metadata
license: mit
base_model: VietAI/vit5-large
tags:
- generated_from_trainer
model-index:
- name: pretrain-vit5-large
results: []
pretrain-vit5-large
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: 4.0415
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
7.9301 | 0.51 | 20 | 5.5874 |
4.5762 | 1.03 | 40 | 4.2359 |
4.1575 | 1.54 | 60 | 4.1457 |
3.9223 | 2.05 | 80 | 4.0708 |
3.9971 | 2.56 | 100 | 4.0415 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3