<!-- 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. -->
GyanShashwat/distilbert-base-uncased-finetuned-test-data-v2
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 5.8903
- Train End Logits Accuracy: 0.0
- Train Start Logits Accuracy: 0.1429
- Epoch: 81
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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.01, 'decay_steps': 100, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Epoch |
|---|---|---|---|
| 5.9801 | 0.0 | 0.0 | 0 |
| 5.9338 | 0.0 | 0.0 | 1 |
| 5.9744 | 0.0 | 0.0 | 2 |
| 5.9011 | 0.0 | 0.0 | 3 |
| 5.9892 | 0.0 | 0.0 | 4 |
| 6.0409 | 0.0 | 0.0 | 5 |
| 5.8902 | 0.0 | 0.0 | 6 |
| 5.9480 | 0.0 | 0.0 | 7 |
| 6.0100 | 0.0 | 0.0 | 8 |
| 6.0898 | 0.0 | 0.0 | 9 |
| 5.9093 | 0.0 | 0.0 | 10 |
| 5.8435 | 0.0 | 0.0 | 11 |
| 5.9528 | 0.0 | 0.0 | 12 |
| 5.9702 | 0.0 | 0.0 | 13 |
| 6.2079 | 0.0 | 0.0 | 14 |
| 6.0707 | 0.0 | 0.0 | 15 |
| 6.0218 | 0.0 | 0.0 | 16 |
| 5.9175 | 0.0 | 0.0 | 17 |
| 5.8957 | 0.0 | 0.0 | 18 |
| 5.9021 | 0.0 | 0.0 | 19 |
| 6.1419 | 0.0 | 0.0 | 20 |
| 6.0310 | 0.0 | 0.0 | 21 |
| 5.8559 | 0.0 | 0.0 | 22 |
| 5.9768 | 0.0 | 0.0 | 23 |
| 6.0752 | 0.0 | 0.0 | 24 |
| 6.3935 | 0.0 | 0.0 | 25 |
| 6.2257 | 0.0 | 0.0 | 26 |
| 6.2152 | 0.0 | 0.0 | 27 |
| 6.1603 | 0.0 | 0.0 | 28 |
| 6.2708 | 0.0 | 0.0 | 29 |
| 5.9893 | 0.0 | 0.0 | 30 |
| 5.6298 | 0.0 | 0.2857 | 31 |
| 5.9713 | 0.0 | 0.0 | 32 |
| 6.1259 | 0.0 | 0.0 | 33 |
| 6.0831 | 0.0 | 0.0 | 34 |
| 6.1936 | 0.0 | 0.0 | 35 |
| 6.1549 | 0.0 | 0.0 | 36 |
| 6.1610 | 0.0 | 0.0 | 37 |
| 6.1028 | 0.0 | 0.0 | 38 |
| 6.3336 | 0.0 | 0.0 | 39 |
| 6.1848 | 0.0 | 0.0 | 40 |
| 6.1255 | 0.0 | 0.0 | 41 |
| 6.0896 | 0.0 | 0.0 | 42 |
| 6.2798 | 0.0 | 0.0 | 43 |
| 6.2555 | 0.0 | 0.0 | 44 |
| 6.3498 | 0.0 | 0.0 | 45 |
| 6.1329 | 0.0 | 0.0 | 46 |
| 6.1033 | 0.0 | 0.0 | 47 |
| 6.1298 | 0.1429 | 0.0 | 48 |
| 6.1285 | 0.0 | 0.0 | 49 |
| 6.3465 | 0.0 | 0.0 | 50 |
| 6.1177 | 0.0 | 0.0 | 51 |
| 6.1626 | 0.0 | 0.0 | 52 |
| 6.0304 | 0.0 | 0.0 | 53 |
| 6.0605 | 0.1429 | 0.0 | 54 |
| 5.9403 | 0.0 | 0.0 | 55 |
| 5.7870 | 0.0 | 0.0 | 56 |
| 6.1490 | 0.0 | 0.0 | 57 |
| 5.9711 | 0.0 | 0.1429 | 58 |
| 6.0982 | 0.0 | 0.0 | 59 |
| 5.7100 | 0.1429 | 0.0 | 60 |
| 5.9671 | 0.0 | 0.0 | 61 |
| 6.0133 | 0.0 | 0.0 | 62 |
| 6.1473 | 0.0 | 0.0 | 63 |
| 5.8185 | 0.0 | 0.0 | 64 |
| 5.8461 | 0.0 | 0.0 | 65 |
| 5.8286 | 0.1429 | 0.0 | 66 |
| 6.1176 | 0.0 | 0.0 | 67 |
| 6.0289 | 0.0 | 0.0 | 68 |
| 6.0143 | 0.0 | 0.0 | 69 |
| 6.1875 | 0.0 | 0.0 | 70 |
| 6.1716 | 0.0 | 0.0 | 71 |
| 5.8779 | 0.0 | 0.0 | 72 |
| 6.1317 | 0.0 | 0.0 | 73 |
| 6.0170 | 0.0 | 0.0 | 74 |
| 6.0243 | 0.0 | 0.0 | 75 |
| 5.9871 | 0.0 | 0.0 | 76 |
| 6.0451 | 0.0 | 0.0 | 77 |
| 6.0820 | 0.0 | 0.0 | 78 |
| 6.1378 | 0.0 | 0.0 | 79 |
| 6.0649 | 0.0 | 0.0 | 80 |
| 5.8903 | 0.0 | 0.1429 | 81 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.0
- Tokenizers 0.13.3
