metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: bert_test_6
results: []
bert_test_6
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7765
- F1: 0.8771
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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 | F1 |
|---|---|---|---|---|
| 1.0636 | 1.0 | 341 | 0.5332 | 0.8392 |
| 0.3956 | 2.0 | 682 | 0.4838 | 0.8527 |
| 0.2223 | 3.0 | 1023 | 0.5233 | 0.8614 |
| 0.1499 | 4.0 | 1364 | 0.6195 | 0.8523 |
| 0.0882 | 5.0 | 1705 | 0.7167 | 0.8586 |
| 0.0528 | 6.0 | 2046 | 0.8098 | 0.8473 |
| 0.0434 | 7.0 | 2387 | 0.7825 | 0.8654 |
| 0.0231 | 8.0 | 2728 | 0.7347 | 0.8799 |
| 0.0105 | 9.0 | 3069 | 0.7785 | 0.8817 |
| 0.0078 | 10.0 | 3410 | 0.7765 | 0.8771 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3