gemma-2-9b-tok20k-overfit-ua / all_results.json
antonpolishko's picture
Model save
73d0ec4 verified
raw
history blame
235 Bytes
{
"epoch": 3.0,
"total_flos": 5.361516984661967e+18,
"train_loss": 5.0057218712328115,
"train_runtime": 5286.5666,
"train_samples": 95663,
"train_samples_per_second": 9.883,
"train_steps_per_second": 0.155
}