Files
OLMo-2-0425-1B-Instruct_SFT…/train_results.json

8 lines
221 B
JSON
Raw Normal View History

{
"total_flos": 9.578088657357636e+18,
"train_loss": 0.46163898064592473,
"train_runtime": 11201.6896,
"train_samples": 125770,
"train_samples_per_second": 33.683,
"train_steps_per_second": 2.105
}