qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919/train_results.json at main - qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919 - Gitea: Git with a cup of tea

W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919

Files

ModelHub XC 7ca2df9d3d 初始化项目，由ModelHub XC社区提供模型

Model: W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919
Source: Original Platform

2026-05-30 15:45:24 +08:00

9 lines

230 B

JSON

Raw Permalink Blame History

 {
     "epoch": 0.9989528795811519,
     "total_flos": 0.0,
     "train_loss": 4.881076782754382,
     "train_runtime": 7384.286,
     "train_samples": 61135,
     "train_samples_per_second": 8.279,
     "train_steps_per_second": 0.065
 }