cs221-bert-base-uncased-finetuned
This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3845
- F1: 0.7493
- Roc Auc: 0.8124
- Accuracy: 0.4224
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.5633 | 1.0 | 70 | 0.5647 | 0.4607 | 0.6281 | 0.1516 |
| 0.4272 | 2.0 | 140 | 0.4229 | 0.6798 | 0.7598 | 0.3484 |
| 0.3367 | 3.0 | 210 | 0.3808 | 0.7315 | 0.7980 | 0.4061 |
| 0.257 | 4.0 | 280 | 0.3716 | 0.7353 | 0.8001 | 0.4188 |
| 0.1934 | 5.0 | 350 | 0.3845 | 0.7493 | 0.8124 | 0.4224 |
| 0.1511 | 6.0 | 420 | 0.3917 | 0.7425 | 0.8063 | 0.4242 |
| 0.1056 | 7.0 | 490 | 0.4091 | 0.7338 | 0.7981 | 0.4368 |
| 0.0816 | 8.0 | 560 | 0.4206 | 0.7463 | 0.8093 | 0.4513 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.21.0