metadata
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: deepseek-ai-deepseek-coder-1.3b-base-finetuned-defect-detection
results: []
deepseek-ai-deepseek-coder-1.3b-base-finetuned-defect-detection
This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8154
- Accuracy: 0.7877
- F1: 0.7861
- Precision: 0.7736
- Recall: 0.7991
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 | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5701 | 1.0 | 996 | 0.4446 | 0.7417 | 0.7633 | 0.6910 | 0.8525 |
| 0.3448 | 2.0 | 1993 | 0.4246 | 0.7681 | 0.7490 | 0.7944 | 0.7086 |
| 0.2305 | 3.0 | 2989 | 0.4693 | 0.7912 | 0.7924 | 0.7701 | 0.8160 |
| 0.1564 | 4.0 | 3986 | 0.5977 | 0.7836 | 0.7790 | 0.7774 | 0.7806 |
| 0.1102 | 5.0 | 4980 | 0.8154 | 0.7877 | 0.7861 | 0.7736 | 0.7991 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2