Hugging Face's logo

saucam
/
llama-airo-3

PEFT
Safetensors
llama
Generated from Trainer
Model card Files Community
1
saucam commited on
Commit
4db226d
•
1 Parent(s): 0192bd6

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. README.md +143 -0
  2. adapter_config.json +34 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-455/README.md +202 -0
  5. checkpoint-455/adapter_config.json +34 -0
  6. checkpoint-455/adapter_model.safetensors +3 -0
  7. checkpoint-455/optimizer.pt +3 -0
  8. checkpoint-455/rng_state.pth +3 -0
  9. checkpoint-455/scheduler.pt +3 -0
  10. checkpoint-455/special_tokens_map.json +23 -0
  11. checkpoint-455/tokenizer.json +0 -0
  12. checkpoint-455/tokenizer_config.json +2062 -0
  13. checkpoint-455/trainer_state.json +3238 -0
  14. checkpoint-455/training_args.bin +3 -0
  15. config.json +2 -2
  16. special_tokens_map.json +7 -0
  17. tokenizer_config.json +1 -0
README.md ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 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: false
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: jondurbin/airoboros-3.2
30
+ type: sharegpt
31
+
32
+ dataset_prepared_path:
33
+ val_set_size: 0.05
34
+ output_dir: ./out
35
+
36
+ sequence_len: 8192
37
+ sample_packing: true
38
+ pad_to_sequence_len: true
39
+
40
+ adapter: lora
41
+ lora_model_dir:
42
+ lora_r: 32
43
+ lora_alpha: 16
44
+ lora_dropout: 0.05
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project: llama3
49
+ wandb_entity: saucam
50
+ wandb_watch: all
51
+ wandb_name: llama3-cosmo-run-1
52
+ wandb_log_model: "end"
53
+
54
+ gradient_accumulation_steps: 4
55
+ micro_batch_size: 2
56
+ num_epochs: 1
57
+ optimizer: adamw_bnb_8bit
58
+ lr_scheduler: cosine
59
+ learning_rate: 0.0002
60
+
61
+ train_on_inputs: false
62
+ group_by_length: false
63
+ bf16: auto
64
+ fp16:
65
+ tf32: false
66
+
67
+ gradient_checkpointing: true
68
+ early_stopping_patience:
69
+ resume_from_checkpoint:
70
+ local_rank:
71
+ logging_steps: 1
72
+ xformers_attention:
73
+ flash_attention: true
74
+ s2_attention:
75
+
76
+ warmup_steps: 10
77
+ evals_per_epoch: 4
78
+ eval_table_size:
79
+ eval_max_new_tokens: 128
80
+ saves_per_epoch: 1
81
+ debug:
82
+ deepspeed:
83
+ weight_decay: 0.0
84
+ fsdp:
85
+ fsdp_config:
86
+ special_tokens:
87
+ pad_token: <|end_of_text|>
88
+
89
+ ```
90
+
91
+ </details><br>
92
+
93
+ # out
94
+
95
+ 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.
96
+ It achieves the following results on the evaluation set:
97
+ - Loss: 0.8437
98
+
99
+ ## Model description
100
+
101
+ More information needed
102
+
103
+ ## Intended uses & limitations
104
+
105
+ More information needed
106
+
107
+ ## Training and evaluation data
108
+
109
+ More information needed
110
+
111
+ ## Training procedure
112
+
113
+ ### Training hyperparameters
114
+
115
+ The following hyperparameters were used during training:
116
+ - learning_rate: 0.0002
117
+ - train_batch_size: 2
118
+ - eval_batch_size: 2
119
+ - seed: 42
120
+ - gradient_accumulation_steps: 4
121
+ - total_train_batch_size: 8
122
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
123
+ - lr_scheduler_type: cosine
124
+ - lr_scheduler_warmup_steps: 10
125
+ - num_epochs: 1
126
+
127
+ ### Training results
128
+
129
+ | Training Loss | Epoch | Step | Validation Loss |
130
+ |:-------------:|:-----:|:----:|:---------------:|
131
+ | 1.1845 | 0.0 | 1 | 1.1821 |
132
+ | 0.9328 | 0.25 | 114 | 0.9228 |
133
+ | 0.8961 | 0.5 | 228 | 0.8713 |
134
+ | 0.824 | 0.75 | 342 | 0.8437 |
135
+
136
+
137
+ ### Framework versions
138
+
139
+ - PEFT 0.10.0
140
+ - Transformers 4.40.0.dev0
141
+ - Pytorch 2.1.2+cu118
142
+ - Datasets 2.15.0
143
+ - 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
+ "up_proj",
24
+ "o_proj",
25
+ "q_proj",
26
+ "gate_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "v_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:e735572408196d97ea490f40c217e61b1409026d8d92a12609aa4bd3fa1dac9e
3
+ size 167934026
checkpoint-455/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-455/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
+ "up_proj",
24
+ "o_proj",
25
+ "q_proj",
26
+ "gate_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-455/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873ab2c8be44150123de180b878901b897d6be295e8a07209a2ea0439699a4cb
3
+ size 167832688
checkpoint-455/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e96e4eedc61691c38fca4959b87c47956d2bff4bee2a0757a9dd75bfda245d47
3
+ size 168625172
checkpoint-455/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65450d449704f61dfb31d317494366992b188f55170846d4ba090fb4f4c888bb
3
+ size 14244
checkpoint-455/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804abfb08c3b558441ed7a64b222b25b348acc69c467bcfcafb7cca5ea43ebbf
3
+ size 1064
checkpoint-455/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-455/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-455/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-455/trainer_state.json ADDED
@@ -0,0 +1,3238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.99945085118067,
5
+ "eval_steps": 114,
6
+ "global_step": 455,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.1220703125,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.1845,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 1.1820911169052124,
21
+ "eval_runtime": 382.4714,
22
+ "eval_samples_per_second": 7.676,
23
+ "eval_steps_per_second": 3.838,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0,
28
+ "grad_norm": 0.1162109375,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.1777,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 0.115234375,
36
+ "learning_rate": 6e-05,
37
+ "loss": 1.1406,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "grad_norm": 0.126953125,
43
+ "learning_rate": 8e-05,
44
+ "loss": 1.2366,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "grad_norm": 0.150390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.2321,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.01,
56
+ "grad_norm": 0.1513671875,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.0941,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "grad_norm": 0.103515625,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.0609,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.02,
70
+ "grad_norm": 0.10498046875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.0332,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.02,
77
+ "grad_norm": 0.0927734375,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.1241,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "grad_norm": 0.1162109375,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.1964,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "grad_norm": 0.150390625,
92
+ "learning_rate": 0.00019999750800065415,
93
+ "loss": 1.254,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.03,
98
+ "grad_norm": 0.130859375,
99
+ "learning_rate": 0.00019999003212681782,
100
+ "loss": 1.0003,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.03,
105
+ "grad_norm": 0.10888671875,
106
+ "learning_rate": 0.00019997757275108847,
107
+ "loss": 1.033,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.03,
112
+ "grad_norm": 0.09619140625,
113
+ "learning_rate": 0.00019996013049444118,
114
+ "loss": 1.0915,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.03,
119
+ "grad_norm": 0.09521484375,
120
+ "learning_rate": 0.00019993770622619782,
121
+ "loss": 1.027,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.04,
126
+ "grad_norm": 0.08154296875,
127
+ "learning_rate": 0.00019991030106398364,
128
+ "loss": 0.8964,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.04,
133
+ "grad_norm": 0.08203125,
134
+ "learning_rate": 0.00019987791637367158,
135
+ "loss": 0.9778,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.04,
140
+ "grad_norm": 0.07666015625,
141
+ "learning_rate": 0.00019984055376931413,
142
+ "loss": 1.0588,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.04,
147
+ "grad_norm": 0.076171875,
148
+ "learning_rate": 0.00019979821511306308,
149
+ "loss": 0.9921,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.04,
154
+ "grad_norm": 0.0830078125,
155
+ "learning_rate": 0.00019975090251507638,
156
+ "loss": 1.0424,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.05,
161
+ "grad_norm": 0.08642578125,
162
+ "learning_rate": 0.0001996986183334134,
163
+ "loss": 1.0514,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.05,
168
+ "grad_norm": 0.07568359375,
169
+ "learning_rate": 0.00019964136517391706,
170
+ "loss": 1.0248,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.05,
175
+ "grad_norm": 0.0927734375,
176
+ "learning_rate": 0.00019957914589008405,
177
+ "loss": 1.0394,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.05,
182
+ "grad_norm": 0.07568359375,
183
+ "learning_rate": 0.00019951196358292266,
184
+ "loss": 1.0678,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.05,
189
+ "grad_norm": 0.07861328125,
190
+ "learning_rate": 0.0001994398216007982,
191
+ "loss": 0.9298,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.06,
196
+ "grad_norm": 0.095703125,
197
+ "learning_rate": 0.00019936272353926615,
198
+ "loss": 0.991,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.06,
203
+ "grad_norm": 0.07958984375,
204
+ "learning_rate": 0.00019928067324089286,
205
+ "loss": 0.9823,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.06,
210
+ "grad_norm": 0.08349609375,
211
+ "learning_rate": 0.00019919367479506413,
212
+ "loss": 1.0103,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.06,
217
+ "grad_norm": 0.07568359375,
218
+ "learning_rate": 0.00019910173253778136,
219
+ "loss": 0.9725,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.07,
224
+ "grad_norm": 0.07421875,
225
+ "learning_rate": 0.00019900485105144543,
226
+ "loss": 1.0453,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.07,
231
+ "grad_norm": 0.0830078125,
232
+ "learning_rate": 0.00019890303516462843,
233
+ "loss": 1.0282,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.07,
238
+ "grad_norm": 0.08544921875,
239
+ "learning_rate": 0.00019879628995183272,
240
+ "loss": 0.9683,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.07,
245
+ "grad_norm": 0.0732421875,
246
+ "learning_rate": 0.00019868462073323838,
247
+ "loss": 0.9711,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.07,
252
+ "grad_norm": 0.07666015625,
253
+ "learning_rate": 0.00019856803307443781,
254
+ "loss": 0.9303,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.08,
259
+ "grad_norm": 0.0751953125,
260
+ "learning_rate": 0.00019844653278615833,
261
+ "loss": 0.9018,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.08,
266
+ "grad_norm": 0.07470703125,
267
+ "learning_rate": 0.0001983201259239728,
268
+ "loss": 0.932,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.08,
273
+ "grad_norm": 0.072265625,
274
+ "learning_rate": 0.00019818881878799752,
275
+ "loss": 0.9073,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.08,
280
+ "grad_norm": 0.0791015625,
281
+ "learning_rate": 0.00019805261792257847,
282
+ "loss": 0.9367,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.09,
287
+ "grad_norm": 0.0771484375,
288
+ "learning_rate": 0.00019791153011596496,
289
+ "loss": 1.0177,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.09,
294
+ "grad_norm": 0.07666015625,
295
+ "learning_rate": 0.00019776556239997146,
296
+ "loss": 0.8887,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.09,
301
+ "grad_norm": 0.08056640625,
302
+ "learning_rate": 0.000197614722049627,
303
+ "loss": 1.0279,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.09,
308
+ "grad_norm": 0.08544921875,
309
+ "learning_rate": 0.00019745901658281266,
310
+ "loss": 1.0993,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.09,
315
+ "grad_norm": 0.0751953125,
316
+ "learning_rate": 0.00019729845375988694,
317
+ "loss": 0.9436,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.1,
322
+ "grad_norm": 0.08203125,
323
+ "learning_rate": 0.00019713304158329873,
324
+ "loss": 1.0442,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.1,
329
+ "grad_norm": 0.08251953125,
330
+ "learning_rate": 0.00019696278829718883,
331
+ "loss": 1.0196,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.1,
336
+ "grad_norm": 0.09130859375,
337
+ "learning_rate": 0.00019678770238697874,
338
+ "loss": 1.0415,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.1,
343
+ "grad_norm": 0.08935546875,
344
+ "learning_rate": 0.00019660779257894796,
345
+ "loss": 0.983,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.11,
350
+ "grad_norm": 0.07763671875,
351
+ "learning_rate": 0.000196423067839799,
352
+ "loss": 0.9415,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.11,
357
+ "grad_norm": 0.09228515625,
358
+ "learning_rate": 0.00019623353737621035,
359
+ "loss": 0.9829,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.11,
364
+ "grad_norm": 0.10009765625,
365
+ "learning_rate": 0.00019603921063437793,
366
+ "loss": 0.9223,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.11,
371
+ "grad_norm": 0.08447265625,
372
+ "learning_rate": 0.00019584009729954396,
373
+ "loss": 0.8714,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.11,
378
+ "grad_norm": 0.08837890625,
379
+ "learning_rate": 0.00019563620729551445,
380
+ "loss": 0.8981,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.12,
385
+ "grad_norm": 0.103515625,
386
+ "learning_rate": 0.00019542755078416456,
387
+ "loss": 0.9528,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.12,
392
+ "grad_norm": 0.08154296875,
393
+ "learning_rate": 0.00019521413816493206,
394
+ "loss": 1.0403,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.12,
399
+ "grad_norm": 0.08251953125,
400
+ "learning_rate": 0.0001949959800742991,
401
+ "loss": 1.0177,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.12,
406
+ "grad_norm": 0.09375,
407
+ "learning_rate": 0.00019477308738526206,
408
+ "loss": 1.0504,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.13,
413
+ "grad_norm": 0.087890625,
414
+ "learning_rate": 0.00019454547120678967,
415
+ "loss": 0.9463,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.13,
420
+ "grad_norm": 0.09130859375,
421
+ "learning_rate": 0.00019431314288326926,
422
+ "loss": 0.907,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.13,
427
+ "grad_norm": 0.083984375,
428
+ "learning_rate": 0.00019407611399394143,
429
+ "loss": 0.8962,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.13,
434
+ "grad_norm": 0.103515625,
435
+ "learning_rate": 0.00019383439635232294,
436
+ "loss": 0.9455,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.13,
441
+ "grad_norm": 0.10009765625,
442
+ "learning_rate": 0.0001935880020056179,
443
+ "loss": 1.0383,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.14,
448
+ "grad_norm": 0.0849609375,
449
+ "learning_rate": 0.00019333694323411734,
450
+ "loss": 0.9763,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.14,
455
+ "grad_norm": 0.09130859375,
456
+ "learning_rate": 0.00019308123255058708,
457
+ "loss": 1.0526,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.14,
462
+ "grad_norm": 0.08251953125,
463
+ "learning_rate": 0.0001928208826996443,
464
+ "loss": 0.8888,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.14,
469
+ "grad_norm": 0.08740234375,
470
+ "learning_rate": 0.00019255590665712214,
471
+ "loss": 0.925,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.14,
476
+ "grad_norm": 0.08203125,
477
+ "learning_rate": 0.00019228631762942307,
478
+ "loss": 0.8944,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.15,
483
+ "grad_norm": 0.09130859375,
484
+ "learning_rate": 0.00019201212905286074,
485
+ "loss": 0.9638,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.15,
490
+ "grad_norm": 0.09814453125,
491
+ "learning_rate": 0.00019173335459299025,
492
+ "loss": 0.9773,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.15,
497
+ "grad_norm": 0.09130859375,
498
+ "learning_rate": 0.00019145000814392696,
499
+ "loss": 0.9241,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.15,
504
+ "grad_norm": 0.091796875,
505
+ "learning_rate": 0.0001911621038276542,
506
+ "loss": 0.9495,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.16,
511
+ "grad_norm": 0.09375,
512
+ "learning_rate": 0.00019086965599331938,
513
+ "loss": 0.9238,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.16,
518
+ "grad_norm": 0.09326171875,
519
+ "learning_rate": 0.00019057267921651866,
520
+ "loss": 0.9721,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.16,
525
+ "grad_norm": 0.09326171875,
526
+ "learning_rate": 0.00019027118829857077,
527
+ "loss": 0.9081,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.16,
532
+ "grad_norm": 0.10546875,
533
+ "learning_rate": 0.00018996519826577907,
534
+ "loss": 0.9803,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.16,
539
+ "grad_norm": 0.0830078125,
540
+ "learning_rate": 0.00018965472436868286,
541
+ "loss": 0.9435,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.17,
546
+ "grad_norm": 0.09814453125,
547
+ "learning_rate": 0.00018933978208129706,
548
+ "loss": 0.8613,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.17,
553
+ "grad_norm": 0.091796875,
554
+ "learning_rate": 0.00018902038710034112,
555
+ "loss": 0.9293,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.17,
560
+ "grad_norm": 0.1015625,
561
+ "learning_rate": 0.0001886965553444568,
562
+ "loss": 1.0039,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.17,
567
+ "grad_norm": 0.091796875,
568
+ "learning_rate": 0.0001883683029534145,
569
+ "loss": 0.9316,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.18,
574
+ "grad_norm": 0.08154296875,
575
+ "learning_rate": 0.00018803564628730915,
576
+ "loss": 0.987,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.18,
581
+ "grad_norm": 0.0908203125,
582
+ "learning_rate": 0.0001876986019257446,
583
+ "loss": 0.9598,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.18,
588
+ "grad_norm": 0.1044921875,
589
+ "learning_rate": 0.0001873571866670074,
590
+ "loss": 0.872,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.18,
595
+ "grad_norm": 0.0859375,
596
+ "learning_rate": 0.00018701141752722964,
597
+ "loss": 0.9035,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.18,
602
+ "grad_norm": 0.095703125,
603
+ "learning_rate": 0.0001866613117395407,
604
+ "loss": 0.9103,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.19,
609
+ "grad_norm": 0.087890625,
610
+ "learning_rate": 0.00018630688675320842,
611
+ "loss": 0.9446,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.19,
616
+ "grad_norm": 0.08251953125,
617
+ "learning_rate": 0.00018594816023276953,
618
+ "loss": 0.8302,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.19,
623
+ "grad_norm": 0.091796875,
624
+ "learning_rate": 0.0001855851500571491,
625
+ "loss": 0.9336,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.19,
630
+ "grad_norm": 0.09521484375,
631
+ "learning_rate": 0.00018521787431876954,
632
+ "loss": 0.9285,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.2,
637
+ "grad_norm": 0.08984375,
638
+ "learning_rate": 0.0001848463513226488,
639
+ "loss": 0.8675,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.2,
644
+ "grad_norm": 0.09521484375,
645
+ "learning_rate": 0.0001844705995854882,
646
+ "loss": 0.9251,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.2,
651
+ "grad_norm": 0.0859375,
652
+ "learning_rate": 0.0001840906378347494,
653
+ "loss": 0.8655,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.2,
658
+ "grad_norm": 0.107421875,
659
+ "learning_rate": 0.00018370648500772108,
660
+ "loss": 0.9182,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.2,
665
+ "grad_norm": 0.09521484375,
666
+ "learning_rate": 0.0001833181602505751,
667
+ "loss": 0.873,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.21,
672
+ "grad_norm": 0.0947265625,
673
+ "learning_rate": 0.00018292568291741228,
674
+ "loss": 0.9838,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.21,
679
+ "grad_norm": 0.099609375,
680
+ "learning_rate": 0.00018252907256929775,
681
+ "loss": 0.8565,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.21,
686
+ "grad_norm": 0.0888671875,
687
+ "learning_rate": 0.00018212834897328613,
688
+ "loss": 0.8747,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.21,
693
+ "grad_norm": 0.0888671875,
694
+ "learning_rate": 0.0001817235321014361,
695
+ "loss": 0.9313,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.22,
700
+ "grad_norm": 0.099609375,
701
+ "learning_rate": 0.0001813146421298154,
702
+ "loss": 0.8365,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.22,
707
+ "grad_norm": 0.10107421875,
708
+ "learning_rate": 0.00018090169943749476,
709
+ "loss": 1.0068,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.22,
714
+ "grad_norm": 0.09228515625,
715
+ "learning_rate": 0.00018048472460553257,
716
+ "loss": 0.8783,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.22,
721
+ "grad_norm": 0.0986328125,
722
+ "learning_rate": 0.00018006373841594905,
723
+ "loss": 0.9325,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.22,
728
+ "grad_norm": 0.09619140625,
729
+ "learning_rate": 0.00017963876185069034,
730
+ "loss": 1.0326,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.23,
735
+ "grad_norm": 0.1064453125,
736
+ "learning_rate": 0.00017920981609058289,
737
+ "loss": 0.8769,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.23,
742
+ "grad_norm": 0.0869140625,
743
+ "learning_rate": 0.00017877692251427782,
744
+ "loss": 0.9167,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.23,
749
+ "grad_norm": 0.1142578125,
750
+ "learning_rate": 0.00017834010269718526,
751
+ "loss": 0.9688,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.23,
756
+ "grad_norm": 0.08740234375,
757
+ "learning_rate": 0.00017789937841039918,
758
+ "loss": 0.8039,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.24,
763
+ "grad_norm": 0.08837890625,
764
+ "learning_rate": 0.0001774547716196123,
765
+ "loss": 0.9943,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.24,
770
+ "grad_norm": 0.1064453125,
771
+ "learning_rate": 0.00017700630448402125,
772
+ "loss": 0.9769,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.24,
777
+ "grad_norm": 0.09619140625,
778
+ "learning_rate": 0.00017655399935522217,
779
+ "loss": 0.8973,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.24,
784
+ "grad_norm": 0.1025390625,
785
+ "learning_rate": 0.0001760978787760968,
786
+ "loss": 0.8602,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.24,
791
+ "grad_norm": 0.09814453125,
792
+ "learning_rate": 0.0001756379654796888,
793
+ "loss": 0.8966,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.25,
798
+ "grad_norm": 0.09521484375,
799
+ "learning_rate": 0.00017517428238807085,
800
+ "loss": 0.8997,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.25,
805
+ "grad_norm": 0.0947265625,
806
+ "learning_rate": 0.0001747068526112022,
807
+ "loss": 0.9476,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.25,
812
+ "grad_norm": 0.09814453125,
813
+ "learning_rate": 0.00017423569944577678,
814
+ "loss": 0.9328,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.25,
819
+ "eval_loss": 0.922809362411499,
820
+ "eval_runtime": 418.8489,
821
+ "eval_samples_per_second": 7.01,
822
+ "eval_steps_per_second": 3.505,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 0.25,
827
+ "grad_norm": 0.09619140625,
828
+ "learning_rate": 0.00017376084637406222,
829
+ "loss": 0.8643,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 0.25,
834
+ "grad_norm": 0.10302734375,
835
+ "learning_rate": 0.0001732823170627294,
836
+ "loss": 0.9659,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 0.26,
841
+ "grad_norm": 0.0986328125,
842
+ "learning_rate": 0.00017280013536167293,
843
+ "loss": 0.8158,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 0.26,
848
+ "grad_norm": 0.1025390625,
849
+ "learning_rate": 0.00017231432530282246,
850
+ "loss": 0.9843,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 0.26,
855
+ "grad_norm": 0.08984375,
856
+ "learning_rate": 0.000171824911098945,
857
+ "loss": 0.9591,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 0.26,
862
+ "grad_norm": 0.09423828125,
863
+ "learning_rate": 0.00017133191714243805,
864
+ "loss": 0.9331,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 0.27,
869
+ "grad_norm": 0.103515625,
870
+ "learning_rate": 0.00017083536800411393,
871
+ "loss": 0.8647,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 0.27,
876
+ "grad_norm": 0.0888671875,
877
+ "learning_rate": 0.00017033528843197525,
878
+ "loss": 1.0038,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 0.27,
883
+ "grad_norm": 0.1005859375,
884
+ "learning_rate": 0.00016983170334998132,
885
+ "loss": 0.8214,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 0.27,
890
+ "grad_norm": 0.08544921875,
891
+ "learning_rate": 0.000169324637856806,
892
+ "loss": 0.8832,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 0.27,
897
+ "grad_norm": 0.0859375,
898
+ "learning_rate": 0.00016881411722458688,
899
+ "loss": 0.8642,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 0.28,
904
+ "grad_norm": 0.09375,
905
+ "learning_rate": 0.00016830016689766558,
906
+ "loss": 0.9047,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 0.28,
911
+ "grad_norm": 0.095703125,
912
+ "learning_rate": 0.0001677828124913197,
913
+ "loss": 0.8494,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 0.28,
918
+ "grad_norm": 0.08837890625,
919
+ "learning_rate": 0.00016726207979048604,
920
+ "loss": 0.9421,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.28,
925
+ "grad_norm": 0.09423828125,
926
+ "learning_rate": 0.0001667379947484756,
927
+ "loss": 0.8429,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.29,
932
+ "grad_norm": 0.10400390625,
933
+ "learning_rate": 0.00016621058348568007,
934
+ "loss": 0.8319,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.29,
939
+ "grad_norm": 0.09912109375,
940
+ "learning_rate": 0.0001656798722882698,
941
+ "loss": 0.8681,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.29,
946
+ "grad_norm": 0.10498046875,
947
+ "learning_rate": 0.00016514588760688397,
948
+ "loss": 0.9469,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.29,
953
+ "grad_norm": 0.091796875,
954
+ "learning_rate": 0.00016460865605531213,
955
+ "loss": 0.9818,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.29,
960
+ "grad_norm": 0.10009765625,
961
+ "learning_rate": 0.0001640682044091678,
962
+ "loss": 0.9046,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.3,
967
+ "grad_norm": 0.09326171875,
968
+ "learning_rate": 0.00016352455960455387,
969
+ "loss": 0.9319,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.3,
974
+ "grad_norm": 0.09716796875,
975
+ "learning_rate": 0.00016297774873672035,
976
+ "loss": 0.963,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.3,
981
+ "grad_norm": 0.103515625,
982
+ "learning_rate": 0.00016242779905871374,
983
+ "loss": 0.8749,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.3,
988
+ "grad_norm": 0.09423828125,
989
+ "learning_rate": 0.00016187473798001879,
990
+ "loss": 0.9731,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.31,
995
+ "grad_norm": 0.1015625,
996
+ "learning_rate": 0.00016131859306519242,
997
+ "loss": 0.8319,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.31,
1002
+ "grad_norm": 0.0908203125,
1003
+ "learning_rate": 0.0001607593920324899,
1004
+ "loss": 0.8156,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.31,
1009
+ "grad_norm": 0.10791015625,
1010
+ "learning_rate": 0.00016019716275248342,
1011
+ "loss": 0.9433,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.31,
1016
+ "grad_norm": 0.12451171875,
1017
+ "learning_rate": 0.0001596319332466729,
1018
+ "loss": 0.913,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.31,
1023
+ "grad_norm": 0.1005859375,
1024
+ "learning_rate": 0.00015906373168608952,
1025
+ "loss": 0.9255,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.32,
1030
+ "grad_norm": 0.10498046875,
1031
+ "learning_rate": 0.00015849258638989165,
1032
+ "loss": 0.9524,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.32,
1037
+ "grad_norm": 0.1015625,
1038
+ "learning_rate": 0.00015791852582395334,
1039
+ "loss": 1.0442,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.32,
1044
+ "grad_norm": 0.123046875,
1045
+ "learning_rate": 0.00015734157859944575,
1046
+ "loss": 0.8188,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.32,
1051
+ "grad_norm": 0.10107421875,
1052
+ "learning_rate": 0.00015676177347141094,
1053
+ "loss": 0.8675,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.33,
1058
+ "grad_norm": 0.09423828125,
1059
+ "learning_rate": 0.00015617913933732892,
1060
+ "loss": 0.9065,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.33,
1065
+ "grad_norm": 0.1064453125,
1066
+ "learning_rate": 0.00015559370523567732,
1067
+ "loss": 0.9665,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.33,
1072
+ "grad_norm": 0.1162109375,
1073
+ "learning_rate": 0.00015500550034448413,
1074
+ "loss": 0.8779,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.33,
1079
+ "grad_norm": 0.08837890625,
1080
+ "learning_rate": 0.0001544145539798734,
1081
+ "loss": 0.8539,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.33,
1086
+ "grad_norm": 0.1142578125,
1087
+ "learning_rate": 0.00015382089559460422,
1088
+ "loss": 0.9068,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.34,
1093
+ "grad_norm": 0.10498046875,
1094
+ "learning_rate": 0.00015322455477660273,
1095
+ "loss": 0.9563,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.34,
1100
+ "grad_norm": 0.09423828125,
1101
+ "learning_rate": 0.00015262556124748751,
1102
+ "loss": 0.8071,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.34,
1107
+ "grad_norm": 0.1123046875,
1108
+ "learning_rate": 0.0001520239448610882,
1109
+ "loss": 0.8971,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.34,
1114
+ "grad_norm": 0.103515625,
1115
+ "learning_rate": 0.00015141973560195768,
1116
+ "loss": 0.883,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.34,
1121
+ "grad_norm": 0.10498046875,
1122
+ "learning_rate": 0.0001508129635838775,
1123
+ "loss": 0.8609,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.35,
1128
+ "grad_norm": 0.10986328125,
1129
+ "learning_rate": 0.000150203659048357,
1130
+ "loss": 0.9184,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.35,
1135
+ "grad_norm": 0.109375,
1136
+ "learning_rate": 0.00014959185236312642,
1137
+ "loss": 0.8602,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.35,
1142
+ "grad_norm": 0.107421875,
1143
+ "learning_rate": 0.00014897757402062284,
1144
+ "loss": 0.8908,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.35,
1149
+ "grad_norm": 0.09521484375,
1150
+ "learning_rate": 0.00014836085463647088,
1151
+ "loss": 0.9134,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.36,
1156
+ "grad_norm": 0.109375,
1157
+ "learning_rate": 0.00014774172494795652,
1158
+ "loss": 0.9385,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.36,
1163
+ "grad_norm": 0.10888671875,
1164
+ "learning_rate": 0.00014712021581249533,
1165
+ "loss": 0.8183,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.36,
1170
+ "grad_norm": 0.09814453125,
1171
+ "learning_rate": 0.00014649635820609456,
1172
+ "loss": 0.8806,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.36,
1177
+ "grad_norm": 0.10009765625,
1178
+ "learning_rate": 0.00014587018322180905,
1179
+ "loss": 0.915,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.36,
1184
+ "grad_norm": 0.12109375,
1185
+ "learning_rate": 0.00014524172206819194,
1186
+ "loss": 0.848,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.37,
1191
+ "grad_norm": 0.10009765625,
1192
+ "learning_rate": 0.00014461100606773884,
1193
+ "loss": 0.9189,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.37,
1198
+ "grad_norm": 0.099609375,
1199
+ "learning_rate": 0.00014397806665532694,
1200
+ "loss": 0.78,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.37,
1205
+ "grad_norm": 0.10205078125,
1206
+ "learning_rate": 0.00014334293537664837,
1207
+ "loss": 0.8854,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.37,
1212
+ "grad_norm": 0.10009765625,
1213
+ "learning_rate": 0.0001427056438866376,
1214
+ "loss": 0.7996,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.38,
1219
+ "grad_norm": 0.10693359375,
1220
+ "learning_rate": 0.00014206622394789432,
1221
+ "loss": 0.9002,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.38,
1226
+ "grad_norm": 0.1083984375,
1227
+ "learning_rate": 0.00014142470742909975,
1228
+ "loss": 0.9172,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.38,
1233
+ "grad_norm": 0.10693359375,
1234
+ "learning_rate": 0.0001407811263034289,
1235
+ "loss": 0.9438,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.38,
1240
+ "grad_norm": 0.12890625,
1241
+ "learning_rate": 0.00014013551264695662,
1242
+ "loss": 0.8709,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.38,
1247
+ "grad_norm": 0.11328125,
1248
+ "learning_rate": 0.00013948789863705912,
1249
+ "loss": 0.8717,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.39,
1254
+ "grad_norm": 0.10205078125,
1255
+ "learning_rate": 0.00013883831655081018,
1256
+ "loss": 0.9313,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.39,
1261
+ "grad_norm": 0.11669921875,
1262
+ "learning_rate": 0.00013818679876337247,
1263
+ "loss": 0.914,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.39,
1268
+ "grad_norm": 0.1064453125,
1269
+ "learning_rate": 0.00013753337774638396,
1270
+ "loss": 0.919,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.39,
1275
+ "grad_norm": 0.10791015625,
1276
+ "learning_rate": 0.00013687808606633966,
1277
+ "loss": 0.9628,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.4,
1282
+ "grad_norm": 0.11376953125,
1283
+ "learning_rate": 0.00013622095638296826,
1284
+ "loss": 0.8947,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.4,
1289
+ "grad_norm": 0.11669921875,
1290
+ "learning_rate": 0.0001355620214476046,
1291
+ "loss": 0.9269,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.4,
1296
+ "grad_norm": 0.10595703125,
1297
+ "learning_rate": 0.00013490131410155728,
1298
+ "loss": 0.8438,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.4,
1303
+ "grad_norm": 0.11669921875,
1304
+ "learning_rate": 0.00013423886727447176,
1305
+ "loss": 0.8986,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.4,
1310
+ "grad_norm": 0.11474609375,
1311
+ "learning_rate": 0.00013357471398268918,
1312
+ "loss": 0.9274,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.41,
1317
+ "grad_norm": 0.111328125,
1318
+ "learning_rate": 0.000132908887327601,
1319
+ "loss": 0.8511,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.41,
1324
+ "grad_norm": 0.11767578125,
1325
+ "learning_rate": 0.00013224142049399895,
1326
+ "loss": 0.809,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.41,
1331
+ "grad_norm": 0.12158203125,
1332
+ "learning_rate": 0.00013157234674842128,
1333
+ "loss": 0.7523,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.41,
1338
+ "grad_norm": 0.11669921875,
1339
+ "learning_rate": 0.00013090169943749476,
1340
+ "loss": 0.9021,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.42,
1345
+ "grad_norm": 0.11865234375,
1346
+ "learning_rate": 0.00013022951198627254,
1347
+ "loss": 0.8875,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.42,
1352
+ "grad_norm": 0.09521484375,
1353
+ "learning_rate": 0.00012955581789656843,
1354
+ "loss": 0.8563,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.42,
1359
+ "grad_norm": 0.1123046875,
1360
+ "learning_rate": 0.000128880650745287,
1361
+ "loss": 0.7841,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.42,
1366
+ "grad_norm": 0.10107421875,
1367
+ "learning_rate": 0.0001282040441827503,
1368
+ "loss": 0.925,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.42,
1373
+ "grad_norm": 0.10107421875,
1374
+ "learning_rate": 0.0001275260319310205,
1375
+ "loss": 1.0102,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.43,
1380
+ "grad_norm": 0.115234375,
1381
+ "learning_rate": 0.00012684664778221942,
1382
+ "loss": 0.7835,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.43,
1387
+ "grad_norm": 0.10791015625,
1388
+ "learning_rate": 0.0001261659255968441,
1389
+ "loss": 0.9312,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.43,
1394
+ "grad_norm": 0.09716796875,
1395
+ "learning_rate": 0.0001254838993020793,
1396
+ "loss": 0.9214,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.43,
1401
+ "grad_norm": 0.10009765625,
1402
+ "learning_rate": 0.00012480060289010679,
1403
+ "loss": 0.8237,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.43,
1408
+ "grad_norm": 0.11279296875,
1409
+ "learning_rate": 0.00012411607041641062,
1410
+ "loss": 0.9152,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.44,
1415
+ "grad_norm": 0.1123046875,
1416
+ "learning_rate": 0.00012343033599808044,
1417
+ "loss": 0.9036,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.44,
1422
+ "grad_norm": 0.1416015625,
1423
+ "learning_rate": 0.00012274343381211066,
1424
+ "loss": 0.901,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.44,
1429
+ "grad_norm": 0.11962890625,
1430
+ "learning_rate": 0.00012205539809369719,
1431
+ "loss": 0.7381,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.44,
1436
+ "grad_norm": 0.111328125,
1437
+ "learning_rate": 0.00012136626313453134,
1438
+ "loss": 0.9358,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.45,
1443
+ "grad_norm": 0.11962890625,
1444
+ "learning_rate": 0.00012067606328109038,
1445
+ "loss": 0.8706,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.45,
1450
+ "grad_norm": 0.11572265625,
1451
+ "learning_rate": 0.00011998483293292602,
1452
+ "loss": 0.9957,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.45,
1457
+ "grad_norm": 0.10498046875,
1458
+ "learning_rate": 0.00011929260654094969,
1459
+ "loss": 0.8489,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.45,
1464
+ "grad_norm": 0.1279296875,
1465
+ "learning_rate": 0.0001185994186057158,
1466
+ "loss": 0.8718,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.45,
1471
+ "grad_norm": 0.09912109375,
1472
+ "learning_rate": 0.00011790530367570194,
1473
+ "loss": 0.8182,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.46,
1478
+ "grad_norm": 0.10498046875,
1479
+ "learning_rate": 0.00011721029634558709,
1480
+ "loss": 0.8512,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.46,
1485
+ "grad_norm": 0.150390625,
1486
+ "learning_rate": 0.00011651443125452759,
1487
+ "loss": 0.9216,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.46,
1492
+ "grad_norm": 0.1318359375,
1493
+ "learning_rate": 0.0001158177430844304,
1494
+ "loss": 0.7999,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.46,
1499
+ "grad_norm": 0.103515625,
1500
+ "learning_rate": 0.00011512026655822483,
1501
+ "loss": 0.7343,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.47,
1506
+ "grad_norm": 0.1005859375,
1507
+ "learning_rate": 0.00011442203643813183,
1508
+ "loss": 0.861,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.47,
1513
+ "grad_norm": 0.1220703125,
1514
+ "learning_rate": 0.00011372308752393144,
1515
+ "loss": 0.8731,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.47,
1520
+ "grad_norm": 0.1298828125,
1521
+ "learning_rate": 0.00011302345465122839,
1522
+ "loss": 0.9257,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.47,
1527
+ "grad_norm": 0.10791015625,
1528
+ "learning_rate": 0.00011232317268971585,
1529
+ "loss": 1.0089,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.47,
1534
+ "grad_norm": 0.1220703125,
1535
+ "learning_rate": 0.00011162227654143778,
1536
+ "loss": 0.877,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.48,
1541
+ "grad_norm": 0.0927734375,
1542
+ "learning_rate": 0.00011092080113904886,
1543
+ "loss": 0.8373,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.48,
1548
+ "grad_norm": 0.10693359375,
1549
+ "learning_rate": 0.00011021878144407408,
1550
+ "loss": 0.8474,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.48,
1555
+ "grad_norm": 0.1025390625,
1556
+ "learning_rate": 0.00010951625244516583,
1557
+ "loss": 0.788,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.48,
1562
+ "grad_norm": 0.1142578125,
1563
+ "learning_rate": 0.00010881324915636019,
1564
+ "loss": 0.8093,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.49,
1569
+ "grad_norm": 0.10986328125,
1570
+ "learning_rate": 0.0001081098066153319,
1571
+ "loss": 0.9342,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.49,
1576
+ "grad_norm": 0.10986328125,
1577
+ "learning_rate": 0.00010740595988164801,
1578
+ "loss": 0.836,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.49,
1583
+ "grad_norm": 0.09423828125,
1584
+ "learning_rate": 0.00010670174403502052,
1585
+ "loss": 0.8206,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.49,
1590
+ "grad_norm": 0.0986328125,
1591
+ "learning_rate": 0.000105997194173558,
1592
+ "loss": 0.8645,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.49,
1597
+ "grad_norm": 0.10107421875,
1598
+ "learning_rate": 0.00010529234541201631,
1599
+ "loss": 0.8027,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.5,
1604
+ "grad_norm": 0.11181640625,
1605
+ "learning_rate": 0.00010458723288004857,
1606
+ "loss": 0.8333,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.5,
1611
+ "grad_norm": 0.10400390625,
1612
+ "learning_rate": 0.00010388189172045406,
1613
+ "loss": 0.8999,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.5,
1618
+ "grad_norm": 0.1142578125,
1619
+ "learning_rate": 0.00010317635708742699,
1620
+ "loss": 0.8961,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.5,
1625
+ "eval_loss": 0.8713043332099915,
1626
+ "eval_runtime": 415.0516,
1627
+ "eval_samples_per_second": 7.074,
1628
+ "eval_steps_per_second": 3.537,
1629
+ "step": 228
1630
+ },
1631
+ {
1632
+ "epoch": 0.5,
1633
+ "grad_norm": 0.103515625,
1634
+ "learning_rate": 0.00010247066414480424,
1635
+ "loss": 0.8739,
1636
+ "step": 229
1637
+ },
1638
+ {
1639
+ "epoch": 0.51,
1640
+ "grad_norm": 0.134765625,
1641
+ "learning_rate": 0.00010176484806431288,
1642
+ "loss": 0.8045,
1643
+ "step": 230
1644
+ },
1645
+ {
1646
+ "epoch": 0.51,
1647
+ "grad_norm": 0.103515625,
1648
+ "learning_rate": 0.00010105894402381704,
1649
+ "loss": 0.9281,
1650
+ "step": 231
1651
+ },
1652
+ {
1653
+ "epoch": 0.51,
1654
+ "grad_norm": 0.1025390625,
1655
+ "learning_rate": 0.00010035298720556493,
1656
+ "loss": 0.8426,
1657
+ "step": 232
1658
+ },
1659
+ {
1660
+ "epoch": 0.51,
1661
+ "grad_norm": 0.11669921875,
1662
+ "learning_rate": 9.964701279443508e-05,
1663
+ "loss": 0.7591,
1664
+ "step": 233
1665
+ },
1666
+ {
1667
+ "epoch": 0.51,
1668
+ "grad_norm": 0.11328125,
1669
+ "learning_rate": 9.894105597618296e-05,
1670
+ "loss": 0.8066,
1671
+ "step": 234
1672
+ },
1673
+ {
1674
+ "epoch": 0.52,
1675
+ "grad_norm": 0.1064453125,
1676
+ "learning_rate": 9.823515193568715e-05,
1677
+ "loss": 0.8372,
1678
+ "step": 235
1679
+ },
1680
+ {
1681
+ "epoch": 0.52,
1682
+ "grad_norm": 0.1015625,
1683
+ "learning_rate": 9.752933585519577e-05,
1684
+ "loss": 0.81,
1685
+ "step": 236
1686
+ },
1687
+ {
1688
+ "epoch": 0.52,
1689
+ "grad_norm": 0.10986328125,
1690
+ "learning_rate": 9.682364291257304e-05,
1691
+ "loss": 1.0054,
1692
+ "step": 237
1693
+ },
1694
+ {
1695
+ "epoch": 0.52,
1696
+ "grad_norm": 0.09814453125,
1697
+ "learning_rate": 9.611810827954599e-05,
1698
+ "loss": 0.8229,
1699
+ "step": 238
1700
+ },
1701
+ {
1702
+ "epoch": 0.52,
1703
+ "grad_norm": 0.19140625,
1704
+ "learning_rate": 9.541276711995148e-05,
1705
+ "loss": 0.7994,
1706
+ "step": 239
1707
+ },
1708
+ {
1709
+ "epoch": 0.53,
1710
+ "grad_norm": 0.1279296875,
1711
+ "learning_rate": 9.470765458798368e-05,
1712
+ "loss": 0.8103,
1713
+ "step": 240
1714
+ },
1715
+ {
1716
+ "epoch": 0.53,
1717
+ "grad_norm": 0.1171875,
1718
+ "learning_rate": 9.400280582644203e-05,
1719
+ "loss": 0.7667,
1720
+ "step": 241
1721
+ },
1722
+ {
1723
+ "epoch": 0.53,
1724
+ "grad_norm": 0.0966796875,
1725
+ "learning_rate": 9.329825596497949e-05,
1726
+ "loss": 0.9226,
1727
+ "step": 242
1728
+ },
1729
+ {
1730
+ "epoch": 0.53,
1731
+ "grad_norm": 0.11279296875,
1732
+ "learning_rate": 9.259404011835201e-05,
1733
+ "loss": 0.751,
1734
+ "step": 243
1735
+ },
1736
+ {
1737
+ "epoch": 0.54,
1738
+ "grad_norm": 0.10498046875,
1739
+ "learning_rate": 9.189019338466812e-05,
1740
+ "loss": 0.978,
1741
+ "step": 244
1742
+ },
1743
+ {
1744
+ "epoch": 0.54,
1745
+ "grad_norm": 0.0986328125,
1746
+ "learning_rate": 9.118675084363986e-05,
1747
+ "loss": 0.8746,
1748
+ "step": 245
1749
+ },
1750
+ {
1751
+ "epoch": 0.54,
1752
+ "grad_norm": 0.1318359375,
1753
+ "learning_rate": 9.048374755483419e-05,
1754
+ "loss": 0.8223,
1755
+ "step": 246
1756
+ },
1757
+ {
1758
+ "epoch": 0.54,
1759
+ "grad_norm": 0.16015625,
1760
+ "learning_rate": 8.978121855592593e-05,
1761
+ "loss": 0.9778,
1762
+ "step": 247
1763
+ },
1764
+ {
1765
+ "epoch": 0.54,
1766
+ "grad_norm": 0.134765625,
1767
+ "learning_rate": 8.907919886095115e-05,
1768
+ "loss": 0.8693,
1769
+ "step": 248
1770
+ },
1771
+ {
1772
+ "epoch": 0.55,
1773
+ "grad_norm": 0.1201171875,
1774
+ "learning_rate": 8.837772345856226e-05,
1775
+ "loss": 0.7726,
1776
+ "step": 249
1777
+ },
1778
+ {
1779
+ "epoch": 0.55,
1780
+ "grad_norm": 0.1494140625,
1781
+ "learning_rate": 8.767682731028415e-05,
1782
+ "loss": 0.7388,
1783
+ "step": 250
1784
+ },
1785
+ {
1786
+ "epoch": 0.55,
1787
+ "grad_norm": 0.1337890625,
1788
+ "learning_rate": 8.697654534877165e-05,
1789
+ "loss": 0.8422,
1790
+ "step": 251
1791
+ },
1792
+ {
1793
+ "epoch": 0.55,
1794
+ "grad_norm": 0.11572265625,
1795
+ "learning_rate": 8.627691247606862e-05,
1796
+ "loss": 0.8306,
1797
+ "step": 252
1798
+ },
1799
+ {
1800
+ "epoch": 0.56,
1801
+ "grad_norm": 0.08984375,
1802
+ "learning_rate": 8.557796356186818e-05,
1803
+ "loss": 0.7276,
1804
+ "step": 253
1805
+ },
1806
+ {
1807
+ "epoch": 0.56,
1808
+ "grad_norm": 0.1337890625,
1809
+ "learning_rate": 8.487973344177517e-05,
1810
+ "loss": 0.8244,
1811
+ "step": 254
1812
+ },
1813
+ {
1814
+ "epoch": 0.56,
1815
+ "grad_norm": 0.10693359375,
1816
+ "learning_rate": 8.418225691556962e-05,
1817
+ "loss": 0.7665,
1818
+ "step": 255
1819
+ },
1820
+ {
1821
+ "epoch": 0.56,
1822
+ "grad_norm": 0.09765625,
1823
+ "learning_rate": 8.348556874547242e-05,
1824
+ "loss": 0.8114,
1825
+ "step": 256
1826
+ },
1827
+ {
1828
+ "epoch": 0.56,
1829
+ "grad_norm": 0.1318359375,
1830
+ "learning_rate": 8.278970365441292e-05,
1831
+ "loss": 0.7918,
1832
+ "step": 257
1833
+ },
1834
+ {
1835
+ "epoch": 0.57,
1836
+ "grad_norm": 0.11669921875,
1837
+ "learning_rate": 8.20946963242981e-05,
1838
+ "loss": 0.8266,
1839
+ "step": 258
1840
+ },
1841
+ {
1842
+ "epoch": 0.57,
1843
+ "grad_norm": 0.11083984375,
1844
+ "learning_rate": 8.140058139428425e-05,
1845
+ "loss": 0.7967,
1846
+ "step": 259
1847
+ },
1848
+ {
1849
+ "epoch": 0.57,
1850
+ "grad_norm": 0.09912109375,
1851
+ "learning_rate": 8.070739345905032e-05,
1852
+ "loss": 0.9177,
1853
+ "step": 260
1854
+ },
1855
+ {
1856
+ "epoch": 0.57,
1857
+ "grad_norm": 0.11474609375,
1858
+ "learning_rate": 8.001516706707401e-05,
1859
+ "loss": 0.9526,
1860
+ "step": 261
1861
+ },
1862
+ {
1863
+ "epoch": 0.58,
1864
+ "grad_norm": 0.11083984375,
1865
+ "learning_rate": 7.932393671890965e-05,
1866
+ "loss": 0.9914,
1867
+ "step": 262
1868
+ },
1869
+ {
1870
+ "epoch": 0.58,
1871
+ "grad_norm": 0.10205078125,
1872
+ "learning_rate": 7.863373686546867e-05,
1873
+ "loss": 0.8242,
1874
+ "step": 263
1875
+ },
1876
+ {
1877
+ "epoch": 0.58,
1878
+ "grad_norm": 0.09716796875,
1879
+ "learning_rate": 7.794460190630282e-05,
1880
+ "loss": 0.6837,
1881
+ "step": 264
1882
+ },
1883
+ {
1884
+ "epoch": 0.58,
1885
+ "grad_norm": 0.11328125,
1886
+ "learning_rate": 7.725656618788937e-05,
1887
+ "loss": 0.8758,
1888
+ "step": 265
1889
+ },
1890
+ {
1891
+ "epoch": 0.58,
1892
+ "grad_norm": 0.11181640625,
1893
+ "learning_rate": 7.656966400191956e-05,
1894
+ "loss": 0.8655,
1895
+ "step": 266
1896
+ },
1897
+ {
1898
+ "epoch": 0.59,
1899
+ "grad_norm": 0.11328125,
1900
+ "learning_rate": 7.58839295835894e-05,
1901
+ "loss": 1.0563,
1902
+ "step": 267
1903
+ },
1904
+ {
1905
+ "epoch": 0.59,
1906
+ "grad_norm": 0.11962890625,
1907
+ "learning_rate": 7.519939710989325e-05,
1908
+ "loss": 0.832,
1909
+ "step": 268
1910
+ },
1911
+ {
1912
+ "epoch": 0.59,
1913
+ "grad_norm": 0.1142578125,
1914
+ "learning_rate": 7.45161006979207e-05,
1915
+ "loss": 0.8198,
1916
+ "step": 269
1917
+ },
1918
+ {
1919
+ "epoch": 0.59,
1920
+ "grad_norm": 0.1103515625,
1921
+ "learning_rate": 7.383407440315596e-05,
1922
+ "loss": 0.8246,
1923
+ "step": 270
1924
+ },
1925
+ {
1926
+ "epoch": 0.6,
1927
+ "grad_norm": 0.10498046875,
1928
+ "learning_rate": 7.315335221778064e-05,
1929
+ "loss": 0.8314,
1930
+ "step": 271
1931
+ },
1932
+ {
1933
+ "epoch": 0.6,
1934
+ "grad_norm": 0.1240234375,
1935
+ "learning_rate": 7.247396806897952e-05,
1936
+ "loss": 0.7107,
1937
+ "step": 272
1938
+ },
1939
+ {
1940
+ "epoch": 0.6,
1941
+ "grad_norm": 0.10498046875,
1942
+ "learning_rate": 7.17959558172497e-05,
1943
+ "loss": 0.8982,
1944
+ "step": 273
1945
+ },
1946
+ {
1947
+ "epoch": 0.6,
1948
+ "grad_norm": 0.1103515625,
1949
+ "learning_rate": 7.111934925471302e-05,
1950
+ "loss": 0.9427,
1951
+ "step": 274
1952
+ },
1953
+ {
1954
+ "epoch": 0.6,
1955
+ "grad_norm": 0.1279296875,
1956
+ "learning_rate": 7.04441821034316e-05,
1957
+ "loss": 0.8454,
1958
+ "step": 275
1959
+ },
1960
+ {
1961
+ "epoch": 0.61,
1962
+ "grad_norm": 0.115234375,
1963
+ "learning_rate": 6.97704880137275e-05,
1964
+ "loss": 0.8044,
1965
+ "step": 276
1966
+ },
1967
+ {
1968
+ "epoch": 0.61,
1969
+ "grad_norm": 0.12451171875,
1970
+ "learning_rate": 6.909830056250527e-05,
1971
+ "loss": 0.8196,
1972
+ "step": 277
1973
+ },
1974
+ {
1975
+ "epoch": 0.61,
1976
+ "grad_norm": 0.13671875,
1977
+ "learning_rate": 6.842765325157874e-05,
1978
+ "loss": 0.8221,
1979
+ "step": 278
1980
+ },
1981
+ {
1982
+ "epoch": 0.61,
1983
+ "grad_norm": 0.119140625,
1984
+ "learning_rate": 6.775857950600106e-05,
1985
+ "loss": 0.8273,
1986
+ "step": 279
1987
+ },
1988
+ {
1989
+ "epoch": 0.62,
1990
+ "grad_norm": 0.0966796875,
1991
+ "learning_rate": 6.7091112672399e-05,
1992
+ "loss": 0.9296,
1993
+ "step": 280
1994
+ },
1995
+ {
1996
+ "epoch": 0.62,
1997
+ "grad_norm": 0.103515625,
1998
+ "learning_rate": 6.642528601731082e-05,
1999
+ "loss": 0.8635,
2000
+ "step": 281
2001
+ },
2002
+ {
2003
+ "epoch": 0.62,
2004
+ "grad_norm": 0.10693359375,
2005
+ "learning_rate": 6.576113272552826e-05,
2006
+ "loss": 0.8622,
2007
+ "step": 282
2008
+ },
2009
+ {
2010
+ "epoch": 0.62,
2011
+ "grad_norm": 0.10693359375,
2012
+ "learning_rate": 6.509868589844273e-05,
2013
+ "loss": 0.8982,
2014
+ "step": 283
2015
+ },
2016
+ {
2017
+ "epoch": 0.62,
2018
+ "grad_norm": 0.1220703125,
2019
+ "learning_rate": 6.44379785523954e-05,
2020
+ "loss": 0.8564,
2021
+ "step": 284
2022
+ },
2023
+ {
2024
+ "epoch": 0.63,
2025
+ "grad_norm": 0.1923828125,
2026
+ "learning_rate": 6.377904361703178e-05,
2027
+ "loss": 0.7286,
2028
+ "step": 285
2029
+ },
2030
+ {
2031
+ "epoch": 0.63,
2032
+ "grad_norm": 0.1005859375,
2033
+ "learning_rate": 6.312191393366035e-05,
2034
+ "loss": 1.0057,
2035
+ "step": 286
2036
+ },
2037
+ {
2038
+ "epoch": 0.63,
2039
+ "grad_norm": 0.12158203125,
2040
+ "learning_rate": 6.246662225361602e-05,
2041
+ "loss": 0.7258,
2042
+ "step": 287
2043
+ },
2044
+ {
2045
+ "epoch": 0.63,
2046
+ "grad_norm": 0.099609375,
2047
+ "learning_rate": 6.181320123662755e-05,
2048
+ "loss": 0.8115,
2049
+ "step": 288
2050
+ },
2051
+ {
2052
+ "epoch": 0.63,
2053
+ "grad_norm": 0.1298828125,
2054
+ "learning_rate": 6.116168344918983e-05,
2055
+ "loss": 0.7434,
2056
+ "step": 289
2057
+ },
2058
+ {
2059
+ "epoch": 0.64,
2060
+ "grad_norm": 0.10009765625,
2061
+ "learning_rate": 6.051210136294089e-05,
2062
+ "loss": 0.875,
2063
+ "step": 290
2064
+ },
2065
+ {
2066
+ "epoch": 0.64,
2067
+ "grad_norm": 0.10791015625,
2068
+ "learning_rate": 5.986448735304339e-05,
2069
+ "loss": 0.9115,
2070
+ "step": 291
2071
+ },
2072
+ {
2073
+ "epoch": 0.64,
2074
+ "grad_norm": 0.1064453125,
2075
+ "learning_rate": 5.921887369657113e-05,
2076
+ "loss": 0.8492,
2077
+ "step": 292
2078
+ },
2079
+ {
2080
+ "epoch": 0.64,
2081
+ "grad_norm": 0.126953125,
2082
+ "learning_rate": 5.857529257090027e-05,
2083
+ "loss": 0.7701,
2084
+ "step": 293
2085
+ },
2086
+ {
2087
+ "epoch": 0.65,
2088
+ "grad_norm": 0.11083984375,
2089
+ "learning_rate": 5.7933776052105745e-05,
2090
+ "loss": 0.9333,
2091
+ "step": 294
2092
+ },
2093
+ {
2094
+ "epoch": 0.65,
2095
+ "grad_norm": 0.1279296875,
2096
+ "learning_rate": 5.729435611336239e-05,
2097
+ "loss": 0.7718,
2098
+ "step": 295
2099
+ },
2100
+ {
2101
+ "epoch": 0.65,
2102
+ "grad_norm": 0.123046875,
2103
+ "learning_rate": 5.6657064623351676e-05,
2104
+ "loss": 0.8522,
2105
+ "step": 296
2106
+ },
2107
+ {
2108
+ "epoch": 0.65,
2109
+ "grad_norm": 0.1982421875,
2110
+ "learning_rate": 5.602193334467307e-05,
2111
+ "loss": 0.7019,
2112
+ "step": 297
2113
+ },
2114
+ {
2115
+ "epoch": 0.65,
2116
+ "grad_norm": 0.11865234375,
2117
+ "learning_rate": 5.5388993932261215e-05,
2118
+ "loss": 0.8389,
2119
+ "step": 298
2120
+ },
2121
+ {
2122
+ "epoch": 0.66,
2123
+ "grad_norm": 0.1259765625,
2124
+ "learning_rate": 5.4758277931808075e-05,
2125
+ "loss": 0.863,
2126
+ "step": 299
2127
+ },
2128
+ {
2129
+ "epoch": 0.66,
2130
+ "grad_norm": 0.115234375,
2131
+ "learning_rate": 5.4129816778190936e-05,
2132
+ "loss": 0.7688,
2133
+ "step": 300
2134
+ },
2135
+ {
2136
+ "epoch": 0.66,
2137
+ "grad_norm": 0.11328125,
2138
+ "learning_rate": 5.350364179390548e-05,
2139
+ "loss": 0.8084,
2140
+ "step": 301
2141
+ },
2142
+ {
2143
+ "epoch": 0.66,
2144
+ "grad_norm": 0.1005859375,
2145
+ "learning_rate": 5.28797841875047e-05,
2146
+ "loss": 0.9221,
2147
+ "step": 302
2148
+ },
2149
+ {
2150
+ "epoch": 0.67,
2151
+ "grad_norm": 0.12255859375,
2152
+ "learning_rate": 5.2258275052043546e-05,
2153
+ "loss": 0.8468,
2154
+ "step": 303
2155
+ },
2156
+ {
2157
+ "epoch": 0.67,
2158
+ "grad_norm": 0.1181640625,
2159
+ "learning_rate": 5.163914536352918e-05,
2160
+ "loss": 0.918,
2161
+ "step": 304
2162
+ },
2163
+ {
2164
+ "epoch": 0.67,
2165
+ "grad_norm": 0.11572265625,
2166
+ "learning_rate": 5.102242597937717e-05,
2167
+ "loss": 0.8958,
2168
+ "step": 305
2169
+ },
2170
+ {
2171
+ "epoch": 0.67,
2172
+ "grad_norm": 0.126953125,
2173
+ "learning_rate": 5.040814763687358e-05,
2174
+ "loss": 0.8718,
2175
+ "step": 306
2176
+ },
2177
+ {
2178
+ "epoch": 0.67,
2179
+ "grad_norm": 0.11376953125,
2180
+ "learning_rate": 4.9796340951642986e-05,
2181
+ "loss": 0.8603,
2182
+ "step": 307
2183
+ },
2184
+ {
2185
+ "epoch": 0.68,
2186
+ "grad_norm": 0.11669921875,
2187
+ "learning_rate": 4.918703641612255e-05,
2188
+ "loss": 0.8245,
2189
+ "step": 308
2190
+ },
2191
+ {
2192
+ "epoch": 0.68,
2193
+ "grad_norm": 0.12890625,
2194
+ "learning_rate": 4.858026439804235e-05,
2195
+ "loss": 0.8881,
2196
+ "step": 309
2197
+ },
2198
+ {
2199
+ "epoch": 0.68,
2200
+ "grad_norm": 0.10791015625,
2201
+ "learning_rate": 4.797605513891179e-05,
2202
+ "loss": 0.921,
2203
+ "step": 310
2204
+ },
2205
+ {
2206
+ "epoch": 0.68,
2207
+ "grad_norm": 0.232421875,
2208
+ "learning_rate": 4.737443875251251e-05,
2209
+ "loss": 0.8585,
2210
+ "step": 311
2211
+ },
2212
+ {
2213
+ "epoch": 0.69,
2214
+ "grad_norm": 0.11474609375,
2215
+ "learning_rate": 4.6775445223397306e-05,
2216
+ "loss": 0.8024,
2217
+ "step": 312
2218
+ },
2219
+ {
2220
+ "epoch": 0.69,
2221
+ "grad_norm": 0.1767578125,
2222
+ "learning_rate": 4.61791044053958e-05,
2223
+ "loss": 0.7499,
2224
+ "step": 313
2225
+ },
2226
+ {
2227
+ "epoch": 0.69,
2228
+ "grad_norm": 0.130859375,
2229
+ "learning_rate": 4.558544602012663e-05,
2230
+ "loss": 0.8993,
2231
+ "step": 314
2232
+ },
2233
+ {
2234
+ "epoch": 0.69,
2235
+ "grad_norm": 0.115234375,
2236
+ "learning_rate": 4.4994499655515865e-05,
2237
+ "loss": 0.8938,
2238
+ "step": 315
2239
+ },
2240
+ {
2241
+ "epoch": 0.69,
2242
+ "grad_norm": 0.11083984375,
2243
+ "learning_rate": 4.440629476432267e-05,
2244
+ "loss": 0.8357,
2245
+ "step": 316
2246
+ },
2247
+ {
2248
+ "epoch": 0.7,
2249
+ "grad_norm": 0.1328125,
2250
+ "learning_rate": 4.3820860662671107e-05,
2251
+ "loss": 0.719,
2252
+ "step": 317
2253
+ },
2254
+ {
2255
+ "epoch": 0.7,
2256
+ "grad_norm": 0.1015625,
2257
+ "learning_rate": 4.323822652858911e-05,
2258
+ "loss": 0.8492,
2259
+ "step": 318
2260
+ },
2261
+ {
2262
+ "epoch": 0.7,
2263
+ "grad_norm": 0.126953125,
2264
+ "learning_rate": 4.265842140055428e-05,
2265
+ "loss": 0.7805,
2266
+ "step": 319
2267
+ },
2268
+ {
2269
+ "epoch": 0.7,
2270
+ "grad_norm": 0.11376953125,
2271
+ "learning_rate": 4.2081474176046646e-05,
2272
+ "loss": 0.814,
2273
+ "step": 320
2274
+ },
2275
+ {
2276
+ "epoch": 0.71,
2277
+ "grad_norm": 0.1103515625,
2278
+ "learning_rate": 4.150741361010837e-05,
2279
+ "loss": 0.8448,
2280
+ "step": 321
2281
+ },
2282
+ {
2283
+ "epoch": 0.71,
2284
+ "grad_norm": 0.1142578125,
2285
+ "learning_rate": 4.093626831391051e-05,
2286
+ "loss": 0.8212,
2287
+ "step": 322
2288
+ },
2289
+ {
2290
+ "epoch": 0.71,
2291
+ "grad_norm": 0.1435546875,
2292
+ "learning_rate": 4.036806675332715e-05,
2293
+ "loss": 0.8006,
2294
+ "step": 323
2295
+ },
2296
+ {
2297
+ "epoch": 0.71,
2298
+ "grad_norm": 0.111328125,
2299
+ "learning_rate": 3.98028372475166e-05,
2300
+ "loss": 0.8723,
2301
+ "step": 324
2302
+ },
2303
+ {
2304
+ "epoch": 0.71,
2305
+ "grad_norm": 0.130859375,
2306
+ "learning_rate": 3.924060796751012e-05,
2307
+ "loss": 0.7984,
2308
+ "step": 325
2309
+ },
2310
+ {
2311
+ "epoch": 0.72,
2312
+ "grad_norm": 0.10302734375,
2313
+ "learning_rate": 3.8681406934807585e-05,
2314
+ "loss": 0.8581,
2315
+ "step": 326
2316
+ },
2317
+ {
2318
+ "epoch": 0.72,
2319
+ "grad_norm": 0.12060546875,
2320
+ "learning_rate": 3.8125262019981224e-05,
2321
+ "loss": 0.8222,
2322
+ "step": 327
2323
+ },
2324
+ {
2325
+ "epoch": 0.72,
2326
+ "grad_norm": 0.12255859375,
2327
+ "learning_rate": 3.757220094128629e-05,
2328
+ "loss": 0.8624,
2329
+ "step": 328
2330
+ },
2331
+ {
2332
+ "epoch": 0.72,
2333
+ "grad_norm": 0.12353515625,
2334
+ "learning_rate": 3.702225126327965e-05,
2335
+ "loss": 0.7377,
2336
+ "step": 329
2337
+ },
2338
+ {
2339
+ "epoch": 0.72,
2340
+ "grad_norm": 0.1044921875,
2341
+ "learning_rate": 3.647544039544615e-05,
2342
+ "loss": 0.8021,
2343
+ "step": 330
2344
+ },
2345
+ {
2346
+ "epoch": 0.73,
2347
+ "grad_norm": 0.125,
2348
+ "learning_rate": 3.5931795590832254e-05,
2349
+ "loss": 0.8053,
2350
+ "step": 331
2351
+ },
2352
+ {
2353
+ "epoch": 0.73,
2354
+ "grad_norm": 0.10546875,
2355
+ "learning_rate": 3.53913439446879e-05,
2356
+ "loss": 1.0031,
2357
+ "step": 332
2358
+ },
2359
+ {
2360
+ "epoch": 0.73,
2361
+ "grad_norm": 0.173828125,
2362
+ "learning_rate": 3.485411239311604e-05,
2363
+ "loss": 0.773,
2364
+ "step": 333
2365
+ },
2366
+ {
2367
+ "epoch": 0.73,
2368
+ "grad_norm": 0.138671875,
2369
+ "learning_rate": 3.432012771173021e-05,
2370
+ "loss": 0.785,
2371
+ "step": 334
2372
+ },
2373
+ {
2374
+ "epoch": 0.74,
2375
+ "grad_norm": 0.0986328125,
2376
+ "learning_rate": 3.378941651431996e-05,
2377
+ "loss": 0.7751,
2378
+ "step": 335
2379
+ },
2380
+ {
2381
+ "epoch": 0.74,
2382
+ "grad_norm": 0.10595703125,
2383
+ "learning_rate": 3.326200525152441e-05,
2384
+ "loss": 0.7843,
2385
+ "step": 336
2386
+ },
2387
+ {
2388
+ "epoch": 0.74,
2389
+ "grad_norm": 0.10302734375,
2390
+ "learning_rate": 3.2737920209514e-05,
2391
+ "loss": 0.8728,
2392
+ "step": 337
2393
+ },
2394
+ {
2395
+ "epoch": 0.74,
2396
+ "grad_norm": 0.1279296875,
2397
+ "learning_rate": 3.2217187508680315e-05,
2398
+ "loss": 0.7532,
2399
+ "step": 338
2400
+ },
2401
+ {
2402
+ "epoch": 0.74,
2403
+ "grad_norm": 0.1328125,
2404
+ "learning_rate": 3.1699833102334395e-05,
2405
+ "loss": 0.8074,
2406
+ "step": 339
2407
+ },
2408
+ {
2409
+ "epoch": 0.75,
2410
+ "grad_norm": 0.0927734375,
2411
+ "learning_rate": 3.118588277541312e-05,
2412
+ "loss": 1.0021,
2413
+ "step": 340
2414
+ },
2415
+ {
2416
+ "epoch": 0.75,
2417
+ "grad_norm": 0.1044921875,
2418
+ "learning_rate": 3.067536214319402e-05,
2419
+ "loss": 0.8352,
2420
+ "step": 341
2421
+ },
2422
+ {
2423
+ "epoch": 0.75,
2424
+ "grad_norm": 0.11767578125,
2425
+ "learning_rate": 3.0168296650018735e-05,
2426
+ "loss": 0.824,
2427
+ "step": 342
2428
+ },
2429
+ {
2430
+ "epoch": 0.75,
2431
+ "eval_loss": 0.8436947464942932,
2432
+ "eval_runtime": 422.1114,
2433
+ "eval_samples_per_second": 6.956,
2434
+ "eval_steps_per_second": 3.478,
2435
+ "step": 342
2436
+ },
2437
+ {
2438
+ "epoch": 0.75,
2439
+ "grad_norm": 0.138671875,
2440
+ "learning_rate": 2.966471156802477e-05,
2441
+ "loss": 0.9148,
2442
+ "step": 343
2443
+ },
2444
+ {
2445
+ "epoch": 0.76,
2446
+ "grad_norm": 0.12353515625,
2447
+ "learning_rate": 2.9164631995886093e-05,
2448
+ "loss": 0.9928,
2449
+ "step": 344
2450
+ },
2451
+ {
2452
+ "epoch": 0.76,
2453
+ "grad_norm": 0.1162109375,
2454
+ "learning_rate": 2.8668082857562005e-05,
2455
+ "loss": 0.8124,
2456
+ "step": 345
2457
+ },
2458
+ {
2459
+ "epoch": 0.76,
2460
+ "grad_norm": 0.10107421875,
2461
+ "learning_rate": 2.8175088901055026e-05,
2462
+ "loss": 0.8412,
2463
+ "step": 346
2464
+ },
2465
+ {
2466
+ "epoch": 0.76,
2467
+ "grad_norm": 0.10986328125,
2468
+ "learning_rate": 2.7685674697177566e-05,
2469
+ "loss": 0.7348,
2470
+ "step": 347
2471
+ },
2472
+ {
2473
+ "epoch": 0.76,
2474
+ "grad_norm": 0.103515625,
2475
+ "learning_rate": 2.7199864638327077e-05,
2476
+ "loss": 0.7976,
2477
+ "step": 348
2478
+ },
2479
+ {
2480
+ "epoch": 0.77,
2481
+ "grad_norm": 0.126953125,
2482
+ "learning_rate": 2.6717682937270604e-05,
2483
+ "loss": 0.7628,
2484
+ "step": 349
2485
+ },
2486
+ {
2487
+ "epoch": 0.77,
2488
+ "grad_norm": 0.10693359375,
2489
+ "learning_rate": 2.6239153625937784e-05,
2490
+ "loss": 0.8783,
2491
+ "step": 350
2492
+ },
2493
+ {
2494
+ "epoch": 0.77,
2495
+ "grad_norm": 0.1337890625,
2496
+ "learning_rate": 2.5764300554223242e-05,
2497
+ "loss": 0.6852,
2498
+ "step": 351
2499
+ },
2500
+ {
2501
+ "epoch": 0.77,
2502
+ "grad_norm": 0.1181640625,
2503
+ "learning_rate": 2.529314738879781e-05,
2504
+ "loss": 0.8181,
2505
+ "step": 352
2506
+ },
2507
+ {
2508
+ "epoch": 0.78,
2509
+ "grad_norm": 0.10693359375,
2510
+ "learning_rate": 2.4825717611929146e-05,
2511
+ "loss": 0.8616,
2512
+ "step": 353
2513
+ },
2514
+ {
2515
+ "epoch": 0.78,
2516
+ "grad_norm": 0.119140625,
2517
+ "learning_rate": 2.4362034520311216e-05,
2518
+ "loss": 0.8029,
2519
+ "step": 354
2520
+ },
2521
+ {
2522
+ "epoch": 0.78,
2523
+ "grad_norm": 0.126953125,
2524
+ "learning_rate": 2.390212122390323e-05,
2525
+ "loss": 0.8134,
2526
+ "step": 355
2527
+ },
2528
+ {
2529
+ "epoch": 0.78,
2530
+ "grad_norm": 0.1298828125,
2531
+ "learning_rate": 2.3446000644777853e-05,
2532
+ "loss": 0.7766,
2533
+ "step": 356
2534
+ },
2535
+ {
2536
+ "epoch": 0.78,
2537
+ "grad_norm": 0.107421875,
2538
+ "learning_rate": 2.2993695515978762e-05,
2539
+ "loss": 0.8786,
2540
+ "step": 357
2541
+ },
2542
+ {
2543
+ "epoch": 0.79,
2544
+ "grad_norm": 0.1181640625,
2545
+ "learning_rate": 2.2545228380387706e-05,
2546
+ "loss": 0.8264,
2547
+ "step": 358
2548
+ },
2549
+ {
2550
+ "epoch": 0.79,
2551
+ "grad_norm": 0.10986328125,
2552
+ "learning_rate": 2.210062158960081e-05,
2553
+ "loss": 0.8366,
2554
+ "step": 359
2555
+ },
2556
+ {
2557
+ "epoch": 0.79,
2558
+ "grad_norm": 0.1025390625,
2559
+ "learning_rate": 2.1659897302814747e-05,
2560
+ "loss": 0.8282,
2561
+ "step": 360
2562
+ },
2563
+ {
2564
+ "epoch": 0.79,
2565
+ "grad_norm": 0.10009765625,
2566
+ "learning_rate": 2.1223077485722198e-05,
2567
+ "loss": 0.9779,
2568
+ "step": 361
2569
+ },
2570
+ {
2571
+ "epoch": 0.8,
2572
+ "grad_norm": 0.11181640625,
2573
+ "learning_rate": 2.0790183909417093e-05,
2574
+ "loss": 0.8431,
2575
+ "step": 362
2576
+ },
2577
+ {
2578
+ "epoch": 0.8,
2579
+ "grad_norm": 0.12451171875,
2580
+ "learning_rate": 2.036123814930967e-05,
2581
+ "loss": 0.8402,
2582
+ "step": 363
2583
+ },
2584
+ {
2585
+ "epoch": 0.8,
2586
+ "grad_norm": 0.10302734375,
2587
+ "learning_rate": 1.9936261584050973e-05,
2588
+ "loss": 0.9097,
2589
+ "step": 364
2590
+ },
2591
+ {
2592
+ "epoch": 0.8,
2593
+ "grad_norm": 0.1083984375,
2594
+ "learning_rate": 1.9515275394467446e-05,
2595
+ "loss": 0.7467,
2596
+ "step": 365
2597
+ },
2598
+ {
2599
+ "epoch": 0.8,
2600
+ "grad_norm": 0.11376953125,
2601
+ "learning_rate": 1.9098300562505266e-05,
2602
+ "loss": 0.9132,
2603
+ "step": 366
2604
+ },
2605
+ {
2606
+ "epoch": 0.81,
2607
+ "grad_norm": 0.09765625,
2608
+ "learning_rate": 1.8685357870184605e-05,
2609
+ "loss": 0.9088,
2610
+ "step": 367
2611
+ },
2612
+ {
2613
+ "epoch": 0.81,
2614
+ "grad_norm": 0.09130859375,
2615
+ "learning_rate": 1.8276467898563887e-05,
2616
+ "loss": 0.8388,
2617
+ "step": 368
2618
+ },
2619
+ {
2620
+ "epoch": 0.81,
2621
+ "grad_norm": 0.09228515625,
2622
+ "learning_rate": 1.7871651026713908e-05,
2623
+ "loss": 0.703,
2624
+ "step": 369
2625
+ },
2626
+ {
2627
+ "epoch": 0.81,
2628
+ "grad_norm": 0.1435546875,
2629
+ "learning_rate": 1.7470927430702277e-05,
2630
+ "loss": 0.8362,
2631
+ "step": 370
2632
+ },
2633
+ {
2634
+ "epoch": 0.81,
2635
+ "grad_norm": 0.09375,
2636
+ "learning_rate": 1.7074317082587755e-05,
2637
+ "loss": 0.7667,
2638
+ "step": 371
2639
+ },
2640
+ {
2641
+ "epoch": 0.82,
2642
+ "grad_norm": 0.185546875,
2643
+ "learning_rate": 1.668183974942491e-05,
2644
+ "loss": 0.8881,
2645
+ "step": 372
2646
+ },
2647
+ {
2648
+ "epoch": 0.82,
2649
+ "grad_norm": 0.12158203125,
2650
+ "learning_rate": 1.6293514992278936e-05,
2651
+ "loss": 0.8335,
2652
+ "step": 373
2653
+ },
2654
+ {
2655
+ "epoch": 0.82,
2656
+ "grad_norm": 0.12353515625,
2657
+ "learning_rate": 1.590936216525061e-05,
2658
+ "loss": 0.8181,
2659
+ "step": 374
2660
+ },
2661
+ {
2662
+ "epoch": 0.82,
2663
+ "grad_norm": 0.1015625,
2664
+ "learning_rate": 1.5529400414511806e-05,
2665
+ "loss": 0.7918,
2666
+ "step": 375
2667
+ },
2668
+ {
2669
+ "epoch": 0.83,
2670
+ "grad_norm": 0.12109375,
2671
+ "learning_rate": 1.5153648677351195e-05,
2672
+ "loss": 0.8674,
2673
+ "step": 376
2674
+ },
2675
+ {
2676
+ "epoch": 0.83,
2677
+ "grad_norm": 0.1123046875,
2678
+ "learning_rate": 1.4782125681230497e-05,
2679
+ "loss": 0.7134,
2680
+ "step": 377
2681
+ },
2682
+ {
2683
+ "epoch": 0.83,
2684
+ "grad_norm": 0.09228515625,
2685
+ "learning_rate": 1.4414849942850927e-05,
2686
+ "loss": 0.8532,
2687
+ "step": 378
2688
+ },
2689
+ {
2690
+ "epoch": 0.83,
2691
+ "grad_norm": 0.1025390625,
2692
+ "learning_rate": 1.4051839767230478e-05,
2693
+ "loss": 0.7936,
2694
+ "step": 379
2695
+ },
2696
+ {
2697
+ "epoch": 0.83,
2698
+ "grad_norm": 0.1025390625,
2699
+ "learning_rate": 1.3693113246791589e-05,
2700
+ "loss": 0.7971,
2701
+ "step": 380
2702
+ },
2703
+ {
2704
+ "epoch": 0.84,
2705
+ "grad_norm": 0.123046875,
2706
+ "learning_rate": 1.333868826045932e-05,
2707
+ "loss": 0.7371,
2708
+ "step": 381
2709
+ },
2710
+ {
2711
+ "epoch": 0.84,
2712
+ "grad_norm": 0.11962890625,
2713
+ "learning_rate": 1.2988582472770373e-05,
2714
+ "loss": 0.7324,
2715
+ "step": 382
2716
+ },
2717
+ {
2718
+ "epoch": 0.84,
2719
+ "grad_norm": 0.10888671875,
2720
+ "learning_rate": 1.2642813332992608e-05,
2721
+ "loss": 0.7527,
2722
+ "step": 383
2723
+ },
2724
+ {
2725
+ "epoch": 0.84,
2726
+ "grad_norm": 0.095703125,
2727
+ "learning_rate": 1.2301398074255443e-05,
2728
+ "loss": 0.8041,
2729
+ "step": 384
2730
+ },
2731
+ {
2732
+ "epoch": 0.85,
2733
+ "grad_norm": 0.09814453125,
2734
+ "learning_rate": 1.196435371269089e-05,
2735
+ "loss": 0.9232,
2736
+ "step": 385
2737
+ },
2738
+ {
2739
+ "epoch": 0.85,
2740
+ "grad_norm": 0.0947265625,
2741
+ "learning_rate": 1.163169704658551e-05,
2742
+ "loss": 0.875,
2743
+ "step": 386
2744
+ },
2745
+ {
2746
+ "epoch": 0.85,
2747
+ "grad_norm": 0.11181640625,
2748
+ "learning_rate": 1.1303444655543206e-05,
2749
+ "loss": 0.9133,
2750
+ "step": 387
2751
+ },
2752
+ {
2753
+ "epoch": 0.85,
2754
+ "grad_norm": 0.1064453125,
2755
+ "learning_rate": 1.0979612899658876e-05,
2756
+ "loss": 0.7921,
2757
+ "step": 388
2758
+ },
2759
+ {
2760
+ "epoch": 0.85,
2761
+ "grad_norm": 0.1064453125,
2762
+ "learning_rate": 1.0660217918702965e-05,
2763
+ "loss": 0.7747,
2764
+ "step": 389
2765
+ },
2766
+ {
2767
+ "epoch": 0.86,
2768
+ "grad_norm": 0.1171875,
2769
+ "learning_rate": 1.0345275631317163e-05,
2770
+ "loss": 0.8552,
2771
+ "step": 390
2772
+ },
2773
+ {
2774
+ "epoch": 0.86,
2775
+ "grad_norm": 0.1005859375,
2776
+ "learning_rate": 1.0034801734220922e-05,
2777
+ "loss": 0.8868,
2778
+ "step": 391
2779
+ },
2780
+ {
2781
+ "epoch": 0.86,
2782
+ "grad_norm": 0.09716796875,
2783
+ "learning_rate": 9.728811701429241e-06,
2784
+ "loss": 0.8623,
2785
+ "step": 392
2786
+ },
2787
+ {
2788
+ "epoch": 0.86,
2789
+ "grad_norm": 0.123046875,
2790
+ "learning_rate": 9.427320783481353e-06,
2791
+ "loss": 0.8697,
2792
+ "step": 393
2793
+ },
2794
+ {
2795
+ "epoch": 0.87,
2796
+ "grad_norm": 0.1279296875,
2797
+ "learning_rate": 9.130344006680657e-06,
2798
+ "loss": 0.749,
2799
+ "step": 394
2800
+ },
2801
+ {
2802
+ "epoch": 0.87,
2803
+ "grad_norm": 0.087890625,
2804
+ "learning_rate": 8.837896172345827e-06,
2805
+ "loss": 0.8668,
2806
+ "step": 395
2807
+ },
2808
+ {
2809
+ "epoch": 0.87,
2810
+ "grad_norm": 0.10009765625,
2811
+ "learning_rate": 8.549991856073069e-06,
2812
+ "loss": 0.9327,
2813
+ "step": 396
2814
+ },
2815
+ {
2816
+ "epoch": 0.87,
2817
+ "grad_norm": 0.111328125,
2818
+ "learning_rate": 8.266645407009788e-06,
2819
+ "loss": 0.8025,
2820
+ "step": 397
2821
+ },
2822
+ {
2823
+ "epoch": 0.87,
2824
+ "grad_norm": 0.10888671875,
2825
+ "learning_rate": 7.987870947139275e-06,
2826
+ "loss": 0.8903,
2827
+ "step": 398
2828
+ },
2829
+ {
2830
+ "epoch": 0.88,
2831
+ "grad_norm": 0.11279296875,
2832
+ "learning_rate": 7.713682370576946e-06,
2833
+ "loss": 0.8081,
2834
+ "step": 399
2835
+ },
2836
+ {
2837
+ "epoch": 0.88,
2838
+ "grad_norm": 0.12158203125,
2839
+ "learning_rate": 7.4440933428779e-06,
2840
+ "loss": 0.7926,
2841
+ "step": 400
2842
+ },
2843
+ {
2844
+ "epoch": 0.88,
2845
+ "grad_norm": 0.10498046875,
2846
+ "learning_rate": 7.17911730035572e-06,
2847
+ "loss": 0.863,
2848
+ "step": 401
2849
+ },
2850
+ {
2851
+ "epoch": 0.88,
2852
+ "grad_norm": 0.10400390625,
2853
+ "learning_rate": 6.9187674494129325e-06,
2854
+ "loss": 0.7536,
2855
+ "step": 402
2856
+ },
2857
+ {
2858
+ "epoch": 0.89,
2859
+ "grad_norm": 0.11328125,
2860
+ "learning_rate": 6.663056765882692e-06,
2861
+ "loss": 0.7939,
2862
+ "step": 403
2863
+ },
2864
+ {
2865
+ "epoch": 0.89,
2866
+ "grad_norm": 0.10693359375,
2867
+ "learning_rate": 6.4119979943821015e-06,
2868
+ "loss": 0.7258,
2869
+ "step": 404
2870
+ },
2871
+ {
2872
+ "epoch": 0.89,
2873
+ "grad_norm": 0.11083984375,
2874
+ "learning_rate": 6.165603647677054e-06,
2875
+ "loss": 0.7775,
2876
+ "step": 405
2877
+ },
2878
+ {
2879
+ "epoch": 0.89,
2880
+ "grad_norm": 0.09716796875,
2881
+ "learning_rate": 5.923886006058565e-06,
2882
+ "loss": 0.8807,
2883
+ "step": 406
2884
+ },
2885
+ {
2886
+ "epoch": 0.89,
2887
+ "grad_norm": 0.09765625,
2888
+ "learning_rate": 5.6868571167307595e-06,
2889
+ "loss": 0.911,
2890
+ "step": 407
2891
+ },
2892
+ {
2893
+ "epoch": 0.9,
2894
+ "grad_norm": 0.103515625,
2895
+ "learning_rate": 5.454528793210356e-06,
2896
+ "loss": 0.8141,
2897
+ "step": 408
2898
+ },
2899
+ {
2900
+ "epoch": 0.9,
2901
+ "grad_norm": 0.10400390625,
2902
+ "learning_rate": 5.2269126147379555e-06,
2903
+ "loss": 0.8843,
2904
+ "step": 409
2905
+ },
2906
+ {
2907
+ "epoch": 0.9,
2908
+ "grad_norm": 0.10107421875,
2909
+ "learning_rate": 5.00401992570092e-06,
2910
+ "loss": 0.7764,
2911
+ "step": 410
2912
+ },
2913
+ {
2914
+ "epoch": 0.9,
2915
+ "grad_norm": 0.109375,
2916
+ "learning_rate": 4.785861835067962e-06,
2917
+ "loss": 0.7584,
2918
+ "step": 411
2919
+ },
2920
+ {
2921
+ "epoch": 0.9,
2922
+ "grad_norm": 0.10595703125,
2923
+ "learning_rate": 4.5724492158354396e-06,
2924
+ "loss": 0.8061,
2925
+ "step": 412
2926
+ },
2927
+ {
2928
+ "epoch": 0.91,
2929
+ "grad_norm": 0.11669921875,
2930
+ "learning_rate": 4.3637927044855475e-06,
2931
+ "loss": 0.8835,
2932
+ "step": 413
2933
+ },
2934
+ {
2935
+ "epoch": 0.91,
2936
+ "grad_norm": 0.1123046875,
2937
+ "learning_rate": 4.159902700456053e-06,
2938
+ "loss": 0.8228,
2939
+ "step": 414
2940
+ },
2941
+ {
2942
+ "epoch": 0.91,
2943
+ "grad_norm": 0.11376953125,
2944
+ "learning_rate": 3.960789365622075e-06,
2945
+ "loss": 0.7909,
2946
+ "step": 415
2947
+ },
2948
+ {
2949
+ "epoch": 0.91,
2950
+ "grad_norm": 0.10693359375,
2951
+ "learning_rate": 3.766462623789646e-06,
2952
+ "loss": 0.9526,
2953
+ "step": 416
2954
+ },
2955
+ {
2956
+ "epoch": 0.92,
2957
+ "grad_norm": 0.08837890625,
2958
+ "learning_rate": 3.57693216020103e-06,
2959
+ "loss": 0.8374,
2960
+ "step": 417
2961
+ },
2962
+ {
2963
+ "epoch": 0.92,
2964
+ "grad_norm": 0.10693359375,
2965
+ "learning_rate": 3.3922074210520405e-06,
2966
+ "loss": 0.8091,
2967
+ "step": 418
2968
+ },
2969
+ {
2970
+ "epoch": 0.92,
2971
+ "grad_norm": 0.1083984375,
2972
+ "learning_rate": 3.2122976130212646e-06,
2973
+ "loss": 0.886,
2974
+ "step": 419
2975
+ },
2976
+ {
2977
+ "epoch": 0.92,
2978
+ "grad_norm": 0.1025390625,
2979
+ "learning_rate": 3.0372117028111825e-06,
2980
+ "loss": 0.7662,
2981
+ "step": 420
2982
+ },
2983
+ {
2984
+ "epoch": 0.92,
2985
+ "grad_norm": 0.1171875,
2986
+ "learning_rate": 2.866958416701271e-06,
2987
+ "loss": 0.9222,
2988
+ "step": 421
2989
+ },
2990
+ {
2991
+ "epoch": 0.93,
2992
+ "grad_norm": 0.103515625,
2993
+ "learning_rate": 2.7015462401130843e-06,
2994
+ "loss": 0.7954,
2995
+ "step": 422
2996
+ },
2997
+ {
2998
+ "epoch": 0.93,
2999
+ "grad_norm": 0.09423828125,
3000
+ "learning_rate": 2.5409834171873482e-06,
3001
+ "loss": 0.7532,
3002
+ "step": 423
3003
+ },
3004
+ {
3005
+ "epoch": 0.93,
3006
+ "grad_norm": 0.11962890625,
3007
+ "learning_rate": 2.3852779503730216e-06,
3008
+ "loss": 0.8322,
3009
+ "step": 424
3010
+ },
3011
+ {
3012
+ "epoch": 0.93,
3013
+ "grad_norm": 0.12890625,
3014
+ "learning_rate": 2.2344376000285604e-06,
3015
+ "loss": 0.7971,
3016
+ "step": 425
3017
+ },
3018
+ {
3019
+ "epoch": 0.94,
3020
+ "grad_norm": 0.1279296875,
3021
+ "learning_rate": 2.088469884035049e-06,
3022
+ "loss": 0.8257,
3023
+ "step": 426
3024
+ },
3025
+ {
3026
+ "epoch": 0.94,
3027
+ "grad_norm": 0.13671875,
3028
+ "learning_rate": 1.9473820774215555e-06,
3029
+ "loss": 0.7701,
3030
+ "step": 427
3031
+ },
3032
+ {
3033
+ "epoch": 0.94,
3034
+ "grad_norm": 0.12109375,
3035
+ "learning_rate": 1.8111812120024885e-06,
3036
+ "loss": 0.8043,
3037
+ "step": 428
3038
+ },
3039
+ {
3040
+ "epoch": 0.94,
3041
+ "grad_norm": 0.10595703125,
3042
+ "learning_rate": 1.6798740760272103e-06,
3043
+ "loss": 0.7984,
3044
+ "step": 429
3045
+ },
3046
+ {
3047
+ "epoch": 0.94,
3048
+ "grad_norm": 0.11767578125,
3049
+ "learning_rate": 1.553467213841664e-06,
3050
+ "loss": 0.8012,
3051
+ "step": 430
3052
+ },
3053
+ {
3054
+ "epoch": 0.95,
3055
+ "grad_norm": 0.10400390625,
3056
+ "learning_rate": 1.4319669255622115e-06,
3057
+ "loss": 0.8198,
3058
+ "step": 431
3059
+ },
3060
+ {
3061
+ "epoch": 0.95,
3062
+ "grad_norm": 0.1083984375,
3063
+ "learning_rate": 1.3153792667616183e-06,
3064
+ "loss": 0.8186,
3065
+ "step": 432
3066
+ },
3067
+ {
3068
+ "epoch": 0.95,
3069
+ "grad_norm": 0.09912109375,
3070
+ "learning_rate": 1.2037100481672835e-06,
3071
+ "loss": 0.722,
3072
+ "step": 433
3073
+ },
3074
+ {
3075
+ "epoch": 0.95,
3076
+ "grad_norm": 0.12158203125,
3077
+ "learning_rate": 1.0969648353715945e-06,
3078
+ "loss": 0.8273,
3079
+ "step": 434
3080
+ },
3081
+ {
3082
+ "epoch": 0.96,
3083
+ "grad_norm": 0.10791015625,
3084
+ "learning_rate": 9.951489485545695e-07,
3085
+ "loss": 0.8434,
3086
+ "step": 435
3087
+ },
3088
+ {
3089
+ "epoch": 0.96,
3090
+ "grad_norm": 0.1123046875,
3091
+ "learning_rate": 8.982674622186605e-07,
3092
+ "loss": 0.8882,
3093
+ "step": 436
3094
+ },
3095
+ {
3096
+ "epoch": 0.96,
3097
+ "grad_norm": 0.130859375,
3098
+ "learning_rate": 8.063252049358982e-07,
3099
+ "loss": 0.9377,
3100
+ "step": 437
3101
+ },
3102
+ {
3103
+ "epoch": 0.96,
3104
+ "grad_norm": 0.0986328125,
3105
+ "learning_rate": 7.193267591071529e-07,
3106
+ "loss": 0.8761,
3107
+ "step": 438
3108
+ },
3109
+ {
3110
+ "epoch": 0.96,
3111
+ "grad_norm": 0.10595703125,
3112
+ "learning_rate": 6.372764607338599e-07,
3113
+ "loss": 0.8163,
3114
+ "step": 439
3115
+ },
3116
+ {
3117
+ "epoch": 0.97,
3118
+ "grad_norm": 0.1005859375,
3119
+ "learning_rate": 5.60178399201805e-07,
3120
+ "loss": 0.8317,
3121
+ "step": 440
3122
+ },
3123
+ {
3124
+ "epoch": 0.97,
3125
+ "grad_norm": 0.11474609375,
3126
+ "learning_rate": 4.880364170773533e-07,
3127
+ "loss": 0.8711,
3128
+ "step": 441
3129
+ },
3130
+ {
3131
+ "epoch": 0.97,
3132
+ "grad_norm": 0.1005859375,
3133
+ "learning_rate": 4.208541099159691e-07,
3134
+ "loss": 0.7127,
3135
+ "step": 442
3136
+ },
3137
+ {
3138
+ "epoch": 0.97,
3139
+ "grad_norm": 0.125,
3140
+ "learning_rate": 3.586348260829486e-07,
3141
+ "loss": 0.8064,
3142
+ "step": 443
3143
+ },
3144
+ {
3145
+ "epoch": 0.98,
3146
+ "grad_norm": 0.10498046875,
3147
+ "learning_rate": 3.013816665865976e-07,
3148
+ "loss": 0.9065,
3149
+ "step": 444
3150
+ },
3151
+ {
3152
+ "epoch": 0.98,
3153
+ "grad_norm": 0.11328125,
3154
+ "learning_rate": 2.490974849236216e-07,
3155
+ "loss": 0.7879,
3156
+ "step": 445
3157
+ },
3158
+ {
3159
+ "epoch": 0.98,
3160
+ "grad_norm": 0.10498046875,
3161
+ "learning_rate": 2.0178488693695096e-07,
3162
+ "loss": 0.7726,
3163
+ "step": 446
3164
+ },
3165
+ {
3166
+ "epoch": 0.98,
3167
+ "grad_norm": 0.11376953125,
3168
+ "learning_rate": 1.5944623068586685e-07,
3169
+ "loss": 0.8243,
3170
+ "step": 447
3171
+ },
3172
+ {
3173
+ "epoch": 0.98,
3174
+ "grad_norm": 0.107421875,
3175
+ "learning_rate": 1.2208362632842862e-07,
3176
+ "loss": 0.8225,
3177
+ "step": 448
3178
+ },
3179
+ {
3180
+ "epoch": 0.99,
3181
+ "grad_norm": 0.10595703125,
3182
+ "learning_rate": 8.969893601634694e-08,
3183
+ "loss": 0.7913,
3184
+ "step": 449
3185
+ },
3186
+ {
3187
+ "epoch": 0.99,
3188
+ "grad_norm": 0.11865234375,
3189
+ "learning_rate": 6.229377380218005e-08,
3190
+ "loss": 0.7748,
3191
+ "step": 450
3192
+ },
3193
+ {
3194
+ "epoch": 0.99,
3195
+ "grad_norm": 0.111328125,
3196
+ "learning_rate": 3.986950555883162e-08,
3197
+ "loss": 0.8305,
3198
+ "step": 451
3199
+ },
3200
+ {
3201
+ "epoch": 0.99,
3202
+ "grad_norm": 0.125,
3203
+ "learning_rate": 2.242724891156067e-08,
3204
+ "loss": 0.8547,
3205
+ "step": 452
3206
+ },
3207
+ {
3208
+ "epoch": 1.0,
3209
+ "grad_norm": 0.11181640625,
3210
+ "learning_rate": 9.96787318218173e-09,
3211
+ "loss": 1.0104,
3212
+ "step": 453
3213
+ },
3214
+ {
3215
+ "epoch": 1.0,
3216
+ "grad_norm": 0.11865234375,
3217
+ "learning_rate": 2.4919993458549784e-09,
3218
+ "loss": 0.8115,
3219
+ "step": 454
3220
+ },
3221
+ {
3222
+ "epoch": 1.0,
3223
+ "grad_norm": 0.146484375,
3224
+ "learning_rate": 0.0,
3225
+ "loss": 0.8365,
3226
+ "step": 455
3227
+ }
3228
+ ],
3229
+ "logging_steps": 1,
3230
+ "max_steps": 455,
3231
+ "num_input_tokens_seen": 0,
3232
+ "num_train_epochs": 1,
3233
+ "save_steps": 500,
3234
+ "total_flos": 1.3577390229395866e+18,
3235
+ "train_batch_size": 2,
3236
+ "trial_name": null,
3237
+ "trial_params": null
3238
+ }
checkpoint-455/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3448952cf903a6b51b62e78021de5a1ee78cd10f9735ac962ba4ded9193c9989
3
+ size 5752
config.json CHANGED
@@ -21,8 +21,8 @@
21
  "rope_scaling": null,
22
  "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "float16",
25
  "transformers_version": "4.40.0.dev0",
26
- "use_cache": true,
27
  "vocab_size": 128256
28
  }
 
21
  "rope_scaling": null,
22
  "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
  "transformers_version": "4.40.0.dev0",
26
+ "use_cache": false,
27
  "vocab_size": 128256
28
  }
special_tokens_map.json CHANGED
@@ -12,5 +12,12 @@
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
 
 
 
 
 
 
 
15
  }
16
  }
 
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
  }
tokenizer_config.json CHANGED
@@ -2057,5 +2057,6 @@
2057
  "attention_mask"
2058
  ],
2059
  "model_max_length": 1000000000000000019884624838656,
 
2060
  "tokenizer_class": "PreTrainedTokenizerFast"
2061
  }
 
2057
  "attention_mask"
2058
  ],
2059
  "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
  }