hp_ablations_gemma_adambeta1_0.85 / train_results.json
sedrickkeh's picture
End of training
88d26a4 verified
raw
history blame contribute delete
221 Bytes
{
"epoch": 2.9991537376586743,
"total_flos": 5064195066298368.0,
"train_loss": 0.5487489427633981,
"train_runtime": 121678.3839,
"train_samples_per_second": 5.593,
"train_steps_per_second": 0.011
}