Qwen2.5-7B-Open-R1-Distill-bi / all_results.json
a-F1's picture
Model save
2172a16 verified
{
"total_flos": 0.0,
"train_loss": 9.352778331691649,
"train_runtime": 124812.4415,
"train_samples": 16610,
"train_samples_per_second": 0.173,
"train_steps_per_second": 0.022
}