metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/Phi-3-mini-128k-instruct
model-index:
- name: CodePhi-3-mini-0.1Klora
results: []
CodePhi-3-mini-0.1Klora
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: 0.7028
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
- 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: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7309 | 0.1 | 10 | 0.7111 |
| 0.6897 | 0.2 | 20 | 0.7091 |
| 0.6818 | 0.3 | 30 | 0.7070 |
| 0.697 | 0.4 | 40 | 0.7050 |
| 0.5746 | 0.5 | 50 | 0.7037 |
| 0.3681 | 0.6 | 60 | 0.7037 |
| 0.478 | 0.7 | 70 | 0.7032 |
| 0.4471 | 0.8 | 80 | 0.7028 |
| 0.6291 | 0.9 | 90 | 0.7027 |
| 0.6592 | 1.0 | 100 | 0.7028 |
Framework versions
- PEFT 0.11.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1