Llama-3.1-8B-Instruct_SFT_mathfisher_v00.03/train_results.json at main - Llama-3.1-8B-Instruct_SFT_mathfisher_v00.03 - Gitea: Git with a cup of tea

Neelectric/Llama-3.1-8B-Instruct_SFT_mathfisher_v00.03

Files

ModelHub XC 42f9cc64eb 初始化项目，由ModelHub XC社区提供模型

Model: Neelectric/Llama-3.1-8B-Instruct_SFT_mathfisher_v00.03
Source: Original Platform

2026-05-13 12:50:24 +08:00

9 lines

259 B

JSON

Raw Permalink Blame History

 {
     "ewc_loss": 8.285045623779297e-06,
     "total_flos": 4.051147348618982e+19,
     "train_loss": 0.44752783132196916,
     "train_runtime": 39436.9749,
     "train_samples": 125770,
     "train_samples_per_second": 9.567,
     "train_steps_per_second": 0.598
 }