- README.md +156 -0
- added_tokens.json +127 -0
- config.json +33 -0
- generation_config.json +7 -0
- logs/events.out.tfevents.1713846416.ip-10-25-205-144.8866.0 +3 -0
- logs/events.out.tfevents.1713852536.ip-10-25-205-144.8866.1 +3 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +150 -0
- tokenizer_config.json +1162 -0
- trainer_state.json +993 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/byt5-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: byt5_3k_4d
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# byt5_3k_4d
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0348
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 800
|
| 39 |
+
- eval_batch_size: 800
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 100
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| No log | 1.0 | 4 | 0.4702 |
|
| 50 |
+
| No log | 2.0 | 8 | 0.4366 |
|
| 51 |
+
| 0.8301 | 3.0 | 12 | 0.4202 |
|
| 52 |
+
| 0.8301 | 4.0 | 16 | 0.3843 |
|
| 53 |
+
| 0.7703 | 5.0 | 20 | 0.3898 |
|
| 54 |
+
| 0.7703 | 6.0 | 24 | 0.3573 |
|
| 55 |
+
| 0.7703 | 7.0 | 28 | 0.3422 |
|
| 56 |
+
| 0.7169 | 8.0 | 32 | 0.3304 |
|
| 57 |
+
| 0.7169 | 9.0 | 36 | 0.3049 |
|
| 58 |
+
| 0.6727 | 10.0 | 40 | 0.3067 |
|
| 59 |
+
| 0.6727 | 11.0 | 44 | 0.2965 |
|
| 60 |
+
| 0.6727 | 12.0 | 48 | 0.2693 |
|
| 61 |
+
| 0.6394 | 13.0 | 52 | 0.2711 |
|
| 62 |
+
| 0.6394 | 14.0 | 56 | 0.2561 |
|
| 63 |
+
| 0.6047 | 15.0 | 60 | 0.2454 |
|
| 64 |
+
| 0.6047 | 16.0 | 64 | 0.2368 |
|
| 65 |
+
| 0.6047 | 17.0 | 68 | 0.2250 |
|
| 66 |
+
| 0.565 | 18.0 | 72 | 0.2110 |
|
| 67 |
+
| 0.565 | 19.0 | 76 | 0.2109 |
|
| 68 |
+
| 0.5368 | 20.0 | 80 | 0.1950 |
|
| 69 |
+
| 0.5368 | 21.0 | 84 | 0.1974 |
|
| 70 |
+
| 0.5368 | 22.0 | 88 | 0.1819 |
|
| 71 |
+
| 0.518 | 23.0 | 92 | 0.1795 |
|
| 72 |
+
| 0.518 | 24.0 | 96 | 0.1648 |
|
| 73 |
+
| 0.4862 | 25.0 | 100 | 0.1675 |
|
| 74 |
+
| 0.4862 | 26.0 | 104 | 0.1550 |
|
| 75 |
+
| 0.4862 | 27.0 | 108 | 0.1530 |
|
| 76 |
+
| 0.4628 | 28.0 | 112 | 0.1447 |
|
| 77 |
+
| 0.4628 | 29.0 | 116 | 0.1442 |
|
| 78 |
+
| 0.4408 | 30.0 | 120 | 0.1310 |
|
| 79 |
+
| 0.4408 | 31.0 | 124 | 0.1336 |
|
| 80 |
+
| 0.4408 | 32.0 | 128 | 0.1235 |
|
| 81 |
+
| 0.4192 | 33.0 | 132 | 0.1191 |
|
| 82 |
+
| 0.4192 | 34.0 | 136 | 0.1193 |
|
| 83 |
+
| 0.4133 | 35.0 | 140 | 0.1123 |
|
| 84 |
+
| 0.4133 | 36.0 | 144 | 0.1156 |
|
| 85 |
+
| 0.4133 | 37.0 | 148 | 0.1051 |
|
| 86 |
+
| 0.3922 | 38.0 | 152 | 0.0999 |
|
| 87 |
+
| 0.3922 | 39.0 | 156 | 0.0991 |
|
| 88 |
+
| 0.3778 | 40.0 | 160 | 0.0995 |
|
| 89 |
+
| 0.3778 | 41.0 | 164 | 0.0912 |
|
| 90 |
+
| 0.3778 | 42.0 | 168 | 0.0903 |
|
| 91 |
+
| 0.3655 | 43.0 | 172 | 0.0841 |
|
| 92 |
+
| 0.3655 | 44.0 | 176 | 0.0790 |
|
| 93 |
+
| 0.3526 | 45.0 | 180 | 0.0827 |
|
| 94 |
+
| 0.3526 | 46.0 | 184 | 0.0756 |
|
| 95 |
+
| 0.3526 | 47.0 | 188 | 0.0747 |
|
| 96 |
+
| 0.3378 | 48.0 | 192 | 0.0737 |
|
| 97 |
+
| 0.3378 | 49.0 | 196 | 0.0747 |
|
| 98 |
+
| 0.3308 | 50.0 | 200 | 0.0729 |
|
| 99 |
+
| 0.3308 | 51.0 | 204 | 0.0665 |
|
| 100 |
+
| 0.3308 | 52.0 | 208 | 0.0663 |
|
| 101 |
+
| 0.321 | 53.0 | 212 | 0.0642 |
|
| 102 |
+
| 0.321 | 54.0 | 216 | 0.0640 |
|
| 103 |
+
| 0.3084 | 55.0 | 220 | 0.0632 |
|
| 104 |
+
| 0.3084 | 56.0 | 224 | 0.0599 |
|
| 105 |
+
| 0.3084 | 57.0 | 228 | 0.0580 |
|
| 106 |
+
| 0.2967 | 58.0 | 232 | 0.0567 |
|
| 107 |
+
| 0.2967 | 59.0 | 236 | 0.0525 |
|
| 108 |
+
| 0.2928 | 60.0 | 240 | 0.0522 |
|
| 109 |
+
| 0.2928 | 61.0 | 244 | 0.0536 |
|
| 110 |
+
| 0.2928 | 62.0 | 248 | 0.0524 |
|
| 111 |
+
| 0.2929 | 63.0 | 252 | 0.0568 |
|
| 112 |
+
| 0.2929 | 64.0 | 256 | 0.0530 |
|
| 113 |
+
| 0.283 | 65.0 | 260 | 0.0476 |
|
| 114 |
+
| 0.283 | 66.0 | 264 | 0.0479 |
|
| 115 |
+
| 0.283 | 67.0 | 268 | 0.0507 |
|
| 116 |
+
| 0.2766 | 68.0 | 272 | 0.0461 |
|
| 117 |
+
| 0.2766 | 69.0 | 276 | 0.0444 |
|
| 118 |
+
| 0.2677 | 70.0 | 280 | 0.0456 |
|
| 119 |
+
| 0.2677 | 71.0 | 284 | 0.0437 |
|
| 120 |
+
| 0.2677 | 72.0 | 288 | 0.0428 |
|
| 121 |
+
| 0.2614 | 73.0 | 292 | 0.0419 |
|
| 122 |
+
| 0.2614 | 74.0 | 296 | 0.0414 |
|
| 123 |
+
| 0.2595 | 75.0 | 300 | 0.0418 |
|
| 124 |
+
| 0.2595 | 76.0 | 304 | 0.0412 |
|
| 125 |
+
| 0.2595 | 77.0 | 308 | 0.0396 |
|
| 126 |
+
| 0.2582 | 78.0 | 312 | 0.0382 |
|
| 127 |
+
| 0.2582 | 79.0 | 316 | 0.0381 |
|
| 128 |
+
| 0.2511 | 80.0 | 320 | 0.0387 |
|
| 129 |
+
| 0.2511 | 81.0 | 324 | 0.0388 |
|
| 130 |
+
| 0.2511 | 82.0 | 328 | 0.0372 |
|
| 131 |
+
| 0.2481 | 83.0 | 332 | 0.0360 |
|
| 132 |
+
| 0.2481 | 84.0 | 336 | 0.0366 |
|
| 133 |
+
| 0.2474 | 85.0 | 340 | 0.0365 |
|
| 134 |
+
| 0.2474 | 86.0 | 344 | 0.0357 |
|
| 135 |
+
| 0.2474 | 87.0 | 348 | 0.0355 |
|
| 136 |
+
| 0.2537 | 88.0 | 352 | 0.0360 |
|
| 137 |
+
| 0.2537 | 89.0 | 356 | 0.0359 |
|
| 138 |
+
| 0.2438 | 90.0 | 360 | 0.0355 |
|
| 139 |
+
| 0.2438 | 91.0 | 364 | 0.0353 |
|
| 140 |
+
| 0.2438 | 92.0 | 368 | 0.0349 |
|
| 141 |
+
| 0.2461 | 93.0 | 372 | 0.0343 |
|
| 142 |
+
| 0.2461 | 94.0 | 376 | 0.0342 |
|
| 143 |
+
| 0.2395 | 95.0 | 380 | 0.0344 |
|
| 144 |
+
| 0.2395 | 96.0 | 384 | 0.0347 |
|
| 145 |
+
| 0.2395 | 97.0 | 388 | 0.0350 |
|
| 146 |
+
| 0.2439 | 98.0 | 392 | 0.0349 |
|
| 147 |
+
| 0.2439 | 99.0 | 396 | 0.0348 |
|
| 148 |
+
| 0.2432 | 100.0 | 400 | 0.0348 |
|
| 149 |
+
|
| 150 |
+
|
| 151 |
+
### Framework versions
|
| 152 |
+
|
| 153 |
+
- Transformers 4.35.2
|
| 154 |
+
- Pytorch 2.2.1+cu121
|
| 155 |
+
- Datasets 2.18.0
|
| 156 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 259,
|
| 3 |
+
"<extra_id_100>": 359,
|
| 4 |
+
"<extra_id_101>": 360,
|
| 5 |
+
"<extra_id_102>": 361,
|
| 6 |
+
"<extra_id_103>": 362,
|
| 7 |
+
"<extra_id_104>": 363,
|
| 8 |
+
"<extra_id_105>": 364,
|
| 9 |
+
"<extra_id_106>": 365,
|
| 10 |
+
"<extra_id_107>": 366,
|
| 11 |
+
"<extra_id_108>": 367,
|
| 12 |
+
"<extra_id_109>": 368,
|
| 13 |
+
"<extra_id_10>": 269,
|
| 14 |
+
"<extra_id_110>": 369,
|
| 15 |
+
"<extra_id_111>": 370,
|
| 16 |
+
"<extra_id_112>": 371,
|
| 17 |
+
"<extra_id_113>": 372,
|
| 18 |
+
"<extra_id_114>": 373,
|
| 19 |
+
"<extra_id_115>": 374,
|
| 20 |
+
"<extra_id_116>": 375,
|
| 21 |
+
"<extra_id_117>": 376,
|
| 22 |
+
"<extra_id_118>": 377,
|
| 23 |
+
"<extra_id_119>": 378,
|
| 24 |
+
"<extra_id_11>": 270,
|
| 25 |
+
"<extra_id_120>": 379,
|
| 26 |
+
"<extra_id_121>": 380,
|
| 27 |
+
"<extra_id_122>": 381,
|
| 28 |
+
"<extra_id_123>": 382,
|
| 29 |
+
"<extra_id_124>": 383,
|
| 30 |
+
"<extra_id_12>": 271,
|
| 31 |
+
"<extra_id_13>": 272,
|
| 32 |
+
"<extra_id_14>": 273,
|
| 33 |
+
"<extra_id_15>": 274,
|
| 34 |
+
"<extra_id_16>": 275,
|
| 35 |
+
"<extra_id_17>": 276,
|
| 36 |
+
"<extra_id_18>": 277,
|
| 37 |
+
"<extra_id_19>": 278,
|
| 38 |
+
"<extra_id_1>": 260,
|
| 39 |
+
"<extra_id_20>": 279,
|
| 40 |
+
"<extra_id_21>": 280,
|
| 41 |
+
"<extra_id_22>": 281,
|
| 42 |
+
"<extra_id_23>": 282,
|
| 43 |
+
"<extra_id_24>": 283,
|
| 44 |
+
"<extra_id_25>": 284,
|
| 45 |
+
"<extra_id_26>": 285,
|
| 46 |
+
"<extra_id_27>": 286,
|
| 47 |
+
"<extra_id_28>": 287,
|
| 48 |
+
"<extra_id_29>": 288,
|
| 49 |
+
"<extra_id_2>": 261,
|
| 50 |
+
"<extra_id_30>": 289,
|
| 51 |
+
"<extra_id_31>": 290,
|
| 52 |
+
"<extra_id_32>": 291,
|
| 53 |
+
"<extra_id_33>": 292,
|
| 54 |
+
"<extra_id_34>": 293,
|
| 55 |
+
"<extra_id_35>": 294,
|
| 56 |
+
"<extra_id_36>": 295,
|
| 57 |
+
"<extra_id_37>": 296,
|
| 58 |
+
"<extra_id_38>": 297,
|
| 59 |
+
"<extra_id_39>": 298,
|
| 60 |
+
"<extra_id_3>": 262,
|
| 61 |
+
"<extra_id_40>": 299,
|
| 62 |
+
"<extra_id_41>": 300,
|
| 63 |
+
"<extra_id_42>": 301,
|
| 64 |
+
"<extra_id_43>": 302,
|
| 65 |
+
"<extra_id_44>": 303,
|
| 66 |
+
"<extra_id_45>": 304,
|
| 67 |
+
"<extra_id_46>": 305,
|
| 68 |
+
"<extra_id_47>": 306,
|
| 69 |
+
"<extra_id_48>": 307,
|
| 70 |
+
"<extra_id_49>": 308,
|
| 71 |
+
"<extra_id_4>": 263,
|
| 72 |
+
"<extra_id_50>": 309,
|
| 73 |
+
"<extra_id_51>": 310,
|
| 74 |
+
"<extra_id_52>": 311,
|
| 75 |
+
"<extra_id_53>": 312,
|
| 76 |
+
"<extra_id_54>": 313,
|
| 77 |
+
"<extra_id_55>": 314,
|
| 78 |
+
"<extra_id_56>": 315,
|
| 79 |
+
"<extra_id_57>": 316,
|
| 80 |
+
"<extra_id_58>": 317,
|
| 81 |
+
"<extra_id_59>": 318,
|
| 82 |
+
"<extra_id_5>": 264,
|
| 83 |
+
"<extra_id_60>": 319,
|
| 84 |
+
"<extra_id_61>": 320,
|
| 85 |
+
"<extra_id_62>": 321,
|
| 86 |
+
"<extra_id_63>": 322,
|
| 87 |
+
"<extra_id_64>": 323,
|
| 88 |
+
"<extra_id_65>": 324,
|
| 89 |
+
"<extra_id_66>": 325,
|
| 90 |
+
"<extra_id_67>": 326,
|
| 91 |
+
"<extra_id_68>": 327,
|
| 92 |
+
"<extra_id_69>": 328,
|
| 93 |
+
"<extra_id_6>": 265,
|
| 94 |
+
"<extra_id_70>": 329,
|
| 95 |
+
"<extra_id_71>": 330,
|
| 96 |
+
"<extra_id_72>": 331,
|
| 97 |
+
"<extra_id_73>": 332,
|
| 98 |
+
"<extra_id_74>": 333,
|
| 99 |
+
"<extra_id_75>": 334,
|
| 100 |
+
"<extra_id_76>": 335,
|
| 101 |
+
"<extra_id_77>": 336,
|
| 102 |
+
"<extra_id_78>": 337,
|
| 103 |
+
"<extra_id_79>": 338,
|
| 104 |
+
"<extra_id_7>": 266,
|
| 105 |
+
"<extra_id_80>": 339,
|
| 106 |
+
"<extra_id_81>": 340,
|
| 107 |
+
"<extra_id_82>": 341,
|
| 108 |
+
"<extra_id_83>": 342,
|
| 109 |
+
"<extra_id_84>": 343,
|
| 110 |
+
"<extra_id_85>": 344,
|
| 111 |
+
"<extra_id_86>": 345,
|
| 112 |
+
"<extra_id_87>": 346,
|
| 113 |
+
"<extra_id_88>": 347,
|
| 114 |
+
"<extra_id_89>": 348,
|
| 115 |
+
"<extra_id_8>": 267,
|
| 116 |
+
"<extra_id_90>": 349,
|
| 117 |
+
"<extra_id_91>": 350,
|
| 118 |
+
"<extra_id_92>": 351,
|
| 119 |
+
"<extra_id_93>": 352,
|
| 120 |
+
"<extra_id_94>": 353,
|
| 121 |
+
"<extra_id_95>": 354,
|
| 122 |
+
"<extra_id_96>": 355,
|
| 123 |
+
"<extra_id_97>": 356,
|
| 124 |
+
"<extra_id_98>": 357,
|
| 125 |
+
"<extra_id_99>": 358,
|
| 126 |
+
"<extra_id_9>": 268
|
| 127 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/byt5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3584,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1472,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"num_decoder_layers": 4,
|
| 22 |
+
"num_heads": 6,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.35.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 384
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.2"
|
| 7 |
+
}
|
logs/events.out.tfevents.1713846416.ip-10-25-205-144.8866.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58660723f1ff058fe63346b9199d47b545e684bec9d1f995d32e71f8f2806c1d
|
| 3 |
+
size 71462
|
logs/events.out.tfevents.1713852536.ip-10-25-205-144.8866.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:875e9404f459e90dd99b09bf6ca3b14c3de1307ca8b82fbfb6d119071a0904c9
|
| 3 |
+
size 38110
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6158bada807558705e9e26098aad17aedc42da823207b33f8dee3fab05d572c7
|
| 3 |
+
size 1198571496
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b96304cfe69fa90826dab1cbd298ee42a5dca2d32ac364eeaf2293e430f6c930
|
| 3 |
+
size 2397245434
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30baa2ab08d0be6effb648982f26878a297a2ecba27846f3f222741d4c9eb22e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c2e8e641e0881a9a98caa87a71b0daaf98aab07bd0e3d063a6da3ec00e41336
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>",
|
| 103 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"eos_token": {
|
| 130 |
+
"content": "</s>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": true,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
"pad_token": {
|
| 137 |
+
"content": "<pad>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
"unk_token": {
|
| 144 |
+
"content": "<unk>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
}
|
| 150 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"259": {
|
| 28 |
+
"content": "<extra_id_0>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"260": {
|
| 36 |
+
"content": "<extra_id_1>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"261": {
|
| 44 |
+
"content": "<extra_id_2>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"262": {
|
| 52 |
+
"content": "<extra_id_3>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"263": {
|
| 60 |
+
"content": "<extra_id_4>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"264": {
|
| 68 |
+
"content": "<extra_id_5>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"265": {
|
| 76 |
+
"content": "<extra_id_6>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"266": {
|
| 84 |
+
"content": "<extra_id_7>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"267": {
|
| 92 |
+
"content": "<extra_id_8>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"268": {
|
| 100 |
+
"content": "<extra_id_9>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"269": {
|
| 108 |
+
"content": "<extra_id_10>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"270": {
|
| 116 |
+
"content": "<extra_id_11>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"271": {
|
| 124 |
+
"content": "<extra_id_12>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"272": {
|
| 132 |
+
"content": "<extra_id_13>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"273": {
|
| 140 |
+
"content": "<extra_id_14>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"274": {
|
| 148 |
+
"content": "<extra_id_15>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"275": {
|
| 156 |
+
"content": "<extra_id_16>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"276": {
|
| 164 |
+
"content": "<extra_id_17>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"277": {
|
| 172 |
+
"content": "<extra_id_18>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"278": {
|
| 180 |
+
"content": "<extra_id_19>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"279": {
|
| 188 |
+
"content": "<extra_id_20>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"280": {
|
| 196 |
+
"content": "<extra_id_21>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"281": {
|
| 204 |
+
"content": "<extra_id_22>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"282": {
|
| 212 |
+
"content": "<extra_id_23>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"283": {
|
| 220 |
+
"content": "<extra_id_24>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"284": {
|
| 228 |
+
"content": "<extra_id_25>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"285": {
|
| 236 |
+
"content": "<extra_id_26>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"286": {
|
| 244 |
+
"content": "<extra_id_27>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"287": {
|
| 252 |
+
"content": "<extra_id_28>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"288": {
|
| 260 |
+
"content": "<extra_id_29>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"289": {
|
| 268 |
+
"content": "<extra_id_30>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"290": {
|
| 276 |
+
"content": "<extra_id_31>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"291": {
|
| 284 |
+
"content": "<extra_id_32>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"292": {
|
| 292 |
+
"content": "<extra_id_33>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"293": {
|
| 300 |
+
"content": "<extra_id_34>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"294": {
|
| 308 |
+
"content": "<extra_id_35>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"295": {
|
| 316 |
+
"content": "<extra_id_36>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"296": {
|
| 324 |
+
"content": "<extra_id_37>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"297": {
|
| 332 |
+
"content": "<extra_id_38>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"298": {
|
| 340 |
+
"content": "<extra_id_39>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"299": {
|
| 348 |
+
"content": "<extra_id_40>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"300": {
|
| 356 |
+
"content": "<extra_id_41>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"301": {
|
| 364 |
+
"content": "<extra_id_42>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"302": {
|
| 372 |
+
"content": "<extra_id_43>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"303": {
|
| 380 |
+
"content": "<extra_id_44>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"304": {
|
| 388 |
+
"content": "<extra_id_45>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"305": {
|
| 396 |
+
"content": "<extra_id_46>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"306": {
|
| 404 |
+
"content": "<extra_id_47>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"307": {
|
| 412 |
+
"content": "<extra_id_48>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"308": {
|
| 420 |
+
"content": "<extra_id_49>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"309": {
|
| 428 |
+
"content": "<extra_id_50>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"310": {
|
| 436 |
+
"content": "<extra_id_51>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"311": {
|
| 444 |
+
"content": "<extra_id_52>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"312": {
|
| 452 |
+
"content": "<extra_id_53>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"313": {
|
| 460 |
+
"content": "<extra_id_54>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"314": {
|
| 468 |
+
"content": "<extra_id_55>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"315": {
|
| 476 |
+
"content": "<extra_id_56>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"316": {
|
| 484 |
+
"content": "<extra_id_57>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"317": {
|
| 492 |
+
"content": "<extra_id_58>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"318": {
|
| 500 |
+
"content": "<extra_id_59>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"319": {
|
| 508 |
+
"content": "<extra_id_60>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"320": {
|
| 516 |
+
"content": "<extra_id_61>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"321": {
|
| 524 |
+
"content": "<extra_id_62>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"322": {
|
| 532 |
+
"content": "<extra_id_63>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"323": {
|
| 540 |
+
"content": "<extra_id_64>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"324": {
|
| 548 |
+
"content": "<extra_id_65>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"325": {
|
| 556 |
+
"content": "<extra_id_66>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"326": {
|
| 564 |
+
"content": "<extra_id_67>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"327": {
|
| 572 |
+
"content": "<extra_id_68>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"328": {
|
| 580 |
+
"content": "<extra_id_69>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"329": {
|
| 588 |
+
"content": "<extra_id_70>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"330": {
|
| 596 |
+
"content": "<extra_id_71>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"331": {
|
| 604 |
+
"content": "<extra_id_72>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"332": {
|
| 612 |
+
"content": "<extra_id_73>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"333": {
|
| 620 |
+
"content": "<extra_id_74>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"334": {
|
| 628 |
+
"content": "<extra_id_75>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"335": {
|
| 636 |
+
"content": "<extra_id_76>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"336": {
|
| 644 |
+
"content": "<extra_id_77>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"337": {
|
| 652 |
+
"content": "<extra_id_78>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"338": {
|
| 660 |
+
"content": "<extra_id_79>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"339": {
|
| 668 |
+
"content": "<extra_id_80>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"340": {
|
| 676 |
+
"content": "<extra_id_81>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"341": {
|
| 684 |
+
"content": "<extra_id_82>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"342": {
|
| 692 |
+
"content": "<extra_id_83>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"343": {
|
| 700 |
+
"content": "<extra_id_84>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"344": {
|
| 708 |
+
"content": "<extra_id_85>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"345": {
|
| 716 |
+
"content": "<extra_id_86>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"346": {
|
| 724 |
+
"content": "<extra_id_87>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"347": {
|
| 732 |
+
"content": "<extra_id_88>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"348": {
|
| 740 |
+
"content": "<extra_id_89>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"349": {
|
| 748 |
+
"content": "<extra_id_90>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"350": {
|
| 756 |
+
"content": "<extra_id_91>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"351": {
|
| 764 |
+
"content": "<extra_id_92>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"352": {
|
| 772 |
+
"content": "<extra_id_93>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"353": {
|
| 780 |
+
"content": "<extra_id_94>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"354": {
|
| 788 |
+
"content": "<extra_id_95>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"355": {
|
| 796 |
+
"content": "<extra_id_96>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"356": {
|
| 804 |
+
"content": "<extra_id_97>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"357": {
|
| 812 |
+
"content": "<extra_id_98>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"358": {
|
| 820 |
+
"content": "<extra_id_99>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"359": {
|
| 828 |
+
"content": "<extra_id_100>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"360": {
|
| 836 |
+
"content": "<extra_id_101>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"361": {
|
| 844 |
+
"content": "<extra_id_102>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"362": {
|
| 852 |
+
"content": "<extra_id_103>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"363": {
|
| 860 |
+
"content": "<extra_id_104>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"364": {
|
| 868 |
+
"content": "<extra_id_105>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"365": {
|
| 876 |
+
"content": "<extra_id_106>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"366": {
|
| 884 |
+
"content": "<extra_id_107>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"367": {
|
| 892 |
+
"content": "<extra_id_108>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"368": {
|
| 900 |
+
"content": "<extra_id_109>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"369": {
|
| 908 |
+
"content": "<extra_id_110>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"370": {
|
| 916 |
+
"content": "<extra_id_111>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"371": {
|
| 924 |
+
"content": "<extra_id_112>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"372": {
|
| 932 |
+
"content": "<extra_id_113>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"373": {
|
| 940 |
+
"content": "<extra_id_114>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"374": {
|
| 948 |
+
"content": "<extra_id_115>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"375": {
|
| 956 |
+
"content": "<extra_id_116>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"376": {
|
| 964 |
+
"content": "<extra_id_117>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"377": {
|
| 972 |
+
"content": "<extra_id_118>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"378": {
|
| 980 |
+
"content": "<extra_id_119>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"379": {
|
| 988 |
+
"content": "<extra_id_120>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"380": {
|
| 996 |
+
"content": "<extra_id_121>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"381": {
|
| 1004 |
+
"content": "<extra_id_122>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"382": {
|
| 1012 |
+
"content": "<extra_id_123>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"383": {
|
| 1020 |
+
"content": "<extra_id_124>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
}
|
| 1027 |
+
},
|
| 1028 |
+
"additional_special_tokens": [
|
| 1029 |
+
"<extra_id_0>",
|
| 1030 |
+
"<extra_id_1>",
|
| 1031 |
+
"<extra_id_2>",
|
| 1032 |
+
"<extra_id_3>",
|
| 1033 |
+
"<extra_id_4>",
|
| 1034 |
+
"<extra_id_5>",
|
| 1035 |
+
"<extra_id_6>",
|
| 1036 |
+
"<extra_id_7>",
|
| 1037 |
+
"<extra_id_8>",
|
| 1038 |
+
"<extra_id_9>",
|
| 1039 |
+
"<extra_id_10>",
|
| 1040 |
+
"<extra_id_11>",
|
| 1041 |
+
"<extra_id_12>",
|
| 1042 |
+
"<extra_id_13>",
|
| 1043 |
+
"<extra_id_14>",
|
| 1044 |
+
"<extra_id_15>",
|
| 1045 |
+
"<extra_id_16>",
|
| 1046 |
+
"<extra_id_17>",
|
| 1047 |
+
"<extra_id_18>",
|
| 1048 |
+
"<extra_id_19>",
|
| 1049 |
+
"<extra_id_20>",
|
| 1050 |
+
"<extra_id_21>",
|
| 1051 |
+
"<extra_id_22>",
|
| 1052 |
+
"<extra_id_23>",
|
| 1053 |
+
"<extra_id_24>",
|
| 1054 |
+
"<extra_id_25>",
|
| 1055 |
+
"<extra_id_26>",
|
| 1056 |
+
"<extra_id_27>",
|
| 1057 |
+
"<extra_id_28>",
|
| 1058 |
+
"<extra_id_29>",
|
| 1059 |
+
"<extra_id_30>",
|
| 1060 |
+
"<extra_id_31>",
|
| 1061 |
+
"<extra_id_32>",
|
| 1062 |
+
"<extra_id_33>",
|
| 1063 |
+
"<extra_id_34>",
|
| 1064 |
+
"<extra_id_35>",
|
| 1065 |
+
"<extra_id_36>",
|
| 1066 |
+
"<extra_id_37>",
|
| 1067 |
+
"<extra_id_38>",
|
| 1068 |
+
"<extra_id_39>",
|
| 1069 |
+
"<extra_id_40>",
|
| 1070 |
+
"<extra_id_41>",
|
| 1071 |
+
"<extra_id_42>",
|
| 1072 |
+
"<extra_id_43>",
|
| 1073 |
+
"<extra_id_44>",
|
| 1074 |
+
"<extra_id_45>",
|
| 1075 |
+
"<extra_id_46>",
|
| 1076 |
+
"<extra_id_47>",
|
| 1077 |
+
"<extra_id_48>",
|
| 1078 |
+
"<extra_id_49>",
|
| 1079 |
+
"<extra_id_50>",
|
| 1080 |
+
"<extra_id_51>",
|
| 1081 |
+
"<extra_id_52>",
|
| 1082 |
+
"<extra_id_53>",
|
| 1083 |
+
"<extra_id_54>",
|
| 1084 |
+
"<extra_id_55>",
|
| 1085 |
+
"<extra_id_56>",
|
| 1086 |
+
"<extra_id_57>",
|
| 1087 |
+
"<extra_id_58>",
|
| 1088 |
+
"<extra_id_59>",
|
| 1089 |
+
"<extra_id_60>",
|
| 1090 |
+
"<extra_id_61>",
|
| 1091 |
+
"<extra_id_62>",
|
| 1092 |
+
"<extra_id_63>",
|
| 1093 |
+
"<extra_id_64>",
|
| 1094 |
+
"<extra_id_65>",
|
| 1095 |
+
"<extra_id_66>",
|
| 1096 |
+
"<extra_id_67>",
|
| 1097 |
+
"<extra_id_68>",
|
| 1098 |
+
"<extra_id_69>",
|
| 1099 |
+
"<extra_id_70>",
|
| 1100 |
+
"<extra_id_71>",
|
| 1101 |
+
"<extra_id_72>",
|
| 1102 |
+
"<extra_id_73>",
|
| 1103 |
+
"<extra_id_74>",
|
| 1104 |
+
"<extra_id_75>",
|
| 1105 |
+
"<extra_id_76>",
|
| 1106 |
+
"<extra_id_77>",
|
| 1107 |
+
"<extra_id_78>",
|
| 1108 |
+
"<extra_id_79>",
|
| 1109 |
+
"<extra_id_80>",
|
| 1110 |
+
"<extra_id_81>",
|
| 1111 |
+
"<extra_id_82>",
|
| 1112 |
+
"<extra_id_83>",
|
| 1113 |
+
"<extra_id_84>",
|
| 1114 |
+
"<extra_id_85>",
|
| 1115 |
+
"<extra_id_86>",
|
| 1116 |
+
"<extra_id_87>",
|
| 1117 |
+
"<extra_id_88>",
|
| 1118 |
+
"<extra_id_89>",
|
| 1119 |
+
"<extra_id_90>",
|
| 1120 |
+
"<extra_id_91>",
|
| 1121 |
+
"<extra_id_92>",
|
| 1122 |
+
"<extra_id_93>",
|
| 1123 |
+
"<extra_id_94>",
|
| 1124 |
+
"<extra_id_95>",
|
| 1125 |
+
"<extra_id_96>",
|
| 1126 |
+
"<extra_id_97>",
|
| 1127 |
+
"<extra_id_98>",
|
| 1128 |
+
"<extra_id_99>",
|
| 1129 |
+
"<extra_id_100>",
|
| 1130 |
+
"<extra_id_101>",
|
| 1131 |
+
"<extra_id_102>",
|
| 1132 |
+
"<extra_id_103>",
|
| 1133 |
+
"<extra_id_104>",
|
| 1134 |
+
"<extra_id_105>",
|
| 1135 |
+
"<extra_id_106>",
|
| 1136 |
+
"<extra_id_107>",
|
| 1137 |
+
"<extra_id_108>",
|
| 1138 |
+
"<extra_id_109>",
|
| 1139 |
+
"<extra_id_110>",
|
| 1140 |
+
"<extra_id_111>",
|
| 1141 |
+
"<extra_id_112>",
|
| 1142 |
+
"<extra_id_113>",
|
| 1143 |
+
"<extra_id_114>",
|
| 1144 |
+
"<extra_id_115>",
|
| 1145 |
+
"<extra_id_116>",
|
| 1146 |
+
"<extra_id_117>",
|
| 1147 |
+
"<extra_id_118>",
|
| 1148 |
+
"<extra_id_119>",
|
| 1149 |
+
"<extra_id_120>",
|
| 1150 |
+
"<extra_id_121>",
|
| 1151 |
+
"<extra_id_122>",
|
| 1152 |
+
"<extra_id_123>",
|
| 1153 |
+
"<extra_id_124>"
|
| 1154 |
+
],
|
| 1155 |
+
"clean_up_tokenization_spaces": true,
|
| 1156 |
+
"eos_token": "</s>",
|
| 1157 |
+
"extra_ids": 0,
|
| 1158 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1159 |
+
"pad_token": "<pad>",
|
| 1160 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 1161 |
+
"unk_token": "<unk>"
|
| 1162 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,993 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.03415210172533989,
|
| 3 |
+
"best_model_checkpoint": "AlexWang99/byt5_3k_4d/checkpoint-376",
|
| 4 |
+
"epoch": 94.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 376,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_loss": 0.47024813294410706,
|
| 14 |
+
"eval_runtime": 10.75,
|
| 15 |
+
"eval_samples_per_second": 930.235,
|
| 16 |
+
"eval_steps_per_second": 1.209,
|
| 17 |
+
"step": 4
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_loss": 0.4366174340248108,
|
| 22 |
+
"eval_runtime": 10.8447,
|
| 23 |
+
"eval_samples_per_second": 922.113,
|
| 24 |
+
"eval_steps_per_second": 1.199,
|
| 25 |
+
"step": 8
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.5,
|
| 29 |
+
"learning_rate": 4.875e-05,
|
| 30 |
+
"loss": 0.8301,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.0,
|
| 35 |
+
"eval_loss": 0.4202331006526947,
|
| 36 |
+
"eval_runtime": 10.7807,
|
| 37 |
+
"eval_samples_per_second": 927.582,
|
| 38 |
+
"eval_steps_per_second": 1.206,
|
| 39 |
+
"step": 12
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.0,
|
| 43 |
+
"eval_loss": 0.38434356451034546,
|
| 44 |
+
"eval_runtime": 10.8022,
|
| 45 |
+
"eval_samples_per_second": 925.735,
|
| 46 |
+
"eval_steps_per_second": 1.203,
|
| 47 |
+
"step": 16
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 5.0,
|
| 51 |
+
"learning_rate": 4.75e-05,
|
| 52 |
+
"loss": 0.7703,
|
| 53 |
+
"step": 20
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 5.0,
|
| 57 |
+
"eval_loss": 0.38975098729133606,
|
| 58 |
+
"eval_runtime": 10.7363,
|
| 59 |
+
"eval_samples_per_second": 931.418,
|
| 60 |
+
"eval_steps_per_second": 1.211,
|
| 61 |
+
"step": 20
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 6.0,
|
| 65 |
+
"eval_loss": 0.35734379291534424,
|
| 66 |
+
"eval_runtime": 10.725,
|
| 67 |
+
"eval_samples_per_second": 932.399,
|
| 68 |
+
"eval_steps_per_second": 1.212,
|
| 69 |
+
"step": 24
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 7.0,
|
| 73 |
+
"eval_loss": 0.34219321608543396,
|
| 74 |
+
"eval_runtime": 10.9668,
|
| 75 |
+
"eval_samples_per_second": 911.84,
|
| 76 |
+
"eval_steps_per_second": 1.185,
|
| 77 |
+
"step": 28
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.5,
|
| 81 |
+
"learning_rate": 4.6250000000000006e-05,
|
| 82 |
+
"loss": 0.7169,
|
| 83 |
+
"step": 30
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 8.0,
|
| 87 |
+
"eval_loss": 0.330382376909256,
|
| 88 |
+
"eval_runtime": 10.8312,
|
| 89 |
+
"eval_samples_per_second": 923.257,
|
| 90 |
+
"eval_steps_per_second": 1.2,
|
| 91 |
+
"step": 32
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 9.0,
|
| 95 |
+
"eval_loss": 0.3048989772796631,
|
| 96 |
+
"eval_runtime": 10.726,
|
| 97 |
+
"eval_samples_per_second": 932.316,
|
| 98 |
+
"eval_steps_per_second": 1.212,
|
| 99 |
+
"step": 36
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 10.0,
|
| 103 |
+
"learning_rate": 4.5e-05,
|
| 104 |
+
"loss": 0.6727,
|
| 105 |
+
"step": 40
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 10.0,
|
| 109 |
+
"eval_loss": 0.30665355920791626,
|
| 110 |
+
"eval_runtime": 10.9181,
|
| 111 |
+
"eval_samples_per_second": 915.912,
|
| 112 |
+
"eval_steps_per_second": 1.191,
|
| 113 |
+
"step": 40
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 11.0,
|
| 117 |
+
"eval_loss": 0.29648929834365845,
|
| 118 |
+
"eval_runtime": 10.7354,
|
| 119 |
+
"eval_samples_per_second": 931.494,
|
| 120 |
+
"eval_steps_per_second": 1.211,
|
| 121 |
+
"step": 44
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 12.0,
|
| 125 |
+
"eval_loss": 0.26932698488235474,
|
| 126 |
+
"eval_runtime": 10.8379,
|
| 127 |
+
"eval_samples_per_second": 922.691,
|
| 128 |
+
"eval_steps_per_second": 1.199,
|
| 129 |
+
"step": 48
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 12.5,
|
| 133 |
+
"learning_rate": 4.375e-05,
|
| 134 |
+
"loss": 0.6394,
|
| 135 |
+
"step": 50
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 13.0,
|
| 139 |
+
"eval_loss": 0.271121084690094,
|
| 140 |
+
"eval_runtime": 10.8381,
|
| 141 |
+
"eval_samples_per_second": 922.67,
|
| 142 |
+
"eval_steps_per_second": 1.199,
|
| 143 |
+
"step": 52
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 14.0,
|
| 147 |
+
"eval_loss": 0.25609534978866577,
|
| 148 |
+
"eval_runtime": 10.7523,
|
| 149 |
+
"eval_samples_per_second": 930.029,
|
| 150 |
+
"eval_steps_per_second": 1.209,
|
| 151 |
+
"step": 56
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 15.0,
|
| 155 |
+
"learning_rate": 4.25e-05,
|
| 156 |
+
"loss": 0.6047,
|
| 157 |
+
"step": 60
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 15.0,
|
| 161 |
+
"eval_loss": 0.2453787624835968,
|
| 162 |
+
"eval_runtime": 10.9268,
|
| 163 |
+
"eval_samples_per_second": 915.184,
|
| 164 |
+
"eval_steps_per_second": 1.19,
|
| 165 |
+
"step": 60
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 16.0,
|
| 169 |
+
"eval_loss": 0.23679418861865997,
|
| 170 |
+
"eval_runtime": 10.7591,
|
| 171 |
+
"eval_samples_per_second": 929.449,
|
| 172 |
+
"eval_steps_per_second": 1.208,
|
| 173 |
+
"step": 64
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 17.0,
|
| 177 |
+
"eval_loss": 0.22503486275672913,
|
| 178 |
+
"eval_runtime": 10.8371,
|
| 179 |
+
"eval_samples_per_second": 922.76,
|
| 180 |
+
"eval_steps_per_second": 1.2,
|
| 181 |
+
"step": 68
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 17.5,
|
| 185 |
+
"learning_rate": 4.125e-05,
|
| 186 |
+
"loss": 0.565,
|
| 187 |
+
"step": 70
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 18.0,
|
| 191 |
+
"eval_loss": 0.21100571751594543,
|
| 192 |
+
"eval_runtime": 10.8584,
|
| 193 |
+
"eval_samples_per_second": 920.947,
|
| 194 |
+
"eval_steps_per_second": 1.197,
|
| 195 |
+
"step": 72
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 19.0,
|
| 199 |
+
"eval_loss": 0.21086934208869934,
|
| 200 |
+
"eval_runtime": 10.746,
|
| 201 |
+
"eval_samples_per_second": 930.581,
|
| 202 |
+
"eval_steps_per_second": 1.21,
|
| 203 |
+
"step": 76
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 20.0,
|
| 207 |
+
"learning_rate": 4e-05,
|
| 208 |
+
"loss": 0.5368,
|
| 209 |
+
"step": 80
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 20.0,
|
| 213 |
+
"eval_loss": 0.1950305849313736,
|
| 214 |
+
"eval_runtime": 10.7833,
|
| 215 |
+
"eval_samples_per_second": 927.356,
|
| 216 |
+
"eval_steps_per_second": 1.206,
|
| 217 |
+
"step": 80
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 21.0,
|
| 221 |
+
"eval_loss": 0.19742541015148163,
|
| 222 |
+
"eval_runtime": 10.7496,
|
| 223 |
+
"eval_samples_per_second": 930.268,
|
| 224 |
+
"eval_steps_per_second": 1.209,
|
| 225 |
+
"step": 84
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 22.0,
|
| 229 |
+
"eval_loss": 0.18190620839595795,
|
| 230 |
+
"eval_runtime": 11.0063,
|
| 231 |
+
"eval_samples_per_second": 908.569,
|
| 232 |
+
"eval_steps_per_second": 1.181,
|
| 233 |
+
"step": 88
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 22.5,
|
| 237 |
+
"learning_rate": 3.875e-05,
|
| 238 |
+
"loss": 0.518,
|
| 239 |
+
"step": 90
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 23.0,
|
| 243 |
+
"eval_loss": 0.1795072704553604,
|
| 244 |
+
"eval_runtime": 10.855,
|
| 245 |
+
"eval_samples_per_second": 921.235,
|
| 246 |
+
"eval_steps_per_second": 1.198,
|
| 247 |
+
"step": 92
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 24.0,
|
| 251 |
+
"eval_loss": 0.16476453840732574,
|
| 252 |
+
"eval_runtime": 10.7846,
|
| 253 |
+
"eval_samples_per_second": 927.252,
|
| 254 |
+
"eval_steps_per_second": 1.205,
|
| 255 |
+
"step": 96
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 25.0,
|
| 259 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 260 |
+
"loss": 0.4862,
|
| 261 |
+
"step": 100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 25.0,
|
| 265 |
+
"eval_loss": 0.16748683154582977,
|
| 266 |
+
"eval_runtime": 10.9227,
|
| 267 |
+
"eval_samples_per_second": 915.525,
|
| 268 |
+
"eval_steps_per_second": 1.19,
|
| 269 |
+
"step": 100
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 26.0,
|
| 273 |
+
"eval_loss": 0.15504491329193115,
|
| 274 |
+
"eval_runtime": 10.7793,
|
| 275 |
+
"eval_samples_per_second": 927.702,
|
| 276 |
+
"eval_steps_per_second": 1.206,
|
| 277 |
+
"step": 104
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 27.0,
|
| 281 |
+
"eval_loss": 0.15300293266773224,
|
| 282 |
+
"eval_runtime": 10.8547,
|
| 283 |
+
"eval_samples_per_second": 921.263,
|
| 284 |
+
"eval_steps_per_second": 1.198,
|
| 285 |
+
"step": 108
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 27.5,
|
| 289 |
+
"learning_rate": 3.625e-05,
|
| 290 |
+
"loss": 0.4628,
|
| 291 |
+
"step": 110
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 28.0,
|
| 295 |
+
"eval_loss": 0.14466118812561035,
|
| 296 |
+
"eval_runtime": 10.8549,
|
| 297 |
+
"eval_samples_per_second": 921.246,
|
| 298 |
+
"eval_steps_per_second": 1.198,
|
| 299 |
+
"step": 112
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 29.0,
|
| 303 |
+
"eval_loss": 0.1442325860261917,
|
| 304 |
+
"eval_runtime": 10.764,
|
| 305 |
+
"eval_samples_per_second": 929.023,
|
| 306 |
+
"eval_steps_per_second": 1.208,
|
| 307 |
+
"step": 116
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 30.0,
|
| 311 |
+
"learning_rate": 3.5e-05,
|
| 312 |
+
"loss": 0.4408,
|
| 313 |
+
"step": 120
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 30.0,
|
| 317 |
+
"eval_loss": 0.13103845715522766,
|
| 318 |
+
"eval_runtime": 10.9404,
|
| 319 |
+
"eval_samples_per_second": 914.043,
|
| 320 |
+
"eval_steps_per_second": 1.188,
|
| 321 |
+
"step": 120
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 31.0,
|
| 325 |
+
"eval_loss": 0.13363589346408844,
|
| 326 |
+
"eval_runtime": 10.7472,
|
| 327 |
+
"eval_samples_per_second": 930.475,
|
| 328 |
+
"eval_steps_per_second": 1.21,
|
| 329 |
+
"step": 124
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 32.0,
|
| 333 |
+
"eval_loss": 0.12347704917192459,
|
| 334 |
+
"eval_runtime": 10.8696,
|
| 335 |
+
"eval_samples_per_second": 920.0,
|
| 336 |
+
"eval_steps_per_second": 1.196,
|
| 337 |
+
"step": 128
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 32.5,
|
| 341 |
+
"learning_rate": 3.375000000000001e-05,
|
| 342 |
+
"loss": 0.4192,
|
| 343 |
+
"step": 130
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 33.0,
|
| 347 |
+
"eval_loss": 0.1190723404288292,
|
| 348 |
+
"eval_runtime": 10.8564,
|
| 349 |
+
"eval_samples_per_second": 921.113,
|
| 350 |
+
"eval_steps_per_second": 1.197,
|
| 351 |
+
"step": 132
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 34.0,
|
| 355 |
+
"eval_loss": 0.11926523596048355,
|
| 356 |
+
"eval_runtime": 10.7486,
|
| 357 |
+
"eval_samples_per_second": 930.351,
|
| 358 |
+
"eval_steps_per_second": 1.209,
|
| 359 |
+
"step": 136
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 35.0,
|
| 363 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 364 |
+
"loss": 0.4133,
|
| 365 |
+
"step": 140
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 35.0,
|
| 369 |
+
"eval_loss": 0.1123439222574234,
|
| 370 |
+
"eval_runtime": 10.9392,
|
| 371 |
+
"eval_samples_per_second": 914.14,
|
| 372 |
+
"eval_steps_per_second": 1.188,
|
| 373 |
+
"step": 140
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 36.0,
|
| 377 |
+
"eval_loss": 0.11556507647037506,
|
| 378 |
+
"eval_runtime": 10.7494,
|
| 379 |
+
"eval_samples_per_second": 930.287,
|
| 380 |
+
"eval_steps_per_second": 1.209,
|
| 381 |
+
"step": 144
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 37.0,
|
| 385 |
+
"eval_loss": 0.10512395203113556,
|
| 386 |
+
"eval_runtime": 10.8606,
|
| 387 |
+
"eval_samples_per_second": 920.755,
|
| 388 |
+
"eval_steps_per_second": 1.197,
|
| 389 |
+
"step": 148
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 37.5,
|
| 393 |
+
"learning_rate": 3.125e-05,
|
| 394 |
+
"loss": 0.3922,
|
| 395 |
+
"step": 150
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 38.0,
|
| 399 |
+
"eval_loss": 0.09992647171020508,
|
| 400 |
+
"eval_runtime": 10.8473,
|
| 401 |
+
"eval_samples_per_second": 921.889,
|
| 402 |
+
"eval_steps_per_second": 1.198,
|
| 403 |
+
"step": 152
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 39.0,
|
| 407 |
+
"eval_loss": 0.09912022948265076,
|
| 408 |
+
"eval_runtime": 10.751,
|
| 409 |
+
"eval_samples_per_second": 930.148,
|
| 410 |
+
"eval_steps_per_second": 1.209,
|
| 411 |
+
"step": 156
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 40.0,
|
| 415 |
+
"learning_rate": 3e-05,
|
| 416 |
+
"loss": 0.3778,
|
| 417 |
+
"step": 160
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 40.0,
|
| 421 |
+
"eval_loss": 0.09952548891305923,
|
| 422 |
+
"eval_runtime": 10.9239,
|
| 423 |
+
"eval_samples_per_second": 915.427,
|
| 424 |
+
"eval_steps_per_second": 1.19,
|
| 425 |
+
"step": 160
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 41.0,
|
| 429 |
+
"eval_loss": 0.09118303656578064,
|
| 430 |
+
"eval_runtime": 10.7525,
|
| 431 |
+
"eval_samples_per_second": 930.014,
|
| 432 |
+
"eval_steps_per_second": 1.209,
|
| 433 |
+
"step": 164
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 42.0,
|
| 437 |
+
"eval_loss": 0.09032606333494186,
|
| 438 |
+
"eval_runtime": 10.8423,
|
| 439 |
+
"eval_samples_per_second": 922.31,
|
| 440 |
+
"eval_steps_per_second": 1.199,
|
| 441 |
+
"step": 168
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 42.5,
|
| 445 |
+
"learning_rate": 2.8749999999999997e-05,
|
| 446 |
+
"loss": 0.3655,
|
| 447 |
+
"step": 170
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 43.0,
|
| 451 |
+
"eval_loss": 0.08409227430820465,
|
| 452 |
+
"eval_runtime": 10.8572,
|
| 453 |
+
"eval_samples_per_second": 921.048,
|
| 454 |
+
"eval_steps_per_second": 1.197,
|
| 455 |
+
"step": 172
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 44.0,
|
| 459 |
+
"eval_loss": 0.0789598897099495,
|
| 460 |
+
"eval_runtime": 10.7437,
|
| 461 |
+
"eval_samples_per_second": 930.776,
|
| 462 |
+
"eval_steps_per_second": 1.21,
|
| 463 |
+
"step": 176
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 45.0,
|
| 467 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 468 |
+
"loss": 0.3526,
|
| 469 |
+
"step": 180
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 45.0,
|
| 473 |
+
"eval_loss": 0.08267370611429214,
|
| 474 |
+
"eval_runtime": 10.9337,
|
| 475 |
+
"eval_samples_per_second": 914.6,
|
| 476 |
+
"eval_steps_per_second": 1.189,
|
| 477 |
+
"step": 180
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 46.0,
|
| 481 |
+
"eval_loss": 0.07559242099523544,
|
| 482 |
+
"eval_runtime": 10.7359,
|
| 483 |
+
"eval_samples_per_second": 931.456,
|
| 484 |
+
"eval_steps_per_second": 1.211,
|
| 485 |
+
"step": 184
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 47.0,
|
| 489 |
+
"eval_loss": 0.07468590885400772,
|
| 490 |
+
"eval_runtime": 10.8561,
|
| 491 |
+
"eval_samples_per_second": 921.142,
|
| 492 |
+
"eval_steps_per_second": 1.197,
|
| 493 |
+
"step": 188
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 47.5,
|
| 497 |
+
"learning_rate": 2.625e-05,
|
| 498 |
+
"loss": 0.3378,
|
| 499 |
+
"step": 190
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 48.0,
|
| 503 |
+
"eval_loss": 0.0737282931804657,
|
| 504 |
+
"eval_runtime": 10.8372,
|
| 505 |
+
"eval_samples_per_second": 922.747,
|
| 506 |
+
"eval_steps_per_second": 1.2,
|
| 507 |
+
"step": 192
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 49.0,
|
| 511 |
+
"eval_loss": 0.07465548813343048,
|
| 512 |
+
"eval_runtime": 10.7608,
|
| 513 |
+
"eval_samples_per_second": 929.3,
|
| 514 |
+
"eval_steps_per_second": 1.208,
|
| 515 |
+
"step": 196
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 50.0,
|
| 519 |
+
"learning_rate": 2.5e-05,
|
| 520 |
+
"loss": 0.3308,
|
| 521 |
+
"step": 200
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 50.0,
|
| 525 |
+
"eval_loss": 0.07294411957263947,
|
| 526 |
+
"eval_runtime": 10.9347,
|
| 527 |
+
"eval_samples_per_second": 914.518,
|
| 528 |
+
"eval_steps_per_second": 1.189,
|
| 529 |
+
"step": 200
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 51.0,
|
| 533 |
+
"eval_loss": 0.0665128082036972,
|
| 534 |
+
"eval_runtime": 10.7481,
|
| 535 |
+
"eval_samples_per_second": 930.401,
|
| 536 |
+
"eval_steps_per_second": 1.21,
|
| 537 |
+
"step": 204
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 52.0,
|
| 541 |
+
"eval_loss": 0.06627500057220459,
|
| 542 |
+
"eval_runtime": 10.8409,
|
| 543 |
+
"eval_samples_per_second": 922.432,
|
| 544 |
+
"eval_steps_per_second": 1.199,
|
| 545 |
+
"step": 208
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 52.5,
|
| 549 |
+
"learning_rate": 2.375e-05,
|
| 550 |
+
"loss": 0.321,
|
| 551 |
+
"step": 210
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 53.0,
|
| 555 |
+
"eval_loss": 0.06422976404428482,
|
| 556 |
+
"eval_runtime": 10.8561,
|
| 557 |
+
"eval_samples_per_second": 921.142,
|
| 558 |
+
"eval_steps_per_second": 1.197,
|
| 559 |
+
"step": 212
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 54.0,
|
| 563 |
+
"eval_loss": 0.06401015818119049,
|
| 564 |
+
"eval_runtime": 10.7568,
|
| 565 |
+
"eval_samples_per_second": 929.646,
|
| 566 |
+
"eval_steps_per_second": 1.209,
|
| 567 |
+
"step": 216
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 55.0,
|
| 571 |
+
"learning_rate": 2.25e-05,
|
| 572 |
+
"loss": 0.3084,
|
| 573 |
+
"step": 220
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 55.0,
|
| 577 |
+
"eval_loss": 0.06319215148687363,
|
| 578 |
+
"eval_runtime": 10.9357,
|
| 579 |
+
"eval_samples_per_second": 914.439,
|
| 580 |
+
"eval_steps_per_second": 1.189,
|
| 581 |
+
"step": 220
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 56.0,
|
| 585 |
+
"eval_loss": 0.059920959174633026,
|
| 586 |
+
"eval_runtime": 10.7511,
|
| 587 |
+
"eval_samples_per_second": 930.141,
|
| 588 |
+
"eval_steps_per_second": 1.209,
|
| 589 |
+
"step": 224
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 57.0,
|
| 593 |
+
"eval_loss": 0.057977043092250824,
|
| 594 |
+
"eval_runtime": 10.8555,
|
| 595 |
+
"eval_samples_per_second": 921.188,
|
| 596 |
+
"eval_steps_per_second": 1.198,
|
| 597 |
+
"step": 228
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 57.5,
|
| 601 |
+
"learning_rate": 2.125e-05,
|
| 602 |
+
"loss": 0.2967,
|
| 603 |
+
"step": 230
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 58.0,
|
| 607 |
+
"eval_loss": 0.05669580027461052,
|
| 608 |
+
"eval_runtime": 10.8434,
|
| 609 |
+
"eval_samples_per_second": 922.219,
|
| 610 |
+
"eval_steps_per_second": 1.199,
|
| 611 |
+
"step": 232
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 59.0,
|
| 615 |
+
"eval_loss": 0.0525004044175148,
|
| 616 |
+
"eval_runtime": 10.7506,
|
| 617 |
+
"eval_samples_per_second": 930.18,
|
| 618 |
+
"eval_steps_per_second": 1.209,
|
| 619 |
+
"step": 236
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 60.0,
|
| 623 |
+
"learning_rate": 2e-05,
|
| 624 |
+
"loss": 0.2928,
|
| 625 |
+
"step": 240
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 60.0,
|
| 629 |
+
"eval_loss": 0.05224265158176422,
|
| 630 |
+
"eval_runtime": 10.9382,
|
| 631 |
+
"eval_samples_per_second": 914.231,
|
| 632 |
+
"eval_steps_per_second": 1.188,
|
| 633 |
+
"step": 240
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 61.0,
|
| 637 |
+
"eval_loss": 0.05358195677399635,
|
| 638 |
+
"eval_runtime": 10.7598,
|
| 639 |
+
"eval_samples_per_second": 929.387,
|
| 640 |
+
"eval_steps_per_second": 1.208,
|
| 641 |
+
"step": 244
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 62.0,
|
| 645 |
+
"eval_loss": 0.052435729652643204,
|
| 646 |
+
"eval_runtime": 10.8537,
|
| 647 |
+
"eval_samples_per_second": 921.341,
|
| 648 |
+
"eval_steps_per_second": 1.198,
|
| 649 |
+
"step": 248
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 62.5,
|
| 653 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 654 |
+
"loss": 0.2929,
|
| 655 |
+
"step": 250
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 63.0,
|
| 659 |
+
"eval_loss": 0.056764379143714905,
|
| 660 |
+
"eval_runtime": 10.8657,
|
| 661 |
+
"eval_samples_per_second": 920.329,
|
| 662 |
+
"eval_steps_per_second": 1.196,
|
| 663 |
+
"step": 252
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 64.0,
|
| 667 |
+
"eval_loss": 0.0530422069132328,
|
| 668 |
+
"eval_runtime": 10.7635,
|
| 669 |
+
"eval_samples_per_second": 929.065,
|
| 670 |
+
"eval_steps_per_second": 1.208,
|
| 671 |
+
"step": 256
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 65.0,
|
| 675 |
+
"learning_rate": 1.75e-05,
|
| 676 |
+
"loss": 0.283,
|
| 677 |
+
"step": 260
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 65.0,
|
| 681 |
+
"eval_loss": 0.04763900488615036,
|
| 682 |
+
"eval_runtime": 10.9405,
|
| 683 |
+
"eval_samples_per_second": 914.038,
|
| 684 |
+
"eval_steps_per_second": 1.188,
|
| 685 |
+
"step": 260
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 66.0,
|
| 689 |
+
"eval_loss": 0.04787232354283333,
|
| 690 |
+
"eval_runtime": 10.7497,
|
| 691 |
+
"eval_samples_per_second": 930.255,
|
| 692 |
+
"eval_steps_per_second": 1.209,
|
| 693 |
+
"step": 264
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 67.0,
|
| 697 |
+
"eval_loss": 0.05069798231124878,
|
| 698 |
+
"eval_runtime": 10.8615,
|
| 699 |
+
"eval_samples_per_second": 920.685,
|
| 700 |
+
"eval_steps_per_second": 1.197,
|
| 701 |
+
"step": 268
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 67.5,
|
| 705 |
+
"learning_rate": 1.6250000000000002e-05,
|
| 706 |
+
"loss": 0.2766,
|
| 707 |
+
"step": 270
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 68.0,
|
| 711 |
+
"eval_loss": 0.04605843871831894,
|
| 712 |
+
"eval_runtime": 10.8475,
|
| 713 |
+
"eval_samples_per_second": 921.871,
|
| 714 |
+
"eval_steps_per_second": 1.198,
|
| 715 |
+
"step": 272
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 69.0,
|
| 719 |
+
"eval_loss": 0.04439115151762962,
|
| 720 |
+
"eval_runtime": 10.7586,
|
| 721 |
+
"eval_samples_per_second": 929.488,
|
| 722 |
+
"eval_steps_per_second": 1.208,
|
| 723 |
+
"step": 276
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 70.0,
|
| 727 |
+
"learning_rate": 1.5e-05,
|
| 728 |
+
"loss": 0.2677,
|
| 729 |
+
"step": 280
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 70.0,
|
| 733 |
+
"eval_loss": 0.0455540269613266,
|
| 734 |
+
"eval_runtime": 10.9449,
|
| 735 |
+
"eval_samples_per_second": 913.667,
|
| 736 |
+
"eval_steps_per_second": 1.188,
|
| 737 |
+
"step": 280
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 71.0,
|
| 741 |
+
"eval_loss": 0.04371872544288635,
|
| 742 |
+
"eval_runtime": 10.758,
|
| 743 |
+
"eval_samples_per_second": 929.543,
|
| 744 |
+
"eval_steps_per_second": 1.208,
|
| 745 |
+
"step": 284
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 72.0,
|
| 749 |
+
"eval_loss": 0.04281056672334671,
|
| 750 |
+
"eval_runtime": 10.8458,
|
| 751 |
+
"eval_samples_per_second": 922.019,
|
| 752 |
+
"eval_steps_per_second": 1.199,
|
| 753 |
+
"step": 288
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 72.5,
|
| 757 |
+
"learning_rate": 1.3750000000000002e-05,
|
| 758 |
+
"loss": 0.2614,
|
| 759 |
+
"step": 290
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 73.0,
|
| 763 |
+
"eval_loss": 0.04188177362084389,
|
| 764 |
+
"eval_runtime": 10.8487,
|
| 765 |
+
"eval_samples_per_second": 921.77,
|
| 766 |
+
"eval_steps_per_second": 1.198,
|
| 767 |
+
"step": 292
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 74.0,
|
| 771 |
+
"eval_loss": 0.04140578955411911,
|
| 772 |
+
"eval_runtime": 10.7507,
|
| 773 |
+
"eval_samples_per_second": 930.172,
|
| 774 |
+
"eval_steps_per_second": 1.209,
|
| 775 |
+
"step": 296
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 75.0,
|
| 779 |
+
"learning_rate": 1.25e-05,
|
| 780 |
+
"loss": 0.2595,
|
| 781 |
+
"step": 300
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 75.0,
|
| 785 |
+
"eval_loss": 0.04175864905118942,
|
| 786 |
+
"eval_runtime": 10.9254,
|
| 787 |
+
"eval_samples_per_second": 915.297,
|
| 788 |
+
"eval_steps_per_second": 1.19,
|
| 789 |
+
"step": 300
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 76.0,
|
| 793 |
+
"eval_loss": 0.04123968258500099,
|
| 794 |
+
"eval_runtime": 10.7366,
|
| 795 |
+
"eval_samples_per_second": 931.392,
|
| 796 |
+
"eval_steps_per_second": 1.211,
|
| 797 |
+
"step": 304
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 77.0,
|
| 801 |
+
"eval_loss": 0.03961934149265289,
|
| 802 |
+
"eval_runtime": 10.8404,
|
| 803 |
+
"eval_samples_per_second": 922.477,
|
| 804 |
+
"eval_steps_per_second": 1.199,
|
| 805 |
+
"step": 308
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 77.5,
|
| 809 |
+
"learning_rate": 1.125e-05,
|
| 810 |
+
"loss": 0.2582,
|
| 811 |
+
"step": 310
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 78.0,
|
| 815 |
+
"eval_loss": 0.03820143640041351,
|
| 816 |
+
"eval_runtime": 10.8282,
|
| 817 |
+
"eval_samples_per_second": 923.515,
|
| 818 |
+
"eval_steps_per_second": 1.201,
|
| 819 |
+
"step": 312
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 79.0,
|
| 823 |
+
"eval_loss": 0.038101743906736374,
|
| 824 |
+
"eval_runtime": 10.7523,
|
| 825 |
+
"eval_samples_per_second": 930.033,
|
| 826 |
+
"eval_steps_per_second": 1.209,
|
| 827 |
+
"step": 316
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 80.0,
|
| 831 |
+
"learning_rate": 1e-05,
|
| 832 |
+
"loss": 0.2511,
|
| 833 |
+
"step": 320
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 80.0,
|
| 837 |
+
"eval_loss": 0.03866468369960785,
|
| 838 |
+
"eval_runtime": 10.9151,
|
| 839 |
+
"eval_samples_per_second": 916.163,
|
| 840 |
+
"eval_steps_per_second": 1.191,
|
| 841 |
+
"step": 320
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 81.0,
|
| 845 |
+
"eval_loss": 0.0387905091047287,
|
| 846 |
+
"eval_runtime": 10.7459,
|
| 847 |
+
"eval_samples_per_second": 930.586,
|
| 848 |
+
"eval_steps_per_second": 1.21,
|
| 849 |
+
"step": 324
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 82.0,
|
| 853 |
+
"eval_loss": 0.03723302111029625,
|
| 854 |
+
"eval_runtime": 10.8332,
|
| 855 |
+
"eval_samples_per_second": 923.092,
|
| 856 |
+
"eval_steps_per_second": 1.2,
|
| 857 |
+
"step": 328
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 82.5,
|
| 861 |
+
"learning_rate": 8.75e-06,
|
| 862 |
+
"loss": 0.2481,
|
| 863 |
+
"step": 330
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 83.0,
|
| 867 |
+
"eval_loss": 0.03600754216313362,
|
| 868 |
+
"eval_runtime": 10.8588,
|
| 869 |
+
"eval_samples_per_second": 920.91,
|
| 870 |
+
"eval_steps_per_second": 1.197,
|
| 871 |
+
"step": 332
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 84.0,
|
| 875 |
+
"eval_loss": 0.036581408232450485,
|
| 876 |
+
"eval_runtime": 10.7405,
|
| 877 |
+
"eval_samples_per_second": 931.052,
|
| 878 |
+
"eval_steps_per_second": 1.21,
|
| 879 |
+
"step": 336
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 85.0,
|
| 883 |
+
"learning_rate": 7.5e-06,
|
| 884 |
+
"loss": 0.2474,
|
| 885 |
+
"step": 340
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 85.0,
|
| 889 |
+
"eval_loss": 0.03646053001284599,
|
| 890 |
+
"eval_runtime": 10.9336,
|
| 891 |
+
"eval_samples_per_second": 914.608,
|
| 892 |
+
"eval_steps_per_second": 1.189,
|
| 893 |
+
"step": 340
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 86.0,
|
| 897 |
+
"eval_loss": 0.03565111756324768,
|
| 898 |
+
"eval_runtime": 10.7346,
|
| 899 |
+
"eval_samples_per_second": 931.569,
|
| 900 |
+
"eval_steps_per_second": 1.211,
|
| 901 |
+
"step": 344
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 87.0,
|
| 905 |
+
"eval_loss": 0.035478148609399796,
|
| 906 |
+
"eval_runtime": 10.8414,
|
| 907 |
+
"eval_samples_per_second": 922.386,
|
| 908 |
+
"eval_steps_per_second": 1.199,
|
| 909 |
+
"step": 348
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 87.5,
|
| 913 |
+
"learning_rate": 6.25e-06,
|
| 914 |
+
"loss": 0.2537,
|
| 915 |
+
"step": 350
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 88.0,
|
| 919 |
+
"eval_loss": 0.03596709668636322,
|
| 920 |
+
"eval_runtime": 10.8347,
|
| 921 |
+
"eval_samples_per_second": 922.957,
|
| 922 |
+
"eval_steps_per_second": 1.2,
|
| 923 |
+
"step": 352
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 89.0,
|
| 927 |
+
"eval_loss": 0.03587077185511589,
|
| 928 |
+
"eval_runtime": 10.7439,
|
| 929 |
+
"eval_samples_per_second": 930.763,
|
| 930 |
+
"eval_steps_per_second": 1.21,
|
| 931 |
+
"step": 356
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 90.0,
|
| 935 |
+
"learning_rate": 5e-06,
|
| 936 |
+
"loss": 0.2438,
|
| 937 |
+
"step": 360
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 90.0,
|
| 941 |
+
"eval_loss": 0.03546379879117012,
|
| 942 |
+
"eval_runtime": 10.9027,
|
| 943 |
+
"eval_samples_per_second": 917.201,
|
| 944 |
+
"eval_steps_per_second": 1.192,
|
| 945 |
+
"step": 360
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 91.0,
|
| 949 |
+
"eval_loss": 0.03530960530042648,
|
| 950 |
+
"eval_runtime": 10.7401,
|
| 951 |
+
"eval_samples_per_second": 931.093,
|
| 952 |
+
"eval_steps_per_second": 1.21,
|
| 953 |
+
"step": 364
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 92.0,
|
| 957 |
+
"eval_loss": 0.034898195415735245,
|
| 958 |
+
"eval_runtime": 10.838,
|
| 959 |
+
"eval_samples_per_second": 922.682,
|
| 960 |
+
"eval_steps_per_second": 1.199,
|
| 961 |
+
"step": 368
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 92.5,
|
| 965 |
+
"learning_rate": 3.75e-06,
|
| 966 |
+
"loss": 0.2461,
|
| 967 |
+
"step": 370
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 93.0,
|
| 971 |
+
"eval_loss": 0.03429694473743439,
|
| 972 |
+
"eval_runtime": 10.8462,
|
| 973 |
+
"eval_samples_per_second": 921.982,
|
| 974 |
+
"eval_steps_per_second": 1.199,
|
| 975 |
+
"step": 372
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 94.0,
|
| 979 |
+
"eval_loss": 0.03415210172533989,
|
| 980 |
+
"eval_runtime": 10.73,
|
| 981 |
+
"eval_samples_per_second": 931.966,
|
| 982 |
+
"eval_steps_per_second": 1.212,
|
| 983 |
+
"step": 376
|
| 984 |
+
}
|
| 985 |
+
],
|
| 986 |
+
"logging_steps": 10,
|
| 987 |
+
"max_steps": 400,
|
| 988 |
+
"num_train_epochs": 100,
|
| 989 |
+
"save_steps": 500,
|
| 990 |
+
"total_flos": 8096480649216000.0,
|
| 991 |
+
"trial_name": null,
|
| 992 |
+
"trial_params": null
|
| 993 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd85a2f86c85bdb72299d6c6ecd62d4ce028f05a1dbbb72a7b85059c09695c78
|
| 3 |
+
size 4792
|