metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: checkpoints
results: []
checkpoints
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8798
- Accuracy: 0.8667
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0973 | 1.0 | 2 | 1.0807 | 0.4667 |
| 1.0801 | 2.0 | 4 | 1.0622 | 0.5333 |
| 1.0713 | 3.0 | 6 | 1.0386 | 0.5333 |
| 1.0396 | 4.0 | 8 | 1.0092 | 0.6 |
| 1.0034 | 5.0 | 10 | 0.9786 | 0.8 |
| 0.9929 | 6.0 | 12 | 0.9501 | 0.8667 |
| 0.9552 | 7.0 | 14 | 0.9236 | 0.8667 |
| 0.9386 | 8.0 | 16 | 0.9011 | 0.8667 |
| 0.9084 | 9.0 | 18 | 0.8862 | 0.8667 |
| 0.897 | 10.0 | 20 | 0.8798 | 0.8667 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1