0.001_idpo_iter_3 / README.md
ShenaoZhang's picture
End of training
f9cb9f9 verified
metadata
license: mit
base_model: ShenaoZhang/0.001_idpo_iter_2
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - ShenaoZhang/0.001_idpo_dataset
model-index:
  - name: 0.001_idpo_iter_3
    results: []

0.001_idpo_iter_3

This model is a fine-tuned version of ShenaoZhang/0.001_idpo_iter_2 on the ShenaoZhang/0.001_idpo_dataset 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: 5e-07
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 128
  • total_eval_batch_size: 64
  • 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

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.2