results
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5475
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.6338 | 0.07 | 100 | 0.5837 |
0.5848 | 0.14 | 200 | 0.5759 |
0.5692 | 0.21 | 300 | 0.5717 |
0.5649 | 0.28 | 400 | 0.5683 |
0.5585 | 0.35 | 500 | 0.5711 |
0.5658 | 0.41 | 600 | 0.5678 |
0.5639 | 0.48 | 700 | 0.5551 |
0.5579 | 0.55 | 800 | 0.5652 |
0.5641 | 0.62 | 900 | 0.5569 |
0.5574 | 0.69 | 1000 | 0.5562 |
0.5487 | 0.76 | 1100 | 0.5595 |
0.5547 | 0.83 | 1200 | 0.5536 |
0.5719 | 0.9 | 1300 | 0.5498 |
0.57 | 0.97 | 1400 | 0.5493 |
0.5451 | 1.04 | 1500 | 0.5536 |
0.537 | 1.1 | 1600 | 0.5502 |
0.5524 | 1.17 | 1700 | 0.5510 |
0.5397 | 1.24 | 1800 | 0.5502 |
0.538 | 1.31 | 1900 | 0.5476 |
0.5341 | 1.38 | 2000 | 0.5475 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Tokenizers 0.15.2
- Downloads last month
- 10