{ "epoch": 0.9994767137624281, "eval_logits/chosen": -2.2673287391662598, "eval_logits/rejected": -2.1683459281921387, "eval_logps/chosen": -283.9482421875, "eval_logps/rejected": -312.3089294433594, "eval_loss": 54835.10546875, "eval_rewards/accuracies": 0.550000011920929, "eval_rewards/chosen": -283.9482421875, "eval_rewards/margins": 28.360675811767578, "eval_rewards/rejected": -312.3089294433594, "eval_runtime": 184.8918, "eval_samples": 2000, "eval_samples_per_second": 10.817, "eval_steps_per_second": 0.676, "total_flos": 0.0, "train_loss": 56244.764594240834, "train_runtime": 21694.4484, "train_samples": 61135, "train_samples_per_second": 2.818, "train_steps_per_second": 0.044 }