metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: VF_BERT_ST_1800
results: []
VF_BERT_ST_1800
This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1814
- Precision: 0.8104
- Recall: 0.8406
- F1: 0.8252
- Accuracy: 0.9657
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 |
|---|---|---|---|---|---|---|---|
| 0.2052 | 1.0 | 569 | 0.1207 | 0.7731 | 0.8082 | 0.7903 | 0.9622 |
| 0.0774 | 2.0 | 1138 | 0.1369 | 0.8062 | 0.7998 | 0.8030 | 0.9629 |
| 0.0507 | 3.0 | 1707 | 0.1351 | 0.8127 | 0.8386 | 0.8254 | 0.9654 |
| 0.0328 | 4.0 | 2276 | 0.1331 | 0.8005 | 0.8414 | 0.8204 | 0.9658 |
| 0.0221 | 5.0 | 2845 | 0.1398 | 0.8144 | 0.8429 | 0.8284 | 0.9668 |
| 0.0157 | 6.0 | 3414 | 0.1481 | 0.8137 | 0.8401 | 0.8267 | 0.9671 |
| 0.0117 | 7.0 | 3983 | 0.1804 | 0.8110 | 0.8439 | 0.8271 | 0.9650 |
| 0.0062 | 8.0 | 4552 | 0.1731 | 0.8133 | 0.8434 | 0.8281 | 0.9658 |
| 0.005 | 9.0 | 5121 | 0.1835 | 0.8100 | 0.8416 | 0.8255 | 0.9660 |
| 0.0043 | 10.0 | 5690 | 0.1814 | 0.8104 | 0.8406 | 0.8252 | 0.9657 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1