outputs
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: 0.6401
- Precision: 0.8329
- Recall: 0.8329
- F1: 0.8326
- Accuracy: 0.8329
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.7876 | 1.0 | 3267 | 0.7410 | 0.8115 | 0.8067 | 0.8065 | 0.8067 |
| 0.5802 | 2.0 | 6534 | 0.6335 | 0.8323 | 0.8304 | 0.8305 | 0.8304 |
| 0.408 | 3.0 | 9801 | 0.6401 | 0.8329 | 0.8329 | 0.8326 | 0.8329 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0