metadata
license: apache-2.0
base_model: google/mt5-large
tags:
- generated_from_keras_callback
model-index:
- name: pakawadeep/mt5-large-finetuned-ctfl-augmented
results: []
pakawadeep/mt5-large-finetuned-ctfl-augmented
This model is a fine-tuned version of google/mt5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.5772
- Validation Loss: 1.1149
- Train Rouge1: 6.5064
- Train Rouge2: 1.1881
- Train Rougel: 6.7185
- Train Rougelsum: 6.7185
- Train Gen Len: 11.6485
- 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 |
|---|---|---|---|---|---|---|---|
| 7.1544 | 4.7384 | 0.2888 | 0.0 | 0.2888 | 0.2475 | 16.6436 | 0 |
| 5.1911 | 2.1738 | 1.4851 | 0.3438 | 1.5242 | 1.5572 | 12.8564 | 1 |
| 3.6169 | 1.7018 | 5.5693 | 0.5776 | 5.5281 | 5.6931 | 11.6931 | 2 |
| 2.8957 | 1.4685 | 5.8581 | 0.8251 | 5.8581 | 5.9818 | 11.0347 | 3 |
| 1.9769 | 1.2807 | 6.6832 | 1.8152 | 6.8069 | 6.8688 | 11.4505 | 4 |
| 1.5772 | 1.1149 | 6.5064 | 1.1881 | 6.7185 | 6.7185 | 11.6485 | 5 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2