<!-- 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. -->
s-man2099/google-pegasus-large
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: 4.0100
- Validation Loss: 3.5622
- 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: {'name': 'Adafactor', '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': 5.999999e-13, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 4.4456 | 3.5894 | 0 |
| 4.0552 | 3.5645 | 1 |
| 4.0056 | 3.5623 | 2 |
| 3.9808 | 3.5622 | 3 |
| 3.9825 | 3.5622 | 4 |
| 4.0072 | 3.5622 | 5 |
| 3.9842 | 3.5622 | 6 |
| 4.0100 | 3.5622 | 7 |
Framework versions
- Transformers 4.34.1
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
