metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: defect-classification-distilbert-baseline-10-epochs
results: []
defect-classification-distilbert-baseline-10-epochs
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2976
- Accuracy: 0.8762
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: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6008 | 1.0 | 1062 | 0.5867 | 0.7578 |
| 0.4986 | 2.0 | 2124 | 0.4298 | 0.8051 |
| 0.4322 | 3.0 | 3186 | 0.3786 | 0.8255 |
| 0.458 | 4.0 | 4248 | 0.3425 | 0.8462 |
| 0.4143 | 5.0 | 5310 | 0.3274 | 0.8533 |
| 0.4443 | 6.0 | 6372 | 0.3153 | 0.8620 |
| 0.3508 | 7.0 | 7434 | 0.3076 | 0.8691 |
| 0.4489 | 8.0 | 8496 | 0.2989 | 0.8745 |
| 0.364 | 9.0 | 9558 | 0.2974 | 0.8764 |
| 0.4091 | 10.0 | 10620 | 0.2976 | 0.8762 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0