Qwen2.5-1.5B-Open-R1-Distill / all_results.json
jeff-gao's picture
End of training
d8e2603 verified
raw
history blame contribute delete
381 Bytes
{
"eval_loss": 0.9643924832344055,
"eval_runtime": 2.5218,
"eval_samples": 100,
"eval_samples_per_second": 51.153,
"eval_steps_per_second": 4.362,
"total_flos": 6.0804602683856e+18,
"train_loss": 0.5375538207954831,
"train_runtime": 15535.6447,
"train_samples": 16610,
"train_samples_per_second": 13.918,
"train_steps_per_second": 0.29
}