Edit model card

doplhin-mistral-dpo-ultrafeedback-binarized-preferences-sigmoid

This model is a fine-tuned version of cognitivecomputations/dolphin-2.1-mistral-7b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6025
  • Rewards/chosen: -7.8168
  • Rewards/rejected: -14.5388
  • Rewards/accuracies: 0.8310
  • Rewards/margins: 6.7220
  • Logps/rejected: -469.4976
  • Logps/chosen: -438.1190
  • Logits/rejected: -2.1911
  • Logits/chosen: -2.3064

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-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • 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

Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen
1.0466 0.25 700 0.8185 -6.6407 -9.8742 0.7464 3.2335 -422.8520 -426.3579 -2.3161 -2.4530
0.7039 0.51 1400 0.7051 -6.5305 -12.5351 0.8085 6.0046 -449.4607 -425.2558 -2.1415 -2.2554
0.9519 0.76 2100 0.6025 -7.8168 -14.5388 0.8310 6.7220 -469.4976 -438.1190 -2.1911 -2.3064

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.2
Downloads last month
1
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for DrishtiSharma/dolphin-2.1-mistral-7b-dpo-ultrafeedback-binarized-preferences-sigmoid

Adapter
(11)
this model