viettel-videberta-finetune-viquad-model7
This model is a fine-tuned version of Fsoft-AIC/videberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6730
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: 13
- eval_batch_size: 13
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 65
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.87 | 260 | 3.2187 |
| 3.6521 | 1.74 | 520 | 2.8990 |
| 3.6521 | 2.61 | 780 | 2.7310 |
| 2.5664 | 3.48 | 1040 | 2.6730 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3