metadata
library_name: transformers
license: agpl-3.0
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: phobert_45k_boduoi_test10k
results: []
phobert_45k_boduoi_test10k
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: 0.4654
- Accuracy: 0.8876
- F1: 0.8882
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3644 | 1.0 | 1407 | 0.2934 | 0.8707 | 0.8722 |
| 0.2799 | 2.0 | 2814 | 0.2776 | 0.8774 | 0.8792 |
| 0.2362 | 3.0 | 4221 | 0.2986 | 0.8839 | 0.8854 |
| 0.1977 | 4.0 | 5628 | 0.3291 | 0.8893 | 0.8890 |
| 0.1665 | 5.0 | 7035 | 0.3141 | 0.8903 | 0.8906 |
| 0.1363 | 6.0 | 8442 | 0.3616 | 0.8892 | 0.8898 |
| 0.1146 | 7.0 | 9849 | 0.3969 | 0.8887 | 0.8888 |
| 0.1016 | 8.0 | 11256 | 0.4377 | 0.8890 | 0.8896 |
| 0.0906 | 9.0 | 12663 | 0.4637 | 0.8875 | 0.8882 |
| 0.0819 | 10.0 | 14070 | 0.4654 | 0.8876 | 0.8882 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1