初始化项目,由ModelHub XC社区提供模型
Model: graf/Qwen3-4B-SFT-science-1e-5 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": 3.0,
|
||||
"eval_loss": 0.6777992248535156,
|
||||
"eval_runtime": 73.1369,
|
||||
"eval_samples_per_second": 70.99,
|
||||
"eval_steps_per_second": 8.874,
|
||||
"total_flos": 8.852766725217714e+18,
|
||||
"train_loss": 0.6584745990833162,
|
||||
"train_runtime": 19013.667,
|
||||
"train_samples_per_second": 15.562,
|
||||
"train_steps_per_second": 0.122
|
||||
}
|
||||
Reference in New Issue
Block a user