{
    "effective_batch_size": 32,
    "epoch": 2.0,
    "final_gradient_accumulation_steps": 1,
    "final_micro_batch_size": 32,
    "num_input_tokens_seen": 726302720,
    "peak_cuda_memory_gib": 213.5380449295044,
    "real_tokens_per_epoch": 363149667,
    "requested_epochs": 2.0,
    "total_flos": 4.372023498453811e+17,
    "total_optimizer_steps_planned": 5542,
    "train_blocks": 88660,
    "train_loss": 2.3499925993530812,
    "train_runtime": 10647.232,
    "train_samples_per_second": 16.654,
    "train_steps_per_second": 0.521,
    "warmup_steps": 111
}