Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
Julian-CF's picture
Model save
dfc1d58 verified
{
"total_flos": 0.0,
"train_loss": 0.148394811640417,
"train_runtime": 218075.7377,
"train_samples": 93733,
"train_samples_per_second": 6.574,
"train_steps_per_second": 0.015
}