distilbert_sst5_padding0model
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: 4.1295
- Accuracy: 0.5018
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2692 | 1.0 | 534 | 1.2088 | 0.4462 |
| 1.0128 | 2.0 | 1068 | 1.1091 | 0.5299 |
| 0.8129 | 3.0 | 1602 | 1.1930 | 0.5262 |
| 0.6431 | 4.0 | 2136 | 1.3783 | 0.5213 |
| 0.4776 | 5.0 | 2670 | 1.7332 | 0.4783 |
| 0.3481 | 6.0 | 3204 | 1.7883 | 0.5140 |
| 0.2633 | 7.0 | 3738 | 2.1206 | 0.4955 |
| 0.191 | 8.0 | 4272 | 2.3658 | 0.5054 |
| 0.1627 | 9.0 | 4806 | 2.6203 | 0.5149 |
| 0.1387 | 10.0 | 5340 | 3.0193 | 0.4955 |
| 0.1049 | 11.0 | 5874 | 3.3081 | 0.5014 |
| 0.0888 | 12.0 | 6408 | 3.5941 | 0.4959 |
| 0.0689 | 13.0 | 6942 | 3.6559 | 0.5095 |
| 0.0615 | 14.0 | 7476 | 3.7450 | 0.5090 |
| 0.0426 | 15.0 | 8010 | 3.9371 | 0.5032 |
| 0.0372 | 16.0 | 8544 | 4.0202 | 0.5086 |
| 0.0255 | 17.0 | 9078 | 4.1399 | 0.4982 |
| 0.0221 | 18.0 | 9612 | 4.1091 | 0.5045 |
| 0.0237 | 19.0 | 10146 | 4.1077 | 0.5009 |
| 0.0206 | 20.0 | 10680 | 4.1295 | 0.5018 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3