|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: google/byt5-small |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: byt5_3k_4d |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# byt5_3k_4d |
|
|
|
|
|
This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0348 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 5e-05 |
|
|
- train_batch_size: 800 |
|
|
- eval_batch_size: 800 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 100 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| No log | 1.0 | 4 | 0.4702 | |
|
|
| No log | 2.0 | 8 | 0.4366 | |
|
|
| 0.8301 | 3.0 | 12 | 0.4202 | |
|
|
| 0.8301 | 4.0 | 16 | 0.3843 | |
|
|
| 0.7703 | 5.0 | 20 | 0.3898 | |
|
|
| 0.7703 | 6.0 | 24 | 0.3573 | |
|
|
| 0.7703 | 7.0 | 28 | 0.3422 | |
|
|
| 0.7169 | 8.0 | 32 | 0.3304 | |
|
|
| 0.7169 | 9.0 | 36 | 0.3049 | |
|
|
| 0.6727 | 10.0 | 40 | 0.3067 | |
|
|
| 0.6727 | 11.0 | 44 | 0.2965 | |
|
|
| 0.6727 | 12.0 | 48 | 0.2693 | |
|
|
| 0.6394 | 13.0 | 52 | 0.2711 | |
|
|
| 0.6394 | 14.0 | 56 | 0.2561 | |
|
|
| 0.6047 | 15.0 | 60 | 0.2454 | |
|
|
| 0.6047 | 16.0 | 64 | 0.2368 | |
|
|
| 0.6047 | 17.0 | 68 | 0.2250 | |
|
|
| 0.565 | 18.0 | 72 | 0.2110 | |
|
|
| 0.565 | 19.0 | 76 | 0.2109 | |
|
|
| 0.5368 | 20.0 | 80 | 0.1950 | |
|
|
| 0.5368 | 21.0 | 84 | 0.1974 | |
|
|
| 0.5368 | 22.0 | 88 | 0.1819 | |
|
|
| 0.518 | 23.0 | 92 | 0.1795 | |
|
|
| 0.518 | 24.0 | 96 | 0.1648 | |
|
|
| 0.4862 | 25.0 | 100 | 0.1675 | |
|
|
| 0.4862 | 26.0 | 104 | 0.1550 | |
|
|
| 0.4862 | 27.0 | 108 | 0.1530 | |
|
|
| 0.4628 | 28.0 | 112 | 0.1447 | |
|
|
| 0.4628 | 29.0 | 116 | 0.1442 | |
|
|
| 0.4408 | 30.0 | 120 | 0.1310 | |
|
|
| 0.4408 | 31.0 | 124 | 0.1336 | |
|
|
| 0.4408 | 32.0 | 128 | 0.1235 | |
|
|
| 0.4192 | 33.0 | 132 | 0.1191 | |
|
|
| 0.4192 | 34.0 | 136 | 0.1193 | |
|
|
| 0.4133 | 35.0 | 140 | 0.1123 | |
|
|
| 0.4133 | 36.0 | 144 | 0.1156 | |
|
|
| 0.4133 | 37.0 | 148 | 0.1051 | |
|
|
| 0.3922 | 38.0 | 152 | 0.0999 | |
|
|
| 0.3922 | 39.0 | 156 | 0.0991 | |
|
|
| 0.3778 | 40.0 | 160 | 0.0995 | |
|
|
| 0.3778 | 41.0 | 164 | 0.0912 | |
|
|
| 0.3778 | 42.0 | 168 | 0.0903 | |
|
|
| 0.3655 | 43.0 | 172 | 0.0841 | |
|
|
| 0.3655 | 44.0 | 176 | 0.0790 | |
|
|
| 0.3526 | 45.0 | 180 | 0.0827 | |
|
|
| 0.3526 | 46.0 | 184 | 0.0756 | |
|
|
| 0.3526 | 47.0 | 188 | 0.0747 | |
|
|
| 0.3378 | 48.0 | 192 | 0.0737 | |
|
|
| 0.3378 | 49.0 | 196 | 0.0747 | |
|
|
| 0.3308 | 50.0 | 200 | 0.0729 | |
|
|
| 0.3308 | 51.0 | 204 | 0.0665 | |
|
|
| 0.3308 | 52.0 | 208 | 0.0663 | |
|
|
| 0.321 | 53.0 | 212 | 0.0642 | |
|
|
| 0.321 | 54.0 | 216 | 0.0640 | |
|
|
| 0.3084 | 55.0 | 220 | 0.0632 | |
|
|
| 0.3084 | 56.0 | 224 | 0.0599 | |
|
|
| 0.3084 | 57.0 | 228 | 0.0580 | |
|
|
| 0.2967 | 58.0 | 232 | 0.0567 | |
|
|
| 0.2967 | 59.0 | 236 | 0.0525 | |
|
|
| 0.2928 | 60.0 | 240 | 0.0522 | |
|
|
| 0.2928 | 61.0 | 244 | 0.0536 | |
|
|
| 0.2928 | 62.0 | 248 | 0.0524 | |
|
|
| 0.2929 | 63.0 | 252 | 0.0568 | |
|
|
| 0.2929 | 64.0 | 256 | 0.0530 | |
|
|
| 0.283 | 65.0 | 260 | 0.0476 | |
|
|
| 0.283 | 66.0 | 264 | 0.0479 | |
|
|
| 0.283 | 67.0 | 268 | 0.0507 | |
|
|
| 0.2766 | 68.0 | 272 | 0.0461 | |
|
|
| 0.2766 | 69.0 | 276 | 0.0444 | |
|
|
| 0.2677 | 70.0 | 280 | 0.0456 | |
|
|
| 0.2677 | 71.0 | 284 | 0.0437 | |
|
|
| 0.2677 | 72.0 | 288 | 0.0428 | |
|
|
| 0.2614 | 73.0 | 292 | 0.0419 | |
|
|
| 0.2614 | 74.0 | 296 | 0.0414 | |
|
|
| 0.2595 | 75.0 | 300 | 0.0418 | |
|
|
| 0.2595 | 76.0 | 304 | 0.0412 | |
|
|
| 0.2595 | 77.0 | 308 | 0.0396 | |
|
|
| 0.2582 | 78.0 | 312 | 0.0382 | |
|
|
| 0.2582 | 79.0 | 316 | 0.0381 | |
|
|
| 0.2511 | 80.0 | 320 | 0.0387 | |
|
|
| 0.2511 | 81.0 | 324 | 0.0388 | |
|
|
| 0.2511 | 82.0 | 328 | 0.0372 | |
|
|
| 0.2481 | 83.0 | 332 | 0.0360 | |
|
|
| 0.2481 | 84.0 | 336 | 0.0366 | |
|
|
| 0.2474 | 85.0 | 340 | 0.0365 | |
|
|
| 0.2474 | 86.0 | 344 | 0.0357 | |
|
|
| 0.2474 | 87.0 | 348 | 0.0355 | |
|
|
| 0.2537 | 88.0 | 352 | 0.0360 | |
|
|
| 0.2537 | 89.0 | 356 | 0.0359 | |
|
|
| 0.2438 | 90.0 | 360 | 0.0355 | |
|
|
| 0.2438 | 91.0 | 364 | 0.0353 | |
|
|
| 0.2438 | 92.0 | 368 | 0.0349 | |
|
|
| 0.2461 | 93.0 | 372 | 0.0343 | |
|
|
| 0.2461 | 94.0 | 376 | 0.0342 | |
|
|
| 0.2395 | 95.0 | 380 | 0.0344 | |
|
|
| 0.2395 | 96.0 | 384 | 0.0347 | |
|
|
| 0.2395 | 97.0 | 388 | 0.0350 | |
|
|
| 0.2439 | 98.0 | 392 | 0.0349 | |
|
|
| 0.2439 | 99.0 | 396 | 0.0348 | |
|
|
| 0.2432 | 100.0 | 400 | 0.0348 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.35.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
