meditron-7b-dpo-full-sft-wo-kqa_silver_wogold

• Loss: 0.6249
• Rewards/chosen: -0.0145
• Rewards/rejected: -0.1983
• Rewards/accuracies: 0.875
• Rewards/margins: 0.1839
• Logps/rejected: -653.1394
• Logps/chosen: -150.2214
• Logits/rejected: -1.0337
• Logits/chosen: -1.4037

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• 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

Framework versions

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