CS221-distilbert-base-uncased-finetuned-semeval
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4379
- F1: 0.7152
- Roc Auc: 0.7863
- Accuracy: 0.4134
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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.5098 | 1.0 | 139 | 0.5033 | 0.5340 | 0.6705 | 0.2022 |
| 0.4132 | 2.0 | 278 | 0.4283 | 0.6646 | 0.7497 | 0.3773 |
| 0.3129 | 3.0 | 417 | 0.4051 | 0.7099 | 0.7818 | 0.4025 |
| 0.2507 | 4.0 | 556 | 0.4146 | 0.7072 | 0.7795 | 0.3935 |
| 0.16 | 5.0 | 695 | 0.4379 | 0.7152 | 0.7863 | 0.4134 |
| 0.1069 | 6.0 | 834 | 0.4643 | 0.7140 | 0.7845 | 0.4079 |
| 0.0873 | 7.0 | 973 | 0.5064 | 0.7060 | 0.7784 | 0.4025 |
| 0.0581 | 8.0 | 1112 | 0.5336 | 0.7119 | 0.7828 | 0.4206 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0