metadata
license: apache-2.0
base_model: distilbert/distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-NER
results: []
bert-base-NER
This model is a fine-tuned version of distilbert/distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2957
- Precision: 0.4291
- Recall: 0.4305
- F1: 0.4298
- Accuracy: 0.9095
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 56 | 0.3666 | 0.2951 | 0.0309 | 0.0559 | 0.8777 |
| No log | 2.0 | 112 | 0.3045 | 0.4456 | 0.3791 | 0.4096 | 0.9088 |
| No log | 3.0 | 168 | 0.2957 | 0.4291 | 0.4305 | 0.4298 | 0.9095 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2