Qwen2.5-1.5B-Open-R1-GRPO / all_results.json
ununtrium's picture
End of training
a3f3840 verified
{
"eval_loss": 0.05640460178256035,
"eval_runtime": 10.2046,
"eval_samples": 99,
"eval_samples_per_second": 9.702,
"eval_steps_per_second": 0.392,
"total_flos": 0.0,
"train_loss": 0.049734286265447736,
"train_runtime": 1467.0643,
"train_samples": 3622,
"train_samples_per_second": 2.469,
"train_steps_per_second": 0.022
}