|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: checkpoint-124500-finetuned-squad |
|
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. --> |
|
|
|
# checkpoint-124500-finetuned-squad |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 14.9594 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | |
|
|:-------------:|:-----:|:------:|:---------------:| |
|
| 3.9975 | 1.0 | 3289 | 3.8405 | |
|
| 3.7311 | 2.0 | 6578 | 3.7114 | |
|
| 3.5681 | 3.0 | 9867 | 3.6829 | |
|
| 3.4101 | 4.0 | 13156 | 3.6368 | |
|
| 3.2487 | 5.0 | 16445 | 3.6526 | |
|
| 3.1143 | 6.0 | 19734 | 3.7567 | |
|
| 2.9783 | 7.0 | 23023 | 3.8469 | |
|
| 2.8295 | 8.0 | 26312 | 4.0040 | |
|
| 2.6912 | 9.0 | 29601 | 4.1996 | |
|
| 2.5424 | 10.0 | 32890 | 4.3387 | |
|
| 2.4161 | 11.0 | 36179 | 4.4988 | |
|
| 2.2713 | 12.0 | 39468 | 4.7861 | |
|
| 2.1413 | 13.0 | 42757 | 4.9276 | |
|
| 2.0125 | 14.0 | 46046 | 5.0598 | |
|
| 1.8798 | 15.0 | 49335 | 5.3347 | |
|
| 1.726 | 16.0 | 52624 | 5.5869 | |
|
| 1.5994 | 17.0 | 55913 | 5.7161 | |
|
| 1.4643 | 18.0 | 59202 | 6.0174 | |
|
| 1.3237 | 19.0 | 62491 | 6.4926 | |
|
| 1.2155 | 20.0 | 65780 | 6.4882 | |
|
| 1.1029 | 21.0 | 69069 | 6.9922 | |
|
| 0.9948 | 22.0 | 72358 | 7.1357 | |
|
| 0.9038 | 23.0 | 75647 | 7.3676 | |
|
| 0.8099 | 24.0 | 78936 | 7.4180 | |
|
| 0.7254 | 25.0 | 82225 | 7.7753 | |
|
| 0.6598 | 26.0 | 85514 | 7.8643 | |
|
| 0.5723 | 27.0 | 88803 | 8.1798 | |
|
| 0.5337 | 28.0 | 92092 | 8.3053 | |
|
| 0.4643 | 29.0 | 95381 | 8.8597 | |
|
| 0.4241 | 30.0 | 98670 | 8.9849 | |
|
| 0.3763 | 31.0 | 101959 | 8.8406 | |
|
| 0.3479 | 32.0 | 105248 | 9.1517 | |
|
| 0.3271 | 33.0 | 108537 | 9.3659 | |
|
| 0.2911 | 34.0 | 111826 | 9.4813 | |
|
| 0.2836 | 35.0 | 115115 | 9.5746 | |
|
| 0.2528 | 36.0 | 118404 | 9.7027 | |
|
| 0.2345 | 37.0 | 121693 | 9.7515 | |
|
| 0.2184 | 38.0 | 124982 | 9.9729 | |
|
| 0.2067 | 39.0 | 128271 | 10.0828 | |
|
| 0.2077 | 40.0 | 131560 | 10.0878 | |
|
| 0.1876 | 41.0 | 134849 | 10.2974 | |
|
| 0.1719 | 42.0 | 138138 | 10.2712 | |
|
| 0.1637 | 43.0 | 141427 | 10.5788 | |
|
| 0.1482 | 44.0 | 144716 | 10.7465 | |
|
| 0.1509 | 45.0 | 148005 | 10.4603 | |
|
| 0.1358 | 46.0 | 151294 | 10.7665 | |
|
| 0.1316 | 47.0 | 154583 | 10.7724 | |
|
| 0.1223 | 48.0 | 157872 | 11.1766 | |
|
| 0.1205 | 49.0 | 161161 | 11.1870 | |
|
| 0.1203 | 50.0 | 164450 | 11.1053 | |
|
| 0.1081 | 51.0 | 167739 | 10.9696 | |
|
| 0.103 | 52.0 | 171028 | 11.2010 | |
|
| 0.0938 | 53.0 | 174317 | 11.6728 | |
|
| 0.0924 | 54.0 | 177606 | 11.1423 | |
|
| 0.0922 | 55.0 | 180895 | 11.7409 | |
|
| 0.0827 | 56.0 | 184184 | 11.7850 | |
|
| 0.0829 | 57.0 | 187473 | 11.8956 | |
|
| 0.073 | 58.0 | 190762 | 11.8915 | |
|
| 0.0788 | 59.0 | 194051 | 12.1617 | |
|
| 0.0734 | 60.0 | 197340 | 12.2007 | |
|
| 0.0729 | 61.0 | 200629 | 12.2388 | |
|
| 0.0663 | 62.0 | 203918 | 12.2471 | |
|
| 0.0662 | 63.0 | 207207 | 12.5830 | |
|
| 0.064 | 64.0 | 210496 | 12.6105 | |
|
| 0.0599 | 65.0 | 213785 | 12.3712 | |
|
| 0.0604 | 66.0 | 217074 | 12.9249 | |
|
| 0.0574 | 67.0 | 220363 | 12.7309 | |
|
| 0.0538 | 68.0 | 223652 | 12.8068 | |
|
| 0.0526 | 69.0 | 226941 | 13.4368 | |
|
| 0.0471 | 70.0 | 230230 | 13.5148 | |
|
| 0.0436 | 71.0 | 233519 | 13.3391 | |
|
| 0.0448 | 72.0 | 236808 | 13.4100 | |
|
| 0.0428 | 73.0 | 240097 | 13.5617 | |
|
| 0.0401 | 74.0 | 243386 | 13.8674 | |
|
| 0.035 | 75.0 | 246675 | 13.5746 | |
|
| 0.0342 | 76.0 | 249964 | 13.5042 | |
|
| 0.0344 | 77.0 | 253253 | 14.2085 | |
|
| 0.0365 | 78.0 | 256542 | 13.6393 | |
|
| 0.0306 | 79.0 | 259831 | 13.9807 | |
|
| 0.0311 | 80.0 | 263120 | 13.9768 | |
|
| 0.0353 | 81.0 | 266409 | 14.5245 | |
|
| 0.0299 | 82.0 | 269698 | 13.9471 | |
|
| 0.0263 | 83.0 | 272987 | 13.7899 | |
|
| 0.0254 | 84.0 | 276276 | 14.3786 | |
|
| 0.0267 | 85.0 | 279565 | 14.5611 | |
|
| 0.022 | 86.0 | 282854 | 14.2658 | |
|
| 0.0198 | 87.0 | 286143 | 14.9215 | |
|
| 0.0193 | 88.0 | 289432 | 14.5650 | |
|
| 0.0228 | 89.0 | 292721 | 14.7014 | |
|
| 0.0184 | 90.0 | 296010 | 14.6946 | |
|
| 0.0182 | 91.0 | 299299 | 14.6614 | |
|
| 0.0188 | 92.0 | 302588 | 14.6915 | |
|
| 0.0196 | 93.0 | 305877 | 14.7262 | |
|
| 0.0138 | 94.0 | 309166 | 14.7625 | |
|
| 0.0201 | 95.0 | 312455 | 15.0442 | |
|
| 0.0189 | 96.0 | 315744 | 14.8832 | |
|
| 0.0148 | 97.0 | 319033 | 14.8995 | |
|
| 0.0129 | 98.0 | 322322 | 14.8974 | |
|
| 0.0132 | 99.0 | 325611 | 14.9813 | |
|
| 0.0139 | 100.0 | 328900 | 14.9594 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.19.2 |
|
- Pytorch 1.11.0+cu102 |
|
- Datasets 2.2.2 |
|
- Tokenizers 0.12.1 |
|
|
