metadata
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: bigcode-starcoderbase-1b-finetuned-defect-detection
results: []
bigcode-starcoderbase-1b-finetuned-defect-detection
This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9591
- Accuracy: 0.7666
- Roc Auc: 0.7662
- Precision: 0.7657
- Recall: 0.7523
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: 4711
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Roc Auc | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.7596 | 1.0 | 996 | 0.5406 | 0.6852 | 0.6897 | 0.6264 | 0.8813 |
| 0.4855 | 2.0 | 1993 | 0.4691 | 0.7377 | 0.7396 | 0.6954 | 0.8237 |
| 0.3547 | 3.0 | 2989 | 0.4832 | 0.7480 | 0.7479 | 0.7410 | 0.7441 |
| 0.2463 | 4.0 | 3986 | 0.5966 | 0.7628 | 0.7646 | 0.7196 | 0.8428 |
| 0.1633 | 5.0 | 4980 | 0.9591 | 0.7666 | 0.7662 | 0.7657 | 0.7523 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2