metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results: []
bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7190
- Precision: 0.4554
- Recall: 0.5226
- F1: 0.4867
- Accuracy: 0.7739
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 51 | 1.0096 | 0.2965 | 0.0405 | 0.0713 | 0.7110 |
No log | 2.0 | 102 | 0.8495 | 0.3573 | 0.2883 | 0.3191 | 0.7415 |
No log | 3.0 | 153 | 0.7566 | 0.4296 | 0.5187 | 0.4700 | 0.7663 |
No log | 4.0 | 204 | 0.7221 | 0.4573 | 0.4718 | 0.4644 | 0.7706 |
No log | 5.0 | 255 | 0.7190 | 0.4554 | 0.5226 | 0.4867 | 0.7739 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1