| | --- |
| | library_name: peft |
| | license: mit |
| | base_model: microsoft/phi-2 |
| | tags: |
| | - base_model:adapter:microsoft/phi-2 |
| | - lora |
| | - transformers |
| | pipeline_tag: text-generation |
| | model-index: |
| | - name: phi-2-QLoRa2-Python |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # phi-2-QLoRa2-Python |
| |
|
| | This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 4.3289 |
| |
|
| | ## 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: 0.0002 |
| | - train_batch_size: 2 |
| | - eval_batch_size: 2 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 2 |
| | - total_train_batch_size: 4 |
| | - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| | - lr_scheduler_type: linear |
| | - lr_scheduler_warmup_steps: 100 |
| | - num_epochs: 3 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:------:|:----:|:---------------:| |
| | | 4.391 | 0.1333 | 100 | 4.3380 | |
| | | 4.273 | 0.2667 | 200 | 4.3430 | |
| | | 4.1309 | 0.4 | 300 | 4.3425 | |
| | | 4.2583 | 0.5333 | 400 | 4.3461 | |
| | | 4.2424 | 0.6667 | 500 | 4.3353 | |
| | | 3.9205 | 0.8 | 600 | 4.3342 | |
| | | 4.0227 | 0.9333 | 700 | 4.3312 | |
| | | 4.3798 | 1.0667 | 800 | 4.3311 | |
| | | 4.3908 | 1.2 | 900 | 4.3360 | |
| | | 3.8848 | 1.3333 | 1000 | 4.3354 | |
| | | 4.3534 | 1.4667 | 1100 | 4.3325 | |
| | | 3.937 | 1.6 | 1200 | 4.3335 | |
| | | 3.9995 | 1.7333 | 1300 | 4.3323 | |
| | | 4.3121 | 1.8667 | 1400 | 4.3314 | |
| | | 4.5389 | 2.0 | 1500 | 4.3312 | |
| | | 3.8369 | 2.1333 | 1600 | 4.3316 | |
| | | 4.3627 | 2.2667 | 1700 | 4.3309 | |
| | | 3.6879 | 2.4 | 1800 | 4.3305 | |
| | | 4.4777 | 2.5333 | 1900 | 4.3296 | |
| | | 4.2731 | 2.6667 | 2000 | 4.3293 | |
| | | 4.1431 | 2.8 | 2100 | 4.3291 | |
| | | 4.1535 | 2.9333 | 2200 | 4.3289 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - PEFT 0.17.1 |
| | - Transformers 4.56.1 |
| | - Pytorch 2.8.0+cu126 |
| | - Datasets 4.0.0 |
| | - Tokenizers 0.22.0 |
