Qwen3-1.7B-Open-R1-GRPO / train_results.json
Blancy's picture
Model save
e8d6b53 verified
raw
history blame contribute delete
200 Bytes
{
"total_flos": 0.0,
"train_loss": 0.055402542805832566,
"train_runtime": 70946.2323,
"train_samples": 1000,
"train_samples_per_second": 0.07,
"train_steps_per_second": 0.003
}