metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_without_preprocessing_grid_search
results: []
BERT_without_preprocessing_grid_search
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: 0.6213
- Precision: 0.8399
- Recall: 0.8622
- F1: 0.8498
- Accuracy: 0.8798
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 257 | 0.6305 | 0.7254 | 0.8018 | 0.7512 | 0.8180 |
| 0.8689 | 2.0 | 514 | 0.4877 | 0.8120 | 0.8500 | 0.8245 | 0.8667 |
| 0.8689 | 3.0 | 771 | 0.4490 | 0.7911 | 0.8590 | 0.8148 | 0.8599 |
| 0.2702 | 4.0 | 1028 | 0.4748 | 0.8291 | 0.8689 | 0.8457 | 0.8730 |
| 0.2702 | 5.0 | 1285 | 0.5217 | 0.8326 | 0.8543 | 0.8413 | 0.8783 |
| 0.1505 | 6.0 | 1542 | 0.5288 | 0.8351 | 0.8650 | 0.8481 | 0.8754 |
| 0.1505 | 7.0 | 1799 | 0.5801 | 0.8417 | 0.8585 | 0.8487 | 0.8769 |
| 0.092 | 8.0 | 2056 | 0.5721 | 0.8402 | 0.8694 | 0.8535 | 0.8818 |
| 0.092 | 9.0 | 2313 | 0.6135 | 0.8453 | 0.8618 | 0.8522 | 0.8808 |
| 0.0723 | 10.0 | 2570 | 0.6213 | 0.8399 | 0.8622 | 0.8498 | 0.8798 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3