metadata
library_name: transformers
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: 0.2326
- Precision: 0.4345
- Recall: 0.6512
- F1: 0.5212
- Accuracy: 0.9357
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 63 | 0.4595 | 0.2973 | 0.0226 | 0.0421 | 0.9067 |
| No log | 2.0 | 126 | 0.2294 | 0.4714 | 0.5936 | 0.5255 | 0.9403 |
| No log | 3.0 | 189 | 0.2326 | 0.4345 | 0.6512 | 0.5212 | 0.9357 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.2.2
- Datasets 3.1.0
- Tokenizers 0.20.3