mlfoundations-dev/oh-dcft-v3.1-llama-3.3-70b-qwen
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: mlfoundations-dev/oh-dcft-v3.1-llama-3.3-70b-qwen
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-08 18:55:13 +08:00
commit b594b8ca91
25 changed files with 5395 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
all_results.json Normal file
View File

@@ -0,0 +1,12 @@
{
"epoch": 2.999194198227236,
"eval_loss": 0.405712366104126,
"eval_runtime": 469.1641,
"eval_samples_per_second": 26.728,
"eval_steps_per_second": 0.418,
"total_flos": 2926650442383360.0,
"train_loss": 0.3617401811868598,
"train_runtime": 75547.7589,
"train_samples_per_second": 9.461,
"train_steps_per_second": 0.074
}