zephyr-7b-dpo-full

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5041
• Rewards/chosen: -1.0932
• Rewards/rejected: -2.0784
• Rewards/accuracies: 0.7930
• Rewards/margins: 0.9852
• Logps/rejected: -456.6373
• Logps/chosen: -356.3788
• Logits/rejected: -2.3599
• Logits/chosen: -2.3858

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: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_batch_size: 64
• 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
0.4965	0.9984	477	0.5041	-1.0932	-2.0784	0.7930	0.9852	-456.6373	-356.3788	-2.3599	-2.3858

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+rocm6.2
• Datasets 3.2.0
• Tokenizers 0.20.3