metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_with_preprocessing_grid_search
results: []
BERT_with_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: 0.9426
- Precision: 0.8396
- Recall: 0.8182
- F1: 0.8282
- Accuracy: 0.8655
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: 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 |
|---|---|---|---|---|---|---|---|
| 0.9585 | 1.0 | 510 | 0.5849 | 0.7825 | 0.8293 | 0.8002 | 0.8473 |
| 0.4334 | 2.0 | 1020 | 0.6323 | 0.8394 | 0.8127 | 0.8226 | 0.8625 |
| 0.281 | 3.0 | 1530 | 0.5389 | 0.8259 | 0.8476 | 0.8348 | 0.8704 |
| 0.2117 | 4.0 | 2040 | 0.7155 | 0.8381 | 0.8243 | 0.8297 | 0.8675 |
| 0.1556 | 5.0 | 2550 | 0.6981 | 0.8420 | 0.8411 | 0.8414 | 0.8729 |
| 0.1216 | 6.0 | 3060 | 0.9238 | 0.8441 | 0.8089 | 0.8237 | 0.8606 |
| 0.108 | 7.0 | 3570 | 0.8514 | 0.8334 | 0.8215 | 0.8270 | 0.8645 |
| 0.0817 | 8.0 | 4080 | 0.8539 | 0.8341 | 0.8245 | 0.8288 | 0.8660 |
| 0.0659 | 9.0 | 4590 | 0.9233 | 0.8441 | 0.8202 | 0.8313 | 0.8655 |
| 0.0588 | 10.0 | 5100 | 0.9426 | 0.8396 | 0.8182 | 0.8282 | 0.8655 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3