Hugging Face's logo

seungduk
/
Bookworm-10.7B-v0.1

PEFT
Safetensors
llama
Generated from Trainer
Model card Files Community
Bookworm-10.7B-v0.1 / README.md
seungduk's picture
seungduk
Update name
0c8247a
preview code
|
raw
history blame contribute delete
1.47 kB
metadata
library_name: peft
tags:
  - generated_from_trainer
base_model: yanolja/KoSOLAR-10.7B-v0.1
model-index:
  - name: seungduk/Bookworm-10.7B-v0.1
    results: []

Built with Axolotl

seungduk/Bookworm-10.7B-v0.1

This model was trained from scratch on the None 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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.7.1
  • Transformers 4.37.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.0
  • Tokenizers 0.15.0