metadata
license: mit
base_model: AdnanRiaz107/CodePhi-3-mini-4k-instruct-python
tags:
- generated_from_trainer
model-index:
- name: CodePhi-3-mini-4k-instruct-pythonAPPSWOLORA
results: []
CodePhi-3-mini-4k-instruct-pythonAPPSWOLORA
This model is a fine-tuned version of AdnanRiaz107/CodePhi-3-mini-4k-instruct-python on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5795
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6559 | 0.1667 | 200 | 0.6520 |
| 0.6709 | 0.3333 | 400 | 0.6225 |
| 0.5701 | 0.5 | 600 | 0.5980 |
| 0.5371 | 0.6667 | 800 | 0.5818 |
| 0.4926 | 0.8333 | 1000 | 0.5789 |
| 0.5058 | 1.0 | 1200 | 0.5795 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1