lambda-qwen2.5-14b-dpo-test/train_results.json

{
    "epoch": 0.998691442030882,
    "total_flos": 0.0,
    "train_loss": 0.5192520058629898,
    "train_runtime": 13862.6582,
    "train_samples": 61134,
    "train_samples_per_second": 4.41,
    "train_steps_per_second": 0.034
}