gemma-7b-dpo-full-orca-v0

This model is a fine-tuned version of lewtun/gemma-7b-sft-full-ultrachat-v0 on the HuggingFaceH4/orca_dpo_pairs dataset. It achieves the following results on the evaluation set:

• Loss: 0.0131
• Rewards/chosen: 4.5525
• Rewards/rejected: -7.7149
• Rewards/accuracies: 0.9922
• Rewards/margins: 12.2674
• Logps/rejected: -860.7157
• Logps/chosen: -725.1588
• Logits/rejected: 141.1811
• Logits/chosen: 94.1054

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• 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: 1

Training results

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.1