metadata
tags:
- generated_from_keras_callback
base_model: google/pegasus-large
model-index:
- name: pegasus-large-musicLyrics
results: []
pegasus-large-musicLyrics
This model is a fine-tuned version of google/pegasus-large on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.0472
- Train Sparse Categorical Accuracy: 0.7971
- Validation Loss: 1.0387
- Validation Sparse Categorical Accuracy: 0.7992
- Epoch: 2
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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|---|---|---|---|---|
| 1.4713 | 0.7524 | 1.0652 | 0.7960 | 0 |
| 1.0824 | 0.7934 | 1.0482 | 0.7982 | 1 |
| 1.0472 | 0.7971 | 1.0387 | 0.7992 | 2 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3