Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +175 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +12 -0
- checkpoint-400/README.md +202 -0
- checkpoint-400/adapter_config.json +34 -0
- checkpoint-400/adapter_model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +17 -0
- checkpoint-400/tokenizer.json +3 -0
- checkpoint-400/tokenizer_config.json +2065 -0
- checkpoint-400/trainer_state.json +3473 -0
- checkpoint-400/training_args.bin +3 -0
- eval_results.json +7 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2065 -0
- train_results.json +8 -0
- trainer_log.jsonl +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- unsloth
|
| 9 |
+
- generated_from_trainer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: llm3br256
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# llm3br256
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the centime dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0123
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0001
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 5.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 0.0612 | 0.0449 | 5 | 0.0560 |
|
| 57 |
+
| 0.0411 | 0.0898 | 10 | 0.0357 |
|
| 58 |
+
| 0.0353 | 0.1347 | 15 | 0.0301 |
|
| 59 |
+
| 0.0286 | 0.1796 | 20 | 0.0264 |
|
| 60 |
+
| 0.0282 | 0.2245 | 25 | 0.0239 |
|
| 61 |
+
| 0.0223 | 0.2694 | 30 | 0.0224 |
|
| 62 |
+
| 0.0242 | 0.3143 | 35 | 0.0209 |
|
| 63 |
+
| 0.0211 | 0.3591 | 40 | 0.0203 |
|
| 64 |
+
| 0.0178 | 0.4040 | 45 | 0.0201 |
|
| 65 |
+
| 0.0206 | 0.4489 | 50 | 0.0196 |
|
| 66 |
+
| 0.0196 | 0.4938 | 55 | 0.0193 |
|
| 67 |
+
| 0.0173 | 0.5387 | 60 | 0.0193 |
|
| 68 |
+
| 0.0184 | 0.5836 | 65 | 0.0193 |
|
| 69 |
+
| 0.0194 | 0.6285 | 70 | 0.0191 |
|
| 70 |
+
| 0.0182 | 0.6734 | 75 | 0.0185 |
|
| 71 |
+
| 0.0169 | 0.7183 | 80 | 0.0183 |
|
| 72 |
+
| 0.0176 | 0.7632 | 85 | 0.0178 |
|
| 73 |
+
| 0.0158 | 0.8081 | 90 | 0.0176 |
|
| 74 |
+
| 0.02 | 0.8530 | 95 | 0.0172 |
|
| 75 |
+
| 0.0165 | 0.8979 | 100 | 0.0173 |
|
| 76 |
+
| 0.0181 | 0.9428 | 105 | 0.0168 |
|
| 77 |
+
| 0.0176 | 0.9877 | 110 | 0.0168 |
|
| 78 |
+
| 0.0184 | 1.0348 | 115 | 0.0183 |
|
| 79 |
+
| 0.0162 | 1.0797 | 120 | 0.0179 |
|
| 80 |
+
| 0.017 | 1.1246 | 125 | 0.0168 |
|
| 81 |
+
| 0.0143 | 1.1695 | 130 | 0.0167 |
|
| 82 |
+
| 0.0177 | 1.2144 | 135 | 0.0166 |
|
| 83 |
+
| 0.0138 | 1.2593 | 140 | 0.0161 |
|
| 84 |
+
| 0.0149 | 1.3042 | 145 | 0.0157 |
|
| 85 |
+
| 0.0162 | 1.3490 | 150 | 0.0160 |
|
| 86 |
+
| 0.0148 | 1.3939 | 155 | 0.0156 |
|
| 87 |
+
| 0.0168 | 1.4388 | 160 | 0.0154 |
|
| 88 |
+
| 0.0148 | 1.4837 | 165 | 0.0153 |
|
| 89 |
+
| 0.0146 | 1.5286 | 170 | 0.0154 |
|
| 90 |
+
| 0.0137 | 1.5735 | 175 | 0.0150 |
|
| 91 |
+
| 0.0144 | 1.6184 | 180 | 0.0150 |
|
| 92 |
+
| 0.0129 | 1.6633 | 185 | 0.0148 |
|
| 93 |
+
| 0.0139 | 1.7082 | 190 | 0.0145 |
|
| 94 |
+
| 0.013 | 1.7531 | 195 | 0.0145 |
|
| 95 |
+
| 0.013 | 1.7980 | 200 | 0.0144 |
|
| 96 |
+
| 0.0124 | 1.8429 | 205 | 0.0144 |
|
| 97 |
+
| 0.0135 | 1.8878 | 210 | 0.0143 |
|
| 98 |
+
| 0.0128 | 1.9327 | 215 | 0.0147 |
|
| 99 |
+
| 0.0149 | 1.9776 | 220 | 0.0143 |
|
| 100 |
+
| 0.0138 | 2.0247 | 225 | 0.0144 |
|
| 101 |
+
| 0.0127 | 2.0696 | 230 | 0.0143 |
|
| 102 |
+
| 0.0116 | 2.1145 | 235 | 0.0142 |
|
| 103 |
+
| 0.0128 | 2.1594 | 240 | 0.0143 |
|
| 104 |
+
| 0.0145 | 2.2043 | 245 | 0.0141 |
|
| 105 |
+
| 0.0147 | 2.2492 | 250 | 0.0139 |
|
| 106 |
+
| 0.0114 | 2.2941 | 255 | 0.0139 |
|
| 107 |
+
| 0.0114 | 2.3389 | 260 | 0.0139 |
|
| 108 |
+
| 0.0112 | 2.3838 | 265 | 0.0137 |
|
| 109 |
+
| 0.0105 | 2.4287 | 270 | 0.0138 |
|
| 110 |
+
| 0.0129 | 2.4736 | 275 | 0.0136 |
|
| 111 |
+
| 0.014 | 2.5185 | 280 | 0.0135 |
|
| 112 |
+
| 0.0124 | 2.5634 | 285 | 0.0136 |
|
| 113 |
+
| 0.0128 | 2.6083 | 290 | 0.0133 |
|
| 114 |
+
| 0.0106 | 2.6532 | 295 | 0.0129 |
|
| 115 |
+
| 0.0099 | 2.6981 | 300 | 0.0129 |
|
| 116 |
+
| 0.0111 | 2.7430 | 305 | 0.0129 |
|
| 117 |
+
| 0.0129 | 2.7879 | 310 | 0.0129 |
|
| 118 |
+
| 0.0088 | 2.8328 | 315 | 0.0129 |
|
| 119 |
+
| 0.0092 | 2.8777 | 320 | 0.0130 |
|
| 120 |
+
| 0.0086 | 2.9226 | 325 | 0.0129 |
|
| 121 |
+
| 0.0132 | 2.9675 | 330 | 0.0126 |
|
| 122 |
+
| 0.0126 | 3.0146 | 335 | 0.0130 |
|
| 123 |
+
| 0.0117 | 3.0595 | 340 | 0.0133 |
|
| 124 |
+
| 0.0102 | 3.1044 | 345 | 0.0132 |
|
| 125 |
+
| 0.0074 | 3.1493 | 350 | 0.0132 |
|
| 126 |
+
| 0.0105 | 3.1942 | 355 | 0.0129 |
|
| 127 |
+
| 0.0117 | 3.2391 | 360 | 0.0129 |
|
| 128 |
+
| 0.0107 | 3.2840 | 365 | 0.0127 |
|
| 129 |
+
| 0.0098 | 3.3288 | 370 | 0.0128 |
|
| 130 |
+
| 0.0092 | 3.3737 | 375 | 0.0127 |
|
| 131 |
+
| 0.0114 | 3.4186 | 380 | 0.0126 |
|
| 132 |
+
| 0.0118 | 3.4635 | 385 | 0.0125 |
|
| 133 |
+
| 0.0108 | 3.5084 | 390 | 0.0123 |
|
| 134 |
+
| 0.0092 | 3.5533 | 395 | 0.0123 |
|
| 135 |
+
| 0.0085 | 3.5982 | 400 | 0.0123 |
|
| 136 |
+
| 0.0088 | 3.6431 | 405 | 0.0126 |
|
| 137 |
+
| 0.0095 | 3.6880 | 410 | 0.0124 |
|
| 138 |
+
| 0.0072 | 3.7329 | 415 | 0.0124 |
|
| 139 |
+
| 0.0105 | 3.7778 | 420 | 0.0123 |
|
| 140 |
+
| 0.0115 | 3.8227 | 425 | 0.0122 |
|
| 141 |
+
| 0.007 | 3.8676 | 430 | 0.0121 |
|
| 142 |
+
| 0.0112 | 3.9125 | 435 | 0.0121 |
|
| 143 |
+
| 0.0103 | 3.9574 | 440 | 0.0121 |
|
| 144 |
+
| 0.0162 | 4.0045 | 445 | 0.0122 |
|
| 145 |
+
| 0.0079 | 4.0494 | 450 | 0.0125 |
|
| 146 |
+
| 0.0102 | 4.0943 | 455 | 0.0126 |
|
| 147 |
+
| 0.0087 | 4.1392 | 460 | 0.0126 |
|
| 148 |
+
| 0.0107 | 4.1841 | 465 | 0.0126 |
|
| 149 |
+
| 0.0105 | 4.2290 | 470 | 0.0125 |
|
| 150 |
+
| 0.0089 | 4.2738 | 475 | 0.0124 |
|
| 151 |
+
| 0.0061 | 4.3187 | 480 | 0.0125 |
|
| 152 |
+
| 0.0074 | 4.3636 | 485 | 0.0126 |
|
| 153 |
+
| 0.008 | 4.4085 | 490 | 0.0126 |
|
| 154 |
+
| 0.0092 | 4.4534 | 495 | 0.0125 |
|
| 155 |
+
| 0.0092 | 4.4983 | 500 | 0.0125 |
|
| 156 |
+
| 0.0061 | 4.5432 | 505 | 0.0124 |
|
| 157 |
+
| 0.0089 | 4.5881 | 510 | 0.0124 |
|
| 158 |
+
| 0.01 | 4.6330 | 515 | 0.0124 |
|
| 159 |
+
| 0.0081 | 4.6779 | 520 | 0.0124 |
|
| 160 |
+
| 0.0072 | 4.7228 | 525 | 0.0124 |
|
| 161 |
+
| 0.0078 | 4.7677 | 530 | 0.0124 |
|
| 162 |
+
| 0.009 | 4.8126 | 535 | 0.0124 |
|
| 163 |
+
| 0.0106 | 4.8575 | 540 | 0.0124 |
|
| 164 |
+
| 0.0079 | 4.9024 | 545 | 0.0124 |
|
| 165 |
+
| 0.0082 | 4.9473 | 550 | 0.0124 |
|
| 166 |
+
| 0.0082 | 4.9921 | 555 | 0.0124 |
|
| 167 |
+
|
| 168 |
+
|
| 169 |
+
### Framework versions
|
| 170 |
+
|
| 171 |
+
- PEFT 0.12.0
|
| 172 |
+
- Transformers 4.46.1
|
| 173 |
+
- Pytorch 2.4.0+cu121
|
| 174 |
+
- Datasets 3.1.0
|
| 175 |
+
- Tokenizers 0.20.3
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 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": 256,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98d60a989529395592fbc1377ce825165fc171ec17c5dbeaf9a5899917523336
|
| 3 |
+
size 1556140392
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.992143658810326,
|
| 3 |
+
"eval_loss": 0.012307128868997097,
|
| 4 |
+
"eval_runtime": 6.2704,
|
| 5 |
+
"eval_samples_per_second": 7.974,
|
| 6 |
+
"eval_steps_per_second": 2.073,
|
| 7 |
+
"total_flos": 9.281622886148997e+17,
|
| 8 |
+
"train_loss": 0.013788488566002868,
|
| 9 |
+
"train_runtime": 7381.5879,
|
| 10 |
+
"train_samples_per_second": 2.412,
|
| 11 |
+
"train_steps_per_second": 0.075
|
| 12 |
+
}
|
checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 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": 256,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-400/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98d60a989529395592fbc1377ce825165fc171ec17c5dbeaf9a5899917523336
|
| 3 |
+
size 1556140392
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a38d2d87db42942a43db76687eececd1279117f781e30be76875beb283fb2235
|
| 3 |
+
size 3112505578
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:887c547cfe997cc016f8919ea9378f7421ed1ca091feca29a1012f5e98acab9f
|
| 3 |
+
size 14308
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f3b4d6c58370f9113775e21223ec19d22837c34e61ae32cd8e2559f2ef885b8
|
| 3 |
+
size 1064
|
checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"split_special_tokens": false,
|
| 2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2065 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,3473 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.01230713166296482,
|
| 3 |
+
"best_model_checkpoint": "/home/paperspace/Data/models/centime/llm3br256/checkpoint-400",
|
| 4 |
+
"epoch": 3.5982042648709314,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008978675645342313,
|
| 13 |
+
"grad_norm": 0.12415610253810883,
|
| 14 |
+
"learning_rate": 1.7857142857142857e-06,
|
| 15 |
+
"loss": 0.0585,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.017957351290684626,
|
| 20 |
+
"grad_norm": 0.11934095621109009,
|
| 21 |
+
"learning_rate": 3.5714285714285714e-06,
|
| 22 |
+
"loss": 0.0573,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.026936026936026935,
|
| 27 |
+
"grad_norm": 0.12277644127607346,
|
| 28 |
+
"learning_rate": 5.357142857142857e-06,
|
| 29 |
+
"loss": 0.0583,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03591470258136925,
|
| 34 |
+
"grad_norm": 0.11886874586343765,
|
| 35 |
+
"learning_rate": 7.142857142857143e-06,
|
| 36 |
+
"loss": 0.0575,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04489337822671156,
|
| 41 |
+
"grad_norm": 0.12854638695716858,
|
| 42 |
+
"learning_rate": 8.92857142857143e-06,
|
| 43 |
+
"loss": 0.0612,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04489337822671156,
|
| 48 |
+
"eval_loss": 0.05599946156144142,
|
| 49 |
+
"eval_runtime": 8.137,
|
| 50 |
+
"eval_samples_per_second": 6.145,
|
| 51 |
+
"eval_steps_per_second": 1.598,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05387205387205387,
|
| 56 |
+
"grad_norm": 0.09200441092252731,
|
| 57 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 58 |
+
"loss": 0.05,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06285072951739619,
|
| 63 |
+
"grad_norm": 0.0996675118803978,
|
| 64 |
+
"learning_rate": 1.25e-05,
|
| 65 |
+
"loss": 0.0515,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0718294051627385,
|
| 70 |
+
"grad_norm": 0.08751285076141357,
|
| 71 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 72 |
+
"loss": 0.0436,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08080808080808081,
|
| 77 |
+
"grad_norm": 0.07102574408054352,
|
| 78 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 79 |
+
"loss": 0.044,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08978675645342311,
|
| 84 |
+
"grad_norm": 0.05904633551836014,
|
| 85 |
+
"learning_rate": 1.785714285714286e-05,
|
| 86 |
+
"loss": 0.0411,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08978675645342311,
|
| 91 |
+
"eval_loss": 0.035706527531147,
|
| 92 |
+
"eval_runtime": 6.2599,
|
| 93 |
+
"eval_samples_per_second": 7.987,
|
| 94 |
+
"eval_steps_per_second": 2.077,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.09876543209876543,
|
| 99 |
+
"grad_norm": 0.07080914080142975,
|
| 100 |
+
"learning_rate": 1.9642857142857145e-05,
|
| 101 |
+
"loss": 0.036,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.10774410774410774,
|
| 106 |
+
"grad_norm": 0.07890115678310394,
|
| 107 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 108 |
+
"loss": 0.0345,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.11672278338945005,
|
| 113 |
+
"grad_norm": 0.06593428552150726,
|
| 114 |
+
"learning_rate": 2.3214285714285715e-05,
|
| 115 |
+
"loss": 0.0351,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.12570145903479238,
|
| 120 |
+
"grad_norm": 0.04619583487510681,
|
| 121 |
+
"learning_rate": 2.5e-05,
|
| 122 |
+
"loss": 0.0338,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.13468013468013468,
|
| 127 |
+
"grad_norm": 0.04647090658545494,
|
| 128 |
+
"learning_rate": 2.6785714285714288e-05,
|
| 129 |
+
"loss": 0.0353,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.13468013468013468,
|
| 134 |
+
"eval_loss": 0.03013807348906994,
|
| 135 |
+
"eval_runtime": 6.2491,
|
| 136 |
+
"eval_samples_per_second": 8.001,
|
| 137 |
+
"eval_steps_per_second": 2.08,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.143658810325477,
|
| 142 |
+
"grad_norm": 0.04043864831328392,
|
| 143 |
+
"learning_rate": 2.857142857142857e-05,
|
| 144 |
+
"loss": 0.0304,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.1526374859708193,
|
| 149 |
+
"grad_norm": 0.043566230684518814,
|
| 150 |
+
"learning_rate": 3.0357142857142857e-05,
|
| 151 |
+
"loss": 0.0303,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.16161616161616163,
|
| 156 |
+
"grad_norm": 0.042150504887104034,
|
| 157 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 158 |
+
"loss": 0.0327,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.17059483726150393,
|
| 163 |
+
"grad_norm": 0.03820006549358368,
|
| 164 |
+
"learning_rate": 3.392857142857143e-05,
|
| 165 |
+
"loss": 0.0271,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.17957351290684623,
|
| 170 |
+
"grad_norm": 0.03358590975403786,
|
| 171 |
+
"learning_rate": 3.571428571428572e-05,
|
| 172 |
+
"loss": 0.0286,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.17957351290684623,
|
| 177 |
+
"eval_loss": 0.026352621614933014,
|
| 178 |
+
"eval_runtime": 6.261,
|
| 179 |
+
"eval_samples_per_second": 7.986,
|
| 180 |
+
"eval_steps_per_second": 2.076,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.18855218855218855,
|
| 185 |
+
"grad_norm": 0.03568700700998306,
|
| 186 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 187 |
+
"loss": 0.0293,
|
| 188 |
+
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.19753086419753085,
|
| 192 |
+
"grad_norm": 0.033443234860897064,
|
| 193 |
+
"learning_rate": 3.928571428571429e-05,
|
| 194 |
+
"loss": 0.027,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.20650953984287318,
|
| 199 |
+
"grad_norm": 0.03302915766835213,
|
| 200 |
+
"learning_rate": 4.107142857142857e-05,
|
| 201 |
+
"loss": 0.027,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.21548821548821548,
|
| 206 |
+
"grad_norm": 0.03412705287337303,
|
| 207 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 208 |
+
"loss": 0.0249,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.2244668911335578,
|
| 213 |
+
"grad_norm": 0.03498664125800133,
|
| 214 |
+
"learning_rate": 4.464285714285715e-05,
|
| 215 |
+
"loss": 0.0282,
|
| 216 |
+
"step": 25
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.2244668911335578,
|
| 220 |
+
"eval_loss": 0.023908844217658043,
|
| 221 |
+
"eval_runtime": 6.2612,
|
| 222 |
+
"eval_samples_per_second": 7.986,
|
| 223 |
+
"eval_steps_per_second": 2.076,
|
| 224 |
+
"step": 25
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.2334455667789001,
|
| 228 |
+
"grad_norm": 0.02876153774559498,
|
| 229 |
+
"learning_rate": 4.642857142857143e-05,
|
| 230 |
+
"loss": 0.0249,
|
| 231 |
+
"step": 26
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.24242424242424243,
|
| 235 |
+
"grad_norm": 0.03279321268200874,
|
| 236 |
+
"learning_rate": 4.8214285714285716e-05,
|
| 237 |
+
"loss": 0.0254,
|
| 238 |
+
"step": 27
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.25140291806958476,
|
| 242 |
+
"grad_norm": 0.03252970054745674,
|
| 243 |
+
"learning_rate": 5e-05,
|
| 244 |
+
"loss": 0.024,
|
| 245 |
+
"step": 28
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.26038159371492703,
|
| 249 |
+
"grad_norm": 0.02586694434285164,
|
| 250 |
+
"learning_rate": 5.1785714285714296e-05,
|
| 251 |
+
"loss": 0.0251,
|
| 252 |
+
"step": 29
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.26936026936026936,
|
| 256 |
+
"grad_norm": 0.028388267382979393,
|
| 257 |
+
"learning_rate": 5.3571428571428575e-05,
|
| 258 |
+
"loss": 0.0223,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.26936026936026936,
|
| 263 |
+
"eval_loss": 0.02239508368074894,
|
| 264 |
+
"eval_runtime": 6.2554,
|
| 265 |
+
"eval_samples_per_second": 7.993,
|
| 266 |
+
"eval_steps_per_second": 2.078,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2783389450056117,
|
| 271 |
+
"grad_norm": 0.040059663355350494,
|
| 272 |
+
"learning_rate": 5.535714285714286e-05,
|
| 273 |
+
"loss": 0.0281,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.287317620650954,
|
| 278 |
+
"grad_norm": 0.02905772626399994,
|
| 279 |
+
"learning_rate": 5.714285714285714e-05,
|
| 280 |
+
"loss": 0.0243,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.2962962962962963,
|
| 285 |
+
"grad_norm": 0.028802093118429184,
|
| 286 |
+
"learning_rate": 5.8928571428571435e-05,
|
| 287 |
+
"loss": 0.0224,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.3052749719416386,
|
| 292 |
+
"grad_norm": 0.031860049813985825,
|
| 293 |
+
"learning_rate": 6.0714285714285715e-05,
|
| 294 |
+
"loss": 0.0246,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.31425364758698093,
|
| 299 |
+
"grad_norm": 0.029610324651002884,
|
| 300 |
+
"learning_rate": 6.25e-05,
|
| 301 |
+
"loss": 0.0242,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.31425364758698093,
|
| 306 |
+
"eval_loss": 0.020946728065609932,
|
| 307 |
+
"eval_runtime": 6.2517,
|
| 308 |
+
"eval_samples_per_second": 7.998,
|
| 309 |
+
"eval_steps_per_second": 2.079,
|
| 310 |
+
"step": 35
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.32323232323232326,
|
| 314 |
+
"grad_norm": 0.025372274219989777,
|
| 315 |
+
"learning_rate": 6.428571428571429e-05,
|
| 316 |
+
"loss": 0.0257,
|
| 317 |
+
"step": 36
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.33221099887766553,
|
| 321 |
+
"grad_norm": 0.030153121799230576,
|
| 322 |
+
"learning_rate": 6.607142857142857e-05,
|
| 323 |
+
"loss": 0.0221,
|
| 324 |
+
"step": 37
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.34118967452300786,
|
| 328 |
+
"grad_norm": 0.023654770106077194,
|
| 329 |
+
"learning_rate": 6.785714285714286e-05,
|
| 330 |
+
"loss": 0.0201,
|
| 331 |
+
"step": 38
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3501683501683502,
|
| 335 |
+
"grad_norm": 0.026218950748443604,
|
| 336 |
+
"learning_rate": 6.964285714285715e-05,
|
| 337 |
+
"loss": 0.0207,
|
| 338 |
+
"step": 39
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.35914702581369246,
|
| 342 |
+
"grad_norm": 0.02605343423783779,
|
| 343 |
+
"learning_rate": 7.142857142857143e-05,
|
| 344 |
+
"loss": 0.0211,
|
| 345 |
+
"step": 40
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.35914702581369246,
|
| 349 |
+
"eval_loss": 0.020273756235837936,
|
| 350 |
+
"eval_runtime": 6.2552,
|
| 351 |
+
"eval_samples_per_second": 7.993,
|
| 352 |
+
"eval_steps_per_second": 2.078,
|
| 353 |
+
"step": 40
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3681257014590348,
|
| 357 |
+
"grad_norm": 0.026552610099315643,
|
| 358 |
+
"learning_rate": 7.321428571428571e-05,
|
| 359 |
+
"loss": 0.0226,
|
| 360 |
+
"step": 41
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3771043771043771,
|
| 364 |
+
"grad_norm": 0.020305411890149117,
|
| 365 |
+
"learning_rate": 7.500000000000001e-05,
|
| 366 |
+
"loss": 0.0187,
|
| 367 |
+
"step": 42
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.38608305274971944,
|
| 371 |
+
"grad_norm": 0.023941006511449814,
|
| 372 |
+
"learning_rate": 7.67857142857143e-05,
|
| 373 |
+
"loss": 0.0213,
|
| 374 |
+
"step": 43
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3950617283950617,
|
| 378 |
+
"grad_norm": 0.024746833369135857,
|
| 379 |
+
"learning_rate": 7.857142857142858e-05,
|
| 380 |
+
"loss": 0.0214,
|
| 381 |
+
"step": 44
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.40404040404040403,
|
| 385 |
+
"grad_norm": 0.018778987228870392,
|
| 386 |
+
"learning_rate": 8.035714285714287e-05,
|
| 387 |
+
"loss": 0.0178,
|
| 388 |
+
"step": 45
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.40404040404040403,
|
| 392 |
+
"eval_loss": 0.0200771763920784,
|
| 393 |
+
"eval_runtime": 6.2549,
|
| 394 |
+
"eval_samples_per_second": 7.994,
|
| 395 |
+
"eval_steps_per_second": 2.078,
|
| 396 |
+
"step": 45
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.41301907968574636,
|
| 400 |
+
"grad_norm": 0.02559836022555828,
|
| 401 |
+
"learning_rate": 8.214285714285714e-05,
|
| 402 |
+
"loss": 0.0186,
|
| 403 |
+
"step": 46
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.4219977553310887,
|
| 407 |
+
"grad_norm": 0.02603279985487461,
|
| 408 |
+
"learning_rate": 8.392857142857144e-05,
|
| 409 |
+
"loss": 0.0205,
|
| 410 |
+
"step": 47
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.43097643097643096,
|
| 414 |
+
"grad_norm": 0.023479154333472252,
|
| 415 |
+
"learning_rate": 8.571428571428571e-05,
|
| 416 |
+
"loss": 0.0207,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.4399551066217733,
|
| 421 |
+
"grad_norm": 0.027948766946792603,
|
| 422 |
+
"learning_rate": 8.75e-05,
|
| 423 |
+
"loss": 0.0199,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.4489337822671156,
|
| 428 |
+
"grad_norm": 0.028703948482871056,
|
| 429 |
+
"learning_rate": 8.92857142857143e-05,
|
| 430 |
+
"loss": 0.0206,
|
| 431 |
+
"step": 50
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.4489337822671156,
|
| 435 |
+
"eval_loss": 0.019621608778834343,
|
| 436 |
+
"eval_runtime": 6.2561,
|
| 437 |
+
"eval_samples_per_second": 7.992,
|
| 438 |
+
"eval_steps_per_second": 2.078,
|
| 439 |
+
"step": 50
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.45791245791245794,
|
| 443 |
+
"grad_norm": 0.021676093339920044,
|
| 444 |
+
"learning_rate": 9.107142857142857e-05,
|
| 445 |
+
"loss": 0.0203,
|
| 446 |
+
"step": 51
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.4668911335578002,
|
| 450 |
+
"grad_norm": 0.02454349212348461,
|
| 451 |
+
"learning_rate": 9.285714285714286e-05,
|
| 452 |
+
"loss": 0.0209,
|
| 453 |
+
"step": 52
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.47586980920314254,
|
| 457 |
+
"grad_norm": 0.02334459312260151,
|
| 458 |
+
"learning_rate": 9.464285714285715e-05,
|
| 459 |
+
"loss": 0.0197,
|
| 460 |
+
"step": 53
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.48484848484848486,
|
| 464 |
+
"grad_norm": 0.03568955883383751,
|
| 465 |
+
"learning_rate": 9.642857142857143e-05,
|
| 466 |
+
"loss": 0.018,
|
| 467 |
+
"step": 54
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.49382716049382713,
|
| 471 |
+
"grad_norm": 0.03706267848610878,
|
| 472 |
+
"learning_rate": 9.821428571428572e-05,
|
| 473 |
+
"loss": 0.0196,
|
| 474 |
+
"step": 55
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.49382716049382713,
|
| 478 |
+
"eval_loss": 0.01931421272456646,
|
| 479 |
+
"eval_runtime": 6.2564,
|
| 480 |
+
"eval_samples_per_second": 7.992,
|
| 481 |
+
"eval_steps_per_second": 2.078,
|
| 482 |
+
"step": 55
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5028058361391695,
|
| 486 |
+
"grad_norm": 0.033131491392850876,
|
| 487 |
+
"learning_rate": 0.0001,
|
| 488 |
+
"loss": 0.0195,
|
| 489 |
+
"step": 56
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.5117845117845118,
|
| 493 |
+
"grad_norm": 0.025286365300416946,
|
| 494 |
+
"learning_rate": 9.999900908311602e-05,
|
| 495 |
+
"loss": 0.0195,
|
| 496 |
+
"step": 57
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.5207631874298541,
|
| 500 |
+
"grad_norm": 0.03591889888048172,
|
| 501 |
+
"learning_rate": 9.999603637174071e-05,
|
| 502 |
+
"loss": 0.0195,
|
| 503 |
+
"step": 58
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.5297418630751964,
|
| 507 |
+
"grad_norm": 0.025091370567679405,
|
| 508 |
+
"learning_rate": 9.999108198370249e-05,
|
| 509 |
+
"loss": 0.0195,
|
| 510 |
+
"step": 59
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.5387205387205387,
|
| 514 |
+
"grad_norm": 0.030630730092525482,
|
| 515 |
+
"learning_rate": 9.998414611537681e-05,
|
| 516 |
+
"loss": 0.0173,
|
| 517 |
+
"step": 60
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.5387205387205387,
|
| 521 |
+
"eval_loss": 0.019306931644678116,
|
| 522 |
+
"eval_runtime": 6.2911,
|
| 523 |
+
"eval_samples_per_second": 7.948,
|
| 524 |
+
"eval_steps_per_second": 2.066,
|
| 525 |
+
"step": 60
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.547699214365881,
|
| 529 |
+
"grad_norm": 0.03352862969040871,
|
| 530 |
+
"learning_rate": 9.997522904167844e-05,
|
| 531 |
+
"loss": 0.0199,
|
| 532 |
+
"step": 61
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.5566778900112234,
|
| 536 |
+
"grad_norm": 0.029540032148361206,
|
| 537 |
+
"learning_rate": 9.996433111605052e-05,
|
| 538 |
+
"loss": 0.0211,
|
| 539 |
+
"step": 62
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.5656565656565656,
|
| 543 |
+
"grad_norm": 0.03420255333185196,
|
| 544 |
+
"learning_rate": 9.995145277045061e-05,
|
| 545 |
+
"loss": 0.0181,
|
| 546 |
+
"step": 63
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.574635241301908,
|
| 550 |
+
"grad_norm": 0.026620274409651756,
|
| 551 |
+
"learning_rate": 9.993659451533353e-05,
|
| 552 |
+
"loss": 0.0206,
|
| 553 |
+
"step": 64
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.5836139169472503,
|
| 557 |
+
"grad_norm": 0.02483481727540493,
|
| 558 |
+
"learning_rate": 9.991975693963107e-05,
|
| 559 |
+
"loss": 0.0184,
|
| 560 |
+
"step": 65
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.5836139169472503,
|
| 564 |
+
"eval_loss": 0.019347084686160088,
|
| 565 |
+
"eval_runtime": 6.2549,
|
| 566 |
+
"eval_samples_per_second": 7.994,
|
| 567 |
+
"eval_steps_per_second": 2.078,
|
| 568 |
+
"step": 65
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.5925925925925926,
|
| 572 |
+
"grad_norm": 0.0339241661131382,
|
| 573 |
+
"learning_rate": 9.990094071072877e-05,
|
| 574 |
+
"loss": 0.0193,
|
| 575 |
+
"step": 66
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.6015712682379349,
|
| 579 |
+
"grad_norm": 0.0241928081959486,
|
| 580 |
+
"learning_rate": 9.988014657443941e-05,
|
| 581 |
+
"loss": 0.0193,
|
| 582 |
+
"step": 67
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.6105499438832772,
|
| 586 |
+
"grad_norm": 0.029822858050465584,
|
| 587 |
+
"learning_rate": 9.985737535497337e-05,
|
| 588 |
+
"loss": 0.0184,
|
| 589 |
+
"step": 68
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.6195286195286195,
|
| 593 |
+
"grad_norm": 0.023182636126875877,
|
| 594 |
+
"learning_rate": 9.983262795490613e-05,
|
| 595 |
+
"loss": 0.0183,
|
| 596 |
+
"step": 69
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.6285072951739619,
|
| 600 |
+
"grad_norm": 0.021179169416427612,
|
| 601 |
+
"learning_rate": 9.980590535514233e-05,
|
| 602 |
+
"loss": 0.0194,
|
| 603 |
+
"step": 70
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.6285072951739619,
|
| 607 |
+
"eval_loss": 0.01905701868236065,
|
| 608 |
+
"eval_runtime": 6.2492,
|
| 609 |
+
"eval_samples_per_second": 8.001,
|
| 610 |
+
"eval_steps_per_second": 2.08,
|
| 611 |
+
"step": 70
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.6374859708193041,
|
| 615 |
+
"grad_norm": 0.02753937430679798,
|
| 616 |
+
"learning_rate": 9.9777208614877e-05,
|
| 617 |
+
"loss": 0.0189,
|
| 618 |
+
"step": 71
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.6464646464646465,
|
| 622 |
+
"grad_norm": 0.027653615921735764,
|
| 623 |
+
"learning_rate": 9.97465388715535e-05,
|
| 624 |
+
"loss": 0.0191,
|
| 625 |
+
"step": 72
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.6554433221099888,
|
| 629 |
+
"grad_norm": 0.020188456401228905,
|
| 630 |
+
"learning_rate": 9.971389734081848e-05,
|
| 631 |
+
"loss": 0.0187,
|
| 632 |
+
"step": 73
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.6644219977553311,
|
| 636 |
+
"grad_norm": 0.029147446155548096,
|
| 637 |
+
"learning_rate": 9.967928531647374e-05,
|
| 638 |
+
"loss": 0.0177,
|
| 639 |
+
"step": 74
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.6734006734006734,
|
| 643 |
+
"grad_norm": 0.023492921143770218,
|
| 644 |
+
"learning_rate": 9.96427041704248e-05,
|
| 645 |
+
"loss": 0.0182,
|
| 646 |
+
"step": 75
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.6734006734006734,
|
| 650 |
+
"eval_loss": 0.018457170575857162,
|
| 651 |
+
"eval_runtime": 6.2525,
|
| 652 |
+
"eval_samples_per_second": 7.997,
|
| 653 |
+
"eval_steps_per_second": 2.079,
|
| 654 |
+
"step": 75
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.6823793490460157,
|
| 658 |
+
"grad_norm": 0.016839003190398216,
|
| 659 |
+
"learning_rate": 9.960415535262671e-05,
|
| 660 |
+
"loss": 0.0169,
|
| 661 |
+
"step": 76
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.691358024691358,
|
| 665 |
+
"grad_norm": 0.024092335253953934,
|
| 666 |
+
"learning_rate": 9.956364039102642e-05,
|
| 667 |
+
"loss": 0.0184,
|
| 668 |
+
"step": 77
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.7003367003367004,
|
| 672 |
+
"grad_norm": 0.026985522359609604,
|
| 673 |
+
"learning_rate": 9.952116089150232e-05,
|
| 674 |
+
"loss": 0.0187,
|
| 675 |
+
"step": 78
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7093153759820426,
|
| 679 |
+
"grad_norm": 0.01973740942776203,
|
| 680 |
+
"learning_rate": 9.947671853780054e-05,
|
| 681 |
+
"loss": 0.0166,
|
| 682 |
+
"step": 79
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.7182940516273849,
|
| 686 |
+
"grad_norm": 0.01972176879644394,
|
| 687 |
+
"learning_rate": 9.943031509146825e-05,
|
| 688 |
+
"loss": 0.0169,
|
| 689 |
+
"step": 80
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7182940516273849,
|
| 693 |
+
"eval_loss": 0.01826069876551628,
|
| 694 |
+
"eval_runtime": 6.2512,
|
| 695 |
+
"eval_samples_per_second": 7.998,
|
| 696 |
+
"eval_steps_per_second": 2.08,
|
| 697 |
+
"step": 80
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.7272727272727273,
|
| 701 |
+
"grad_norm": 0.020164869725704193,
|
| 702 |
+
"learning_rate": 9.938195239178374e-05,
|
| 703 |
+
"loss": 0.0172,
|
| 704 |
+
"step": 81
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.7362514029180696,
|
| 708 |
+
"grad_norm": 0.02163533680140972,
|
| 709 |
+
"learning_rate": 9.933163235568367e-05,
|
| 710 |
+
"loss": 0.0183,
|
| 711 |
+
"step": 82
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.745230078563412,
|
| 715 |
+
"grad_norm": 0.018531063571572304,
|
| 716 |
+
"learning_rate": 9.927935697768698e-05,
|
| 717 |
+
"loss": 0.0171,
|
| 718 |
+
"step": 83
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.7542087542087542,
|
| 722 |
+
"grad_norm": 0.027429502457380295,
|
| 723 |
+
"learning_rate": 9.922512832981584e-05,
|
| 724 |
+
"loss": 0.0214,
|
| 725 |
+
"step": 84
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.7631874298540965,
|
| 729 |
+
"grad_norm": 0.019089698791503906,
|
| 730 |
+
"learning_rate": 9.916894856151357e-05,
|
| 731 |
+
"loss": 0.0176,
|
| 732 |
+
"step": 85
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.7631874298540965,
|
| 736 |
+
"eval_loss": 0.017831869423389435,
|
| 737 |
+
"eval_runtime": 6.2838,
|
| 738 |
+
"eval_samples_per_second": 7.957,
|
| 739 |
+
"eval_steps_per_second": 2.069,
|
| 740 |
+
"step": 85
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.7721661054994389,
|
| 744 |
+
"grad_norm": 0.018925415351986885,
|
| 745 |
+
"learning_rate": 9.91108198995594e-05,
|
| 746 |
+
"loss": 0.0156,
|
| 747 |
+
"step": 86
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.7811447811447811,
|
| 751 |
+
"grad_norm": 0.021234937012195587,
|
| 752 |
+
"learning_rate": 9.905074464798024e-05,
|
| 753 |
+
"loss": 0.0186,
|
| 754 |
+
"step": 87
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.7901234567901234,
|
| 758 |
+
"grad_norm": 0.018775297328829765,
|
| 759 |
+
"learning_rate": 9.898872518795932e-05,
|
| 760 |
+
"loss": 0.0163,
|
| 761 |
+
"step": 88
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.7991021324354658,
|
| 765 |
+
"grad_norm": 0.016489777714014053,
|
| 766 |
+
"learning_rate": 9.892476397774186e-05,
|
| 767 |
+
"loss": 0.0173,
|
| 768 |
+
"step": 89
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.8080808080808081,
|
| 772 |
+
"grad_norm": 0.018042977899312973,
|
| 773 |
+
"learning_rate": 9.885886355253758e-05,
|
| 774 |
+
"loss": 0.0158,
|
| 775 |
+
"step": 90
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.8080808080808081,
|
| 779 |
+
"eval_loss": 0.017583945766091347,
|
| 780 |
+
"eval_runtime": 6.2497,
|
| 781 |
+
"eval_samples_per_second": 8.0,
|
| 782 |
+
"eval_steps_per_second": 2.08,
|
| 783 |
+
"step": 90
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.8170594837261503,
|
| 787 |
+
"grad_norm": 0.020747726783156395,
|
| 788 |
+
"learning_rate": 9.879102652442024e-05,
|
| 789 |
+
"loss": 0.0178,
|
| 790 |
+
"step": 91
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.8260381593714927,
|
| 794 |
+
"grad_norm": 0.024066736921668053,
|
| 795 |
+
"learning_rate": 9.872125558222409e-05,
|
| 796 |
+
"loss": 0.0158,
|
| 797 |
+
"step": 92
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.835016835016835,
|
| 801 |
+
"grad_norm": 0.015819448977708817,
|
| 802 |
+
"learning_rate": 9.864955349143734e-05,
|
| 803 |
+
"loss": 0.0162,
|
| 804 |
+
"step": 93
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.8439955106621774,
|
| 808 |
+
"grad_norm": 0.018356909975409508,
|
| 809 |
+
"learning_rate": 9.857592309409247e-05,
|
| 810 |
+
"loss": 0.0154,
|
| 811 |
+
"step": 94
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.8529741863075196,
|
| 815 |
+
"grad_norm": 0.027337217703461647,
|
| 816 |
+
"learning_rate": 9.850036730865364e-05,
|
| 817 |
+
"loss": 0.02,
|
| 818 |
+
"step": 95
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.8529741863075196,
|
| 822 |
+
"eval_loss": 0.017212502658367157,
|
| 823 |
+
"eval_runtime": 6.3032,
|
| 824 |
+
"eval_samples_per_second": 7.932,
|
| 825 |
+
"eval_steps_per_second": 2.062,
|
| 826 |
+
"step": 95
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.8619528619528619,
|
| 830 |
+
"grad_norm": 0.019369499757885933,
|
| 831 |
+
"learning_rate": 9.842288912990096e-05,
|
| 832 |
+
"loss": 0.0194,
|
| 833 |
+
"step": 96
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.8709315375982043,
|
| 837 |
+
"grad_norm": 0.0162061657756567,
|
| 838 |
+
"learning_rate": 9.83434916288119e-05,
|
| 839 |
+
"loss": 0.0152,
|
| 840 |
+
"step": 97
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.8799102132435466,
|
| 844 |
+
"grad_norm": 0.023736393079161644,
|
| 845 |
+
"learning_rate": 9.82621779524394e-05,
|
| 846 |
+
"loss": 0.017,
|
| 847 |
+
"step": 98
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.8888888888888888,
|
| 851 |
+
"grad_norm": 0.01927589811384678,
|
| 852 |
+
"learning_rate": 9.817895132378725e-05,
|
| 853 |
+
"loss": 0.0158,
|
| 854 |
+
"step": 99
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.8978675645342312,
|
| 858 |
+
"grad_norm": 0.025313647463917732,
|
| 859 |
+
"learning_rate": 9.809381504168234e-05,
|
| 860 |
+
"loss": 0.0165,
|
| 861 |
+
"step": 100
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.8978675645342312,
|
| 865 |
+
"eval_loss": 0.017287207767367363,
|
| 866 |
+
"eval_runtime": 6.2491,
|
| 867 |
+
"eval_samples_per_second": 8.001,
|
| 868 |
+
"eval_steps_per_second": 2.08,
|
| 869 |
+
"step": 100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.9068462401795735,
|
| 873 |
+
"grad_norm": 0.021926885470747948,
|
| 874 |
+
"learning_rate": 9.800677248064382e-05,
|
| 875 |
+
"loss": 0.0169,
|
| 876 |
+
"step": 101
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.9158249158249159,
|
| 880 |
+
"grad_norm": 0.02485627494752407,
|
| 881 |
+
"learning_rate": 9.791782709074944e-05,
|
| 882 |
+
"loss": 0.0152,
|
| 883 |
+
"step": 102
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.9248035914702581,
|
| 887 |
+
"grad_norm": 0.021951181814074516,
|
| 888 |
+
"learning_rate": 9.782698239749873e-05,
|
| 889 |
+
"loss": 0.017,
|
| 890 |
+
"step": 103
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.9337822671156004,
|
| 894 |
+
"grad_norm": 0.02424493059515953,
|
| 895 |
+
"learning_rate": 9.77342420016733e-05,
|
| 896 |
+
"loss": 0.0172,
|
| 897 |
+
"step": 104
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.9427609427609428,
|
| 901 |
+
"grad_norm": 0.028901271522045135,
|
| 902 |
+
"learning_rate": 9.763960957919413e-05,
|
| 903 |
+
"loss": 0.0181,
|
| 904 |
+
"step": 105
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.9427609427609428,
|
| 908 |
+
"eval_loss": 0.016786355525255203,
|
| 909 |
+
"eval_runtime": 6.2498,
|
| 910 |
+
"eval_samples_per_second": 8.0,
|
| 911 |
+
"eval_steps_per_second": 2.08,
|
| 912 |
+
"step": 105
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.9517396184062851,
|
| 916 |
+
"grad_norm": 0.017801107838749886,
|
| 917 |
+
"learning_rate": 9.754308888097583e-05,
|
| 918 |
+
"loss": 0.0165,
|
| 919 |
+
"step": 106
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.9607182940516273,
|
| 923 |
+
"grad_norm": 0.037076808512210846,
|
| 924 |
+
"learning_rate": 9.744468373277797e-05,
|
| 925 |
+
"loss": 0.0162,
|
| 926 |
+
"step": 107
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.9696969696969697,
|
| 930 |
+
"grad_norm": 0.019457461312413216,
|
| 931 |
+
"learning_rate": 9.734439803505345e-05,
|
| 932 |
+
"loss": 0.0158,
|
| 933 |
+
"step": 108
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.978675645342312,
|
| 937 |
+
"grad_norm": 0.02191469632089138,
|
| 938 |
+
"learning_rate": 9.724223576279395e-05,
|
| 939 |
+
"loss": 0.0163,
|
| 940 |
+
"step": 109
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.9876543209876543,
|
| 944 |
+
"grad_norm": 0.024242915213108063,
|
| 945 |
+
"learning_rate": 9.713820096537225e-05,
|
| 946 |
+
"loss": 0.0176,
|
| 947 |
+
"step": 110
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9876543209876543,
|
| 951 |
+
"eval_loss": 0.016797909513115883,
|
| 952 |
+
"eval_runtime": 6.2548,
|
| 953 |
+
"eval_samples_per_second": 7.994,
|
| 954 |
+
"eval_steps_per_second": 2.078,
|
| 955 |
+
"step": 110
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.9966329966329966,
|
| 959 |
+
"grad_norm": 0.02136295475065708,
|
| 960 |
+
"learning_rate": 9.703229776638185e-05,
|
| 961 |
+
"loss": 0.0166,
|
| 962 |
+
"step": 111
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.0078563411896746,
|
| 966 |
+
"grad_norm": 0.08904732018709183,
|
| 967 |
+
"learning_rate": 9.692453036347351e-05,
|
| 968 |
+
"loss": 0.0323,
|
| 969 |
+
"step": 112
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.0168350168350169,
|
| 973 |
+
"grad_norm": 0.031474873423576355,
|
| 974 |
+
"learning_rate": 9.681490302818874e-05,
|
| 975 |
+
"loss": 0.0159,
|
| 976 |
+
"step": 113
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.0258136924803591,
|
| 980 |
+
"grad_norm": 0.02854473888874054,
|
| 981 |
+
"learning_rate": 9.670342010579065e-05,
|
| 982 |
+
"loss": 0.0141,
|
| 983 |
+
"step": 114
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.0347923681257014,
|
| 987 |
+
"grad_norm": 0.029452061280608177,
|
| 988 |
+
"learning_rate": 9.659008601509168e-05,
|
| 989 |
+
"loss": 0.0184,
|
| 990 |
+
"step": 115
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.0347923681257014,
|
| 994 |
+
"eval_loss": 0.0183156318962574,
|
| 995 |
+
"eval_runtime": 6.2458,
|
| 996 |
+
"eval_samples_per_second": 8.005,
|
| 997 |
+
"eval_steps_per_second": 2.081,
|
| 998 |
+
"step": 115
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.0437710437710437,
|
| 1002 |
+
"grad_norm": 0.02467503771185875,
|
| 1003 |
+
"learning_rate": 9.647490524827834e-05,
|
| 1004 |
+
"loss": 0.0157,
|
| 1005 |
+
"step": 116
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.0527497194163862,
|
| 1009 |
+
"grad_norm": 0.021488968282938004,
|
| 1010 |
+
"learning_rate": 9.635788237073334e-05,
|
| 1011 |
+
"loss": 0.0152,
|
| 1012 |
+
"step": 117
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.0617283950617284,
|
| 1016 |
+
"grad_norm": 0.02372926101088524,
|
| 1017 |
+
"learning_rate": 9.623902202085444e-05,
|
| 1018 |
+
"loss": 0.0176,
|
| 1019 |
+
"step": 118
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.0707070707070707,
|
| 1023 |
+
"grad_norm": 0.01808401569724083,
|
| 1024 |
+
"learning_rate": 9.611832890987076e-05,
|
| 1025 |
+
"loss": 0.0156,
|
| 1026 |
+
"step": 119
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.079685746352413,
|
| 1030 |
+
"grad_norm": 0.021259043365716934,
|
| 1031 |
+
"learning_rate": 9.599580782165598e-05,
|
| 1032 |
+
"loss": 0.0162,
|
| 1033 |
+
"step": 120
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.079685746352413,
|
| 1037 |
+
"eval_loss": 0.017910869792103767,
|
| 1038 |
+
"eval_runtime": 6.2515,
|
| 1039 |
+
"eval_samples_per_second": 7.998,
|
| 1040 |
+
"eval_steps_per_second": 2.079,
|
| 1041 |
+
"step": 120
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.0886644219977553,
|
| 1045 |
+
"grad_norm": 0.024560727179050446,
|
| 1046 |
+
"learning_rate": 9.587146361253868e-05,
|
| 1047 |
+
"loss": 0.0161,
|
| 1048 |
+
"step": 121
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.0976430976430978,
|
| 1052 |
+
"grad_norm": 0.02424251101911068,
|
| 1053 |
+
"learning_rate": 9.57453012111099e-05,
|
| 1054 |
+
"loss": 0.0178,
|
| 1055 |
+
"step": 122
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.10662177328844,
|
| 1059 |
+
"grad_norm": 0.021675804629921913,
|
| 1060 |
+
"learning_rate": 9.561732561802778e-05,
|
| 1061 |
+
"loss": 0.017,
|
| 1062 |
+
"step": 123
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.1156004489337823,
|
| 1066 |
+
"grad_norm": 0.019624771550297737,
|
| 1067 |
+
"learning_rate": 9.548754190581939e-05,
|
| 1068 |
+
"loss": 0.017,
|
| 1069 |
+
"step": 124
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.1245791245791246,
|
| 1073 |
+
"grad_norm": 0.019135547801852226,
|
| 1074 |
+
"learning_rate": 9.53559552186796e-05,
|
| 1075 |
+
"loss": 0.017,
|
| 1076 |
+
"step": 125
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.1245791245791246,
|
| 1080 |
+
"eval_loss": 0.016845999285578728,
|
| 1081 |
+
"eval_runtime": 6.2653,
|
| 1082 |
+
"eval_samples_per_second": 7.98,
|
| 1083 |
+
"eval_steps_per_second": 2.075,
|
| 1084 |
+
"step": 125
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.1335578002244668,
|
| 1088 |
+
"grad_norm": 0.012162208557128906,
|
| 1089 |
+
"learning_rate": 9.522257077226717e-05,
|
| 1090 |
+
"loss": 0.0123,
|
| 1091 |
+
"step": 126
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.142536475869809,
|
| 1095 |
+
"grad_norm": 0.017864948138594627,
|
| 1096 |
+
"learning_rate": 9.508739385349812e-05,
|
| 1097 |
+
"loss": 0.017,
|
| 1098 |
+
"step": 127
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.1515151515151516,
|
| 1102 |
+
"grad_norm": 0.017155688256025314,
|
| 1103 |
+
"learning_rate": 9.49504298203361e-05,
|
| 1104 |
+
"loss": 0.0156,
|
| 1105 |
+
"step": 128
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.1604938271604939,
|
| 1109 |
+
"grad_norm": 0.016472933813929558,
|
| 1110 |
+
"learning_rate": 9.481168410158003e-05,
|
| 1111 |
+
"loss": 0.0154,
|
| 1112 |
+
"step": 129
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.1694725028058361,
|
| 1116 |
+
"grad_norm": 0.014728706330060959,
|
| 1117 |
+
"learning_rate": 9.467116219664894e-05,
|
| 1118 |
+
"loss": 0.0143,
|
| 1119 |
+
"step": 130
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.1694725028058361,
|
| 1123 |
+
"eval_loss": 0.016655858606100082,
|
| 1124 |
+
"eval_runtime": 6.2511,
|
| 1125 |
+
"eval_samples_per_second": 7.999,
|
| 1126 |
+
"eval_steps_per_second": 2.08,
|
| 1127 |
+
"step": 130
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.1784511784511784,
|
| 1131 |
+
"grad_norm": 0.014423094689846039,
|
| 1132 |
+
"learning_rate": 9.45288696753639e-05,
|
| 1133 |
+
"loss": 0.015,
|
| 1134 |
+
"step": 131
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.1874298540965207,
|
| 1138 |
+
"grad_norm": 0.01742757484316826,
|
| 1139 |
+
"learning_rate": 9.438481217772744e-05,
|
| 1140 |
+
"loss": 0.016,
|
| 1141 |
+
"step": 132
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.1964085297418632,
|
| 1145 |
+
"grad_norm": 0.01627536118030548,
|
| 1146 |
+
"learning_rate": 9.423899541369978e-05,
|
| 1147 |
+
"loss": 0.0131,
|
| 1148 |
+
"step": 133
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.2053872053872055,
|
| 1152 |
+
"grad_norm": 0.017055079340934753,
|
| 1153 |
+
"learning_rate": 9.409142516297269e-05,
|
| 1154 |
+
"loss": 0.016,
|
| 1155 |
+
"step": 134
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.2143658810325477,
|
| 1159 |
+
"grad_norm": 0.01879395917057991,
|
| 1160 |
+
"learning_rate": 9.394210727474028e-05,
|
| 1161 |
+
"loss": 0.0177,
|
| 1162 |
+
"step": 135
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.2143658810325477,
|
| 1166 |
+
"eval_loss": 0.016584472730755806,
|
| 1167 |
+
"eval_runtime": 6.2484,
|
| 1168 |
+
"eval_samples_per_second": 8.002,
|
| 1169 |
+
"eval_steps_per_second": 2.081,
|
| 1170 |
+
"step": 135
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.22334455667789,
|
| 1174 |
+
"grad_norm": 0.01821809820830822,
|
| 1175 |
+
"learning_rate": 9.379104766746722e-05,
|
| 1176 |
+
"loss": 0.0163,
|
| 1177 |
+
"step": 136
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.2323232323232323,
|
| 1181 |
+
"grad_norm": 0.018335649743676186,
|
| 1182 |
+
"learning_rate": 9.363825232865413e-05,
|
| 1183 |
+
"loss": 0.0138,
|
| 1184 |
+
"step": 137
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.2413019079685745,
|
| 1188 |
+
"grad_norm": 0.014240071177482605,
|
| 1189 |
+
"learning_rate": 9.348372731460023e-05,
|
| 1190 |
+
"loss": 0.0119,
|
| 1191 |
+
"step": 138
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.250280583613917,
|
| 1195 |
+
"grad_norm": 0.02089606784284115,
|
| 1196 |
+
"learning_rate": 9.332747875016332e-05,
|
| 1197 |
+
"loss": 0.0166,
|
| 1198 |
+
"step": 139
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.2592592592592593,
|
| 1202 |
+
"grad_norm": 0.023216476663947105,
|
| 1203 |
+
"learning_rate": 9.316951282851707e-05,
|
| 1204 |
+
"loss": 0.0138,
|
| 1205 |
+
"step": 140
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.2592592592592593,
|
| 1209 |
+
"eval_loss": 0.01608719676733017,
|
| 1210 |
+
"eval_runtime": 6.3168,
|
| 1211 |
+
"eval_samples_per_second": 7.915,
|
| 1212 |
+
"eval_steps_per_second": 2.058,
|
| 1213 |
+
"step": 140
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.2682379349046016,
|
| 1217 |
+
"grad_norm": 0.01914984919130802,
|
| 1218 |
+
"learning_rate": 9.300983581090541e-05,
|
| 1219 |
+
"loss": 0.0157,
|
| 1220 |
+
"step": 141
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.2772166105499438,
|
| 1224 |
+
"grad_norm": 0.020874816924333572,
|
| 1225 |
+
"learning_rate": 9.284845402639446e-05,
|
| 1226 |
+
"loss": 0.0142,
|
| 1227 |
+
"step": 142
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.2861952861952861,
|
| 1231 |
+
"grad_norm": 0.017665155231952667,
|
| 1232 |
+
"learning_rate": 9.26853738716216e-05,
|
| 1233 |
+
"loss": 0.0148,
|
| 1234 |
+
"step": 143
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.2951739618406286,
|
| 1238 |
+
"grad_norm": 0.01927882246673107,
|
| 1239 |
+
"learning_rate": 9.2520601810542e-05,
|
| 1240 |
+
"loss": 0.0153,
|
| 1241 |
+
"step": 144
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.3041526374859709,
|
| 1245 |
+
"grad_norm": 0.018328847363591194,
|
| 1246 |
+
"learning_rate": 9.235414437417234e-05,
|
| 1247 |
+
"loss": 0.0149,
|
| 1248 |
+
"step": 145
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.3041526374859709,
|
| 1252 |
+
"eval_loss": 0.01574772223830223,
|
| 1253 |
+
"eval_runtime": 6.2751,
|
| 1254 |
+
"eval_samples_per_second": 7.968,
|
| 1255 |
+
"eval_steps_per_second": 2.072,
|
| 1256 |
+
"step": 145
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.3131313131313131,
|
| 1260 |
+
"grad_norm": 0.016565755009651184,
|
| 1261 |
+
"learning_rate": 9.2186008160332e-05,
|
| 1262 |
+
"loss": 0.0124,
|
| 1263 |
+
"step": 146
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.3221099887766554,
|
| 1267 |
+
"grad_norm": 0.023094868287444115,
|
| 1268 |
+
"learning_rate": 9.201619983338153e-05,
|
| 1269 |
+
"loss": 0.0188,
|
| 1270 |
+
"step": 147
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.3310886644219977,
|
| 1274 |
+
"grad_norm": 0.022368893027305603,
|
| 1275 |
+
"learning_rate": 9.18447261239584e-05,
|
| 1276 |
+
"loss": 0.0128,
|
| 1277 |
+
"step": 148
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.34006734006734,
|
| 1281 |
+
"grad_norm": 0.013615472242236137,
|
| 1282 |
+
"learning_rate": 9.167159382871039e-05,
|
| 1283 |
+
"loss": 0.0142,
|
| 1284 |
+
"step": 149
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.3490460157126825,
|
| 1288 |
+
"grad_norm": 0.021693168208003044,
|
| 1289 |
+
"learning_rate": 9.149680981002609e-05,
|
| 1290 |
+
"loss": 0.0162,
|
| 1291 |
+
"step": 150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.3490460157126825,
|
| 1295 |
+
"eval_loss": 0.0159834623336792,
|
| 1296 |
+
"eval_runtime": 6.2576,
|
| 1297 |
+
"eval_samples_per_second": 7.99,
|
| 1298 |
+
"eval_steps_per_second": 2.077,
|
| 1299 |
+
"step": 150
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.3580246913580247,
|
| 1303 |
+
"grad_norm": 0.016352703794836998,
|
| 1304 |
+
"learning_rate": 9.13203809957629e-05,
|
| 1305 |
+
"loss": 0.0149,
|
| 1306 |
+
"step": 151
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.367003367003367,
|
| 1310 |
+
"grad_norm": 0.019222285598516464,
|
| 1311 |
+
"learning_rate": 9.114231437897244e-05,
|
| 1312 |
+
"loss": 0.0166,
|
| 1313 |
+
"step": 152
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.3759820426487093,
|
| 1317 |
+
"grad_norm": 0.014903879724442959,
|
| 1318 |
+
"learning_rate": 9.096261701762342e-05,
|
| 1319 |
+
"loss": 0.0146,
|
| 1320 |
+
"step": 153
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.3849607182940518,
|
| 1324 |
+
"grad_norm": 0.01564696989953518,
|
| 1325 |
+
"learning_rate": 9.078129603432181e-05,
|
| 1326 |
+
"loss": 0.0141,
|
| 1327 |
+
"step": 154
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.393939393939394,
|
| 1331 |
+
"grad_norm": 0.020336154848337173,
|
| 1332 |
+
"learning_rate": 9.059835861602853e-05,
|
| 1333 |
+
"loss": 0.0148,
|
| 1334 |
+
"step": 155
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.393939393939394,
|
| 1338 |
+
"eval_loss": 0.015588033944368362,
|
| 1339 |
+
"eval_runtime": 6.2569,
|
| 1340 |
+
"eval_samples_per_second": 7.991,
|
| 1341 |
+
"eval_steps_per_second": 2.078,
|
| 1342 |
+
"step": 155
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.4029180695847363,
|
| 1346 |
+
"grad_norm": 0.01628415659070015,
|
| 1347 |
+
"learning_rate": 9.041381201377468e-05,
|
| 1348 |
+
"loss": 0.0152,
|
| 1349 |
+
"step": 156
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.4118967452300786,
|
| 1353 |
+
"grad_norm": 0.01812385767698288,
|
| 1354 |
+
"learning_rate": 9.0227663542374e-05,
|
| 1355 |
+
"loss": 0.0146,
|
| 1356 |
+
"step": 157
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.4208754208754208,
|
| 1360 |
+
"grad_norm": 0.023446347564458847,
|
| 1361 |
+
"learning_rate": 9.003992058013302e-05,
|
| 1362 |
+
"loss": 0.015,
|
| 1363 |
+
"step": 158
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.4298540965207631,
|
| 1367 |
+
"grad_norm": 0.02031407319009304,
|
| 1368 |
+
"learning_rate": 8.985059056855858e-05,
|
| 1369 |
+
"loss": 0.0144,
|
| 1370 |
+
"step": 159
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.4388327721661054,
|
| 1374 |
+
"grad_norm": 0.022712191566824913,
|
| 1375 |
+
"learning_rate": 8.965968101206291e-05,
|
| 1376 |
+
"loss": 0.0168,
|
| 1377 |
+
"step": 160
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.4388327721661054,
|
| 1381 |
+
"eval_loss": 0.015444611199200153,
|
| 1382 |
+
"eval_runtime": 6.2545,
|
| 1383 |
+
"eval_samples_per_second": 7.994,
|
| 1384 |
+
"eval_steps_per_second": 2.079,
|
| 1385 |
+
"step": 160
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.4478114478114479,
|
| 1389 |
+
"grad_norm": 0.018817342817783356,
|
| 1390 |
+
"learning_rate": 8.94671994776661e-05,
|
| 1391 |
+
"loss": 0.0147,
|
| 1392 |
+
"step": 161
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.4567901234567902,
|
| 1396 |
+
"grad_norm": 0.014623799361288548,
|
| 1397 |
+
"learning_rate": 8.927315359469626e-05,
|
| 1398 |
+
"loss": 0.0129,
|
| 1399 |
+
"step": 162
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.4657687991021324,
|
| 1403 |
+
"grad_norm": 0.02344674989581108,
|
| 1404 |
+
"learning_rate": 8.907755105448704e-05,
|
| 1405 |
+
"loss": 0.019,
|
| 1406 |
+
"step": 163
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.4747474747474747,
|
| 1410 |
+
"grad_norm": 0.02390502393245697,
|
| 1411 |
+
"learning_rate": 8.888039961007282e-05,
|
| 1412 |
+
"loss": 0.0157,
|
| 1413 |
+
"step": 164
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.4837261503928172,
|
| 1417 |
+
"grad_norm": 0.017417486757040024,
|
| 1418 |
+
"learning_rate": 8.868170707588142e-05,
|
| 1419 |
+
"loss": 0.0148,
|
| 1420 |
+
"step": 165
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.4837261503928172,
|
| 1424 |
+
"eval_loss": 0.015270690433681011,
|
| 1425 |
+
"eval_runtime": 6.2526,
|
| 1426 |
+
"eval_samples_per_second": 7.997,
|
| 1427 |
+
"eval_steps_per_second": 2.079,
|
| 1428 |
+
"step": 165
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.4927048260381595,
|
| 1432 |
+
"grad_norm": 0.01864814944565296,
|
| 1433 |
+
"learning_rate": 8.848148132742431e-05,
|
| 1434 |
+
"loss": 0.0133,
|
| 1435 |
+
"step": 166
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.5016835016835017,
|
| 1439 |
+
"grad_norm": 0.014610537327826023,
|
| 1440 |
+
"learning_rate": 8.827973030098448e-05,
|
| 1441 |
+
"loss": 0.0135,
|
| 1442 |
+
"step": 167
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.510662177328844,
|
| 1446 |
+
"grad_norm": 0.0179497878998518,
|
| 1447 |
+
"learning_rate": 8.807646199330187e-05,
|
| 1448 |
+
"loss": 0.0159,
|
| 1449 |
+
"step": 168
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.5196408529741863,
|
| 1453 |
+
"grad_norm": 0.024205263704061508,
|
| 1454 |
+
"learning_rate": 8.787168446125638e-05,
|
| 1455 |
+
"loss": 0.0129,
|
| 1456 |
+
"step": 169
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.5286195286195285,
|
| 1460 |
+
"grad_norm": 0.018040824681520462,
|
| 1461 |
+
"learning_rate": 8.766540582154859e-05,
|
| 1462 |
+
"loss": 0.0146,
|
| 1463 |
+
"step": 170
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.5286195286195285,
|
| 1467 |
+
"eval_loss": 0.015371887013316154,
|
| 1468 |
+
"eval_runtime": 6.2476,
|
| 1469 |
+
"eval_samples_per_second": 8.003,
|
| 1470 |
+
"eval_steps_per_second": 2.081,
|
| 1471 |
+
"step": 170
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.5375982042648708,
|
| 1475 |
+
"grad_norm": 0.017247065901756287,
|
| 1476 |
+
"learning_rate": 8.745763425037797e-05,
|
| 1477 |
+
"loss": 0.015,
|
| 1478 |
+
"step": 171
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.546576879910213,
|
| 1482 |
+
"grad_norm": 0.019299406558275223,
|
| 1483 |
+
"learning_rate": 8.724837798311882e-05,
|
| 1484 |
+
"loss": 0.0153,
|
| 1485 |
+
"step": 172
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.5555555555555556,
|
| 1489 |
+
"grad_norm": 0.015991205349564552,
|
| 1490 |
+
"learning_rate": 8.703764531399392e-05,
|
| 1491 |
+
"loss": 0.0122,
|
| 1492 |
+
"step": 173
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.5645342312008979,
|
| 1496 |
+
"grad_norm": 0.015190811827778816,
|
| 1497 |
+
"learning_rate": 8.682544459574562e-05,
|
| 1498 |
+
"loss": 0.0144,
|
| 1499 |
+
"step": 174
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.5735129068462403,
|
| 1503 |
+
"grad_norm": 0.01828867383301258,
|
| 1504 |
+
"learning_rate": 8.661178423930491e-05,
|
| 1505 |
+
"loss": 0.0137,
|
| 1506 |
+
"step": 175
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.5735129068462403,
|
| 1510 |
+
"eval_loss": 0.014978926628828049,
|
| 1511 |
+
"eval_runtime": 6.2611,
|
| 1512 |
+
"eval_samples_per_second": 7.986,
|
| 1513 |
+
"eval_steps_per_second": 2.076,
|
| 1514 |
+
"step": 175
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.5824915824915826,
|
| 1518 |
+
"grad_norm": 0.01734633930027485,
|
| 1519 |
+
"learning_rate": 8.639667271345798e-05,
|
| 1520 |
+
"loss": 0.0177,
|
| 1521 |
+
"step": 176
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.5914702581369249,
|
| 1525 |
+
"grad_norm": 0.019932016730308533,
|
| 1526 |
+
"learning_rate": 8.618011854451056e-05,
|
| 1527 |
+
"loss": 0.0115,
|
| 1528 |
+
"step": 177
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.6004489337822672,
|
| 1532 |
+
"grad_norm": 0.026310300454497337,
|
| 1533 |
+
"learning_rate": 8.596213031594991e-05,
|
| 1534 |
+
"loss": 0.0167,
|
| 1535 |
+
"step": 178
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.6094276094276094,
|
| 1539 |
+
"grad_norm": 0.024424167349934578,
|
| 1540 |
+
"learning_rate": 8.57427166681047e-05,
|
| 1541 |
+
"loss": 0.0153,
|
| 1542 |
+
"step": 179
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.6184062850729517,
|
| 1546 |
+
"grad_norm": 0.016459695994853973,
|
| 1547 |
+
"learning_rate": 8.552188629780244e-05,
|
| 1548 |
+
"loss": 0.0144,
|
| 1549 |
+
"step": 180
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.6184062850729517,
|
| 1553 |
+
"eval_loss": 0.014994567260146141,
|
| 1554 |
+
"eval_runtime": 6.2493,
|
| 1555 |
+
"eval_samples_per_second": 8.001,
|
| 1556 |
+
"eval_steps_per_second": 2.08,
|
| 1557 |
+
"step": 180
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.627384960718294,
|
| 1561 |
+
"grad_norm": 0.021496936678886414,
|
| 1562 |
+
"learning_rate": 8.529964795802485e-05,
|
| 1563 |
+
"loss": 0.0125,
|
| 1564 |
+
"step": 181
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.6363636363636362,
|
| 1568 |
+
"grad_norm": 0.019307784736156464,
|
| 1569 |
+
"learning_rate": 8.507601045756085e-05,
|
| 1570 |
+
"loss": 0.0152,
|
| 1571 |
+
"step": 182
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.6453423120089785,
|
| 1575 |
+
"grad_norm": 0.016401201486587524,
|
| 1576 |
+
"learning_rate": 8.485098266065744e-05,
|
| 1577 |
+
"loss": 0.0125,
|
| 1578 |
+
"step": 183
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.654320987654321,
|
| 1582 |
+
"grad_norm": 0.023525064811110497,
|
| 1583 |
+
"learning_rate": 8.462457348666835e-05,
|
| 1584 |
+
"loss": 0.0163,
|
| 1585 |
+
"step": 184
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.6632996632996633,
|
| 1589 |
+
"grad_norm": 0.020476635545492172,
|
| 1590 |
+
"learning_rate": 8.439679190970052e-05,
|
| 1591 |
+
"loss": 0.0129,
|
| 1592 |
+
"step": 185
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.6632996632996633,
|
| 1596 |
+
"eval_loss": 0.014757846482098103,
|
| 1597 |
+
"eval_runtime": 6.3022,
|
| 1598 |
+
"eval_samples_per_second": 7.934,
|
| 1599 |
+
"eval_steps_per_second": 2.063,
|
| 1600 |
+
"step": 185
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.6722783389450058,
|
| 1604 |
+
"grad_norm": 0.027425814419984818,
|
| 1605 |
+
"learning_rate": 8.416764695825835e-05,
|
| 1606 |
+
"loss": 0.015,
|
| 1607 |
+
"step": 186
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.681257014590348,
|
| 1611 |
+
"grad_norm": 0.019989849999547005,
|
| 1612 |
+
"learning_rate": 8.39371477148859e-05,
|
| 1613 |
+
"loss": 0.0166,
|
| 1614 |
+
"step": 187
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.6902356902356903,
|
| 1618 |
+
"grad_norm": 0.015978503972291946,
|
| 1619 |
+
"learning_rate": 8.370530331580686e-05,
|
| 1620 |
+
"loss": 0.0131,
|
| 1621 |
+
"step": 188
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.6992143658810326,
|
| 1625 |
+
"grad_norm": 0.02169989049434662,
|
| 1626 |
+
"learning_rate": 8.347212295056239e-05,
|
| 1627 |
+
"loss": 0.0158,
|
| 1628 |
+
"step": 189
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.7081930415263749,
|
| 1632 |
+
"grad_norm": 0.02388261817395687,
|
| 1633 |
+
"learning_rate": 8.323761586164695e-05,
|
| 1634 |
+
"loss": 0.0139,
|
| 1635 |
+
"step": 190
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.7081930415263749,
|
| 1639 |
+
"eval_loss": 0.014534353278577328,
|
| 1640 |
+
"eval_runtime": 6.2541,
|
| 1641 |
+
"eval_samples_per_second": 7.995,
|
| 1642 |
+
"eval_steps_per_second": 2.079,
|
| 1643 |
+
"step": 190
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 1.7171717171717171,
|
| 1647 |
+
"grad_norm": 0.014390088617801666,
|
| 1648 |
+
"learning_rate": 8.300179134414188e-05,
|
| 1649 |
+
"loss": 0.0116,
|
| 1650 |
+
"step": 191
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.7261503928170594,
|
| 1654 |
+
"grad_norm": 0.022068368270993233,
|
| 1655 |
+
"learning_rate": 8.276465874534702e-05,
|
| 1656 |
+
"loss": 0.0127,
|
| 1657 |
+
"step": 192
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.7351290684624017,
|
| 1661 |
+
"grad_norm": 0.020960543304681778,
|
| 1662 |
+
"learning_rate": 8.252622746441021e-05,
|
| 1663 |
+
"loss": 0.0142,
|
| 1664 |
+
"step": 193
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.7441077441077442,
|
| 1668 |
+
"grad_norm": 0.01721160300076008,
|
| 1669 |
+
"learning_rate": 8.228650695195472e-05,
|
| 1670 |
+
"loss": 0.0151,
|
| 1671 |
+
"step": 194
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.7530864197530864,
|
| 1675 |
+
"grad_norm": 0.014986108988523483,
|
| 1676 |
+
"learning_rate": 8.204550670970469e-05,
|
| 1677 |
+
"loss": 0.013,
|
| 1678 |
+
"step": 195
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.7530864197530864,
|
| 1682 |
+
"eval_loss": 0.014544461853802204,
|
| 1683 |
+
"eval_runtime": 6.2711,
|
| 1684 |
+
"eval_samples_per_second": 7.973,
|
| 1685 |
+
"eval_steps_per_second": 2.073,
|
| 1686 |
+
"step": 195
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.7620650953984287,
|
| 1690 |
+
"grad_norm": 0.01918155886232853,
|
| 1691 |
+
"learning_rate": 8.180323629010848e-05,
|
| 1692 |
+
"loss": 0.0146,
|
| 1693 |
+
"step": 196
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.7710437710437712,
|
| 1697 |
+
"grad_norm": 0.015731407329440117,
|
| 1698 |
+
"learning_rate": 8.155970529596006e-05,
|
| 1699 |
+
"loss": 0.0147,
|
| 1700 |
+
"step": 197
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.7800224466891135,
|
| 1704 |
+
"grad_norm": 0.01721978560090065,
|
| 1705 |
+
"learning_rate": 8.131492338001839e-05,
|
| 1706 |
+
"loss": 0.0132,
|
| 1707 |
+
"step": 198
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.7890011223344557,
|
| 1711 |
+
"grad_norm": 0.019031619653105736,
|
| 1712 |
+
"learning_rate": 8.106890024462481e-05,
|
| 1713 |
+
"loss": 0.0149,
|
| 1714 |
+
"step": 199
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.797979797979798,
|
| 1718 |
+
"grad_norm": 0.017630157992243767,
|
| 1719 |
+
"learning_rate": 8.082164564131845e-05,
|
| 1720 |
+
"loss": 0.013,
|
| 1721 |
+
"step": 200
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 1.797979797979798,
|
| 1725 |
+
"eval_loss": 0.01437403354793787,
|
| 1726 |
+
"eval_runtime": 6.2492,
|
| 1727 |
+
"eval_samples_per_second": 8.001,
|
| 1728 |
+
"eval_steps_per_second": 2.08,
|
| 1729 |
+
"step": 200
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 1.8069584736251403,
|
| 1733 |
+
"grad_norm": 0.02445027232170105,
|
| 1734 |
+
"learning_rate": 8.057316937044977e-05,
|
| 1735 |
+
"loss": 0.018,
|
| 1736 |
+
"step": 201
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.8159371492704826,
|
| 1740 |
+
"grad_norm": 0.021661758422851562,
|
| 1741 |
+
"learning_rate": 8.032348128079203e-05,
|
| 1742 |
+
"loss": 0.0151,
|
| 1743 |
+
"step": 202
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.8249158249158248,
|
| 1747 |
+
"grad_norm": 0.01885199546813965,
|
| 1748 |
+
"learning_rate": 8.0072591269151e-05,
|
| 1749 |
+
"loss": 0.0135,
|
| 1750 |
+
"step": 203
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.833894500561167,
|
| 1754 |
+
"grad_norm": 0.020552242174744606,
|
| 1755 |
+
"learning_rate": 7.982050927997264e-05,
|
| 1756 |
+
"loss": 0.0141,
|
| 1757 |
+
"step": 204
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.8428731762065096,
|
| 1761 |
+
"grad_norm": 0.016624536365270615,
|
| 1762 |
+
"learning_rate": 7.956724530494887e-05,
|
| 1763 |
+
"loss": 0.0124,
|
| 1764 |
+
"step": 205
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.8428731762065096,
|
| 1768 |
+
"eval_loss": 0.014373213052749634,
|
| 1769 |
+
"eval_runtime": 6.2577,
|
| 1770 |
+
"eval_samples_per_second": 7.99,
|
| 1771 |
+
"eval_steps_per_second": 2.077,
|
| 1772 |
+
"step": 205
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 1.8518518518518519,
|
| 1776 |
+
"grad_norm": 0.023108718916773796,
|
| 1777 |
+
"learning_rate": 7.931280938262169e-05,
|
| 1778 |
+
"loss": 0.0166,
|
| 1779 |
+
"step": 206
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.8608305274971941,
|
| 1783 |
+
"grad_norm": 0.014059687964618206,
|
| 1784 |
+
"learning_rate": 7.905721159798513e-05,
|
| 1785 |
+
"loss": 0.0129,
|
| 1786 |
+
"step": 207
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.8698092031425366,
|
| 1790 |
+
"grad_norm": 0.019422784447669983,
|
| 1791 |
+
"learning_rate": 7.880046208208563e-05,
|
| 1792 |
+
"loss": 0.0149,
|
| 1793 |
+
"step": 208
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.878787878787879,
|
| 1797 |
+
"grad_norm": 0.01858607865869999,
|
| 1798 |
+
"learning_rate": 7.854257101162037e-05,
|
| 1799 |
+
"loss": 0.0134,
|
| 1800 |
+
"step": 209
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 1.8877665544332212,
|
| 1804 |
+
"grad_norm": 0.019326094537973404,
|
| 1805 |
+
"learning_rate": 7.828354860853399e-05,
|
| 1806 |
+
"loss": 0.0135,
|
| 1807 |
+
"step": 210
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.8877665544332212,
|
| 1811 |
+
"eval_loss": 0.014275193214416504,
|
| 1812 |
+
"eval_runtime": 6.2658,
|
| 1813 |
+
"eval_samples_per_second": 7.98,
|
| 1814 |
+
"eval_steps_per_second": 2.075,
|
| 1815 |
+
"step": 210
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.8967452300785634,
|
| 1819 |
+
"grad_norm": 0.013561426661908627,
|
| 1820 |
+
"learning_rate": 7.802340513961342e-05,
|
| 1821 |
+
"loss": 0.012,
|
| 1822 |
+
"step": 211
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.9057239057239057,
|
| 1826 |
+
"grad_norm": 0.01908908411860466,
|
| 1827 |
+
"learning_rate": 7.776215091608085e-05,
|
| 1828 |
+
"loss": 0.0132,
|
| 1829 |
+
"step": 212
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.914702581369248,
|
| 1833 |
+
"grad_norm": 0.016201447695493698,
|
| 1834 |
+
"learning_rate": 7.749979629318516e-05,
|
| 1835 |
+
"loss": 0.0126,
|
| 1836 |
+
"step": 213
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.9236812570145903,
|
| 1840 |
+
"grad_norm": 0.015391174703836441,
|
| 1841 |
+
"learning_rate": 7.723635166979133e-05,
|
| 1842 |
+
"loss": 0.0135,
|
| 1843 |
+
"step": 214
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.9326599326599325,
|
| 1847 |
+
"grad_norm": 0.016166241839528084,
|
| 1848 |
+
"learning_rate": 7.697182748796841e-05,
|
| 1849 |
+
"loss": 0.0128,
|
| 1850 |
+
"step": 215
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.9326599326599325,
|
| 1854 |
+
"eval_loss": 0.014707864262163639,
|
| 1855 |
+
"eval_runtime": 6.2641,
|
| 1856 |
+
"eval_samples_per_second": 7.982,
|
| 1857 |
+
"eval_steps_per_second": 2.075,
|
| 1858 |
+
"step": 215
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.941638608305275,
|
| 1862 |
+
"grad_norm": 0.02329264022409916,
|
| 1863 |
+
"learning_rate": 7.670623423257548e-05,
|
| 1864 |
+
"loss": 0.0131,
|
| 1865 |
+
"step": 216
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.9506172839506173,
|
| 1869 |
+
"grad_norm": 0.01891166903078556,
|
| 1870 |
+
"learning_rate": 7.64395824308462e-05,
|
| 1871 |
+
"loss": 0.0137,
|
| 1872 |
+
"step": 217
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.9595959595959596,
|
| 1876 |
+
"grad_norm": 0.015786990523338318,
|
| 1877 |
+
"learning_rate": 7.617188265197148e-05,
|
| 1878 |
+
"loss": 0.0128,
|
| 1879 |
+
"step": 218
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.968574635241302,
|
| 1883 |
+
"grad_norm": 0.021409448236227036,
|
| 1884 |
+
"learning_rate": 7.590314550668054e-05,
|
| 1885 |
+
"loss": 0.0142,
|
| 1886 |
+
"step": 219
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.9775533108866443,
|
| 1890 |
+
"grad_norm": 0.025052543729543686,
|
| 1891 |
+
"learning_rate": 7.563338164682036e-05,
|
| 1892 |
+
"loss": 0.0149,
|
| 1893 |
+
"step": 220
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.9775533108866443,
|
| 1897 |
+
"eval_loss": 0.01433955691754818,
|
| 1898 |
+
"eval_runtime": 6.2639,
|
| 1899 |
+
"eval_samples_per_second": 7.982,
|
| 1900 |
+
"eval_steps_per_second": 2.075,
|
| 1901 |
+
"step": 220
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 1.9865319865319866,
|
| 1905 |
+
"grad_norm": 0.013938682153820992,
|
| 1906 |
+
"learning_rate": 7.536260176493348e-05,
|
| 1907 |
+
"loss": 0.0143,
|
| 1908 |
+
"step": 221
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 1.9955106621773289,
|
| 1912 |
+
"grad_norm": 0.01827586442232132,
|
| 1913 |
+
"learning_rate": 7.509081659383417e-05,
|
| 1914 |
+
"loss": 0.0134,
|
| 1915 |
+
"step": 222
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 2.006734006734007,
|
| 1919 |
+
"grad_norm": 0.04617556184530258,
|
| 1920 |
+
"learning_rate": 7.481803690618304e-05,
|
| 1921 |
+
"loss": 0.0255,
|
| 1922 |
+
"step": 223
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 2.015712682379349,
|
| 1926 |
+
"grad_norm": 0.01754753105342388,
|
| 1927 |
+
"learning_rate": 7.454427351405999e-05,
|
| 1928 |
+
"loss": 0.0154,
|
| 1929 |
+
"step": 224
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 2.0246913580246915,
|
| 1933 |
+
"grad_norm": 0.025898197665810585,
|
| 1934 |
+
"learning_rate": 7.426953726853574e-05,
|
| 1935 |
+
"loss": 0.0138,
|
| 1936 |
+
"step": 225
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 2.0246913580246915,
|
| 1940 |
+
"eval_loss": 0.014397691935300827,
|
| 1941 |
+
"eval_runtime": 6.2513,
|
| 1942 |
+
"eval_samples_per_second": 7.998,
|
| 1943 |
+
"eval_steps_per_second": 2.08,
|
| 1944 |
+
"step": 225
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 2.0336700336700337,
|
| 1948 |
+
"grad_norm": 0.01992025040090084,
|
| 1949 |
+
"learning_rate": 7.399383905924165e-05,
|
| 1950 |
+
"loss": 0.0113,
|
| 1951 |
+
"step": 226
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.042648709315376,
|
| 1955 |
+
"grad_norm": 0.014167600311338902,
|
| 1956 |
+
"learning_rate": 7.371718981393815e-05,
|
| 1957 |
+
"loss": 0.0108,
|
| 1958 |
+
"step": 227
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 2.0516273849607183,
|
| 1962 |
+
"grad_norm": 0.021143754944205284,
|
| 1963 |
+
"learning_rate": 7.343960049808156e-05,
|
| 1964 |
+
"loss": 0.0136,
|
| 1965 |
+
"step": 228
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 2.0606060606060606,
|
| 1969 |
+
"grad_norm": 0.025208963081240654,
|
| 1970 |
+
"learning_rate": 7.316108211438945e-05,
|
| 1971 |
+
"loss": 0.0129,
|
| 1972 |
+
"step": 229
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 2.069584736251403,
|
| 1976 |
+
"grad_norm": 0.017190365120768547,
|
| 1977 |
+
"learning_rate": 7.288164570240463e-05,
|
| 1978 |
+
"loss": 0.0127,
|
| 1979 |
+
"step": 230
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 2.069584736251403,
|
| 1983 |
+
"eval_loss": 0.014279232360422611,
|
| 1984 |
+
"eval_runtime": 6.2544,
|
| 1985 |
+
"eval_samples_per_second": 7.994,
|
| 1986 |
+
"eval_steps_per_second": 2.079,
|
| 1987 |
+
"step": 230
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.078563411896745,
|
| 1991 |
+
"grad_norm": 0.01911742240190506,
|
| 1992 |
+
"learning_rate": 7.26013023380574e-05,
|
| 1993 |
+
"loss": 0.0121,
|
| 1994 |
+
"step": 231
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.0875420875420874,
|
| 1998 |
+
"grad_norm": 0.022378170862793922,
|
| 1999 |
+
"learning_rate": 7.232006313322667e-05,
|
| 2000 |
+
"loss": 0.013,
|
| 2001 |
+
"step": 232
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 2.0965207631874296,
|
| 2005 |
+
"grad_norm": 0.020126372575759888,
|
| 2006 |
+
"learning_rate": 7.203793923529956e-05,
|
| 2007 |
+
"loss": 0.0127,
|
| 2008 |
+
"step": 233
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 2.1054994388327724,
|
| 2012 |
+
"grad_norm": 0.018375013023614883,
|
| 2013 |
+
"learning_rate": 7.175494182672939e-05,
|
| 2014 |
+
"loss": 0.0141,
|
| 2015 |
+
"step": 234
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 2.1144781144781146,
|
| 2019 |
+
"grad_norm": 0.016569405794143677,
|
| 2020 |
+
"learning_rate": 7.147108212459257e-05,
|
| 2021 |
+
"loss": 0.0116,
|
| 2022 |
+
"step": 235
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 2.1144781144781146,
|
| 2026 |
+
"eval_loss": 0.0142152588814497,
|
| 2027 |
+
"eval_runtime": 6.2529,
|
| 2028 |
+
"eval_samples_per_second": 7.996,
|
| 2029 |
+
"eval_steps_per_second": 2.079,
|
| 2030 |
+
"step": 235
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 2.123456790123457,
|
| 2034 |
+
"grad_norm": 0.013866296038031578,
|
| 2035 |
+
"learning_rate": 7.118637138014396e-05,
|
| 2036 |
+
"loss": 0.011,
|
| 2037 |
+
"step": 236
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 2.132435465768799,
|
| 2041 |
+
"grad_norm": 0.0164170078933239,
|
| 2042 |
+
"learning_rate": 7.090082087837092e-05,
|
| 2043 |
+
"loss": 0.0137,
|
| 2044 |
+
"step": 237
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 2.1414141414141414,
|
| 2048 |
+
"grad_norm": 0.014653601683676243,
|
| 2049 |
+
"learning_rate": 7.061444193754596e-05,
|
| 2050 |
+
"loss": 0.012,
|
| 2051 |
+
"step": 238
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 2.1503928170594837,
|
| 2055 |
+
"grad_norm": 0.020761555060744286,
|
| 2056 |
+
"learning_rate": 7.032724590877821e-05,
|
| 2057 |
+
"loss": 0.0119,
|
| 2058 |
+
"step": 239
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 2.159371492704826,
|
| 2062 |
+
"grad_norm": 0.019674135372042656,
|
| 2063 |
+
"learning_rate": 7.003924417556343e-05,
|
| 2064 |
+
"loss": 0.0128,
|
| 2065 |
+
"step": 240
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 2.159371492704826,
|
| 2069 |
+
"eval_loss": 0.014257782138884068,
|
| 2070 |
+
"eval_runtime": 6.307,
|
| 2071 |
+
"eval_samples_per_second": 7.928,
|
| 2072 |
+
"eval_steps_per_second": 2.061,
|
| 2073 |
+
"step": 240
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 2.1683501683501682,
|
| 2077 |
+
"grad_norm": 0.017319727689027786,
|
| 2078 |
+
"learning_rate": 6.975044815333282e-05,
|
| 2079 |
+
"loss": 0.0109,
|
| 2080 |
+
"step": 241
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 2.1773288439955105,
|
| 2084 |
+
"grad_norm": 0.02167445980012417,
|
| 2085 |
+
"learning_rate": 6.946086928900054e-05,
|
| 2086 |
+
"loss": 0.0132,
|
| 2087 |
+
"step": 242
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 2.186307519640853,
|
| 2091 |
+
"grad_norm": 0.016814757138490677,
|
| 2092 |
+
"learning_rate": 6.917051906051006e-05,
|
| 2093 |
+
"loss": 0.0106,
|
| 2094 |
+
"step": 243
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 2.1952861952861955,
|
| 2098 |
+
"grad_norm": 0.012457667849957943,
|
| 2099 |
+
"learning_rate": 6.887940897637908e-05,
|
| 2100 |
+
"loss": 0.0103,
|
| 2101 |
+
"step": 244
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 2.204264870931538,
|
| 2105 |
+
"grad_norm": 0.022774742916226387,
|
| 2106 |
+
"learning_rate": 6.858755057524354e-05,
|
| 2107 |
+
"loss": 0.0145,
|
| 2108 |
+
"step": 245
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 2.204264870931538,
|
| 2112 |
+
"eval_loss": 0.014115707948803902,
|
| 2113 |
+
"eval_runtime": 6.2503,
|
| 2114 |
+
"eval_samples_per_second": 8.0,
|
| 2115 |
+
"eval_steps_per_second": 2.08,
|
| 2116 |
+
"step": 245
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 2.21324354657688,
|
| 2120 |
+
"grad_norm": 0.018725769594311714,
|
| 2121 |
+
"learning_rate": 6.829495542540013e-05,
|
| 2122 |
+
"loss": 0.0118,
|
| 2123 |
+
"step": 246
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 2.2222222222222223,
|
| 2127 |
+
"grad_norm": 0.019993796944618225,
|
| 2128 |
+
"learning_rate": 6.80016351243478e-05,
|
| 2129 |
+
"loss": 0.0142,
|
| 2130 |
+
"step": 247
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.2312008978675646,
|
| 2134 |
+
"grad_norm": 0.016696954146027565,
|
| 2135 |
+
"learning_rate": 6.77076012983281e-05,
|
| 2136 |
+
"loss": 0.0119,
|
| 2137 |
+
"step": 248
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 2.240179573512907,
|
| 2141 |
+
"grad_norm": 0.016207238659262657,
|
| 2142 |
+
"learning_rate": 6.741286560186437e-05,
|
| 2143 |
+
"loss": 0.0096,
|
| 2144 |
+
"step": 249
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 2.249158249158249,
|
| 2148 |
+
"grad_norm": 0.019286343827843666,
|
| 2149 |
+
"learning_rate": 6.711743971729967e-05,
|
| 2150 |
+
"loss": 0.0147,
|
| 2151 |
+
"step": 250
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 2.249158249158249,
|
| 2155 |
+
"eval_loss": 0.013896584510803223,
|
| 2156 |
+
"eval_runtime": 6.2584,
|
| 2157 |
+
"eval_samples_per_second": 7.989,
|
| 2158 |
+
"eval_steps_per_second": 2.077,
|
| 2159 |
+
"step": 250
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.2581369248035914,
|
| 2163 |
+
"grad_norm": 0.013443589210510254,
|
| 2164 |
+
"learning_rate": 6.682133535433393e-05,
|
| 2165 |
+
"loss": 0.0102,
|
| 2166 |
+
"step": 251
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.2671156004489337,
|
| 2170 |
+
"grad_norm": 0.016910936683416367,
|
| 2171 |
+
"learning_rate": 6.652456424955963e-05,
|
| 2172 |
+
"loss": 0.0147,
|
| 2173 |
+
"step": 252
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.276094276094276,
|
| 2177 |
+
"grad_norm": 0.01767115481197834,
|
| 2178 |
+
"learning_rate": 6.622713816599673e-05,
|
| 2179 |
+
"loss": 0.0112,
|
| 2180 |
+
"step": 253
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.285072951739618,
|
| 2184 |
+
"grad_norm": 0.017718922346830368,
|
| 2185 |
+
"learning_rate": 6.592906889262632e-05,
|
| 2186 |
+
"loss": 0.013,
|
| 2187 |
+
"step": 254
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.2940516273849605,
|
| 2191 |
+
"grad_norm": 0.01557993981987238,
|
| 2192 |
+
"learning_rate": 6.563036824392344e-05,
|
| 2193 |
+
"loss": 0.0114,
|
| 2194 |
+
"step": 255
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.2940516273849605,
|
| 2198 |
+
"eval_loss": 0.013858611695468426,
|
| 2199 |
+
"eval_runtime": 6.2582,
|
| 2200 |
+
"eval_samples_per_second": 7.99,
|
| 2201 |
+
"eval_steps_per_second": 2.077,
|
| 2202 |
+
"step": 255
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 2.303030303030303,
|
| 2206 |
+
"grad_norm": 0.015414374880492687,
|
| 2207 |
+
"learning_rate": 6.533104805938873e-05,
|
| 2208 |
+
"loss": 0.0114,
|
| 2209 |
+
"step": 256
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 2.3120089786756455,
|
| 2213 |
+
"grad_norm": 0.01631319336593151,
|
| 2214 |
+
"learning_rate": 6.503112020307916e-05,
|
| 2215 |
+
"loss": 0.0116,
|
| 2216 |
+
"step": 257
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 2.3209876543209877,
|
| 2220 |
+
"grad_norm": 0.02034182660281658,
|
| 2221 |
+
"learning_rate": 6.473059656313782e-05,
|
| 2222 |
+
"loss": 0.0133,
|
| 2223 |
+
"step": 258
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 2.32996632996633,
|
| 2227 |
+
"grad_norm": 0.01835636980831623,
|
| 2228 |
+
"learning_rate": 6.442948905132266e-05,
|
| 2229 |
+
"loss": 0.0127,
|
| 2230 |
+
"step": 259
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 2.3389450056116723,
|
| 2234 |
+
"grad_norm": 0.01679323986172676,
|
| 2235 |
+
"learning_rate": 6.412780960253436e-05,
|
| 2236 |
+
"loss": 0.0114,
|
| 2237 |
+
"step": 260
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 2.3389450056116723,
|
| 2241 |
+
"eval_loss": 0.01390094868838787,
|
| 2242 |
+
"eval_runtime": 6.2592,
|
| 2243 |
+
"eval_samples_per_second": 7.988,
|
| 2244 |
+
"eval_steps_per_second": 2.077,
|
| 2245 |
+
"step": 260
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 2.3479236812570146,
|
| 2249 |
+
"grad_norm": 0.016404911875724792,
|
| 2250 |
+
"learning_rate": 6.382557017434332e-05,
|
| 2251 |
+
"loss": 0.0122,
|
| 2252 |
+
"step": 261
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 2.356902356902357,
|
| 2256 |
+
"grad_norm": 0.012671472504734993,
|
| 2257 |
+
"learning_rate": 6.352278274651561e-05,
|
| 2258 |
+
"loss": 0.0091,
|
| 2259 |
+
"step": 262
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 2.365881032547699,
|
| 2263 |
+
"grad_norm": 0.01708405278623104,
|
| 2264 |
+
"learning_rate": 6.321945932053822e-05,
|
| 2265 |
+
"loss": 0.0125,
|
| 2266 |
+
"step": 263
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 2.3748597081930414,
|
| 2270 |
+
"grad_norm": 0.019615929573774338,
|
| 2271 |
+
"learning_rate": 6.291561191914333e-05,
|
| 2272 |
+
"loss": 0.0125,
|
| 2273 |
+
"step": 264
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 2.3838383838383836,
|
| 2277 |
+
"grad_norm": 0.014311819337308407,
|
| 2278 |
+
"learning_rate": 6.261125258583171e-05,
|
| 2279 |
+
"loss": 0.0112,
|
| 2280 |
+
"step": 265
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 2.3838383838383836,
|
| 2284 |
+
"eval_loss": 0.013734661974012852,
|
| 2285 |
+
"eval_runtime": 6.2541,
|
| 2286 |
+
"eval_samples_per_second": 7.995,
|
| 2287 |
+
"eval_steps_per_second": 2.079,
|
| 2288 |
+
"step": 265
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 2.3928170594837264,
|
| 2292 |
+
"grad_norm": 0.01536188181489706,
|
| 2293 |
+
"learning_rate": 6.230639338439549e-05,
|
| 2294 |
+
"loss": 0.0134,
|
| 2295 |
+
"step": 266
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 2.4017957351290686,
|
| 2299 |
+
"grad_norm": 0.01723441854119301,
|
| 2300 |
+
"learning_rate": 6.200104639843985e-05,
|
| 2301 |
+
"loss": 0.0125,
|
| 2302 |
+
"step": 267
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 2.410774410774411,
|
| 2306 |
+
"grad_norm": 0.013469617813825607,
|
| 2307 |
+
"learning_rate": 6.169522373090412e-05,
|
| 2308 |
+
"loss": 0.0117,
|
| 2309 |
+
"step": 268
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 2.419753086419753,
|
| 2313 |
+
"grad_norm": 0.016679449006915092,
|
| 2314 |
+
"learning_rate": 6.138893750358212e-05,
|
| 2315 |
+
"loss": 0.012,
|
| 2316 |
+
"step": 269
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 2.4287317620650954,
|
| 2320 |
+
"grad_norm": 0.014688557013869286,
|
| 2321 |
+
"learning_rate": 6.108219985664161e-05,
|
| 2322 |
+
"loss": 0.0105,
|
| 2323 |
+
"step": 270
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 2.4287317620650954,
|
| 2327 |
+
"eval_loss": 0.013788803480565548,
|
| 2328 |
+
"eval_runtime": 6.2591,
|
| 2329 |
+
"eval_samples_per_second": 7.988,
|
| 2330 |
+
"eval_steps_per_second": 2.077,
|
| 2331 |
+
"step": 270
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 2.4377104377104377,
|
| 2335 |
+
"grad_norm": 0.01410532183945179,
|
| 2336 |
+
"learning_rate": 6.0775022948143115e-05,
|
| 2337 |
+
"loss": 0.0137,
|
| 2338 |
+
"step": 271
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 2.44668911335578,
|
| 2342 |
+
"grad_norm": 0.018949788063764572,
|
| 2343 |
+
"learning_rate": 6.046741895355802e-05,
|
| 2344 |
+
"loss": 0.0117,
|
| 2345 |
+
"step": 272
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 2.4556677890011223,
|
| 2349 |
+
"grad_norm": 0.01841340772807598,
|
| 2350 |
+
"learning_rate": 6.015940006528602e-05,
|
| 2351 |
+
"loss": 0.0108,
|
| 2352 |
+
"step": 273
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 2.4646464646464645,
|
| 2356 |
+
"grad_norm": 0.015688767656683922,
|
| 2357 |
+
"learning_rate": 5.9850978492171794e-05,
|
| 2358 |
+
"loss": 0.011,
|
| 2359 |
+
"step": 274
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 2.473625140291807,
|
| 2363 |
+
"grad_norm": 0.017808249220252037,
|
| 2364 |
+
"learning_rate": 5.954216645902109e-05,
|
| 2365 |
+
"loss": 0.0129,
|
| 2366 |
+
"step": 275
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 2.473625140291807,
|
| 2370 |
+
"eval_loss": 0.01363787055015564,
|
| 2371 |
+
"eval_runtime": 6.2939,
|
| 2372 |
+
"eval_samples_per_second": 7.944,
|
| 2373 |
+
"eval_steps_per_second": 2.066,
|
| 2374 |
+
"step": 275
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 2.482603815937149,
|
| 2378 |
+
"grad_norm": 0.016168171539902687,
|
| 2379 |
+
"learning_rate": 5.923297620611623e-05,
|
| 2380 |
+
"loss": 0.0107,
|
| 2381 |
+
"step": 276
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 2.4915824915824913,
|
| 2385 |
+
"grad_norm": 0.016473444178700447,
|
| 2386 |
+
"learning_rate": 5.892341998873089e-05,
|
| 2387 |
+
"loss": 0.0137,
|
| 2388 |
+
"step": 277
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 2.500561167227834,
|
| 2392 |
+
"grad_norm": 0.019177664071321487,
|
| 2393 |
+
"learning_rate": 5.861351007664434e-05,
|
| 2394 |
+
"loss": 0.0127,
|
| 2395 |
+
"step": 278
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 2.5095398428731763,
|
| 2399 |
+
"grad_norm": 0.01716047339141369,
|
| 2400 |
+
"learning_rate": 5.83032587536552e-05,
|
| 2401 |
+
"loss": 0.0127,
|
| 2402 |
+
"step": 279
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 2.5185185185185186,
|
| 2406 |
+
"grad_norm": 0.019998129457235336,
|
| 2407 |
+
"learning_rate": 5.799267831709442e-05,
|
| 2408 |
+
"loss": 0.014,
|
| 2409 |
+
"step": 280
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 2.5185185185185186,
|
| 2413 |
+
"eval_loss": 0.013543778099119663,
|
| 2414 |
+
"eval_runtime": 6.2505,
|
| 2415 |
+
"eval_samples_per_second": 7.999,
|
| 2416 |
+
"eval_steps_per_second": 2.08,
|
| 2417 |
+
"step": 280
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 2.527497194163861,
|
| 2421 |
+
"grad_norm": 0.013933787122368813,
|
| 2422 |
+
"learning_rate": 5.7681781077337905e-05,
|
| 2423 |
+
"loss": 0.0096,
|
| 2424 |
+
"step": 281
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 2.536475869809203,
|
| 2428 |
+
"grad_norm": 0.015824446454644203,
|
| 2429 |
+
"learning_rate": 5.737057935731868e-05,
|
| 2430 |
+
"loss": 0.0092,
|
| 2431 |
+
"step": 282
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 2.5454545454545454,
|
| 2435 |
+
"grad_norm": 0.01764868013560772,
|
| 2436 |
+
"learning_rate": 5.705908549203823e-05,
|
| 2437 |
+
"loss": 0.0126,
|
| 2438 |
+
"step": 283
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 2.5544332210998877,
|
| 2442 |
+
"grad_norm": 0.022920994088053703,
|
| 2443 |
+
"learning_rate": 5.674731182807781e-05,
|
| 2444 |
+
"loss": 0.0122,
|
| 2445 |
+
"step": 284
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.56341189674523,
|
| 2449 |
+
"grad_norm": 0.01605917327105999,
|
| 2450 |
+
"learning_rate": 5.643527072310891e-05,
|
| 2451 |
+
"loss": 0.0124,
|
| 2452 |
+
"step": 285
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 2.56341189674523,
|
| 2456 |
+
"eval_loss": 0.013581929728388786,
|
| 2457 |
+
"eval_runtime": 6.2549,
|
| 2458 |
+
"eval_samples_per_second": 7.994,
|
| 2459 |
+
"eval_steps_per_second": 2.078,
|
| 2460 |
+
"step": 285
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.5723905723905722,
|
| 2464 |
+
"grad_norm": 0.022532224655151367,
|
| 2465 |
+
"learning_rate": 5.612297454540352e-05,
|
| 2466 |
+
"loss": 0.0134,
|
| 2467 |
+
"step": 286
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.581369248035915,
|
| 2471 |
+
"grad_norm": 0.01806466281414032,
|
| 2472 |
+
"learning_rate": 5.581043567334383e-05,
|
| 2473 |
+
"loss": 0.0105,
|
| 2474 |
+
"step": 287
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 2.590347923681257,
|
| 2478 |
+
"grad_norm": 0.019253233447670937,
|
| 2479 |
+
"learning_rate": 5.5497666494931654e-05,
|
| 2480 |
+
"loss": 0.0116,
|
| 2481 |
+
"step": 288
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 2.5993265993265995,
|
| 2485 |
+
"grad_norm": 0.016167184337973595,
|
| 2486 |
+
"learning_rate": 5.518467940729739e-05,
|
| 2487 |
+
"loss": 0.0127,
|
| 2488 |
+
"step": 289
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 2.6083052749719418,
|
| 2492 |
+
"grad_norm": 0.019589709118008614,
|
| 2493 |
+
"learning_rate": 5.487148681620862e-05,
|
| 2494 |
+
"loss": 0.0128,
|
| 2495 |
+
"step": 290
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 2.6083052749719418,
|
| 2499 |
+
"eval_loss": 0.01327795721590519,
|
| 2500 |
+
"eval_runtime": 6.258,
|
| 2501 |
+
"eval_samples_per_second": 7.99,
|
| 2502 |
+
"eval_steps_per_second": 2.077,
|
| 2503 |
+
"step": 290
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 2.617283950617284,
|
| 2507 |
+
"grad_norm": 0.017755387350916862,
|
| 2508 |
+
"learning_rate": 5.455810113557839e-05,
|
| 2509 |
+
"loss": 0.0129,
|
| 2510 |
+
"step": 291
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 2.6262626262626263,
|
| 2514 |
+
"grad_norm": 0.01898750476539135,
|
| 2515 |
+
"learning_rate": 5.4244534786973214e-05,
|
| 2516 |
+
"loss": 0.0113,
|
| 2517 |
+
"step": 292
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 2.6352413019079686,
|
| 2521 |
+
"grad_norm": 0.014957334846258163,
|
| 2522 |
+
"learning_rate": 5.3930800199120616e-05,
|
| 2523 |
+
"loss": 0.0132,
|
| 2524 |
+
"step": 293
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 2.644219977553311,
|
| 2528 |
+
"grad_norm": 0.014244873076677322,
|
| 2529 |
+
"learning_rate": 5.361690980741663e-05,
|
| 2530 |
+
"loss": 0.0111,
|
| 2531 |
+
"step": 294
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 2.653198653198653,
|
| 2535 |
+
"grad_norm": 0.013911189511418343,
|
| 2536 |
+
"learning_rate": 5.330287605343279e-05,
|
| 2537 |
+
"loss": 0.0106,
|
| 2538 |
+
"step": 295
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 2.653198653198653,
|
| 2542 |
+
"eval_loss": 0.01291807834059,
|
| 2543 |
+
"eval_runtime": 6.2514,
|
| 2544 |
+
"eval_samples_per_second": 7.998,
|
| 2545 |
+
"eval_steps_per_second": 2.08,
|
| 2546 |
+
"step": 295
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 2.6621773288439954,
|
| 2550 |
+
"grad_norm": 0.017059607431292534,
|
| 2551 |
+
"learning_rate": 5.298871138442307e-05,
|
| 2552 |
+
"loss": 0.0127,
|
| 2553 |
+
"step": 296
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 2.6711560044893377,
|
| 2557 |
+
"grad_norm": 0.0140462601557374,
|
| 2558 |
+
"learning_rate": 5.267442825283048e-05,
|
| 2559 |
+
"loss": 0.0123,
|
| 2560 |
+
"step": 297
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 2.68013468013468,
|
| 2564 |
+
"grad_norm": 0.019492056220769882,
|
| 2565 |
+
"learning_rate": 5.236003911579345e-05,
|
| 2566 |
+
"loss": 0.0138,
|
| 2567 |
+
"step": 298
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 2.689113355780022,
|
| 2571 |
+
"grad_norm": 0.018796566873788834,
|
| 2572 |
+
"learning_rate": 5.204555643465215e-05,
|
| 2573 |
+
"loss": 0.011,
|
| 2574 |
+
"step": 299
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 2.698092031425365,
|
| 2578 |
+
"grad_norm": 0.012939135544002056,
|
| 2579 |
+
"learning_rate": 5.173099267445451e-05,
|
| 2580 |
+
"loss": 0.0099,
|
| 2581 |
+
"step": 300
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 2.698092031425365,
|
| 2585 |
+
"eval_loss": 0.012918239459395409,
|
| 2586 |
+
"eval_runtime": 6.2607,
|
| 2587 |
+
"eval_samples_per_second": 7.986,
|
| 2588 |
+
"eval_steps_per_second": 2.076,
|
| 2589 |
+
"step": 300
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 2.707070707070707,
|
| 2593 |
+
"grad_norm": 0.01702980510890484,
|
| 2594 |
+
"learning_rate": 5.1416360303462206e-05,
|
| 2595 |
+
"loss": 0.0116,
|
| 2596 |
+
"step": 301
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 2.7160493827160495,
|
| 2600 |
+
"grad_norm": 0.021528059616684914,
|
| 2601 |
+
"learning_rate": 5.110167179265636e-05,
|
| 2602 |
+
"loss": 0.0134,
|
| 2603 |
+
"step": 302
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 2.7250280583613917,
|
| 2607 |
+
"grad_norm": 0.013685944490134716,
|
| 2608 |
+
"learning_rate": 5.078693961524329e-05,
|
| 2609 |
+
"loss": 0.0109,
|
| 2610 |
+
"step": 303
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 2.734006734006734,
|
| 2614 |
+
"grad_norm": 0.016435936093330383,
|
| 2615 |
+
"learning_rate": 5.0472176246160184e-05,
|
| 2616 |
+
"loss": 0.0121,
|
| 2617 |
+
"step": 304
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 2.7429854096520763,
|
| 2621 |
+
"grad_norm": 0.019511640071868896,
|
| 2622 |
+
"learning_rate": 5.01573941615805e-05,
|
| 2623 |
+
"loss": 0.0111,
|
| 2624 |
+
"step": 305
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 2.7429854096520763,
|
| 2628 |
+
"eval_loss": 0.012916718609631062,
|
| 2629 |
+
"eval_runtime": 6.27,
|
| 2630 |
+
"eval_samples_per_second": 7.974,
|
| 2631 |
+
"eval_steps_per_second": 2.073,
|
| 2632 |
+
"step": 305
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 2.7519640852974185,
|
| 2636 |
+
"grad_norm": 0.01732565462589264,
|
| 2637 |
+
"learning_rate": 4.984260583841953e-05,
|
| 2638 |
+
"loss": 0.0115,
|
| 2639 |
+
"step": 306
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 2.760942760942761,
|
| 2643 |
+
"grad_norm": 0.021635642275214195,
|
| 2644 |
+
"learning_rate": 4.9527823753839834e-05,
|
| 2645 |
+
"loss": 0.0135,
|
| 2646 |
+
"step": 307
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 2.7699214365881035,
|
| 2650 |
+
"grad_norm": 0.012034310959279537,
|
| 2651 |
+
"learning_rate": 4.9213060384756716e-05,
|
| 2652 |
+
"loss": 0.009,
|
| 2653 |
+
"step": 308
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 2.778900112233446,
|
| 2657 |
+
"grad_norm": 0.020500048995018005,
|
| 2658 |
+
"learning_rate": 4.8898328207343666e-05,
|
| 2659 |
+
"loss": 0.0123,
|
| 2660 |
+
"step": 309
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 2.787878787878788,
|
| 2664 |
+
"grad_norm": 0.01599585823714733,
|
| 2665 |
+
"learning_rate": 4.858363969653781e-05,
|
| 2666 |
+
"loss": 0.0129,
|
| 2667 |
+
"step": 310
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 2.787878787878788,
|
| 2671 |
+
"eval_loss": 0.012887900695204735,
|
| 2672 |
+
"eval_runtime": 6.2513,
|
| 2673 |
+
"eval_samples_per_second": 7.998,
|
| 2674 |
+
"eval_steps_per_second": 2.08,
|
| 2675 |
+
"step": 310
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 2.7968574635241303,
|
| 2679 |
+
"grad_norm": 0.01829446479678154,
|
| 2680 |
+
"learning_rate": 4.8269007325545506e-05,
|
| 2681 |
+
"loss": 0.0127,
|
| 2682 |
+
"step": 311
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 2.8058361391694726,
|
| 2686 |
+
"grad_norm": 0.014843763783574104,
|
| 2687 |
+
"learning_rate": 4.7954443565347865e-05,
|
| 2688 |
+
"loss": 0.0104,
|
| 2689 |
+
"step": 312
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 2.814814814814815,
|
| 2693 |
+
"grad_norm": 0.018556272611021996,
|
| 2694 |
+
"learning_rate": 4.7639960884206576e-05,
|
| 2695 |
+
"loss": 0.0132,
|
| 2696 |
+
"step": 313
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 2.823793490460157,
|
| 2700 |
+
"grad_norm": 0.016161100938916206,
|
| 2701 |
+
"learning_rate": 4.7325571747169545e-05,
|
| 2702 |
+
"loss": 0.0106,
|
| 2703 |
+
"step": 314
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 2.8327721661054994,
|
| 2707 |
+
"grad_norm": 0.01768597401678562,
|
| 2708 |
+
"learning_rate": 4.7011288615576934e-05,
|
| 2709 |
+
"loss": 0.0088,
|
| 2710 |
+
"step": 315
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 2.8327721661054994,
|
| 2714 |
+
"eval_loss": 0.012852279469370842,
|
| 2715 |
+
"eval_runtime": 6.2725,
|
| 2716 |
+
"eval_samples_per_second": 7.971,
|
| 2717 |
+
"eval_steps_per_second": 2.073,
|
| 2718 |
+
"step": 315
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.8417508417508417,
|
| 2722 |
+
"grad_norm": 0.022071367129683495,
|
| 2723 |
+
"learning_rate": 4.6697123946567227e-05,
|
| 2724 |
+
"loss": 0.0159,
|
| 2725 |
+
"step": 316
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.850729517396184,
|
| 2729 |
+
"grad_norm": 0.012250754982233047,
|
| 2730 |
+
"learning_rate": 4.63830901925834e-05,
|
| 2731 |
+
"loss": 0.0098,
|
| 2732 |
+
"step": 317
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.8597081930415262,
|
| 2736 |
+
"grad_norm": 0.015096920542418957,
|
| 2737 |
+
"learning_rate": 4.60691998008794e-05,
|
| 2738 |
+
"loss": 0.011,
|
| 2739 |
+
"step": 318
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.8686868686868685,
|
| 2743 |
+
"grad_norm": 0.016319630667567253,
|
| 2744 |
+
"learning_rate": 4.575546521302681e-05,
|
| 2745 |
+
"loss": 0.0115,
|
| 2746 |
+
"step": 319
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.877665544332211,
|
| 2750 |
+
"grad_norm": 0.01583506353199482,
|
| 2751 |
+
"learning_rate": 4.544189886442162e-05,
|
| 2752 |
+
"loss": 0.0092,
|
| 2753 |
+
"step": 320
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.877665544332211,
|
| 2757 |
+
"eval_loss": 0.012964904308319092,
|
| 2758 |
+
"eval_runtime": 6.2575,
|
| 2759 |
+
"eval_samples_per_second": 7.99,
|
| 2760 |
+
"eval_steps_per_second": 2.077,
|
| 2761 |
+
"step": 320
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 2.886644219977553,
|
| 2765 |
+
"grad_norm": 0.020128175616264343,
|
| 2766 |
+
"learning_rate": 4.5128513183791386e-05,
|
| 2767 |
+
"loss": 0.0141,
|
| 2768 |
+
"step": 321
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 2.8956228956228958,
|
| 2772 |
+
"grad_norm": 0.019213715568184853,
|
| 2773 |
+
"learning_rate": 4.481532059270262e-05,
|
| 2774 |
+
"loss": 0.0115,
|
| 2775 |
+
"step": 322
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 2.904601571268238,
|
| 2779 |
+
"grad_norm": 0.024485057219862938,
|
| 2780 |
+
"learning_rate": 4.450233350506836e-05,
|
| 2781 |
+
"loss": 0.0135,
|
| 2782 |
+
"step": 323
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 2.9135802469135803,
|
| 2786 |
+
"grad_norm": 0.019438456743955612,
|
| 2787 |
+
"learning_rate": 4.418956432665618e-05,
|
| 2788 |
+
"loss": 0.0108,
|
| 2789 |
+
"step": 324
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 2.9225589225589226,
|
| 2793 |
+
"grad_norm": 0.013679172843694687,
|
| 2794 |
+
"learning_rate": 4.387702545459649e-05,
|
| 2795 |
+
"loss": 0.0086,
|
| 2796 |
+
"step": 325
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 2.9225589225589226,
|
| 2800 |
+
"eval_loss": 0.012879169546067715,
|
| 2801 |
+
"eval_runtime": 6.2664,
|
| 2802 |
+
"eval_samples_per_second": 7.979,
|
| 2803 |
+
"eval_steps_per_second": 2.075,
|
| 2804 |
+
"step": 325
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 2.931537598204265,
|
| 2808 |
+
"grad_norm": 0.018316788598895073,
|
| 2809 |
+
"learning_rate": 4.356472927689109e-05,
|
| 2810 |
+
"loss": 0.0112,
|
| 2811 |
+
"step": 326
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 2.940516273849607,
|
| 2815 |
+
"grad_norm": 0.01569702848792076,
|
| 2816 |
+
"learning_rate": 4.32526881719222e-05,
|
| 2817 |
+
"loss": 0.0129,
|
| 2818 |
+
"step": 327
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 2.9494949494949494,
|
| 2822 |
+
"grad_norm": 0.01372100692242384,
|
| 2823 |
+
"learning_rate": 4.2940914507961775e-05,
|
| 2824 |
+
"loss": 0.0104,
|
| 2825 |
+
"step": 328
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 2.9584736251402917,
|
| 2829 |
+
"grad_norm": 0.015811212360858917,
|
| 2830 |
+
"learning_rate": 4.262942064268134e-05,
|
| 2831 |
+
"loss": 0.0123,
|
| 2832 |
+
"step": 329
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 2.9674523007856344,
|
| 2836 |
+
"grad_norm": 0.018124472349882126,
|
| 2837 |
+
"learning_rate": 4.23182189226621e-05,
|
| 2838 |
+
"loss": 0.0132,
|
| 2839 |
+
"step": 330
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 2.9674523007856344,
|
| 2843 |
+
"eval_loss": 0.012610589154064655,
|
| 2844 |
+
"eval_runtime": 6.2539,
|
| 2845 |
+
"eval_samples_per_second": 7.995,
|
| 2846 |
+
"eval_steps_per_second": 2.079,
|
| 2847 |
+
"step": 330
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 2.9764309764309766,
|
| 2851 |
+
"grad_norm": 0.015013212338089943,
|
| 2852 |
+
"learning_rate": 4.20073216829056e-05,
|
| 2853 |
+
"loss": 0.0124,
|
| 2854 |
+
"step": 331
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 2.985409652076319,
|
| 2858 |
+
"grad_norm": 0.013129116035997868,
|
| 2859 |
+
"learning_rate": 4.169674124634481e-05,
|
| 2860 |
+
"loss": 0.009,
|
| 2861 |
+
"step": 332
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 2.994388327721661,
|
| 2865 |
+
"grad_norm": 0.01896873489022255,
|
| 2866 |
+
"learning_rate": 4.138648992335566e-05,
|
| 2867 |
+
"loss": 0.0131,
|
| 2868 |
+
"step": 333
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 3.005611672278339,
|
| 2872 |
+
"grad_norm": 0.03602827712893486,
|
| 2873 |
+
"learning_rate": 4.107658001126913e-05,
|
| 2874 |
+
"loss": 0.0173,
|
| 2875 |
+
"step": 334
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 3.014590347923681,
|
| 2879 |
+
"grad_norm": 0.021112319082021713,
|
| 2880 |
+
"learning_rate": 4.0767023793883785e-05,
|
| 2881 |
+
"loss": 0.0126,
|
| 2882 |
+
"step": 335
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 3.014590347923681,
|
| 2886 |
+
"eval_loss": 0.012994157150387764,
|
| 2887 |
+
"eval_runtime": 6.2538,
|
| 2888 |
+
"eval_samples_per_second": 7.995,
|
| 2889 |
+
"eval_steps_per_second": 2.079,
|
| 2890 |
+
"step": 335
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 3.0235690235690234,
|
| 2894 |
+
"grad_norm": 0.01987135224044323,
|
| 2895 |
+
"learning_rate": 4.045783354097893e-05,
|
| 2896 |
+
"loss": 0.0092,
|
| 2897 |
+
"step": 336
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 3.032547699214366,
|
| 2901 |
+
"grad_norm": 0.025037603452801704,
|
| 2902 |
+
"learning_rate": 4.0149021507828224e-05,
|
| 2903 |
+
"loss": 0.0131,
|
| 2904 |
+
"step": 337
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 3.0415263748597083,
|
| 2908 |
+
"grad_norm": 0.017175879329442978,
|
| 2909 |
+
"learning_rate": 3.984059993471399e-05,
|
| 2910 |
+
"loss": 0.0086,
|
| 2911 |
+
"step": 338
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 3.0505050505050506,
|
| 2915 |
+
"grad_norm": 0.018214913085103035,
|
| 2916 |
+
"learning_rate": 3.9532581046442e-05,
|
| 2917 |
+
"loss": 0.0104,
|
| 2918 |
+
"step": 339
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 3.059483726150393,
|
| 2922 |
+
"grad_norm": 0.016980677843093872,
|
| 2923 |
+
"learning_rate": 3.9224977051856904e-05,
|
| 2924 |
+
"loss": 0.0117,
|
| 2925 |
+
"step": 340
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 3.059483726150393,
|
| 2929 |
+
"eval_loss": 0.013331728056073189,
|
| 2930 |
+
"eval_runtime": 6.2785,
|
| 2931 |
+
"eval_samples_per_second": 7.964,
|
| 2932 |
+
"eval_steps_per_second": 2.071,
|
| 2933 |
+
"step": 340
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 3.068462401795735,
|
| 2937 |
+
"grad_norm": 0.016574935987591743,
|
| 2938 |
+
"learning_rate": 3.8917800143358404e-05,
|
| 2939 |
+
"loss": 0.0077,
|
| 2940 |
+
"step": 341
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"epoch": 3.0774410774410774,
|
| 2944 |
+
"grad_norm": 0.020380405709147453,
|
| 2945 |
+
"learning_rate": 3.861106249641789e-05,
|
| 2946 |
+
"loss": 0.0097,
|
| 2947 |
+
"step": 342
|
| 2948 |
+
},
|
| 2949 |
+
{
|
| 2950 |
+
"epoch": 3.0864197530864197,
|
| 2951 |
+
"grad_norm": 0.026123059913516045,
|
| 2952 |
+
"learning_rate": 3.830477626909589e-05,
|
| 2953 |
+
"loss": 0.0125,
|
| 2954 |
+
"step": 343
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 3.095398428731762,
|
| 2958 |
+
"grad_norm": 0.02141587808728218,
|
| 2959 |
+
"learning_rate": 3.7998953601560175e-05,
|
| 2960 |
+
"loss": 0.0111,
|
| 2961 |
+
"step": 344
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 3.1043771043771042,
|
| 2965 |
+
"grad_norm": 0.021793678402900696,
|
| 2966 |
+
"learning_rate": 3.769360661560453e-05,
|
| 2967 |
+
"loss": 0.0102,
|
| 2968 |
+
"step": 345
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"epoch": 3.1043771043771042,
|
| 2972 |
+
"eval_loss": 0.013248049654066563,
|
| 2973 |
+
"eval_runtime": 6.2478,
|
| 2974 |
+
"eval_samples_per_second": 8.003,
|
| 2975 |
+
"eval_steps_per_second": 2.081,
|
| 2976 |
+
"step": 345
|
| 2977 |
+
},
|
| 2978 |
+
{
|
| 2979 |
+
"epoch": 3.1133557800224465,
|
| 2980 |
+
"grad_norm": 0.013916864059865475,
|
| 2981 |
+
"learning_rate": 3.73887474141683e-05,
|
| 2982 |
+
"loss": 0.0088,
|
| 2983 |
+
"step": 346
|
| 2984 |
+
},
|
| 2985 |
+
{
|
| 2986 |
+
"epoch": 3.122334455667789,
|
| 2987 |
+
"grad_norm": 0.015638204291462898,
|
| 2988 |
+
"learning_rate": 3.708438808085668e-05,
|
| 2989 |
+
"loss": 0.01,
|
| 2990 |
+
"step": 347
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 3.1313131313131315,
|
| 2994 |
+
"grad_norm": 0.017211005091667175,
|
| 2995 |
+
"learning_rate": 3.6780540679461784e-05,
|
| 2996 |
+
"loss": 0.0091,
|
| 2997 |
+
"step": 348
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 3.1402918069584738,
|
| 3001 |
+
"grad_norm": 0.02173846773803234,
|
| 3002 |
+
"learning_rate": 3.64772172534844e-05,
|
| 3003 |
+
"loss": 0.0118,
|
| 3004 |
+
"step": 349
|
| 3005 |
+
},
|
| 3006 |
+
{
|
| 3007 |
+
"epoch": 3.149270482603816,
|
| 3008 |
+
"grad_norm": 0.012991265393793583,
|
| 3009 |
+
"learning_rate": 3.6174429825656685e-05,
|
| 3010 |
+
"loss": 0.0074,
|
| 3011 |
+
"step": 350
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 3.149270482603816,
|
| 3015 |
+
"eval_loss": 0.013174821622669697,
|
| 3016 |
+
"eval_runtime": 6.296,
|
| 3017 |
+
"eval_samples_per_second": 7.942,
|
| 3018 |
+
"eval_steps_per_second": 2.065,
|
| 3019 |
+
"step": 350
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 3.1582491582491583,
|
| 3023 |
+
"grad_norm": 0.02047666721045971,
|
| 3024 |
+
"learning_rate": 3.587219039746564e-05,
|
| 3025 |
+
"loss": 0.0124,
|
| 3026 |
+
"step": 351
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 3.1672278338945006,
|
| 3030 |
+
"grad_norm": 0.0238481592386961,
|
| 3031 |
+
"learning_rate": 3.557051094867735e-05,
|
| 3032 |
+
"loss": 0.0122,
|
| 3033 |
+
"step": 352
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 3.176206509539843,
|
| 3037 |
+
"grad_norm": 0.01623239740729332,
|
| 3038 |
+
"learning_rate": 3.5269403436862175e-05,
|
| 3039 |
+
"loss": 0.0089,
|
| 3040 |
+
"step": 353
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 3.185185185185185,
|
| 3044 |
+
"grad_norm": 0.019198792055249214,
|
| 3045 |
+
"learning_rate": 3.496887979692084e-05,
|
| 3046 |
+
"loss": 0.0111,
|
| 3047 |
+
"step": 354
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 3.1941638608305274,
|
| 3051 |
+
"grad_norm": 0.019949574023485184,
|
| 3052 |
+
"learning_rate": 3.466895194061128e-05,
|
| 3053 |
+
"loss": 0.0105,
|
| 3054 |
+
"step": 355
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 3.1941638608305274,
|
| 3058 |
+
"eval_loss": 0.01294049434363842,
|
| 3059 |
+
"eval_runtime": 6.2659,
|
| 3060 |
+
"eval_samples_per_second": 7.98,
|
| 3061 |
+
"eval_steps_per_second": 2.075,
|
| 3062 |
+
"step": 355
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 3.2031425364758697,
|
| 3066 |
+
"grad_norm": 0.01906234584748745,
|
| 3067 |
+
"learning_rate": 3.436963175607656e-05,
|
| 3068 |
+
"loss": 0.0096,
|
| 3069 |
+
"step": 356
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 3.212121212121212,
|
| 3073 |
+
"grad_norm": 0.019578171893954277,
|
| 3074 |
+
"learning_rate": 3.4070931107373675e-05,
|
| 3075 |
+
"loss": 0.0092,
|
| 3076 |
+
"step": 357
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 3.221099887766554,
|
| 3080 |
+
"grad_norm": 0.015484723262488842,
|
| 3081 |
+
"learning_rate": 3.377286183400328e-05,
|
| 3082 |
+
"loss": 0.011,
|
| 3083 |
+
"step": 358
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 3.230078563411897,
|
| 3087 |
+
"grad_norm": 0.017633194103837013,
|
| 3088 |
+
"learning_rate": 3.3475435750440356e-05,
|
| 3089 |
+
"loss": 0.0101,
|
| 3090 |
+
"step": 359
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 3.239057239057239,
|
| 3094 |
+
"grad_norm": 0.020478319376707077,
|
| 3095 |
+
"learning_rate": 3.3178664645666066e-05,
|
| 3096 |
+
"loss": 0.0117,
|
| 3097 |
+
"step": 360
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 3.239057239057239,
|
| 3101 |
+
"eval_loss": 0.012872601859271526,
|
| 3102 |
+
"eval_runtime": 6.2587,
|
| 3103 |
+
"eval_samples_per_second": 7.989,
|
| 3104 |
+
"eval_steps_per_second": 2.077,
|
| 3105 |
+
"step": 360
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 3.2480359147025815,
|
| 3109 |
+
"grad_norm": 0.015297391451895237,
|
| 3110 |
+
"learning_rate": 3.2882560282700336e-05,
|
| 3111 |
+
"loss": 0.0096,
|
| 3112 |
+
"step": 361
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 3.2570145903479237,
|
| 3116 |
+
"grad_norm": 0.01740657351911068,
|
| 3117 |
+
"learning_rate": 3.258713439813566e-05,
|
| 3118 |
+
"loss": 0.0105,
|
| 3119 |
+
"step": 362
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 3.265993265993266,
|
| 3123 |
+
"grad_norm": 0.019270438700914383,
|
| 3124 |
+
"learning_rate": 3.229239870167191e-05,
|
| 3125 |
+
"loss": 0.0103,
|
| 3126 |
+
"step": 363
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 3.2749719416386083,
|
| 3130 |
+
"grad_norm": 0.017028817906975746,
|
| 3131 |
+
"learning_rate": 3.199836487565222e-05,
|
| 3132 |
+
"loss": 0.0109,
|
| 3133 |
+
"step": 364
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 3.2839506172839505,
|
| 3137 |
+
"grad_norm": 0.0167669877409935,
|
| 3138 |
+
"learning_rate": 3.170504457459989e-05,
|
| 3139 |
+
"loss": 0.0107,
|
| 3140 |
+
"step": 365
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 3.2839506172839505,
|
| 3144 |
+
"eval_loss": 0.012733125127851963,
|
| 3145 |
+
"eval_runtime": 6.2533,
|
| 3146 |
+
"eval_samples_per_second": 7.996,
|
| 3147 |
+
"eval_steps_per_second": 2.079,
|
| 3148 |
+
"step": 365
|
| 3149 |
+
},
|
| 3150 |
+
{
|
| 3151 |
+
"epoch": 3.292929292929293,
|
| 3152 |
+
"grad_norm": 0.01785757951438427,
|
| 3153 |
+
"learning_rate": 3.1412449424756474e-05,
|
| 3154 |
+
"loss": 0.0097,
|
| 3155 |
+
"step": 366
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 3.301907968574635,
|
| 3159 |
+
"grad_norm": 0.01732640527188778,
|
| 3160 |
+
"learning_rate": 3.112059102362093e-05,
|
| 3161 |
+
"loss": 0.0106,
|
| 3162 |
+
"step": 367
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 3.3108866442199774,
|
| 3166 |
+
"grad_norm": 0.015373657457530499,
|
| 3167 |
+
"learning_rate": 3.082948093948997e-05,
|
| 3168 |
+
"loss": 0.0094,
|
| 3169 |
+
"step": 368
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 3.31986531986532,
|
| 3173 |
+
"grad_norm": 0.01795523799955845,
|
| 3174 |
+
"learning_rate": 3.053913071099947e-05,
|
| 3175 |
+
"loss": 0.0096,
|
| 3176 |
+
"step": 369
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 3.3288439955106623,
|
| 3180 |
+
"grad_norm": 0.017400693148374557,
|
| 3181 |
+
"learning_rate": 3.0249551846667207e-05,
|
| 3182 |
+
"loss": 0.0098,
|
| 3183 |
+
"step": 370
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 3.3288439955106623,
|
| 3187 |
+
"eval_loss": 0.012761359103024006,
|
| 3188 |
+
"eval_runtime": 6.2866,
|
| 3189 |
+
"eval_samples_per_second": 7.953,
|
| 3190 |
+
"eval_steps_per_second": 2.068,
|
| 3191 |
+
"step": 370
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 3.3378226711560046,
|
| 3195 |
+
"grad_norm": 0.02055426687002182,
|
| 3196 |
+
"learning_rate": 2.996075582443658e-05,
|
| 3197 |
+
"loss": 0.0115,
|
| 3198 |
+
"step": 371
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 3.346801346801347,
|
| 3202 |
+
"grad_norm": 0.014372746460139751,
|
| 3203 |
+
"learning_rate": 2.9672754091221805e-05,
|
| 3204 |
+
"loss": 0.0086,
|
| 3205 |
+
"step": 372
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 3.355780022446689,
|
| 3209 |
+
"grad_norm": 0.01651662401854992,
|
| 3210 |
+
"learning_rate": 2.938555806245406e-05,
|
| 3211 |
+
"loss": 0.0106,
|
| 3212 |
+
"step": 373
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 3.3647586980920314,
|
| 3216 |
+
"grad_norm": 0.016991253942251205,
|
| 3217 |
+
"learning_rate": 2.9099179121629117e-05,
|
| 3218 |
+
"loss": 0.0115,
|
| 3219 |
+
"step": 374
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 3.3737373737373737,
|
| 3223 |
+
"grad_norm": 0.016502108424901962,
|
| 3224 |
+
"learning_rate": 2.881362861985606e-05,
|
| 3225 |
+
"loss": 0.0092,
|
| 3226 |
+
"step": 375
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 3.3737373737373737,
|
| 3230 |
+
"eval_loss": 0.012749603018164635,
|
| 3231 |
+
"eval_runtime": 6.2727,
|
| 3232 |
+
"eval_samples_per_second": 7.971,
|
| 3233 |
+
"eval_steps_per_second": 2.072,
|
| 3234 |
+
"step": 375
|
| 3235 |
+
},
|
| 3236 |
+
{
|
| 3237 |
+
"epoch": 3.382716049382716,
|
| 3238 |
+
"grad_norm": 0.015984639525413513,
|
| 3239 |
+
"learning_rate": 2.8528917875407433e-05,
|
| 3240 |
+
"loss": 0.0094,
|
| 3241 |
+
"step": 376
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"epoch": 3.3916947250280582,
|
| 3245 |
+
"grad_norm": 0.03028254769742489,
|
| 3246 |
+
"learning_rate": 2.8245058173270622e-05,
|
| 3247 |
+
"loss": 0.0102,
|
| 3248 |
+
"step": 377
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"epoch": 3.4006734006734005,
|
| 3252 |
+
"grad_norm": 0.021088914945721626,
|
| 3253 |
+
"learning_rate": 2.796206076470044e-05,
|
| 3254 |
+
"loss": 0.0082,
|
| 3255 |
+
"step": 378
|
| 3256 |
+
},
|
| 3257 |
+
{
|
| 3258 |
+
"epoch": 3.409652076318743,
|
| 3259 |
+
"grad_norm": 0.019139107316732407,
|
| 3260 |
+
"learning_rate": 2.7679936866773315e-05,
|
| 3261 |
+
"loss": 0.0095,
|
| 3262 |
+
"step": 379
|
| 3263 |
+
},
|
| 3264 |
+
{
|
| 3265 |
+
"epoch": 3.418630751964085,
|
| 3266 |
+
"grad_norm": 0.018426954746246338,
|
| 3267 |
+
"learning_rate": 2.739869766194263e-05,
|
| 3268 |
+
"loss": 0.0114,
|
| 3269 |
+
"step": 380
|
| 3270 |
+
},
|
| 3271 |
+
{
|
| 3272 |
+
"epoch": 3.418630751964085,
|
| 3273 |
+
"eval_loss": 0.012560264207422733,
|
| 3274 |
+
"eval_runtime": 6.2597,
|
| 3275 |
+
"eval_samples_per_second": 7.988,
|
| 3276 |
+
"eval_steps_per_second": 2.077,
|
| 3277 |
+
"step": 380
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 3.4276094276094278,
|
| 3281 |
+
"grad_norm": 0.019736235961318016,
|
| 3282 |
+
"learning_rate": 2.7118354297595396e-05,
|
| 3283 |
+
"loss": 0.01,
|
| 3284 |
+
"step": 381
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 3.43658810325477,
|
| 3288 |
+
"grad_norm": 0.015529734082520008,
|
| 3289 |
+
"learning_rate": 2.683891788561055e-05,
|
| 3290 |
+
"loss": 0.0109,
|
| 3291 |
+
"step": 382
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 3.4455667789001123,
|
| 3295 |
+
"grad_norm": 0.01170337200164795,
|
| 3296 |
+
"learning_rate": 2.6560399501918465e-05,
|
| 3297 |
+
"loss": 0.0083,
|
| 3298 |
+
"step": 383
|
| 3299 |
+
},
|
| 3300 |
+
{
|
| 3301 |
+
"epoch": 3.4545454545454546,
|
| 3302 |
+
"grad_norm": 0.016096895560622215,
|
| 3303 |
+
"learning_rate": 2.6282810186061862e-05,
|
| 3304 |
+
"loss": 0.0095,
|
| 3305 |
+
"step": 384
|
| 3306 |
+
},
|
| 3307 |
+
{
|
| 3308 |
+
"epoch": 3.463524130190797,
|
| 3309 |
+
"grad_norm": 0.022902794182300568,
|
| 3310 |
+
"learning_rate": 2.600616094075835e-05,
|
| 3311 |
+
"loss": 0.0118,
|
| 3312 |
+
"step": 385
|
| 3313 |
+
},
|
| 3314 |
+
{
|
| 3315 |
+
"epoch": 3.463524130190797,
|
| 3316 |
+
"eval_loss": 0.012463411316275597,
|
| 3317 |
+
"eval_runtime": 6.256,
|
| 3318 |
+
"eval_samples_per_second": 7.992,
|
| 3319 |
+
"eval_steps_per_second": 2.078,
|
| 3320 |
+
"step": 385
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 3.472502805836139,
|
| 3324 |
+
"grad_norm": 0.01635258086025715,
|
| 3325 |
+
"learning_rate": 2.5730462731464273e-05,
|
| 3326 |
+
"loss": 0.0106,
|
| 3327 |
+
"step": 386
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 3.4814814814814814,
|
| 3331 |
+
"grad_norm": 0.019135868176817894,
|
| 3332 |
+
"learning_rate": 2.5455726485940012e-05,
|
| 3333 |
+
"loss": 0.0088,
|
| 3334 |
+
"step": 387
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 3.4904601571268237,
|
| 3338 |
+
"grad_norm": 0.015336276032030582,
|
| 3339 |
+
"learning_rate": 2.5181963093816962e-05,
|
| 3340 |
+
"loss": 0.0086,
|
| 3341 |
+
"step": 388
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 3.499438832772166,
|
| 3345 |
+
"grad_norm": 0.019149543717503548,
|
| 3346 |
+
"learning_rate": 2.4909183406165836e-05,
|
| 3347 |
+
"loss": 0.0095,
|
| 3348 |
+
"step": 389
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 3.5084175084175087,
|
| 3352 |
+
"grad_norm": 0.01899711787700653,
|
| 3353 |
+
"learning_rate": 2.4637398235066527e-05,
|
| 3354 |
+
"loss": 0.0108,
|
| 3355 |
+
"step": 390
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 3.5084175084175087,
|
| 3359 |
+
"eval_loss": 0.012311117723584175,
|
| 3360 |
+
"eval_runtime": 6.2629,
|
| 3361 |
+
"eval_samples_per_second": 7.983,
|
| 3362 |
+
"eval_steps_per_second": 2.076,
|
| 3363 |
+
"step": 390
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 3.517396184062851,
|
| 3367 |
+
"grad_norm": 0.025319568812847137,
|
| 3368 |
+
"learning_rate": 2.4366618353179644e-05,
|
| 3369 |
+
"loss": 0.0128,
|
| 3370 |
+
"step": 391
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 3.526374859708193,
|
| 3374 |
+
"grad_norm": 0.014999724924564362,
|
| 3375 |
+
"learning_rate": 2.4096854493319477e-05,
|
| 3376 |
+
"loss": 0.0089,
|
| 3377 |
+
"step": 392
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 3.5353535353535355,
|
| 3381 |
+
"grad_norm": 0.0133373336866498,
|
| 3382 |
+
"learning_rate": 2.3828117348028528e-05,
|
| 3383 |
+
"loss": 0.0088,
|
| 3384 |
+
"step": 393
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 3.5443322109988777,
|
| 3388 |
+
"grad_norm": 0.016392188146710396,
|
| 3389 |
+
"learning_rate": 2.3560417569153796e-05,
|
| 3390 |
+
"loss": 0.0096,
|
| 3391 |
+
"step": 394
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 3.55331088664422,
|
| 3395 |
+
"grad_norm": 0.017216209322214127,
|
| 3396 |
+
"learning_rate": 2.3293765767424537e-05,
|
| 3397 |
+
"loss": 0.0092,
|
| 3398 |
+
"step": 395
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 3.55331088664422,
|
| 3402 |
+
"eval_loss": 0.012257438153028488,
|
| 3403 |
+
"eval_runtime": 6.2604,
|
| 3404 |
+
"eval_samples_per_second": 7.987,
|
| 3405 |
+
"eval_steps_per_second": 2.077,
|
| 3406 |
+
"step": 395
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 3.5622895622895623,
|
| 3410 |
+
"grad_norm": 0.021824954077601433,
|
| 3411 |
+
"learning_rate": 2.3028172512031604e-05,
|
| 3412 |
+
"loss": 0.0101,
|
| 3413 |
+
"step": 396
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 3.5712682379349046,
|
| 3417 |
+
"grad_norm": 0.017453951761126518,
|
| 3418 |
+
"learning_rate": 2.276364833020868e-05,
|
| 3419 |
+
"loss": 0.0103,
|
| 3420 |
+
"step": 397
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 3.580246913580247,
|
| 3424 |
+
"grad_norm": 0.014409264549612999,
|
| 3425 |
+
"learning_rate": 2.2500203706814856e-05,
|
| 3426 |
+
"loss": 0.0089,
|
| 3427 |
+
"step": 398
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 3.589225589225589,
|
| 3431 |
+
"grad_norm": 0.015458152629435062,
|
| 3432 |
+
"learning_rate": 2.2237849083919142e-05,
|
| 3433 |
+
"loss": 0.0097,
|
| 3434 |
+
"step": 399
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 3.5982042648709314,
|
| 3438 |
+
"grad_norm": 0.01887071318924427,
|
| 3439 |
+
"learning_rate": 2.1976594860386597e-05,
|
| 3440 |
+
"loss": 0.0085,
|
| 3441 |
+
"step": 400
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 3.5982042648709314,
|
| 3445 |
+
"eval_loss": 0.01230713166296482,
|
| 3446 |
+
"eval_runtime": 6.2496,
|
| 3447 |
+
"eval_samples_per_second": 8.0,
|
| 3448 |
+
"eval_steps_per_second": 2.08,
|
| 3449 |
+
"step": 400
|
| 3450 |
+
}
|
| 3451 |
+
],
|
| 3452 |
+
"logging_steps": 1,
|
| 3453 |
+
"max_steps": 555,
|
| 3454 |
+
"num_input_tokens_seen": 0,
|
| 3455 |
+
"num_train_epochs": 5,
|
| 3456 |
+
"save_steps": 50,
|
| 3457 |
+
"stateful_callbacks": {
|
| 3458 |
+
"TrainerControl": {
|
| 3459 |
+
"args": {
|
| 3460 |
+
"should_epoch_stop": false,
|
| 3461 |
+
"should_evaluate": false,
|
| 3462 |
+
"should_log": false,
|
| 3463 |
+
"should_save": true,
|
| 3464 |
+
"should_training_stop": false
|
| 3465 |
+
},
|
| 3466 |
+
"attributes": {}
|
| 3467 |
+
}
|
| 3468 |
+
},
|
| 3469 |
+
"total_flos": 6.688454143520932e+17,
|
| 3470 |
+
"train_batch_size": 4,
|
| 3471 |
+
"trial_name": null,
|
| 3472 |
+
"trial_params": null
|
| 3473 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7620db18748370d6edc12f1526de582c700650730ef6c3f303f0f681b0be506d
|
| 3 |
+
size 5432
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.992143658810326,
|
| 3 |
+
"eval_loss": 0.012307128868997097,
|
| 4 |
+
"eval_runtime": 6.2704,
|
| 5 |
+
"eval_samples_per_second": 7.974,
|
| 6 |
+
"eval_steps_per_second": 2.073
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"split_special_tokens": false,
|
| 2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2065 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.992143658810326,
|
| 3 |
+
"total_flos": 9.281622886148997e+17,
|
| 4 |
+
"train_loss": 0.013788488566002868,
|
| 5 |
+
"train_runtime": 7381.5879,
|
| 6 |
+
"train_samples_per_second": 2.412,
|
| 7 |
+
"train_steps_per_second": 0.075
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7620db18748370d6edc12f1526de582c700650730ef6c3f303f0f681b0be506d
|
| 3 |
+
size 5432
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|