OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04/all_results.json

{
    "ewc_loss": 0.50390625,
    "ewc_loss_diag": 0.000789642333984375,
    "ewc_loss_parallel": 0.000423431396484375,
    "total_flos": 5.156325133756924e+19,
    "train_loss": 0.8269113934204859,
    "train_runtime": 50783.0573,
    "train_samples": 125770,
    "train_samples_per_second": 7.43,
    "train_steps_per_second": 0.464
}