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

9 lines
261 B
JSON
Raw Normal View History

{
"ewc_loss": 2.2411346435546875e-05,
"total_flos": 3.1829322264618205e+19,
"train_loss": 0.9959457731411026,
"train_runtime": 37043.5107,
"train_samples": 145693,
"train_samples_per_second": 11.799,
"train_steps_per_second": 0.737
}