hp_ablations_qwen_epoch3_dcftv1.2 / train_results.json
sedrickkeh's picture
End of training
c18f775 verified
raw
history blame contribute delete
221 Bytes
{
"epoch": 2.9934162399414777,
"total_flos": 2144724936818688.0,
"train_loss": 0.6140779541151731,
"train_runtime": 27853.5124,
"train_samples_per_second": 18.844,
"train_steps_per_second": 0.037
}