初始化项目,由ModelHub XC社区提供模型

Model: akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-13 04:40:09 +08:00
commit 584122fc98
12 changed files with 2934 additions and 0 deletions

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"total_flos": 287156144701440.0,
"train_loss": 0.4225423020029825,
"train_runtime": 9655.7571,
"train_samples": 18521,
"train_samples_per_second": 2.082,
"train_steps_per_second": 0.033
}