metadata
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_keras_callback
model-index:
- name: pakawadeep/mt5-base-finetuned-ctfl-augmented
results: []
pakawadeep/mt5-base-finetuned-ctfl-augmented
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.1182
- Validation Loss: 0.9736
- Train Rouge1: 8.6987
- Train Rouge2: 1.8812
- Train Rougel: 8.6987
- Train Rougelsum: 8.7694
- Train Gen Len: 11.9703
- Epoch: 10
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 |
|---|---|---|---|---|---|---|---|
| 6.9468 | 2.5770 | 1.3751 | 0.2405 | 1.3339 | 1.3916 | 8.5050 | 0 |
| 3.5520 | 2.0970 | 5.5693 | 0.8251 | 5.5487 | 5.6106 | 10.8564 | 1 |
| 2.7376 | 2.2001 | 5.1568 | 1.3201 | 4.9505 | 5.1155 | 10.0099 | 2 |
| 2.4757 | 1.8936 | 6.2706 | 1.1881 | 6.2235 | 6.3885 | 10.3614 | 3 |
| 2.1064 | 1.5432 | 7.4045 | 1.6832 | 7.2136 | 7.4116 | 11.1040 | 4 |
| 1.8167 | 1.3532 | 8.4866 | 2.1782 | 8.4158 | 8.6987 | 11.5644 | 5 |
| 1.6032 | 1.1789 | 8.6987 | 2.1782 | 8.4866 | 8.6987 | 11.8267 | 6 |
| 1.4351 | 1.1083 | 8.6987 | 2.1782 | 8.4866 | 8.6987 | 11.9059 | 7 |
| 1.3021 | 1.0607 | 8.9109 | 2.3762 | 8.8048 | 8.9816 | 11.9604 | 8 |
| 1.2060 | 1.0120 | 8.9109 | 2.3762 | 8.8048 | 8.9816 | 11.9455 | 9 |
| 1.1182 | 0.9736 | 8.6987 | 1.8812 | 8.6987 | 8.7694 | 11.9703 | 10 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2