<!-- 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. -->
whisper_charsplit_new_round4__0005
This model is a fine-tuned version of bigmorning/whisper_charsplit_new_round2__0061 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0009
- Train Accuracy: 0.0795
- Train Wermet: 8.4533
- Validation Loss: 0.5771
- Validation Accuracy: 0.0771
- Validation Wermet: 7.4112
- Epoch: 4
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': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|---|---|---|---|---|---|---|
| 0.0009 | 0.0795 | 7.9702 | 0.5713 | 0.0770 | 6.9300 | 0 |
| 0.0011 | 0.0795 | 7.7485 | 0.5743 | 0.0771 | 6.6465 | 1 |
| 0.0011 | 0.0795 | 8.1600 | 0.5748 | 0.0771 | 7.1363 | 2 |
| 0.0008 | 0.0795 | 8.1954 | 0.5845 | 0.0770 | 7.1869 | 3 |
| 0.0009 | 0.0795 | 8.4533 | 0.5771 | 0.0771 | 7.4112 | 4 |
Framework versions
- Transformers 4.32.0.dev0
- TensorFlow 2.12.0
- Tokenizers 0.13.3
