gemma-2-9b-tok20k-overfit-ua / train_results.json
antonpolishko's picture
Model save
d5745e7 verified
{
"epoch": 3.0,
"total_flos": 5.361516984661967e+18,
"train_loss": 5.0057218712328115,
"train_runtime": 5088.8536,
"train_samples": 95663,
"train_samples_per_second": 10.267,
"train_steps_per_second": 0.161
}