<!-- 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. -->
bert_Pfinal_4CLASES_2e-5_16_10
This model is a fine-tuned version of fredymad/bert_Pfinal_4CLASES_2e-5_16_2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9126
- Accuracy: 0.8960
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1814 | 1.0 | 669 | 0.4063 | 0.8960 |
| 0.1821 | 2.0 | 1338 | 0.4814 | 0.8904 |
| 0.1029 | 3.0 | 2007 | 0.5948 | 0.8968 |
| 0.0545 | 4.0 | 2676 | 0.6543 | 0.8949 |
| 0.038 | 5.0 | 3345 | 0.7463 | 0.8953 |
| 0.0122 | 6.0 | 4014 | 0.8268 | 0.8968 |
| 0.0137 | 7.0 | 4683 | 0.8442 | 0.8964 |
| 0.0061 | 8.0 | 5352 | 0.8852 | 0.8953 |
| 0.0073 | 9.0 | 6021 | 0.9132 | 0.8957 |
| 0.002 | 10.0 | 6690 | 0.9126 | 0.8960 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
