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

11 lines
336 B
JSON
Raw Permalink Normal View History

{
"ewc_loss": 0.50390625,
"ewc_loss_diag": 0.000789642333984375,
"ewc_loss_parallel": 0.000423431396484375,
"total_flos": 5.156325133756924e+19,
"train_loss": 0.8269113934204859,
"train_runtime": 50783.0573,
"train_samples": 125770,
"train_samples_per_second": 7.43,
"train_steps_per_second": 0.464
}