Hugging Face's logo

alsokit
/
Phi-3-medium-128K-LoRA

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
Phi-3-medium-128K-LoRA / README.md
alsokit's picture
alsokit
Upload 17 files
56e5777 verified
preview code
|
raw
history blame contribute delete
1.35 kB
metadata
base_model: microsoft/Phi-3-medium-128k-instruct
library_name: peft
license: other
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: train_2024-07-24-15-00-21
    results: []

train_2024-07-24-15-00-21

This model is a fine-tuned version of microsoft/Phi-3-medium-128k-instruct on the ALS dataset.

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-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 3.0

Training results

Framework versions

  • PEFT 0.11.1
  • Transformers 4.43.1
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1