--- license: apache-2.0 base_model: t5-small tags: - generated_from_trainer metrics: - bleu model-index: - name: my_awesome_opus_books_model results: [] --- # my_awesome_opus_books_model This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0129 - Bleu: 100.0 - Gen Len: 13.0 ## 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: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 200 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| | No log | 1.0 | 2 | 6.1851 | 0.0 | 12.0 | | No log | 2.0 | 4 | 6.0627 | 0.0 | 12.0 | | No log | 3.0 | 6 | 6.0627 | 0.0 | 12.0 | | No log | 4.0 | 8 | 5.8390 | 0.0 | 12.0 | | No log | 5.0 | 10 | 5.6596 | 0.0 | 12.0 | | No log | 6.0 | 12 | 5.4424 | 0.0 | 12.0 | | No log | 7.0 | 14 | 5.2815 | 0.0 | 12.0 | | No log | 8.0 | 16 | 5.1388 | 0.0 | 12.0 | | No log | 9.0 | 18 | 4.9987 | 0.0 | 12.0 | | No log | 10.0 | 20 | 4.8170 | 0.0 | 12.0 | | No log | 11.0 | 22 | 4.6353 | 0.0 | 12.0 | | No log | 12.0 | 24 | 4.4854 | 0.0 | 12.0 | | No log | 13.0 | 26 | 4.3039 | 0.0 | 12.0 | | No log | 14.0 | 28 | 4.1131 | 0.0 | 12.0 | | No log | 15.0 | 30 | 3.9509 | 0.0 | 12.0 | | No log | 16.0 | 32 | 3.7972 | 0.0 | 12.0 | | No log | 17.0 | 34 | 3.6481 | 5.5224 | 15.0 | | No log | 18.0 | 36 | 3.5111 | 5.5224 | 15.0 | | No log | 19.0 | 38 | 3.3768 | 5.5224 | 15.0 | | No log | 20.0 | 40 | 3.2433 | 5.5224 | 15.0 | | No log | 21.0 | 42 | 3.1126 | 5.5224 | 15.0 | | No log | 22.0 | 44 | 3.0030 | 5.5224 | 15.0 | | No log | 23.0 | 46 | 2.8871 | 5.5224 | 15.0 | | No log | 24.0 | 48 | 2.7639 | 5.5224 | 15.0 | | No log | 25.0 | 50 | 2.6478 | 5.5224 | 15.0 | | No log | 26.0 | 52 | 2.5302 | 5.5224 | 15.0 | | No log | 27.0 | 54 | 2.4243 | 5.5224 | 15.0 | | No log | 28.0 | 56 | 2.3275 | 5.5224 | 15.0 | | No log | 29.0 | 58 | 2.2400 | 5.5224 | 15.0 | | No log | 30.0 | 60 | 2.1625 | 5.5224 | 15.0 | | No log | 31.0 | 62 | 2.0853 | 5.5224 | 15.0 | | No log | 32.0 | 64 | 2.0021 | 5.5224 | 14.0 | | No log | 33.0 | 66 | 1.9144 | 5.5224 | 14.0 | | No log | 34.0 | 68 | 1.8281 | 5.5224 | 14.0 | | No log | 35.0 | 70 | 1.7493 | 5.5224 | 14.0 | | No log | 36.0 | 72 | 1.6698 | 5.5224 | 14.0 | | No log | 37.0 | 74 | 1.5966 | 5.5224 | 14.0 | | No log | 38.0 | 76 | 1.5277 | 5.5224 | 14.0 | | No log | 39.0 | 78 | 1.4569 | 5.5224 | 14.0 | | No log | 40.0 | 80 | 1.3870 | 5.5224 | 14.0 | | No log | 41.0 | 82 | 1.3169 | 6.5673 | 12.0 | | No log | 42.0 | 84 | 1.2468 | 6.5673 | 12.0 | | No log | 43.0 | 86 | 1.1823 | 6.5673 | 12.0 | | No log | 44.0 | 88 | 1.1232 | 6.5673 | 12.0 | | No log | 45.0 | 90 | 1.0667 | 6.5673 | 12.0 | | No log | 46.0 | 92 | 1.0127 | 6.5673 | 12.0 | | No log | 47.0 | 94 | 0.9854 | 6.5673 | 12.0 | | No log | 48.0 | 96 | 0.9303 | 6.5673 | 12.0 | | No log | 49.0 | 98 | 0.8819 | 0.0 | 19.0 | | No log | 50.0 | 100 | 0.8386 | 0.0 | 19.0 | | No log | 51.0 | 102 | 0.7923 | 0.0 | 19.0 | | No log | 52.0 | 104 | 0.7454 | 0.0 | 19.0 | | No log | 53.0 | 106 | 0.7012 | 100.0 | 13.0 | | No log | 54.0 | 108 | 0.6630 | 100.0 | 13.0 | | No log | 55.0 | 110 | 0.6287 | 100.0 | 13.0 | | No log | 56.0 | 112 | 0.5939 | 100.0 | 13.0 | | No log | 57.0 | 114 | 0.5608 | 100.0 | 13.0 | | No log | 58.0 | 116 | 0.5308 | 100.0 | 13.0 | | No log | 59.0 | 118 | 0.5019 | 100.0 | 13.0 | | No log | 60.0 | 120 | 0.4757 | 100.0 | 13.0 | | No log | 61.0 | 122 | 0.4503 | 100.0 | 13.0 | | No log | 62.0 | 124 | 0.4254 | 100.0 | 13.0 | | No log | 63.0 | 126 | 0.4007 | 100.0 | 13.0 | | No log | 64.0 | 128 | 0.3801 | 100.0 | 13.0 | | No log | 65.0 | 130 | 0.3607 | 100.0 | 13.0 | | No log | 66.0 | 132 | 0.3438 | 100.0 | 13.0 | | No log | 67.0 | 134 | 0.3276 | 100.0 | 13.0 | | No log | 68.0 | 136 | 0.3132 | 100.0 | 13.0 | | No log | 69.0 | 138 | 0.3000 | 100.0 | 13.0 | | No log | 70.0 | 140 | 0.2872 | 100.0 | 13.0 | | No log | 71.0 | 142 | 0.2747 | 100.0 | 13.0 | | No log | 72.0 | 144 | 0.2633 | 100.0 | 13.0 | | No log | 73.0 | 146 | 0.2537 | 100.0 | 13.0 | | No log | 74.0 | 148 | 0.2453 | 100.0 | 13.0 | | No log | 75.0 | 150 | 0.2377 | 100.0 | 13.0 | | No log | 76.0 | 152 | 0.2303 | 100.0 | 13.0 | | No log | 77.0 | 154 | 0.2222 | 100.0 | 13.0 | | No log | 78.0 | 156 | 0.2141 | 100.0 | 13.0 | | No log | 79.0 | 158 | 0.2066 | 100.0 | 13.0 | | No log | 80.0 | 160 | 0.1987 | 100.0 | 13.0 | | No log | 81.0 | 162 | 0.1919 | 100.0 | 13.0 | | No log | 82.0 | 164 | 0.1857 | 100.0 | 13.0 | | No log | 83.0 | 166 | 0.1798 | 100.0 | 13.0 | | No log | 84.0 | 168 | 0.1742 | 100.0 | 13.0 | | No log | 85.0 | 170 | 0.1687 | 100.0 | 13.0 | | No log | 86.0 | 172 | 0.1633 | 100.0 | 13.0 | | No log | 87.0 | 174 | 0.1577 | 100.0 | 13.0 | | No log | 88.0 | 176 | 0.1526 | 100.0 | 13.0 | | No log | 89.0 | 178 | 0.1477 | 100.0 | 13.0 | | No log | 90.0 | 180 | 0.1429 | 100.0 | 13.0 | | No log | 91.0 | 182 | 0.1380 | 100.0 | 13.0 | | No log | 92.0 | 184 | 0.1334 | 100.0 | 13.0 | | No log | 93.0 | 186 | 0.1281 | 100.0 | 13.0 | | No log | 94.0 | 188 | 0.1230 | 100.0 | 13.0 | | No log | 95.0 | 190 | 0.1180 | 100.0 | 13.0 | | No log | 96.0 | 192 | 0.1136 | 100.0 | 13.0 | | No log | 97.0 | 194 | 0.1093 | 100.0 | 13.0 | | No log | 98.0 | 196 | 0.1050 | 100.0 | 13.0 | | No log | 99.0 | 198 | 0.1013 | 100.0 | 13.0 | | No log | 100.0 | 200 | 0.0979 | 100.0 | 13.0 | | No log | 101.0 | 202 | 0.0953 | 100.0 | 13.0 | | No log | 102.0 | 204 | 0.0931 | 100.0 | 13.0 | | No log | 103.0 | 206 | 0.0907 | 100.0 | 13.0 | | No log | 104.0 | 208 | 0.0887 | 100.0 | 13.0 | | No log | 105.0 | 210 | 0.0866 | 100.0 | 13.0 | | No log | 106.0 | 212 | 0.0844 | 100.0 | 13.0 | | No log | 107.0 | 214 | 0.0822 | 100.0 | 13.0 | | No log | 108.0 | 216 | 0.0795 | 100.0 | 13.0 | | No log | 109.0 | 218 | 0.0768 | 100.0 | 13.0 | | No log | 110.0 | 220 | 0.0743 | 100.0 | 13.0 | | No log | 111.0 | 222 | 0.0715 | 100.0 | 13.0 | | No log | 112.0 | 224 | 0.0687 | 100.0 | 13.0 | | No log | 113.0 | 226 | 0.0663 | 100.0 | 13.0 | | No log | 114.0 | 228 | 0.0641 | 100.0 | 13.0 | | No log | 115.0 | 230 | 0.0620 | 100.0 | 13.0 | | No log | 116.0 | 232 | 0.0598 | 100.0 | 13.0 | | No log | 117.0 | 234 | 0.0577 | 100.0 | 13.0 | | No log | 118.0 | 236 | 0.0557 | 100.0 | 13.0 | | No log | 119.0 | 238 | 0.0541 | 100.0 | 13.0 | | No log | 120.0 | 240 | 0.0523 | 100.0 | 13.0 | | No log | 121.0 | 242 | 0.0506 | 100.0 | 13.0 | | No log | 122.0 | 244 | 0.0489 | 100.0 | 13.0 | | No log | 123.0 | 246 | 0.0472 | 100.0 | 13.0 | | No log | 124.0 | 248 | 0.0456 | 100.0 | 13.0 | | No log | 125.0 | 250 | 0.0441 | 100.0 | 13.0 | | No log | 126.0 | 252 | 0.0429 | 100.0 | 13.0 | | No log | 127.0 | 254 | 0.0416 | 100.0 | 13.0 | | No log | 128.0 | 256 | 0.0405 | 100.0 | 13.0 | | No log | 129.0 | 258 | 0.0393 | 100.0 | 13.0 | | No log | 130.0 | 260 | 0.0382 | 100.0 | 13.0 | | No log | 131.0 | 262 | 0.0370 | 100.0 | 13.0 | | No log | 132.0 | 264 | 0.0357 | 100.0 | 13.0 | | No log | 133.0 | 266 | 0.0345 | 100.0 | 13.0 | | No log | 134.0 | 268 | 0.0332 | 100.0 | 13.0 | | No log | 135.0 | 270 | 0.0322 | 100.0 | 13.0 | | No log | 136.0 | 272 | 0.0311 | 100.0 | 13.0 | | No log | 137.0 | 274 | 0.0303 | 100.0 | 13.0 | | No log | 138.0 | 276 | 0.0295 | 100.0 | 13.0 | | No log | 139.0 | 278 | 0.0288 | 100.0 | 13.0 | | No log | 140.0 | 280 | 0.0282 | 100.0 | 13.0 | | No log | 141.0 | 282 | 0.0275 | 100.0 | 13.0 | | No log | 142.0 | 284 | 0.0267 | 100.0 | 13.0 | | No log | 143.0 | 286 | 0.0261 | 100.0 | 13.0 | | No log | 144.0 | 288 | 0.0254 | 100.0 | 13.0 | | No log | 145.0 | 290 | 0.0249 | 100.0 | 13.0 | | No log | 146.0 | 292 | 0.0243 | 100.0 | 13.0 | | No log | 147.0 | 294 | 0.0238 | 100.0 | 13.0 | | No log | 148.0 | 296 | 0.0233 | 100.0 | 13.0 | | No log | 149.0 | 298 | 0.0229 | 100.0 | 13.0 | | No log | 150.0 | 300 | 0.0225 | 100.0 | 13.0 | | No log | 151.0 | 302 | 0.0222 | 100.0 | 13.0 | | No log | 152.0 | 304 | 0.0218 | 100.0 | 13.0 | | No log | 153.0 | 306 | 0.0215 | 100.0 | 13.0 | | No log | 154.0 | 308 | 0.0212 | 100.0 | 13.0 | | No log | 155.0 | 310 | 0.0210 | 100.0 | 13.0 | | No log | 156.0 | 312 | 0.0208 | 100.0 | 13.0 | | No log | 157.0 | 314 | 0.0205 | 100.0 | 13.0 | | No log | 158.0 | 316 | 0.0202 | 100.0 | 13.0 | | No log | 159.0 | 318 | 0.0200 | 100.0 | 13.0 | | No log | 160.0 | 320 | 0.0197 | 100.0 | 13.0 | | No log | 161.0 | 322 | 0.0194 | 100.0 | 13.0 | | No log | 162.0 | 324 | 0.0191 | 100.0 | 13.0 | | No log | 163.0 | 326 | 0.0188 | 100.0 | 13.0 | | No log | 164.0 | 328 | 0.0185 | 100.0 | 13.0 | | No log | 165.0 | 330 | 0.0181 | 100.0 | 13.0 | | No log | 166.0 | 332 | 0.0178 | 100.0 | 13.0 | | No log | 167.0 | 334 | 0.0175 | 100.0 | 13.0 | | No log | 168.0 | 336 | 0.0171 | 100.0 | 13.0 | | No log | 169.0 | 338 | 0.0168 | 100.0 | 13.0 | | No log | 170.0 | 340 | 0.0166 | 100.0 | 13.0 | | No log | 171.0 | 342 | 0.0162 | 100.0 | 13.0 | | No log | 172.0 | 344 | 0.0162 | 100.0 | 13.0 | | No log | 173.0 | 346 | 0.0159 | 100.0 | 13.0 | | No log | 174.0 | 348 | 0.0158 | 100.0 | 13.0 | | No log | 175.0 | 350 | 0.0156 | 100.0 | 13.0 | | No log | 176.0 | 352 | 0.0154 | 100.0 | 13.0 | | No log | 177.0 | 354 | 0.0152 | 100.0 | 13.0 | | No log | 178.0 | 356 | 0.0151 | 100.0 | 13.0 | | No log | 179.0 | 358 | 0.0149 | 100.0 | 13.0 | | No log | 180.0 | 360 | 0.0147 | 100.0 | 13.0 | | No log | 181.0 | 362 | 0.0146 | 100.0 | 13.0 | | No log | 182.0 | 364 | 0.0144 | 100.0 | 13.0 | | No log | 183.0 | 366 | 0.0144 | 100.0 | 13.0 | | No log | 184.0 | 368 | 0.0142 | 100.0 | 13.0 | | No log | 185.0 | 370 | 0.0141 | 100.0 | 13.0 | | No log | 186.0 | 372 | 0.0140 | 100.0 | 13.0 | | No log | 187.0 | 374 | 0.0139 | 100.0 | 13.0 | | No log | 188.0 | 376 | 0.0137 | 100.0 | 13.0 | | No log | 189.0 | 378 | 0.0136 | 100.0 | 13.0 | | No log | 190.0 | 380 | 0.0135 | 100.0 | 13.0 | | No log | 191.0 | 382 | 0.0134 | 100.0 | 13.0 | | No log | 192.0 | 384 | 0.0134 | 100.0 | 13.0 | | No log | 193.0 | 386 | 0.0133 | 100.0 | 13.0 | | No log | 194.0 | 388 | 0.0132 | 100.0 | 13.0 | | No log | 195.0 | 390 | 0.0132 | 100.0 | 13.0 | | No log | 196.0 | 392 | 0.0131 | 100.0 | 13.0 | | No log | 197.0 | 394 | 0.0131 | 100.0 | 13.0 | | No log | 198.0 | 396 | 0.0130 | 100.0 | 13.0 | | No log | 199.0 | 398 | 0.0130 | 100.0 | 13.0 | | No log | 200.0 | 400 | 0.0129 | 100.0 | 13.0 | ### Framework versions - Transformers 4.36.1 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0