metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner
results: []
distilbert-base-uncased-finetuned-ner
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: 0.0622
- Precision: 0.9250
- Recall: 0.9367
- F1: 0.9308
- Accuracy: 0.9834
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 |
|---|---|---|---|---|---|---|---|
| 0.2446 | 1.0 | 878 | 0.0727 | 0.8940 | 0.9136 | 0.9037 | 0.9786 |
| 0.0514 | 2.0 | 1756 | 0.0604 | 0.9223 | 0.9331 | 0.9277 | 0.9829 |
| 0.0312 | 3.0 | 2634 | 0.0622 | 0.9250 | 0.9367 | 0.9308 | 0.9834 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.0+cu118
- Datasets 2.19.1
- Tokenizers 0.15.2