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: BERT_ST_DA_1000
results: []
BERT_ST_DA_1000
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: 0.1864
- Precision: 0.9653
- Recall: 0.9736
- F1: 0.9694
- Accuracy: 0.9655
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
- 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 | 495 | 0.1375 | 0.9614 | 0.9662 | 0.9638 | 0.9590 |
| 0.2452 | 2.0 | 990 | 0.1262 | 0.9652 | 0.9705 | 0.9679 | 0.9632 |
| 0.0853 | 3.0 | 1485 | 0.1396 | 0.9638 | 0.9677 | 0.9657 | 0.9619 |
| 0.0479 | 4.0 | 1980 | 0.1485 | 0.9637 | 0.9729 | 0.9683 | 0.9651 |
| 0.0275 | 5.0 | 2475 | 0.1641 | 0.9633 | 0.9727 | 0.9680 | 0.9642 |
| 0.0181 | 6.0 | 2970 | 0.1753 | 0.9641 | 0.9739 | 0.9689 | 0.9655 |
| 0.0112 | 7.0 | 3465 | 0.1675 | 0.9659 | 0.9724 | 0.9691 | 0.9657 |
| 0.0074 | 8.0 | 3960 | 0.1817 | 0.9650 | 0.9745 | 0.9697 | 0.9663 |
| 0.0054 | 9.0 | 4455 | 0.1878 | 0.9652 | 0.9737 | 0.9694 | 0.9657 |
| 0.0038 | 10.0 | 4950 | 0.1864 | 0.9653 | 0.9736 | 0.9694 | 0.9655 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1