初始化项目,由ModelHub XC社区提供模型
Model: huseyinatahaninan/appworld_distillation_sft-SFT-Qwen3-4B-Instruct-2507 Source: Original Platform
This commit is contained in:
12
all_results.json
Normal file
12
all_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"eval_loss": 0.25876814126968384,
|
||||
"eval_runtime": 8.9435,
|
||||
"eval_samples_per_second": 4.361,
|
||||
"eval_steps_per_second": 0.559,
|
||||
"total_flos": 3.3888284102885376e+17,
|
||||
"train_loss": 0.3828152969479561,
|
||||
"train_runtime": 594.2554,
|
||||
"train_samples_per_second": 0.875,
|
||||
"train_steps_per_second": 0.034
|
||||
}
|
||||
Reference in New Issue
Block a user