R1-Distill-1.5B-Qwen-GRPO / train_results.json
alphadl's picture
Model save
0e09188 verified
raw
history blame contribute delete
201 Bytes
{
"total_flos": 0.0,
"train_loss": 0.0479528897729047,
"train_runtime": 135512.3968,
"train_samples": 93733,
"train_samples_per_second": 0.692,
"train_steps_per_second": 0.086
}