metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-large-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: CS221-bert-large-uncased-finetuned-semeval
results: []
CS221-bert-large-uncased-finetuned-semeval
This model is a fine-tuned version of google-bert/bert-large-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3493
- F1: 0.7668
- Roc Auc: 0.8210
- Accuracy: 0.4765
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 |
|---|---|---|---|---|---|---|
| 0.55 | 1.0 | 70 | 0.5378 | 0.4156 | 0.6228 | 0.1625 |
| 0.3931 | 2.0 | 140 | 0.4018 | 0.6857 | 0.7636 | 0.3989 |
| 0.2768 | 3.0 | 210 | 0.3776 | 0.7337 | 0.7972 | 0.4422 |
| 0.2033 | 4.0 | 280 | 0.3493 | 0.7668 | 0.8210 | 0.4765 |
| 0.1157 | 5.0 | 350 | 0.3954 | 0.7648 | 0.8254 | 0.4675 |
| 0.0746 | 6.0 | 420 | 0.4089 | 0.7660 | 0.8235 | 0.4747 |
| 0.0539 | 7.0 | 490 | 0.4444 | 0.7597 | 0.8170 | 0.4567 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0