Hugging Face's logo

KatyTheCutie
/
Qwen-101

PEFT
TensorBoard
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Metrics Community
Qwen-101 / README.md
KatyTheCutie's picture
KatyTheCutie
Upload folder using huggingface_hub
ed1991b verified
preview code
|
raw
history blame contribute delete
1.23 kB
metadata
license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: Qwen/Qwen1.5-1.8B
model-index:
  - name: train_2024-03-15-07-07-32
    results: []

train_2024-03-15-07-07-32

This model is a fine-tuned version of Qwen/Qwen1.5-1.8B on the PIPPA 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
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2