qwen25_3b_intruct_diverse / train_results.json
ashleyferraro's picture
initial upload
486734f verified
{
"epoch": 2.9994666666666667,
"total_flos": 485028904697856.0,
"train_loss": 0.0026980684696038845,
"train_runtime": 169.643,
"train_samples_per_second": 265.263,
"train_steps_per_second": 16.588
}