chrlu's picture
End of training
724cb0f verified
metadata
license: other
base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - argilla/dpo-mix-7k
model-index:
  - name: zephyr-7b-gemma-hinge
    results: []

zephyr-7b-gemma-hinge

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-gemma-sft-v0.1 on the argilla/dpo-mix-7k dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5273
  • Rewards/chosen: -2.6335
  • Rewards/rejected: -3.8935
  • Rewards/accuracies: 0.7292
  • Rewards/margins: 1.2600
  • Logps/rejected: -439.9419
  • Logps/chosen: -416.3391
  • Logits/rejected: 96.0524
  • Logits/chosen: 101.8806

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: 2
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 128
  • 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: 2

Training results

Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen
0.1516 1.8957 100 0.5250 -2.6386 -3.9001 0.7188 1.2616 -440.0739 -416.4398 95.9739 101.8169

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.1.2+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1