{ "epoch": 1.0, "eval_logits/chosen": 98.61418151855469, "eval_logits/rejected": 98.59135437011719, "eval_logps/chosen": -32.61461639404297, "eval_logps/rejected": -36.286746978759766, "eval_loss": 0.7295444011688232, "eval_rewards/accuracies": 0.550664484500885, "eval_rewards/chosen": -0.10286416858434677, "eval_rewards/margins": 0.08926620334386826, "eval_rewards/rejected": -0.19213035702705383, "eval_runtime": 103.7555, "eval_samples": 343, "eval_samples_per_second": 3.306, "eval_steps_per_second": 0.414, "train_loss": 0.5886486524111265, "train_runtime": 2556.9439, "train_samples": 3079, "train_samples_per_second": 1.204, "train_steps_per_second": 0.151 }