metadata
base_model: microsoft/Phi-3-mini-4k-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-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2057
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6123 | 0.2807 | 100 | 1.3855 |
| 1.3959 | 0.5614 | 200 | 1.3212 |
| 1.2889 | 0.8421 | 300 | 1.2876 |
| 1.332 | 1.1228 | 400 | 1.2582 |
| 1.2596 | 1.4035 | 500 | 1.2443 |
| 1.2424 | 1.6842 | 600 | 1.2284 |
| 1.1912 | 1.9649 | 700 | 1.2161 |
| 1.1686 | 2.2456 | 800 | 1.2123 |
| 1.2223 | 2.5263 | 900 | 1.2074 |
| 1.1395 | 2.8070 | 1000 | 1.2057 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1