metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: results
results: []
results
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: 0.0488
- Accuracy: 0.8207
- Precision: 0.9268
- Recall: 0.8840
- F1: 0.9030
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0242 | 0.9971 | 173 | 0.0552 | 0.8452 | 0.8964 | 0.8905 | 0.8883 |
| 0.0298 | 2.0 | 347 | 0.0488 | 0.8207 | 0.9268 | 0.8840 | 0.9030 |
| 0.0236 | 2.9971 | 520 | 0.0484 | 0.8214 | 0.9338 | 0.8680 | 0.8971 |
| 0.0298 | 4.0 | 694 | 0.0498 | 0.8251 | 0.9357 | 0.8719 | 0.9004 |
| 0.0232 | 4.9971 | 867 | 0.0477 | 0.8281 | 0.9381 | 0.8732 | 0.9020 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1