qwen4B_models/qwen_4B_d2_iter3_model/all_results.json

{
    "epoch": 1.9869281045751634,
    "eval_loss": 0.7803115844726562,
    "eval_runtime": 8.3907,
    "eval_samples_per_second": 16.208,
    "eval_steps_per_second": 2.026,
    "total_flos": 20289411874816.0,
    "train_loss": 0.8229627185746243,
    "train_runtime": 505.2345,
    "train_samples_per_second": 4.822,
    "train_steps_per_second": 0.301
}