metadata
base_model: vinai/bartpho-word-base
tags:
- generated_from_trainer
model-index:
- name: bartpho-word-base-ed-notpl
results: []
bartpho-word-base-ed-notpl
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: 0.0296
- F1 Micro: 0.8132
- Recall Micro: 0.8123
- Precision Micro: 0.8142
- F1 Macro: 0.5908
- Recall Macro: 0.6258
- Precision Macro: 0.5885
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | F1 Micro | Recall Micro | Precision Micro | F1 Macro | Recall Macro | Precision Macro |
---|---|---|---|---|---|---|---|---|---|
No log | 0.9987 | 393 | 0.0272 | 0.788 | 0.7979 | 0.7783 | 0.4634 | 0.4821 | 0.5358 |
0.155 | 2.0 | 787 | 0.0260 | 0.7757 | 0.7633 | 0.7885 | 0.5149 | 0.5538 | 0.5169 |
0.0248 | 2.9987 | 1180 | 0.0248 | 0.7874 | 0.7887 | 0.7861 | 0.5407 | 0.5681 | 0.5688 |
0.0197 | 4.0 | 1574 | 0.0237 | 0.8067 | 0.8191 | 0.7948 | 0.5628 | 0.5908 | 0.5900 |
0.0197 | 4.9987 | 1967 | 0.0240 | 0.8061 | 0.8049 | 0.8073 | 0.5601 | 0.5593 | 0.5880 |
0.0158 | 6.0 | 2361 | 0.0269 | 0.7982 | 0.8027 | 0.7937 | 0.5866 | 0.6815 | 0.5364 |
0.0121 | 6.9987 | 2754 | 0.0268 | 0.8132 | 0.8123 | 0.8140 | 0.5979 | 0.6077 | 0.6182 |
0.0097 | 8.0 | 3148 | 0.0279 | 0.8184 | 0.8200 | 0.8169 | 0.5908 | 0.6050 | 0.6037 |
0.0082 | 8.9987 | 3541 | 0.0288 | 0.8129 | 0.8114 | 0.8144 | 0.5895 | 0.6285 | 0.5846 |
0.0082 | 9.9873 | 3930 | 0.0296 | 0.8132 | 0.8123 | 0.8142 | 0.5908 | 0.6258 | 0.5885 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1