hp_ablations_qwen_lr1e-5 / train_results.json
sedrickkeh's picture
End of training
150b19a verified
raw
history blame contribute delete
219 Bytes
{
"epoch": 2.996011396011396,
"total_flos": 2755219238682624.0,
"train_loss": 0.5826670261641435,
"train_runtime": 70447.3802,
"train_samples_per_second": 9.565,
"train_steps_per_second": 0.019
}