Qwen2.5-1.5B-Open-R1-GRPO / all_results.json
KMasaki's picture
Model save
78864cd verified
{
"total_flos": 0.0,
"train_loss": 0.08076191042202922,
"train_runtime": 127083.2818,
"train_samples": 93733,
"train_samples_per_second": 0.738,
"train_steps_per_second": 0.026
}