<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
mellange
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0700
- Precision: 0.6033
- Recall: 0.7430
- F1: 0.6659
- Accuracy: 0.9774
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: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 20 | 0.1842 | 0.0 | 0.0 | 0.0 | 0.9406 |
| No log | 2.0 | 40 | 0.0925 | 0.3797 | 0.4377 | 0.4066 | 0.9670 |
| No log | 3.0 | 60 | 0.0700 | 0.5085 | 0.6107 | 0.5549 | 0.9756 |
| No log | 4.0 | 80 | 0.0775 | 0.4908 | 0.7506 | 0.5936 | 0.9703 |
| No log | 5.0 | 100 | 0.0649 | 0.6110 | 0.7074 | 0.6557 | 0.9781 |
| No log | 6.0 | 120 | 0.0688 | 0.5784 | 0.7226 | 0.6425 | 0.9769 |
| No log | 7.0 | 140 | 0.0708 | 0.5612 | 0.7583 | 0.6450 | 0.9759 |
| No log | 8.0 | 160 | 0.0701 | 0.5796 | 0.7506 | 0.6541 | 0.9768 |
| No log | 9.0 | 180 | 0.0700 | 0.6033 | 0.7430 | 0.6659 | 0.9774 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.11.0
- Datasets 2.13.1
- Tokenizers 0.13.3
