Files
llama-3-8b-base-simpo-8xh200/train_results.json

9 lines
231 B
JSON
Raw Normal View History

{
"epoch": 0.9989528795811519,
"total_flos": 0.0,
"train_loss": 2.230338767889411,
"train_runtime": 2802.8273,
"train_samples": 61135,
"train_samples_per_second": 21.812,
"train_steps_per_second": 0.17
}