<!-- 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. -->
distilbert-base-uncased-PINA-dfnew
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2599
- Accuracy: 0.9510
- Precision: 0.8737
- Recall: 0.8532
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 | Precision | Recall |
---|---|---|---|---|---|---|
1.1798 | 1.0 | 1438 | 0.4320 | 0.9016 | 0.7777 | 0.7182 |
0.2987 | 2.0 | 2876 | 0.2779 | 0.9369 | 0.8340 | 0.8270 |
0.1579 | 3.0 | 4314 | 0.2608 | 0.9445 | 0.8374 | 0.8378 |
0.0913 | 4.0 | 5752 | 0.2599 | 0.9510 | 0.8737 | 0.8532 |
0.0547 | 5.0 | 7190 | 0.2716 | 0.9531 | 0.8893 | 0.8682 |
0.0309 | 6.0 | 8628 | 0.2748 | 0.9531 | 0.8921 | 0.8750 |
0.0174 | 7.0 | 10066 | 0.2860 | 0.9545 | 0.8966 | 0.8710 |
0.01 | 8.0 | 11504 | 0.2972 | 0.9543 | 0.9087 | 0.8989 |
0.0063 | 9.0 | 12942 | 0.3012 | 0.9536 | 0.9066 | 0.8967 |
0.0044 | 10.0 | 14380 | 0.2978 | 0.9551 | 0.9108 | 0.8997 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3