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

11 lines
340 B
JSON
Raw Normal View History

{
"ewc_loss": 0.224609375,
"ewc_loss_diag": 2.4199485778808594e-05,
"ewc_loss_parallel": 0.0002002716064453125,
"total_flos": 5.62815163329864e+19,
"train_loss": 0.5611200594813073,
"train_runtime": 47572.7611,
"train_samples": 125770,
"train_samples_per_second": 7.931,
"train_steps_per_second": 0.496
}