SmolLM2-1.7B-WithChatTemplate-DPO-Tulu3-decontaminated-masked/train_results.json at main - SmolLM2-1.7B-WithChatTemplate-DPO-Tulu3-decontaminated-masked - Gitea: Git with a cup of tea

ali-elganzory/SmolLM2-1.7B-WithChatTemplate-DPO-Tulu3-decontaminated-masked

Files

ModelHub XC 45298283e8 初始化项目，由ModelHub XC社区提供模型

Model: ali-elganzory/SmolLM2-1.7B-WithChatTemplate-DPO-Tulu3-decontaminated-masked
Source: Original Platform

2026-08-30 06:04:17 +08:00

9 lines

219 B

JSON

Raw Permalink Blame History

 {
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 3.0287644077354754,
     "train_runtime": 5560.8629,
     "train_samples": 272585,
     "train_samples_per_second": 49.018,
     "train_steps_per_second": 0.383
 }