open-sci-ref-v0.02-1.7b-nemotron-hq-300B-16k-DPO-Tulu3-decontaminated/all_results.json

{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 3.0317540988116196,
    "train_runtime": 18550.6661,
    "train_samples": 272585,
    "train_samples_per_second": 14.694,
    "train_steps_per_second": 0.115
}