|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-base |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: pakawadeep/mt5-base-finetuned-ctfl-augmented_2 |
|
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-base-finetuned-ctfl-augmented_2 |
|
|
|
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.4142 |
|
- Validation Loss: 0.7725 |
|
- Train Rouge1: 8.6516 |
|
- Train Rouge2: 0.8911 |
|
- Train Rougel: 8.6634 |
|
- Train Rougelsum: 8.8579 |
|
- Train Gen Len: 11.9307 |
|
- Epoch: 28 |
|
|
|
## 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 | |
|
|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:| |
|
| 6.2987 | 3.0653 | 5.1273 | 0.9901 | 5.0743 | 5.2334 | 7.9208 | 0 | |
|
| 2.9686 | 2.1339 | 6.0644 | 1.3201 | 6.1056 | 6.1056 | 9.7277 | 1 | |
|
| 1.9868 | 1.6122 | 6.4356 | 1.6832 | 6.5535 | 6.5064 | 11.2970 | 2 | |
|
| 1.4819 | 1.2447 | 8.2744 | 2.1782 | 8.3663 | 8.4017 | 11.7921 | 3 | |
|
| 1.5597 | 1.4425 | 7.9208 | 2.3762 | 7.9915 | 8.0387 | 11.7376 | 4 | |
|
| 1.2413 | 1.2182 | 8.8048 | 2.1782 | 8.8826 | 8.9109 | 11.8713 | 5 | |
|
| 1.2091 | 1.2376 | 7.7793 | 1.3861 | 7.9208 | 7.9915 | 11.8861 | 6 | |
|
| 1.0808 | 1.1154 | 8.2744 | 1.3861 | 8.4512 | 8.5219 | 11.9455 | 7 | |
|
| 0.9719 | 1.0578 | 7.9915 | 1.1881 | 8.1683 | 8.2037 | 11.9604 | 8 | |
|
| 1.0497 | 1.0547 | 8.4394 | 1.3861 | 8.4925 | 8.6103 | 11.9158 | 9 | |
|
| 0.9426 | 1.0468 | 8.2744 | 1.3861 | 8.4512 | 8.5219 | 11.9455 | 10 | |
|
| 0.8904 | 0.9902 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9257 | 11 | |
|
| 0.8371 | 0.9637 | 7.7970 | 0.8911 | 7.9562 | 7.9915 | 11.9505 | 12 | |
|
| 0.8025 | 0.9304 | 7.9562 | 0.8911 | 8.0151 | 8.1094 | 11.9109 | 13 | |
|
| 0.7650 | 0.9143 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9257 | 14 | |
|
| 0.7276 | 0.8825 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9059 | 15 | |
|
| 0.6877 | 0.8607 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9257 | 16 | |
|
| 0.6566 | 0.8303 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9257 | 17 | |
|
| 0.6205 | 0.8124 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9307 | 18 | |
|
| 0.5878 | 0.7924 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9257 | 19 | |
|
| 0.5535 | 0.7724 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.8911 | 20 | |
|
| 0.5243 | 0.7751 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.9109 | 21 | |
|
| 0.5444 | 0.8057 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.8911 | 22 | |
|
| 0.5281 | 0.7875 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.8663 | 23 | |
|
| 0.4990 | 0.7810 | 8.1565 | 0.8911 | 8.2567 | 8.3687 | 11.8762 | 24 | |
|
| 0.4762 | 0.7858 | 8.6516 | 0.8911 | 8.6634 | 8.8579 | 11.8812 | 25 | |
|
| 0.4538 | 0.7793 | 8.6516 | 0.8911 | 8.6634 | 8.8579 | 11.9158 | 26 | |
|
| 0.4330 | 0.7813 | 8.6516 | 0.8911 | 8.6634 | 8.8579 | 11.8762 | 27 | |
|
| 0.4142 | 0.7725 | 8.6516 | 0.8911 | 8.6634 | 8.8579 | 11.9307 | 28 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- TensorFlow 2.15.0 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
