metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_keras_callback
model-index:
- name: pakawadeep/mt5-small-finetuned-ctfl-augmented_2
results: []
pakawadeep/mt5-small-finetuned-ctfl-augmented_2
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.5137
- Validation Loss: 1.3902
- Train Rouge1: 7.7086
- Train Rouge2: 2.0792
- Train Rougel: 7.7086
- Train Rougelsum: 7.7086
- Train Gen Len: 11.9653
- Epoch: 5
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 |
|---|---|---|---|---|---|---|---|
| 8.2342 | 2.0102 | 1.5963 | 0.0 | 1.6101 | 1.6005 | 16.5050 | 0 |
| 3.7896 | 1.7810 | 4.8515 | 0.7426 | 4.8845 | 4.8680 | 11.8614 | 1 |
| 2.7018 | 1.7212 | 6.8812 | 1.4851 | 6.8812 | 6.8812 | 11.9554 | 2 |
| 2.1382 | 1.5885 | 7.8996 | 2.0792 | 7.9066 | 7.9066 | 11.9010 | 3 |
| 1.7718 | 1.4799 | 7.7086 | 2.0792 | 7.7086 | 7.7086 | 11.8911 | 4 |
| 1.5137 | 1.3902 | 7.7086 | 2.0792 | 7.7086 | 7.7086 | 11.9653 | 5 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.20.0
- Tokenizers 0.19.1