初始化项目,由ModelHub XC社区提供模型
Model: open-sci/sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated 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": 5.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.4691426753997803,
|
||||
"total_flos": 1658037051588608.0,
|
||||
"train_loss": 1.0214215231449046,
|
||||
"train_runtime": 6105.894,
|
||||
"train_samples_per_second": 24.566,
|
||||
"train_steps_per_second": 0.192,
|
||||
"valid_targets_mean": 13499.5,
|
||||
"valid_targets_min": 3345
|
||||
}
|
||||
Reference in New Issue
Block a user