metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/Phi-3.5-mini-instruct
model-index:
- name: CodePhi-3.5-mini-0.4Klora
results: []
CodePhi-3.5-mini-0.4Klora
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6789
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: 40
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.603 | 0.25 | 100 | 0.7058 |
| 0.6586 | 0.5 | 200 | 0.6842 |
| 0.6558 | 0.75 | 300 | 0.6790 |
| 0.6028 | 1.0 | 400 | 0.6789 |
Framework versions
- PEFT 0.11.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1