Files
qwen2_7B-dis-wspo-full_E1/train_results.json

8 lines
218 B
JSON
Raw Normal View History

{
"epoch": 0.9998691270776077,
"total_flos": 167763918716928.0,
"train_loss": 0.3737170026252407,
"train_runtime": 21184.4179,
"train_samples_per_second": 2.886,
"train_steps_per_second": 0.09
}