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

11 lines
337 B
JSON
Raw Normal View History

{
"ewc_loss": 0.0849609375,
"ewc_loss_diag": 3.457069396972656e-05,
"ewc_loss_parallel": 0.0005035400390625,
"total_flos": 5.62815163329864e+19,
"train_loss": 0.4737072293779522,
"train_runtime": 48395.8245,
"train_samples": 125770,
"train_samples_per_second": 7.796,
"train_steps_per_second": 0.487
}