biomistral-7b-dpo-full-sft-wo-live_qa

This model is a fine-tuned version of Minbyul/biomistral-7b-wo-live_qa-sft on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• Loss: 0.4714
• Rewards/chosen: -0.1308
• Rewards/rejected: -0.7214
• Rewards/accuracies: 0.75
• Rewards/margins: 0.5906
• Logps/rejected: -487.4595
• Logps/chosen: -90.0080
• Logits/rejected: -4.0457
• Logits/chosen: -5.2055

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	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.1183	0.82	100	0.4731	-0.1249	-0.7085	0.75	0.5837	-486.1749	-89.4136	-4.0476	-5.2050

Framework versions

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