metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: text_classification
results: []
text_classification
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: 0.3020
- Accuracy: 0.926
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: 4
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5849 | 0.1 | 625 | 0.4289 | 0.8756 |
| 1.7008 | 0.2 | 1250 | 0.3622 | 0.8884 |
| 1.3654 | 0.3 | 1875 | 0.4385 | 0.8968 |
| 1.3265 | 0.4 | 2500 | 0.3949 | 0.898 |
| 0.0032 | 0.5 | 3125 | 0.4126 | 0.9084 |
| 2.4059 | 0.6 | 3750 | 0.3381 | 0.9112 |
| 0.9658 | 0.7 | 4375 | 0.3089 | 0.916 |
| 0.0045 | 0.8 | 5000 | 0.3200 | 0.9216 |
| 0.0062 | 0.9 | 5625 | 0.3020 | 0.926 |
| 0.0699 | 1.0 | 6250 | 0.3042 | 0.9252 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2