metadata
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
tags:
- generated_from_trainer
model-index:
- name: phi3_5_mini_instruct_lora_chemical_eng_flash
results: []
phi3_5_mini_instruct_lora_chemical_eng_flash
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0794
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0874 | 0.7319 | 100 | 0.0869 |
| 0.0781 | 1.4639 | 200 | 0.0809 |
| 0.0764 | 2.1958 | 300 | 0.0800 |
| 0.0782 | 2.9277 | 400 | 0.0794 |
| 0.0769 | 3.6597 | 500 | 0.0795 |
| 0.0697 | 4.3916 | 600 | 0.0794 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1