metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: 14apr-bert-uncased
results: []
14apr-bert-uncased
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1141
- Precision: 0.9797
- Recall: 0.9796
- F1: 0.9797
- Accuracy: 0.9774
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1405 | 1.0 | 2500 | 0.1016 | 0.9731 | 0.9761 | 0.9746 | 0.9721 |
| 0.0994 | 2.0 | 5000 | 0.0939 | 0.9776 | 0.9774 | 0.9775 | 0.9750 |
| 0.0731 | 3.0 | 7500 | 0.0968 | 0.9783 | 0.9790 | 0.9787 | 0.9767 |
| 0.045 | 4.0 | 10000 | 0.1075 | 0.9790 | 0.9798 | 0.9794 | 0.9773 |
| 0.035 | 5.0 | 12500 | 0.1141 | 0.9797 | 0.9796 | 0.9797 | 0.9774 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2