<!-- 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-base-uncased-finetuned-sst2
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.2982
- Accuracy: 0.9323
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 |
|---|---|---|---|---|
| 0.1817 | 1.0 | 4210 | 0.2920 | 0.9186 |
| 0.1297 | 2.0 | 8420 | 0.3069 | 0.9209 |
| 0.0978 | 3.0 | 12630 | 0.2982 | 0.9323 |
| 0.062 | 4.0 | 16840 | 0.3278 | 0.9312 |
| 0.0303 | 5.0 | 21050 | 0.3642 | 0.9323 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0
- Datasets 2.2.2
- Tokenizers 0.12.1
