metadata
license: mit
base_model: VietAI/vit5-large
tags:
- generated_from_trainer
model-index:
- name: KLTN_COQE_viT5_PAOSL_v4
results: []
KLTN_COQE_viT5_PAOSL_v4
This model is a fine-tuned version of VietAI/vit5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0033
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:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2831 | 1.98 | 200 | 0.1297 |
| 0.1433 | 3.96 | 400 | 0.0509 |
| 0.0558 | 5.94 | 600 | 0.0209 |
| 0.0259 | 7.92 | 800 | 0.0072 |
| 0.0101 | 9.9 | 1000 | 0.0033 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1