<!-- 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. -->
auto_bot
This model is a fine-tuned version of deepset/gelectra-base-germanquad on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1041
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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 1 | 2.7932 |
| No log | 2.0 | 2 | 2.8536 |
| No log | 3.0 | 3 | 2.8856 |
| No log | 4.0 | 4 | 2.9470 |
| No log | 5.0 | 5 | 2.9948 |
| No log | 6.0 | 6 | 3.0745 |
| No log | 7.0 | 7 | 3.1467 |
| No log | 8.0 | 8 | 3.2018 |
| No log | 9.0 | 9 | 3.2549 |
| No log | 10.0 | 10 | 3.2827 |
| No log | 11.0 | 11 | 3.2572 |
| No log | 12.0 | 12 | 3.1982 |
| No log | 13.0 | 13 | 3.1229 |
| No log | 14.0 | 14 | 3.0666 |
| No log | 15.0 | 15 | 3.0209 |
| No log | 16.0 | 16 | 2.9706 |
| No log | 17.0 | 17 | 2.9060 |
| No log | 18.0 | 18 | 2.8304 |
| No log | 19.0 | 19 | 2.7950 |
| No log | 20.0 | 20 | 2.7435 |
| No log | 21.0 | 21 | 2.7194 |
| No log | 22.0 | 22 | 2.7012 |
| No log | 23.0 | 23 | 2.6803 |
| No log | 24.0 | 24 | 2.6647 |
| No log | 25.0 | 25 | 2.6490 |
| No log | 26.0 | 26 | 2.6476 |
| No log | 27.0 | 27 | 2.6626 |
| No log | 28.0 | 28 | 2.6928 |
| No log | 29.0 | 29 | 2.7398 |
| No log | 30.0 | 30 | 2.7371 |
| No log | 31.0 | 31 | 2.7501 |
| No log | 32.0 | 32 | 2.7698 |
| No log | 33.0 | 33 | 2.7965 |
| No log | 34.0 | 34 | 2.8332 |
| No log | 35.0 | 35 | 2.8756 |
| No log | 36.0 | 36 | 2.9246 |
| No log | 37.0 | 37 | 2.9754 |
| No log | 38.0 | 38 | 3.0306 |
| No log | 39.0 | 39 | 3.0738 |
| No log | 40.0 | 40 | 3.1037 |
| No log | 41.0 | 41 | 3.1197 |
| No log | 42.0 | 42 | 3.1269 |
| No log | 43.0 | 43 | 3.1520 |
| No log | 44.0 | 44 | 3.1566 |
| No log | 45.0 | 45 | 3.1706 |
| No log | 46.0 | 46 | 3.1815 |
| No log | 47.0 | 47 | 3.1709 |
| No log | 48.0 | 48 | 3.1615 |
| No log | 49.0 | 49 | 3.1367 |
| No log | 50.0 | 50 | 3.1303 |
| No log | 51.0 | 51 | 3.1252 |
| No log | 52.0 | 52 | 3.1182 |
| No log | 53.0 | 53 | 3.1105 |
| No log | 54.0 | 54 | 3.0899 |
| No log | 55.0 | 55 | 3.0767 |
| No log | 56.0 | 56 | 3.0598 |
| No log | 57.0 | 57 | 3.0419 |
| No log | 58.0 | 58 | 3.0298 |
| No log | 59.0 | 59 | 3.0371 |
| No log | 60.0 | 60 | 3.0315 |
| No log | 61.0 | 61 | 3.0238 |
| No log | 62.0 | 62 | 3.0137 |
| No log | 63.0 | 63 | 3.0129 |
| No log | 64.0 | 64 | 3.0188 |
| No log | 65.0 | 65 | 3.0242 |
| No log | 66.0 | 66 | 3.0289 |
| No log | 67.0 | 67 | 3.0293 |
| No log | 68.0 | 68 | 3.0229 |
| No log | 69.0 | 69 | 3.0187 |
| No log | 70.0 | 70 | 3.0121 |
| No log | 71.0 | 71 | 3.0028 |
| No log | 72.0 | 72 | 2.9944 |
| No log | 73.0 | 73 | 2.9858 |
| No log | 74.0 | 74 | 2.9779 |
| No log | 75.0 | 75 | 2.9792 |
| No log | 76.0 | 76 | 2.9778 |
| No log | 77.0 | 77 | 2.9800 |
| No log | 78.0 | 78 | 2.9846 |
| No log | 79.0 | 79 | 2.9932 |
| No log | 80.0 | 80 | 3.0056 |
| No log | 81.0 | 81 | 3.0129 |
| No log | 82.0 | 82 | 3.0216 |
| No log | 83.0 | 83 | 3.0312 |
| No log | 84.0 | 84 | 3.0401 |
| No log | 85.0 | 85 | 3.0507 |
| No log | 86.0 | 86 | 3.0582 |
| No log | 87.0 | 87 | 3.0625 |
| No log | 88.0 | 88 | 3.0660 |
| No log | 89.0 | 89 | 3.0694 |
| No log | 90.0 | 90 | 3.0757 |
| No log | 91.0 | 91 | 3.0818 |
| No log | 92.0 | 92 | 3.0873 |
| No log | 93.0 | 93 | 3.0904 |
| No log | 94.0 | 94 | 3.0936 |
| No log | 95.0 | 95 | 3.0975 |
| No log | 96.0 | 96 | 3.1001 |
| No log | 97.0 | 97 | 3.1019 |
| No log | 98.0 | 98 | 3.1030 |
| No log | 99.0 | 99 | 3.1038 |
| No log | 100.0 | 100 | 3.1041 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2
