QWEN3-4B-Base-stage2/train_results.json at 575758bd08d5660364c45654d1f9f791f6bda652 - QWEN3-4B-Base-stage2 - Gitea: Git with a cup of tea

alwaysgood/QWEN3-4B-Base-stage2

Files

ModelHub XC 575758bd08 初始化项目，由ModelHub XC社区提供模型

Model: alwaysgood/QWEN3-4B-Base-stage2
Source: Original Platform

2026-05-01 17:47:32 +08:00

8 lines

208 B

JSON

Raw Blame History

 {
     "epoch": 1.0,
     "total_flos": 1.6013083311596544e+16,
     "train_loss": 1.9567182964748806,
     "train_runtime": 294.7814,
     "train_samples_per_second": 12.087,
     "train_steps_per_second": 0.305
 }