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: ner_checkpoints
results: []
ner_checkpoints
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: 0.1307
- Precision: 0.9077
- Recall: 0.9222
- F1: 0.9149
- Accuracy: 0.9833
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0429 | 1.0 | 878 | 0.0399 | 0.9270 | 0.9368 | 0.9319 | 0.9890 |
| 0.0186 | 2.0 | 1756 | 0.0402 | 0.9458 | 0.9501 | 0.9480 | 0.9910 |
| 0.0094 | 3.0 | 2634 | 0.0386 | 0.9500 | 0.9537 | 0.9518 | 0.9916 |
| 0.0036 | 4.0 | 3512 | 0.0392 | 0.9491 | 0.9549 | 0.9520 | 0.9917 |
| 0.0018 | 5.0 | 4390 | 0.0393 | 0.9503 | 0.9565 | 0.9534 | 0.9918 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2