CoolFace
Modelpublic

seanyhan/qwen-3-8b-base-r-dpo-ultrafeedback-4xH200-batch-128-rerun-2-runpod

sourceHugging Faceupdated 5mo agoView on Hugging Face
0likes9downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128

This model is a fine-tuned version of jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5469
  • —R Dpo/chosen Len: 294.4800
  • —R Dpo/rejected Len: 249.8700
  • —R Dpo/length Delta: 44.6100
  • —R Dpo/regularization Term: 4.4610
  • —Logps/chosen: -2936.7747
  • —Logps/rejected: -2579.1685
  • —Logps/ref Chosen: -281.4850
  • —Logps/ref Rejected: -261.8005
  • —Logits/chosen: 0.6320
  • —Logits/rejected: 0.5334

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
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —distributed_type: multi-GPU
  • —num_devices: 4
  • —gradientaccumulationsteps: 8
  • —totaltrainbatch_size: 128
  • —totalevalbatch_size: 16
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 1

Training results

Training LossEpochStepValidation LossR Dpo/chosen LenR Dpo/rejected LenR Dpo/length DeltaR Dpo/regularization TermLogps/chosenLogps/rejectedLogps/ref ChosenLogps/ref RejectedLogits/chosenLogits/rejected
6.66080.41882000.7288294.4800249.870044.61004.4610-2819.1780-2438.3210-281.4850-261.80050.60770.5856
4.53880.83774000.5469294.4800249.870044.61004.4610-2936.7747-2579.1685-281.4850-261.80050.63200.5334

Framework versions

  • —Transformers 4.51.0
  • —Pytorch 2.3.1+cu121
  • —Datasets 2.21.0
  • —Tokenizers 0.21.4