Qwen3-1.7B-Open-R1-Code-GRPO / all_results.json
Blancy's picture
Model save
88fb2fe verified
raw
history blame
201 Bytes
{
"total_flos": 0.0,
"train_loss": 0.024176058914698324,
"train_runtime": 19938.5063,
"train_samples": 1086,
"train_samples_per_second": 0.054,
"train_steps_per_second": 0.002
}