metadata
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: bigcode-starcoderbase-1b-finetuned-defect-cwe-group-detection
results: []
bigcode-starcoderbase-1b-finetuned-defect-cwe-group-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: 0.7332
- Accuracy: 0.7603
- Precision: 0.7915
- Recall: 0.5933
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 | Precision | Recall |
|---|---|---|---|---|---|---|
| No log | 1.0 | 462 | 0.5916 | 0.7378 | 0.5849 | 0.4951 |
| 0.7929 | 2.0 | 925 | 0.4926 | 0.7760 | 0.7951 | 0.5958 |
| 0.4345 | 3.0 | 1387 | 0.6382 | 0.7316 | 0.7372 | 0.6156 |
| 0.3051 | 4.0 | 1850 | 0.6161 | 0.7580 | 0.7736 | 0.6097 |
| 0.2378 | 4.99 | 2310 | 0.7332 | 0.7603 | 0.7915 | 0.5933 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2