metadata
license: apache-2.0
base_model: bedus-creation/mBart-small-dataset-i-eng-lim
tags:
- generated_from_keras_callback
model-index:
- name: bedus-creation/mBart-small-dataset-ii-eng-lim-004
results: []
bedus-creation/mBart-small-dataset-ii-eng-lim-004
This model is a fine-tuned version of bedus-creation/mBart-small-dataset-i-eng-lim on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.3009
- Validation Loss: 0.2834
- Epoch: 20
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': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.9940 | 0.4653 | 0 |
| 0.4659 | 0.3647 | 1 |
| 0.4011 | 0.3331 | 2 |
| 0.3798 | 0.3284 | 3 |
| 0.3640 | 0.3210 | 4 |
| 0.3539 | 0.3087 | 5 |
| 0.3456 | 0.3106 | 6 |
| 0.3377 | 0.3049 | 7 |
| 0.3340 | 0.2998 | 8 |
| 0.3285 | 0.2974 | 9 |
| 0.3246 | 0.2980 | 10 |
| 0.3202 | 0.2950 | 11 |
| 0.3174 | 0.2910 | 12 |
| 0.3154 | 0.2932 | 13 |
| 0.3124 | 0.2882 | 14 |
| 0.3094 | 0.2895 | 15 |
| 0.3092 | 0.2880 | 16 |
| 0.3073 | 0.2861 | 17 |
| 0.3043 | 0.2842 | 18 |
| 0.3037 | 0.2856 | 19 |
| 0.3009 | 0.2834 | 20 |
Framework versions
- Transformers 4.33.3
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3