metadata
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: FineTune_Vit5_LR0_00001_time2
results: []
FineTune_Vit5_LR0_00001_time2
This model is a fine-tuned version of VietAI/vit5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6803
- Validation Loss: 0.7039
- Train Rouge1: 48.5820
- Train Rouge2: 26.3291
- Train Rougel: 39.9040
- Train Rougelsum: 39.9339
- Train Gen Len: 14.1547
- Epoch: 0
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': 'Adam', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|---|---|---|---|---|---|---|---|
| 0.6803 | 0.7039 | 48.5820 | 26.3291 | 39.9040 | 39.9339 | 14.1547 | 0 |
Framework versions
- Transformers 4.26.0
- TensorFlow 2.9.2
- Datasets 2.9.0
- Tokenizers 0.13.2