train_results.json

{
    "before_init_mem_cpu": 3802071040,
    "before_init_mem_gpu": 22016,
    "epoch": 0.9807355516637478,
    "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
}