Hugging Face's logo

jjinkoo
/
LORA_finetuned

PEFT
TensorBoard
Safetensors
llama
trl
sft
Generated from Trainer
Model card Files Metrics Community
LORA_finetuned / README.md
jjinkoo's picture
jjinkoo
End of training
123d018 verified
preview code
|
raw
history blame
1.64 kB
metadata
license: llama3
base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: results
    results: []
library_name: peft

results

This model is a fine-tuned version of MLP-KTLim/llama-3-Korean-Bllossom-8B on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • _load_in_8bit: False
  • _load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: True
  • bnb_4bit_compute_dtype: bfloat16
  • bnb_4bit_quant_storage: uint8
  • load_in_4bit: True
  • load_in_8bit: False

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: linear
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.4.0.dev0
  • Transformers 4.43.3
  • Pytorch 2.4.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1