hp_ablations_gemma_adambeta1_0.9 / train_results.json
sedrickkeh's picture
End of training
ebba0b3 verified
raw
history blame contribute delete
220 Bytes
{
"epoch": 2.9991537376586743,
"total_flos": 5064195066298368.0,
"train_loss": 0.5477321235823218,
"train_runtime": 120499.276,
"train_samples_per_second": 5.648,
"train_steps_per_second": 0.011
}