Files
Llama-3.1-8B-Instruct_SFT_s…/train_results.json

9 lines
260 B
JSON
Raw Normal View History

{
"ewc_loss": 4.029273986816406e-05,
"total_flos": 3.1829322264618205e+19,
"train_loss": 0.9772039013299405,
"train_runtime": 37330.6602,
"train_samples": 145693,
"train_samples_per_second": 11.708,
"train_steps_per_second": 0.732
}