openthoughts3_100k_qwen25_1b_bsz512_lr16e5_epochs5/train_results.json at main - openthoughts3_100k_qwen25_1b_bsz512_lr16e5_epochs5 - Gitea: Git with a cup of tea

mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz512_lr16e5_epochs5

Files

ModelHub XC c87c4f234b 初始化项目，由ModelHub XC社区提供模型

Model: mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz512_lr16e5_epochs5
Source: Original Platform

2026-09-20 09:48:14 +08:00

8 lines

219 B

JSON

Raw Permalink Blame History

 {
     "epoch": 4.987212276214834,
     "total_flos": 7100358600687616.0,
     "train_loss": 1.0383980158047799,
     "train_runtime": 35038.9958,
     "train_samples_per_second": 14.27,
     "train_steps_per_second": 0.028
 }