laion/nemotron-terminal-file_operations__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-file_operations__Qwen3-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-25 13:43:02 +08:00
commit 9b8b38a224
23 changed files with 155288 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": 105365.67588997465,
"achieved_tflops_per_gpu_theoretical": 2868955.5056036036,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.17860357463359833,
"mfu_percent": 7446.337518726124,
"mfu_percent_theoretical": 202753.03926527235,
"total_flos": 4.68228205146905e+18,
"train_loss": 0.0,
"train_runtime": 1.3887,
"train_samples_per_second": 81133.704,
"train_steps_per_second": 846.823,
"valid_targets_mean": 9335.2,
"valid_targets_min": 3239
}