open-sci-ref-v0.02-1.7b-nemotron-hq-300B-16384-rope_theta-1M-long_sft_16k/train_results.json

{
    "epoch": 1.0,
    "total_flos": 889480391426048.0,
    "train_loss": 0.9303844255645997,
    "train_runtime": 18614.4314,
    "train_samples_per_second": 2.79,
    "train_steps_per_second": 0.087
}