<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
pretrained-m-bert-100
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 5.7643
- Validation Loss: 15.3282
- Epoch: 99
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:
- optimizer: {'name': 'Adam', 'learning_rate': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 10.2677 | 10.9468 | 0 |
| 7.8146 | 10.9178 | 1 |
| 6.8830 | 11.4644 | 2 |
| 6.4854 | 11.6027 | 3 |
| 6.3696 | 11.5359 | 4 |
| 6.3373 | 12.1261 | 5 |
| 6.4347 | 11.7670 | 6 |
| 6.0652 | 12.2223 | 7 |
| 5.9448 | 12.1202 | 8 |
| 6.0746 | 12.0816 | 9 |
| 6.0138 | 12.4949 | 10 |
| 5.9344 | 12.8130 | 11 |
| 5.9458 | 12.4795 | 12 |
| 5.9723 | 12.8273 | 13 |
| 6.0556 | 12.3681 | 14 |
| 5.8662 | 12.5367 | 15 |
| 5.8969 | 12.8070 | 16 |
| 5.9584 | 13.0502 | 17 |
| 5.8317 | 12.9219 | 18 |
| 5.8259 | 13.0385 | 19 |
| 5.8747 | 13.0952 | 20 |
| 5.7600 | 13.2153 | 21 |
| 5.8675 | 13.2446 | 22 |
| 5.8878 | 13.1709 | 23 |
| 5.7433 | 13.0553 | 24 |
| 5.6823 | 13.2854 | 25 |
| 5.8674 | 13.5718 | 26 |
| 5.7787 | 14.0820 | 27 |
| 5.8037 | 13.5664 | 28 |
| 5.9530 | 13.0143 | 29 |
| 5.8236 | 13.0637 | 30 |
| 5.7696 | 13.5515 | 31 |
| 5.9817 | 13.4774 | 32 |
| 5.6877 | 13.6842 | 33 |
| 5.7816 | 13.5667 | 34 |
| 5.7775 | 13.3846 | 35 |
| 5.7104 | 13.6230 | 36 |
| 5.8429 | 13.5487 | 37 |
| 5.8082 | 13.6563 | 38 |
| 5.8588 | 13.6359 | 39 |
| 5.6482 | 13.8751 | 40 |
| 5.7874 | 13.6936 | 41 |
| 5.7451 | 14.1454 | 42 |
| 5.7165 | 13.8532 | 43 |
| 5.7180 | 14.0519 | 44 |
| 5.6640 | 14.0859 | 45 |
| 5.6735 | 14.0086 | 46 |
| 5.6666 | 14.1733 | 47 |
| 5.6681 | 13.9786 | 48 |
| 5.8221 | 14.0396 | 49 |
| 5.8544 | 14.0354 | 50 |
| 5.6817 | 14.4682 | 51 |
| 5.7215 | 14.2324 | 52 |
| 5.7315 | 13.9238 | 53 |
| 5.9291 | 14.2091 | 54 |
| 5.6790 | 13.6927 | 55 |
| 5.8746 | 14.1590 | 56 |
| 5.7267 | 14.4351 | 57 |
| 5.7268 | 14.0592 | 58 |
| 5.7535 | 14.2763 | 59 |
| 5.7884 | 13.8493 | 60 |
| 5.6596 | 14.0534 | 61 |
| 5.7041 | 14.4408 | 62 |
| 5.6752 | 14.4218 | 63 |
| 5.7102 | 14.3895 | 64 |
| 5.7761 | 14.3942 | 65 |
| 5.7248 | 14.5926 | 66 |
| 5.7945 | 14.2754 | 67 |
| 5.9298 | 14.3393 | 68 |
| 5.8765 | 14.5247 | 69 |
| 5.7173 | 14.3060 | 70 |
| 5.6568 | 14.1837 | 71 |
| 5.8706 | 14.0935 | 72 |
| 5.6913 | 14.0180 | 73 |
| 5.7403 | 14.9313 | 74 |
| 5.8633 | 14.1447 | 75 |
| 5.8216 | 14.5450 | 76 |
| 5.7655 | 14.4690 | 77 |
| 5.7860 | 14.4312 | 78 |
| 5.6992 | 14.1038 | 79 |
| 5.7390 | 14.5180 | 80 |
| 5.7588 | 14.2374 | 81 |
| 5.7709 | 14.4895 | 82 |
| 5.6294 | 14.9558 | 83 |
| 5.8151 | 14.5835 | 84 |
| 5.7965 | 14.8980 | 85 |
| 5.8296 | 14.5919 | 86 |
| 5.6494 | 15.2158 | 87 |
| 5.8014 | 14.9455 | 88 |
| 5.7313 | 14.4270 | 89 |
| 5.7492 | 14.2205 | 90 |
| 5.7618 | 15.2789 | 91 |
| 5.7249 | 15.0650 | 92 |
| 5.6761 | 14.8731 | 93 |
| 5.8601 | 14.6370 | 94 |
| 5.6296 | 14.8570 | 95 |
| 5.7572 | 14.7718 | 96 |
| 5.6341 | 14.9328 | 97 |
| 5.6881 | 14.9298 | 98 |
| 5.7643 | 15.3282 | 99 |
Framework versions
- Transformers 4.27.0.dev0
- TensorFlow 2.9.2
- Datasets 2.9.0
- Tokenizers 0.13.2
