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

9 lines
259 B
JSON
Raw Permalink Normal View History

{
"ewc_loss": 0.00012302398681640625,
"total_flos": 4.051147348618982e+19,
"train_loss": 0.37770841820814355,
"train_runtime": 39471.777,
"train_samples": 125770,
"train_samples_per_second": 9.559,
"train_steps_per_second": 0.597
}