Qwen2.5-7B-Instruct-R1-forfinance/train_results.json

{
    "epoch": 2.0,
    "total_flos": 119307564613632.0,
    "train_loss": 0.7332022241674937,
    "train_runtime": 6450.9735,
    "train_samples_per_second": 6.168,
    "train_steps_per_second": 0.048
}