{ "epoch": 0.998691442030882, "eval_dpo_lambda": 0.9499999284744263, "eval_logits/chosen": -0.9673975706100464, "eval_logits/rejected": -1.0031267404556274, "eval_logps/chosen": -338.55499267578125, "eval_logps/rejected": -360.69610595703125, "eval_loss": 0.5627262592315674, "eval_rewards/accuracies": 0.7329999804496765, "eval_rewards/chosen": -0.3790811598300934, "eval_rewards/margins": 0.5175721645355225, "eval_rewards/rejected": -0.8966532945632935, "eval_runtime": 561.3254, "eval_samples": 2000, "eval_samples_per_second": 3.563, "eval_steps_per_second": 0.891, "total_flos": 0.0, "train_loss": 0.5879578035582537, "train_runtime": 40532.5341, "train_samples": 61134, "train_samples_per_second": 1.508, "train_steps_per_second": 0.012 }