dbbuc_30p
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1597
- Precision: 0.5256
- Recall: 0.5222
- F1: 0.5239
- Accuracy: 0.9675
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 267 | 0.1502 | 0.3872 | 0.3270 | 0.3546 | 0.9595 |
0.1891 | 2.0 | 534 | 0.1349 | 0.4992 | 0.4825 | 0.4907 | 0.9650 |
0.1891 | 3.0 | 801 | 0.1412 | 0.4708 | 0.5254 | 0.4966 | 0.9642 |
0.056 | 4.0 | 1068 | 0.1539 | 0.5055 | 0.5143 | 0.5098 | 0.9667 |
0.056 | 5.0 | 1335 | 0.1597 | 0.5256 | 0.5222 | 0.5239 | 0.9675 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 3