metadata
license: mit
base_model: vinai/phobert-base
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of vinai/phobert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7735
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 347 | 1.2051 |
| 1.3864 | 2.0 | 694 | 1.1012 |
| 0.8986 | 3.0 | 1041 | 1.0558 |
| 0.8986 | 4.0 | 1388 | 1.1254 |
| 0.6019 | 5.0 | 1735 | 1.4252 |
| 0.3972 | 6.0 | 2082 | 1.5207 |
| 0.3972 | 7.0 | 2429 | 1.6013 |
| 0.2536 | 8.0 | 2776 | 1.8216 |
| 0.1597 | 9.0 | 3123 | 2.0175 |
| 0.1597 | 10.0 | 3470 | 2.0884 |
| 0.1262 | 11.0 | 3817 | 2.3397 |
| 0.0789 | 12.0 | 4164 | 2.4385 |
| 0.0545 | 13.0 | 4511 | 2.5664 |
| 0.0545 | 14.0 | 4858 | 2.6797 |
| 0.0312 | 15.0 | 5205 | 2.7723 |
| 0.032 | 16.0 | 5552 | 2.8236 |
| 0.032 | 17.0 | 5899 | 2.7557 |
| 0.0237 | 18.0 | 6246 | 2.8256 |
| 0.0157 | 19.0 | 6593 | 2.8168 |
| 0.0157 | 20.0 | 6940 | 2.8602 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.4.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2