<!-- 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. -->
distilbert-base-uncased-finetuned-ft500
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: 1.1340
- Accuracy: 0.5433
- F1: 0.5118
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: 64
- eval_batch_size: 64
- 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 | Accuracy | F1 |
---|---|---|---|---|---|
1.16 | 1.0 | 188 | 1.0855 | 0.5493 | 0.4985 |
1.0291 | 2.0 | 376 | 1.0792 | 0.5587 | 0.5114 |
0.9661 | 3.0 | 564 | 1.0798 | 0.558 | 0.5267 |
0.9104 | 4.0 | 752 | 1.0935 | 0.5447 | 0.5136 |
0.8611 | 5.0 | 940 | 1.1340 | 0.5433 | 0.5118 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1