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

9 lines
260 B
JSON
Raw Permalink Normal View History

{
"ewc_loss": 0.0002918243408203125,
"total_flos": 3.1829322264618205e+19,
"train_loss": 0.9272488037147323,
"train_runtime": 37031.0594,
"train_samples": 145693,
"train_samples_per_second": 11.803,
"train_steps_per_second": 0.738
}