初始化项目,由ModelHub XC社区提供模型

Model: ali-elganzory/1.7b-MixtureVitae-web_curated-100BT-longsft_16k-SFT-Tulu3-decontaminated
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-14 22:38:41 +08:00
commit a04e4f2b55
16 changed files with 267025 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"total_flos": 2.19812273324032e+16,
"train_loss": 0.2031160936633208,
"train_runtime": 9356.8224,
"train_samples": 936509,
"train_samples_per_second": 200.177,
"train_steps_per_second": 1.564
}