laion/nemotron-terminal-data_processing__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-data_processing__Qwen3-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-12 05:15:30 +08:00
commit 754d4ef06b
23 changed files with 154088 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
all_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 55493.00432659637,
"achieved_tflops_per_gpu_theoretical": 1813433.511628669,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.11563363671302795,
"mfu_percent": 3921.7670902188247,
"mfu_percent_theoretical": 128157.84534478225,
"total_flos": 2.2525720316251996e+18,
"train_loss": 0.0,
"train_runtime": 1.2685,
"train_samples_per_second": 51247.723,
"train_steps_per_second": 535.267,
"valid_targets_mean": 7221.4,
"valid_targets_min": 1533
}