metadata
base_model: microsoft/Phi-3-mini-128k-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: phi-3-mini-LoRA
results: []
phi-3-mini-LoRA
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: 0.9261
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0422 | 0.6024 | 100 | 0.9495 |
| 0.8992 | 1.2048 | 200 | 0.9344 |
| 0.8815 | 1.8072 | 300 | 0.9300 |
| 0.8884 | 2.4096 | 400 | 0.9286 |
| 0.8645 | 3.0120 | 500 | 0.9257 |
| 0.8637 | 3.6145 | 600 | 0.9261 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1