Hugging Face's logo

MichaelKim
/
EEVE-Korean-Instruct-10.8B-v1.0_train_r4_r16_v2

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
EEVE-Korean-Instruct-10.8B-v1.0_train_r4_r16_v2 / README.md
MichaelKim's picture
MichaelKim
End of training
a0e606c verified
preview code
|
raw
history blame
1.45 kB
metadata
base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
library_name: peft
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: EEVE-Korean-Instruct-10.8B-v1.0_train_r4_r16_v2
    results: []

Visualize in Weights & Biases

EEVE-Korean-Instruct-10.8B-v1.0_train_r4_r16_v2

This model is a fine-tuned version of yanolja/EEVE-Korean-Instruct-10.8B-v1.0 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: 0.0001
  • train_batch_size: 10
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.12.0
  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Tokenizers 0.19.1