hp_ablations_qwen_lr1e-6 / train_results.json
sedrickkeh's picture
End of training
47f2e8c verified
raw
history blame contribute delete
218 Bytes
{
"epoch": 2.996011396011396,
"total_flos": 2755219238682624.0,
"train_loss": 0.642158996931857,
"train_runtime": 70520.3628,
"train_samples_per_second": 9.556,
"train_steps_per_second": 0.019
}