Hugging Face's logo

KrithikV
/
phi-3-mini-LoRA-MEDQA-V2

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
phi-3-mini-LoRA-MEDQA-V2 / README.md
KrithikV's picture
KrithikV
HuggingFaceUser/adapter-medmobile-MEDQA-V2
0c08c29 verified
preview code
|
raw
history blame
1.53 kB
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-MEDQA-V2
    results: []

phi-3-mini-LoRA-MEDQA-V2

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: 0.6687

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: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • 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
0.7097 1.4493 100 0.6728
0.667 2.8986 200 0.6687

Framework versions

  • PEFT 0.12.0
  • Transformers 4.43.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1