<!-- 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
This model is a fine-tuned version of GyanShashwat/distilbert-base-uncased-finetuned-test-data on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 6.0539
- Train End Logits Accuracy: 0.0
- Train Start Logits Accuracy: 0.0
- Epoch: 75
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': 500, '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 |
|---|---|---|---|
| 6.5953 | 0.0 | 0.0 | 0 |
| 6.0959 | 0.0 | 0.0 | 1 |
| 6.0750 | 0.0 | 0.1429 | 2 |
| 6.2449 | 0.0 | 0.0 | 3 |
| 6.6021 | 0.0 | 0.0 | 4 |
| 6.4264 | 0.0 | 0.0 | 5 |
| 6.6183 | 0.0 | 0.0 | 6 |
| 6.4572 | 0.0 | 0.0 | 7 |
| 6.2062 | 0.0 | 0.0 | 8 |
| 6.3750 | 0.0 | 0.0 | 9 |
| 6.4880 | 0.0 | 0.0 | 10 |
| 6.6889 | 0.0 | 0.0 | 11 |
| 6.0914 | 0.0 | 0.0 | 12 |
| 6.0446 | 0.0 | 0.0 | 13 |
| 6.8131 | 0.0 | 0.0 | 14 |
| 6.9439 | 0.0 | 0.0 | 15 |
| 6.0789 | 0.0 | 0.0 | 16 |
| 6.3060 | 0.0 | 0.0 | 17 |
| 6.1862 | 0.0 | 0.0 | 18 |
| 6.4202 | 0.0 | 0.0 | 19 |
| 6.0899 | 0.0 | 0.0 | 20 |
| 6.4460 | 0.0 | 0.0 | 21 |
| 6.0554 | 0.0 | 0.0 | 22 |
| 6.1655 | 0.0 | 0.0 | 23 |
| 6.3298 | 0.0 | 0.0 | 24 |
| 6.1062 | 0.0 | 0.0 | 25 |
| 6.2737 | 0.0 | 0.0 | 26 |
| 6.1412 | 0.0 | 0.0 | 27 |
| 6.2286 | 0.0 | 0.0 | 28 |
| 6.2041 | 0.0 | 0.0 | 29 |
| 6.7055 | 0.0 | 0.0 | 30 |
| 6.2596 | 0.0 | 0.0 | 31 |
| 6.7166 | 0.0 | 0.0 | 32 |
| 6.1891 | 0.0 | 0.0 | 33 |
| 6.1920 | 0.0 | 0.0 | 34 |
| 6.2608 | 0.0 | 0.0 | 35 |
| 6.0968 | 0.0 | 0.0 | 36 |
| 6.6072 | 0.0 | 0.0 | 37 |
| 6.2966 | 0.0 | 0.0 | 38 |
| 6.4528 | 0.0 | 0.0 | 39 |
| 6.5660 | 0.0 | 0.0 | 40 |
| 6.3345 | 0.0 | 0.0 | 41 |
| 6.1812 | 0.0 | 0.0 | 42 |
| 6.1986 | 0.0 | 0.0 | 43 |
| 6.2477 | 0.0 | 0.0 | 44 |
| 6.2783 | 0.0 | 0.0 | 45 |
| 6.7758 | 0.0 | 0.0 | 46 |
| 6.0984 | 0.0 | 0.0 | 47 |
| 6.1547 | 0.0 | 0.0 | 48 |
| 6.1153 | 0.0 | 0.0 | 49 |
| 6.2574 | 0.0 | 0.0 | 50 |
| 5.9857 | 0.0 | 0.0 | 51 |
| 6.1978 | 0.0 | 0.0 | 52 |
| 6.4674 | 0.0 | 0.0 | 53 |
| 6.0991 | 0.0 | 0.0 | 54 |
| 6.2534 | 0.0 | 0.0 | 55 |
| 6.1088 | 0.0 | 0.0 | 56 |
| 5.8161 | 0.0 | 0.0 | 57 |
| 5.9146 | 0.0 | 0.0 | 58 |
| 6.2400 | 0.0 | 0.0 | 59 |
| 6.2602 | 0.1429 | 0.0 | 60 |
| 6.0889 | 0.0 | 0.0 | 61 |
| 6.2283 | 0.0 | 0.0 | 62 |
| 6.4321 | 0.0 | 0.0 | 63 |
| 6.6588 | 0.0 | 0.0 | 64 |
| 6.2557 | 0.0 | 0.0 | 65 |
| 6.2958 | 0.0 | 0.0 | 66 |
| 6.1113 | 0.0 | 0.0 | 67 |
| 6.3594 | 0.0 | 0.0 | 68 |
| 5.9983 | 0.0 | 0.0 | 69 |
| 6.0230 | 0.0 | 0.1429 | 70 |
| 6.1085 | 0.0 | 0.0 | 71 |
| 6.3313 | 0.0 | 0.0 | 72 |
| 6.4739 | 0.0 | 0.0 | 73 |
| 6.1131 | 0.0 | 0.0 | 74 |
| 6.0539 | 0.0 | 0.0 | 75 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.0
- Tokenizers 0.13.3
