train_results.json

{
    "epoch": 79.99,
    "init_mem_cpu_alloc_delta": 51353,
    "init_mem_cpu_peaked_delta": 18306,
    "init_mem_gpu_alloc_delta": 0,
    "init_mem_gpu_peaked_delta": 0,
    "total_flos": 3.4759190857567523e+19,
    "train_mem_cpu_alloc_delta": 34575838,
    "train_mem_cpu_peaked_delta": 171805020,
    "train_mem_gpu_alloc_delta": 3790510080,
    "train_mem_gpu_peaked_delta": 6257791488,
    "train_runtime": 32940.4351,
    "train_samples": 3478,
    "train_samples_per_second": 0.151
}