407
+ "epoch": 1.97,
2408
+ "grad_norm": 0.09987551718950272,
2409
+ "learning_rate": 0.00010332131483226804,
2410
+ "loss": 0.3901,
2411
+ "step": 334
2412
+ },
2413
+ {
2414
+ "epoch": 1.97,
2415
+ "grad_norm": 0.10001327842473984,
2416
+ "learning_rate": 0.00010284698020885053,
2417
+ "loss": 0.3697,
2418
+ "step": 335
2419
+ },
2420
+ {
2421
+ "epoch": 1.98,
2422
+ "grad_norm": 0.11250711232423782,
2423
+ "learning_rate": 0.00010237258146928848,
2424
+ "loss": 0.3744,
2425
+ "step": 336
2426
+ },
2427
+ {
2428
+ "epoch": 1.98,
2429
+ "eval_loss": 0.4941823482513428,
2430
+ "eval_runtime": 21.4596,
2431
+ "eval_samples_per_second": 46.273,
2432
+ "eval_steps_per_second": 11.603,
2433
+ "step": 336
2434
+ },
2435
+ {
2436
+ "epoch": 1.99,
2437
+ "grad_norm": 0.11110812425613403,
2438
+ "learning_rate": 0.00010189812929739976,
2439
+ "loss": 0.3929,
2440
+ "step": 337
2441
+ },
2442
+ {
2443
+ "epoch": 1.99,
2444
+ "grad_norm": 0.10165286064147949,
2445
+ "learning_rate": 0.00010142363437820565,
2446
+ "loss": 0.387,
2447
+ "step": 338
2448
+ },
2449
+ {
2450
+ "epoch": 2.0,
2451
+ "grad_norm": 0.10643592476844788,
2452
+ "learning_rate": 0.00010094910739769008,
2453
+ "loss": 0.3994,
2454
+ "step": 339
2455
+ },
2456
+ {
2457
+ "epoch": 2.0,
2458
+ "grad_norm": 0.10812180489301682,
2459
+ "learning_rate": 0.00010047455904255909,
2460
+ "loss": 0.3933,
2461
+ "step": 340
2462
+ },
2463
+ {
2464
+ "epoch": 2.01,
2465
+ "grad_norm": 0.10249359905719757,
2466
+ "learning_rate": 0.0001,
2467
+ "loss": 0.3867,
2468
+ "step": 341
2469
+ },
2470
+ {
2471
+ "epoch": 2.01,
2472
+ "grad_norm": 0.10428471863269806,
2473
+ "learning_rate": 9.952544095744092e-05,
2474
+ "loss": 0.3792,
2475
+ "step": 342
2476
+ },
2477
+ {
2478
+ "epoch": 2.0,
2479
+ "grad_norm": 0.11811227351427078,
2480
+ "learning_rate": 9.905089260230995e-05,
2481
+ "loss": 0.3711,
2482
+ "step": 343
2483
+ },
2484
+ {
2485
+ "epoch": 2.01,
2486
+ "grad_norm": 0.11514988541603088,
2487
+ "learning_rate": 9.857636562179437e-05,
2488
+ "loss": 0.3566,
2489
+ "step": 344
2490
+ },
2491
+ {
2492
+ "epoch": 2.02,
2493
+ "grad_norm": 0.11116521805524826,
2494
+ "learning_rate": 9.810187070260027e-05,
2495
+ "loss": 0.3551,
2496
+ "step": 345
2497
+ },
2498
+ {
2499
+ "epoch": 2.02,
2500
+ "grad_norm": 0.1339193433523178,
2501
+ "learning_rate": 9.762741853071153e-05,
2502
+ "loss": 0.3615,
2503
+ "step": 346
2504
+ },
2505
+ {
2506
+ "epoch": 2.03,
2507
+ "grad_norm": 0.13373638689517975,
2508
+ "learning_rate": 9.715301979114946e-05,
2509
+ "loss": 0.3392,
2510
+ "step": 347
2511
+ },
2512
+ {
2513
+ "epoch": 2.03,
2514
+ "grad_norm": 0.12637023627758026,
2515
+ "learning_rate": 9.667868516773201e-05,
2516
+ "loss": 0.3116,
2517
+ "step": 348
2518
+ },
2519
+ {
2520
+ "epoch": 2.04,
2521
+ "grad_norm": 0.11064064502716064,
2522
+ "learning_rate": 9.620442534283307e-05,
2523
+ "loss": 0.3395,
2524
+ "step": 349
2525
+ },
2526
+ {
2527
+ "epoch": 2.05,
2528
+ "grad_norm": 0.10704579204320908,
2529
+ "learning_rate": 9.573025099714217e-05,
2530
+ "loss": 0.3504,
2531
+ "step": 350
2532
+ },
2533
+ {
2534
+ "epoch": 2.05,
2535
+ "grad_norm": 0.11721500009298325,
2536
+ "learning_rate": 9.525617280942371e-05,
2537
+ "loss": 0.3377,
2538
+ "step": 351
2539
+ },
2540
+ {
2541
+ "epoch": 2.06,
2542
+ "grad_norm": 0.11729004979133606,
2543
+ "learning_rate": 9.478220145627645e-05,
2544
+ "loss": 0.346,
2545
+ "step": 352
2546
+ },
2547
+ {
2548
+ "epoch": 2.06,
2549
+ "grad_norm": 0.10619601607322693,
2550
+ "learning_rate": 9.430834761189338e-05,
2551
+ "loss": 0.349,
2552
+ "step": 353
2553
+ },
2554
+ {
2555
+ "epoch": 2.07,
2556
+ "grad_norm": 0.1071799099445343,
2557
+ "learning_rate": 9.383462194782085e-05,
2558
+ "loss": 0.3508,
2559
+ "step": 354
2560
+ },
2561
+ {
2562
+ "epoch": 2.08,
2563
+ "grad_norm": 0.10692652314901352,
2564
+ "learning_rate": 9.336103513271869e-05,
2565
+ "loss": 0.3327,
2566
+ "step": 355
2567
+ },
2568
+ {
2569
+ "epoch": 2.08,
2570
+ "grad_norm": 0.11744857579469681,
2571
+ "learning_rate": 9.288759783211967e-05,
2572
+ "loss": 0.3527,
2573
+ "step": 356
2574
+ },
2575
+ {
2576
+ "epoch": 2.09,
2577
+ "grad_norm": 0.1182284876704216,
2578
+ "learning_rate": 9.24143207081893e-05,
2579
+ "loss": 0.3388,
2580
+ "step": 357
2581
+ },
2582
+ {
2583
+ "epoch": 2.09,
2584
+ "grad_norm": 0.12824517488479614,
2585
+ "learning_rate": 9.194121441948596e-05,
2586
+ "loss": 0.3601,
2587
+ "step": 358
2588
+ },
2589
+ {
2590
+ "epoch": 2.1,
2591
+ "grad_norm": 0.11172507703304291,
2592
+ "learning_rate": 9.146828962072051e-05,
2593
+ "loss": 0.3523,
2594
+ "step": 359
2595
+ },
2596
+ {
2597
+ "epoch": 2.11,
2598
+ "grad_norm": 0.1088048666715622,
2599
+ "learning_rate": 9.099555696251667e-05,
2600
+ "loss": 0.3349,
2601
+ "step": 360
2602
+ },
2603
+ {
2604
+ "epoch": 2.11,
2605
+ "grad_norm": 0.11656352877616882,
2606
+ "learning_rate": 9.0523027091171e-05,
2607
+ "loss": 0.3446,
2608
+ "step": 361
2609
+ },
2610
+ {
2611
+ "epoch": 2.12,
2612
+ "grad_norm": 0.1138211190700531,
2613
+ "learning_rate": 9.0050710648413e-05,
2614
+ "loss": 0.3394,
2615
+ "step": 362
2616
+ },
2617
+ {
2618
+ "epoch": 2.12,
2619
+ "grad_norm": 0.11616445332765579,
2620
+ "learning_rate": 8.957861827116577e-05,
2621
+ "loss": 0.3489,
2622
+ "step": 363
2623
+ },
2624
+ {
2625
+ "epoch": 2.13,
2626
+ "grad_norm": 0.11222302168607712,
2627
+ "learning_rate": 8.910676059130611e-05,
2628
+ "loss": 0.353,
2629
+ "step": 364
2630
+ },
2631
+ {
2632
+ "epoch": 2.14,
2633
+ "grad_norm": 0.11436023563146591,
2634
+ "learning_rate": 8.863514823542542e-05,
2635
+ "loss": 0.3269,
2636
+ "step": 365
2637
+ },
2638
+ {
2639
+ "epoch": 2.14,
2640
+ "grad_norm": 0.12150812894105911,
2641
+ "learning_rate": 8.81637918245902e-05,
2642
+ "loss": 0.3419,
2643
+ "step": 366
2644
+ },
2645
+ {
2646
+ "epoch": 2.15,
2647
+ "grad_norm": 0.11648691445589066,
2648
+ "learning_rate": 8.769270197410276e-05,
2649
+ "loss": 0.3374,
2650
+ "step": 367
2651
+ },
2652
+ {
2653
+ "epoch": 2.15,
2654
+ "grad_norm": 0.11707336455583572,
2655
+ "learning_rate": 8.722188929326236e-05,
2656
+ "loss": 0.3489,
2657
+ "step": 368
2658
+ },
2659
+ {
2660
+ "epoch": 2.16,
2661
+ "grad_norm": 0.11122533679008484,
2662
+ "learning_rate": 8.67513643851262e-05,
2663
+ "loss": 0.3476,
2664
+ "step": 369
2665
+ },
2666
+ {
2667
+ "epoch": 2.16,
2668
+ "grad_norm": 0.11035927385091782,
2669
+ "learning_rate": 8.628113784627053e-05,
2670
+ "loss": 0.3416,
2671
+ "step": 370
2672
+ },
2673
+ {
2674
+ "epoch": 2.17,
2675
+ "grad_norm": 0.11648087203502655,
2676
+ "learning_rate": 8.581122026655221e-05,
2677
+ "loss": 0.337,
2678
+ "step": 371
2679
+ },
2680
+ {
2681
+ "epoch": 2.18,
2682
+ "grad_norm": 0.11055613309144974,
2683
+ "learning_rate": 8.534162222887003e-05,
2684
+ "loss": 0.3479,
2685
+ "step": 372
2686
+ },
2687
+ {
2688
+ "epoch": 2.18,
2689
+ "grad_norm": 0.11321202665567398,
2690
+ "learning_rate": 8.487235430892649e-05,
2691
+ "loss": 0.3567,
2692
+ "step": 373
2693
+ },
2694
+ {
2695
+ "epoch": 2.19,
2696
+ "grad_norm": 0.11344156414270401,
2697
+ "learning_rate": 8.44034270749896e-05,
2698
+ "loss": 0.3502,
2699
+ "step": 374
2700
+ },
2701
+ {
2702
+ "epoch": 2.19,
2703
+ "grad_norm": 0.11430197954177856,
2704
+ "learning_rate": 8.393485108765478e-05,
2705
+ "loss": 0.3406,
2706
+ "step": 375
2707
+ },
2708
+ {
2709
+ "epoch": 2.2,
2710
+ "grad_norm": 0.11915215104818344,
2711
+ "learning_rate": 8.346663689960725e-05,
2712
+ "loss": 0.3387,
2713
+ "step": 376
2714
+ },
2715
+ {
2716
+ "epoch": 2.21,
2717
+ "grad_norm": 0.11410155147314072,
2718
+ "learning_rate": 8.299879505538406e-05,
2719
+ "loss": 0.3441,
2720
+ "step": 377
2721
+ },
2722
+ {
2723
+ "epoch": 2.21,
2724
+ "grad_norm": 0.1166268065571785,
2725
+ "learning_rate": 8.253133609113699e-05,
2726
+ "loss": 0.3278,
2727
+ "step": 378
2728
+ },
2729
+ {
2730
+ "epoch": 2.21,
2731
+ "eval_loss": 0.5011767745018005,
2732
+ "eval_runtime": 21.4646,
2733
+ "eval_samples_per_second": 46.262,
2734
+ "eval_steps_per_second": 11.601,
2735
+ "step": 378
2736
+ },
2737
+ {
2738
+ "epoch": 2.22,
2739
+ "grad_norm": 0.1214762032032013,
2740
+ "learning_rate": 8.206427053439495e-05,
2741
+ "loss": 0.351,
2742
+ "step": 379
2743
+ },
2744
+ {
2745
+ "epoch": 2.22,
2746
+ "grad_norm": 0.1124025508761406,
2747
+ "learning_rate": 8.159760890382702e-05,
2748
+ "loss": 0.35,
2749
+ "step": 380
2750
+ },
2751
+ {
2752
+ "epoch": 2.23,
2753
+ "grad_norm": 0.1132451742887497,
2754
+ "learning_rate": 8.113136170900557e-05,
2755
+ "loss": 0.336,
2756
+ "step": 381
2757
+ },
2758
+ {
2759
+ "epoch": 2.24,
2760
+ "grad_norm": 0.11561685800552368,
2761
+ "learning_rate": 8.066553945016968e-05,
2762
+ "loss": 0.3296,
2763
+ "step": 382
2764
+ },
2765
+ {
2766
+ "epoch": 2.24,
2767
+ "grad_norm": 0.11814241856336594,
2768
+ "learning_rate": 8.02001526179883e-05,
2769
+ "loss": 0.339,
2770
+ "step": 383
2771
+ },
2772
+ {
2773
+ "epoch": 2.25,
2774
+ "grad_norm": 0.11445321887731552,
2775
+ "learning_rate": 7.973521169332451e-05,
2776
+ "loss": 0.3437,
2777
+ "step": 384
2778
+ },
2779
+ {
2780
+ "epoch": 2.25,
2781
+ "grad_norm": 0.11405869573354721,
2782
+ "learning_rate": 7.927072714699903e-05,
2783
+ "loss": 0.3591,
2784
+ "step": 385
2785
+ },
2786
+ {
2787
+ "epoch": 2.26,
2788
+ "grad_norm": 0.12095706909894943,
2789
+ "learning_rate": 7.880670943955467e-05,
2790
+ "loss": 0.3475,
2791
+ "step": 386
2792
+ },
2793
+ {
2794
+ "epoch": 2.27,
2795
+ "grad_norm": 0.12278500199317932,
2796
+ "learning_rate": 7.834316902102071e-05,
2797
+ "loss": 0.3299,
2798
+ "step": 387
2799
+ },
2800
+ {
2801
+ "epoch": 2.27,
2802
+ "grad_norm": 0.12034577131271362,
2803
+ "learning_rate": 7.78801163306774e-05,
2804
+ "loss": 0.3523,
2805
+ "step": 388
2806
+ },
2807
+ {
2808
+ "epoch": 2.28,
2809
+ "grad_norm": 0.11056854575872421,
2810
+ "learning_rate": 7.741756179682116e-05,
2811
+ "loss": 0.3224,
2812
+ "step": 389
2813
+ },
2814
+ {
2815
+ "epoch": 2.28,
2816
+ "grad_norm": 0.11459018290042877,
2817
+ "learning_rate": 7.695551583652936e-05,
2818
+ "loss": 0.3458,
2819
+ "step": 390
2820
+ },
2821
+ {
2822
+ "epoch": 2.29,
2823
+ "grad_norm": 0.11864470690488815,
2824
+ "learning_rate": 7.649398885542604e-05,
2825
+ "loss": 0.3408,
2826
+ "step": 391
2827
+ },
2828
+ {
2829
+ "epoch": 2.3,
2830
+ "grad_norm": 0.11902540177106857,
2831
+ "learning_rate": 7.603299124744743e-05,
2832
+ "loss": 0.337,
2833
+ "step": 392
2834
+ },
2835
+ {
2836
+ "epoch": 2.3,
2837
+ "grad_norm": 0.11285750567913055,
2838
+ "learning_rate": 7.557253339460777e-05,
2839
+ "loss": 0.3406,
2840
+ "step": 393
2841
+ },
2842
+ {
2843
+ "epoch": 2.31,
2844
+ "grad_norm": 0.11690229177474976,
2845
+ "learning_rate": 7.511262566676573e-05,
2846
+ "loss": 0.3407,
2847
+ "step": 394
2848
+ },
2849
+ {
2850
+ "epoch": 2.31,
2851
+ "grad_norm": 0.11694052070379257,
2852
+ "learning_rate": 7.465327842139074e-05,
2853
+ "loss": 0.34,
2854
+ "step": 395
2855
+ },
2856
+ {
2857
+ "epoch": 2.32,
2858
+ "grad_norm": 0.1170695573091507,
2859
+ "learning_rate": 7.419450200332964e-05,
2860
+ "loss": 0.3449,
2861
+ "step": 396
2862
+ },
2863
+ {
2864
+ "epoch": 2.32,
2865
+ "grad_norm": 0.11467460542917252,
2866
+ "learning_rate": 7.373630674457393e-05,
2867
+ "loss": 0.3429,
2868
+ "step": 397
2869
+ },
2870
+ {
2871
+ "epoch": 2.33,
2872
+ "grad_norm": 0.1154307872056961,
2873
+ "learning_rate": 7.327870296402682e-05,
2874
+ "loss": 0.3518,
2875
+ "step": 398
2876
+ },
2877
+ {
2878
+ "epoch": 2.34,
2879
+ "grad_norm": 0.11852456629276276,
2880
+ "learning_rate": 7.28217009672711e-05,
2881
+ "loss": 0.3444,
2882
+ "step": 399
2883
+ },
2884
+ {
2885
+ "epoch": 2.34,
2886
+ "grad_norm": 0.11891540884971619,
2887
+ "learning_rate": 7.236531104633698e-05,
2888
+ "loss": 0.3394,
2889
+ "step": 400
2890
+ },
2891
+ {
2892
+ "epoch": 2.35,
2893
+ "grad_norm": 0.12176164239645004,
2894
+ "learning_rate": 7.190954347947009e-05,
2895
+ "loss": 0.322,
2896
+ "step": 401
2897
+ },
2898
+ {
2899
+ "epoch": 2.35,
2900
+ "grad_norm": 0.11945579946041107,
2901
+ "learning_rate": 7.145440853090034e-05,
2902
+ "loss": 0.344,
2903
+ "step": 402
2904
+ },
2905
+ {
2906
+ "epoch": 2.36,
2907
+ "grad_norm": 0.11632686853408813,
2908
+ "learning_rate": 7.099991645061044e-05,
2909
+ "loss": 0.3502,
2910
+ "step": 403
2911
+ },
2912
+ {
2913
+ "epoch": 2.37,
2914
+ "grad_norm": 0.12018176913261414,
2915
+ "learning_rate": 7.054607747410535e-05,
2916
+ "loss": 0.3523,
2917
+ "step": 404
2918
+ },
2919
+ {
2920
+ "epoch": 2.37,
2921
+ "grad_norm": 0.11948262155056,
2922
+ "learning_rate": 7.009290182218166e-05,
2923
+ "loss": 0.34,
2924
+ "step": 405
2925
+ },
2926
+ {
2927
+ "epoch": 2.38,
2928
+ "grad_norm": 0.11255805939435959,
2929
+ "learning_rate": 6.964039970069723e-05,
2930
+ "loss": 0.343,
2931
+ "step": 406
2932
+ },
2933
+ {
2934
+ "epoch": 2.38,
2935
+ "grad_norm": 0.1162085086107254,
2936
+ "learning_rate": 6.918858130034167e-05,
2937
+ "loss": 0.3451,
2938
+ "step": 407
2939
+ },
2940
+ {
2941
+ "epoch": 2.39,
2942
+ "grad_norm": 0.11837758123874664,
2943
+ "learning_rate": 6.87374567964066e-05,
2944
+ "loss": 0.3424,
2945
+ "step": 408
2946
+ },
2947
+ {
2948
+ "epoch": 2.4,
2949
+ "grad_norm": 0.11716870218515396,
2950
+ "learning_rate": 6.828703634855651e-05,
2951
+ "loss": 0.3449,
2952
+ "step": 409
2953
+ },
2954
+ {
2955
+ "epoch": 2.4,
2956
+ "grad_norm": 0.11923764646053314,
2957
+ "learning_rate": 6.783733010060018e-05,
2958
+ "loss": 0.3503,
2959
+ "step": 410
2960
+ },
2961
+ {
2962
+ "epoch": 2.41,
2963
+ "grad_norm": 0.11688950657844543,
2964
+ "learning_rate": 6.738834818026187e-05,
2965
+ "loss": 0.3515,
2966
+ "step": 411
2967
+ },
2968
+ {
2969
+ "epoch": 2.41,
2970
+ "grad_norm": 0.11869969964027405,
2971
+ "learning_rate": 6.694010069895362e-05,
2972
+ "loss": 0.3357,
2973
+ "step": 412
2974
+ },
2975
+ {
2976
+ "epoch": 2.42,
2977
+ "grad_norm": 0.11307539790868759,
2978
+ "learning_rate": 6.649259775154725e-05,
2979
+ "loss": 0.331,
2980
+ "step": 413
2981
+ },
2982
+ {
2983
+ "epoch": 2.43,
2984
+ "grad_norm": 0.11562840640544891,
2985
+ "learning_rate": 6.604584941614705e-05,
2986
+ "loss": 0.352,
2987
+ "step": 414
2988
+ },
2989
+ {
2990
+ "epoch": 2.43,
2991
+ "grad_norm": 0.11388909071683884,
2992
+ "learning_rate": 6.559986575386307e-05,
2993
+ "loss": 0.3439,
2994
+ "step": 415
2995
+ },
2996
+ {
2997
+ "epoch": 2.44,
2998
+ "grad_norm": 0.11977346241474152,
2999
+ "learning_rate": 6.515465680858412e-05,
3000
+ "loss": 0.3686,
3001
+ "step": 416
3002
+ },
3003
+ {
3004
+ "epoch": 2.44,
3005
+ "grad_norm": 0.11565675586462021,
3006
+ "learning_rate": 6.471023260675196e-05,
3007
+ "loss": 0.339,
3008
+ "step": 417
3009
+ },
3010
+ {
3011
+ "epoch": 2.45,
3012
+ "grad_norm": 0.1227443665266037,
3013
+ "learning_rate": 6.426660315713529e-05,
3014
+ "loss": 0.3424,
3015
+ "step": 418
3016
+ },
3017
+ {
3018
+ "epoch": 2.46,
3019
+ "grad_norm": 0.11462421715259552,
3020
+ "learning_rate": 6.382377845060438e-05,
3021
+ "loss": 0.3221,
3022
+ "step": 419
3023
+ },
3024
+ {
3025
+ "epoch": 2.46,
3026
+ "grad_norm": 0.1177360862493515,
3027
+ "learning_rate": 6.338176845990608e-05,
3028
+ "loss": 0.344,
3029
+ "step": 420
3030
+ },
3031
+ {
3032
+ "epoch": 2.46,
3033
+ "eval_loss": 0.5003070831298828,
3034
+ "eval_runtime": 21.4617,
3035
+ "eval_samples_per_second": 46.268,
3036
+ "eval_steps_per_second": 11.602,
3037
+ "step": 420
3038
+ },
3039
+ {
3040
+ "epoch": 2.47,
3041
+ "grad_norm": 0.11535537987947464,
3042
+ "learning_rate": 6.294058313943915e-05,
3043
+ "loss": 0.3384,
3044
+ "step": 421
3045
+ },
3046
+ {
3047
+ "epoch": 2.47,
3048
+ "grad_norm": 0.12123331427574158,
3049
+ "learning_rate": 6.250023242503031e-05,
3050
+ "loss": 0.3402,
3051
+ "step": 422
3052
+ },
3053
+ {
3054
+ "epoch": 2.48,
3055
+ "grad_norm": 0.11845969408750534,
3056
+ "learning_rate": 6.206072623371027e-05,
3057
+ "loss": 0.3327,
3058
+ "step": 423
3059
+ },
3060
+ {
3061
+ "epoch": 2.49,
3062
+ "grad_norm": 0.12011318653821945,
3063
+ "learning_rate": 6.16220744634903e-05,
3064
+ "loss": 0.3243,
3065
+ "step": 424
3066
+ },
3067
+ {
3068
+ "epoch": 2.49,
3069
+ "grad_norm": 0.12184374779462814,
3070
+ "learning_rate": 6.118428699313965e-05,
3071
+ "loss": 0.3431,
3072
+ "step": 425
3073
+ },
3074
+ {
3075
+ "epoch": 2.5,
3076
+ "grad_norm": 0.11864135414361954,
3077
+ "learning_rate": 6.0747373681962794e-05,
3078
+ "loss": 0.3268,
3079
+ "step": 426
3080
+ },
3081
+ {
3082
+ "epoch": 2.5,
3083
+ "grad_norm": 0.12076004594564438,
3084
+ "learning_rate": 6.031134436957746e-05,
3085
+ "loss": 0.3623,
3086
+ "step": 427
3087
+ },
3088
+ {
3089
+ "epoch": 2.51,
3090
+ "grad_norm": 0.11430728435516357,
3091
+ "learning_rate": 5.9876208875693144e-05,
3092
+ "loss": 0.3307,
3093
+ "step": 428
3094
+ },
3095
+ {
3096
+ "epoch": 2.51,
3097
+ "grad_norm": 0.11330832540988922,
3098
+ "learning_rate": 5.9441976999889745e-05,
3099
+ "loss": 0.3373,
3100
+ "step": 429
3101
+ },
3102
+ {
3103
+ "epoch": 2.52,
3104
+ "grad_norm": 0.11900202184915543,
3105
+ "learning_rate": 5.900865852139714e-05,
3106
+ "loss": 0.3546,
3107
+ "step": 430
3108
+ },
3109
+ {
3110
+ "epoch": 2.53,
3111
+ "grad_norm": 0.11765287816524506,
3112
+ "learning_rate": 5.8576263198874746e-05,
3113
+ "loss": 0.3286,
3114
+ "step": 431
3115
+ },
3116
+ {
3117
+ "epoch": 2.53,
3118
+ "grad_norm": 0.11611023545265198,
3119
+ "learning_rate": 5.814480077019173e-05,
3120
+ "loss": 0.3463,
3121
+ "step": 432
3122
+ },
3123
+ {
3124
+ "epoch": 2.54,
3125
+ "grad_norm": 0.116789311170578,
3126
+ "learning_rate": 5.7714280952207954e-05,
3127
+ "loss": 0.3449,
3128
+ "step": 433
3129
+ },
3130
+ {
3131
+ "epoch": 2.54,
3132
+ "grad_norm": 0.11763904243707657,
3133
+ "learning_rate": 5.728471344055482e-05,
3134
+ "loss": 0.3437,
3135
+ "step": 434
3136
+ },
3137
+ {
3138
+ "epoch": 2.55,
3139
+ "grad_norm": 0.11893092840909958,
3140
+ "learning_rate": 5.685610790941713e-05,
3141
+ "loss": 0.3513,
3142
+ "step": 435
3143
+ },
3144
+ {
3145
+ "epoch": 2.56,
3146
+ "grad_norm": 0.1151190996170044,
3147
+ "learning_rate": 5.6428474011315255e-05,
3148
+ "loss": 0.3209,
3149
+ "step": 436
3150
+ },
3151
+ {
3152
+ "epoch": 2.56,
3153
+ "grad_norm": 0.12135551869869232,
3154
+ "learning_rate": 5.600182137688745e-05,
3155
+ "loss": 0.3472,
3156
+ "step": 437
3157
+ },
3158
+ {
3159
+ "epoch": 2.57,
3160
+ "grad_norm": 0.11336695402860641,
3161
+ "learning_rate": 5.5576159614673385e-05,
3162
+ "loss": 0.3272,
3163
+ "step": 438
3164
+ },
3165
+ {
3166
+ "epoch": 2.57,
3167
+ "grad_norm": 0.11953918635845184,
3168
+ "learning_rate": 5.515149831089739e-05,
3169
+ "loss": 0.3233,
3170
+ "step": 439
3171
+ },
3172
+ {
3173
+ "epoch": 2.58,
3174
+ "grad_norm": 0.1199425756931305,
3175
+ "learning_rate": 5.4727847029252733e-05,
3176
+ "loss": 0.3431,
3177
+ "step": 440
3178
+ },
3179
+ {
3180
+ "epoch": 2.59,
3181
+ "grad_norm": 0.11986943334341049,
3182
+ "learning_rate": 5.430521531068633e-05,
3183
+ "loss": 0.3351,
3184
+ "step": 441
3185
+ },
3186
+ {
3187
+ "epoch": 2.59,
3188
+ "grad_norm": 0.12421400845050812,
3189
+ "learning_rate": 5.3883612673183616e-05,
3190
+ "loss": 0.3676,
3191
+ "step": 442
3192
+ },
3193
+ {
3194
+ "epoch": 2.6,
3195
+ "grad_norm": 0.11908672749996185,
3196
+ "learning_rate": 5.3463048611554445e-05,
3197
+ "loss": 0.3463,
3198
+ "step": 443
3199
+ },
3200
+ {
3201
+ "epoch": 2.6,
3202
+ "grad_norm": 0.11805973201990128,
3203
+ "learning_rate": 5.304353259721917e-05,
3204
+ "loss": 0.3323,
3205
+ "step": 444
3206
+ },
3207
+ {
3208
+ "epoch": 2.61,
3209
+ "grad_norm": 0.12039713561534882,
3210
+ "learning_rate": 5.2625074077995215e-05,
3211
+ "loss": 0.3436,
3212
+ "step": 445
3213
+ },
3214
+ {
3215
+ "epoch": 2.62,
3216
+ "grad_norm": 0.11868314445018768,
3217
+ "learning_rate": 5.220768247788458e-05,
3218
+ "loss": 0.344,
3219
+ "step": 446
3220
+ },
3221
+ {
3222
+ "epoch": 2.62,
3223
+ "grad_norm": 0.12498147040605545,
3224
+ "learning_rate": 5.179136719686124e-05,
3225
+ "loss": 0.3486,
3226
+ "step": 447
3227
+ },
3228
+ {
3229
+ "epoch": 2.63,
3230
+ "grad_norm": 0.1151999980211258,
3231
+ "learning_rate": 5.137613761065982e-05,
3232
+ "loss": 0.3376,
3233
+ "step": 448
3234
+ },
3235
+ {
3236
+ "epoch": 2.63,
3237
+ "grad_norm": 0.11347607523202896,
3238
+ "learning_rate": 5.0962003070564254e-05,
3239
+ "loss": 0.3451,
3240
+ "step": 449
3241
+ },
3242
+ {
3243
+ "epoch": 2.64,
3244
+ "grad_norm": 0.11494697630405426,
3245
+ "learning_rate": 5.054897290319713e-05,
3246
+ "loss": 0.3212,
3247
+ "step": 450
3248
+ },
3249
+ {
3250
+ "epoch": 2.65,
3251
+ "grad_norm": 0.12121488898992538,
3252
+ "learning_rate": 5.013705641030978e-05,
3253
+ "loss": 0.3284,
3254
+ "step": 451
3255
+ },
3256
+ {
3257
+ "epoch": 2.65,
3258
+ "grad_norm": 0.11501440405845642,
3259
+ "learning_rate": 4.9726262868572685e-05,
3260
+ "loss": 0.336,
3261
+ "step": 452
3262
+ },
3263
+ {
3264
+ "epoch": 2.66,
3265
+ "grad_norm": 0.12091628462076187,
3266
+ "learning_rate": 4.931660152936672e-05,
3267
+ "loss": 0.3443,
3268
+ "step": 453
3269
+ },
3270
+ {
3271
+ "epoch": 2.66,
3272
+ "grad_norm": 0.11806819587945938,
3273
+ "learning_rate": 4.8908081618574685e-05,
3274
+ "loss": 0.337,
3275
+ "step": 454
3276
+ },
3277
+ {
3278
+ "epoch": 2.67,
3279
+ "grad_norm": 0.12331026047468185,
3280
+ "learning_rate": 4.8500712336373454e-05,
3281
+ "loss": 0.3424,
3282
+ "step": 455
3283
+ },
3284
+ {
3285
+ "epoch": 2.68,
3286
+ "grad_norm": 0.11950333416461945,
3287
+ "learning_rate": 4.809450285702697e-05,
3288
+ "loss": 0.3439,
3289
+ "step": 456
3290
+ },
3291
+ {
3292
+ "epoch": 2.68,
3293
+ "grad_norm": 0.12057134509086609,
3294
+ "learning_rate": 4.7689462328679555e-05,
3295
+ "loss": 0.3473,
3296
+ "step": 457
3297
+ },
3298
+ {
3299
+ "epoch": 2.69,
3300
+ "grad_norm": 0.12127847224473953,
3301
+ "learning_rate": 4.728559987314974e-05,
3302
+ "loss": 0.3409,
3303
+ "step": 458
3304
+ },
3305
+ {
3306
+ "epoch": 2.69,
3307
+ "grad_norm": 0.12870007753372192,
3308
+ "learning_rate": 4.688292458572515e-05,
3309
+ "loss": 0.3732,
3310
+ "step": 459
3311
+ },
3312
+ {
3313
+ "epoch": 2.7,
3314
+ "grad_norm": 0.11999403685331345,
3315
+ "learning_rate": 4.6481445534957314e-05,
3316
+ "loss": 0.3444,
3317
+ "step": 460
3318
+ },
3319
+ {
3320
+ "epoch": 2.7,
3321
+ "grad_norm": 0.11927364021539688,
3322
+ "learning_rate": 4.608117176245773e-05,
3323
+ "loss": 0.3225,
3324
+ "step": 461
3325
+ },
3326
+ {
3327
+ "epoch": 2.71,
3328
+ "grad_norm": 0.11497607827186584,
3329
+ "learning_rate": 4.5682112282694075e-05,
3330
+ "loss": 0.3216,
3331
+ "step": 462
3332
+ },
3333
+ {
3334
+ "epoch": 2.71,
3335
+ "eval_loss": 0.4984052777290344,
3336
+ "eval_runtime": 21.4488,
3337
+ "eval_samples_per_second": 46.296,
3338
+ "eval_steps_per_second": 11.609,
3339
+ "step": 462
3340
+ },
3341
+ {
3342
+ "epoch": 2.72,
3343
+ "grad_norm": 0.125841423869133,
3344
+ "learning_rate": 4.528427608278718e-05,
3345
+ "loss": 0.3703,
3346
+ "step": 463
3347
+ },
3348
+ {
3349
+ "epoch": 2.72,
3350
+ "grad_norm": 0.12718433141708374,
3351
+ "learning_rate": 4.488767212230883e-05,
3352
+ "loss": 0.3439,
3353
+ "step": 464
3354
+ },
3355
+ {
3356
+ "epoch": 2.73,
3357
+ "grad_norm": 0.12245268374681473,
3358
+ "learning_rate": 4.4492309333079686e-05,
3359
+ "loss": 0.3512,
3360
+ "step": 465
3361
+ },
3362
+ {
3363
+ "epoch": 2.73,
3364
+ "grad_norm": 0.11985602229833603,
3365
+ "learning_rate": 4.409819661896839e-05,
3366
+ "loss": 0.3378,
3367
+ "step": 466
3368
+ },
3369
+ {
3370
+ "epoch": 2.74,
3371
+ "grad_norm": 0.12222087383270264,
3372
+ "learning_rate": 4.3705342855691e-05,
3373
+ "loss": 0.3514,
3374
+ "step": 467
3375
+ },
3376
+ {
3377
+ "epoch": 2.75,
3378
+ "grad_norm": 0.11923618614673615,
3379
+ "learning_rate": 4.331375689061089e-05,
3380
+ "loss": 0.3366,
3381
+ "step": 468
3382
+ },
3383
+ {
3384
+ "epoch": 2.75,
3385
+ "grad_norm": 0.12106750160455704,
3386
+ "learning_rate": 4.2923447542539787e-05,
3387
+ "loss": 0.3541,
3388
+ "step": 469
3389
+ },
3390
+ {
3391
+ "epoch": 2.76,
3392
+ "grad_norm": 0.12061194330453873,
3393
+ "learning_rate": 4.2534423601539055e-05,
3394
+ "loss": 0.3407,
3395
+ "step": 470
3396
+ },
3397
+ {
3398
+ "epoch": 2.76,
3399
+ "grad_norm": 0.12152953445911407,
3400
+ "learning_rate": 4.2146693828721574e-05,
3401
+ "loss": 0.341,
3402
+ "step": 471
3403
+ },
3404
+ {
3405
+ "epoch": 2.77,
3406
+ "grad_norm": 0.12051062285900116,
3407
+ "learning_rate": 4.176026695605476e-05,
3408
+ "loss": 0.341,
3409
+ "step": 472
3410
+ },
3411
+ {
3412
+ "epoch": 2.78,
3413
+ "grad_norm": 0.11901510506868362,
3414
+ "learning_rate": 4.1375151686163605e-05,
3415
+ "loss": 0.3438,
3416
+ "step": 473
3417
+ },
3418
+ {
3419
+ "epoch": 2.78,
3420
+ "grad_norm": 0.12126335501670837,
3421
+ "learning_rate": 4.099135669213483e-05,
3422
+ "loss": 0.3481,
3423
+ "step": 474
3424
+ },
3425
+ {
3426
+ "epoch": 2.79,
3427
+ "grad_norm": 0.12033100426197052,
3428
+ "learning_rate": 4.060889061732165e-05,
3429
+ "loss": 0.335,
3430
+ "step": 475
3431
+ },
3432
+ {
3433
+ "epoch": 2.79,
3434
+ "grad_norm": 0.1273912489414215,
3435
+ "learning_rate": 4.022776207514884e-05,
3436
+ "loss": 0.3575,
3437
+ "step": 476
3438
+ },
3439
+ {
3440
+ "epoch": 2.8,
3441
+ "grad_norm": 0.12302430719137192,
3442
+ "learning_rate": 3.984797964891914e-05,
3443
+ "loss": 0.3432,
3444
+ "step": 477
3445
+ },
3446
+ {
3447
+ "epoch": 2.81,
3448
+ "grad_norm": 0.1207548975944519,
3449
+ "learning_rate": 3.946955189161954e-05,
3450
+ "loss": 0.3342,
3451
+ "step": 478
3452
+ },
3453
+ {
3454
+ "epoch": 2.81,
3455
+ "grad_norm": 0.1166522428393364,
3456
+ "learning_rate": 3.9092487325728997e-05,
3457
+ "loss": 0.3224,
3458
+ "step": 479
3459
+ },
3460
+ {
3461
+ "epoch": 2.82,
3462
+ "grad_norm": 0.11961046606302261,
3463
+ "learning_rate": 3.871679444302635e-05,
3464
+ "loss": 0.3514,
3465
+ "step": 480
3466
+ },
3467
+ {
3468
+ "epoch": 2.82,
3469
+ "grad_norm": 0.11425036936998367,
3470
+ "learning_rate": 3.834248170439901e-05,
3471
+ "loss": 0.3343,
3472
+ "step": 481
3473
+ },
3474
+ {
3475
+ "epoch": 2.83,
3476
+ "grad_norm": 0.11901889741420746,
3477
+ "learning_rate": 3.796955753965263e-05,
3478
+ "loss": 0.3488,
3479
+ "step": 482
3480
+ },
3481
+ {
3482
+ "epoch": 2.84,
3483
+ "grad_norm": 0.12250632792711258,
3484
+ "learning_rate": 3.7598030347321e-05,
3485
+ "loss": 0.3497,
3486
+ "step": 483
3487
+ },
3488
+ {
3489
+ "epoch": 2.84,
3490
+ "grad_norm": 0.1186257004737854,
3491
+ "learning_rate": 3.722790849447717e-05,
3492
+ "loss": 0.3231,
3493
+ "step": 484
3494
+ },
3495
+ {
3496
+ "epoch": 2.85,
3497
+ "grad_norm": 0.1168690025806427,
3498
+ "learning_rate": 3.6859200316544765e-05,
3499
+ "loss": 0.3201,
3500
+ "step": 485
3501
+ },
3502
+ {
3503
+ "epoch": 2.85,
3504
+ "grad_norm": 0.1150059625506401,
3505
+ "learning_rate": 3.64919141171104e-05,
3506
+ "loss": 0.3171,
3507
+ "step": 486
3508
+ },
3509
+ {
3510
+ "epoch": 2.86,
3511
+ "grad_norm": 0.1203169897198677,
3512
+ "learning_rate": 3.612605816773674e-05,
3513
+ "loss": 0.3447,
3514
+ "step": 487
3515
+ },
3516
+ {
3517
+ "epoch": 2.86,
3518
+ "grad_norm": 0.1196681559085846,
3519
+ "learning_rate": 3.576164070777611e-05,
3520
+ "loss": 0.3362,
3521
+ "step": 488
3522
+ },
3523
+ {
3524
+ "epoch": 2.87,
3525
+ "grad_norm": 0.12342015653848648,
3526
+ "learning_rate": 3.5398669944184894e-05,
3527
+ "loss": 0.3434,
3528
+ "step": 489
3529
+ },
3530
+ {
3531
+ "epoch": 2.88,
3532
+ "grad_norm": 0.1177283450961113,
3533
+ "learning_rate": 3.503715405133888e-05,
3534
+ "loss": 0.3319,
3535
+ "step": 490
3536
+ },
3537
+ {
3538
+ "epoch": 2.88,
3539
+ "grad_norm": 0.12056996673345566,
3540
+ "learning_rate": 3.467710117084897e-05,
3541
+ "loss": 0.3342,
3542
+ "step": 491
3543
+ },
3544
+ {
3545
+ "epoch": 2.89,
3546
+ "grad_norm": 0.12151093780994415,
3547
+ "learning_rate": 3.4318519411378e-05,
3548
+ "loss": 0.343,
3549
+ "step": 492
3550
+ },
3551
+ {
3552
+ "epoch": 2.89,
3553
+ "grad_norm": 0.12013455480337143,
3554
+ "learning_rate": 3.396141684845807e-05,
3555
+ "loss": 0.342,
3556
+ "step": 493
3557
+ },
3558
+ {
3559
+ "epoch": 2.9,
3560
+ "grad_norm": 0.11809618771076202,
3561
+ "learning_rate": 3.3605801524308535e-05,
3562
+ "loss": 0.331,
3563
+ "step": 494
3564
+ },
3565
+ {
3566
+ "epoch": 2.91,
3567
+ "grad_norm": 0.11887520551681519,
3568
+ "learning_rate": 3.3251681447655144e-05,
3569
+ "loss": 0.3468,
3570
+ "step": 495
3571
+ },
3572
+ {
3573
+ "epoch": 2.91,
3574
+ "grad_norm": 0.11792317032814026,
3575
+ "learning_rate": 3.289906459354948e-05,
3576
+ "loss": 0.3276,
3577
+ "step": 496
3578
+ },
3579
+ {
3580
+ "epoch": 2.92,
3581
+ "grad_norm": 0.11810489743947983,
3582
+ "learning_rate": 3.254795890318935e-05,
3583
+ "loss": 0.3376,
3584
+ "step": 497
3585
+ },
3586
+ {
3587
+ "epoch": 2.92,
3588
+ "grad_norm": 0.12175795435905457,
3589
+ "learning_rate": 3.219837228374018e-05,
3590
+ "loss": 0.3403,
3591
+ "step": 498
3592
+ },
3593
+ {
3594
+ "epoch": 2.93,
3595
+ "grad_norm": 0.11994338035583496,
3596
+ "learning_rate": 3.185031260815659e-05,
3597
+ "loss": 0.3252,
3598
+ "step": 499
3599
+ },
3600
+ {
3601
+ "epoch": 2.94,
3602
+ "grad_norm": 0.11685537546873093,
3603
+ "learning_rate": 3.150378771500542e-05,
3604
+ "loss": 0.3342,
3605
+ "step": 500
3606
+ },
3607
+ {
3608
+ "epoch": 2.94,
3609
+ "grad_norm": 0.11831715703010559,
3610
+ "learning_rate": 3.1158805408288994e-05,
3611
+ "loss": 0.3327,
3612
+ "step": 501
3613
+ },
3614
+ {
3615
+ "epoch": 2.95,
3616
+ "grad_norm": 0.121400386095047,
3617
+ "learning_rate": 3.081537345726936e-05,
3618
+ "loss": 0.3522,
3619
+ "step": 502
3620
+ },
3621
+ {
3622
+ "epoch": 2.95,
3623
+ "grad_norm": 0.11787579953670502,
3624
+ "learning_rate": 3.047349959629352e-05,
3625
+ "loss": 0.3322,
3626
+ "step": 503
3627
+ },
3628
+ {
3629
+ "epoch": 2.96,
3630
+ "grad_norm": 0.12182048708200455,
3631
+ "learning_rate": 3.0133191524618953e-05,
3632
+ "loss": 0.3371,
3633
+ "step": 504
3634
+ },
3635
+ {
3636
+ "epoch": 2.96,
3637
+ "eval_loss": 0.49804943799972534,
3638
+ "eval_runtime": 21.4624,
3639
+ "eval_samples_per_second": 46.267,
3640
+ "eval_steps_per_second": 11.602,
3641
+ "step": 504
3642
+ }
3643
+ ],
3644
+ "logging_steps": 1,
3645
+ "max_steps": 672,
3646
+ "num_input_tokens_seen": 0,
3647
+ "num_train_epochs": 4,
3648
+ "save_steps": 168,
3649
+ "total_flos": 1.5039570715638497e+18,
3650
+ "train_batch_size": 1,
3651
+ "trial_name": null,
3652
+ "trial_params": null
3653
+ }
checkpoint-504/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a2f0ef670d0281abf97e6b6a3c9043bd5509665b561215ad64107dc2e4edda
3
+ size 5752
checkpoint-672/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.10.0
checkpoint-672/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-672/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bf7e29273c37913018025ec5cf7102154f4b2a0daabc44a1691cd1c96b9a0b
3
+ size 335604696
checkpoint-672/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc32011ecd6e176c742c8d20e9f79f89c96a0b48bee7e34d7c6e6f111904c53
3
+ size 168625172
checkpoint-672/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3031e43f212678a34d1aeec0a228d41518f4ddc7a019848c849ea3ed0a49b977
3
+ size 15024