Files
P9-split5_only_answer_Qwen3…/train_results.json

9 lines
232 B
JSON
Raw Normal View History

{
"epoch": 6.0,
"total_flos": 519624752562176.0,
"train_loss": 0.5481295004301296,
"train_runtime": 70704.5263,
"train_samples": 41198,
"train_samples_per_second": 3.496,
"train_steps_per_second": 0.008
}