experiment_2
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1211
- Precision: 0.8841
- Recall: 0.8926
- F1: 0.8883
- Accuracy: 0.9747
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2418 | 1.0 | 878 | 0.0695 | 0.9159 | 0.9255 | 0.9207 | 0.9816 |
0.0541 | 2.0 | 1756 | 0.0592 | 0.9244 | 0.9343 | 0.9293 | 0.9833 |
0.0303 | 3.0 | 2634 | 0.0602 | 0.9260 | 0.9388 | 0.9323 | 0.9838 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.11.0+cpu
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 14
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Dataset used to train sophiestein/experiment_2
Evaluation results
- Precision on conll2003self-reported0.884
- Recall on conll2003self-reported0.893
- F1 on conll2003self-reported0.888
- Accuracy on conll2003self-reported0.975