distilbert-base-uncased-finetuned-adl_hw1
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: 0.1960
- Accuracy: 0.9613
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.2188 | 1.0 | 938 | 1.5454 | 0.839 |
| 0.9831 | 2.0 | 1876 | 0.3904 | 0.9387 |
| 0.1846 | 3.0 | 2814 | 0.2134 | 0.954 |
| 0.0573 | 4.0 | 3752 | 0.1980 | 0.9553 |
| 0.0250 | 5.0 | 4690 | 0.1897 | 0.961 |
| 0.0152 | 6.0 | 5628 | 0.1960 | 0.9613 |
| 0.0106 | 7.0 | 6566 | 0.2114 | 0.9587 |
| 0.0062 | 8.0 | 7504 | 0.2186 | 0.958 |
| 0.0070 | 9.0 | 8442 | 0.2197 | 0.9593 |
| 0.0058 | 10.0 | 9380 | 0.2265 | 0.959 |
| 0.0047 | 11.0 | 10318 | 0.2355 | 0.9597 |
| 0.0025 | 12.0 | 11256 | 0.2423 | 0.9583 |
| 0.0020 | 13.0 | 12194 | 0.2365 | 0.9597 |
| 0.0005 | 14.0 | 13132 | 0.2464 | 0.9583 |
| 0.0008 | 15.0 | 14070 | 0.2444 | 0.9583 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.14.0+cu130
- Datasets 5.0.1
- Tokenizers 0.23.1