metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: CS221-bert-base-uncased-finetuned-semeval-NT-sun
results: []
CS221-bert-base-uncased-finetuned-semeval-NT-sun
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4060
- F1: 0.6852
- Roc Auc: 0.7739
- Accuracy: 0.5135
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|
| 0.4264 | 1.0 | 93 | 0.4356 | 0.6154 | 0.7316 | 0.4811 |
| 0.3577 | 2.0 | 186 | 0.3867 | 0.6667 | 0.7663 | 0.4811 |
| 0.321 | 3.0 | 279 | 0.3666 | 0.6773 | 0.7702 | 0.4973 |
| 0.2953 | 4.0 | 372 | 0.3691 | 0.6698 | 0.7625 | 0.4973 |
| 0.236 | 5.0 | 465 | 0.3840 | 0.6667 | 0.7645 | 0.4757 |
| 0.2011 | 6.0 | 558 | 0.4060 | 0.6852 | 0.7739 | 0.5135 |
| 0.1135 | 7.0 | 651 | 0.4200 | 0.6711 | 0.7690 | 0.4865 |
| 0.1056 | 8.0 | 744 | 0.4691 | 0.6636 | 0.7607 | 0.4973 |
| 0.0854 | 9.0 | 837 | 0.4758 | 0.6727 | 0.7680 | 0.5027 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Tokenizers 0.21.0