bert-finetuned-sem_eval-english
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2105
- F1: 0.7156
- Roc Auc: 0.8116
- Accuracy: 0.6051
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
No log | 1.0 | 98 | 0.2581 | 0.5504 | 0.7059 | 0.4462 |
No log | 2.0 | 196 | 0.2321 | 0.6514 | 0.7642 | 0.4974 |
No log | 3.0 | 294 | 0.2166 | 0.6781 | 0.7843 | 0.5333 |
No log | 4.0 | 392 | 0.2166 | 0.6635 | 0.7858 | 0.5385 |
No log | 5.0 | 490 | 0.2128 | 0.6890 | 0.7955 | 0.5795 |
0.202 | 6.0 | 588 | 0.2122 | 0.6744 | 0.7941 | 0.5590 |
0.202 | 7.0 | 686 | 0.2105 | 0.7156 | 0.8116 | 0.6051 |
0.202 | 8.0 | 784 | 0.2163 | 0.6946 | 0.8043 | 0.5846 |
0.202 | 9.0 | 882 | 0.2162 | 0.6869 | 0.7997 | 0.5692 |
0.202 | 10.0 | 980 | 0.2180 | 0.6837 | 0.7990 | 0.5692 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4