openthoughts3_100k_qwen25_1b_bsz256_lr16e5_epochs5/train_results.json at main - openthoughts3_100k_qwen25_1b_bsz256_lr16e5_epochs5 - Gitea: Git with a cup of tea

mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz256_lr16e5_epochs5

Files

ModelHub XC 84f44cd484 初始化项目，由ModelHub XC社区提供模型

Model: mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz256_lr16e5_epochs5
Source: Original Platform

2026-06-16 07:03:13 +08:00

8 lines

206 B

JSON

Raw Permalink Blame History

 {
     "epoch": 5.0,
     "total_flos": 7122204608430080.0,
     "train_loss": 1.0036099467436066,
     "train_runtime": 36219.8634,
     "train_samples_per_second": 13.805,
     "train_steps_per_second": 0.054
 }