|
--- |
|
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: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# 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](https://huggingface.co/bedus-creation/mBart-small-dataset-i-eng-lim) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.3073 |
|
- Validation Loss: 0.2861 |
|
- Epoch: 17 |
|
|
|
## 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 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- TensorFlow 2.13.0 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
