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_55k_boduoi_test14k
results: []
phobert_55k_boduoi_test14k
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: 0.9433
- Accuracy: 0.8078
- F1: 0.8537
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 |
|---|---|---|---|---|---|
| 0.3601 | 1.0 | 1725 | 0.7095 | 0.7082 | 0.7864 |
| 0.2727 | 2.0 | 3450 | 0.6126 | 0.7577 | 0.8202 |
| 0.229 | 3.0 | 5175 | 0.7614 | 0.7444 | 0.8116 |
| 0.1946 | 4.0 | 6900 | 0.6227 | 0.7929 | 0.8439 |
| 0.1633 | 5.0 | 8625 | 0.7921 | 0.7551 | 0.8190 |
| 0.1378 | 6.0 | 10350 | 0.7906 | 0.7750 | 0.8323 |
| 0.1161 | 7.0 | 12075 | 0.8249 | 0.7990 | 0.8480 |
| 0.1 | 8.0 | 13800 | 0.8345 | 0.8257 | 0.8652 |
| 0.0917 | 9.0 | 15525 | 0.8945 | 0.8113 | 0.8560 |
| 0.0852 | 10.0 | 17250 | 0.9433 | 0.8078 | 0.8537 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1