metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: MyBERT
results: []
MyBERT
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4607
- Accuracy: 0.8597
- F1: 0.8596
- Precision: 0.8602
- Recall: 0.8597
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5404 | 1.0 | 2573 | 0.5438 | 0.8028 | 0.8032 | 0.8142 | 0.8028 |
| 0.322 | 2.0 | 5146 | 0.4764 | 0.8391 | 0.8391 | 0.8440 | 0.8391 |
| 0.2292 | 3.0 | 7719 | 0.4607 | 0.8597 | 0.8596 | 0.8602 | 0.8597 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4