gemma-2-9b-overfit-ua / train_results.json
antonpolishko's picture
Model save
b9907cc verified
raw
history blame contribute delete
236 Bytes
{
"epoch": 3.0,
"total_flos": 7.187967826039144e+18,
"train_loss": 1.5352961912832626,
"train_runtime": 6782.5225,
"train_samples": 95663,
"train_samples_per_second": 10.345,
"train_steps_per_second": 0.162
}