<!-- 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_SST2_finetune
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3630
- Accuracy: 0.8372
- F1: 0.8371
- Precision: 0.8373
- Recall: 0.8372
- Learning Rate: 0.0000
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | Precision | Recall | Rate |
---|---|---|---|---|---|---|---|---|
0.4616 | 1.0 | 8419 | 0.3845 | 0.8337 | 0.8334 | 0.8350 | 0.8337 | 0.0000 |
0.3644 | 2.0 | 16838 | 0.3730 | 0.8291 | 0.8291 | 0.8300 | 0.8291 | 0.0000 |
0.3526 | 3.0 | 25257 | 0.3661 | 0.8280 | 0.8277 | 0.8290 | 0.8280 | 0.0000 |
0.346 | 4.0 | 33676 | 0.3709 | 0.8349 | 0.8345 | 0.8369 | 0.8349 | 0.0000 |
0.3436 | 5.0 | 42095 | 0.3674 | 0.8383 | 0.8383 | 0.8384 | 0.8383 | 0.0000 |
0.3412 | 6.0 | 50514 | 0.3630 | 0.8372 | 0.8371 | 0.8373 | 0.8372 | 0.0000 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3