|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: pakawadeep/mt5-small-finetuned-ctfl-augmented |
|
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. --> |
|
|
|
# pakawadeep/mt5-small-finetuned-ctfl-augmented |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.9381 |
|
- Validation Loss: 0.9416 |
|
- Train Rouge1: 7.9915 |
|
- Train Rouge2: 1.3861 |
|
- Train Rougel: 7.9562 |
|
- Train Rougelsum: 7.9915 |
|
- Train Gen Len: 11.9653 |
|
- Epoch: 29 |
|
|
|
## 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': 2e-05, '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 | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch | |
|
|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:| |
|
| 10.7577 | 3.2303 | 0.7164 | 0.0 | 0.7206 | 0.7052 | 16.1683 | 0 | |
|
| 5.8846 | 1.9848 | 1.5545 | 0.0 | 1.5846 | 1.5614 | 16.7376 | 1 | |
|
| 4.2789 | 1.7719 | 5.0684 | 0.7426 | 5.1391 | 5.1155 | 11.6386 | 2 | |
|
| 3.4851 | 1.7527 | 5.2310 | 0.9406 | 5.2310 | 5.2074 | 11.1040 | 3 | |
|
| 2.9892 | 1.7038 | 6.2235 | 0.8251 | 6.3225 | 6.2777 | 11.3812 | 4 | |
|
| 2.6463 | 1.6585 | 8.2037 | 2.1782 | 8.2037 | 8.2037 | 11.4901 | 5 | |
|
| 2.3897 | 1.5964 | 8.6987 | 2.1782 | 8.6987 | 8.4866 | 11.7030 | 6 | |
|
| 2.1794 | 1.5112 | 8.6987 | 2.1782 | 8.6987 | 8.4866 | 11.8317 | 7 | |
|
| 1.9896 | 1.4461 | 8.2037 | 2.1782 | 8.2037 | 8.2037 | 11.9059 | 8 | |
|
| 1.8347 | 1.3770 | 8.2037 | 2.1782 | 8.2037 | 8.2037 | 11.9703 | 9 | |
|
| 1.7101 | 1.3155 | 8.2037 | 2.1782 | 8.2037 | 8.2037 | 11.9505 | 10 | |
|
| 1.6003 | 1.2598 | 8.6987 | 2.1782 | 8.6987 | 8.6987 | 11.9109 | 11 | |
|
| 1.5041 | 1.2367 | 8.6987 | 2.1782 | 8.6987 | 8.6987 | 11.9505 | 12 | |
|
| 1.4309 | 1.2286 | 8.6987 | 2.1782 | 8.6987 | 8.6987 | 11.9554 | 13 | |
|
| 1.3618 | 1.1795 | 8.9109 | 2.3762 | 9.0877 | 8.9816 | 11.9554 | 14 | |
|
| 1.3090 | 1.1625 | 8.9109 | 2.3762 | 9.0877 | 8.9816 | 11.9455 | 15 | |
|
| 1.2669 | 1.1210 | 8.9109 | 2.3762 | 9.0877 | 8.9816 | 11.9554 | 16 | |
|
| 1.2262 | 1.0769 | 8.6987 | 1.7822 | 8.7694 | 8.7341 | 11.9752 | 17 | |
|
| 1.1915 | 1.0724 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9752 | 18 | |
|
| 1.1562 | 1.0444 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9703 | 19 | |
|
| 1.1291 | 1.0318 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9653 | 20 | |
|
| 1.1063 | 1.0321 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9554 | 21 | |
|
| 1.0786 | 1.0124 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9604 | 22 | |
|
| 1.0540 | 1.0062 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9604 | 23 | |
|
| 1.0241 | 0.9787 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9653 | 24 | |
|
| 1.0086 | 0.9683 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9703 | 25 | |
|
| 0.9883 | 0.9665 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9653 | 26 | |
|
| 0.9661 | 0.9521 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9703 | 27 | |
|
| 0.9543 | 0.9693 | 8.4512 | 1.3861 | 8.4866 | 8.4512 | 11.9703 | 28 | |
|
| 0.9381 | 0.9416 | 7.9915 | 1.3861 | 7.9562 | 7.9915 | 11.9653 | 29 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- TensorFlow 2.15.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|