distilbert-base-uncased-finetuned-adl_hw1
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3776
- Macro F1: 0.2959
- Micro F1: 0.3948
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Micro F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 169 | 0.4358 | 0.0564 | 0.0375 |
| No log | 2.0 | 338 | 0.4235 | 0.0815 | 0.0732 |
| 0.4295 | 3.0 | 507 | 0.3946 | 0.2038 | 0.3030 |
| 0.4295 | 4.0 | 676 | 0.3826 | 0.2612 | 0.3687 |
| 0.4295 | 5.0 | 845 | 0.3776 | 0.2959 | 0.3948 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1