qwen_model_testing / all_results.json
sravanthib's picture
Training completed
cf9b9e2 verified
{
"epoch": 0.0182648401826484,
"total_flos": 1.394108846267433e+17,
"train_loss": 8.501841735839843,
"train_runtime": 190.4124,
"train_samples_per_second": 8.403,
"train_steps_per_second": 0.053
}