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_1800
results: []
BERT_ST_DA_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: 0.1918
- Precision: 0.9710
- Recall: 0.9712
- F1: 0.9711
- Accuracy: 0.9675
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 |
|---|---|---|---|---|---|---|---|
| 0.1075 | 1.0 | 1050 | 0.1338 | 0.9633 | 0.9650 | 0.9641 | 0.9616 |
| 0.0565 | 2.0 | 2100 | 0.1253 | 0.9661 | 0.9687 | 0.9674 | 0.9647 |
| 0.0358 | 3.0 | 3150 | 0.1386 | 0.9691 | 0.9703 | 0.9697 | 0.9666 |
| 0.0211 | 4.0 | 4200 | 0.1516 | 0.9701 | 0.9707 | 0.9704 | 0.9670 |
| 0.0118 | 5.0 | 5250 | 0.1586 | 0.9697 | 0.9726 | 0.9711 | 0.9676 |
| 0.0084 | 6.0 | 6300 | 0.1791 | 0.9685 | 0.9698 | 0.9691 | 0.9654 |
| 0.0054 | 7.0 | 7350 | 0.1849 | 0.9692 | 0.9692 | 0.9692 | 0.9657 |
| 0.0031 | 8.0 | 8400 | 0.1887 | 0.9690 | 0.9708 | 0.9699 | 0.9660 |
| 0.0023 | 9.0 | 9450 | 0.1931 | 0.9705 | 0.9703 | 0.9704 | 0.9669 |
| 0.0017 | 10.0 | 10500 | 0.1918 | 0.9710 | 0.9712 | 0.9711 | 0.9675 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1