Qwen2.5-1.5B-Open-R1-Distill / all_results.json
wnj13's picture
End of training
4813ded verified
raw
history blame contribute delete
381 Bytes
{
"eval_loss": 0.8607348203659058,
"eval_runtime": 50.5963,
"eval_samples": 100,
"eval_samples_per_second": 10.139,
"eval_steps_per_second": 10.139,
"total_flos": 76965426954240.0,
"train_loss": 0.8771114350247613,
"train_runtime": 110619.4732,
"train_samples": 16610,
"train_samples_per_second": 0.782,
"train_steps_per_second": 0.024
}