Files
P2-split5_prob_Qwen3-8B-Bas…/train_results.json

9 lines
232 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 597372590817280.0,
"train_loss": 0.4411480824549993,
"train_runtime": 57703.0115,
"train_samples": 24520,
"train_samples_per_second": 1.275,
"train_steps_per_second": 0.013
}