metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_keras_callback
model-index:
- name: pop_genre5
results: []
pop_genre5
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6216
- Validation Loss: 0.9008
- Epoch: 6
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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 1e-05}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 1.6302 | 1.1708 | 0 |
| 1.1317 | 1.0782 | 1 |
| 0.9470 | 0.9557 | 2 |
| 0.8303 | 0.9179 | 3 |
| 0.7424 | 0.8998 | 4 |
| 0.6816 | 0.9115 | 5 |
| 0.6216 | 0.9008 | 6 |
Framework versions
- Transformers 4.32.1
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3