results_v3
This model is a fine-tuned version of vinai/phobert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0940
- Accuracy: 0.6
- F1: 0.6089
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 20 | 0.8388 | 0.675 | 0.6324 |
| No log | 2.0 | 40 | 0.9717 | 0.55 | 0.5431 |
| No log | 3.0 | 60 | 0.9652 | 0.65 | 0.6324 |
| No log | 4.0 | 80 | 0.9685 | 0.575 | 0.5842 |
| No log | 5.0 | 100 | 0.9198 | 0.675 | 0.6660 |
| No log | 6.0 | 120 | 1.1792 | 0.525 | 0.5320 |
| No log | 7.0 | 140 | 1.0582 | 0.65 | 0.6494 |
| No log | 8.0 | 160 | 1.0988 | 0.575 | 0.5902 |
| No log | 9.0 | 180 | 1.0824 | 0.6 | 0.6049 |
| No log | 10.0 | 200 | 1.0940 | 0.6 | 0.6089 |
Framework versions
- Transformers 5.22.1
- Pytorch 2.14.1+cu130
- Datasets 2.20.0
- Tokenizers 0.23.3