FineTunedllema_nada / README.md
Nada81's picture
End of training
3945bb8 verified
metadata
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: beomi/llama-2-ko-7b
model-index:
  - name: FineTunedllema_nada
    results: []

FineTunedllema_nada

This model is a fine-tuned version of beomi/llama-2-ko-7b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8265

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
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.9417 1.0 112 0.8217
0.7246 2.0 225 0.7960
0.5382 2.99 336 0.8265

Framework versions

  • PEFT 0.7.2.dev0
  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.2