Model: Hyeongwon/P2-split2_prob_Qwen3-8B-Base_0325-04-bs128-lr1e-5-epoch6 Source: Original Platform
9 lines
232 B
JSON
9 lines
232 B
JSON
{
|
|
"epoch": 6.0,
|
|
"total_flos": 1202499003482112.0,
|
|
"train_loss": 0.440722111040953,
|
|
"train_runtime": 115067.3138,
|
|
"train_samples": 24556,
|
|
"train_samples_per_second": 1.28,
|
|
"train_steps_per_second": 0.007
|
|
} |