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

9 lines
259 B
JSON
Raw Permalink Normal View History

{
"ewc_loss": 8.285045623779297e-06,
"total_flos": 4.051147348618982e+19,
"train_loss": 0.44752783132196916,
"train_runtime": 39436.9749,
"train_samples": 125770,
"train_samples_per_second": 9.567,
"train_steps_per_second": 0.598
}