Files
Qwen2.5-1.5B-DPO-Tulu3-deco…/train_results.json
ModelHub XC 6cfa14f09a 初始化项目,由ModelHub XC社区提供模型
Model: ali-elganzory/Qwen2.5-1.5B-DPO-Tulu3-decontaminated-masked
Source: Original Platform
2026-08-23 06:43:28 +08:00

9 lines
219 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 2.9490895759331788,
"train_runtime": 4813.8824,
"train_samples": 272585,
"train_samples_per_second": 56.625,
"train_steps_per_second": 0.442
}