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

8 lines
220 B
JSON
Raw Normal View History

{
"total_flos": 5.1161189248846004e+19,
"train_loss": 0.3374735962292906,
"train_runtime": 47030.8323,
"train_samples": 125770,
"train_samples_per_second": 8.023,
"train_steps_per_second": 0.501
}