metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
- wer
model-index:
- name: bert-finetuned-ner-tokenizer
results: []
bert-finetuned-ner-tokenizer
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0280
- Precision: 0.7896
- Recall: 0.8536
- F1: 0.8203
- Accuracy: 0.9919
- Wer: 0.0079
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Wer |
|---|---|---|---|---|---|---|---|---|
| 0.0515 | 1.0 | 768 | 0.0273 | 0.7510 | 0.8495 | 0.7972 | 0.9907 | 0.0089 |
| 0.0192 | 2.0 | 1536 | 0.0259 | 0.7567 | 0.8627 | 0.8062 | 0.9911 | 0.0086 |
| 0.0158 | 3.0 | 2304 | 0.0259 | 0.7828 | 0.8565 | 0.8180 | 0.9916 | 0.0082 |
| 0.0111 | 4.0 | 3072 | 0.0280 | 0.7896 | 0.8536 | 0.8203 | 0.9919 | 0.0079 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1