初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama3-8b-base-new-method-q_t-0.4-s_star0.6
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-13 08:00:38 +08:00
commit 5155db5af1
496 changed files with 13684 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.9989528795811519,
"total_flos": 0.0,
"train_loss": 4.696330676288725,
"train_runtime": 6071.6812,
"train_samples": 61135,
"train_samples_per_second": 10.069,
"train_steps_per_second": 0.079
}