hp_ablations_qwen_lr1e-6 / all_results.json
sedrickkeh's picture
End of training
47f2e8c verified
raw
history blame contribute delete
360 Bytes
{
"epoch": 2.996011396011396,
"eval_loss": 0.6290851831436157,
"eval_runtime": 442.0822,
"eval_samples_per_second": 26.744,
"eval_steps_per_second": 0.418,
"total_flos": 2755219238682624.0,
"train_loss": 0.642158996931857,
"train_runtime": 70520.3628,
"train_samples_per_second": 9.556,
"train_steps_per_second": 0.019
}