初始化项目,由ModelHub XC社区提供模型

Model: graf/Qwen3-4B-SFT-science-1e-5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-30 05:11:19 +08:00
commit afd3adcaa1
20 changed files with 170647 additions and 0 deletions

12
all_results.json Normal file
View File

@@ -0,0 +1,12 @@
{
"epoch": 3.0,
"eval_loss": 0.6777992248535156,
"eval_runtime": 73.1369,
"eval_samples_per_second": 70.99,
"eval_steps_per_second": 8.874,
"total_flos": 8.852766725217714e+18,
"train_loss": 0.6584745990833162,
"train_runtime": 19013.667,
"train_samples_per_second": 15.562,
"train_steps_per_second": 0.122
}