<!-- 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-finetuned-sst2
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: 0.4028
- Accuracy: 0.9083
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.188 | 1.0 | 4210 | 0.3127 | 0.9037 |
| 0.1299 | 2.0 | 8420 | 0.3887 | 0.9048 |
| 0.0845 | 3.0 | 12630 | 0.4028 | 0.9083 |
| 0.0691 | 4.0 | 16840 | 0.3924 | 0.9071 |
| 0.052 | 5.0 | 21050 | 0.5047 | 0.9002 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
