Qwen3-8B-Open-R1-GRPO-spatial-dea / train_results.json
vcabeli's picture
Model save
7fd2b90 verified
raw
history blame
199 Bytes
{
"total_flos": 0.0,
"train_loss": 0.04093834859403697,
"train_runtime": 1244.7225,
"train_samples": 1092,
"train_samples_per_second": 0.877,
"train_steps_per_second": 0.018
}