metadata
license: apache-2.0
base_model: pakawadeep/mt5-base-finetuned-ctfl
tags:
- generated_from_keras_callback
model-index:
- name: pakawadeep/mt5-base-finetuned-ctfl
results: []
pakawadeep/mt5-base-finetuned-ctfl
This model is a fine-tuned version of pakawadeep/mt5-base-finetuned-ctfl on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.7190
- Validation Loss: 0.9805
- Train Rouge1: 8.4866
- Train Rouge2: 2.1782
- Train Rougel: 8.2744
- Train Rougelsum: 8.2744
- Train Gen Len: 11.9208
- Epoch: 6
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 |
---|---|---|---|---|---|---|---|
1.1067 | 1.0353 | 7.4965 | 1.6832 | 7.4257 | 7.3904 | 11.8762 | 0 |
0.9573 | 1.0010 | 7.9915 | 1.6832 | 7.9208 | 7.7793 | 11.9109 | 1 |
0.8858 | 1.0002 | 8.4866 | 2.1782 | 8.2744 | 8.2744 | 11.9158 | 2 |
0.8402 | 0.9827 | 8.4866 | 2.1782 | 8.2744 | 8.2744 | 11.9554 | 3 |
0.7900 | 0.9961 | 8.4866 | 2.1782 | 8.2744 | 8.2744 | 11.9158 | 4 |
0.7646 | 0.9898 | 8.4866 | 2.1782 | 8.2744 | 8.2744 | 11.9505 | 5 |
0.7190 | 0.9805 | 8.4866 | 2.1782 | 8.2744 | 8.2744 | 11.9208 | 6 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2