Qwen2.5-1.5B-Open-R1-Distill / all_results.json
gordonguanghui's picture
Model save
f1eece1 verified
raw
history blame contribute delete
214 Bytes
{
"total_flos": 488621249396736.0,
"train_loss": 0.5612765536157053,
"train_runtime": 11040.6024,
"train_samples": 93733,
"train_samples_per_second": 3.107,
"train_steps_per_second": 0.049
}