distilbert-base-uncased_classification_finetuned_mobile01_all_f1max_epochmax5
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2639
- F1: 0.9144
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: 16
- eval_batch_size: 16
- 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 | F1 |
---|---|---|---|---|
0.5164 | 1.0 | 909 | 0.3926 | 0.8297 |
0.3534 | 2.0 | 1818 | 0.3137 | 0.8768 |
0.2669 | 3.0 | 2727 | 0.2672 | 0.9023 |
0.2233 | 4.0 | 3636 | 0.2643 | 0.9104 |
0.1852 | 5.0 | 4545 | 0.2639 | 0.9144 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.