CodePhi-3-St
This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7978
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adafactor and the args are: No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6382 | 1.0 | 54 | 0.8045 |
| 0.8836 | 2.0 | 108 | 0.7987 |
| 0.993 | 2.9577 | 159 | 0.7978 |
Framework versions
- PEFT 0.12.0
- Transformers 4.49.0
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for AdnanRiaz107/CodePhi-3-St
Base model
microsoft/Phi-3-mini-128k-instruct