laion/nemotron-terminal-dependency_management__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/nemotron-terminal-dependency_management__Qwen3-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-23 16:38:11 +08:00
commit 6b631eb202
23 changed files with 154208 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": 101767.32661666165,
"achieved_tflops_per_gpu_theoretical": 2989585.235467485,
"epoch": 7.0,
"mfu_percent": 7192.037216725205,
"mfu_percent_theoretical": 211278.1085136032,
"total_flos": 2.6866574226798674e+18,
"train_loss": 0.0,
"train_runtime": 0.825,
"train_samples_per_second": 84297.403,
"train_steps_per_second": 882.429
}