Hugging Face's logo

youndukn
/
mythomax-13b-sft-lora

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
Generated from Trainer
trl
sft
Model card Files Metrics Community
mythomax-13b-sft-lora / README.md
youndukn's picture
youndukn
End of training
875b468 verified
preview code
|
raw
history blame
1.58 kB
metadata
license: other
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - youndukn/ROLE_PLAY_INSTRUCT
base_model: Gryphe/MythoMax-L2-13b
model-index:
  - name: mythomax-13b-sft-lora
    results: []

mythomax-13b-sft-lora

This model is a fine-tuned version of Gryphe/MythoMax-L2-13b on the youndukn/ROLE_PLAY_INSTRUCT dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5062

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: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 128
  • total_train_batch_size: 512
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.5495 0.99 11 1.5062

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.1.0
  • Datasets 2.14.6
  • Tokenizers 0.15.0