Qwen2.5-1.5B-Open-R1-GRPO-Math / train_client_0_results.json
Ziyao1010's picture
Model save
79bddb9 verified
{
"client_id": 0,
"total_flos": 0.0,
"train_loss": 0.011118112752834955,
"train_runtime": 226.5086,
"train_samples": 100,
"train_samples_per_second": 0.441,
"train_steps_per_second": 0.018
}