qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.6/train_results.json at 9268b0b92957a879c89386c8d714d2e64e8d8da5 - qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.6 - Gitea: Git with a cup of tea

jackf857/qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.6

Files

ModelHub XC 9268b0b929 初始化项目，由ModelHub XC社区提供模型

Model: jackf857/qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.6
Source: Original Platform

2026-05-13 01:12:57 +08:00

9 lines

232 B

JSON

Raw Blame History

 {
     "epoch": 0.999244142101285,
     "total_flos": 0.0,
     "train_loss": 1.1374638212250148,
     "train_runtime": 2122.2138,
     "train_samples": 42336,
     "train_samples_per_second": 19.949,
     "train_steps_per_second": 0.311
 }