{ "before_init_mem_cpu": 3802071040, "before_init_mem_gpu": 22016, "epoch": 0.9807355516637478, "eval_logits/chosen": -12.004097938537598, "eval_logits/rejected": -17.047502517700195, "eval_logps/chosen": -2.168222427368164, "eval_logps/rejected": -4.787535667419434, "eval_loss": 1.0162526369094849, "eval_mem_cpu_alloc_delta": 466944, "eval_mem_cpu_peaked_delta": 0, "eval_mem_gpu_alloc_delta": 0, "eval_mem_gpu_peaked_delta": 25220711424, "eval_rewards/accuracies": 0.9166666865348816, "eval_rewards/chosen": -21.682226181030273, "eval_rewards/margins": 26.193130493164062, "eval_rewards/rejected": -47.875362396240234, "eval_runtime": 9.9413, "eval_samples_per_second": 9.456, "eval_sft_loss": 0.01844729855656624, "eval_steps_per_second": 1.207, "init_mem_cpu_alloc_delta": 364544, "init_mem_cpu_peaked_delta": 0, "init_mem_gpu_alloc_delta": 0, "init_mem_gpu_peaked_delta": 0, "total_flos": 39867492466688.0, "train_loss": 3.085822834287371, "train_mem_cpu_alloc_delta": 5213659136, "train_mem_cpu_peaked_delta": 22737326080, "train_mem_gpu_alloc_delta": 16267848704, "train_mem_gpu_peaked_delta": 36029468160, "train_runtime": 1628.7465, "train_samples_per_second": 2.805, "train_steps_per_second": 0.021 }