metadata
base_model: vinai/bartpho-word-base
tags:
- generated_from_trainer
model-index:
- name: bartpho-word-base-ed-with-tpl-ed-tpl-v3
results: []
bartpho-word-base-ed-with-tpl-ed-tpl-v3
This model is a fine-tuned version of vinai/bartpho-word-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0267
- F1 Micro: 0.8050
- Recall Micro: 0.8024
- Precision Micro: 0.8075
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 | F1 Micro | Recall Micro | Precision Micro |
|---|---|---|---|---|---|---|
| No log | 0.9987 | 393 | 0.0270 | 0.7861 | 0.7727 | 0.8000 |
| 0.0654 | 2.0 | 787 | 0.0262 | 0.7755 | 0.7798 | 0.7713 |
| 0.0247 | 2.9987 | 1180 | 0.0246 | 0.7892 | 0.7816 | 0.7969 |
| 0.0197 | 4.0 | 1574 | 0.0233 | 0.8078 | 0.7949 | 0.8210 |
| 0.0197 | 4.9987 | 1967 | 0.0235 | 0.8064 | 0.8018 | 0.8110 |
| 0.016 | 6.0 | 2361 | 0.0262 | 0.8027 | 0.7951 | 0.8104 |
| 0.0123 | 6.9987 | 2754 | 0.0261 | 0.8080 | 0.8067 | 0.8093 |
| 0.0102 | 7.9898 | 3144 | 0.0267 | 0.8050 | 0.8024 | 0.8075 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1