<!-- 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. -->
gpt-work-filter-auto-complete
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0939
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | 22 | 0.6395 |
No log | 2.0 | 44 | 0.6235 |
No log | 3.0 | 66 | 0.6035 |
No log | 4.0 | 88 | 0.5845 |
No log | 5.0 | 110 | 0.5645 |
No log | 6.0 | 132 | 0.5442 |
No log | 7.0 | 154 | 0.5346 |
No log | 8.0 | 176 | 0.5167 |
No log | 9.0 | 198 | 0.5009 |
No log | 10.0 | 220 | 0.4893 |
No log | 11.0 | 242 | 0.4676 |
No log | 12.0 | 264 | 0.4498 |
No log | 13.0 | 286 | 0.4382 |
No log | 14.0 | 308 | 0.4276 |
No log | 15.0 | 330 | 0.4132 |
No log | 16.0 | 352 | 0.4075 |
No log | 17.0 | 374 | 0.3952 |
No log | 18.0 | 396 | 0.3822 |
No log | 19.0 | 418 | 0.3677 |
No log | 20.0 | 440 | 0.3563 |
No log | 21.0 | 462 | 0.3495 |
No log | 22.0 | 484 | 0.3455 |
0.6366 | 23.0 | 506 | 0.3316 |
0.6366 | 24.0 | 528 | 0.3126 |
0.6366 | 25.0 | 550 | 0.3118 |
0.6366 | 26.0 | 572 | 0.3021 |
0.6366 | 27.0 | 594 | 0.2944 |
0.6366 | 28.0 | 616 | 0.2878 |
0.6366 | 29.0 | 638 | 0.2772 |
0.6366 | 30.0 | 660 | 0.2701 |
0.6366 | 31.0 | 682 | 0.2643 |
0.6366 | 32.0 | 704 | 0.2576 |
0.6366 | 33.0 | 726 | 0.2514 |
0.6366 | 34.0 | 748 | 0.2467 |
0.6366 | 35.0 | 770 | 0.2359 |
0.6366 | 36.0 | 792 | 0.2326 |
0.6366 | 37.0 | 814 | 0.2205 |
0.6366 | 38.0 | 836 | 0.2182 |
0.6366 | 39.0 | 858 | 0.2137 |
0.6366 | 40.0 | 880 | 0.2086 |
0.6366 | 41.0 | 902 | 0.2058 |
0.6366 | 42.0 | 924 | 0.1979 |
0.6366 | 43.0 | 946 | 0.1930 |
0.6366 | 44.0 | 968 | 0.1922 |
0.6366 | 45.0 | 990 | 0.1853 |
0.4122 | 46.0 | 1012 | 0.1800 |
0.4122 | 47.0 | 1034 | 0.1787 |
0.4122 | 48.0 | 1056 | 0.1738 |
0.4122 | 49.0 | 1078 | 0.1689 |
0.4122 | 50.0 | 1100 | 0.1670 |
0.4122 | 51.0 | 1122 | 0.1583 |
0.4122 | 52.0 | 1144 | 0.1560 |
0.4122 | 53.0 | 1166 | 0.1540 |
0.4122 | 54.0 | 1188 | 0.1507 |
0.4122 | 55.0 | 1210 | 0.1475 |
0.4122 | 56.0 | 1232 | 0.1452 |
0.4122 | 57.0 | 1254 | 0.1458 |
0.4122 | 58.0 | 1276 | 0.1425 |
0.4122 | 59.0 | 1298 | 0.1377 |
0.4122 | 60.0 | 1320 | 0.1338 |
0.4122 | 61.0 | 1342 | 0.1365 |
0.4122 | 62.0 | 1364 | 0.1278 |
0.4122 | 63.0 | 1386 | 0.1272 |
0.4122 | 64.0 | 1408 | 0.1253 |
0.4122 | 65.0 | 1430 | 0.1251 |
0.4122 | 66.0 | 1452 | 0.1217 |
0.4122 | 67.0 | 1474 | 0.1219 |
0.4122 | 68.0 | 1496 | 0.1177 |
0.3005 | 69.0 | 1518 | 0.1174 |
0.3005 | 70.0 | 1540 | 0.1155 |
0.3005 | 71.0 | 1562 | 0.1144 |
0.3005 | 72.0 | 1584 | 0.1127 |
0.3005 | 73.0 | 1606 | 0.1106 |
0.3005 | 74.0 | 1628 | 0.1098 |
0.3005 | 75.0 | 1650 | 0.1092 |
0.3005 | 76.0 | 1672 | 0.1067 |
0.3005 | 77.0 | 1694 | 0.1086 |
0.3005 | 78.0 | 1716 | 0.1042 |
0.3005 | 79.0 | 1738 | 0.1051 |
0.3005 | 80.0 | 1760 | 0.1038 |
0.3005 | 81.0 | 1782 | 0.1022 |
0.3005 | 82.0 | 1804 | 0.1015 |
0.3005 | 83.0 | 1826 | 0.1004 |
0.3005 | 84.0 | 1848 | 0.1003 |
0.3005 | 85.0 | 1870 | 0.0978 |
0.3005 | 86.0 | 1892 | 0.0987 |
0.3005 | 87.0 | 1914 | 0.0974 |
0.3005 | 88.0 | 1936 | 0.0975 |
0.3005 | 89.0 | 1958 | 0.0965 |
0.3005 | 90.0 | 1980 | 0.0960 |
0.2455 | 91.0 | 2002 | 0.0958 |
0.2455 | 92.0 | 2024 | 0.0952 |
0.2455 | 93.0 | 2046 | 0.0952 |
0.2455 | 94.0 | 2068 | 0.0944 |
0.2455 | 95.0 | 2090 | 0.0943 |
0.2455 | 96.0 | 2112 | 0.0940 |
0.2455 | 97.0 | 2134 | 0.0942 |
0.2455 | 98.0 | 2156 | 0.0940 |
0.2455 | 99.0 | 2178 | 0.0939 |
0.2455 | 100.0 | 2200 | 0.0939 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3