outputs-dpo

This model is a fine-tuned version of dynamofl/dynamo-1.6B-v0.4-mosaic on the snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.5811
• Rewards/chosen: -0.5596
• Rewards/rejected: -0.9329
• Rewards/accuracies: 0.7964
• Rewards/margins: 0.3733
• Logps/rejected: -549.6418
• Logps/chosen: -503.2280
• Logits/rejected: 15.4763
• Logits/chosen: 15.8957

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 6
• gradient_accumulation_steps: 16
• total_train_batch_size: 96
• total_eval_batch_size: 6
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2