my_awesome_model_3
This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0954
- Accuracy: 0.9680
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.09 | 200 | 0.2369 | 0.9040 |
| No log | 0.19 | 400 | 0.1859 | 0.9324 |
| 0.2931 | 0.28 | 600 | 0.1624 | 0.9442 |
| 0.2931 | 0.38 | 800 | 0.1194 | 0.9569 |
| 0.1456 | 0.47 | 1000 | 0.1245 | 0.9588 |
| 0.1456 | 0.57 | 1200 | 0.1044 | 0.9617 |
| 0.1456 | 0.66 | 1400 | 0.1063 | 0.9611 |
| 0.1194 | 0.75 | 1600 | 0.1021 | 0.9634 |
| 0.1194 | 0.85 | 1800 | 0.1618 | 0.9490 |
| 0.1107 | 0.94 | 2000 | 0.1113 | 0.9643 |
| 0.1107 | 1.04 | 2200 | 0.1163 | 0.9630 |
| 0.1107 | 1.13 | 2400 | 0.0954 | 0.9680 |
| 0.079 | 1.22 | 2600 | 0.1272 | 0.9635 |
| 0.079 | 1.32 | 2800 | 0.0976 | 0.9657 |
| 0.0715 | 1.41 | 3000 | 0.0995 | 0.9680 |
| 0.0715 | 1.51 | 3200 | 0.0996 | 0.9660 |
| 0.0715 | 1.6 | 3400 | 0.1001 | 0.9670 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2