distilbert_finetuned
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: 0.5219
- Accuracy: 0.7358
- F1: 0.7562
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: 9.426559053989038e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 10
- 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 | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 122 | 0.5219 | 0.7358 | 0.7562 |
No log | 2.0 | 244 | 0.5235 | 0.7513 | 0.7400 |
No log | 3.0 | 366 | 0.7853 | 0.7193 | 0.6691 |
No log | 4.0 | 488 | 0.9671 | 0.7245 | 0.7030 |
0.332 | 5.0 | 610 | 1.1997 | 0.7172 | 0.7128 |
0.332 | 6.0 | 732 | 1.3708 | 0.7245 | 0.7245 |
0.332 | 7.0 | 854 | 1.5733 | 0.7234 | 0.7118 |
0.332 | 8.0 | 976 | 1.7145 | 0.7245 | 0.7056 |
0.0365 | 9.0 | 1098 | 1.7506 | 0.7307 | 0.7172 |
0.0365 | 10.0 | 1220 | 1.8002 | 0.7245 | 0.7107 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 5