all_results.json

{
    "before_init_mem_cpu": 699817984,
    "before_init_mem_gpu": 0,
    "epoch": 5.98,
    "eval_accuracy": 0.544073054441718,
    "eval_loss": 1.9982993602752686,
    "eval_mem_cpu_alloc_delta": 9977856,
    "eval_mem_cpu_peaked_delta": 60305408,
    "eval_mem_gpu_alloc_delta": 0,
    "eval_mem_gpu_peaked_delta": 2357757952,
    "eval_runtime": 481.5484,
    "eval_samples": 588,
    "eval_samples_per_second": 1.221,
    "eval_steps_per_second": 0.305,
    "init_mem_cpu_alloc_delta": -283938816,
    "init_mem_cpu_peaked_delta": 332918784,
    "init_mem_gpu_alloc_delta": 334744576,
    "init_mem_gpu_peaked_delta": 0,
    "perplexity": 7.376500655769286,
    "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
}