|
|
--- |
|
|
library_name: peft |
|
|
license: mit |
|
|
base_model: microsoft/phi-2 |
|
|
tags: |
|
|
- base_model:adapter:microsoft/phi-2 |
|
|
- transformers |
|
|
pipeline_tag: text-generation |
|
|
model-index: |
|
|
- name: phi-2-IA3_1-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-IA3_1-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: 4.4994 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 6.003 | 0.1333 | 100 | 6.1547 | |
|
|
| 5.798 | 0.2667 | 200 | 5.8543 | |
|
|
| 5.4963 | 0.4 | 300 | 5.5766 | |
|
|
| 5.4936 | 0.5333 | 400 | 5.3316 | |
|
|
| 5.2081 | 0.6667 | 500 | 5.1551 | |
|
|
| 4.8002 | 0.8 | 600 | 5.0209 | |
|
|
| 4.7734 | 0.9333 | 700 | 4.9287 | |
|
|
| 4.9121 | 1.0667 | 800 | 4.8604 | |
|
|
| 4.8736 | 1.2 | 900 | 4.8028 | |
|
|
| 4.4034 | 1.3333 | 1000 | 4.7485 | |
|
|
| 4.7587 | 1.4667 | 1100 | 4.6937 | |
|
|
| 4.3786 | 1.6 | 1200 | 4.6457 | |
|
|
| 4.3765 | 1.7333 | 1300 | 4.6145 | |
|
|
| 4.6507 | 1.8667 | 1400 | 4.5827 | |
|
|
| 4.8214 | 2.0 | 1500 | 4.5567 | |
|
|
| 4.1151 | 2.1333 | 1600 | 4.5434 | |
|
|
| 4.6073 | 2.2667 | 1700 | 4.5267 | |
|
|
| 3.9566 | 2.4 | 1800 | 4.5202 | |
|
|
| 4.7471 | 2.5333 | 1900 | 4.5094 | |
|
|
| 4.5244 | 2.6667 | 2000 | 4.5046 | |
|
|
| 4.3776 | 2.8 | 2100 | 4.5010 | |
|
|
| 4.3815 | 2.9333 | 2200 | 4.4994 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.17.1 |
|
|
- Transformers 4.56.1 |
|
|
- Pytorch 2.8.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.0 |
