metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_keras_callback
model-index:
- name: j-gc/T5-BASE_Model_News_Summarization
results: []
j-gc/T5-BASE_Model_News_Summarization
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.4340
- Validation Loss: 1.2628
- Train Lr: 2e-05
- Epoch: 3
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 Lr | Epoch |
|---|---|---|---|
| 1.4772 | 1.2804 | 2e-05 | 0 |
| 1.4433 | 1.2744 | 2e-05 | 1 |
| 1.4417 | 1.2696 | 2e-05 | 2 |
| 1.4340 | 1.2628 | 2e-05 | 3 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2