Files
STAIR-Qwen2-7B-DPO-3/all_results.json

8 lines
201 B
JSON
Raw Normal View History

{
"epoch": 0.992,
"total_flos": 8638359306240.0,
"train_loss": 0.8013531161892798,
"train_runtime": 531.301,
"train_samples_per_second": 7.529,
"train_steps_per_second": 0.058
}