metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_keras_callback
model-index:
- name: s-man2099/fblc-2000
results: []
s-man2099/fblc-2000
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.8733
- Validation Loss: 3.3447
- 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': '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': 6e-05, '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 |
|---|---|---|
| 3.5721 | 3.3704 | 0 |
| 3.3599 | 3.3262 | 1 |
| 3.2316 | 3.3114 | 2 |
| 3.1259 | 3.3045 | 3 |
| 3.0387 | 3.3135 | 4 |
| 2.9528 | 3.3179 | 5 |
| 2.8733 | 3.3447 | 6 |
Framework versions
- Transformers 4.34.1
- TensorFlow 2.14.0
- Datasets 2.14.6
- Tokenizers 0.14.1