--- license: apache-2.0 base_model: distilgpt2 tags: - generated_from_trainer model-index: - name: StatementOfWork_Generator_Omega_BS_512_2 results: [] --- # StatementOfWork_Generator_Omega_BS_512_2 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.8120 ## 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: 50 - eval_batch_size: 50 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 150 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 4 | 0.9839 | | No log | 2.0 | 8 | 0.9786 | | No log | 3.0 | 12 | 0.9767 | | No log | 4.0 | 16 | 0.9757 | | No log | 5.0 | 20 | 0.9716 | | No log | 6.0 | 24 | 0.9670 | | No log | 7.0 | 28 | 0.9663 | | No log | 8.0 | 32 | 0.9627 | | No log | 9.0 | 36 | 0.9571 | | No log | 10.0 | 40 | 0.9573 | | No log | 11.0 | 44 | 0.9520 | | No log | 12.0 | 48 | 0.9511 | | No log | 13.0 | 52 | 0.9486 | | No log | 14.0 | 56 | 0.9425 | | No log | 15.0 | 60 | 0.9440 | | No log | 16.0 | 64 | 0.9392 | | No log | 17.0 | 68 | 0.9357 | | No log | 18.0 | 72 | 0.9368 | | No log | 19.0 | 76 | 0.9333 | | No log | 20.0 | 80 | 0.9284 | | No log | 21.0 | 84 | 0.9260 | | No log | 22.0 | 88 | 0.9244 | | No log | 23.0 | 92 | 0.9228 | | No log | 24.0 | 96 | 0.9192 | | No log | 25.0 | 100 | 0.9163 | | No log | 26.0 | 104 | 0.9164 | | No log | 27.0 | 108 | 0.9135 | | No log | 28.0 | 112 | 0.9107 | | No log | 29.0 | 116 | 0.9105 | | No log | 30.0 | 120 | 0.9068 | | No log | 31.0 | 124 | 0.9050 | | No log | 32.0 | 128 | 0.9034 | | No log | 33.0 | 132 | 0.9012 | | No log | 34.0 | 136 | 0.8966 | | No log | 35.0 | 140 | 0.8968 | | No log | 36.0 | 144 | 0.8953 | | No log | 37.0 | 148 | 0.8920 | | No log | 38.0 | 152 | 0.8920 | | No log | 39.0 | 156 | 0.8912 | | No log | 40.0 | 160 | 0.8877 | | No log | 41.0 | 164 | 0.8871 | | No log | 42.0 | 168 | 0.8857 | | No log | 43.0 | 172 | 0.8800 | | No log | 44.0 | 176 | 0.8789 | | No log | 45.0 | 180 | 0.8831 | | No log | 46.0 | 184 | 0.8794 | | No log | 47.0 | 188 | 0.8757 | | No log | 48.0 | 192 | 0.8760 | | No log | 49.0 | 196 | 0.8730 | | No log | 50.0 | 200 | 0.8726 | | No log | 51.0 | 204 | 0.8719 | | No log | 52.0 | 208 | 0.8689 | | No log | 53.0 | 212 | 0.8691 | | No log | 54.0 | 216 | 0.8679 | | No log | 55.0 | 220 | 0.8633 | | No log | 56.0 | 224 | 0.8623 | | No log | 57.0 | 228 | 0.8624 | | No log | 58.0 | 232 | 0.8610 | | No log | 59.0 | 236 | 0.8601 | | No log | 60.0 | 240 | 0.8586 | | No log | 61.0 | 244 | 0.8583 | | No log | 62.0 | 248 | 0.8564 | | No log | 63.0 | 252 | 0.8552 | | No log | 64.0 | 256 | 0.8545 | | No log | 65.0 | 260 | 0.8526 | | No log | 66.0 | 264 | 0.8513 | | No log | 67.0 | 268 | 0.8508 | | No log | 68.0 | 272 | 0.8501 | | No log | 69.0 | 276 | 0.8484 | | No log | 70.0 | 280 | 0.8479 | | No log | 71.0 | 284 | 0.8465 | | No log | 72.0 | 288 | 0.8464 | | No log | 73.0 | 292 | 0.8452 | | No log | 74.0 | 296 | 0.8442 | | No log | 75.0 | 300 | 0.8443 | | No log | 76.0 | 304 | 0.8425 | | No log | 77.0 | 308 | 0.8410 | | No log | 78.0 | 312 | 0.8402 | | No log | 79.0 | 316 | 0.8394 | | No log | 80.0 | 320 | 0.8385 | | No log | 81.0 | 324 | 0.8380 | | No log | 82.0 | 328 | 0.8380 | | No log | 83.0 | 332 | 0.8369 | | No log | 84.0 | 336 | 0.8356 | | No log | 85.0 | 340 | 0.8351 | | No log | 86.0 | 344 | 0.8343 | | No log | 87.0 | 348 | 0.8326 | | No log | 88.0 | 352 | 0.8331 | | No log | 89.0 | 356 | 0.8328 | | No log | 90.0 | 360 | 0.8306 | | No log | 91.0 | 364 | 0.8310 | | No log | 92.0 | 368 | 0.8314 | | No log | 93.0 | 372 | 0.8295 | | No log | 94.0 | 376 | 0.8287 | | No log | 95.0 | 380 | 0.8286 | | No log | 96.0 | 384 | 0.8276 | | No log | 97.0 | 388 | 0.8270 | | No log | 98.0 | 392 | 0.8262 | | No log | 99.0 | 396 | 0.8251 | | No log | 100.0 | 400 | 0.8241 | | No log | 101.0 | 404 | 0.8231 | | No log | 102.0 | 408 | 0.8225 | | No log | 103.0 | 412 | 0.8235 | | No log | 104.0 | 416 | 0.8234 | | No log | 105.0 | 420 | 0.8225 | | No log | 106.0 | 424 | 0.8219 | | No log | 107.0 | 428 | 0.8209 | | No log | 108.0 | 432 | 0.8204 | | No log | 109.0 | 436 | 0.8195 | | No log | 110.0 | 440 | 0.8191 | | No log | 111.0 | 444 | 0.8191 | | No log | 112.0 | 448 | 0.8193 | | No log | 113.0 | 452 | 0.8197 | | No log | 114.0 | 456 | 0.8191 | | No log | 115.0 | 460 | 0.8179 | | No log | 116.0 | 464 | 0.8176 | | No log | 117.0 | 468 | 0.8173 | | No log | 118.0 | 472 | 0.8172 | | No log | 119.0 | 476 | 0.8174 | | No log | 120.0 | 480 | 0.8171 | | No log | 121.0 | 484 | 0.8169 | | No log | 122.0 | 488 | 0.8168 | | No log | 123.0 | 492 | 0.8162 | | No log | 124.0 | 496 | 0.8161 | | 0.3706 | 125.0 | 500 | 0.8160 | | 0.3706 | 126.0 | 504 | 0.8156 | | 0.3706 | 127.0 | 508 | 0.8145 | | 0.3706 | 128.0 | 512 | 0.8143 | | 0.3706 | 129.0 | 516 | 0.8143 | | 0.3706 | 130.0 | 520 | 0.8145 | | 0.3706 | 131.0 | 524 | 0.8147 | | 0.3706 | 132.0 | 528 | 0.8142 | | 0.3706 | 133.0 | 532 | 0.8136 | | 0.3706 | 134.0 | 536 | 0.8136 | | 0.3706 | 135.0 | 540 | 0.8138 | | 0.3706 | 136.0 | 544 | 0.8139 | | 0.3706 | 137.0 | 548 | 0.8140 | | 0.3706 | 138.0 | 552 | 0.8138 | | 0.3706 | 139.0 | 556 | 0.8134 | | 0.3706 | 140.0 | 560 | 0.8130 | | 0.3706 | 141.0 | 564 | 0.8128 | | 0.3706 | 142.0 | 568 | 0.8127 | | 0.3706 | 143.0 | 572 | 0.8126 | | 0.3706 | 144.0 | 576 | 0.8124 | | 0.3706 | 145.0 | 580 | 0.8123 | | 0.3706 | 146.0 | 584 | 0.8121 | | 0.3706 | 147.0 | 588 | 0.8120 | | 0.3706 | 148.0 | 592 | 0.8120 | | 0.3706 | 149.0 | 596 | 0.8120 | | 0.3706 | 150.0 | 600 | 0.8120 | ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2