<!-- 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-ag
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5233
- Accuracy: 0.1520
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-06
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 290 | 0.4902 | 0.2435 |
| 0.379 | 2.0 | 580 | 0.4798 | 0.2176 |
| 0.379 | 3.0 | 870 | 0.4815 | 0.1986 |
| 0.3232 | 4.0 | 1160 | 0.5008 | 0.1675 |
| 0.3232 | 5.0 | 1450 | 0.5090 | 0.1727 |
| 0.295 | 6.0 | 1740 | 0.5092 | 0.1762 |
| 0.2697 | 7.0 | 2030 | 0.5164 | 0.1641 |
| 0.2697 | 8.0 | 2320 | 0.5151 | 0.1589 |
| 0.2597 | 9.0 | 2610 | 0.5210 | 0.1572 |
| 0.2597 | 10.0 | 2900 | 0.5233 | 0.1520 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
