train_results.json

{
    "before_init_mem_cpu": 699817984,
    "before_init_mem_gpu": 0,
    "epoch": 5.98,
    "init_mem_cpu_alloc_delta": -283938816,
    "init_mem_cpu_peaked_delta": 332918784,
    "init_mem_gpu_alloc_delta": 334744576,
    "init_mem_gpu_peaked_delta": 0,
    "train_loss": 2.0183091745143984,
    "train_mem_cpu_alloc_delta": 1155149824,
    "train_mem_cpu_peaked_delta": 308719616,
    "train_mem_gpu_alloc_delta": 988995584,
    "train_mem_gpu_peaked_delta": 4500811776,
    "train_runtime": 35067.5673,
    "train_samples": 5325,
    "train_samples_per_second": 0.911,
    "train_steps_per_second": 0.007
}