Dfyd-R1-Distill-Qwen-1.5B-GRPO / train_results.json
wnj13's picture
Model save
d216d09 verified
raw
history blame contribute delete
202 Bytes
{
"total_flos": 0.0,
"train_loss": 0.0033100851627775683,
"train_runtime": 14646.384,
"train_samples": 93733,
"train_samples_per_second": 0.068,
"train_steps_per_second": 0.034
}