cs221-roberta-large-finetuned-40-epochs
This model is a fine-tuned version of Kuongan/CS221-roberta-large-finetuned-semeval on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1118
- F1: 0.9456
- Roc Auc: 0.9577
- Accuracy: 0.8755
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: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.128 | 1.0 | 70 | 0.1118 | 0.9456 | 0.9577 | 0.8755 |
| 0.0949 | 2.0 | 140 | 0.1189 | 0.9409 | 0.9535 | 0.8592 |
| 0.0537 | 3.0 | 210 | 0.1296 | 0.9412 | 0.9529 | 0.8610 |
| 0.038 | 4.0 | 280 | 0.1405 | 0.9375 | 0.9510 | 0.8574 |
| 0.0485 | 5.0 | 350 | 0.1521 | 0.9364 | 0.9523 | 0.8538 |
| 0.0313 | 6.0 | 420 | 0.1455 | 0.9444 | 0.9586 | 0.8664 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0