<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
PhoBERT-Final_Mixed-aug_insert_synonym-1
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: 1.1893
- Accuracy: 0.7
- F1: 0.6994
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: 41
- 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 |
---|---|---|---|---|---|
0.8943 | 1.0 | 88 | 0.7593 | 0.68 | 0.6676 |
0.5876 | 2.0 | 176 | 0.7350 | 0.67 | 0.6686 |
0.4016 | 3.0 | 264 | 0.8227 | 0.7 | 0.7001 |
0.2584 | 4.0 | 352 | 0.9111 | 0.69 | 0.6856 |
0.1981 | 5.0 | 440 | 1.0283 | 0.73 | 0.7308 |
0.1335 | 6.0 | 528 | 1.1292 | 0.7 | 0.7000 |
0.087 | 7.0 | 616 | 1.1323 | 0.7 | 0.7013 |
0.0726 | 8.0 | 704 | 1.1893 | 0.7 | 0.6994 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3