distilbert-base-uncased-finetuned-pad-clf
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: 0.1289
- Accuracy: 0.975
- F1: 0.9749
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: 256
- eval_batch_size: 256
- 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 | F1 |
---|---|---|---|---|---|
No log | 1.0 | 4 | 0.6435 | 0.6083 | 0.5142 |
No log | 2.0 | 8 | 0.5480 | 0.9083 | 0.9081 |
No log | 3.0 | 12 | 0.4297 | 0.9417 | 0.9417 |
0.5756 | 4.0 | 16 | 0.3197 | 0.9667 | 0.9666 |
0.5756 | 5.0 | 20 | 0.2381 | 0.9667 | 0.9665 |
0.5756 | 6.0 | 24 | 0.1897 | 0.975 | 0.9749 |
0.5756 | 7.0 | 28 | 0.1611 | 0.975 | 0.9749 |
0.2307 | 8.0 | 32 | 0.1431 | 0.975 | 0.9749 |
0.2307 | 9.0 | 36 | 0.1328 | 0.975 | 0.9749 |
0.2307 | 10.0 | 40 | 0.1289 | 0.975 | 0.9749 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 3