Qwen2.5-1.5B-Open-R1-Distill / train_results.json
Blancy's picture
Model save
f212069 verified
raw
history blame contribute delete
219 Bytes
{
"total_flos": 5.828408442271826e+17,
"train_loss": 0.10050818478102819,
"train_runtime": 2227.4528,
"train_samples": 10000,
"train_samples_per_second": 32.502,
"train_steps_per_second": 0.254
}