metadata
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- 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: 0.5149
- Accuracy: 0.7523
- F1: 0.7482
- Precision: 0.7430
- Recall: 0.7533
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: 2
- eval_batch_size: 2
- seed: 4711
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.7604 | 1.0 | 996 | 0.5379 | 0.7144 | 0.6627 | 0.7829 | 0.5745 |
| 0.4649 | 2.0 | 1992 | 0.4524 | 0.7480 | 0.7585 | 0.7129 | 0.8104 |
| 0.318 | 3.0 | 2988 | 0.5149 | 0.7523 | 0.7482 | 0.7430 | 0.7533 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0