初始化项目,由ModelHub XC社区提供模型
Model: laion/swesmith-316__Qwen3-8B Source: Original Platform
This commit is contained in:
16
all_results.json
Normal file
16
all_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 2.551643175725337,
|
||||
"achieved_tflops_per_gpu_theoretical": 132.12827795010355,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.20894506573677063,
|
||||
"mfu_percent": 0.1803281396272323,
|
||||
"mfu_percent_theoretical": 9.337687487639826,
|
||||
"total_flos": 5.930599290241024e+16,
|
||||
"train_loss": 0.2524434221642358,
|
||||
"train_runtime": 726.3211,
|
||||
"train_samples_per_second": 3.045,
|
||||
"train_steps_per_second": 0.039,
|
||||
"valid_targets_mean": 5717.0,
|
||||
"valid_targets_min": 1502
|
||||
}
|
||||
Reference in New Issue
Block a user