{ "epoch": 1.0, "eval_logits/chosen": -5.205519676208496, "eval_logits/rejected": -4.045749187469482, "eval_logps/chosen": -90.00802612304688, "eval_logps/rejected": -487.45953369140625, "eval_loss": 0.47143450379371643, "eval_rewards/accuracies": 0.75, "eval_rewards/chosen": -0.13080169260501862, "eval_rewards/margins": 0.5905601382255554, "eval_rewards/rejected": -0.7213618159294128, "eval_runtime": 5.4486, "eval_samples": 4, "eval_samples_per_second": 0.734, "eval_steps_per_second": 0.184, "train_loss": 0.24888706256131657, "train_runtime": 2705.2939, "train_samples": 7808, "train_samples_per_second": 2.886, "train_steps_per_second": 0.045 }