Llama-3.1-8B-Instruct_SFT_mathfisher_v00.05/train_results.json

{
    "ewc_loss": 4.124641418457031e-05,
    "total_flos": 5.62815163329864e+19,
    "train_loss": 0.44794003818420614,
    "train_runtime": 46891.4367,
    "train_samples": 125770,
    "train_samples_per_second": 8.046,
    "train_steps_per_second": 0.503
}