初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama3-8b-base-new-method-s_star0.6-20260426-230653
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-05 23:45:11 +08:00
commit 7bc7b67926
27 changed files with 12247 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": 4.544049396954742,
"train_runtime": 6685.0038,
"train_samples": 61135,
"train_samples_per_second": 9.145,
"train_steps_per_second": 0.071
}