Files
OLMo-2-1124-7B-Instruct_SFT…/train_results.json

11 lines
342 B
JSON
Raw Permalink Normal View History

{
"ewc_loss": 0.1064453125,
"ewc_loss_diag": 0.0003643035888671875,
"ewc_loss_parallel": 7.009506225585938e-05,
"total_flos": 5.156325133756924e+19,
"train_loss": 0.46243270478726584,
"train_runtime": 51121.2309,
"train_samples": 125770,
"train_samples_per_second": 7.381,
"train_steps_per_second": 0.461
}