metadata
base_model: vinai/bartpho-word-base
tags:
- generated_from_trainer
model-index:
- name: bartpho-word-base-ed-with-tpl
results: []
bartpho-word-base-ed-with-tpl
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: 0.0290
- F1 Micro: 0.8028
- Recall Micro: 0.7998
- Precision Micro: 0.8058
- F1 Macro: 0.5871
- Recall Macro: 0.6278
- Precision Macro: 0.5995
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: 5
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 | 0.0357 | 0.8039 | 0.8063 | 0.8016 | 0.5247 | 0.4945 | 0.6251 |
0.0066 | 2.0 | 787 | 0.0329 | 0.7708 | 0.7553 | 0.7869 | 0.5412 | 0.5687 | 0.5780 |
0.0089 | 2.9987 | 1180 | 0.0288 | 0.7958 | 0.7919 | 0.7996 | 0.5812 | 0.6155 | 0.5868 |
0.0116 | 4.0 | 1574 | 0.0280 | 0.8018 | 0.8007 | 0.8030 | 0.5702 | 0.5968 | 0.5947 |
0.0116 | 4.9936 | 1965 | 0.0290 | 0.8028 | 0.7998 | 0.8058 | 0.5871 | 0.6278 | 0.5995 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1