This model is a fine-tuned version of
distilbert-base-uncased on the None dataset.
It achieves the following results on the evaluation set:
|
|:-------------:|:-----:|:-----:|:---------------:|:------------:|:------:|
| No log | 1.0 | 414 | 12.5408 | 0.7209 | 0.6040 |
| 15.149 | 2.0 | 828 | 12.3090 | 0.7209 | 0.6040 |
| 14.6783 | 3.0 | 1242 | 12.0749 | 0.7209 | 0.6040 |
| 14.3834 | 4.0 | 1656 | 11.8351 | 0.7209 | 0.6040 |
| 14.0974 | 5.0 | 2070 | 11.5917 | 0.7209 | 0.6040 |
| 14.0974 | 6.0 | 2484 | 11.3454 | 0.7209 | 0.6040 |
| 13.6572 | 7.0 | 2898 | 11.0976 | 0.7209 | 0.6040 |
| 13.3155 | 8.0 | 3312 | 10.8493 | 0.7209 | 0.6040 |
| 12.952 | 9.0 | 3726 | 10.6010 | 0.7209 | 0.6040 |
| 12.6532 | 10.0 | 4140 | 10.3537 | 0.7209 | 0.6040 |
| 12.2132 | 11.0 | 4554 | 10.1076 | 0.7209 | 0.6040 |
| 12.2132 | 12.0 | 4968 | 9.8630 | 0.7209 | 0.6040 |
| 11.8996 | 13.0 | 5382 | 9.6207 | 0.7209 | 0.6040 |
| 11.4989 | 14.0 | 5796 | 9.3809 | 0.7209 | 0.6040 |
| 11.3115 | 15.0 | 6210 | 9.1439 | 0.7209 | 0.6040 |
| 10.807 | 16.0 | 6624 | 8.9100 | 0.7209 | 0.6040 |
| 10.5865 | 17.0 | 7038 | 8.6792 | 0.7209 | 0.6040 |
| 10.5865 | 18.0 | 7452 | 8.4524 | 0.7209 | 0.6040 |
| 10.114 | 19.0 | 7866 | 8.2293 | 0.7209 | 0.6040 |
| 9.8898 | 20.0 | 8280 | 8.0108 | 0.7209 | 0.6040 |
| 9.6071 | 21.0 | 8694 | 7.7968 | 0.7209 | 0.6040 |
| 9.1826 | 22.0 | 9108 | 7.5876 | 0.7209 | 0.6040 |
| 8.9698 | 23.0 | 9522 | 7.3836 | 0.7209 | 0.6040 |
| 8.9698 | 24.0 | 9936 | 7.1848 | 0.7209 | 0.6040 |
| 8.6174 | 25.0 | 10350 | 6.9917 | 0.7209 | 0.6040 |
| 8.4551 | 26.0 | 10764 | 6.8044 | 0.7209 | 0.6040 |
| 8.0627 | 27.0 | 11178 | 6.6234 | 0.7198 | 0.6035 |
| 7.7999 | 28.0 | 11592 | 6.4491 | 0.7198 | 0.6035 |
| 7.6306 | 29.0 | 12006 | 6.2814 | 0.7209 | 0.6062 |
| 7.6306 | 30.0 | 12420 | 6.1208 | 0.7198 | 0.6056 |
| 7.4025 | 31.0 | 12834 | 5.9676 | 0.7186 | 0.6050 |
| 7.07 | 32.0 | 13248 | 5.8217 | 0.7186 | 0.6050 |
| 7.0205 | 33.0 | 13662 | 5.6837 | 0.7186 | 0.6071 |
| 6.5798 | 34.0 | 14076 | 5.5534 | 0.7186 | 0.6092 |
| 6.5798 | 35.0 | 14490 | 5.4311 | 0.7186 | 0.6092 |
| 6.6085 | 36.0 | 14904 | 5.3169 | 0.7198 | 0.6118 |
| 6.3328 | 37.0 | 15318 | 5.2109 | 0.7186 | 0.6112 |
| 6.2354 | 38.0 | 15732 | 5.1133 | 0.7174 | 0.6125 |
| 6.065 | 39.0 | 16146 | 5.0239 | 0.7151 | 0.6113 |
| 5.9298 | 40.0 | 16560 | 4.9429 | 0.7128 | 0.6101 |
| 5.9298 | 41.0 | 16974 | 4.8704 | 0.7105 | 0.6088 |
| 5.8174 | 42.0 | 17388 | 4.8060 | 0.7093 | 0.6082 |
| 5.7507 | 43.0 | 17802 | 4.7497 | 0.7093 | 0.6082 |
| 5.6812 | 44.0 | 18216 | 4.7014 | 0.7081 | 0.6076 |
| 5.4982 | 45.0 | 18630 | 4.6608 | 0.7081 | 0.6095 |
| 5.509 | 46.0 | 19044 | 4.6278 | 0.7058 | 0.6082 |
| 5.509 | 47.0 | 19458 | 4.6023 | 0.7035 | 0.6070 |
| 5.4924 | 48.0 | 19872 | 4.5841 | 0.7035 | 0.6070 |
| 5.453 | 49.0 | 20286 | 4.5733 | 0.7035 | 0.6070 |
| 5.4353 | 50.0 | 20700 | 4.5697 | 0.7035 | 0.6070 |