cs221-cs221-deberta-v3-base-finetuned-finetuned-finetuned
This model is a fine-tuned version of sercetexam9/cs221-deberta-v3-base-finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4521
- F1: 0.7824
- Roc Auc: 0.8376
- Accuracy: 0.5
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: 32
- eval_batch_size: 32
- 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.1539 | 1.0 | 70 | 0.3972 | 0.7775 | 0.8364 | 0.4982 |
| 0.1227 | 2.0 | 140 | 0.4107 | 0.7719 | 0.8302 | 0.4801 |
| 0.0758 | 3.0 | 210 | 0.4207 | 0.7652 | 0.8222 | 0.4838 |
| 0.0589 | 4.0 | 280 | 0.4414 | 0.7714 | 0.8280 | 0.4910 |
| 0.047 | 5.0 | 350 | 0.4566 | 0.7789 | 0.8348 | 0.4928 |
| 0.0389 | 6.0 | 420 | 0.4521 | 0.7824 | 0.8376 | 0.5 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.21.0