Minbyul's picture
End of training
e21b692 verified
metadata
license: apache-2.0
base_model: Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-step1
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: biomistral-7b-wo-kqa_golden-iter-dpo-step1
    results: []

biomistral-7b-wo-kqa_golden-iter-dpo-step1

This model is a fine-tuned version of Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-step1 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6935
  • Rewards/chosen: -0.0242
  • Rewards/rejected: -0.0287
  • Rewards/accuracies: 0.5833
  • Rewards/margins: 0.0045
  • Logps/rejected: -167.6166
  • Logps/chosen: -188.0933
  • Logits/rejected: -2.5183
  • Logits/chosen: -2.8619

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: 1e-07
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • 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 4.38.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.2