Hugging Face's logo

GOODYEONSU
/
qwen2-0.5-4bit-test

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
qwen2-0.5-4bit-test / README.md
GOODYEONSU's picture
GOODYEONSU
Model save
34d4f91 verified
preview code
|
raw
history blame contribute delete
1.2 kB
metadata
base_model: Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4
library_name: peft
license: apache-2.0
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: qwen2-0.5-4bit-test
    results: []

qwen2-0.5-4bit-test

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4 on an unknown 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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 1

Training results

Framework versions

  • PEFT 0.12.0
  • Transformers 4.43.3
  • Pytorch 2.4.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1