初始化项目,由ModelHub XC社区提供模型
Model: leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic Source: Original Platform
This commit is contained in:
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.013345611529686698,
|
||||
"train_runtime": 16054.0136,
|
||||
"train_samples": 3053,
|
||||
"train_samples_per_second": 0.951,
|
||||
"train_steps_per_second": 0.118
|
||||
}
|
||||
Reference in New Issue
Block a user