Fischerboot commited on
Commit
4b62e1c
1 Parent(s): 32359e3

uploaded qlora

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +160 -2
  2. adapter_config.json +34 -0
  3. adapter_model.bin +3 -0
  4. checkpoint153/README.md +202 -0
  5. checkpoint153/adapter_config.json +34 -0
  6. checkpoint153/adapter_model.safetensors +3 -0
  7. checkpoint153/optimizer.pt +3 -0
  8. checkpoint153/rng_state.pth +3 -0
  9. checkpoint153/scheduler.pt +3 -0
  10. checkpoint153/special_tokens_map.json +23 -0
  11. checkpoint153/tokenizer.json +0 -0
  12. checkpoint153/tokenizer_config.json +2063 -0
  13. checkpoint153/trainer_state.json +1136 -0
  14. checkpoint153/training_args.bin +3 -0
  15. checkpoint306/README.md +202 -0
  16. checkpoint306/adapter_config.json +34 -0
  17. checkpoint306/adapter_model.safetensors +3 -0
  18. checkpoint306/optimizer.pt +3 -0
  19. checkpoint306/rng_state.pth +3 -0
  20. checkpoint306/scheduler.pt +3 -0
  21. checkpoint306/special_tokens_map.json +23 -0
  22. checkpoint306/tokenizer.json +0 -0
  23. checkpoint306/tokenizer_config.json +2063 -0
  24. checkpoint306/trainer_state.json +2239 -0
  25. checkpoint306/training_args.bin +3 -0
  26. checkpoint459/README.md +202 -0
  27. checkpoint459/adapter_config.json +34 -0
  28. checkpoint459/adapter_model.safetensors +3 -0
  29. checkpoint459/optimizer.pt +3 -0
  30. checkpoint459/rng_state.pth +3 -0
  31. checkpoint459/scheduler.pt +3 -0
  32. checkpoint459/special_tokens_map.json +23 -0
  33. checkpoint459/tokenizer.json +0 -0
  34. checkpoint459/tokenizer_config.json +2063 -0
  35. checkpoint459/trainer_state.json +3342 -0
  36. checkpoint459/training_args.bin +3 -0
  37. checkpoint612/README.md +202 -0
  38. checkpoint612/adapter_config.json +34 -0
  39. checkpoint612/adapter_model.safetensors +3 -0
  40. checkpoint612/optimizer.pt +3 -0
  41. checkpoint612/rng_state.pth +3 -0
  42. checkpoint612/scheduler.pt +3 -0
  43. checkpoint612/special_tokens_map.json +23 -0
  44. checkpoint612/tokenizer.json +0 -0
  45. checkpoint612/tokenizer_config.json +2063 -0
  46. checkpoint612/trainer_state.json +0 -0
  47. checkpoint612/training_args.bin +3 -0
  48. config.json +44 -0
  49. special_tokens_map.json +23 -0
  50. tokenizer.json +0 -0
README.md CHANGED
@@ -1,5 +1,163 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
3
  ---
4
 
5
- qlora adapter for Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP, maybe is good maybe not?
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
3
+ library_name: peft
4
+ license: llama3
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: outputs/qlora-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: `0.4.1`
19
+ ```yaml
20
+ base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
21
+ model_type: LlamaForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: true
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: practical-dreamer/RPGPT_PublicDomain-alpaca
30
+ type: alpaca
31
+ dataset_prepared_path: last_run_prepared
32
+ val_set_size: 0.1
33
+ output_dir: ./outputs/qlora-out
34
+
35
+ adapter: qlora
36
+ lora_model_dir:
37
+
38
+ sequence_len: 8192
39
+ sample_packing: true
40
+ pad_to_sequence_len: true
41
+
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
+ lora_target_modules:
48
+ - gate_proj
49
+ - down_proj
50
+ - up_proj
51
+ - q_proj
52
+ - v_proj
53
+ - k_proj
54
+ - o_proj
55
+
56
+ wandb_project:
57
+ wandb_entity:
58
+ wandb_watch:
59
+ wandb_name:
60
+ wandb_log_model:
61
+
62
+ gradient_accumulation_steps: 4
63
+ micro_batch_size: 2
64
+ num_epochs: 4
65
+ optimizer: adamw_bnb_8bit
66
+ lr_scheduler: cosine
67
+ learning_rate: 0.0002
68
+
69
+ train_on_inputs: false
70
+ group_by_length: false
71
+ bf16: auto
72
+ fp16:
73
+ tf32: false
74
+
75
+ gradient_checkpointing: true
76
+ early_stopping_patience:
77
+ resume_from_checkpoint:
78
+ local_rank:
79
+ logging_steps: 1
80
+ xformers_attention:
81
+ flash_attention: true
82
+
83
+ loss_watchdog_threshold: 5.0
84
+ loss_watchdog_patience: 3
85
+
86
+ warmup_steps: 10
87
+ evals_per_epoch: 4
88
+ eval_table_size:
89
+ eval_max_new_tokens: 128
90
+ saves_per_epoch: 1
91
+ debug:
92
+ deepspeed:
93
+ weight_decay: 0.0
94
+ fsdp:
95
+ fsdp_config:
96
+ special_tokens:
97
+ ```
98
+
99
+ </details><br>
100
+
101
+ # outputs/qlora-out
102
+
103
+ This model is a fine-tuned version of [Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP](https://huggingface.co/Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP) on the None dataset.
104
+ It achieves the following results on the evaluation set:
105
+ - Loss: 1.0083
106
+
107
+ ## Model description
108
+
109
+ More information needed
110
+
111
+ ## Intended uses & limitations
112
+
113
+ More information needed
114
+
115
+ ## Training and evaluation data
116
+
117
+ More information needed
118
+
119
+ ## Training procedure
120
+
121
+ ### Training hyperparameters
122
+
123
+ The following hyperparameters were used during training:
124
+ - learning_rate: 0.0002
125
+ - train_batch_size: 2
126
+ - eval_batch_size: 2
127
+ - seed: 42
128
+ - gradient_accumulation_steps: 4
129
+ - total_train_batch_size: 8
130
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
131
+ - lr_scheduler_type: cosine
132
+ - lr_scheduler_warmup_steps: 10
133
+ - num_epochs: 4
134
+
135
+ ### Training results
136
+
137
+ | Training Loss | Epoch | Step | Validation Loss |
138
+ |:-------------:|:------:|:----:|:---------------:|
139
+ | 1.3184 | 0.0065 | 1 | 1.3193 |
140
+ | 1.089 | 0.2545 | 39 | 1.1131 |
141
+ | 1.0475 | 0.5090 | 78 | 1.0719 |
142
+ | 1.0362 | 0.7635 | 117 | 1.0525 |
143
+ | 1.0619 | 1.0049 | 156 | 1.0389 |
144
+ | 1.0165 | 1.2594 | 195 | 1.0322 |
145
+ | 0.9394 | 1.5139 | 234 | 1.0246 |
146
+ | 0.999 | 1.7684 | 273 | 1.0182 |
147
+ | 0.9615 | 2.0082 | 312 | 1.0137 |
148
+ | 0.9543 | 2.2626 | 351 | 1.0136 |
149
+ | 0.9429 | 2.5171 | 390 | 1.0109 |
150
+ | 0.9474 | 2.7716 | 429 | 1.0076 |
151
+ | 0.8902 | 3.0098 | 468 | 1.0061 |
152
+ | 0.9144 | 3.2643 | 507 | 1.0089 |
153
+ | 0.9026 | 3.5188 | 546 | 1.0082 |
154
+ | 0.9163 | 3.7732 | 585 | 1.0083 |
155
+
156
+
157
+ ### Framework versions
158
+
159
+ - PEFT 0.11.1
160
+ - Transformers 4.41.1
161
+ - Pytorch 2.1.2+cu118
162
+ - Datasets 2.19.1
163
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP",
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
+ "o_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15d45c23ce4abe1eb8bc92d2e0b6883d5b7703da1f982c8c9f87d5a04ebe24b
3
+ size 167934026
checkpoint153/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint153/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP",
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
+ "o_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint153/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104d2cc2c27392ea2490baa4f411b07c34d1a809a7d14ceb0630b83602fb7c0b
3
+ size 167832688
checkpoint153/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937515d1bc23c02bf1951fbe7fef8f3efb5c2804cc7a63c3874c0de909f5b2b6
3
+ size 168624724
checkpoint153/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ebf8ca1123e182ff021076b39781c430bef1619704f527cb42fd9fba8b69867
3
+ size 14244
checkpoint153/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d648cd2a5f16724393b5bff59a360933794f8b59ea121d5888f1026d644803f
3
+ size 1064
checkpoint153/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": "<|eot_id|>",
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
+ }
checkpoint153/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint153/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint153/trainer_state.json ADDED
@@ -0,0 +1,1136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.99836867862969,
5
+ "eval_steps": 39,
6
+ "global_step": 153,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0065252854812398045,
13
+ "grad_norm": 0.23828125,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.3184,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0065252854812398045,
20
+ "eval_loss": 1.3192611932754517,
21
+ "eval_runtime": 235.1739,
22
+ "eval_samples_per_second": 1.811,
23
+ "eval_steps_per_second": 0.906,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.013050570962479609,
28
+ "grad_norm": 0.2373046875,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.3213,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01957585644371941,
35
+ "grad_norm": 0.2373046875,
36
+ "learning_rate": 6e-05,
37
+ "loss": 1.3232,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.026101141924959218,
42
+ "grad_norm": 0.259765625,
43
+ "learning_rate": 8e-05,
44
+ "loss": 1.3418,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.03262642740619902,
49
+ "grad_norm": 0.275390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.2712,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.03915171288743882,
56
+ "grad_norm": 0.2412109375,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.2682,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.04567699836867863,
63
+ "grad_norm": 0.1015625,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.2672,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.052202283849918436,
70
+ "grad_norm": 0.44140625,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.2337,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.05872756933115824,
77
+ "grad_norm": 0.51171875,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.3138,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.06525285481239804,
84
+ "grad_norm": 0.326171875,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.238,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.07177814029363784,
91
+ "grad_norm": 0.138671875,
92
+ "learning_rate": 0.0001999986383177335,
93
+ "loss": 1.2244,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.07830342577487764,
98
+ "grad_norm": 0.07666015625,
99
+ "learning_rate": 0.0001999945533080175,
100
+ "loss": 1.1796,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.08482871125611746,
105
+ "grad_norm": 0.1171875,
106
+ "learning_rate": 0.0001999877450821018,
107
+ "loss": 1.1873,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.09135399673735727,
112
+ "grad_norm": 0.154296875,
113
+ "learning_rate": 0.0001999782138253991,
114
+ "loss": 1.1684,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.09787928221859707,
119
+ "grad_norm": 0.15625,
120
+ "learning_rate": 0.00019996595979748037,
121
+ "loss": 1.2122,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.10440456769983687,
126
+ "grad_norm": 0.12158203125,
127
+ "learning_rate": 0.00019995098333206742,
128
+ "loss": 1.1772,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.11092985318107668,
133
+ "grad_norm": 0.07958984375,
134
+ "learning_rate": 0.00019993328483702393,
135
+ "loss": 1.1742,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.11745513866231648,
140
+ "grad_norm": 0.09326171875,
141
+ "learning_rate": 0.00019991286479434454,
142
+ "loss": 1.1791,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.12398042414355628,
147
+ "grad_norm": 0.11474609375,
148
+ "learning_rate": 0.00019988972376014142,
149
+ "loss": 1.1651,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.13050570962479607,
154
+ "grad_norm": 0.1572265625,
155
+ "learning_rate": 0.00019986386236462924,
156
+ "loss": 1.1874,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.1370309951060359,
161
+ "grad_norm": 0.12255859375,
162
+ "learning_rate": 0.00019983528131210812,
163
+ "loss": 1.1371,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.14355628058727568,
168
+ "grad_norm": 0.08544921875,
169
+ "learning_rate": 0.00019980398138094428,
170
+ "loss": 1.1725,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.1500815660685155,
175
+ "grad_norm": 0.07763671875,
176
+ "learning_rate": 0.00019976996342354898,
177
+ "loss": 1.1264,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.1566068515497553,
182
+ "grad_norm": 0.078125,
183
+ "learning_rate": 0.00019973322836635518,
184
+ "loss": 1.091,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.1631321370309951,
189
+ "grad_norm": 0.09423828125,
190
+ "learning_rate": 0.00019969377720979237,
191
+ "loss": 1.1636,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.16965742251223492,
196
+ "grad_norm": 0.1044921875,
197
+ "learning_rate": 0.00019965161102825945,
198
+ "loss": 1.1472,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.1761827079934747,
203
+ "grad_norm": 0.0751953125,
204
+ "learning_rate": 0.00019960673097009518,
205
+ "loss": 1.1212,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.18270799347471453,
210
+ "grad_norm": 0.072265625,
211
+ "learning_rate": 0.00019955913825754713,
212
+ "loss": 1.1466,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.18923327895595432,
217
+ "grad_norm": 0.0693359375,
218
+ "learning_rate": 0.0001995088341867384,
219
+ "loss": 1.1235,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.19575856443719414,
224
+ "grad_norm": 0.06787109375,
225
+ "learning_rate": 0.0001994558201276322,
226
+ "loss": 1.1123,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.20228384991843393,
231
+ "grad_norm": 0.07177734375,
232
+ "learning_rate": 0.0001994000975239946,
233
+ "loss": 1.1459,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.20880913539967375,
238
+ "grad_norm": 0.07470703125,
239
+ "learning_rate": 0.00019934166789335525,
240
+ "loss": 1.1231,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.21533442088091354,
245
+ "grad_norm": 0.06689453125,
246
+ "learning_rate": 0.00019928053282696596,
247
+ "loss": 1.1153,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.22185970636215335,
252
+ "grad_norm": 0.078125,
253
+ "learning_rate": 0.00019921669398975745,
254
+ "loss": 1.0979,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.22838499184339314,
259
+ "grad_norm": 0.07421875,
260
+ "learning_rate": 0.000199150153120294,
261
+ "loss": 1.0667,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.23491027732463296,
266
+ "grad_norm": 0.06689453125,
267
+ "learning_rate": 0.00019908091203072598,
268
+ "loss": 1.1144,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.24143556280587275,
273
+ "grad_norm": 0.07080078125,
274
+ "learning_rate": 0.00019900897260674073,
275
+ "loss": 1.104,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.24796084828711257,
280
+ "grad_norm": 0.06689453125,
281
+ "learning_rate": 0.00019893433680751103,
282
+ "loss": 1.1016,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.2544861337683524,
287
+ "grad_norm": 0.07275390625,
288
+ "learning_rate": 0.0001988570066656417,
289
+ "loss": 1.089,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.2544861337683524,
294
+ "eval_loss": 1.1131086349487305,
295
+ "eval_runtime": 236.8764,
296
+ "eval_samples_per_second": 1.798,
297
+ "eval_steps_per_second": 0.899,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.26101141924959215,
302
+ "grad_norm": 0.078125,
303
+ "learning_rate": 0.00019877698428711442,
304
+ "loss": 1.1207,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.26753670473083196,
309
+ "grad_norm": 0.06982421875,
310
+ "learning_rate": 0.00019869427185123027,
311
+ "loss": 1.1376,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.2740619902120718,
316
+ "grad_norm": 0.06982421875,
317
+ "learning_rate": 0.00019860887161055038,
318
+ "loss": 1.1,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.2805872756933116,
323
+ "grad_norm": 0.080078125,
324
+ "learning_rate": 0.00019852078589083466,
325
+ "loss": 1.1185,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.28711256117455136,
330
+ "grad_norm": 0.0732421875,
331
+ "learning_rate": 0.0001984300170909783,
332
+ "loss": 1.1282,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.2936378466557912,
337
+ "grad_norm": 0.0654296875,
338
+ "learning_rate": 0.00019833656768294662,
339
+ "loss": 1.1505,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.300163132137031,
344
+ "grad_norm": 0.06689453125,
345
+ "learning_rate": 0.0001982404402117077,
346
+ "loss": 1.1102,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.3066884176182708,
351
+ "grad_norm": 0.0712890625,
352
+ "learning_rate": 0.00019814163729516292,
353
+ "loss": 1.1254,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.3132137030995106,
358
+ "grad_norm": 0.0673828125,
359
+ "learning_rate": 0.0001980401616240759,
360
+ "loss": 1.0934,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.3197389885807504,
365
+ "grad_norm": 0.06689453125,
366
+ "learning_rate": 0.00019793601596199912,
367
+ "loss": 1.0792,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.3262642740619902,
372
+ "grad_norm": 0.07177734375,
373
+ "learning_rate": 0.00019782920314519856,
374
+ "loss": 1.0936,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.33278955954323003,
379
+ "grad_norm": 0.06884765625,
380
+ "learning_rate": 0.00019771972608257659,
381
+ "loss": 1.0636,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.33931484502446985,
386
+ "grad_norm": 0.0673828125,
387
+ "learning_rate": 0.00019760758775559274,
388
+ "loss": 1.0693,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3458401305057096,
393
+ "grad_norm": 0.06787109375,
394
+ "learning_rate": 0.00019749279121818235,
395
+ "loss": 1.0882,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3523654159869494,
400
+ "grad_norm": 0.0703125,
401
+ "learning_rate": 0.0001973753395966737,
402
+ "loss": 1.1066,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.35889070146818924,
407
+ "grad_norm": 0.0712890625,
408
+ "learning_rate": 0.00019725523608970255,
409
+ "loss": 1.049,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.36541598694942906,
414
+ "grad_norm": 0.06982421875,
415
+ "learning_rate": 0.00019713248396812524,
416
+ "loss": 1.1083,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3719412724306688,
421
+ "grad_norm": 0.072265625,
422
+ "learning_rate": 0.00019700708657492948,
423
+ "loss": 1.0854,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.37846655791190864,
428
+ "grad_norm": 0.07275390625,
429
+ "learning_rate": 0.0001968790473251434,
430
+ "loss": 1.0954,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.38499184339314846,
435
+ "grad_norm": 0.07373046875,
436
+ "learning_rate": 0.00019674836970574254,
437
+ "loss": 1.0833,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3915171288743883,
442
+ "grad_norm": 0.07275390625,
443
+ "learning_rate": 0.00019661505727555482,
444
+ "loss": 1.0945,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.39804241435562804,
449
+ "grad_norm": 0.07080078125,
450
+ "learning_rate": 0.0001964791136651637,
451
+ "loss": 1.07,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.40456769983686786,
456
+ "grad_norm": 0.07177734375,
457
+ "learning_rate": 0.00019634054257680923,
458
+ "loss": 1.0998,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4110929853181077,
463
+ "grad_norm": 0.0712890625,
464
+ "learning_rate": 0.0001961993477842873,
465
+ "loss": 1.0718,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4176182707993475,
470
+ "grad_norm": 0.078125,
471
+ "learning_rate": 0.0001960555331328468,
472
+ "loss": 1.0285,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.42414355628058725,
477
+ "grad_norm": 0.08203125,
478
+ "learning_rate": 0.00019590910253908494,
479
+ "loss": 1.0836,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.43066884176182707,
484
+ "grad_norm": 0.076171875,
485
+ "learning_rate": 0.0001957600599908406,
486
+ "loss": 1.0836,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4371941272430669,
491
+ "grad_norm": 0.07373046875,
492
+ "learning_rate": 0.00019560840954708565,
493
+ "loss": 1.0868,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4437194127243067,
498
+ "grad_norm": 0.06884765625,
499
+ "learning_rate": 0.0001954541553378145,
500
+ "loss": 1.115,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.45024469820554647,
505
+ "grad_norm": 0.0703125,
506
+ "learning_rate": 0.0001952973015639316,
507
+ "loss": 1.047,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.4567699836867863,
512
+ "grad_norm": 0.07373046875,
513
+ "learning_rate": 0.00019513785249713697,
514
+ "loss": 1.0878,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.4632952691680261,
519
+ "grad_norm": 0.07275390625,
520
+ "learning_rate": 0.00019497581247980992,
521
+ "loss": 1.0547,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.4698205546492659,
526
+ "grad_norm": 0.0732421875,
527
+ "learning_rate": 0.00019481118592489086,
528
+ "loss": 1.0907,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.4763458401305057,
533
+ "grad_norm": 0.0703125,
534
+ "learning_rate": 0.00019464397731576094,
535
+ "loss": 1.053,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4828711256117455,
540
+ "grad_norm": 0.07421875,
541
+ "learning_rate": 0.00019447419120612017,
542
+ "loss": 1.0768,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4893964110929853,
547
+ "grad_norm": 0.0732421875,
548
+ "learning_rate": 0.00019430183221986325,
549
+ "loss": 1.0599,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.49592169657422513,
554
+ "grad_norm": 0.076171875,
555
+ "learning_rate": 0.00019412690505095365,
556
+ "loss": 1.0721,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5024469820554649,
561
+ "grad_norm": 0.07666015625,
562
+ "learning_rate": 0.00019394941446329583,
563
+ "loss": 1.0802,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5089722675367048,
568
+ "grad_norm": 0.0771484375,
569
+ "learning_rate": 0.00019376936529060554,
570
+ "loss": 1.0475,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5089722675367048,
575
+ "eval_loss": 1.0718731880187988,
576
+ "eval_runtime": 236.7722,
577
+ "eval_samples_per_second": 1.799,
578
+ "eval_steps_per_second": 0.9,
579
+ "step": 78
580
+ },
581
+ {
582
+ "epoch": 0.5154975530179445,
583
+ "grad_norm": 0.072265625,
584
+ "learning_rate": 0.00019358676243627808,
585
+ "loss": 1.0706,
586
+ "step": 79
587
+ },
588
+ {
589
+ "epoch": 0.5220228384991843,
590
+ "grad_norm": 0.07568359375,
591
+ "learning_rate": 0.0001934016108732548,
592
+ "loss": 1.0679,
593
+ "step": 80
594
+ },
595
+ {
596
+ "epoch": 0.5285481239804242,
597
+ "grad_norm": 0.08056640625,
598
+ "learning_rate": 0.00019321391564388775,
599
+ "loss": 1.044,
600
+ "step": 81
601
+ },
602
+ {
603
+ "epoch": 0.5350734094616639,
604
+ "grad_norm": 0.078125,
605
+ "learning_rate": 0.00019302368185980217,
606
+ "loss": 1.0878,
607
+ "step": 82
608
+ },
609
+ {
610
+ "epoch": 0.5415986949429038,
611
+ "grad_norm": 0.08447265625,
612
+ "learning_rate": 0.00019283091470175754,
613
+ "loss": 1.0469,
614
+ "step": 83
615
+ },
616
+ {
617
+ "epoch": 0.5481239804241436,
618
+ "grad_norm": 0.07861328125,
619
+ "learning_rate": 0.00019263561941950622,
620
+ "loss": 1.0453,
621
+ "step": 84
622
+ },
623
+ {
624
+ "epoch": 0.5546492659053833,
625
+ "grad_norm": 0.08154296875,
626
+ "learning_rate": 0.00019243780133165067,
627
+ "loss": 1.0677,
628
+ "step": 85
629
+ },
630
+ {
631
+ "epoch": 0.5611745513866232,
632
+ "grad_norm": 0.08056640625,
633
+ "learning_rate": 0.00019223746582549853,
634
+ "loss": 1.0648,
635
+ "step": 86
636
+ },
637
+ {
638
+ "epoch": 0.567699836867863,
639
+ "grad_norm": 0.083984375,
640
+ "learning_rate": 0.00019203461835691594,
641
+ "loss": 1.0891,
642
+ "step": 87
643
+ },
644
+ {
645
+ "epoch": 0.5742251223491027,
646
+ "grad_norm": 0.08447265625,
647
+ "learning_rate": 0.00019182926445017893,
648
+ "loss": 1.0607,
649
+ "step": 88
650
+ },
651
+ {
652
+ "epoch": 0.5807504078303426,
653
+ "grad_norm": 0.078125,
654
+ "learning_rate": 0.00019162140969782292,
655
+ "loss": 1.0241,
656
+ "step": 89
657
+ },
658
+ {
659
+ "epoch": 0.5872756933115824,
660
+ "grad_norm": 0.08642578125,
661
+ "learning_rate": 0.00019141105976049053,
662
+ "loss": 1.0675,
663
+ "step": 90
664
+ },
665
+ {
666
+ "epoch": 0.5938009787928222,
667
+ "grad_norm": 0.08642578125,
668
+ "learning_rate": 0.00019119822036677738,
669
+ "loss": 1.0538,
670
+ "step": 91
671
+ },
672
+ {
673
+ "epoch": 0.600326264274062,
674
+ "grad_norm": 0.0751953125,
675
+ "learning_rate": 0.000190982897313076,
676
+ "loss": 1.0572,
677
+ "step": 92
678
+ },
679
+ {
680
+ "epoch": 0.6068515497553018,
681
+ "grad_norm": 0.076171875,
682
+ "learning_rate": 0.00019076509646341806,
683
+ "loss": 1.0372,
684
+ "step": 93
685
+ },
686
+ {
687
+ "epoch": 0.6133768352365416,
688
+ "grad_norm": 0.07861328125,
689
+ "learning_rate": 0.00019054482374931467,
690
+ "loss": 1.0693,
691
+ "step": 94
692
+ },
693
+ {
694
+ "epoch": 0.6199021207177814,
695
+ "grad_norm": 0.07861328125,
696
+ "learning_rate": 0.0001903220851695948,
697
+ "loss": 1.0726,
698
+ "step": 95
699
+ },
700
+ {
701
+ "epoch": 0.6264274061990212,
702
+ "grad_norm": 0.0791015625,
703
+ "learning_rate": 0.0001900968867902419,
704
+ "loss": 1.0543,
705
+ "step": 96
706
+ },
707
+ {
708
+ "epoch": 0.632952691680261,
709
+ "grad_norm": 0.08447265625,
710
+ "learning_rate": 0.00018986923474422884,
711
+ "loss": 1.0577,
712
+ "step": 97
713
+ },
714
+ {
715
+ "epoch": 0.6394779771615008,
716
+ "grad_norm": 0.08447265625,
717
+ "learning_rate": 0.0001896391352313506,
718
+ "loss": 1.0649,
719
+ "step": 98
720
+ },
721
+ {
722
+ "epoch": 0.6460032626427407,
723
+ "grad_norm": 0.08056640625,
724
+ "learning_rate": 0.0001894065945180558,
725
+ "loss": 1.0828,
726
+ "step": 99
727
+ },
728
+ {
729
+ "epoch": 0.6525285481239804,
730
+ "grad_norm": 0.07861328125,
731
+ "learning_rate": 0.0001891716189372757,
732
+ "loss": 1.0805,
733
+ "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6590538336052202,
737
+ "grad_norm": 0.07861328125,
738
+ "learning_rate": 0.0001889342148882519,
739
+ "loss": 1.0158,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6655791190864601,
744
+ "grad_norm": 0.08056640625,
745
+ "learning_rate": 0.00018869438883636214,
746
+ "loss": 1.0686,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6721044045676998,
751
+ "grad_norm": 0.07958984375,
752
+ "learning_rate": 0.000188452147312944,
753
+ "loss": 1.0498,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6786296900489397,
758
+ "grad_norm": 0.07861328125,
759
+ "learning_rate": 0.0001882074969151172,
760
+ "loss": 1.0783,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6851549755301795,
765
+ "grad_norm": 0.08056640625,
766
+ "learning_rate": 0.000187960444305604,
767
+ "loss": 0.9942,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6916802610114192,
772
+ "grad_norm": 0.0791015625,
773
+ "learning_rate": 0.00018771099621254746,
774
+ "loss": 1.0517,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.6982055464926591,
779
+ "grad_norm": 0.0810546875,
780
+ "learning_rate": 0.0001874591594293285,
781
+ "loss": 1.0619,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7047308319738989,
786
+ "grad_norm": 0.08251953125,
787
+ "learning_rate": 0.00018720494081438078,
788
+ "loss": 1.0584,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7112561174551386,
793
+ "grad_norm": 0.08740234375,
794
+ "learning_rate": 0.00018694834729100386,
795
+ "loss": 1.0466,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7177814029363785,
800
+ "grad_norm": 0.08349609375,
801
+ "learning_rate": 0.00018668938584717471,
802
+ "loss": 1.0391,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7243066884176182,
807
+ "grad_norm": 0.08251953125,
808
+ "learning_rate": 0.00018642806353535754,
809
+ "loss": 1.0331,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7308319738988581,
814
+ "grad_norm": 0.0859375,
815
+ "learning_rate": 0.00018616438747231148,
816
+ "loss": 1.0671,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7373572593800979,
821
+ "grad_norm": 0.087890625,
822
+ "learning_rate": 0.00018589836483889687,
823
+ "loss": 1.0525,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7438825448613376,
828
+ "grad_norm": 0.08935546875,
829
+ "learning_rate": 0.0001856300028798798,
830
+ "loss": 1.0182,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7504078303425775,
835
+ "grad_norm": 0.08349609375,
836
+ "learning_rate": 0.00018535930890373466,
837
+ "loss": 1.0566,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7569331158238173,
842
+ "grad_norm": 0.080078125,
843
+ "learning_rate": 0.00018508629028244519,
844
+ "loss": 1.0316,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.763458401305057,
849
+ "grad_norm": 0.09033203125,
850
+ "learning_rate": 0.0001848109544513037,
851
+ "loss": 1.0362,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.763458401305057,
856
+ "eval_loss": 1.0525188446044922,
857
+ "eval_runtime": 236.6432,
858
+ "eval_samples_per_second": 1.8,
859
+ "eval_steps_per_second": 0.9,
860
+ "step": 117
861
+ },
862
+ {
863
+ "epoch": 0.7699836867862969,
864
+ "grad_norm": 0.08544921875,
865
+ "learning_rate": 0.00018453330890870855,
866
+ "loss": 1.0141,
867
+ "step": 118
868
+ },
869
+ {
870
+ "epoch": 0.7765089722675367,
871
+ "grad_norm": 0.08203125,
872
+ "learning_rate": 0.00018425336121596,
873
+ "loss": 1.0464,
874
+ "step": 119
875
+ },
876
+ {
877
+ "epoch": 0.7830342577487766,
878
+ "grad_norm": 0.0830078125,
879
+ "learning_rate": 0.00018397111899705419,
880
+ "loss": 1.0278,
881
+ "step": 120
882
+ },
883
+ {
884
+ "epoch": 0.7895595432300163,
885
+ "grad_norm": 0.080078125,
886
+ "learning_rate": 0.00018368658993847566,
887
+ "loss": 1.0439,
888
+ "step": 121
889
+ },
890
+ {
891
+ "epoch": 0.7960848287112561,
892
+ "grad_norm": 0.08251953125,
893
+ "learning_rate": 0.0001833997817889878,
894
+ "loss": 1.053,
895
+ "step": 122
896
+ },
897
+ {
898
+ "epoch": 0.802610114192496,
899
+ "grad_norm": 0.08642578125,
900
+ "learning_rate": 0.0001831107023594221,
901
+ "loss": 1.0447,
902
+ "step": 123
903
+ },
904
+ {
905
+ "epoch": 0.8091353996737357,
906
+ "grad_norm": 0.08349609375,
907
+ "learning_rate": 0.00018281935952246518,
908
+ "loss": 1.0347,
909
+ "step": 124
910
+ },
911
+ {
912
+ "epoch": 0.8156606851549756,
913
+ "grad_norm": 0.0810546875,
914
+ "learning_rate": 0.00018252576121244456,
915
+ "loss": 1.0628,
916
+ "step": 125
917
+ },
918
+ {
919
+ "epoch": 0.8221859706362153,
920
+ "grad_norm": 0.08056640625,
921
+ "learning_rate": 0.00018222991542511246,
922
+ "loss": 1.0112,
923
+ "step": 126
924
+ },
925
+ {
926
+ "epoch": 0.8287112561174551,
927
+ "grad_norm": 0.08984375,
928
+ "learning_rate": 0.0001819318302174281,
929
+ "loss": 1.0657,
930
+ "step": 127
931
+ },
932
+ {
933
+ "epoch": 0.835236541598695,
934
+ "grad_norm": 0.08837890625,
935
+ "learning_rate": 0.00018163151370733838,
936
+ "loss": 1.0936,
937
+ "step": 128
938
+ },
939
+ {
940
+ "epoch": 0.8417618270799347,
941
+ "grad_norm": 0.0869140625,
942
+ "learning_rate": 0.00018132897407355657,
943
+ "loss": 1.0519,
944
+ "step": 129
945
+ },
946
+ {
947
+ "epoch": 0.8482871125611745,
948
+ "grad_norm": 0.08447265625,
949
+ "learning_rate": 0.00018102421955533974,
950
+ "loss": 1.018,
951
+ "step": 130
952
+ },
953
+ {
954
+ "epoch": 0.8548123980424144,
955
+ "grad_norm": 0.08349609375,
956
+ "learning_rate": 0.00018071725845226436,
957
+ "loss": 0.9982,
958
+ "step": 131
959
+ },
960
+ {
961
+ "epoch": 0.8613376835236541,
962
+ "grad_norm": 0.0966796875,
963
+ "learning_rate": 0.0001804080991240003,
964
+ "loss": 1.0522,
965
+ "step": 132
966
+ },
967
+ {
968
+ "epoch": 0.867862969004894,
969
+ "grad_norm": 0.0830078125,
970
+ "learning_rate": 0.000180096749990083,
971
+ "loss": 1.0149,
972
+ "step": 133
973
+ },
974
+ {
975
+ "epoch": 0.8743882544861338,
976
+ "grad_norm": 0.0810546875,
977
+ "learning_rate": 0.00017978321952968434,
978
+ "loss": 1.0096,
979
+ "step": 134
980
+ },
981
+ {
982
+ "epoch": 0.8809135399673735,
983
+ "grad_norm": 0.09765625,
984
+ "learning_rate": 0.00017946751628138174,
985
+ "loss": 1.0551,
986
+ "step": 135
987
+ },
988
+ {
989
+ "epoch": 0.8874388254486134,
990
+ "grad_norm": 0.083984375,
991
+ "learning_rate": 0.00017914964884292544,
992
+ "loss": 1.0384,
993
+ "step": 136
994
+ },
995
+ {
996
+ "epoch": 0.8939641109298532,
997
+ "grad_norm": 0.09326171875,
998
+ "learning_rate": 0.0001788296258710045,
999
+ "loss": 1.0341,
1000
+ "step": 137
1001
+ },
1002
+ {
1003
+ "epoch": 0.9004893964110929,
1004
+ "grad_norm": 0.0859375,
1005
+ "learning_rate": 0.0001785074560810111,
1006
+ "loss": 1.0162,
1007
+ "step": 138
1008
+ },
1009
+ {
1010
+ "epoch": 0.9070146818923328,
1011
+ "grad_norm": 0.0849609375,
1012
+ "learning_rate": 0.000178183148246803,
1013
+ "loss": 1.0332,
1014
+ "step": 139
1015
+ },
1016
+ {
1017
+ "epoch": 0.9135399673735726,
1018
+ "grad_norm": 0.08251953125,
1019
+ "learning_rate": 0.00017785671120046473,
1020
+ "loss": 1.0219,
1021
+ "step": 140
1022
+ },
1023
+ {
1024
+ "epoch": 0.9200652528548124,
1025
+ "grad_norm": 0.080078125,
1026
+ "learning_rate": 0.00017752815383206705,
1027
+ "loss": 1.0557,
1028
+ "step": 141
1029
+ },
1030
+ {
1031
+ "epoch": 0.9265905383360522,
1032
+ "grad_norm": 0.0849609375,
1033
+ "learning_rate": 0.0001771974850894248,
1034
+ "loss": 1.075,
1035
+ "step": 142
1036
+ },
1037
+ {
1038
+ "epoch": 0.933115823817292,
1039
+ "grad_norm": 0.087890625,
1040
+ "learning_rate": 0.0001768647139778532,
1041
+ "loss": 1.0458,
1042
+ "step": 143
1043
+ },
1044
+ {
1045
+ "epoch": 0.9396411092985318,
1046
+ "grad_norm": 0.0830078125,
1047
+ "learning_rate": 0.00017652984955992277,
1048
+ "loss": 1.054,
1049
+ "step": 144
1050
+ },
1051
+ {
1052
+ "epoch": 0.9461663947797716,
1053
+ "grad_norm": 0.08154296875,
1054
+ "learning_rate": 0.0001761929009552122,
1055
+ "loss": 1.0297,
1056
+ "step": 145
1057
+ },
1058
+ {
1059
+ "epoch": 0.9526916802610114,
1060
+ "grad_norm": 0.0849609375,
1061
+ "learning_rate": 0.00017585387734006034,
1062
+ "loss": 1.0299,
1063
+ "step": 146
1064
+ },
1065
+ {
1066
+ "epoch": 0.9592169657422512,
1067
+ "grad_norm": 0.0810546875,
1068
+ "learning_rate": 0.00017551278794731607,
1069
+ "loss": 1.0578,
1070
+ "step": 147
1071
+ },
1072
+ {
1073
+ "epoch": 0.965742251223491,
1074
+ "grad_norm": 0.0859375,
1075
+ "learning_rate": 0.00017516964206608696,
1076
+ "loss": 1.0362,
1077
+ "step": 148
1078
+ },
1079
+ {
1080
+ "epoch": 0.9722675367047309,
1081
+ "grad_norm": 0.09130859375,
1082
+ "learning_rate": 0.00017482444904148617,
1083
+ "loss": 1.0356,
1084
+ "step": 149
1085
+ },
1086
+ {
1087
+ "epoch": 0.9787928221859706,
1088
+ "grad_norm": 0.0869140625,
1089
+ "learning_rate": 0.0001744772182743782,
1090
+ "loss": 1.038,
1091
+ "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.9853181076672104,
1095
+ "grad_norm": 0.0859375,
1096
+ "learning_rate": 0.00017412795922112253,
1097
+ "loss": 1.0445,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.9918433931484503,
1102
+ "grad_norm": 0.08544921875,
1103
+ "learning_rate": 0.0001737766813933164,
1104
+ "loss": 1.0524,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.99836867862969,
1109
+ "grad_norm": 0.08837890625,
1110
+ "learning_rate": 0.00017342339435753553,
1111
+ "loss": 1.0517,
1112
+ "step": 153
1113
+ }
1114
+ ],
1115
+ "logging_steps": 1,
1116
+ "max_steps": 612,
1117
+ "num_input_tokens_seen": 0,
1118
+ "num_train_epochs": 4,
1119
+ "save_steps": 153,
1120
+ "stateful_callbacks": {
1121
+ "TrainerControl": {
1122
+ "args": {
1123
+ "should_epoch_stop": false,
1124
+ "should_evaluate": false,
1125
+ "should_log": false,
1126
+ "should_save": true,
1127
+ "should_training_stop": false
1128
+ },
1129
+ "attributes": {}
1130
+ }
1131
+ },
1132
+ "total_flos": 4.565583967247401e+17,
1133
+ "train_batch_size": 2,
1134
+ "trial_name": null,
1135
+ "trial_params": null
1136
+ }
checkpoint153/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998c86e0068ec82450c4b585a291b75939d4efaf9fcfdeab3730d3a755504c16
3
+ size 5944
checkpoint306/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint306/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP",
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
+ "o_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint306/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4784dd293a49e30767b072ac00181267d1530d41fabb8bccf4b1a20a5565558c
3
+ size 167832688
checkpoint306/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26cc0d3ec49a98c6275b038242b596b2230a57b9132b6814e256f861956066fd
3
+ size 168625172
checkpoint306/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a29c4bf2c6d98fc84d005cf46ff00742f297b207e83ef8766c5462522d1b0b4
3
+ size 14244
checkpoint306/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d7bcef9e659da02789a36fd5eb9cdb5e6648299ded2a2014e8eba443109fde
3
+ size 1064
checkpoint306/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": "<|eot_id|>",
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
+ }
checkpoint306/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint306/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint306/trainer_state.json ADDED
@@ -0,0 +1,2239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9836867862969005,
5
+ "eval_steps": 39,
6
+ "global_step": 306,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0065252854812398045,
13
+ "grad_norm": 0.23828125,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.3184,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0065252854812398045,
20
+ "eval_loss": 1.3192611932754517,
21
+ "eval_runtime": 235.1739,
22
+ "eval_samples_per_second": 1.811,
23
+ "eval_steps_per_second": 0.906,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.013050570962479609,
28
+ "grad_norm": 0.2373046875,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.3213,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01957585644371941,
35
+ "grad_norm": 0.2373046875,
36
+ "learning_rate": 6e-05,
37
+ "loss": 1.3232,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.026101141924959218,
42
+ "grad_norm": 0.259765625,
43
+ "learning_rate": 8e-05,
44
+ "loss": 1.3418,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.03262642740619902,
49
+ "grad_norm": 0.275390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.2712,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.03915171288743882,
56
+ "grad_norm": 0.2412109375,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.2682,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.04567699836867863,
63
+ "grad_norm": 0.1015625,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.2672,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.052202283849918436,
70
+ "grad_norm": 0.44140625,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.2337,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.05872756933115824,
77
+ "grad_norm": 0.51171875,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.3138,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.06525285481239804,
84
+ "grad_norm": 0.326171875,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.238,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.07177814029363784,
91
+ "grad_norm": 0.138671875,
92
+ "learning_rate": 0.0001999986383177335,
93
+ "loss": 1.2244,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.07830342577487764,
98
+ "grad_norm": 0.07666015625,
99
+ "learning_rate": 0.0001999945533080175,
100
+ "loss": 1.1796,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.08482871125611746,
105
+ "grad_norm": 0.1171875,
106
+ "learning_rate": 0.0001999877450821018,
107
+ "loss": 1.1873,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.09135399673735727,
112
+ "grad_norm": 0.154296875,
113
+ "learning_rate": 0.0001999782138253991,
114
+ "loss": 1.1684,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.09787928221859707,
119
+ "grad_norm": 0.15625,
120
+ "learning_rate": 0.00019996595979748037,
121
+ "loss": 1.2122,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.10440456769983687,
126
+ "grad_norm": 0.12158203125,
127
+ "learning_rate": 0.00019995098333206742,
128
+ "loss": 1.1772,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.11092985318107668,
133
+ "grad_norm": 0.07958984375,
134
+ "learning_rate": 0.00019993328483702393,
135
+ "loss": 1.1742,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.11745513866231648,
140
+ "grad_norm": 0.09326171875,
141
+ "learning_rate": 0.00019991286479434454,
142
+ "loss": 1.1791,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.12398042414355628,
147
+ "grad_norm": 0.11474609375,
148
+ "learning_rate": 0.00019988972376014142,
149
+ "loss": 1.1651,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.13050570962479607,
154
+ "grad_norm": 0.1572265625,
155
+ "learning_rate": 0.00019986386236462924,
156
+ "loss": 1.1874,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.1370309951060359,
161
+ "grad_norm": 0.12255859375,
162
+ "learning_rate": 0.00019983528131210812,
163
+ "loss": 1.1371,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.14355628058727568,
168
+ "grad_norm": 0.08544921875,
169
+ "learning_rate": 0.00019980398138094428,
170
+ "loss": 1.1725,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.1500815660685155,
175
+ "grad_norm": 0.07763671875,
176
+ "learning_rate": 0.00019976996342354898,
177
+ "loss": 1.1264,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.1566068515497553,
182
+ "grad_norm": 0.078125,
183
+ "learning_rate": 0.00019973322836635518,
184
+ "loss": 1.091,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.1631321370309951,
189
+ "grad_norm": 0.09423828125,
190
+ "learning_rate": 0.00019969377720979237,
191
+ "loss": 1.1636,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.16965742251223492,
196
+ "grad_norm": 0.1044921875,
197
+ "learning_rate": 0.00019965161102825945,
198
+ "loss": 1.1472,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.1761827079934747,
203
+ "grad_norm": 0.0751953125,
204
+ "learning_rate": 0.00019960673097009518,
205
+ "loss": 1.1212,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.18270799347471453,
210
+ "grad_norm": 0.072265625,
211
+ "learning_rate": 0.00019955913825754713,
212
+ "loss": 1.1466,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.18923327895595432,
217
+ "grad_norm": 0.0693359375,
218
+ "learning_rate": 0.0001995088341867384,
219
+ "loss": 1.1235,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.19575856443719414,
224
+ "grad_norm": 0.06787109375,
225
+ "learning_rate": 0.0001994558201276322,
226
+ "loss": 1.1123,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.20228384991843393,
231
+ "grad_norm": 0.07177734375,
232
+ "learning_rate": 0.0001994000975239946,
233
+ "loss": 1.1459,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.20880913539967375,
238
+ "grad_norm": 0.07470703125,
239
+ "learning_rate": 0.00019934166789335525,
240
+ "loss": 1.1231,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.21533442088091354,
245
+ "grad_norm": 0.06689453125,
246
+ "learning_rate": 0.00019928053282696596,
247
+ "loss": 1.1153,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.22185970636215335,
252
+ "grad_norm": 0.078125,
253
+ "learning_rate": 0.00019921669398975745,
254
+ "loss": 1.0979,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.22838499184339314,
259
+ "grad_norm": 0.07421875,
260
+ "learning_rate": 0.000199150153120294,
261
+ "loss": 1.0667,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.23491027732463296,
266
+ "grad_norm": 0.06689453125,
267
+ "learning_rate": 0.00019908091203072598,
268
+ "loss": 1.1144,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.24143556280587275,
273
+ "grad_norm": 0.07080078125,
274
+ "learning_rate": 0.00019900897260674073,
275
+ "loss": 1.104,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.24796084828711257,
280
+ "grad_norm": 0.06689453125,
281
+ "learning_rate": 0.00019893433680751103,
282
+ "loss": 1.1016,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.2544861337683524,
287
+ "grad_norm": 0.07275390625,
288
+ "learning_rate": 0.0001988570066656417,
289
+ "loss": 1.089,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.2544861337683524,
294
+ "eval_loss": 1.1131086349487305,
295
+ "eval_runtime": 236.8764,
296
+ "eval_samples_per_second": 1.798,
297
+ "eval_steps_per_second": 0.899,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.26101141924959215,
302
+ "grad_norm": 0.078125,
303
+ "learning_rate": 0.00019877698428711442,
304
+ "loss": 1.1207,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.26753670473083196,
309
+ "grad_norm": 0.06982421875,
310
+ "learning_rate": 0.00019869427185123027,
311
+ "loss": 1.1376,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.2740619902120718,
316
+ "grad_norm": 0.06982421875,
317
+ "learning_rate": 0.00019860887161055038,
318
+ "loss": 1.1,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.2805872756933116,
323
+ "grad_norm": 0.080078125,
324
+ "learning_rate": 0.00019852078589083466,
325
+ "loss": 1.1185,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.28711256117455136,
330
+ "grad_norm": 0.0732421875,
331
+ "learning_rate": 0.0001984300170909783,
332
+ "loss": 1.1282,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.2936378466557912,
337
+ "grad_norm": 0.0654296875,
338
+ "learning_rate": 0.00019833656768294662,
339
+ "loss": 1.1505,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.300163132137031,
344
+ "grad_norm": 0.06689453125,
345
+ "learning_rate": 0.0001982404402117077,
346
+ "loss": 1.1102,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.3066884176182708,
351
+ "grad_norm": 0.0712890625,
352
+ "learning_rate": 0.00019814163729516292,
353
+ "loss": 1.1254,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.3132137030995106,
358
+ "grad_norm": 0.0673828125,
359
+ "learning_rate": 0.0001980401616240759,
360
+ "loss": 1.0934,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.3197389885807504,
365
+ "grad_norm": 0.06689453125,
366
+ "learning_rate": 0.00019793601596199912,
367
+ "loss": 1.0792,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.3262642740619902,
372
+ "grad_norm": 0.07177734375,
373
+ "learning_rate": 0.00019782920314519856,
374
+ "loss": 1.0936,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.33278955954323003,
379
+ "grad_norm": 0.06884765625,
380
+ "learning_rate": 0.00019771972608257659,
381
+ "loss": 1.0636,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.33931484502446985,
386
+ "grad_norm": 0.0673828125,
387
+ "learning_rate": 0.00019760758775559274,
388
+ "loss": 1.0693,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3458401305057096,
393
+ "grad_norm": 0.06787109375,
394
+ "learning_rate": 0.00019749279121818235,
395
+ "loss": 1.0882,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3523654159869494,
400
+ "grad_norm": 0.0703125,
401
+ "learning_rate": 0.0001973753395966737,
402
+ "loss": 1.1066,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.35889070146818924,
407
+ "grad_norm": 0.0712890625,
408
+ "learning_rate": 0.00019725523608970255,
409
+ "loss": 1.049,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.36541598694942906,
414
+ "grad_norm": 0.06982421875,
415
+ "learning_rate": 0.00019713248396812524,
416
+ "loss": 1.1083,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3719412724306688,
421
+ "grad_norm": 0.072265625,
422
+ "learning_rate": 0.00019700708657492948,
423
+ "loss": 1.0854,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.37846655791190864,
428
+ "grad_norm": 0.07275390625,
429
+ "learning_rate": 0.0001968790473251434,
430
+ "loss": 1.0954,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.38499184339314846,
435
+ "grad_norm": 0.07373046875,
436
+ "learning_rate": 0.00019674836970574254,
437
+ "loss": 1.0833,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3915171288743883,
442
+ "grad_norm": 0.07275390625,
443
+ "learning_rate": 0.00019661505727555482,
444
+ "loss": 1.0945,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.39804241435562804,
449
+ "grad_norm": 0.07080078125,
450
+ "learning_rate": 0.0001964791136651637,
451
+ "loss": 1.07,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.40456769983686786,
456
+ "grad_norm": 0.07177734375,
457
+ "learning_rate": 0.00019634054257680923,
458
+ "loss": 1.0998,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4110929853181077,
463
+ "grad_norm": 0.0712890625,
464
+ "learning_rate": 0.0001961993477842873,
465
+ "loss": 1.0718,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4176182707993475,
470
+ "grad_norm": 0.078125,
471
+ "learning_rate": 0.0001960555331328468,
472
+ "loss": 1.0285,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.42414355628058725,
477
+ "grad_norm": 0.08203125,
478
+ "learning_rate": 0.00019590910253908494,
479
+ "loss": 1.0836,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.43066884176182707,
484
+ "grad_norm": 0.076171875,
485
+ "learning_rate": 0.0001957600599908406,
486
+ "loss": 1.0836,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4371941272430669,
491
+ "grad_norm": 0.07373046875,
492
+ "learning_rate": 0.00019560840954708565,
493
+ "loss": 1.0868,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4437194127243067,
498
+ "grad_norm": 0.06884765625,
499
+ "learning_rate": 0.0001954541553378145,
500
+ "loss": 1.115,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.45024469820554647,
505
+ "grad_norm": 0.0703125,
506
+ "learning_rate": 0.0001952973015639316,
507
+ "loss": 1.047,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.4567699836867863,
512
+ "grad_norm": 0.07373046875,
513
+ "learning_rate": 0.00019513785249713697,
514
+ "loss": 1.0878,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.4632952691680261,
519
+ "grad_norm": 0.07275390625,
520
+ "learning_rate": 0.00019497581247980992,
521
+ "loss": 1.0547,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.4698205546492659,
526
+ "grad_norm": 0.0732421875,
527
+ "learning_rate": 0.00019481118592489086,
528
+ "loss": 1.0907,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.4763458401305057,
533
+ "grad_norm": 0.0703125,
534
+ "learning_rate": 0.00019464397731576094,
535
+ "loss": 1.053,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4828711256117455,
540
+ "grad_norm": 0.07421875,
541
+ "learning_rate": 0.00019447419120612017,
542
+ "loss": 1.0768,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4893964110929853,
547
+ "grad_norm": 0.0732421875,
548
+ "learning_rate": 0.00019430183221986325,
549
+ "loss": 1.0599,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.49592169657422513,
554
+ "grad_norm": 0.076171875,
555
+ "learning_rate": 0.00019412690505095365,
556
+ "loss": 1.0721,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5024469820554649,
561
+ "grad_norm": 0.07666015625,
562
+ "learning_rate": 0.00019394941446329583,
563
+ "loss": 1.0802,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5089722675367048,
568
+ "grad_norm": 0.0771484375,
569
+ "learning_rate": 0.00019376936529060554,
570
+ "loss": 1.0475,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5089722675367048,
575
+ "eval_loss": 1.0718731880187988,
576
+ "eval_runtime": 236.7722,
577
+ "eval_samples_per_second": 1.799,
578
+ "eval_steps_per_second": 0.9,
579
+ "step": 78
580
+ },
581
+ {
582
+ "epoch": 0.5154975530179445,
583
+ "grad_norm": 0.072265625,
584
+ "learning_rate": 0.00019358676243627808,
585
+ "loss": 1.0706,
586
+ "step": 79
587
+ },
588
+ {
589
+ "epoch": 0.5220228384991843,
590
+ "grad_norm": 0.07568359375,
591
+ "learning_rate": 0.0001934016108732548,
592
+ "loss": 1.0679,
593
+ "step": 80
594
+ },
595
+ {
596
+ "epoch": 0.5285481239804242,
597
+ "grad_norm": 0.08056640625,
598
+ "learning_rate": 0.00019321391564388775,
599
+ "loss": 1.044,
600
+ "step": 81
601
+ },
602
+ {
603
+ "epoch": 0.5350734094616639,
604
+ "grad_norm": 0.078125,
605
+ "learning_rate": 0.00019302368185980217,
606
+ "loss": 1.0878,
607
+ "step": 82
608
+ },
609
+ {
610
+ "epoch": 0.5415986949429038,
611
+ "grad_norm": 0.08447265625,
612
+ "learning_rate": 0.00019283091470175754,
613
+ "loss": 1.0469,
614
+ "step": 83
615
+ },
616
+ {
617
+ "epoch": 0.5481239804241436,
618
+ "grad_norm": 0.07861328125,
619
+ "learning_rate": 0.00019263561941950622,
620
+ "loss": 1.0453,
621
+ "step": 84
622
+ },
623
+ {
624
+ "epoch": 0.5546492659053833,
625
+ "grad_norm": 0.08154296875,
626
+ "learning_rate": 0.00019243780133165067,
627
+ "loss": 1.0677,
628
+ "step": 85
629
+ },
630
+ {
631
+ "epoch": 0.5611745513866232,
632
+ "grad_norm": 0.08056640625,
633
+ "learning_rate": 0.00019223746582549853,
634
+ "loss": 1.0648,
635
+ "step": 86
636
+ },
637
+ {
638
+ "epoch": 0.567699836867863,
639
+ "grad_norm": 0.083984375,
640
+ "learning_rate": 0.00019203461835691594,
641
+ "loss": 1.0891,
642
+ "step": 87
643
+ },
644
+ {
645
+ "epoch": 0.5742251223491027,
646
+ "grad_norm": 0.08447265625,
647
+ "learning_rate": 0.00019182926445017893,
648
+ "loss": 1.0607,
649
+ "step": 88
650
+ },
651
+ {
652
+ "epoch": 0.5807504078303426,
653
+ "grad_norm": 0.078125,
654
+ "learning_rate": 0.00019162140969782292,
655
+ "loss": 1.0241,
656
+ "step": 89
657
+ },
658
+ {
659
+ "epoch": 0.5872756933115824,
660
+ "grad_norm": 0.08642578125,
661
+ "learning_rate": 0.00019141105976049053,
662
+ "loss": 1.0675,
663
+ "step": 90
664
+ },
665
+ {
666
+ "epoch": 0.5938009787928222,
667
+ "grad_norm": 0.08642578125,
668
+ "learning_rate": 0.00019119822036677738,
669
+ "loss": 1.0538,
670
+ "step": 91
671
+ },
672
+ {
673
+ "epoch": 0.600326264274062,
674
+ "grad_norm": 0.0751953125,
675
+ "learning_rate": 0.000190982897313076,
676
+ "loss": 1.0572,
677
+ "step": 92
678
+ },
679
+ {
680
+ "epoch": 0.6068515497553018,
681
+ "grad_norm": 0.076171875,
682
+ "learning_rate": 0.00019076509646341806,
683
+ "loss": 1.0372,
684
+ "step": 93
685
+ },
686
+ {
687
+ "epoch": 0.6133768352365416,
688
+ "grad_norm": 0.07861328125,
689
+ "learning_rate": 0.00019054482374931467,
690
+ "loss": 1.0693,
691
+ "step": 94
692
+ },
693
+ {
694
+ "epoch": 0.6199021207177814,
695
+ "grad_norm": 0.07861328125,
696
+ "learning_rate": 0.0001903220851695948,
697
+ "loss": 1.0726,
698
+ "step": 95
699
+ },
700
+ {
701
+ "epoch": 0.6264274061990212,
702
+ "grad_norm": 0.0791015625,
703
+ "learning_rate": 0.0001900968867902419,
704
+ "loss": 1.0543,
705
+ "step": 96
706
+ },
707
+ {
708
+ "epoch": 0.632952691680261,
709
+ "grad_norm": 0.08447265625,
710
+ "learning_rate": 0.00018986923474422884,
711
+ "loss": 1.0577,
712
+ "step": 97
713
+ },
714
+ {
715
+ "epoch": 0.6394779771615008,
716
+ "grad_norm": 0.08447265625,
717
+ "learning_rate": 0.0001896391352313506,
718
+ "loss": 1.0649,
719
+ "step": 98
720
+ },
721
+ {
722
+ "epoch": 0.6460032626427407,
723
+ "grad_norm": 0.08056640625,
724
+ "learning_rate": 0.0001894065945180558,
725
+ "loss": 1.0828,
726
+ "step": 99
727
+ },
728
+ {
729
+ "epoch": 0.6525285481239804,
730
+ "grad_norm": 0.07861328125,
731
+ "learning_rate": 0.0001891716189372757,
732
+ "loss": 1.0805,
733
+ "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6590538336052202,
737
+ "grad_norm": 0.07861328125,
738
+ "learning_rate": 0.0001889342148882519,
739
+ "loss": 1.0158,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6655791190864601,
744
+ "grad_norm": 0.08056640625,
745
+ "learning_rate": 0.00018869438883636214,
746
+ "loss": 1.0686,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6721044045676998,
751
+ "grad_norm": 0.07958984375,
752
+ "learning_rate": 0.000188452147312944,
753
+ "loss": 1.0498,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6786296900489397,
758
+ "grad_norm": 0.07861328125,
759
+ "learning_rate": 0.0001882074969151172,
760
+ "loss": 1.0783,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6851549755301795,
765
+ "grad_norm": 0.08056640625,
766
+ "learning_rate": 0.000187960444305604,
767
+ "loss": 0.9942,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6916802610114192,
772
+ "grad_norm": 0.0791015625,
773
+ "learning_rate": 0.00018771099621254746,
774
+ "loss": 1.0517,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.6982055464926591,
779
+ "grad_norm": 0.0810546875,
780
+ "learning_rate": 0.0001874591594293285,
781
+ "loss": 1.0619,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7047308319738989,
786
+ "grad_norm": 0.08251953125,
787
+ "learning_rate": 0.00018720494081438078,
788
+ "loss": 1.0584,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7112561174551386,
793
+ "grad_norm": 0.08740234375,
794
+ "learning_rate": 0.00018694834729100386,
795
+ "loss": 1.0466,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7177814029363785,
800
+ "grad_norm": 0.08349609375,
801
+ "learning_rate": 0.00018668938584717471,
802
+ "loss": 1.0391,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7243066884176182,
807
+ "grad_norm": 0.08251953125,
808
+ "learning_rate": 0.00018642806353535754,
809
+ "loss": 1.0331,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7308319738988581,
814
+ "grad_norm": 0.0859375,
815
+ "learning_rate": 0.00018616438747231148,
816
+ "loss": 1.0671,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7373572593800979,
821
+ "grad_norm": 0.087890625,
822
+ "learning_rate": 0.00018589836483889687,
823
+ "loss": 1.0525,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7438825448613376,
828
+ "grad_norm": 0.08935546875,
829
+ "learning_rate": 0.0001856300028798798,
830
+ "loss": 1.0182,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7504078303425775,
835
+ "grad_norm": 0.08349609375,
836
+ "learning_rate": 0.00018535930890373466,
837
+ "loss": 1.0566,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7569331158238173,
842
+ "grad_norm": 0.080078125,
843
+ "learning_rate": 0.00018508629028244519,
844
+ "loss": 1.0316,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.763458401305057,
849
+ "grad_norm": 0.09033203125,
850
+ "learning_rate": 0.0001848109544513037,
851
+ "loss": 1.0362,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.763458401305057,
856
+ "eval_loss": 1.0525188446044922,
857
+ "eval_runtime": 236.6432,
858
+ "eval_samples_per_second": 1.8,
859
+ "eval_steps_per_second": 0.9,
860
+ "step": 117
861
+ },
862
+ {
863
+ "epoch": 0.7699836867862969,
864
+ "grad_norm": 0.08544921875,
865
+ "learning_rate": 0.00018453330890870855,
866
+ "loss": 1.0141,
867
+ "step": 118
868
+ },
869
+ {
870
+ "epoch": 0.7765089722675367,
871
+ "grad_norm": 0.08203125,
872
+ "learning_rate": 0.00018425336121596,
873
+ "loss": 1.0464,
874
+ "step": 119
875
+ },
876
+ {
877
+ "epoch": 0.7830342577487766,
878
+ "grad_norm": 0.0830078125,
879
+ "learning_rate": 0.00018397111899705419,
880
+ "loss": 1.0278,
881
+ "step": 120
882
+ },
883
+ {
884
+ "epoch": 0.7895595432300163,
885
+ "grad_norm": 0.080078125,
886
+ "learning_rate": 0.00018368658993847566,
887
+ "loss": 1.0439,
888
+ "step": 121
889
+ },
890
+ {
891
+ "epoch": 0.7960848287112561,
892
+ "grad_norm": 0.08251953125,
893
+ "learning_rate": 0.0001833997817889878,
894
+ "loss": 1.053,
895
+ "step": 122
896
+ },
897
+ {
898
+ "epoch": 0.802610114192496,
899
+ "grad_norm": 0.08642578125,
900
+ "learning_rate": 0.0001831107023594221,
901
+ "loss": 1.0447,
902
+ "step": 123
903
+ },
904
+ {
905
+ "epoch": 0.8091353996737357,
906
+ "grad_norm": 0.08349609375,
907
+ "learning_rate": 0.00018281935952246518,
908
+ "loss": 1.0347,
909
+ "step": 124
910
+ },
911
+ {
912
+ "epoch": 0.8156606851549756,
913
+ "grad_norm": 0.0810546875,
914
+ "learning_rate": 0.00018252576121244456,
915
+ "loss": 1.0628,
916
+ "step": 125
917
+ },
918
+ {
919
+ "epoch": 0.8221859706362153,
920
+ "grad_norm": 0.08056640625,
921
+ "learning_rate": 0.00018222991542511246,
922
+ "loss": 1.0112,
923
+ "step": 126
924
+ },
925
+ {
926
+ "epoch": 0.8287112561174551,
927
+ "grad_norm": 0.08984375,
928
+ "learning_rate": 0.0001819318302174281,
929
+ "loss": 1.0657,
930
+ "step": 127
931
+ },
932
+ {
933
+ "epoch": 0.835236541598695,
934
+ "grad_norm": 0.08837890625,
935
+ "learning_rate": 0.00018163151370733838,
936
+ "loss": 1.0936,
937
+ "step": 128
938
+ },
939
+ {
940
+ "epoch": 0.8417618270799347,
941
+ "grad_norm": 0.0869140625,
942
+ "learning_rate": 0.00018132897407355657,
943
+ "loss": 1.0519,
944
+ "step": 129
945
+ },
946
+ {
947
+ "epoch": 0.8482871125611745,
948
+ "grad_norm": 0.08447265625,
949
+ "learning_rate": 0.00018102421955533974,
950
+ "loss": 1.018,
951
+ "step": 130
952
+ },
953
+ {
954
+ "epoch": 0.8548123980424144,
955
+ "grad_norm": 0.08349609375,
956
+ "learning_rate": 0.00018071725845226436,
957
+ "loss": 0.9982,
958
+ "step": 131
959
+ },
960
+ {
961
+ "epoch": 0.8613376835236541,
962
+ "grad_norm": 0.0966796875,
963
+ "learning_rate": 0.0001804080991240003,
964
+ "loss": 1.0522,
965
+ "step": 132
966
+ },
967
+ {
968
+ "epoch": 0.867862969004894,
969
+ "grad_norm": 0.0830078125,
970
+ "learning_rate": 0.000180096749990083,
971
+ "loss": 1.0149,
972
+ "step": 133
973
+ },
974
+ {
975
+ "epoch": 0.8743882544861338,
976
+ "grad_norm": 0.0810546875,
977
+ "learning_rate": 0.00017978321952968434,
978
+ "loss": 1.0096,
979
+ "step": 134
980
+ },
981
+ {
982
+ "epoch": 0.8809135399673735,
983
+ "grad_norm": 0.09765625,
984
+ "learning_rate": 0.00017946751628138174,
985
+ "loss": 1.0551,
986
+ "step": 135
987
+ },
988
+ {
989
+ "epoch": 0.8874388254486134,
990
+ "grad_norm": 0.083984375,
991
+ "learning_rate": 0.00017914964884292544,
992
+ "loss": 1.0384,
993
+ "step": 136
994
+ },
995
+ {
996
+ "epoch": 0.8939641109298532,
997
+ "grad_norm": 0.09326171875,
998
+ "learning_rate": 0.0001788296258710045,
999
+ "loss": 1.0341,
1000
+ "step": 137
1001
+ },
1002
+ {
1003
+ "epoch": 0.9004893964110929,
1004
+ "grad_norm": 0.0859375,
1005
+ "learning_rate": 0.0001785074560810111,
1006
+ "loss": 1.0162,
1007
+ "step": 138
1008
+ },
1009
+ {
1010
+ "epoch": 0.9070146818923328,
1011
+ "grad_norm": 0.0849609375,
1012
+ "learning_rate": 0.000178183148246803,
1013
+ "loss": 1.0332,
1014
+ "step": 139
1015
+ },
1016
+ {
1017
+ "epoch": 0.9135399673735726,
1018
+ "grad_norm": 0.08251953125,
1019
+ "learning_rate": 0.00017785671120046473,
1020
+ "loss": 1.0219,
1021
+ "step": 140
1022
+ },
1023
+ {
1024
+ "epoch": 0.9200652528548124,
1025
+ "grad_norm": 0.080078125,
1026
+ "learning_rate": 0.00017752815383206705,
1027
+ "loss": 1.0557,
1028
+ "step": 141
1029
+ },
1030
+ {
1031
+ "epoch": 0.9265905383360522,
1032
+ "grad_norm": 0.0849609375,
1033
+ "learning_rate": 0.0001771974850894248,
1034
+ "loss": 1.075,
1035
+ "step": 142
1036
+ },
1037
+ {
1038
+ "epoch": 0.933115823817292,
1039
+ "grad_norm": 0.087890625,
1040
+ "learning_rate": 0.0001768647139778532,
1041
+ "loss": 1.0458,
1042
+ "step": 143
1043
+ },
1044
+ {
1045
+ "epoch": 0.9396411092985318,
1046
+ "grad_norm": 0.0830078125,
1047
+ "learning_rate": 0.00017652984955992277,
1048
+ "loss": 1.054,
1049
+ "step": 144
1050
+ },
1051
+ {
1052
+ "epoch": 0.9461663947797716,
1053
+ "grad_norm": 0.08154296875,
1054
+ "learning_rate": 0.0001761929009552122,
1055
+ "loss": 1.0297,
1056
+ "step": 145
1057
+ },
1058
+ {
1059
+ "epoch": 0.9526916802610114,
1060
+ "grad_norm": 0.0849609375,
1061
+ "learning_rate": 0.00017585387734006034,
1062
+ "loss": 1.0299,
1063
+ "step": 146
1064
+ },
1065
+ {
1066
+ "epoch": 0.9592169657422512,
1067
+ "grad_norm": 0.0810546875,
1068
+ "learning_rate": 0.00017551278794731607,
1069
+ "loss": 1.0578,
1070
+ "step": 147
1071
+ },
1072
+ {
1073
+ "epoch": 0.965742251223491,
1074
+ "grad_norm": 0.0859375,
1075
+ "learning_rate": 0.00017516964206608696,
1076
+ "loss": 1.0362,
1077
+ "step": 148
1078
+ },
1079
+ {
1080
+ "epoch": 0.9722675367047309,
1081
+ "grad_norm": 0.09130859375,
1082
+ "learning_rate": 0.00017482444904148617,
1083
+ "loss": 1.0356,
1084
+ "step": 149
1085
+ },
1086
+ {
1087
+ "epoch": 0.9787928221859706,
1088
+ "grad_norm": 0.0869140625,
1089
+ "learning_rate": 0.0001744772182743782,
1090
+ "loss": 1.038,
1091
+ "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.9853181076672104,
1095
+ "grad_norm": 0.0859375,
1096
+ "learning_rate": 0.00017412795922112253,
1097
+ "loss": 1.0445,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.9918433931484503,
1102
+ "grad_norm": 0.08544921875,
1103
+ "learning_rate": 0.0001737766813933164,
1104
+ "loss": 1.0524,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.99836867862969,
1109
+ "grad_norm": 0.08837890625,
1110
+ "learning_rate": 0.00017342339435753553,
1111
+ "loss": 1.0517,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 1.0048939641109298,
1116
+ "grad_norm": 0.083984375,
1117
+ "learning_rate": 0.00017306810773507376,
1118
+ "loss": 1.0033,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 1.0114192495921697,
1123
+ "grad_norm": 0.09033203125,
1124
+ "learning_rate": 0.00017271083120168102,
1125
+ "loss": 1.0477,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 1.0048939641109298,
1130
+ "grad_norm": 0.13671875,
1131
+ "learning_rate": 0.00017235157448729967,
1132
+ "loss": 1.0619,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 1.0048939641109298,
1137
+ "eval_loss": 1.0388679504394531,
1138
+ "eval_runtime": 236.7713,
1139
+ "eval_samples_per_second": 1.799,
1140
+ "eval_steps_per_second": 0.9,
1141
+ "step": 156
1142
+ },
1143
+ {
1144
+ "epoch": 1.0114192495921697,
1145
+ "grad_norm": 0.08740234375,
1146
+ "learning_rate": 0.0001719903473757996,
1147
+ "loss": 1.0131,
1148
+ "step": 157
1149
+ },
1150
+ {
1151
+ "epoch": 1.0179445350734095,
1152
+ "grad_norm": 0.0927734375,
1153
+ "learning_rate": 0.0001716271597047119,
1154
+ "loss": 0.9966,
1155
+ "step": 158
1156
+ },
1157
+ {
1158
+ "epoch": 1.0244698205546492,
1159
+ "grad_norm": 0.0947265625,
1160
+ "learning_rate": 0.0001712620213649608,
1161
+ "loss": 0.9817,
1162
+ "step": 159
1163
+ },
1164
+ {
1165
+ "epoch": 1.030995106035889,
1166
+ "grad_norm": 0.0888671875,
1167
+ "learning_rate": 0.00017089494230059432,
1168
+ "loss": 1.0036,
1169
+ "step": 160
1170
+ },
1171
+ {
1172
+ "epoch": 1.037520391517129,
1173
+ "grad_norm": 0.09716796875,
1174
+ "learning_rate": 0.0001705259325085135,
1175
+ "loss": 1.0318,
1176
+ "step": 161
1177
+ },
1178
+ {
1179
+ "epoch": 1.0440456769983686,
1180
+ "grad_norm": 0.09814453125,
1181
+ "learning_rate": 0.00017015500203820022,
1182
+ "loss": 1.0106,
1183
+ "step": 162
1184
+ },
1185
+ {
1186
+ "epoch": 1.0505709624796085,
1187
+ "grad_norm": 0.09521484375,
1188
+ "learning_rate": 0.0001697821609914432,
1189
+ "loss": 1.0178,
1190
+ "step": 163
1191
+ },
1192
+ {
1193
+ "epoch": 1.0570962479608483,
1194
+ "grad_norm": 0.09033203125,
1195
+ "learning_rate": 0.0001694074195220634,
1196
+ "loss": 0.9909,
1197
+ "step": 164
1198
+ },
1199
+ {
1200
+ "epoch": 1.0636215334420882,
1201
+ "grad_norm": 0.08740234375,
1202
+ "learning_rate": 0.000169030787835637,
1203
+ "loss": 0.9916,
1204
+ "step": 165
1205
+ },
1206
+ {
1207
+ "epoch": 1.0701468189233279,
1208
+ "grad_norm": 0.09130859375,
1209
+ "learning_rate": 0.00016865227618921788,
1210
+ "loss": 1.0101,
1211
+ "step": 166
1212
+ },
1213
+ {
1214
+ "epoch": 1.0766721044045677,
1215
+ "grad_norm": 0.0908203125,
1216
+ "learning_rate": 0.00016827189489105788,
1217
+ "loss": 0.9966,
1218
+ "step": 167
1219
+ },
1220
+ {
1221
+ "epoch": 1.0831973898858076,
1222
+ "grad_norm": 0.09521484375,
1223
+ "learning_rate": 0.00016788965430032638,
1224
+ "loss": 1.0048,
1225
+ "step": 168
1226
+ },
1227
+ {
1228
+ "epoch": 1.0897226753670473,
1229
+ "grad_norm": 0.09521484375,
1230
+ "learning_rate": 0.00016750556482682805,
1231
+ "loss": 1.0074,
1232
+ "step": 169
1233
+ },
1234
+ {
1235
+ "epoch": 1.0962479608482871,
1236
+ "grad_norm": 0.08935546875,
1237
+ "learning_rate": 0.00016711963693071943,
1238
+ "loss": 0.9762,
1239
+ "step": 170
1240
+ },
1241
+ {
1242
+ "epoch": 1.102773246329527,
1243
+ "grad_norm": 0.09619140625,
1244
+ "learning_rate": 0.00016673188112222394,
1245
+ "loss": 1.0044,
1246
+ "step": 171
1247
+ },
1248
+ {
1249
+ "epoch": 1.1092985318107667,
1250
+ "grad_norm": 0.091796875,
1251
+ "learning_rate": 0.00016634230796134576,
1252
+ "loss": 0.9972,
1253
+ "step": 172
1254
+ },
1255
+ {
1256
+ "epoch": 1.1158238172920065,
1257
+ "grad_norm": 0.09228515625,
1258
+ "learning_rate": 0.0001659509280575821,
1259
+ "loss": 1.0308,
1260
+ "step": 173
1261
+ },
1262
+ {
1263
+ "epoch": 1.1223491027732464,
1264
+ "grad_norm": 0.0927734375,
1265
+ "learning_rate": 0.0001655577520696346,
1266
+ "loss": 0.996,
1267
+ "step": 174
1268
+ },
1269
+ {
1270
+ "epoch": 1.128874388254486,
1271
+ "grad_norm": 0.0947265625,
1272
+ "learning_rate": 0.00016516279070511854,
1273
+ "loss": 0.9671,
1274
+ "step": 175
1275
+ },
1276
+ {
1277
+ "epoch": 1.135399673735726,
1278
+ "grad_norm": 0.09228515625,
1279
+ "learning_rate": 0.00016476605472027172,
1280
+ "loss": 1.0121,
1281
+ "step": 176
1282
+ },
1283
+ {
1284
+ "epoch": 1.1419249592169658,
1285
+ "grad_norm": 0.0927734375,
1286
+ "learning_rate": 0.00016436755491966115,
1287
+ "loss": 1.0132,
1288
+ "step": 177
1289
+ },
1290
+ {
1291
+ "epoch": 1.1484502446982057,
1292
+ "grad_norm": 0.09375,
1293
+ "learning_rate": 0.00016396730215588915,
1294
+ "loss": 1.0146,
1295
+ "step": 178
1296
+ },
1297
+ {
1298
+ "epoch": 1.1549755301794453,
1299
+ "grad_norm": 0.09521484375,
1300
+ "learning_rate": 0.0001635653073292975,
1301
+ "loss": 0.9911,
1302
+ "step": 179
1303
+ },
1304
+ {
1305
+ "epoch": 1.1615008156606852,
1306
+ "grad_norm": 0.09716796875,
1307
+ "learning_rate": 0.0001631615813876707,
1308
+ "loss": 1.0125,
1309
+ "step": 180
1310
+ },
1311
+ {
1312
+ "epoch": 1.1680261011419248,
1313
+ "grad_norm": 0.09521484375,
1314
+ "learning_rate": 0.0001627561353259379,
1315
+ "loss": 1.0162,
1316
+ "step": 181
1317
+ },
1318
+ {
1319
+ "epoch": 1.1745513866231647,
1320
+ "grad_norm": 0.09716796875,
1321
+ "learning_rate": 0.00016234898018587337,
1322
+ "loss": 0.995,
1323
+ "step": 182
1324
+ },
1325
+ {
1326
+ "epoch": 1.1810766721044046,
1327
+ "grad_norm": 0.09326171875,
1328
+ "learning_rate": 0.00016194012705579572,
1329
+ "loss": 0.9839,
1330
+ "step": 183
1331
+ },
1332
+ {
1333
+ "epoch": 1.1876019575856445,
1334
+ "grad_norm": 0.09716796875,
1335
+ "learning_rate": 0.00016152958707026614,
1336
+ "loss": 1.0107,
1337
+ "step": 184
1338
+ },
1339
+ {
1340
+ "epoch": 1.1941272430668841,
1341
+ "grad_norm": 0.09326171875,
1342
+ "learning_rate": 0.00016111737140978494,
1343
+ "loss": 0.9715,
1344
+ "step": 185
1345
+ },
1346
+ {
1347
+ "epoch": 1.200652528548124,
1348
+ "grad_norm": 0.09326171875,
1349
+ "learning_rate": 0.00016070349130048724,
1350
+ "loss": 0.9751,
1351
+ "step": 186
1352
+ },
1353
+ {
1354
+ "epoch": 1.2071778140293639,
1355
+ "grad_norm": 0.09375,
1356
+ "learning_rate": 0.00016028795801383718,
1357
+ "loss": 0.9845,
1358
+ "step": 187
1359
+ },
1360
+ {
1361
+ "epoch": 1.2137030995106035,
1362
+ "grad_norm": 0.10302734375,
1363
+ "learning_rate": 0.0001598707828663209,
1364
+ "loss": 0.9604,
1365
+ "step": 188
1366
+ },
1367
+ {
1368
+ "epoch": 1.2202283849918434,
1369
+ "grad_norm": 0.09765625,
1370
+ "learning_rate": 0.00015945197721913833,
1371
+ "loss": 0.9715,
1372
+ "step": 189
1373
+ },
1374
+ {
1375
+ "epoch": 1.2267536704730833,
1376
+ "grad_norm": 0.0966796875,
1377
+ "learning_rate": 0.00015903155247789404,
1378
+ "loss": 1.0156,
1379
+ "step": 190
1380
+ },
1381
+ {
1382
+ "epoch": 1.233278955954323,
1383
+ "grad_norm": 0.09814453125,
1384
+ "learning_rate": 0.00015860952009228625,
1385
+ "loss": 1.0044,
1386
+ "step": 191
1387
+ },
1388
+ {
1389
+ "epoch": 1.2398042414355628,
1390
+ "grad_norm": 0.099609375,
1391
+ "learning_rate": 0.0001581858915557953,
1392
+ "loss": 0.9849,
1393
+ "step": 192
1394
+ },
1395
+ {
1396
+ "epoch": 1.2463295269168027,
1397
+ "grad_norm": 0.09619140625,
1398
+ "learning_rate": 0.0001577606784053705,
1399
+ "loss": 1.0007,
1400
+ "step": 193
1401
+ },
1402
+ {
1403
+ "epoch": 1.2528548123980423,
1404
+ "grad_norm": 0.0947265625,
1405
+ "learning_rate": 0.00015733389222111592,
1406
+ "loss": 0.9682,
1407
+ "step": 194
1408
+ },
1409
+ {
1410
+ "epoch": 1.2593800978792822,
1411
+ "grad_norm": 0.0966796875,
1412
+ "learning_rate": 0.00015690554462597522,
1413
+ "loss": 1.0165,
1414
+ "step": 195
1415
+ },
1416
+ {
1417
+ "epoch": 1.2593800978792822,
1418
+ "eval_loss": 1.0322120189666748,
1419
+ "eval_runtime": 236.6694,
1420
+ "eval_samples_per_second": 1.8,
1421
+ "eval_steps_per_second": 0.9,
1422
+ "step": 195
1423
+ },
1424
+ {
1425
+ "epoch": 1.265905383360522,
1426
+ "grad_norm": 0.1005859375,
1427
+ "learning_rate": 0.00015647564728541485,
1428
+ "loss": 1.0376,
1429
+ "step": 196
1430
+ },
1431
+ {
1432
+ "epoch": 1.272430668841762,
1433
+ "grad_norm": 0.09619140625,
1434
+ "learning_rate": 0.0001560442119071065,
1435
+ "loss": 1.0066,
1436
+ "step": 197
1437
+ },
1438
+ {
1439
+ "epoch": 1.2789559543230016,
1440
+ "grad_norm": 0.095703125,
1441
+ "learning_rate": 0.00015561125024060826,
1442
+ "loss": 0.9872,
1443
+ "step": 198
1444
+ },
1445
+ {
1446
+ "epoch": 1.2854812398042414,
1447
+ "grad_norm": 0.0966796875,
1448
+ "learning_rate": 0.0001551767740770446,
1449
+ "loss": 1.0079,
1450
+ "step": 199
1451
+ },
1452
+ {
1453
+ "epoch": 1.2920065252854813,
1454
+ "grad_norm": 0.09765625,
1455
+ "learning_rate": 0.00015474079524878525,
1456
+ "loss": 0.9865,
1457
+ "step": 200
1458
+ },
1459
+ {
1460
+ "epoch": 1.298531810766721,
1461
+ "grad_norm": 0.09423828125,
1462
+ "learning_rate": 0.000154303325629123,
1463
+ "loss": 0.9747,
1464
+ "step": 201
1465
+ },
1466
+ {
1467
+ "epoch": 1.3050570962479608,
1468
+ "grad_norm": 0.09814453125,
1469
+ "learning_rate": 0.0001538643771319503,
1470
+ "loss": 1.0119,
1471
+ "step": 202
1472
+ },
1473
+ {
1474
+ "epoch": 1.3115823817292007,
1475
+ "grad_norm": 0.095703125,
1476
+ "learning_rate": 0.00015342396171143488,
1477
+ "loss": 0.9815,
1478
+ "step": 203
1479
+ },
1480
+ {
1481
+ "epoch": 1.3181076672104406,
1482
+ "grad_norm": 0.09912109375,
1483
+ "learning_rate": 0.00015298209136169403,
1484
+ "loss": 0.9772,
1485
+ "step": 204
1486
+ },
1487
+ {
1488
+ "epoch": 1.3246329526916802,
1489
+ "grad_norm": 0.095703125,
1490
+ "learning_rate": 0.00015253877811646817,
1491
+ "loss": 0.9804,
1492
+ "step": 205
1493
+ },
1494
+ {
1495
+ "epoch": 1.3311582381729201,
1496
+ "grad_norm": 0.09716796875,
1497
+ "learning_rate": 0.00015209403404879303,
1498
+ "loss": 0.9457,
1499
+ "step": 206
1500
+ },
1501
+ {
1502
+ "epoch": 1.3376835236541598,
1503
+ "grad_norm": 0.1005859375,
1504
+ "learning_rate": 0.0001516478712706708,
1505
+ "loss": 0.9951,
1506
+ "step": 207
1507
+ },
1508
+ {
1509
+ "epoch": 1.3442088091353996,
1510
+ "grad_norm": 0.09521484375,
1511
+ "learning_rate": 0.00015120030193274027,
1512
+ "loss": 1.0085,
1513
+ "step": 208
1514
+ },
1515
+ {
1516
+ "epoch": 1.3507340946166395,
1517
+ "grad_norm": 0.09619140625,
1518
+ "learning_rate": 0.00015075133822394613,
1519
+ "loss": 1.0105,
1520
+ "step": 209
1521
+ },
1522
+ {
1523
+ "epoch": 1.3572593800978794,
1524
+ "grad_norm": 0.1025390625,
1525
+ "learning_rate": 0.00015030099237120674,
1526
+ "loss": 1.005,
1527
+ "step": 210
1528
+ },
1529
+ {
1530
+ "epoch": 1.363784665579119,
1531
+ "grad_norm": 0.0986328125,
1532
+ "learning_rate": 0.00014984927663908137,
1533
+ "loss": 0.9703,
1534
+ "step": 211
1535
+ },
1536
+ {
1537
+ "epoch": 1.370309951060359,
1538
+ "grad_norm": 0.0947265625,
1539
+ "learning_rate": 0.00014939620332943604,
1540
+ "loss": 0.9747,
1541
+ "step": 212
1542
+ },
1543
+ {
1544
+ "epoch": 1.3768352365415986,
1545
+ "grad_norm": 0.09716796875,
1546
+ "learning_rate": 0.00014894178478110857,
1547
+ "loss": 0.9785,
1548
+ "step": 213
1549
+ },
1550
+ {
1551
+ "epoch": 1.3833605220228384,
1552
+ "grad_norm": 0.09814453125,
1553
+ "learning_rate": 0.00014848603336957251,
1554
+ "loss": 1.0329,
1555
+ "step": 214
1556
+ },
1557
+ {
1558
+ "epoch": 1.3898858075040783,
1559
+ "grad_norm": 0.09423828125,
1560
+ "learning_rate": 0.00014802896150660022,
1561
+ "loss": 0.9429,
1562
+ "step": 215
1563
+ },
1564
+ {
1565
+ "epoch": 1.3964110929853182,
1566
+ "grad_norm": 0.099609375,
1567
+ "learning_rate": 0.00014757058163992464,
1568
+ "loss": 0.9578,
1569
+ "step": 216
1570
+ },
1571
+ {
1572
+ "epoch": 1.4029363784665578,
1573
+ "grad_norm": 0.1025390625,
1574
+ "learning_rate": 0.00014711090625290057,
1575
+ "loss": 1.0216,
1576
+ "step": 217
1577
+ },
1578
+ {
1579
+ "epoch": 1.4094616639477977,
1580
+ "grad_norm": 0.10986328125,
1581
+ "learning_rate": 0.0001466499478641644,
1582
+ "loss": 0.9792,
1583
+ "step": 218
1584
+ },
1585
+ {
1586
+ "epoch": 1.4159869494290376,
1587
+ "grad_norm": 0.095703125,
1588
+ "learning_rate": 0.00014618771902729342,
1589
+ "loss": 1.0001,
1590
+ "step": 219
1591
+ },
1592
+ {
1593
+ "epoch": 1.4225122349102772,
1594
+ "grad_norm": 0.1044921875,
1595
+ "learning_rate": 0.00014572423233046386,
1596
+ "loss": 1.0057,
1597
+ "step": 220
1598
+ },
1599
+ {
1600
+ "epoch": 1.429037520391517,
1601
+ "grad_norm": 0.09912109375,
1602
+ "learning_rate": 0.000145259500396108,
1603
+ "loss": 0.9698,
1604
+ "step": 221
1605
+ },
1606
+ {
1607
+ "epoch": 1.435562805872757,
1608
+ "grad_norm": 0.09814453125,
1609
+ "learning_rate": 0.00014479353588057052,
1610
+ "loss": 0.9533,
1611
+ "step": 222
1612
+ },
1613
+ {
1614
+ "epoch": 1.4420880913539968,
1615
+ "grad_norm": 0.103515625,
1616
+ "learning_rate": 0.00014432635147376376,
1617
+ "loss": 0.9686,
1618
+ "step": 223
1619
+ },
1620
+ {
1621
+ "epoch": 1.4486133768352365,
1622
+ "grad_norm": 0.0986328125,
1623
+ "learning_rate": 0.00014385795989882221,
1624
+ "loss": 1.0278,
1625
+ "step": 224
1626
+ },
1627
+ {
1628
+ "epoch": 1.4551386623164764,
1629
+ "grad_norm": 0.103515625,
1630
+ "learning_rate": 0.00014338837391175582,
1631
+ "loss": 1.0013,
1632
+ "step": 225
1633
+ },
1634
+ {
1635
+ "epoch": 1.461663947797716,
1636
+ "grad_norm": 0.10400390625,
1637
+ "learning_rate": 0.00014291760630110288,
1638
+ "loss": 1.0053,
1639
+ "step": 226
1640
+ },
1641
+ {
1642
+ "epoch": 1.468189233278956,
1643
+ "grad_norm": 0.10302734375,
1644
+ "learning_rate": 0.00014244566988758152,
1645
+ "loss": 1.0216,
1646
+ "step": 227
1647
+ },
1648
+ {
1649
+ "epoch": 1.4747145187601958,
1650
+ "grad_norm": 0.09912109375,
1651
+ "learning_rate": 0.0001419725775237406,
1652
+ "loss": 0.992,
1653
+ "step": 228
1654
+ },
1655
+ {
1656
+ "epoch": 1.4812398042414356,
1657
+ "grad_norm": 0.099609375,
1658
+ "learning_rate": 0.00014149834209360986,
1659
+ "loss": 1.0053,
1660
+ "step": 229
1661
+ },
1662
+ {
1663
+ "epoch": 1.4877650897226753,
1664
+ "grad_norm": 0.103515625,
1665
+ "learning_rate": 0.0001410229765123487,
1666
+ "loss": 0.9948,
1667
+ "step": 230
1668
+ },
1669
+ {
1670
+ "epoch": 1.4942903752039152,
1671
+ "grad_norm": 0.09912109375,
1672
+ "learning_rate": 0.00014054649372589482,
1673
+ "loss": 0.9717,
1674
+ "step": 231
1675
+ },
1676
+ {
1677
+ "epoch": 1.5008156606851548,
1678
+ "grad_norm": 0.0986328125,
1679
+ "learning_rate": 0.00014006890671061143,
1680
+ "loss": 0.9805,
1681
+ "step": 232
1682
+ },
1683
+ {
1684
+ "epoch": 1.5073409461663947,
1685
+ "grad_norm": 0.10400390625,
1686
+ "learning_rate": 0.00013959022847293391,
1687
+ "loss": 0.9826,
1688
+ "step": 233
1689
+ },
1690
+ {
1691
+ "epoch": 1.5138662316476346,
1692
+ "grad_norm": 0.09765625,
1693
+ "learning_rate": 0.0001391104720490156,
1694
+ "loss": 0.9394,
1695
+ "step": 234
1696
+ },
1697
+ {
1698
+ "epoch": 1.5138662316476346,
1699
+ "eval_loss": 1.0245814323425293,
1700
+ "eval_runtime": 236.6376,
1701
+ "eval_samples_per_second": 1.8,
1702
+ "eval_steps_per_second": 0.9,
1703
+ "step": 234
1704
+ },
1705
+ {
1706
+ "epoch": 1.5203915171288744,
1707
+ "grad_norm": 0.10107421875,
1708
+ "learning_rate": 0.0001386296505043728,
1709
+ "loss": 0.9857,
1710
+ "step": 235
1711
+ },
1712
+ {
1713
+ "epoch": 1.5269168026101143,
1714
+ "grad_norm": 0.099609375,
1715
+ "learning_rate": 0.000138147776933529,
1716
+ "loss": 0.997,
1717
+ "step": 236
1718
+ },
1719
+ {
1720
+ "epoch": 1.533442088091354,
1721
+ "grad_norm": 0.107421875,
1722
+ "learning_rate": 0.00013766486445965795,
1723
+ "loss": 0.9927,
1724
+ "step": 237
1725
+ },
1726
+ {
1727
+ "epoch": 1.5399673735725938,
1728
+ "grad_norm": 0.095703125,
1729
+ "learning_rate": 0.00013718092623422686,
1730
+ "loss": 0.9745,
1731
+ "step": 238
1732
+ },
1733
+ {
1734
+ "epoch": 1.5464926590538335,
1735
+ "grad_norm": 0.1005859375,
1736
+ "learning_rate": 0.00013669597543663762,
1737
+ "loss": 0.9842,
1738
+ "step": 239
1739
+ },
1740
+ {
1741
+ "epoch": 1.5530179445350734,
1742
+ "grad_norm": 0.099609375,
1743
+ "learning_rate": 0.00013621002527386834,
1744
+ "loss": 1.0102,
1745
+ "step": 240
1746
+ },
1747
+ {
1748
+ "epoch": 1.5595432300163132,
1749
+ "grad_norm": 0.1015625,
1750
+ "learning_rate": 0.0001357230889801133,
1751
+ "loss": 0.9389,
1752
+ "step": 241
1753
+ },
1754
+ {
1755
+ "epoch": 1.566068515497553,
1756
+ "grad_norm": 0.099609375,
1757
+ "learning_rate": 0.00013523517981642286,
1758
+ "loss": 1.0044,
1759
+ "step": 242
1760
+ },
1761
+ {
1762
+ "epoch": 1.572593800978793,
1763
+ "grad_norm": 0.09716796875,
1764
+ "learning_rate": 0.0001347463110703422,
1765
+ "loss": 0.9698,
1766
+ "step": 243
1767
+ },
1768
+ {
1769
+ "epoch": 1.5791190864600326,
1770
+ "grad_norm": 0.1015625,
1771
+ "learning_rate": 0.00013425649605554928,
1772
+ "loss": 0.9858,
1773
+ "step": 244
1774
+ },
1775
+ {
1776
+ "epoch": 1.5856443719412723,
1777
+ "grad_norm": 0.1396484375,
1778
+ "learning_rate": 0.00013376574811149253,
1779
+ "loss": 0.9513,
1780
+ "step": 245
1781
+ },
1782
+ {
1783
+ "epoch": 1.5921696574225122,
1784
+ "grad_norm": 0.10009765625,
1785
+ "learning_rate": 0.00013327408060302738,
1786
+ "loss": 0.9943,
1787
+ "step": 246
1788
+ },
1789
+ {
1790
+ "epoch": 1.598694942903752,
1791
+ "grad_norm": 0.0986328125,
1792
+ "learning_rate": 0.00013278150692005243,
1793
+ "loss": 0.9933,
1794
+ "step": 247
1795
+ },
1796
+ {
1797
+ "epoch": 1.605220228384992,
1798
+ "grad_norm": 0.1005859375,
1799
+ "learning_rate": 0.00013228804047714463,
1800
+ "loss": 0.9865,
1801
+ "step": 248
1802
+ },
1803
+ {
1804
+ "epoch": 1.6117455138662318,
1805
+ "grad_norm": 0.09716796875,
1806
+ "learning_rate": 0.00013179369471319404,
1807
+ "loss": 0.9466,
1808
+ "step": 249
1809
+ },
1810
+ {
1811
+ "epoch": 1.6182707993474714,
1812
+ "grad_norm": 0.0986328125,
1813
+ "learning_rate": 0.0001312984830910379,
1814
+ "loss": 0.9684,
1815
+ "step": 250
1816
+ },
1817
+ {
1818
+ "epoch": 1.6247960848287113,
1819
+ "grad_norm": 0.10205078125,
1820
+ "learning_rate": 0.00013080241909709387,
1821
+ "loss": 1.004,
1822
+ "step": 251
1823
+ },
1824
+ {
1825
+ "epoch": 1.631321370309951,
1826
+ "grad_norm": 0.10400390625,
1827
+ "learning_rate": 0.00013030551624099287,
1828
+ "loss": 0.9964,
1829
+ "step": 252
1830
+ },
1831
+ {
1832
+ "epoch": 1.6378466557911908,
1833
+ "grad_norm": 0.10888671875,
1834
+ "learning_rate": 0.000129807788055211,
1835
+ "loss": 0.9745,
1836
+ "step": 253
1837
+ },
1838
+ {
1839
+ "epoch": 1.6443719412724307,
1840
+ "grad_norm": 0.1044921875,
1841
+ "learning_rate": 0.00012930924809470115,
1842
+ "loss": 1.0074,
1843
+ "step": 254
1844
+ },
1845
+ {
1846
+ "epoch": 1.6508972267536706,
1847
+ "grad_norm": 0.1064453125,
1848
+ "learning_rate": 0.00012880990993652377,
1849
+ "loss": 0.9842,
1850
+ "step": 255
1851
+ },
1852
+ {
1853
+ "epoch": 1.6574225122349104,
1854
+ "grad_norm": 0.1025390625,
1855
+ "learning_rate": 0.00012830978717947718,
1856
+ "loss": 0.9699,
1857
+ "step": 256
1858
+ },
1859
+ {
1860
+ "epoch": 1.66394779771615,
1861
+ "grad_norm": 0.10009765625,
1862
+ "learning_rate": 0.00012780889344372718,
1863
+ "loss": 0.9892,
1864
+ "step": 257
1865
+ },
1866
+ {
1867
+ "epoch": 1.6704730831973897,
1868
+ "grad_norm": 0.1025390625,
1869
+ "learning_rate": 0.00012730724237043615,
1870
+ "loss": 0.9804,
1871
+ "step": 258
1872
+ },
1873
+ {
1874
+ "epoch": 1.6769983686786296,
1875
+ "grad_norm": 0.09814453125,
1876
+ "learning_rate": 0.0001268048476213914,
1877
+ "loss": 0.9873,
1878
+ "step": 259
1879
+ },
1880
+ {
1881
+ "epoch": 1.6835236541598695,
1882
+ "grad_norm": 0.09765625,
1883
+ "learning_rate": 0.0001263017228786334,
1884
+ "loss": 0.9737,
1885
+ "step": 260
1886
+ },
1887
+ {
1888
+ "epoch": 1.6900489396411094,
1889
+ "grad_norm": 0.10107421875,
1890
+ "learning_rate": 0.00012579788184408295,
1891
+ "loss": 1.0064,
1892
+ "step": 261
1893
+ },
1894
+ {
1895
+ "epoch": 1.6965742251223492,
1896
+ "grad_norm": 0.10888671875,
1897
+ "learning_rate": 0.00012529333823916807,
1898
+ "loss": 0.9745,
1899
+ "step": 262
1900
+ },
1901
+ {
1902
+ "epoch": 1.7030995106035889,
1903
+ "grad_norm": 0.1005859375,
1904
+ "learning_rate": 0.0001247881058044504,
1905
+ "loss": 0.9988,
1906
+ "step": 263
1907
+ },
1908
+ {
1909
+ "epoch": 1.7096247960848288,
1910
+ "grad_norm": 0.10595703125,
1911
+ "learning_rate": 0.00012428219829925083,
1912
+ "loss": 1.0021,
1913
+ "step": 264
1914
+ },
1915
+ {
1916
+ "epoch": 1.7161500815660684,
1917
+ "grad_norm": 0.09814453125,
1918
+ "learning_rate": 0.00012377562950127493,
1919
+ "loss": 0.9681,
1920
+ "step": 265
1921
+ },
1922
+ {
1923
+ "epoch": 1.7226753670473083,
1924
+ "grad_norm": 0.107421875,
1925
+ "learning_rate": 0.00012326841320623767,
1926
+ "loss": 0.9968,
1927
+ "step": 266
1928
+ },
1929
+ {
1930
+ "epoch": 1.7292006525285482,
1931
+ "grad_norm": 0.10791015625,
1932
+ "learning_rate": 0.00012276056322748778,
1933
+ "loss": 1.0235,
1934
+ "step": 267
1935
+ },
1936
+ {
1937
+ "epoch": 1.735725938009788,
1938
+ "grad_norm": 0.10498046875,
1939
+ "learning_rate": 0.00012225209339563145,
1940
+ "loss": 0.977,
1941
+ "step": 268
1942
+ },
1943
+ {
1944
+ "epoch": 1.7422512234910277,
1945
+ "grad_norm": 0.10302734375,
1946
+ "learning_rate": 0.00012174301755815571,
1947
+ "loss": 1.0021,
1948
+ "step": 269
1949
+ },
1950
+ {
1951
+ "epoch": 1.7487765089722676,
1952
+ "grad_norm": 0.09716796875,
1953
+ "learning_rate": 0.0001212333495790514,
1954
+ "loss": 0.9781,
1955
+ "step": 270
1956
+ },
1957
+ {
1958
+ "epoch": 1.7553017944535072,
1959
+ "grad_norm": 0.10546875,
1960
+ "learning_rate": 0.00012072310333843544,
1961
+ "loss": 0.9901,
1962
+ "step": 271
1963
+ },
1964
+ {
1965
+ "epoch": 1.761827079934747,
1966
+ "grad_norm": 0.10205078125,
1967
+ "learning_rate": 0.00012021229273217302,
1968
+ "loss": 0.9675,
1969
+ "step": 272
1970
+ },
1971
+ {
1972
+ "epoch": 1.768352365415987,
1973
+ "grad_norm": 0.10546875,
1974
+ "learning_rate": 0.00011970093167149905,
1975
+ "loss": 0.999,
1976
+ "step": 273
1977
+ },
1978
+ {
1979
+ "epoch": 1.768352365415987,
1980
+ "eval_loss": 1.0181984901428223,
1981
+ "eval_runtime": 236.6668,
1982
+ "eval_samples_per_second": 1.8,
1983
+ "eval_steps_per_second": 0.9,
1984
+ "step": 273
1985
+ },
1986
+ {
1987
+ "epoch": 1.7748776508972268,
1988
+ "grad_norm": 0.1005859375,
1989
+ "learning_rate": 0.00011918903408263924,
1990
+ "loss": 0.9798,
1991
+ "step": 274
1992
+ },
1993
+ {
1994
+ "epoch": 1.7814029363784667,
1995
+ "grad_norm": 0.103515625,
1996
+ "learning_rate": 0.000118676613906431,
1997
+ "loss": 0.9826,
1998
+ "step": 275
1999
+ },
2000
+ {
2001
+ "epoch": 1.7879282218597063,
2002
+ "grad_norm": 0.0986328125,
2003
+ "learning_rate": 0.00011816368509794364,
2004
+ "loss": 0.9781,
2005
+ "step": 276
2006
+ },
2007
+ {
2008
+ "epoch": 1.7944535073409462,
2009
+ "grad_norm": 0.099609375,
2010
+ "learning_rate": 0.00011765026162609847,
2011
+ "loss": 0.9811,
2012
+ "step": 277
2013
+ },
2014
+ {
2015
+ "epoch": 1.8009787928221859,
2016
+ "grad_norm": 0.10498046875,
2017
+ "learning_rate": 0.00011713635747328818,
2018
+ "loss": 0.9859,
2019
+ "step": 278
2020
+ },
2021
+ {
2022
+ "epoch": 1.8075040783034257,
2023
+ "grad_norm": 0.10107421875,
2024
+ "learning_rate": 0.00011662198663499619,
2025
+ "loss": 0.9644,
2026
+ "step": 279
2027
+ },
2028
+ {
2029
+ "epoch": 1.8140293637846656,
2030
+ "grad_norm": 0.1025390625,
2031
+ "learning_rate": 0.0001161071631194155,
2032
+ "loss": 0.9931,
2033
+ "step": 280
2034
+ },
2035
+ {
2036
+ "epoch": 1.8205546492659055,
2037
+ "grad_norm": 0.09716796875,
2038
+ "learning_rate": 0.00011559190094706714,
2039
+ "loss": 1.0061,
2040
+ "step": 281
2041
+ },
2042
+ {
2043
+ "epoch": 1.8270799347471451,
2044
+ "grad_norm": 0.1015625,
2045
+ "learning_rate": 0.00011507621415041837,
2046
+ "loss": 0.9511,
2047
+ "step": 282
2048
+ },
2049
+ {
2050
+ "epoch": 1.833605220228385,
2051
+ "grad_norm": 0.10888671875,
2052
+ "learning_rate": 0.00011456011677350051,
2053
+ "loss": 0.9875,
2054
+ "step": 283
2055
+ },
2056
+ {
2057
+ "epoch": 1.8401305057096247,
2058
+ "grad_norm": 0.099609375,
2059
+ "learning_rate": 0.00011404362287152646,
2060
+ "loss": 0.9577,
2061
+ "step": 284
2062
+ },
2063
+ {
2064
+ "epoch": 1.8466557911908645,
2065
+ "grad_norm": 0.10205078125,
2066
+ "learning_rate": 0.00011352674651050796,
2067
+ "loss": 1.0018,
2068
+ "step": 285
2069
+ },
2070
+ {
2071
+ "epoch": 1.8531810766721044,
2072
+ "grad_norm": 0.1025390625,
2073
+ "learning_rate": 0.00011300950176687255,
2074
+ "loss": 0.9738,
2075
+ "step": 286
2076
+ },
2077
+ {
2078
+ "epoch": 1.8597063621533443,
2079
+ "grad_norm": 0.10009765625,
2080
+ "learning_rate": 0.00011249190272708008,
2081
+ "loss": 0.9635,
2082
+ "step": 287
2083
+ },
2084
+ {
2085
+ "epoch": 1.8662316476345842,
2086
+ "grad_norm": 0.10302734375,
2087
+ "learning_rate": 0.00011197396348723923,
2088
+ "loss": 0.9783,
2089
+ "step": 288
2090
+ },
2091
+ {
2092
+ "epoch": 1.8727569331158238,
2093
+ "grad_norm": 0.1123046875,
2094
+ "learning_rate": 0.0001114556981527236,
2095
+ "loss": 0.9895,
2096
+ "step": 289
2097
+ },
2098
+ {
2099
+ "epoch": 1.8792822185970635,
2100
+ "grad_norm": 0.10009765625,
2101
+ "learning_rate": 0.00011093712083778746,
2102
+ "loss": 0.9993,
2103
+ "step": 290
2104
+ },
2105
+ {
2106
+ "epoch": 1.8858075040783033,
2107
+ "grad_norm": 0.1123046875,
2108
+ "learning_rate": 0.00011041824566518146,
2109
+ "loss": 0.9842,
2110
+ "step": 291
2111
+ },
2112
+ {
2113
+ "epoch": 1.8923327895595432,
2114
+ "grad_norm": 0.10498046875,
2115
+ "learning_rate": 0.00010989908676576807,
2116
+ "loss": 0.9693,
2117
+ "step": 292
2118
+ },
2119
+ {
2120
+ "epoch": 1.898858075040783,
2121
+ "grad_norm": 0.0986328125,
2122
+ "learning_rate": 0.00010937965827813661,
2123
+ "loss": 0.9838,
2124
+ "step": 293
2125
+ },
2126
+ {
2127
+ "epoch": 1.905383360522023,
2128
+ "grad_norm": 0.1064453125,
2129
+ "learning_rate": 0.00010885997434821831,
2130
+ "loss": 0.9992,
2131
+ "step": 294
2132
+ },
2133
+ {
2134
+ "epoch": 1.9119086460032626,
2135
+ "grad_norm": 0.09912109375,
2136
+ "learning_rate": 0.00010834004912890092,
2137
+ "loss": 1.0066,
2138
+ "step": 295
2139
+ },
2140
+ {
2141
+ "epoch": 1.9184339314845025,
2142
+ "grad_norm": 0.10009765625,
2143
+ "learning_rate": 0.00010781989677964355,
2144
+ "loss": 0.9737,
2145
+ "step": 296
2146
+ },
2147
+ {
2148
+ "epoch": 1.9249592169657421,
2149
+ "grad_norm": 0.10546875,
2150
+ "learning_rate": 0.00010729953146609076,
2151
+ "loss": 0.9913,
2152
+ "step": 297
2153
+ },
2154
+ {
2155
+ "epoch": 1.931484502446982,
2156
+ "grad_norm": 0.10546875,
2157
+ "learning_rate": 0.00010677896735968693,
2158
+ "loss": 0.9835,
2159
+ "step": 298
2160
+ },
2161
+ {
2162
+ "epoch": 1.9380097879282219,
2163
+ "grad_norm": 0.1015625,
2164
+ "learning_rate": 0.00010625821863729036,
2165
+ "loss": 0.967,
2166
+ "step": 299
2167
+ },
2168
+ {
2169
+ "epoch": 1.9445350734094617,
2170
+ "grad_norm": 0.1015625,
2171
+ "learning_rate": 0.00010573729948078699,
2172
+ "loss": 0.9724,
2173
+ "step": 300
2174
+ },
2175
+ {
2176
+ "epoch": 1.9510603588907016,
2177
+ "grad_norm": 0.1005859375,
2178
+ "learning_rate": 0.00010521622407670439,
2179
+ "loss": 0.9732,
2180
+ "step": 301
2181
+ },
2182
+ {
2183
+ "epoch": 1.9575856443719413,
2184
+ "grad_norm": 0.1005859375,
2185
+ "learning_rate": 0.00010469500661582536,
2186
+ "loss": 1.0138,
2187
+ "step": 302
2188
+ },
2189
+ {
2190
+ "epoch": 1.964110929853181,
2191
+ "grad_norm": 0.1015625,
2192
+ "learning_rate": 0.00010417366129280133,
2193
+ "loss": 0.9903,
2194
+ "step": 303
2195
+ },
2196
+ {
2197
+ "epoch": 1.9706362153344208,
2198
+ "grad_norm": 0.099609375,
2199
+ "learning_rate": 0.0001036522023057659,
2200
+ "loss": 0.962,
2201
+ "step": 304
2202
+ },
2203
+ {
2204
+ "epoch": 1.9771615008156607,
2205
+ "grad_norm": 0.10302734375,
2206
+ "learning_rate": 0.00010313064385594822,
2207
+ "loss": 0.9793,
2208
+ "step": 305
2209
+ },
2210
+ {
2211
+ "epoch": 1.9836867862969005,
2212
+ "grad_norm": 0.103515625,
2213
+ "learning_rate": 0.0001026090001472861,
2214
+ "loss": 0.975,
2215
+ "step": 306
2216
+ }
2217
+ ],
2218
+ "logging_steps": 1,
2219
+ "max_steps": 612,
2220
+ "num_input_tokens_seen": 0,
2221
+ "num_train_epochs": 4,
2222
+ "save_steps": 153,
2223
+ "stateful_callbacks": {
2224
+ "TrainerControl": {
2225
+ "args": {
2226
+ "should_epoch_stop": false,
2227
+ "should_evaluate": false,
2228
+ "should_log": false,
2229
+ "should_save": true,
2230
+ "should_training_stop": false
2231
+ },
2232
+ "attributes": {}
2233
+ }
2234
+ },
2235
+ "total_flos": 9.127437882233979e+17,
2236
+ "train_batch_size": 2,
2237
+ "trial_name": null,
2238
+ "trial_params": null
2239
+ }
checkpoint306/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998c86e0068ec82450c4b585a291b75939d4efaf9fcfdeab3730d3a755504c16
3
+ size 5944
checkpoint459/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint459/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP",
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
+ "o_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint459/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9969cfadcad9649f9ffb90c58d71cbd66189b9c4b4c7654d4bee5b50bff7740a
3
+ size 167832688
checkpoint459/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840f3c002d1e300fae3ae00cffaa638c0612394ac34cbc034a2bad001324f27c
3
+ size 168625172
checkpoint459/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba836741f4591c9a45a772d2f2a2edd307d3754d8b8aeb17899e82806b84a9f
3
+ size 14244
checkpoint459/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd5dc264d85d3ba7d3f6cdf51a3b954fabe59a3def2344dff82d4b07df94de9
3
+ size 1064
checkpoint459/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": "<|eot_id|>",
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
+ }
checkpoint459/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint459/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint459/trainer_state.json ADDED
@@ -0,0 +1,3342 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.967373572593801,
5
+ "eval_steps": 39,
6
+ "global_step": 459,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0065252854812398045,
13
+ "grad_norm": 0.23828125,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.3184,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0065252854812398045,
20
+ "eval_loss": 1.3192611932754517,
21
+ "eval_runtime": 235.1739,
22
+ "eval_samples_per_second": 1.811,
23
+ "eval_steps_per_second": 0.906,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.013050570962479609,
28
+ "grad_norm": 0.2373046875,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.3213,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01957585644371941,
35
+ "grad_norm": 0.2373046875,
36
+ "learning_rate": 6e-05,
37
+ "loss": 1.3232,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.026101141924959218,
42
+ "grad_norm": 0.259765625,
43
+ "learning_rate": 8e-05,
44
+ "loss": 1.3418,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.03262642740619902,
49
+ "grad_norm": 0.275390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.2712,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.03915171288743882,
56
+ "grad_norm": 0.2412109375,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.2682,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.04567699836867863,
63
+ "grad_norm": 0.1015625,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.2672,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.052202283849918436,
70
+ "grad_norm": 0.44140625,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.2337,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.05872756933115824,
77
+ "grad_norm": 0.51171875,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.3138,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.06525285481239804,
84
+ "grad_norm": 0.326171875,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.238,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.07177814029363784,
91
+ "grad_norm": 0.138671875,
92
+ "learning_rate": 0.0001999986383177335,
93
+ "loss": 1.2244,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.07830342577487764,
98
+ "grad_norm": 0.07666015625,
99
+ "learning_rate": 0.0001999945533080175,
100
+ "loss": 1.1796,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.08482871125611746,
105
+ "grad_norm": 0.1171875,
106
+ "learning_rate": 0.0001999877450821018,
107
+ "loss": 1.1873,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.09135399673735727,
112
+ "grad_norm": 0.154296875,
113
+ "learning_rate": 0.0001999782138253991,
114
+ "loss": 1.1684,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.09787928221859707,
119
+ "grad_norm": 0.15625,
120
+ "learning_rate": 0.00019996595979748037,
121
+ "loss": 1.2122,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.10440456769983687,
126
+ "grad_norm": 0.12158203125,
127
+ "learning_rate": 0.00019995098333206742,
128
+ "loss": 1.1772,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.11092985318107668,
133
+ "grad_norm": 0.07958984375,
134
+ "learning_rate": 0.00019993328483702393,
135
+ "loss": 1.1742,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.11745513866231648,
140
+ "grad_norm": 0.09326171875,
141
+ "learning_rate": 0.00019991286479434454,
142
+ "loss": 1.1791,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.12398042414355628,
147
+ "grad_norm": 0.11474609375,
148
+ "learning_rate": 0.00019988972376014142,
149
+ "loss": 1.1651,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.13050570962479607,
154
+ "grad_norm": 0.1572265625,
155
+ "learning_rate": 0.00019986386236462924,
156
+ "loss": 1.1874,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.1370309951060359,
161
+ "grad_norm": 0.12255859375,
162
+ "learning_rate": 0.00019983528131210812,
163
+ "loss": 1.1371,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.14355628058727568,
168
+ "grad_norm": 0.08544921875,
169
+ "learning_rate": 0.00019980398138094428,
170
+ "loss": 1.1725,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.1500815660685155,
175
+ "grad_norm": 0.07763671875,
176
+ "learning_rate": 0.00019976996342354898,
177
+ "loss": 1.1264,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.1566068515497553,
182
+ "grad_norm": 0.078125,
183
+ "learning_rate": 0.00019973322836635518,
184
+ "loss": 1.091,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.1631321370309951,
189
+ "grad_norm": 0.09423828125,
190
+ "learning_rate": 0.00019969377720979237,
191
+ "loss": 1.1636,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.16965742251223492,
196
+ "grad_norm": 0.1044921875,
197
+ "learning_rate": 0.00019965161102825945,
198
+ "loss": 1.1472,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.1761827079934747,
203
+ "grad_norm": 0.0751953125,
204
+ "learning_rate": 0.00019960673097009518,
205
+ "loss": 1.1212,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.18270799347471453,
210
+ "grad_norm": 0.072265625,
211
+ "learning_rate": 0.00019955913825754713,
212
+ "loss": 1.1466,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.18923327895595432,
217
+ "grad_norm": 0.0693359375,
218
+ "learning_rate": 0.0001995088341867384,
219
+ "loss": 1.1235,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.19575856443719414,
224
+ "grad_norm": 0.06787109375,
225
+ "learning_rate": 0.0001994558201276322,
226
+ "loss": 1.1123,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.20228384991843393,
231
+ "grad_norm": 0.07177734375,
232
+ "learning_rate": 0.0001994000975239946,
233
+ "loss": 1.1459,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.20880913539967375,
238
+ "grad_norm": 0.07470703125,
239
+ "learning_rate": 0.00019934166789335525,
240
+ "loss": 1.1231,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.21533442088091354,
245
+ "grad_norm": 0.06689453125,
246
+ "learning_rate": 0.00019928053282696596,
247
+ "loss": 1.1153,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.22185970636215335,
252
+ "grad_norm": 0.078125,
253
+ "learning_rate": 0.00019921669398975745,
254
+ "loss": 1.0979,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.22838499184339314,
259
+ "grad_norm": 0.07421875,
260
+ "learning_rate": 0.000199150153120294,
261
+ "loss": 1.0667,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.23491027732463296,
266
+ "grad_norm": 0.06689453125,
267
+ "learning_rate": 0.00019908091203072598,
268
+ "loss": 1.1144,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.24143556280587275,
273
+ "grad_norm": 0.07080078125,
274
+ "learning_rate": 0.00019900897260674073,
275
+ "loss": 1.104,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.24796084828711257,
280
+ "grad_norm": 0.06689453125,
281
+ "learning_rate": 0.00019893433680751103,
282
+ "loss": 1.1016,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.2544861337683524,
287
+ "grad_norm": 0.07275390625,
288
+ "learning_rate": 0.0001988570066656417,
289
+ "loss": 1.089,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.2544861337683524,
294
+ "eval_loss": 1.1131086349487305,
295
+ "eval_runtime": 236.8764,
296
+ "eval_samples_per_second": 1.798,
297
+ "eval_steps_per_second": 0.899,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.26101141924959215,
302
+ "grad_norm": 0.078125,
303
+ "learning_rate": 0.00019877698428711442,
304
+ "loss": 1.1207,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.26753670473083196,
309
+ "grad_norm": 0.06982421875,
310
+ "learning_rate": 0.00019869427185123027,
311
+ "loss": 1.1376,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.2740619902120718,
316
+ "grad_norm": 0.06982421875,
317
+ "learning_rate": 0.00019860887161055038,
318
+ "loss": 1.1,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.2805872756933116,
323
+ "grad_norm": 0.080078125,
324
+ "learning_rate": 0.00019852078589083466,
325
+ "loss": 1.1185,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.28711256117455136,
330
+ "grad_norm": 0.0732421875,
331
+ "learning_rate": 0.0001984300170909783,
332
+ "loss": 1.1282,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.2936378466557912,
337
+ "grad_norm": 0.0654296875,
338
+ "learning_rate": 0.00019833656768294662,
339
+ "loss": 1.1505,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.300163132137031,
344
+ "grad_norm": 0.06689453125,
345
+ "learning_rate": 0.0001982404402117077,
346
+ "loss": 1.1102,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.3066884176182708,
351
+ "grad_norm": 0.0712890625,
352
+ "learning_rate": 0.00019814163729516292,
353
+ "loss": 1.1254,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.3132137030995106,
358
+ "grad_norm": 0.0673828125,
359
+ "learning_rate": 0.0001980401616240759,
360
+ "loss": 1.0934,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.3197389885807504,
365
+ "grad_norm": 0.06689453125,
366
+ "learning_rate": 0.00019793601596199912,
367
+ "loss": 1.0792,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.3262642740619902,
372
+ "grad_norm": 0.07177734375,
373
+ "learning_rate": 0.00019782920314519856,
374
+ "loss": 1.0936,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.33278955954323003,
379
+ "grad_norm": 0.06884765625,
380
+ "learning_rate": 0.00019771972608257659,
381
+ "loss": 1.0636,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.33931484502446985,
386
+ "grad_norm": 0.0673828125,
387
+ "learning_rate": 0.00019760758775559274,
388
+ "loss": 1.0693,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3458401305057096,
393
+ "grad_norm": 0.06787109375,
394
+ "learning_rate": 0.00019749279121818235,
395
+ "loss": 1.0882,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3523654159869494,
400
+ "grad_norm": 0.0703125,
401
+ "learning_rate": 0.0001973753395966737,
402
+ "loss": 1.1066,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.35889070146818924,
407
+ "grad_norm": 0.0712890625,
408
+ "learning_rate": 0.00019725523608970255,
409
+ "loss": 1.049,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.36541598694942906,
414
+ "grad_norm": 0.06982421875,
415
+ "learning_rate": 0.00019713248396812524,
416
+ "loss": 1.1083,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3719412724306688,
421
+ "grad_norm": 0.072265625,
422
+ "learning_rate": 0.00019700708657492948,
423
+ "loss": 1.0854,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.37846655791190864,
428
+ "grad_norm": 0.07275390625,
429
+ "learning_rate": 0.0001968790473251434,
430
+ "loss": 1.0954,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.38499184339314846,
435
+ "grad_norm": 0.07373046875,
436
+ "learning_rate": 0.00019674836970574254,
437
+ "loss": 1.0833,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3915171288743883,
442
+ "grad_norm": 0.07275390625,
443
+ "learning_rate": 0.00019661505727555482,
444
+ "loss": 1.0945,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.39804241435562804,
449
+ "grad_norm": 0.07080078125,
450
+ "learning_rate": 0.0001964791136651637,
451
+ "loss": 1.07,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.40456769983686786,
456
+ "grad_norm": 0.07177734375,
457
+ "learning_rate": 0.00019634054257680923,
458
+ "loss": 1.0998,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4110929853181077,
463
+ "grad_norm": 0.0712890625,
464
+ "learning_rate": 0.0001961993477842873,
465
+ "loss": 1.0718,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4176182707993475,
470
+ "grad_norm": 0.078125,
471
+ "learning_rate": 0.0001960555331328468,
472
+ "loss": 1.0285,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.42414355628058725,
477
+ "grad_norm": 0.08203125,
478
+ "learning_rate": 0.00019590910253908494,
479
+ "loss": 1.0836,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.43066884176182707,
484
+ "grad_norm": 0.076171875,
485
+ "learning_rate": 0.0001957600599908406,
486
+ "loss": 1.0836,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4371941272430669,
491
+ "grad_norm": 0.07373046875,
492
+ "learning_rate": 0.00019560840954708565,
493
+ "loss": 1.0868,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4437194127243067,
498
+ "grad_norm": 0.06884765625,
499
+ "learning_rate": 0.0001954541553378145,
500
+ "loss": 1.115,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.45024469820554647,
505
+ "grad_norm": 0.0703125,
506
+ "learning_rate": 0.0001952973015639316,
507
+ "loss": 1.047,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.4567699836867863,
512
+ "grad_norm": 0.07373046875,
513
+ "learning_rate": 0.00019513785249713697,
514
+ "loss": 1.0878,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.4632952691680261,
519
+ "grad_norm": 0.07275390625,
520
+ "learning_rate": 0.00019497581247980992,
521
+ "loss": 1.0547,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.4698205546492659,
526
+ "grad_norm": 0.0732421875,
527
+ "learning_rate": 0.00019481118592489086,
528
+ "loss": 1.0907,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.4763458401305057,
533
+ "grad_norm": 0.0703125,
534
+ "learning_rate": 0.00019464397731576094,
535
+ "loss": 1.053,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4828711256117455,
540
+ "grad_norm": 0.07421875,
541
+ "learning_rate": 0.00019447419120612017,
542
+ "loss": 1.0768,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4893964110929853,
547
+ "grad_norm": 0.0732421875,
548
+ "learning_rate": 0.00019430183221986325,
549
+ "loss": 1.0599,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.49592169657422513,
554
+ "grad_norm": 0.076171875,
555
+ "learning_rate": 0.00019412690505095365,
556
+ "loss": 1.0721,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5024469820554649,
561
+ "grad_norm": 0.07666015625,
562
+ "learning_rate": 0.00019394941446329583,
563
+ "loss": 1.0802,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5089722675367048,
568
+ "grad_norm": 0.0771484375,
569
+ "learning_rate": 0.00019376936529060554,
570
+ "loss": 1.0475,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5089722675367048,
575
+ "eval_loss": 1.0718731880187988,
576
+ "eval_runtime": 236.7722,
577
+ "eval_samples_per_second": 1.799,
578
+ "eval_steps_per_second": 0.9,
579
+ "step": 78
580
+ },
581
+ {
582
+ "epoch": 0.5154975530179445,
583
+ "grad_norm": 0.072265625,
584
+ "learning_rate": 0.00019358676243627808,
585
+ "loss": 1.0706,
586
+ "step": 79
587
+ },
588
+ {
589
+ "epoch": 0.5220228384991843,
590
+ "grad_norm": 0.07568359375,
591
+ "learning_rate": 0.0001934016108732548,
592
+ "loss": 1.0679,
593
+ "step": 80
594
+ },
595
+ {
596
+ "epoch": 0.5285481239804242,
597
+ "grad_norm": 0.08056640625,
598
+ "learning_rate": 0.00019321391564388775,
599
+ "loss": 1.044,
600
+ "step": 81
601
+ },
602
+ {
603
+ "epoch": 0.5350734094616639,
604
+ "grad_norm": 0.078125,
605
+ "learning_rate": 0.00019302368185980217,
606
+ "loss": 1.0878,
607
+ "step": 82
608
+ },
609
+ {
610
+ "epoch": 0.5415986949429038,
611
+ "grad_norm": 0.08447265625,
612
+ "learning_rate": 0.00019283091470175754,
613
+ "loss": 1.0469,
614
+ "step": 83
615
+ },
616
+ {
617
+ "epoch": 0.5481239804241436,
618
+ "grad_norm": 0.07861328125,
619
+ "learning_rate": 0.00019263561941950622,
620
+ "loss": 1.0453,
621
+ "step": 84
622
+ },
623
+ {
624
+ "epoch": 0.5546492659053833,
625
+ "grad_norm": 0.08154296875,
626
+ "learning_rate": 0.00019243780133165067,
627
+ "loss": 1.0677,
628
+ "step": 85
629
+ },
630
+ {
631
+ "epoch": 0.5611745513866232,
632
+ "grad_norm": 0.08056640625,
633
+ "learning_rate": 0.00019223746582549853,
634
+ "loss": 1.0648,
635
+ "step": 86
636
+ },
637
+ {
638
+ "epoch": 0.567699836867863,
639
+ "grad_norm": 0.083984375,
640
+ "learning_rate": 0.00019203461835691594,
641
+ "loss": 1.0891,
642
+ "step": 87
643
+ },
644
+ {
645
+ "epoch": 0.5742251223491027,
646
+ "grad_norm": 0.08447265625,
647
+ "learning_rate": 0.00019182926445017893,
648
+ "loss": 1.0607,
649
+ "step": 88
650
+ },
651
+ {
652
+ "epoch": 0.5807504078303426,
653
+ "grad_norm": 0.078125,
654
+ "learning_rate": 0.00019162140969782292,
655
+ "loss": 1.0241,
656
+ "step": 89
657
+ },
658
+ {
659
+ "epoch": 0.5872756933115824,
660
+ "grad_norm": 0.08642578125,
661
+ "learning_rate": 0.00019141105976049053,
662
+ "loss": 1.0675,
663
+ "step": 90
664
+ },
665
+ {
666
+ "epoch": 0.5938009787928222,
667
+ "grad_norm": 0.08642578125,
668
+ "learning_rate": 0.00019119822036677738,
669
+ "loss": 1.0538,
670
+ "step": 91
671
+ },
672
+ {
673
+ "epoch": 0.600326264274062,
674
+ "grad_norm": 0.0751953125,
675
+ "learning_rate": 0.000190982897313076,
676
+ "loss": 1.0572,
677
+ "step": 92
678
+ },
679
+ {
680
+ "epoch": 0.6068515497553018,
681
+ "grad_norm": 0.076171875,
682
+ "learning_rate": 0.00019076509646341806,
683
+ "loss": 1.0372,
684
+ "step": 93
685
+ },
686
+ {
687
+ "epoch": 0.6133768352365416,
688
+ "grad_norm": 0.07861328125,
689
+ "learning_rate": 0.00019054482374931467,
690
+ "loss": 1.0693,
691
+ "step": 94
692
+ },
693
+ {
694
+ "epoch": 0.6199021207177814,
695
+ "grad_norm": 0.07861328125,
696
+ "learning_rate": 0.0001903220851695948,
697
+ "loss": 1.0726,
698
+ "step": 95
699
+ },
700
+ {
701
+ "epoch": 0.6264274061990212,
702
+ "grad_norm": 0.0791015625,
703
+ "learning_rate": 0.0001900968867902419,
704
+ "loss": 1.0543,
705
+ "step": 96
706
+ },
707
+ {
708
+ "epoch": 0.632952691680261,
709
+ "grad_norm": 0.08447265625,
710
+ "learning_rate": 0.00018986923474422884,
711
+ "loss": 1.0577,
712
+ "step": 97
713
+ },
714
+ {
715
+ "epoch": 0.6394779771615008,
716
+ "grad_norm": 0.08447265625,
717
+ "learning_rate": 0.0001896391352313506,
718
+ "loss": 1.0649,
719
+ "step": 98
720
+ },
721
+ {
722
+ "epoch": 0.6460032626427407,
723
+ "grad_norm": 0.08056640625,
724
+ "learning_rate": 0.0001894065945180558,
725
+ "loss": 1.0828,
726
+ "step": 99
727
+ },
728
+ {
729
+ "epoch": 0.6525285481239804,
730
+ "grad_norm": 0.07861328125,
731
+ "learning_rate": 0.0001891716189372757,
732
+ "loss": 1.0805,
733
+ "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6590538336052202,
737
+ "grad_norm": 0.07861328125,
738
+ "learning_rate": 0.0001889342148882519,
739
+ "loss": 1.0158,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6655791190864601,
744
+ "grad_norm": 0.08056640625,
745
+ "learning_rate": 0.00018869438883636214,
746
+ "loss": 1.0686,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6721044045676998,
751
+ "grad_norm": 0.07958984375,
752
+ "learning_rate": 0.000188452147312944,
753
+ "loss": 1.0498,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6786296900489397,
758
+ "grad_norm": 0.07861328125,
759
+ "learning_rate": 0.0001882074969151172,
760
+ "loss": 1.0783,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6851549755301795,
765
+ "grad_norm": 0.08056640625,
766
+ "learning_rate": 0.000187960444305604,
767
+ "loss": 0.9942,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6916802610114192,
772
+ "grad_norm": 0.0791015625,
773
+ "learning_rate": 0.00018771099621254746,
774
+ "loss": 1.0517,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.6982055464926591,
779
+ "grad_norm": 0.0810546875,
780
+ "learning_rate": 0.0001874591594293285,
781
+ "loss": 1.0619,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7047308319738989,
786
+ "grad_norm": 0.08251953125,
787
+ "learning_rate": 0.00018720494081438078,
788
+ "loss": 1.0584,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7112561174551386,
793
+ "grad_norm": 0.08740234375,
794
+ "learning_rate": 0.00018694834729100386,
795
+ "loss": 1.0466,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7177814029363785,
800
+ "grad_norm": 0.08349609375,
801
+ "learning_rate": 0.00018668938584717471,
802
+ "loss": 1.0391,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7243066884176182,
807
+ "grad_norm": 0.08251953125,
808
+ "learning_rate": 0.00018642806353535754,
809
+ "loss": 1.0331,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7308319738988581,
814
+ "grad_norm": 0.0859375,
815
+ "learning_rate": 0.00018616438747231148,
816
+ "loss": 1.0671,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7373572593800979,
821
+ "grad_norm": 0.087890625,
822
+ "learning_rate": 0.00018589836483889687,
823
+ "loss": 1.0525,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7438825448613376,
828
+ "grad_norm": 0.08935546875,
829
+ "learning_rate": 0.0001856300028798798,
830
+ "loss": 1.0182,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7504078303425775,
835
+ "grad_norm": 0.08349609375,
836
+ "learning_rate": 0.00018535930890373466,
837
+ "loss": 1.0566,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7569331158238173,
842
+ "grad_norm": 0.080078125,
843
+ "learning_rate": 0.00018508629028244519,
844
+ "loss": 1.0316,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.763458401305057,
849
+ "grad_norm": 0.09033203125,
850
+ "learning_rate": 0.0001848109544513037,
851
+ "loss": 1.0362,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.763458401305057,
856
+ "eval_loss": 1.0525188446044922,
857
+ "eval_runtime": 236.6432,
858
+ "eval_samples_per_second": 1.8,
859
+ "eval_steps_per_second": 0.9,
860
+ "step": 117
861
+ },
862
+ {
863
+ "epoch": 0.7699836867862969,
864
+ "grad_norm": 0.08544921875,
865
+ "learning_rate": 0.00018453330890870855,
866
+ "loss": 1.0141,
867
+ "step": 118
868
+ },
869
+ {
870
+ "epoch": 0.7765089722675367,
871
+ "grad_norm": 0.08203125,
872
+ "learning_rate": 0.00018425336121596,
873
+ "loss": 1.0464,
874
+ "step": 119
875
+ },
876
+ {
877
+ "epoch": 0.7830342577487766,
878
+ "grad_norm": 0.0830078125,
879
+ "learning_rate": 0.00018397111899705419,
880
+ "loss": 1.0278,
881
+ "step": 120
882
+ },
883
+ {
884
+ "epoch": 0.7895595432300163,
885
+ "grad_norm": 0.080078125,
886
+ "learning_rate": 0.00018368658993847566,
887
+ "loss": 1.0439,
888
+ "step": 121
889
+ },
890
+ {
891
+ "epoch": 0.7960848287112561,
892
+ "grad_norm": 0.08251953125,
893
+ "learning_rate": 0.0001833997817889878,
894
+ "loss": 1.053,
895
+ "step": 122
896
+ },
897
+ {
898
+ "epoch": 0.802610114192496,
899
+ "grad_norm": 0.08642578125,
900
+ "learning_rate": 0.0001831107023594221,
901
+ "loss": 1.0447,
902
+ "step": 123
903
+ },
904
+ {
905
+ "epoch": 0.8091353996737357,
906
+ "grad_norm": 0.08349609375,
907
+ "learning_rate": 0.00018281935952246518,
908
+ "loss": 1.0347,
909
+ "step": 124
910
+ },
911
+ {
912
+ "epoch": 0.8156606851549756,
913
+ "grad_norm": 0.0810546875,
914
+ "learning_rate": 0.00018252576121244456,
915
+ "loss": 1.0628,
916
+ "step": 125
917
+ },
918
+ {
919
+ "epoch": 0.8221859706362153,
920
+ "grad_norm": 0.08056640625,
921
+ "learning_rate": 0.00018222991542511246,
922
+ "loss": 1.0112,
923
+ "step": 126
924
+ },
925
+ {
926
+ "epoch": 0.8287112561174551,
927
+ "grad_norm": 0.08984375,
928
+ "learning_rate": 0.0001819318302174281,
929
+ "loss": 1.0657,
930
+ "step": 127
931
+ },
932
+ {
933
+ "epoch": 0.835236541598695,
934
+ "grad_norm": 0.08837890625,
935
+ "learning_rate": 0.00018163151370733838,
936
+ "loss": 1.0936,
937
+ "step": 128
938
+ },
939
+ {
940
+ "epoch": 0.8417618270799347,
941
+ "grad_norm": 0.0869140625,
942
+ "learning_rate": 0.00018132897407355657,
943
+ "loss": 1.0519,
944
+ "step": 129
945
+ },
946
+ {
947
+ "epoch": 0.8482871125611745,
948
+ "grad_norm": 0.08447265625,
949
+ "learning_rate": 0.00018102421955533974,
950
+ "loss": 1.018,
951
+ "step": 130
952
+ },
953
+ {
954
+ "epoch": 0.8548123980424144,
955
+ "grad_norm": 0.08349609375,
956
+ "learning_rate": 0.00018071725845226436,
957
+ "loss": 0.9982,
958
+ "step": 131
959
+ },
960
+ {
961
+ "epoch": 0.8613376835236541,
962
+ "grad_norm": 0.0966796875,
963
+ "learning_rate": 0.0001804080991240003,
964
+ "loss": 1.0522,
965
+ "step": 132
966
+ },
967
+ {
968
+ "epoch": 0.867862969004894,
969
+ "grad_norm": 0.0830078125,
970
+ "learning_rate": 0.000180096749990083,
971
+ "loss": 1.0149,
972
+ "step": 133
973
+ },
974
+ {
975
+ "epoch": 0.8743882544861338,
976
+ "grad_norm": 0.0810546875,
977
+ "learning_rate": 0.00017978321952968434,
978
+ "loss": 1.0096,
979
+ "step": 134
980
+ },
981
+ {
982
+ "epoch": 0.8809135399673735,
983
+ "grad_norm": 0.09765625,
984
+ "learning_rate": 0.00017946751628138174,
985
+ "loss": 1.0551,
986
+ "step": 135
987
+ },
988
+ {
989
+ "epoch": 0.8874388254486134,
990
+ "grad_norm": 0.083984375,
991
+ "learning_rate": 0.00017914964884292544,
992
+ "loss": 1.0384,
993
+ "step": 136
994
+ },
995
+ {
996
+ "epoch": 0.8939641109298532,
997
+ "grad_norm": 0.09326171875,
998
+ "learning_rate": 0.0001788296258710045,
999
+ "loss": 1.0341,
1000
+ "step": 137
1001
+ },
1002
+ {
1003
+ "epoch": 0.9004893964110929,
1004
+ "grad_norm": 0.0859375,
1005
+ "learning_rate": 0.0001785074560810111,
1006
+ "loss": 1.0162,
1007
+ "step": 138
1008
+ },
1009
+ {
1010
+ "epoch": 0.9070146818923328,
1011
+ "grad_norm": 0.0849609375,
1012
+ "learning_rate": 0.000178183148246803,
1013
+ "loss": 1.0332,
1014
+ "step": 139
1015
+ },
1016
+ {
1017
+ "epoch": 0.9135399673735726,
1018
+ "grad_norm": 0.08251953125,
1019
+ "learning_rate": 0.00017785671120046473,
1020
+ "loss": 1.0219,
1021
+ "step": 140
1022
+ },
1023
+ {
1024
+ "epoch": 0.9200652528548124,
1025
+ "grad_norm": 0.080078125,
1026
+ "learning_rate": 0.00017752815383206705,
1027
+ "loss": 1.0557,
1028
+ "step": 141
1029
+ },
1030
+ {
1031
+ "epoch": 0.9265905383360522,
1032
+ "grad_norm": 0.0849609375,
1033
+ "learning_rate": 0.0001771974850894248,
1034
+ "loss": 1.075,
1035
+ "step": 142
1036
+ },
1037
+ {
1038
+ "epoch": 0.933115823817292,
1039
+ "grad_norm": 0.087890625,
1040
+ "learning_rate": 0.0001768647139778532,
1041
+ "loss": 1.0458,
1042
+ "step": 143
1043
+ },
1044
+ {
1045
+ "epoch": 0.9396411092985318,
1046
+ "grad_norm": 0.0830078125,
1047
+ "learning_rate": 0.00017652984955992277,
1048
+ "loss": 1.054,
1049
+ "step": 144
1050
+ },
1051
+ {
1052
+ "epoch": 0.9461663947797716,
1053
+ "grad_norm": 0.08154296875,
1054
+ "learning_rate": 0.0001761929009552122,
1055
+ "loss": 1.0297,
1056
+ "step": 145
1057
+ },
1058
+ {
1059
+ "epoch": 0.9526916802610114,
1060
+ "grad_norm": 0.0849609375,
1061
+ "learning_rate": 0.00017585387734006034,
1062
+ "loss": 1.0299,
1063
+ "step": 146
1064
+ },
1065
+ {
1066
+ "epoch": 0.9592169657422512,
1067
+ "grad_norm": 0.0810546875,
1068
+ "learning_rate": 0.00017551278794731607,
1069
+ "loss": 1.0578,
1070
+ "step": 147
1071
+ },
1072
+ {
1073
+ "epoch": 0.965742251223491,
1074
+ "grad_norm": 0.0859375,
1075
+ "learning_rate": 0.00017516964206608696,
1076
+ "loss": 1.0362,
1077
+ "step": 148
1078
+ },
1079
+ {
1080
+ "epoch": 0.9722675367047309,
1081
+ "grad_norm": 0.09130859375,
1082
+ "learning_rate": 0.00017482444904148617,
1083
+ "loss": 1.0356,
1084
+ "step": 149
1085
+ },
1086
+ {
1087
+ "epoch": 0.9787928221859706,
1088
+ "grad_norm": 0.0869140625,
1089
+ "learning_rate": 0.0001744772182743782,
1090
+ "loss": 1.038,
1091
+ "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.9853181076672104,
1095
+ "grad_norm": 0.0859375,
1096
+ "learning_rate": 0.00017412795922112253,
1097
+ "loss": 1.0445,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.9918433931484503,
1102
+ "grad_norm": 0.08544921875,
1103
+ "learning_rate": 0.0001737766813933164,
1104
+ "loss": 1.0524,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.99836867862969,
1109
+ "grad_norm": 0.08837890625,
1110
+ "learning_rate": 0.00017342339435753553,
1111
+ "loss": 1.0517,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 1.0048939641109298,
1116
+ "grad_norm": 0.083984375,
1117
+ "learning_rate": 0.00017306810773507376,
1118
+ "loss": 1.0033,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 1.0114192495921697,
1123
+ "grad_norm": 0.09033203125,
1124
+ "learning_rate": 0.00017271083120168102,
1125
+ "loss": 1.0477,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 1.0048939641109298,
1130
+ "grad_norm": 0.13671875,
1131
+ "learning_rate": 0.00017235157448729967,
1132
+ "loss": 1.0619,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 1.0048939641109298,
1137
+ "eval_loss": 1.0388679504394531,
1138
+ "eval_runtime": 236.7713,
1139
+ "eval_samples_per_second": 1.799,
1140
+ "eval_steps_per_second": 0.9,
1141
+ "step": 156
1142
+ },
1143
+ {
1144
+ "epoch": 1.0114192495921697,
1145
+ "grad_norm": 0.08740234375,
1146
+ "learning_rate": 0.0001719903473757996,
1147
+ "loss": 1.0131,
1148
+ "step": 157
1149
+ },
1150
+ {
1151
+ "epoch": 1.0179445350734095,
1152
+ "grad_norm": 0.0927734375,
1153
+ "learning_rate": 0.0001716271597047119,
1154
+ "loss": 0.9966,
1155
+ "step": 158
1156
+ },
1157
+ {
1158
+ "epoch": 1.0244698205546492,
1159
+ "grad_norm": 0.0947265625,
1160
+ "learning_rate": 0.0001712620213649608,
1161
+ "loss": 0.9817,
1162
+ "step": 159
1163
+ },
1164
+ {
1165
+ "epoch": 1.030995106035889,
1166
+ "grad_norm": 0.0888671875,
1167
+ "learning_rate": 0.00017089494230059432,
1168
+ "loss": 1.0036,
1169
+ "step": 160
1170
+ },
1171
+ {
1172
+ "epoch": 1.037520391517129,
1173
+ "grad_norm": 0.09716796875,
1174
+ "learning_rate": 0.0001705259325085135,
1175
+ "loss": 1.0318,
1176
+ "step": 161
1177
+ },
1178
+ {
1179
+ "epoch": 1.0440456769983686,
1180
+ "grad_norm": 0.09814453125,
1181
+ "learning_rate": 0.00017015500203820022,
1182
+ "loss": 1.0106,
1183
+ "step": 162
1184
+ },
1185
+ {
1186
+ "epoch": 1.0505709624796085,
1187
+ "grad_norm": 0.09521484375,
1188
+ "learning_rate": 0.0001697821609914432,
1189
+ "loss": 1.0178,
1190
+ "step": 163
1191
+ },
1192
+ {
1193
+ "epoch": 1.0570962479608483,
1194
+ "grad_norm": 0.09033203125,
1195
+ "learning_rate": 0.0001694074195220634,
1196
+ "loss": 0.9909,
1197
+ "step": 164
1198
+ },
1199
+ {
1200
+ "epoch": 1.0636215334420882,
1201
+ "grad_norm": 0.08740234375,
1202
+ "learning_rate": 0.000169030787835637,
1203
+ "loss": 0.9916,
1204
+ "step": 165
1205
+ },
1206
+ {
1207
+ "epoch": 1.0701468189233279,
1208
+ "grad_norm": 0.09130859375,
1209
+ "learning_rate": 0.00016865227618921788,
1210
+ "loss": 1.0101,
1211
+ "step": 166
1212
+ },
1213
+ {
1214
+ "epoch": 1.0766721044045677,
1215
+ "grad_norm": 0.0908203125,
1216
+ "learning_rate": 0.00016827189489105788,
1217
+ "loss": 0.9966,
1218
+ "step": 167
1219
+ },
1220
+ {
1221
+ "epoch": 1.0831973898858076,
1222
+ "grad_norm": 0.09521484375,
1223
+ "learning_rate": 0.00016788965430032638,
1224
+ "loss": 1.0048,
1225
+ "step": 168
1226
+ },
1227
+ {
1228
+ "epoch": 1.0897226753670473,
1229
+ "grad_norm": 0.09521484375,
1230
+ "learning_rate": 0.00016750556482682805,
1231
+ "loss": 1.0074,
1232
+ "step": 169
1233
+ },
1234
+ {
1235
+ "epoch": 1.0962479608482871,
1236
+ "grad_norm": 0.08935546875,
1237
+ "learning_rate": 0.00016711963693071943,
1238
+ "loss": 0.9762,
1239
+ "step": 170
1240
+ },
1241
+ {
1242
+ "epoch": 1.102773246329527,
1243
+ "grad_norm": 0.09619140625,
1244
+ "learning_rate": 0.00016673188112222394,
1245
+ "loss": 1.0044,
1246
+ "step": 171
1247
+ },
1248
+ {
1249
+ "epoch": 1.1092985318107667,
1250
+ "grad_norm": 0.091796875,
1251
+ "learning_rate": 0.00016634230796134576,
1252
+ "loss": 0.9972,
1253
+ "step": 172
1254
+ },
1255
+ {
1256
+ "epoch": 1.1158238172920065,
1257
+ "grad_norm": 0.09228515625,
1258
+ "learning_rate": 0.0001659509280575821,
1259
+ "loss": 1.0308,
1260
+ "step": 173
1261
+ },
1262
+ {
1263
+ "epoch": 1.1223491027732464,
1264
+ "grad_norm": 0.0927734375,
1265
+ "learning_rate": 0.0001655577520696346,
1266
+ "loss": 0.996,
1267
+ "step": 174
1268
+ },
1269
+ {
1270
+ "epoch": 1.128874388254486,
1271
+ "grad_norm": 0.0947265625,
1272
+ "learning_rate": 0.00016516279070511854,
1273
+ "loss": 0.9671,
1274
+ "step": 175
1275
+ },
1276
+ {
1277
+ "epoch": 1.135399673735726,
1278
+ "grad_norm": 0.09228515625,
1279
+ "learning_rate": 0.00016476605472027172,
1280
+ "loss": 1.0121,
1281
+ "step": 176
1282
+ },
1283
+ {
1284
+ "epoch": 1.1419249592169658,
1285
+ "grad_norm": 0.0927734375,
1286
+ "learning_rate": 0.00016436755491966115,
1287
+ "loss": 1.0132,
1288
+ "step": 177
1289
+ },
1290
+ {
1291
+ "epoch": 1.1484502446982057,
1292
+ "grad_norm": 0.09375,
1293
+ "learning_rate": 0.00016396730215588915,
1294
+ "loss": 1.0146,
1295
+ "step": 178
1296
+ },
1297
+ {
1298
+ "epoch": 1.1549755301794453,
1299
+ "grad_norm": 0.09521484375,
1300
+ "learning_rate": 0.0001635653073292975,
1301
+ "loss": 0.9911,
1302
+ "step": 179
1303
+ },
1304
+ {
1305
+ "epoch": 1.1615008156606852,
1306
+ "grad_norm": 0.09716796875,
1307
+ "learning_rate": 0.0001631615813876707,
1308
+ "loss": 1.0125,
1309
+ "step": 180
1310
+ },
1311
+ {
1312
+ "epoch": 1.1680261011419248,
1313
+ "grad_norm": 0.09521484375,
1314
+ "learning_rate": 0.0001627561353259379,
1315
+ "loss": 1.0162,
1316
+ "step": 181
1317
+ },
1318
+ {
1319
+ "epoch": 1.1745513866231647,
1320
+ "grad_norm": 0.09716796875,
1321
+ "learning_rate": 0.00016234898018587337,
1322
+ "loss": 0.995,
1323
+ "step": 182
1324
+ },
1325
+ {
1326
+ "epoch": 1.1810766721044046,
1327
+ "grad_norm": 0.09326171875,
1328
+ "learning_rate": 0.00016194012705579572,
1329
+ "loss": 0.9839,
1330
+ "step": 183
1331
+ },
1332
+ {
1333
+ "epoch": 1.1876019575856445,
1334
+ "grad_norm": 0.09716796875,
1335
+ "learning_rate": 0.00016152958707026614,
1336
+ "loss": 1.0107,
1337
+ "step": 184
1338
+ },
1339
+ {
1340
+ "epoch": 1.1941272430668841,
1341
+ "grad_norm": 0.09326171875,
1342
+ "learning_rate": 0.00016111737140978494,
1343
+ "loss": 0.9715,
1344
+ "step": 185
1345
+ },
1346
+ {
1347
+ "epoch": 1.200652528548124,
1348
+ "grad_norm": 0.09326171875,
1349
+ "learning_rate": 0.00016070349130048724,
1350
+ "loss": 0.9751,
1351
+ "step": 186
1352
+ },
1353
+ {
1354
+ "epoch": 1.2071778140293639,
1355
+ "grad_norm": 0.09375,
1356
+ "learning_rate": 0.00016028795801383718,
1357
+ "loss": 0.9845,
1358
+ "step": 187
1359
+ },
1360
+ {
1361
+ "epoch": 1.2137030995106035,
1362
+ "grad_norm": 0.10302734375,
1363
+ "learning_rate": 0.0001598707828663209,
1364
+ "loss": 0.9604,
1365
+ "step": 188
1366
+ },
1367
+ {
1368
+ "epoch": 1.2202283849918434,
1369
+ "grad_norm": 0.09765625,
1370
+ "learning_rate": 0.00015945197721913833,
1371
+ "loss": 0.9715,
1372
+ "step": 189
1373
+ },
1374
+ {
1375
+ "epoch": 1.2267536704730833,
1376
+ "grad_norm": 0.0966796875,
1377
+ "learning_rate": 0.00015903155247789404,
1378
+ "loss": 1.0156,
1379
+ "step": 190
1380
+ },
1381
+ {
1382
+ "epoch": 1.233278955954323,
1383
+ "grad_norm": 0.09814453125,
1384
+ "learning_rate": 0.00015860952009228625,
1385
+ "loss": 1.0044,
1386
+ "step": 191
1387
+ },
1388
+ {
1389
+ "epoch": 1.2398042414355628,
1390
+ "grad_norm": 0.099609375,
1391
+ "learning_rate": 0.0001581858915557953,
1392
+ "loss": 0.9849,
1393
+ "step": 192
1394
+ },
1395
+ {
1396
+ "epoch": 1.2463295269168027,
1397
+ "grad_norm": 0.09619140625,
1398
+ "learning_rate": 0.0001577606784053705,
1399
+ "loss": 1.0007,
1400
+ "step": 193
1401
+ },
1402
+ {
1403
+ "epoch": 1.2528548123980423,
1404
+ "grad_norm": 0.0947265625,
1405
+ "learning_rate": 0.00015733389222111592,
1406
+ "loss": 0.9682,
1407
+ "step": 194
1408
+ },
1409
+ {
1410
+ "epoch": 1.2593800978792822,
1411
+ "grad_norm": 0.0966796875,
1412
+ "learning_rate": 0.00015690554462597522,
1413
+ "loss": 1.0165,
1414
+ "step": 195
1415
+ },
1416
+ {
1417
+ "epoch": 1.2593800978792822,
1418
+ "eval_loss": 1.0322120189666748,
1419
+ "eval_runtime": 236.6694,
1420
+ "eval_samples_per_second": 1.8,
1421
+ "eval_steps_per_second": 0.9,
1422
+ "step": 195
1423
+ },
1424
+ {
1425
+ "epoch": 1.265905383360522,
1426
+ "grad_norm": 0.1005859375,
1427
+ "learning_rate": 0.00015647564728541485,
1428
+ "loss": 1.0376,
1429
+ "step": 196
1430
+ },
1431
+ {
1432
+ "epoch": 1.272430668841762,
1433
+ "grad_norm": 0.09619140625,
1434
+ "learning_rate": 0.0001560442119071065,
1435
+ "loss": 1.0066,
1436
+ "step": 197
1437
+ },
1438
+ {
1439
+ "epoch": 1.2789559543230016,
1440
+ "grad_norm": 0.095703125,
1441
+ "learning_rate": 0.00015561125024060826,
1442
+ "loss": 0.9872,
1443
+ "step": 198
1444
+ },
1445
+ {
1446
+ "epoch": 1.2854812398042414,
1447
+ "grad_norm": 0.0966796875,
1448
+ "learning_rate": 0.0001551767740770446,
1449
+ "loss": 1.0079,
1450
+ "step": 199
1451
+ },
1452
+ {
1453
+ "epoch": 1.2920065252854813,
1454
+ "grad_norm": 0.09765625,
1455
+ "learning_rate": 0.00015474079524878525,
1456
+ "loss": 0.9865,
1457
+ "step": 200
1458
+ },
1459
+ {
1460
+ "epoch": 1.298531810766721,
1461
+ "grad_norm": 0.09423828125,
1462
+ "learning_rate": 0.000154303325629123,
1463
+ "loss": 0.9747,
1464
+ "step": 201
1465
+ },
1466
+ {
1467
+ "epoch": 1.3050570962479608,
1468
+ "grad_norm": 0.09814453125,
1469
+ "learning_rate": 0.0001538643771319503,
1470
+ "loss": 1.0119,
1471
+ "step": 202
1472
+ },
1473
+ {
1474
+ "epoch": 1.3115823817292007,
1475
+ "grad_norm": 0.095703125,
1476
+ "learning_rate": 0.00015342396171143488,
1477
+ "loss": 0.9815,
1478
+ "step": 203
1479
+ },
1480
+ {
1481
+ "epoch": 1.3181076672104406,
1482
+ "grad_norm": 0.09912109375,
1483
+ "learning_rate": 0.00015298209136169403,
1484
+ "loss": 0.9772,
1485
+ "step": 204
1486
+ },
1487
+ {
1488
+ "epoch": 1.3246329526916802,
1489
+ "grad_norm": 0.095703125,
1490
+ "learning_rate": 0.00015253877811646817,
1491
+ "loss": 0.9804,
1492
+ "step": 205
1493
+ },
1494
+ {
1495
+ "epoch": 1.3311582381729201,
1496
+ "grad_norm": 0.09716796875,
1497
+ "learning_rate": 0.00015209403404879303,
1498
+ "loss": 0.9457,
1499
+ "step": 206
1500
+ },
1501
+ {
1502
+ "epoch": 1.3376835236541598,
1503
+ "grad_norm": 0.1005859375,
1504
+ "learning_rate": 0.0001516478712706708,
1505
+ "loss": 0.9951,
1506
+ "step": 207
1507
+ },
1508
+ {
1509
+ "epoch": 1.3442088091353996,
1510
+ "grad_norm": 0.09521484375,
1511
+ "learning_rate": 0.00015120030193274027,
1512
+ "loss": 1.0085,
1513
+ "step": 208
1514
+ },
1515
+ {
1516
+ "epoch": 1.3507340946166395,
1517
+ "grad_norm": 0.09619140625,
1518
+ "learning_rate": 0.00015075133822394613,
1519
+ "loss": 1.0105,
1520
+ "step": 209
1521
+ },
1522
+ {
1523
+ "epoch": 1.3572593800978794,
1524
+ "grad_norm": 0.1025390625,
1525
+ "learning_rate": 0.00015030099237120674,
1526
+ "loss": 1.005,
1527
+ "step": 210
1528
+ },
1529
+ {
1530
+ "epoch": 1.363784665579119,
1531
+ "grad_norm": 0.0986328125,
1532
+ "learning_rate": 0.00014984927663908137,
1533
+ "loss": 0.9703,
1534
+ "step": 211
1535
+ },
1536
+ {
1537
+ "epoch": 1.370309951060359,
1538
+ "grad_norm": 0.0947265625,
1539
+ "learning_rate": 0.00014939620332943604,
1540
+ "loss": 0.9747,
1541
+ "step": 212
1542
+ },
1543
+ {
1544
+ "epoch": 1.3768352365415986,
1545
+ "grad_norm": 0.09716796875,
1546
+ "learning_rate": 0.00014894178478110857,
1547
+ "loss": 0.9785,
1548
+ "step": 213
1549
+ },
1550
+ {
1551
+ "epoch": 1.3833605220228384,
1552
+ "grad_norm": 0.09814453125,
1553
+ "learning_rate": 0.00014848603336957251,
1554
+ "loss": 1.0329,
1555
+ "step": 214
1556
+ },
1557
+ {
1558
+ "epoch": 1.3898858075040783,
1559
+ "grad_norm": 0.09423828125,
1560
+ "learning_rate": 0.00014802896150660022,
1561
+ "loss": 0.9429,
1562
+ "step": 215
1563
+ },
1564
+ {
1565
+ "epoch": 1.3964110929853182,
1566
+ "grad_norm": 0.099609375,
1567
+ "learning_rate": 0.00014757058163992464,
1568
+ "loss": 0.9578,
1569
+ "step": 216
1570
+ },
1571
+ {
1572
+ "epoch": 1.4029363784665578,
1573
+ "grad_norm": 0.1025390625,
1574
+ "learning_rate": 0.00014711090625290057,
1575
+ "loss": 1.0216,
1576
+ "step": 217
1577
+ },
1578
+ {
1579
+ "epoch": 1.4094616639477977,
1580
+ "grad_norm": 0.10986328125,
1581
+ "learning_rate": 0.0001466499478641644,
1582
+ "loss": 0.9792,
1583
+ "step": 218
1584
+ },
1585
+ {
1586
+ "epoch": 1.4159869494290376,
1587
+ "grad_norm": 0.095703125,
1588
+ "learning_rate": 0.00014618771902729342,
1589
+ "loss": 1.0001,
1590
+ "step": 219
1591
+ },
1592
+ {
1593
+ "epoch": 1.4225122349102772,
1594
+ "grad_norm": 0.1044921875,
1595
+ "learning_rate": 0.00014572423233046386,
1596
+ "loss": 1.0057,
1597
+ "step": 220
1598
+ },
1599
+ {
1600
+ "epoch": 1.429037520391517,
1601
+ "grad_norm": 0.09912109375,
1602
+ "learning_rate": 0.000145259500396108,
1603
+ "loss": 0.9698,
1604
+ "step": 221
1605
+ },
1606
+ {
1607
+ "epoch": 1.435562805872757,
1608
+ "grad_norm": 0.09814453125,
1609
+ "learning_rate": 0.00014479353588057052,
1610
+ "loss": 0.9533,
1611
+ "step": 222
1612
+ },
1613
+ {
1614
+ "epoch": 1.4420880913539968,
1615
+ "grad_norm": 0.103515625,
1616
+ "learning_rate": 0.00014432635147376376,
1617
+ "loss": 0.9686,
1618
+ "step": 223
1619
+ },
1620
+ {
1621
+ "epoch": 1.4486133768352365,
1622
+ "grad_norm": 0.0986328125,
1623
+ "learning_rate": 0.00014385795989882221,
1624
+ "loss": 1.0278,
1625
+ "step": 224
1626
+ },
1627
+ {
1628
+ "epoch": 1.4551386623164764,
1629
+ "grad_norm": 0.103515625,
1630
+ "learning_rate": 0.00014338837391175582,
1631
+ "loss": 1.0013,
1632
+ "step": 225
1633
+ },
1634
+ {
1635
+ "epoch": 1.461663947797716,
1636
+ "grad_norm": 0.10400390625,
1637
+ "learning_rate": 0.00014291760630110288,
1638
+ "loss": 1.0053,
1639
+ "step": 226
1640
+ },
1641
+ {
1642
+ "epoch": 1.468189233278956,
1643
+ "grad_norm": 0.10302734375,
1644
+ "learning_rate": 0.00014244566988758152,
1645
+ "loss": 1.0216,
1646
+ "step": 227
1647
+ },
1648
+ {
1649
+ "epoch": 1.4747145187601958,
1650
+ "grad_norm": 0.09912109375,
1651
+ "learning_rate": 0.0001419725775237406,
1652
+ "loss": 0.992,
1653
+ "step": 228
1654
+ },
1655
+ {
1656
+ "epoch": 1.4812398042414356,
1657
+ "grad_norm": 0.099609375,
1658
+ "learning_rate": 0.00014149834209360986,
1659
+ "loss": 1.0053,
1660
+ "step": 229
1661
+ },
1662
+ {
1663
+ "epoch": 1.4877650897226753,
1664
+ "grad_norm": 0.103515625,
1665
+ "learning_rate": 0.0001410229765123487,
1666
+ "loss": 0.9948,
1667
+ "step": 230
1668
+ },
1669
+ {
1670
+ "epoch": 1.4942903752039152,
1671
+ "grad_norm": 0.09912109375,
1672
+ "learning_rate": 0.00014054649372589482,
1673
+ "loss": 0.9717,
1674
+ "step": 231
1675
+ },
1676
+ {
1677
+ "epoch": 1.5008156606851548,
1678
+ "grad_norm": 0.0986328125,
1679
+ "learning_rate": 0.00014006890671061143,
1680
+ "loss": 0.9805,
1681
+ "step": 232
1682
+ },
1683
+ {
1684
+ "epoch": 1.5073409461663947,
1685
+ "grad_norm": 0.10400390625,
1686
+ "learning_rate": 0.00013959022847293391,
1687
+ "loss": 0.9826,
1688
+ "step": 233
1689
+ },
1690
+ {
1691
+ "epoch": 1.5138662316476346,
1692
+ "grad_norm": 0.09765625,
1693
+ "learning_rate": 0.0001391104720490156,
1694
+ "loss": 0.9394,
1695
+ "step": 234
1696
+ },
1697
+ {
1698
+ "epoch": 1.5138662316476346,
1699
+ "eval_loss": 1.0245814323425293,
1700
+ "eval_runtime": 236.6376,
1701
+ "eval_samples_per_second": 1.8,
1702
+ "eval_steps_per_second": 0.9,
1703
+ "step": 234
1704
+ },
1705
+ {
1706
+ "epoch": 1.5203915171288744,
1707
+ "grad_norm": 0.10107421875,
1708
+ "learning_rate": 0.0001386296505043728,
1709
+ "loss": 0.9857,
1710
+ "step": 235
1711
+ },
1712
+ {
1713
+ "epoch": 1.5269168026101143,
1714
+ "grad_norm": 0.099609375,
1715
+ "learning_rate": 0.000138147776933529,
1716
+ "loss": 0.997,
1717
+ "step": 236
1718
+ },
1719
+ {
1720
+ "epoch": 1.533442088091354,
1721
+ "grad_norm": 0.107421875,
1722
+ "learning_rate": 0.00013766486445965795,
1723
+ "loss": 0.9927,
1724
+ "step": 237
1725
+ },
1726
+ {
1727
+ "epoch": 1.5399673735725938,
1728
+ "grad_norm": 0.095703125,
1729
+ "learning_rate": 0.00013718092623422686,
1730
+ "loss": 0.9745,
1731
+ "step": 238
1732
+ },
1733
+ {
1734
+ "epoch": 1.5464926590538335,
1735
+ "grad_norm": 0.1005859375,
1736
+ "learning_rate": 0.00013669597543663762,
1737
+ "loss": 0.9842,
1738
+ "step": 239
1739
+ },
1740
+ {
1741
+ "epoch": 1.5530179445350734,
1742
+ "grad_norm": 0.099609375,
1743
+ "learning_rate": 0.00013621002527386834,
1744
+ "loss": 1.0102,
1745
+ "step": 240
1746
+ },
1747
+ {
1748
+ "epoch": 1.5595432300163132,
1749
+ "grad_norm": 0.1015625,
1750
+ "learning_rate": 0.0001357230889801133,
1751
+ "loss": 0.9389,
1752
+ "step": 241
1753
+ },
1754
+ {
1755
+ "epoch": 1.566068515497553,
1756
+ "grad_norm": 0.099609375,
1757
+ "learning_rate": 0.00013523517981642286,
1758
+ "loss": 1.0044,
1759
+ "step": 242
1760
+ },
1761
+ {
1762
+ "epoch": 1.572593800978793,
1763
+ "grad_norm": 0.09716796875,
1764
+ "learning_rate": 0.0001347463110703422,
1765
+ "loss": 0.9698,
1766
+ "step": 243
1767
+ },
1768
+ {
1769
+ "epoch": 1.5791190864600326,
1770
+ "grad_norm": 0.1015625,
1771
+ "learning_rate": 0.00013425649605554928,
1772
+ "loss": 0.9858,
1773
+ "step": 244
1774
+ },
1775
+ {
1776
+ "epoch": 1.5856443719412723,
1777
+ "grad_norm": 0.1396484375,
1778
+ "learning_rate": 0.00013376574811149253,
1779
+ "loss": 0.9513,
1780
+ "step": 245
1781
+ },
1782
+ {
1783
+ "epoch": 1.5921696574225122,
1784
+ "grad_norm": 0.10009765625,
1785
+ "learning_rate": 0.00013327408060302738,
1786
+ "loss": 0.9943,
1787
+ "step": 246
1788
+ },
1789
+ {
1790
+ "epoch": 1.598694942903752,
1791
+ "grad_norm": 0.0986328125,
1792
+ "learning_rate": 0.00013278150692005243,
1793
+ "loss": 0.9933,
1794
+ "step": 247
1795
+ },
1796
+ {
1797
+ "epoch": 1.605220228384992,
1798
+ "grad_norm": 0.1005859375,
1799
+ "learning_rate": 0.00013228804047714463,
1800
+ "loss": 0.9865,
1801
+ "step": 248
1802
+ },
1803
+ {
1804
+ "epoch": 1.6117455138662318,
1805
+ "grad_norm": 0.09716796875,
1806
+ "learning_rate": 0.00013179369471319404,
1807
+ "loss": 0.9466,
1808
+ "step": 249
1809
+ },
1810
+ {
1811
+ "epoch": 1.6182707993474714,
1812
+ "grad_norm": 0.0986328125,
1813
+ "learning_rate": 0.0001312984830910379,
1814
+ "loss": 0.9684,
1815
+ "step": 250
1816
+ },
1817
+ {
1818
+ "epoch": 1.6247960848287113,
1819
+ "grad_norm": 0.10205078125,
1820
+ "learning_rate": 0.00013080241909709387,
1821
+ "loss": 1.004,
1822
+ "step": 251
1823
+ },
1824
+ {
1825
+ "epoch": 1.631321370309951,
1826
+ "grad_norm": 0.10400390625,
1827
+ "learning_rate": 0.00013030551624099287,
1828
+ "loss": 0.9964,
1829
+ "step": 252
1830
+ },
1831
+ {
1832
+ "epoch": 1.6378466557911908,
1833
+ "grad_norm": 0.10888671875,
1834
+ "learning_rate": 0.000129807788055211,
1835
+ "loss": 0.9745,
1836
+ "step": 253
1837
+ },
1838
+ {
1839
+ "epoch": 1.6443719412724307,
1840
+ "grad_norm": 0.1044921875,
1841
+ "learning_rate": 0.00012930924809470115,
1842
+ "loss": 1.0074,
1843
+ "step": 254
1844
+ },
1845
+ {
1846
+ "epoch": 1.6508972267536706,
1847
+ "grad_norm": 0.1064453125,
1848
+ "learning_rate": 0.00012880990993652377,
1849
+ "loss": 0.9842,
1850
+ "step": 255
1851
+ },
1852
+ {
1853
+ "epoch": 1.6574225122349104,
1854
+ "grad_norm": 0.1025390625,
1855
+ "learning_rate": 0.00012830978717947718,
1856
+ "loss": 0.9699,
1857
+ "step": 256
1858
+ },
1859
+ {
1860
+ "epoch": 1.66394779771615,
1861
+ "grad_norm": 0.10009765625,
1862
+ "learning_rate": 0.00012780889344372718,
1863
+ "loss": 0.9892,
1864
+ "step": 257
1865
+ },
1866
+ {
1867
+ "epoch": 1.6704730831973897,
1868
+ "grad_norm": 0.1025390625,
1869
+ "learning_rate": 0.00012730724237043615,
1870
+ "loss": 0.9804,
1871
+ "step": 258
1872
+ },
1873
+ {
1874
+ "epoch": 1.6769983686786296,
1875
+ "grad_norm": 0.09814453125,
1876
+ "learning_rate": 0.0001268048476213914,
1877
+ "loss": 0.9873,
1878
+ "step": 259
1879
+ },
1880
+ {
1881
+ "epoch": 1.6835236541598695,
1882
+ "grad_norm": 0.09765625,
1883
+ "learning_rate": 0.0001263017228786334,
1884
+ "loss": 0.9737,
1885
+ "step": 260
1886
+ },
1887
+ {
1888
+ "epoch": 1.6900489396411094,
1889
+ "grad_norm": 0.10107421875,
1890
+ "learning_rate": 0.00012579788184408295,
1891
+ "loss": 1.0064,
1892
+ "step": 261
1893
+ },
1894
+ {
1895
+ "epoch": 1.6965742251223492,
1896
+ "grad_norm": 0.10888671875,
1897
+ "learning_rate": 0.00012529333823916807,
1898
+ "loss": 0.9745,
1899
+ "step": 262
1900
+ },
1901
+ {
1902
+ "epoch": 1.7030995106035889,
1903
+ "grad_norm": 0.1005859375,
1904
+ "learning_rate": 0.0001247881058044504,
1905
+ "loss": 0.9988,
1906
+ "step": 263
1907
+ },
1908
+ {
1909
+ "epoch": 1.7096247960848288,
1910
+ "grad_norm": 0.10595703125,
1911
+ "learning_rate": 0.00012428219829925083,
1912
+ "loss": 1.0021,
1913
+ "step": 264
1914
+ },
1915
+ {
1916
+ "epoch": 1.7161500815660684,
1917
+ "grad_norm": 0.09814453125,
1918
+ "learning_rate": 0.00012377562950127493,
1919
+ "loss": 0.9681,
1920
+ "step": 265
1921
+ },
1922
+ {
1923
+ "epoch": 1.7226753670473083,
1924
+ "grad_norm": 0.107421875,
1925
+ "learning_rate": 0.00012326841320623767,
1926
+ "loss": 0.9968,
1927
+ "step": 266
1928
+ },
1929
+ {
1930
+ "epoch": 1.7292006525285482,
1931
+ "grad_norm": 0.10791015625,
1932
+ "learning_rate": 0.00012276056322748778,
1933
+ "loss": 1.0235,
1934
+ "step": 267
1935
+ },
1936
+ {
1937
+ "epoch": 1.735725938009788,
1938
+ "grad_norm": 0.10498046875,
1939
+ "learning_rate": 0.00012225209339563145,
1940
+ "loss": 0.977,
1941
+ "step": 268
1942
+ },
1943
+ {
1944
+ "epoch": 1.7422512234910277,
1945
+ "grad_norm": 0.10302734375,
1946
+ "learning_rate": 0.00012174301755815571,
1947
+ "loss": 1.0021,
1948
+ "step": 269
1949
+ },
1950
+ {
1951
+ "epoch": 1.7487765089722676,
1952
+ "grad_norm": 0.09716796875,
1953
+ "learning_rate": 0.0001212333495790514,
1954
+ "loss": 0.9781,
1955
+ "step": 270
1956
+ },
1957
+ {
1958
+ "epoch": 1.7553017944535072,
1959
+ "grad_norm": 0.10546875,
1960
+ "learning_rate": 0.00012072310333843544,
1961
+ "loss": 0.9901,
1962
+ "step": 271
1963
+ },
1964
+ {
1965
+ "epoch": 1.761827079934747,
1966
+ "grad_norm": 0.10205078125,
1967
+ "learning_rate": 0.00012021229273217302,
1968
+ "loss": 0.9675,
1969
+ "step": 272
1970
+ },
1971
+ {
1972
+ "epoch": 1.768352365415987,
1973
+ "grad_norm": 0.10546875,
1974
+ "learning_rate": 0.00011970093167149905,
1975
+ "loss": 0.999,
1976
+ "step": 273
1977
+ },
1978
+ {
1979
+ "epoch": 1.768352365415987,
1980
+ "eval_loss": 1.0181984901428223,
1981
+ "eval_runtime": 236.6668,
1982
+ "eval_samples_per_second": 1.8,
1983
+ "eval_steps_per_second": 0.9,
1984
+ "step": 273
1985
+ },
1986
+ {
1987
+ "epoch": 1.7748776508972268,
1988
+ "grad_norm": 0.1005859375,
1989
+ "learning_rate": 0.00011918903408263924,
1990
+ "loss": 0.9798,
1991
+ "step": 274
1992
+ },
1993
+ {
1994
+ "epoch": 1.7814029363784667,
1995
+ "grad_norm": 0.103515625,
1996
+ "learning_rate": 0.000118676613906431,
1997
+ "loss": 0.9826,
1998
+ "step": 275
1999
+ },
2000
+ {
2001
+ "epoch": 1.7879282218597063,
2002
+ "grad_norm": 0.0986328125,
2003
+ "learning_rate": 0.00011816368509794364,
2004
+ "loss": 0.9781,
2005
+ "step": 276
2006
+ },
2007
+ {
2008
+ "epoch": 1.7944535073409462,
2009
+ "grad_norm": 0.099609375,
2010
+ "learning_rate": 0.00011765026162609847,
2011
+ "loss": 0.9811,
2012
+ "step": 277
2013
+ },
2014
+ {
2015
+ "epoch": 1.8009787928221859,
2016
+ "grad_norm": 0.10498046875,
2017
+ "learning_rate": 0.00011713635747328818,
2018
+ "loss": 0.9859,
2019
+ "step": 278
2020
+ },
2021
+ {
2022
+ "epoch": 1.8075040783034257,
2023
+ "grad_norm": 0.10107421875,
2024
+ "learning_rate": 0.00011662198663499619,
2025
+ "loss": 0.9644,
2026
+ "step": 279
2027
+ },
2028
+ {
2029
+ "epoch": 1.8140293637846656,
2030
+ "grad_norm": 0.1025390625,
2031
+ "learning_rate": 0.0001161071631194155,
2032
+ "loss": 0.9931,
2033
+ "step": 280
2034
+ },
2035
+ {
2036
+ "epoch": 1.8205546492659055,
2037
+ "grad_norm": 0.09716796875,
2038
+ "learning_rate": 0.00011559190094706714,
2039
+ "loss": 1.0061,
2040
+ "step": 281
2041
+ },
2042
+ {
2043
+ "epoch": 1.8270799347471451,
2044
+ "grad_norm": 0.1015625,
2045
+ "learning_rate": 0.00011507621415041837,
2046
+ "loss": 0.9511,
2047
+ "step": 282
2048
+ },
2049
+ {
2050
+ "epoch": 1.833605220228385,
2051
+ "grad_norm": 0.10888671875,
2052
+ "learning_rate": 0.00011456011677350051,
2053
+ "loss": 0.9875,
2054
+ "step": 283
2055
+ },
2056
+ {
2057
+ "epoch": 1.8401305057096247,
2058
+ "grad_norm": 0.099609375,
2059
+ "learning_rate": 0.00011404362287152646,
2060
+ "loss": 0.9577,
2061
+ "step": 284
2062
+ },
2063
+ {
2064
+ "epoch": 1.8466557911908645,
2065
+ "grad_norm": 0.10205078125,
2066
+ "learning_rate": 0.00011352674651050796,
2067
+ "loss": 1.0018,
2068
+ "step": 285
2069
+ },
2070
+ {
2071
+ "epoch": 1.8531810766721044,
2072
+ "grad_norm": 0.1025390625,
2073
+ "learning_rate": 0.00011300950176687255,
2074
+ "loss": 0.9738,
2075
+ "step": 286
2076
+ },
2077
+ {
2078
+ "epoch": 1.8597063621533443,
2079
+ "grad_norm": 0.10009765625,
2080
+ "learning_rate": 0.00011249190272708008,
2081
+ "loss": 0.9635,
2082
+ "step": 287
2083
+ },
2084
+ {
2085
+ "epoch": 1.8662316476345842,
2086
+ "grad_norm": 0.10302734375,
2087
+ "learning_rate": 0.00011197396348723923,
2088
+ "loss": 0.9783,
2089
+ "step": 288
2090
+ },
2091
+ {
2092
+ "epoch": 1.8727569331158238,
2093
+ "grad_norm": 0.1123046875,
2094
+ "learning_rate": 0.0001114556981527236,
2095
+ "loss": 0.9895,
2096
+ "step": 289
2097
+ },
2098
+ {
2099
+ "epoch": 1.8792822185970635,
2100
+ "grad_norm": 0.10009765625,
2101
+ "learning_rate": 0.00011093712083778746,
2102
+ "loss": 0.9993,
2103
+ "step": 290
2104
+ },
2105
+ {
2106
+ "epoch": 1.8858075040783033,
2107
+ "grad_norm": 0.1123046875,
2108
+ "learning_rate": 0.00011041824566518146,
2109
+ "loss": 0.9842,
2110
+ "step": 291
2111
+ },
2112
+ {
2113
+ "epoch": 1.8923327895595432,
2114
+ "grad_norm": 0.10498046875,
2115
+ "learning_rate": 0.00010989908676576807,
2116
+ "loss": 0.9693,
2117
+ "step": 292
2118
+ },
2119
+ {
2120
+ "epoch": 1.898858075040783,
2121
+ "grad_norm": 0.0986328125,
2122
+ "learning_rate": 0.00010937965827813661,
2123
+ "loss": 0.9838,
2124
+ "step": 293
2125
+ },
2126
+ {
2127
+ "epoch": 1.905383360522023,
2128
+ "grad_norm": 0.1064453125,
2129
+ "learning_rate": 0.00010885997434821831,
2130
+ "loss": 0.9992,
2131
+ "step": 294
2132
+ },
2133
+ {
2134
+ "epoch": 1.9119086460032626,
2135
+ "grad_norm": 0.09912109375,
2136
+ "learning_rate": 0.00010834004912890092,
2137
+ "loss": 1.0066,
2138
+ "step": 295
2139
+ },
2140
+ {
2141
+ "epoch": 1.9184339314845025,
2142
+ "grad_norm": 0.10009765625,
2143
+ "learning_rate": 0.00010781989677964355,
2144
+ "loss": 0.9737,
2145
+ "step": 296
2146
+ },
2147
+ {
2148
+ "epoch": 1.9249592169657421,
2149
+ "grad_norm": 0.10546875,
2150
+ "learning_rate": 0.00010729953146609076,
2151
+ "loss": 0.9913,
2152
+ "step": 297
2153
+ },
2154
+ {
2155
+ "epoch": 1.931484502446982,
2156
+ "grad_norm": 0.10546875,
2157
+ "learning_rate": 0.00010677896735968693,
2158
+ "loss": 0.9835,
2159
+ "step": 298
2160
+ },
2161
+ {
2162
+ "epoch": 1.9380097879282219,
2163
+ "grad_norm": 0.1015625,
2164
+ "learning_rate": 0.00010625821863729036,
2165
+ "loss": 0.967,
2166
+ "step": 299
2167
+ },
2168
+ {
2169
+ "epoch": 1.9445350734094617,
2170
+ "grad_norm": 0.1015625,
2171
+ "learning_rate": 0.00010573729948078699,
2172
+ "loss": 0.9724,
2173
+ "step": 300
2174
+ },
2175
+ {
2176
+ "epoch": 1.9510603588907016,
2177
+ "grad_norm": 0.1005859375,
2178
+ "learning_rate": 0.00010521622407670439,
2179
+ "loss": 0.9732,
2180
+ "step": 301
2181
+ },
2182
+ {
2183
+ "epoch": 1.9575856443719413,
2184
+ "grad_norm": 0.1005859375,
2185
+ "learning_rate": 0.00010469500661582536,
2186
+ "loss": 1.0138,
2187
+ "step": 302
2188
+ },
2189
+ {
2190
+ "epoch": 1.964110929853181,
2191
+ "grad_norm": 0.1015625,
2192
+ "learning_rate": 0.00010417366129280133,
2193
+ "loss": 0.9903,
2194
+ "step": 303
2195
+ },
2196
+ {
2197
+ "epoch": 1.9706362153344208,
2198
+ "grad_norm": 0.099609375,
2199
+ "learning_rate": 0.0001036522023057659,
2200
+ "loss": 0.962,
2201
+ "step": 304
2202
+ },
2203
+ {
2204
+ "epoch": 1.9771615008156607,
2205
+ "grad_norm": 0.10302734375,
2206
+ "learning_rate": 0.00010313064385594822,
2207
+ "loss": 0.9793,
2208
+ "step": 305
2209
+ },
2210
+ {
2211
+ "epoch": 1.9836867862969005,
2212
+ "grad_norm": 0.103515625,
2213
+ "learning_rate": 0.0001026090001472861,
2214
+ "loss": 0.975,
2215
+ "step": 306
2216
+ },
2217
+ {
2218
+ "epoch": 1.9902120717781404,
2219
+ "grad_norm": 0.10107421875,
2220
+ "learning_rate": 0.00010208728538603929,
2221
+ "loss": 1.0116,
2222
+ "step": 307
2223
+ },
2224
+ {
2225
+ "epoch": 1.99673735725938,
2226
+ "grad_norm": 0.09814453125,
2227
+ "learning_rate": 0.00010156551378040258,
2228
+ "loss": 0.938,
2229
+ "step": 308
2230
+ },
2231
+ {
2232
+ "epoch": 2.00326264274062,
2233
+ "grad_norm": 0.10009765625,
2234
+ "learning_rate": 0.00010104369954011883,
2235
+ "loss": 0.9709,
2236
+ "step": 309
2237
+ },
2238
+ {
2239
+ "epoch": 2.0097879282218596,
2240
+ "grad_norm": 0.103515625,
2241
+ "learning_rate": 0.00010052185687609197,
2242
+ "loss": 0.9863,
2243
+ "step": 310
2244
+ },
2245
+ {
2246
+ "epoch": 2.00163132137031,
2247
+ "grad_norm": 0.125,
2248
+ "learning_rate": 0.0001,
2249
+ "loss": 0.9435,
2250
+ "step": 311
2251
+ },
2252
+ {
2253
+ "epoch": 2.00815660685155,
2254
+ "grad_norm": 0.10498046875,
2255
+ "learning_rate": 9.947814312390808e-05,
2256
+ "loss": 0.9615,
2257
+ "step": 312
2258
+ },
2259
+ {
2260
+ "epoch": 2.00815660685155,
2261
+ "eval_loss": 1.0137028694152832,
2262
+ "eval_runtime": 236.7283,
2263
+ "eval_samples_per_second": 1.8,
2264
+ "eval_steps_per_second": 0.9,
2265
+ "step": 312
2266
+ },
2267
+ {
2268
+ "epoch": 2.0146818923327894,
2269
+ "grad_norm": 0.1025390625,
2270
+ "learning_rate": 9.89563004598812e-05,
2271
+ "loss": 0.9438,
2272
+ "step": 313
2273
+ },
2274
+ {
2275
+ "epoch": 2.0212071778140293,
2276
+ "grad_norm": 0.10400390625,
2277
+ "learning_rate": 9.843448621959745e-05,
2278
+ "loss": 0.9277,
2279
+ "step": 314
2280
+ },
2281
+ {
2282
+ "epoch": 2.027732463295269,
2283
+ "grad_norm": 0.10498046875,
2284
+ "learning_rate": 9.79127146139607e-05,
2285
+ "loss": 0.9363,
2286
+ "step": 315
2287
+ },
2288
+ {
2289
+ "epoch": 2.034257748776509,
2290
+ "grad_norm": 0.1103515625,
2291
+ "learning_rate": 9.739099985271394e-05,
2292
+ "loss": 0.9413,
2293
+ "step": 316
2294
+ },
2295
+ {
2296
+ "epoch": 2.040783034257749,
2297
+ "grad_norm": 0.111328125,
2298
+ "learning_rate": 9.686935614405183e-05,
2299
+ "loss": 0.9416,
2300
+ "step": 317
2301
+ },
2302
+ {
2303
+ "epoch": 2.0473083197389887,
2304
+ "grad_norm": 0.1083984375,
2305
+ "learning_rate": 9.63477976942341e-05,
2306
+ "loss": 0.9062,
2307
+ "step": 318
2308
+ },
2309
+ {
2310
+ "epoch": 2.053833605220228,
2311
+ "grad_norm": 0.10400390625,
2312
+ "learning_rate": 9.582633870719871e-05,
2313
+ "loss": 0.9278,
2314
+ "step": 319
2315
+ },
2316
+ {
2317
+ "epoch": 2.060358890701468,
2318
+ "grad_norm": 0.10546875,
2319
+ "learning_rate": 9.530499338417465e-05,
2320
+ "loss": 0.9146,
2321
+ "step": 320
2322
+ },
2323
+ {
2324
+ "epoch": 2.066884176182708,
2325
+ "grad_norm": 0.10498046875,
2326
+ "learning_rate": 9.478377592329563e-05,
2327
+ "loss": 0.9237,
2328
+ "step": 321
2329
+ },
2330
+ {
2331
+ "epoch": 2.073409461663948,
2332
+ "grad_norm": 0.11376953125,
2333
+ "learning_rate": 9.426270051921304e-05,
2334
+ "loss": 0.9012,
2335
+ "step": 322
2336
+ },
2337
+ {
2338
+ "epoch": 2.0799347471451877,
2339
+ "grad_norm": 0.10791015625,
2340
+ "learning_rate": 9.374178136270966e-05,
2341
+ "loss": 0.9912,
2342
+ "step": 323
2343
+ },
2344
+ {
2345
+ "epoch": 2.0864600326264275,
2346
+ "grad_norm": 0.10400390625,
2347
+ "learning_rate": 9.32210326403131e-05,
2348
+ "loss": 0.9729,
2349
+ "step": 324
2350
+ },
2351
+ {
2352
+ "epoch": 2.0929853181076674,
2353
+ "grad_norm": 0.10693359375,
2354
+ "learning_rate": 9.270046853390925e-05,
2355
+ "loss": 0.9389,
2356
+ "step": 325
2357
+ },
2358
+ {
2359
+ "epoch": 2.099510603588907,
2360
+ "grad_norm": 0.11279296875,
2361
+ "learning_rate": 9.218010322035647e-05,
2362
+ "loss": 0.9115,
2363
+ "step": 326
2364
+ },
2365
+ {
2366
+ "epoch": 2.1060358890701467,
2367
+ "grad_norm": 0.10693359375,
2368
+ "learning_rate": 9.165995087109911e-05,
2369
+ "loss": 0.9356,
2370
+ "step": 327
2371
+ },
2372
+ {
2373
+ "epoch": 2.1125611745513866,
2374
+ "grad_norm": 0.11376953125,
2375
+ "learning_rate": 9.114002565178172e-05,
2376
+ "loss": 0.9522,
2377
+ "step": 328
2378
+ },
2379
+ {
2380
+ "epoch": 2.1190864600326265,
2381
+ "grad_norm": 0.10791015625,
2382
+ "learning_rate": 9.062034172186341e-05,
2383
+ "loss": 0.9283,
2384
+ "step": 329
2385
+ },
2386
+ {
2387
+ "epoch": 2.1256117455138663,
2388
+ "grad_norm": 0.109375,
2389
+ "learning_rate": 9.010091323423192e-05,
2390
+ "loss": 0.9014,
2391
+ "step": 330
2392
+ },
2393
+ {
2394
+ "epoch": 2.132137030995106,
2395
+ "grad_norm": 0.109375,
2396
+ "learning_rate": 8.958175433481855e-05,
2397
+ "loss": 0.9904,
2398
+ "step": 331
2399
+ },
2400
+ {
2401
+ "epoch": 2.1386623164763456,
2402
+ "grad_norm": 0.10791015625,
2403
+ "learning_rate": 8.906287916221259e-05,
2404
+ "loss": 0.9195,
2405
+ "step": 332
2406
+ },
2407
+ {
2408
+ "epoch": 2.1451876019575855,
2409
+ "grad_norm": 0.1123046875,
2410
+ "learning_rate": 8.85443018472764e-05,
2411
+ "loss": 0.9338,
2412
+ "step": 333
2413
+ },
2414
+ {
2415
+ "epoch": 2.1517128874388254,
2416
+ "grad_norm": 0.11669921875,
2417
+ "learning_rate": 8.802603651276078e-05,
2418
+ "loss": 0.9206,
2419
+ "step": 334
2420
+ },
2421
+ {
2422
+ "epoch": 2.1582381729200653,
2423
+ "grad_norm": 0.111328125,
2424
+ "learning_rate": 8.750809727291995e-05,
2425
+ "loss": 0.914,
2426
+ "step": 335
2427
+ },
2428
+ {
2429
+ "epoch": 2.164763458401305,
2430
+ "grad_norm": 0.11279296875,
2431
+ "learning_rate": 8.699049823312748e-05,
2432
+ "loss": 0.9463,
2433
+ "step": 336
2434
+ },
2435
+ {
2436
+ "epoch": 2.171288743882545,
2437
+ "grad_norm": 0.1162109375,
2438
+ "learning_rate": 8.647325348949206e-05,
2439
+ "loss": 0.965,
2440
+ "step": 337
2441
+ },
2442
+ {
2443
+ "epoch": 2.177814029363785,
2444
+ "grad_norm": 0.111328125,
2445
+ "learning_rate": 8.595637712847358e-05,
2446
+ "loss": 0.934,
2447
+ "step": 338
2448
+ },
2449
+ {
2450
+ "epoch": 2.1843393148450243,
2451
+ "grad_norm": 0.11083984375,
2452
+ "learning_rate": 8.543988322649954e-05,
2453
+ "loss": 0.9272,
2454
+ "step": 339
2455
+ },
2456
+ {
2457
+ "epoch": 2.190864600326264,
2458
+ "grad_norm": 0.11279296875,
2459
+ "learning_rate": 8.492378584958164e-05,
2460
+ "loss": 0.9586,
2461
+ "step": 340
2462
+ },
2463
+ {
2464
+ "epoch": 2.197389885807504,
2465
+ "grad_norm": 0.111328125,
2466
+ "learning_rate": 8.440809905293288e-05,
2467
+ "loss": 0.9502,
2468
+ "step": 341
2469
+ },
2470
+ {
2471
+ "epoch": 2.203915171288744,
2472
+ "grad_norm": 0.11669921875,
2473
+ "learning_rate": 8.389283688058454e-05,
2474
+ "loss": 0.932,
2475
+ "step": 342
2476
+ },
2477
+ {
2478
+ "epoch": 2.210440456769984,
2479
+ "grad_norm": 0.1103515625,
2480
+ "learning_rate": 8.337801336500383e-05,
2481
+ "loss": 0.8973,
2482
+ "step": 343
2483
+ },
2484
+ {
2485
+ "epoch": 2.2169657422512237,
2486
+ "grad_norm": 0.111328125,
2487
+ "learning_rate": 8.286364252671187e-05,
2488
+ "loss": 0.9526,
2489
+ "step": 344
2490
+ },
2491
+ {
2492
+ "epoch": 2.223491027732463,
2493
+ "grad_norm": 0.119140625,
2494
+ "learning_rate": 8.234973837390154e-05,
2495
+ "loss": 0.9433,
2496
+ "step": 345
2497
+ },
2498
+ {
2499
+ "epoch": 2.230016313213703,
2500
+ "grad_norm": 0.12255859375,
2501
+ "learning_rate": 8.183631490205637e-05,
2502
+ "loss": 0.9374,
2503
+ "step": 346
2504
+ },
2505
+ {
2506
+ "epoch": 2.236541598694943,
2507
+ "grad_norm": 0.1171875,
2508
+ "learning_rate": 8.132338609356904e-05,
2509
+ "loss": 0.9552,
2510
+ "step": 347
2511
+ },
2512
+ {
2513
+ "epoch": 2.2430668841761827,
2514
+ "grad_norm": 0.115234375,
2515
+ "learning_rate": 8.081096591736076e-05,
2516
+ "loss": 0.9477,
2517
+ "step": 348
2518
+ },
2519
+ {
2520
+ "epoch": 2.2495921696574226,
2521
+ "grad_norm": 0.12109375,
2522
+ "learning_rate": 8.029906832850098e-05,
2523
+ "loss": 0.9447,
2524
+ "step": 349
2525
+ },
2526
+ {
2527
+ "epoch": 2.2561174551386625,
2528
+ "grad_norm": 0.12158203125,
2529
+ "learning_rate": 7.978770726782697e-05,
2530
+ "loss": 0.967,
2531
+ "step": 350
2532
+ },
2533
+ {
2534
+ "epoch": 2.262642740619902,
2535
+ "grad_norm": 0.11474609375,
2536
+ "learning_rate": 7.927689666156458e-05,
2537
+ "loss": 0.9543,
2538
+ "step": 351
2539
+ },
2540
+ {
2541
+ "epoch": 2.262642740619902,
2542
+ "eval_loss": 1.0135549306869507,
2543
+ "eval_runtime": 236.6247,
2544
+ "eval_samples_per_second": 1.8,
2545
+ "eval_steps_per_second": 0.9,
2546
+ "step": 351
2547
+ },
2548
+ {
2549
+ "epoch": 2.2691680261011418,
2550
+ "grad_norm": 0.11962890625,
2551
+ "learning_rate": 7.876665042094867e-05,
2552
+ "loss": 0.9324,
2553
+ "step": 352
2554
+ },
2555
+ {
2556
+ "epoch": 2.2756933115823816,
2557
+ "grad_norm": 0.11572265625,
2558
+ "learning_rate": 7.825698244184431e-05,
2559
+ "loss": 0.916,
2560
+ "step": 353
2561
+ },
2562
+ {
2563
+ "epoch": 2.2822185970636215,
2564
+ "grad_norm": 0.11279296875,
2565
+ "learning_rate": 7.774790660436858e-05,
2566
+ "loss": 0.944,
2567
+ "step": 354
2568
+ },
2569
+ {
2570
+ "epoch": 2.2887438825448614,
2571
+ "grad_norm": 0.111328125,
2572
+ "learning_rate": 7.723943677251222e-05,
2573
+ "loss": 0.9552,
2574
+ "step": 355
2575
+ },
2576
+ {
2577
+ "epoch": 2.2952691680261013,
2578
+ "grad_norm": 0.11083984375,
2579
+ "learning_rate": 7.673158679376234e-05,
2580
+ "loss": 0.9198,
2581
+ "step": 356
2582
+ },
2583
+ {
2584
+ "epoch": 2.301794453507341,
2585
+ "grad_norm": 0.11572265625,
2586
+ "learning_rate": 7.622437049872512e-05,
2587
+ "loss": 0.8879,
2588
+ "step": 357
2589
+ },
2590
+ {
2591
+ "epoch": 2.3083197389885806,
2592
+ "grad_norm": 0.11279296875,
2593
+ "learning_rate": 7.57178017007492e-05,
2594
+ "loss": 0.9387,
2595
+ "step": 358
2596
+ },
2597
+ {
2598
+ "epoch": 2.3148450244698204,
2599
+ "grad_norm": 0.11572265625,
2600
+ "learning_rate": 7.521189419554963e-05,
2601
+ "loss": 0.9313,
2602
+ "step": 359
2603
+ },
2604
+ {
2605
+ "epoch": 2.3213703099510603,
2606
+ "grad_norm": 0.11474609375,
2607
+ "learning_rate": 7.470666176083192e-05,
2608
+ "loss": 0.9465,
2609
+ "step": 360
2610
+ },
2611
+ {
2612
+ "epoch": 2.3278955954323,
2613
+ "grad_norm": 0.11572265625,
2614
+ "learning_rate": 7.420211815591709e-05,
2615
+ "loss": 0.9473,
2616
+ "step": 361
2617
+ },
2618
+ {
2619
+ "epoch": 2.33442088091354,
2620
+ "grad_norm": 0.10791015625,
2621
+ "learning_rate": 7.369827712136661e-05,
2622
+ "loss": 0.9085,
2623
+ "step": 362
2624
+ },
2625
+ {
2626
+ "epoch": 2.34094616639478,
2627
+ "grad_norm": 0.119140625,
2628
+ "learning_rate": 7.319515237860864e-05,
2629
+ "loss": 0.9189,
2630
+ "step": 363
2631
+ },
2632
+ {
2633
+ "epoch": 2.34747145187602,
2634
+ "grad_norm": 0.11279296875,
2635
+ "learning_rate": 7.269275762956392e-05,
2636
+ "loss": 0.907,
2637
+ "step": 364
2638
+ },
2639
+ {
2640
+ "epoch": 2.3539967373572592,
2641
+ "grad_norm": 0.1103515625,
2642
+ "learning_rate": 7.219110655627281e-05,
2643
+ "loss": 0.9054,
2644
+ "step": 365
2645
+ },
2646
+ {
2647
+ "epoch": 2.360522022838499,
2648
+ "grad_norm": 0.1171875,
2649
+ "learning_rate": 7.169021282052283e-05,
2650
+ "loss": 0.9429,
2651
+ "step": 366
2652
+ },
2653
+ {
2654
+ "epoch": 2.367047308319739,
2655
+ "grad_norm": 0.11865234375,
2656
+ "learning_rate": 7.119009006347625e-05,
2657
+ "loss": 0.9486,
2658
+ "step": 367
2659
+ },
2660
+ {
2661
+ "epoch": 2.373572593800979,
2662
+ "grad_norm": 0.1181640625,
2663
+ "learning_rate": 7.069075190529888e-05,
2664
+ "loss": 0.9674,
2665
+ "step": 368
2666
+ },
2667
+ {
2668
+ "epoch": 2.3800978792822187,
2669
+ "grad_norm": 0.11376953125,
2670
+ "learning_rate": 7.019221194478904e-05,
2671
+ "loss": 0.9107,
2672
+ "step": 369
2673
+ },
2674
+ {
2675
+ "epoch": 2.3866231647634586,
2676
+ "grad_norm": 0.1201171875,
2677
+ "learning_rate": 6.969448375900715e-05,
2678
+ "loss": 0.9486,
2679
+ "step": 370
2680
+ },
2681
+ {
2682
+ "epoch": 2.393148450244698,
2683
+ "grad_norm": 0.11328125,
2684
+ "learning_rate": 6.919758090290614e-05,
2685
+ "loss": 0.9153,
2686
+ "step": 371
2687
+ },
2688
+ {
2689
+ "epoch": 2.399673735725938,
2690
+ "grad_norm": 0.1171875,
2691
+ "learning_rate": 6.870151690896209e-05,
2692
+ "loss": 0.9534,
2693
+ "step": 372
2694
+ },
2695
+ {
2696
+ "epoch": 2.4061990212071778,
2697
+ "grad_norm": 0.12255859375,
2698
+ "learning_rate": 6.820630528680597e-05,
2699
+ "loss": 0.9451,
2700
+ "step": 373
2701
+ },
2702
+ {
2703
+ "epoch": 2.4127243066884176,
2704
+ "grad_norm": 0.11865234375,
2705
+ "learning_rate": 6.77119595228554e-05,
2706
+ "loss": 0.9591,
2707
+ "step": 374
2708
+ },
2709
+ {
2710
+ "epoch": 2.4192495921696575,
2711
+ "grad_norm": 0.1171875,
2712
+ "learning_rate": 6.721849307994756e-05,
2713
+ "loss": 0.9148,
2714
+ "step": 375
2715
+ },
2716
+ {
2717
+ "epoch": 2.4257748776508974,
2718
+ "grad_norm": 0.11572265625,
2719
+ "learning_rate": 6.672591939697261e-05,
2720
+ "loss": 0.9226,
2721
+ "step": 376
2722
+ },
2723
+ {
2724
+ "epoch": 2.432300163132137,
2725
+ "grad_norm": 0.11181640625,
2726
+ "learning_rate": 6.623425188850746e-05,
2727
+ "loss": 0.9417,
2728
+ "step": 377
2729
+ },
2730
+ {
2731
+ "epoch": 2.4388254486133767,
2732
+ "grad_norm": 0.1142578125,
2733
+ "learning_rate": 6.574350394445074e-05,
2734
+ "loss": 0.9601,
2735
+ "step": 378
2736
+ },
2737
+ {
2738
+ "epoch": 2.4453507340946166,
2739
+ "grad_norm": 0.11279296875,
2740
+ "learning_rate": 6.525368892965784e-05,
2741
+ "loss": 0.926,
2742
+ "step": 379
2743
+ },
2744
+ {
2745
+ "epoch": 2.4518760195758564,
2746
+ "grad_norm": 0.11474609375,
2747
+ "learning_rate": 6.476482018357713e-05,
2748
+ "loss": 0.9551,
2749
+ "step": 380
2750
+ },
2751
+ {
2752
+ "epoch": 2.4584013050570963,
2753
+ "grad_norm": 0.11279296875,
2754
+ "learning_rate": 6.427691101988673e-05,
2755
+ "loss": 0.8944,
2756
+ "step": 381
2757
+ },
2758
+ {
2759
+ "epoch": 2.464926590538336,
2760
+ "grad_norm": 0.1181640625,
2761
+ "learning_rate": 6.378997472613169e-05,
2762
+ "loss": 0.9158,
2763
+ "step": 382
2764
+ },
2765
+ {
2766
+ "epoch": 2.471451876019576,
2767
+ "grad_norm": 0.12158203125,
2768
+ "learning_rate": 6.330402456336237e-05,
2769
+ "loss": 0.9419,
2770
+ "step": 383
2771
+ },
2772
+ {
2773
+ "epoch": 2.4779771615008155,
2774
+ "grad_norm": 0.115234375,
2775
+ "learning_rate": 6.281907376577316e-05,
2776
+ "loss": 0.9032,
2777
+ "step": 384
2778
+ },
2779
+ {
2780
+ "epoch": 2.4845024469820554,
2781
+ "grad_norm": 0.11572265625,
2782
+ "learning_rate": 6.233513554034204e-05,
2783
+ "loss": 0.9402,
2784
+ "step": 385
2785
+ },
2786
+ {
2787
+ "epoch": 2.4910277324632952,
2788
+ "grad_norm": 0.11474609375,
2789
+ "learning_rate": 6.185222306647105e-05,
2790
+ "loss": 0.9304,
2791
+ "step": 386
2792
+ },
2793
+ {
2794
+ "epoch": 2.497553017944535,
2795
+ "grad_norm": 0.1162109375,
2796
+ "learning_rate": 6.137034949562719e-05,
2797
+ "loss": 0.889,
2798
+ "step": 387
2799
+ },
2800
+ {
2801
+ "epoch": 2.504078303425775,
2802
+ "grad_norm": 0.1201171875,
2803
+ "learning_rate": 6.0889527950984416e-05,
2804
+ "loss": 0.9222,
2805
+ "step": 388
2806
+ },
2807
+ {
2808
+ "epoch": 2.5106035889070144,
2809
+ "grad_norm": 0.11767578125,
2810
+ "learning_rate": 6.040977152706613e-05,
2811
+ "loss": 0.9559,
2812
+ "step": 389
2813
+ },
2814
+ {
2815
+ "epoch": 2.5171288743882547,
2816
+ "grad_norm": 0.11669921875,
2817
+ "learning_rate": 5.9931093289388576e-05,
2818
+ "loss": 0.9429,
2819
+ "step": 390
2820
+ },
2821
+ {
2822
+ "epoch": 2.5171288743882547,
2823
+ "eval_loss": 1.01093590259552,
2824
+ "eval_runtime": 236.9616,
2825
+ "eval_samples_per_second": 1.798,
2826
+ "eval_steps_per_second": 0.899,
2827
+ "step": 390
2828
+ },
2829
+ {
2830
+ "epoch": 2.523654159869494,
2831
+ "grad_norm": 0.11328125,
2832
+ "learning_rate": 5.94535062741052e-05,
2833
+ "loss": 0.9203,
2834
+ "step": 391
2835
+ },
2836
+ {
2837
+ "epoch": 2.530179445350734,
2838
+ "grad_norm": 0.115234375,
2839
+ "learning_rate": 5.897702348765129e-05,
2840
+ "loss": 0.9144,
2841
+ "step": 392
2842
+ },
2843
+ {
2844
+ "epoch": 2.536704730831974,
2845
+ "grad_norm": 0.12158203125,
2846
+ "learning_rate": 5.8501657906390175e-05,
2847
+ "loss": 0.9355,
2848
+ "step": 393
2849
+ },
2850
+ {
2851
+ "epoch": 2.5432300163132138,
2852
+ "grad_norm": 0.11474609375,
2853
+ "learning_rate": 5.8027422476259385e-05,
2854
+ "loss": 0.9335,
2855
+ "step": 394
2856
+ },
2857
+ {
2858
+ "epoch": 2.5497553017944536,
2859
+ "grad_norm": 0.11279296875,
2860
+ "learning_rate": 5.755433011241851e-05,
2861
+ "loss": 0.9035,
2862
+ "step": 395
2863
+ },
2864
+ {
2865
+ "epoch": 2.556280587275693,
2866
+ "grad_norm": 0.11767578125,
2867
+ "learning_rate": 5.7082393698897166e-05,
2868
+ "loss": 0.9362,
2869
+ "step": 396
2870
+ },
2871
+ {
2872
+ "epoch": 2.5628058727569334,
2873
+ "grad_norm": 0.1123046875,
2874
+ "learning_rate": 5.6611626088244194e-05,
2875
+ "loss": 0.9197,
2876
+ "step": 397
2877
+ },
2878
+ {
2879
+ "epoch": 2.569331158238173,
2880
+ "grad_norm": 0.1181640625,
2881
+ "learning_rate": 5.614204010117785e-05,
2882
+ "loss": 0.9333,
2883
+ "step": 398
2884
+ },
2885
+ {
2886
+ "epoch": 2.5758564437194127,
2887
+ "grad_norm": 0.11669921875,
2888
+ "learning_rate": 5.567364852623629e-05,
2889
+ "loss": 0.9325,
2890
+ "step": 399
2891
+ },
2892
+ {
2893
+ "epoch": 2.5823817292006526,
2894
+ "grad_norm": 0.12255859375,
2895
+ "learning_rate": 5.520646411942951e-05,
2896
+ "loss": 0.9402,
2897
+ "step": 400
2898
+ },
2899
+ {
2900
+ "epoch": 2.5889070146818924,
2901
+ "grad_norm": 0.11572265625,
2902
+ "learning_rate": 5.474049960389205e-05,
2903
+ "loss": 0.94,
2904
+ "step": 401
2905
+ },
2906
+ {
2907
+ "epoch": 2.5954323001631323,
2908
+ "grad_norm": 0.12060546875,
2909
+ "learning_rate": 5.4275767669536146e-05,
2910
+ "loss": 0.9528,
2911
+ "step": 402
2912
+ },
2913
+ {
2914
+ "epoch": 2.6019575856443717,
2915
+ "grad_norm": 0.1240234375,
2916
+ "learning_rate": 5.381228097270659e-05,
2917
+ "loss": 0.9199,
2918
+ "step": 403
2919
+ },
2920
+ {
2921
+ "epoch": 2.6084828711256116,
2922
+ "grad_norm": 0.1171875,
2923
+ "learning_rate": 5.3350052135835616e-05,
2924
+ "loss": 0.9296,
2925
+ "step": 404
2926
+ },
2927
+ {
2928
+ "epoch": 2.6150081566068515,
2929
+ "grad_norm": 0.1142578125,
2930
+ "learning_rate": 5.2889093747099427e-05,
2931
+ "loss": 0.9182,
2932
+ "step": 405
2933
+ },
2934
+ {
2935
+ "epoch": 2.6215334420880914,
2936
+ "grad_norm": 0.11376953125,
2937
+ "learning_rate": 5.242941836007536e-05,
2938
+ "loss": 0.9101,
2939
+ "step": 406
2940
+ },
2941
+ {
2942
+ "epoch": 2.6280587275693312,
2943
+ "grad_norm": 0.1181640625,
2944
+ "learning_rate": 5.197103849339978e-05,
2945
+ "loss": 0.9244,
2946
+ "step": 407
2947
+ },
2948
+ {
2949
+ "epoch": 2.634584013050571,
2950
+ "grad_norm": 0.11865234375,
2951
+ "learning_rate": 5.151396663042749e-05,
2952
+ "loss": 0.9184,
2953
+ "step": 408
2954
+ },
2955
+ {
2956
+ "epoch": 2.641109298531811,
2957
+ "grad_norm": 0.1171875,
2958
+ "learning_rate": 5.105821521889147e-05,
2959
+ "loss": 0.921,
2960
+ "step": 409
2961
+ },
2962
+ {
2963
+ "epoch": 2.6476345840130504,
2964
+ "grad_norm": 0.12158203125,
2965
+ "learning_rate": 5.060379667056399e-05,
2966
+ "loss": 0.9483,
2967
+ "step": 410
2968
+ },
2969
+ {
2970
+ "epoch": 2.6541598694942903,
2971
+ "grad_norm": 0.12060546875,
2972
+ "learning_rate": 5.015072336091866e-05,
2973
+ "loss": 0.9114,
2974
+ "step": 411
2975
+ },
2976
+ {
2977
+ "epoch": 2.66068515497553,
2978
+ "grad_norm": 0.1171875,
2979
+ "learning_rate": 4.969900762879325e-05,
2980
+ "loss": 0.9111,
2981
+ "step": 412
2982
+ },
2983
+ {
2984
+ "epoch": 2.66721044045677,
2985
+ "grad_norm": 0.1220703125,
2986
+ "learning_rate": 4.924866177605389e-05,
2987
+ "loss": 0.9212,
2988
+ "step": 413
2989
+ },
2990
+ {
2991
+ "epoch": 2.67373572593801,
2992
+ "grad_norm": 0.11328125,
2993
+ "learning_rate": 4.8799698067259757e-05,
2994
+ "loss": 0.9264,
2995
+ "step": 414
2996
+ },
2997
+ {
2998
+ "epoch": 2.6802610114192493,
2999
+ "grad_norm": 0.11083984375,
3000
+ "learning_rate": 4.8352128729329226e-05,
3001
+ "loss": 0.9116,
3002
+ "step": 415
3003
+ },
3004
+ {
3005
+ "epoch": 2.6867862969004896,
3006
+ "grad_norm": 0.11083984375,
3007
+ "learning_rate": 4.790596595120699e-05,
3008
+ "loss": 0.8868,
3009
+ "step": 416
3010
+ },
3011
+ {
3012
+ "epoch": 2.693311582381729,
3013
+ "grad_norm": 0.12060546875,
3014
+ "learning_rate": 4.746122188353182e-05,
3015
+ "loss": 0.944,
3016
+ "step": 417
3017
+ },
3018
+ {
3019
+ "epoch": 2.699836867862969,
3020
+ "grad_norm": 0.1181640625,
3021
+ "learning_rate": 4.7017908638305995e-05,
3022
+ "loss": 0.8952,
3023
+ "step": 418
3024
+ },
3025
+ {
3026
+ "epoch": 2.706362153344209,
3027
+ "grad_norm": 0.11474609375,
3028
+ "learning_rate": 4.657603828856517e-05,
3029
+ "loss": 0.9058,
3030
+ "step": 419
3031
+ },
3032
+ {
3033
+ "epoch": 2.7128874388254487,
3034
+ "grad_norm": 0.11279296875,
3035
+ "learning_rate": 4.61356228680497e-05,
3036
+ "loss": 0.9116,
3037
+ "step": 420
3038
+ },
3039
+ {
3040
+ "epoch": 2.7194127243066886,
3041
+ "grad_norm": 0.1162109375,
3042
+ "learning_rate": 4.569667437087702e-05,
3043
+ "loss": 0.9119,
3044
+ "step": 421
3045
+ },
3046
+ {
3047
+ "epoch": 2.725938009787928,
3048
+ "grad_norm": 0.11572265625,
3049
+ "learning_rate": 4.5259204751214743e-05,
3050
+ "loss": 0.9118,
3051
+ "step": 422
3052
+ },
3053
+ {
3054
+ "epoch": 2.732463295269168,
3055
+ "grad_norm": 0.11767578125,
3056
+ "learning_rate": 4.48232259229554e-05,
3057
+ "loss": 0.9487,
3058
+ "step": 423
3059
+ },
3060
+ {
3061
+ "epoch": 2.7389885807504077,
3062
+ "grad_norm": 0.1162109375,
3063
+ "learning_rate": 4.4388749759391754e-05,
3064
+ "loss": 0.935,
3065
+ "step": 424
3066
+ },
3067
+ {
3068
+ "epoch": 2.7455138662316476,
3069
+ "grad_norm": 0.1162109375,
3070
+ "learning_rate": 4.395578809289349e-05,
3071
+ "loss": 0.9099,
3072
+ "step": 425
3073
+ },
3074
+ {
3075
+ "epoch": 2.7520391517128875,
3076
+ "grad_norm": 0.1171875,
3077
+ "learning_rate": 4.352435271458516e-05,
3078
+ "loss": 0.9145,
3079
+ "step": 426
3080
+ },
3081
+ {
3082
+ "epoch": 2.7585644371941274,
3083
+ "grad_norm": 0.11767578125,
3084
+ "learning_rate": 4.30944553740248e-05,
3085
+ "loss": 0.9546,
3086
+ "step": 427
3087
+ },
3088
+ {
3089
+ "epoch": 2.7650897226753672,
3090
+ "grad_norm": 0.119140625,
3091
+ "learning_rate": 4.2666107778884065e-05,
3092
+ "loss": 0.9493,
3093
+ "step": 428
3094
+ },
3095
+ {
3096
+ "epoch": 2.7716150081566067,
3097
+ "grad_norm": 0.1162109375,
3098
+ "learning_rate": 4.223932159462954e-05,
3099
+ "loss": 0.9474,
3100
+ "step": 429
3101
+ },
3102
+ {
3103
+ "epoch": 2.7716150081566067,
3104
+ "eval_loss": 1.0076324939727783,
3105
+ "eval_runtime": 236.9962,
3106
+ "eval_samples_per_second": 1.797,
3107
+ "eval_steps_per_second": 0.899,
3108
+ "step": 429
3109
+ },
3110
+ {
3111
+ "epoch": 2.7781402936378465,
3112
+ "grad_norm": 0.1181640625,
3113
+ "learning_rate": 4.181410844420474e-05,
3114
+ "loss": 0.912,
3115
+ "step": 430
3116
+ },
3117
+ {
3118
+ "epoch": 2.7846655791190864,
3119
+ "grad_norm": 0.12353515625,
3120
+ "learning_rate": 4.139047990771378e-05,
3121
+ "loss": 0.9421,
3122
+ "step": 431
3123
+ },
3124
+ {
3125
+ "epoch": 2.7911908646003263,
3126
+ "grad_norm": 0.119140625,
3127
+ "learning_rate": 4.096844752210598e-05,
3128
+ "loss": 0.9336,
3129
+ "step": 432
3130
+ },
3131
+ {
3132
+ "epoch": 2.797716150081566,
3133
+ "grad_norm": 0.1181640625,
3134
+ "learning_rate": 4.054802278086168e-05,
3135
+ "loss": 0.9236,
3136
+ "step": 433
3137
+ },
3138
+ {
3139
+ "epoch": 2.804241435562806,
3140
+ "grad_norm": 0.1171875,
3141
+ "learning_rate": 4.012921713367916e-05,
3142
+ "loss": 0.9253,
3143
+ "step": 434
3144
+ },
3145
+ {
3146
+ "epoch": 2.810766721044046,
3147
+ "grad_norm": 0.119140625,
3148
+ "learning_rate": 3.971204198616284e-05,
3149
+ "loss": 0.9349,
3150
+ "step": 435
3151
+ },
3152
+ {
3153
+ "epoch": 2.8172920065252853,
3154
+ "grad_norm": 0.1162109375,
3155
+ "learning_rate": 3.929650869951278e-05,
3156
+ "loss": 0.9411,
3157
+ "step": 436
3158
+ },
3159
+ {
3160
+ "epoch": 2.823817292006525,
3161
+ "grad_norm": 0.11669921875,
3162
+ "learning_rate": 3.8882628590215074e-05,
3163
+ "loss": 0.919,
3164
+ "step": 437
3165
+ },
3166
+ {
3167
+ "epoch": 2.830342577487765,
3168
+ "grad_norm": 0.1171875,
3169
+ "learning_rate": 3.84704129297339e-05,
3170
+ "loss": 0.8996,
3171
+ "step": 438
3172
+ },
3173
+ {
3174
+ "epoch": 2.836867862969005,
3175
+ "grad_norm": 0.11767578125,
3176
+ "learning_rate": 3.8059872944204324e-05,
3177
+ "loss": 0.9372,
3178
+ "step": 439
3179
+ },
3180
+ {
3181
+ "epoch": 2.843393148450245,
3182
+ "grad_norm": 0.1171875,
3183
+ "learning_rate": 3.7651019814126654e-05,
3184
+ "loss": 0.924,
3185
+ "step": 440
3186
+ },
3187
+ {
3188
+ "epoch": 2.8499184339314843,
3189
+ "grad_norm": 0.11474609375,
3190
+ "learning_rate": 3.724386467406211e-05,
3191
+ "loss": 0.92,
3192
+ "step": 441
3193
+ },
3194
+ {
3195
+ "epoch": 2.8564437194127246,
3196
+ "grad_norm": 0.12060546875,
3197
+ "learning_rate": 3.6838418612329305e-05,
3198
+ "loss": 0.9146,
3199
+ "step": 442
3200
+ },
3201
+ {
3202
+ "epoch": 2.862969004893964,
3203
+ "grad_norm": 0.12109375,
3204
+ "learning_rate": 3.6434692670702545e-05,
3205
+ "loss": 0.9371,
3206
+ "step": 443
3207
+ },
3208
+ {
3209
+ "epoch": 2.869494290375204,
3210
+ "grad_norm": 0.1181640625,
3211
+ "learning_rate": 3.60326978441109e-05,
3212
+ "loss": 0.9144,
3213
+ "step": 444
3214
+ },
3215
+ {
3216
+ "epoch": 2.8760195758564437,
3217
+ "grad_norm": 0.11376953125,
3218
+ "learning_rate": 3.563244508033887e-05,
3219
+ "loss": 0.9173,
3220
+ "step": 445
3221
+ },
3222
+ {
3223
+ "epoch": 2.8825448613376836,
3224
+ "grad_norm": 0.115234375,
3225
+ "learning_rate": 3.523394527972833e-05,
3226
+ "loss": 0.8944,
3227
+ "step": 446
3228
+ },
3229
+ {
3230
+ "epoch": 2.8890701468189235,
3231
+ "grad_norm": 0.1162109375,
3232
+ "learning_rate": 3.4837209294881467e-05,
3233
+ "loss": 0.9118,
3234
+ "step": 447
3235
+ },
3236
+ {
3237
+ "epoch": 2.895595432300163,
3238
+ "grad_norm": 0.11669921875,
3239
+ "learning_rate": 3.4442247930365426e-05,
3240
+ "loss": 0.9365,
3241
+ "step": 448
3242
+ },
3243
+ {
3244
+ "epoch": 2.902120717781403,
3245
+ "grad_norm": 0.11767578125,
3246
+ "learning_rate": 3.4049071942417896e-05,
3247
+ "loss": 0.9189,
3248
+ "step": 449
3249
+ },
3250
+ {
3251
+ "epoch": 2.9086460032626427,
3252
+ "grad_norm": 0.1201171875,
3253
+ "learning_rate": 3.365769203865425e-05,
3254
+ "loss": 0.9505,
3255
+ "step": 450
3256
+ },
3257
+ {
3258
+ "epoch": 2.9151712887438825,
3259
+ "grad_norm": 0.1181640625,
3260
+ "learning_rate": 3.3268118877776066e-05,
3261
+ "loss": 0.9264,
3262
+ "step": 451
3263
+ },
3264
+ {
3265
+ "epoch": 2.9216965742251224,
3266
+ "grad_norm": 0.11767578125,
3267
+ "learning_rate": 3.288036306928055e-05,
3268
+ "loss": 0.9301,
3269
+ "step": 452
3270
+ },
3271
+ {
3272
+ "epoch": 2.9282218597063623,
3273
+ "grad_norm": 0.11865234375,
3274
+ "learning_rate": 3.249443517317194e-05,
3275
+ "loss": 0.9225,
3276
+ "step": 453
3277
+ },
3278
+ {
3279
+ "epoch": 2.934747145187602,
3280
+ "grad_norm": 0.115234375,
3281
+ "learning_rate": 3.211034569967365e-05,
3282
+ "loss": 0.8961,
3283
+ "step": 454
3284
+ },
3285
+ {
3286
+ "epoch": 2.9412724306688416,
3287
+ "grad_norm": 0.1162109375,
3288
+ "learning_rate": 3.172810510894213e-05,
3289
+ "loss": 0.9446,
3290
+ "step": 455
3291
+ },
3292
+ {
3293
+ "epoch": 2.9477977161500815,
3294
+ "grad_norm": 0.12060546875,
3295
+ "learning_rate": 3.1347723810782134e-05,
3296
+ "loss": 0.934,
3297
+ "step": 456
3298
+ },
3299
+ {
3300
+ "epoch": 2.9543230016313213,
3301
+ "grad_norm": 0.11767578125,
3302
+ "learning_rate": 3.0969212164362957e-05,
3303
+ "loss": 0.9451,
3304
+ "step": 457
3305
+ },
3306
+ {
3307
+ "epoch": 2.960848287112561,
3308
+ "grad_norm": 0.11669921875,
3309
+ "learning_rate": 3.059258047793661e-05,
3310
+ "loss": 0.9477,
3311
+ "step": 458
3312
+ },
3313
+ {
3314
+ "epoch": 2.967373572593801,
3315
+ "grad_norm": 0.11669921875,
3316
+ "learning_rate": 3.0217839008556816e-05,
3317
+ "loss": 0.9171,
3318
+ "step": 459
3319
+ }
3320
+ ],
3321
+ "logging_steps": 1,
3322
+ "max_steps": 612,
3323
+ "num_input_tokens_seen": 0,
3324
+ "num_train_epochs": 4,
3325
+ "save_steps": 153,
3326
+ "stateful_callbacks": {
3327
+ "TrainerControl": {
3328
+ "args": {
3329
+ "should_epoch_stop": false,
3330
+ "should_evaluate": false,
3331
+ "should_log": false,
3332
+ "should_save": true,
3333
+ "should_training_stop": false
3334
+ },
3335
+ "attributes": {}
3336
+ }
3337
+ },
3338
+ "total_flos": 1.3689291797220557e+18,
3339
+ "train_batch_size": 2,
3340
+ "trial_name": null,
3341
+ "trial_params": null
3342
+ }
checkpoint459/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998c86e0068ec82450c4b585a291b75939d4efaf9fcfdeab3730d3a755504c16
3
+ size 5944
checkpoint612/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint612/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP",
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
+ "o_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint612/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b6c3f38631b19259be1102593c5323edca04adbbbdcccb63d2a50dcecc29d8
3
+ size 167832688
checkpoint612/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9b87269dc09e3db678af3e12b15648335471889c54ab735edd23cafc2ba09a
3
+ size 168625172
checkpoint612/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8915896c58dc4f63b8513f84b086c918856f8fbdefbe347e6d8944177de44dd2
3
+ size 14244
checkpoint612/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0daaafc8c17e56b7ca4eb7ee3472e889e34289a485f9c81babc2e83abbc131f8
3
+ size 1064
checkpoint612/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": "<|eot_id|>",
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
+ }
checkpoint612/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint612/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint612/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint612/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998c86e0068ec82450c4b585a291b75939d4efaf9fcfdeab3730d3a755504c16
3
+ size 5944
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_storage": "bfloat16",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": true,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": null,
38
+ "rope_theta": 500000.0,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.41.1",
42
+ "use_cache": false,
43
+ "vocab_size": 128256
44
+ }
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": "<|eot_id|>",
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff