metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-NER
results: []
datasets:
- conll2003
language:
- en
pipeline_tag: token-classification
distilbert-NER
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: 0.0649
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.9838
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: 64
- eval_batch_size: 32
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0.91 | 200 | 0.0681 | 0.0 | 0.0 | 0.0 | 0.9805 |
| No log | 1.82 | 400 | 0.0599 | 0.0 | 0.0 | 0.0 | 0.9827 |
| 0.1171 | 2.73 | 600 | 0.0641 | 0.0 | 0.0 | 0.0 | 0.9834 |
| 0.1171 | 3.64 | 800 | 0.0652 | 0.0 | 0.0 | 0.0 | 0.9843 |
| 0.0177 | 4.55 | 1000 | 0.0649 | 0.0 | 0.0 | 0.0 | 0.9838 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2