Hugging Face's logo

lesso17
/
b4714fba-168e-45ac-abb8-e2ca48f92fe1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b4714fba-168e-45ac-abb8-e2ca48f92fe1 / README.md
lesso17's picture
lesso17
End of training
949a534 verified
preview code
|
raw
history blame
2.01 kB
metadata
library_name: peft
license: llama3
base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: b4714fba-168e-45ac-abb8-e2ca48f92fe1
    results: []

Built with Axolotl

b4714fba-168e-45ac-abb8-e2ca48f92fe1

This model is a fine-tuned version of MLP-KTLim/llama-3-Korean-Bllossom-8B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3281

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: 0.000217
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 170
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0000 1 1.7878
1.4405 0.0008 50 1.2865
1.4487 0.0017 100 1.4199
1.4667 0.0025 150 1.3877
1.4872 0.0034 200 1.3281

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1