metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/Phi-3-mini-128k-instruct
model-index:
- name: CodePhi-3-mini-128k-instruct-pythonAPPSLORA3k
results: []
CodePhi-3-mini-128k-instruct-pythonAPPSLORA3k
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: 0.6653
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-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- training_steps: 3000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7559 | 0.0667 | 200 | 0.7381 |
| 0.6846 | 0.1333 | 400 | 0.7010 |
| 0.6779 | 0.2 | 600 | 0.6869 |
| 0.6019 | 0.2667 | 800 | 0.6796 |
| 0.3809 | 0.3333 | 1000 | 0.6797 |
| 0.489 | 0.4 | 1200 | 0.6763 |
| 0.5024 | 0.4667 | 1400 | 0.6728 |
| 0.6033 | 0.5333 | 1600 | 0.6695 |
| 0.6379 | 0.6 | 1800 | 0.6671 |
| 0.5938 | 0.6667 | 2000 | 0.6661 |
| 0.6045 | 0.7333 | 2200 | 0.6654 |
| 0.3571 | 0.8 | 2400 | 0.6653 |
| 0.6675 | 0.8667 | 2600 | 0.6653 |
| 0.8997 | 0.9333 | 2800 | 0.6653 |
| 0.6634 | 1.0 | 3000 | 0.6653 |
Framework versions
- PEFT 0.11.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1