Qwen2.5-7B-1m-Open-R1-Distill / all_results.json
skzxjus's picture
End of training
187871f verified
raw
history blame contribute delete
412 Bytes
{
"epoch": 0.9955555555555555,
"eval_loss": 0.6304788589477539,
"eval_runtime": 2.3444,
"eval_samples": 100,
"eval_samples_per_second": 54.171,
"eval_steps_per_second": 1.706,
"total_flos": 175887366488064.0,
"train_loss": 0.6538166212184089,
"train_runtime": 1597.3219,
"train_samples": 16610,
"train_samples_per_second": 13.504,
"train_steps_per_second": 0.105
}