metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-aug_replace_synonym-train
results: []
PhoBERT-aug_replace_synonym-train
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: 0.8485
- Accuracy: 0.72
- F1: 0.7286
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0028 | 1.0 | 44 | 0.7954 | 0.74 | 0.7308 |
| 0.6793 | 2.0 | 88 | 0.6225 | 0.73 | 0.7309 |
| 0.512 | 3.0 | 132 | 0.6529 | 0.75 | 0.7527 |
| 0.4119 | 4.0 | 176 | 0.7080 | 0.73 | 0.7264 |
| 0.3267 | 5.0 | 220 | 0.7347 | 0.72 | 0.7309 |
| 0.2618 | 6.0 | 264 | 0.8040 | 0.73 | 0.7398 |
| 0.2485 | 7.0 | 308 | 0.8175 | 0.73 | 0.7389 |
| 0.2287 | 8.0 | 352 | 0.8485 | 0.72 | 0.7286 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3