laion/swesmith-3160__Qwen3-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: laion/swesmith-3160__Qwen3-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-27 08:32:18 +08:00
commit 4d7471389d
23 changed files with 153020 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
train_results.json Normal file
View File

@@ -0,0 +1,12 @@
{
"achieved_tflops_per_gpu": 25246.89276564641,
"achieved_tflops_per_gpu_theoretical": 950998.3624027147,
"epoch": 7.0,
"mfu_percent": 1784.2327042859654,
"mfu_percent_theoretical": 67208.36483411411,
"total_flos": 6.648213778192138e+17,
"train_loss": 0.0,
"train_runtime": 0.8229,
"train_samples_per_second": 26879.554,
"train_steps_per_second": 280.704
}