selfbiorag-7b-dpo-full-wo-healthsearch_qa-ep3

This model is a fine-tuned version of dmis-lab/selfbiorag_7b on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• Loss: 0.6669
• Rewards/chosen: 0.0740
• Rewards/rejected: 0.0190
• Rewards/accuracies: 0.6977
• Rewards/margins: 0.0550
• Logps/rejected: -170.3629
• Logps/chosen: -158.5215
• Logits/rejected: -1.6515
• Logits/chosen: -1.6773

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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

Training Loss	Epoch	Step	Logits/chosen	Logits/rejected	Logps/chosen	Logps/rejected	Validation Loss	Rewards/accuracies	Rewards/chosen	Rewards/margins	Rewards/rejected
0.6508	0.61	100	-1.6968	-1.6723	-158.8701	-170.2428	0.6691	0.6941	0.0706	0.0503	0.0202

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.15.2