metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: phobert-base-v2-finetuned-cola
results: []
phobert-base-v2-finetuned-cola
This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2267
- Matthews Correlation: 0.8593
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| No log | 1.0 | 45 | 0.3137 | 0.6724 |
| No log | 2.0 | 90 | 0.2182 | 0.8019 |
| No log | 3.0 | 135 | 0.2210 | 0.7962 |
| No log | 4.0 | 180 | 0.1678 | 0.8521 |
| No log | 5.0 | 225 | 0.1886 | 0.8420 |
| No log | 6.0 | 270 | 0.1851 | 0.8560 |
| No log | 7.0 | 315 | 0.2300 | 0.8356 |
| No log | 8.0 | 360 | 0.2267 | 0.8593 |
| No log | 9.0 | 405 | 0.2221 | 0.8583 |
| No log | 10.0 | 450 | 0.2767 | 0.8153 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2