OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.05/train_results.json

{
    "ewc_loss": 0.119140625,
    "ewc_loss_diag": 0.00030517578125,
    "ewc_loss_parallel": 8.869171142578125e-05,
    "total_flos": 5.156325133756924e+19,
    "train_loss": 0.5050858836974098,
    "train_runtime": 50355.4873,
    "train_samples": 125770,
    "train_samples_per_second": 7.493,
    "train_steps_per_second": 0.468
}