<!-- 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. -->
SiriRRR/bart-base-finetuned-test
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5900
- Validation Loss: 2.6982
- Epoch: 7
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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 2864, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
Train Loss | Validation Loss | Epoch |
---|---|---|
2.4667 | 2.1935 | 0 |
1.7786 | 2.2691 | 1 |
1.4244 | 2.3324 | 2 |
1.1479 | 2.4362 | 3 |
0.9405 | 2.5442 | 4 |
0.7770 | 2.5797 | 5 |
0.6615 | 2.6505 | 6 |
0.5900 | 2.6982 | 7 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.9.2
- Datasets 2.7.1
- Tokenizers 0.13.2