- reports/loss-v1.csv: full train/val loss log over 20k steps - reports/loss-v1.txt: ASCII loss curve (steep descent then flattening tail) Training ran ~58 min on M1 MPS at 5.7 it/s. No overfitting (train~=val).
23 lines
1.5 KiB
Plaintext
23 lines
1.5 KiB
Plaintext
loss curve — v1 (final train 1.5122, val 1.5198 @ iter 19500)
|
|
2.829 |*
|
|
2.751 |
|
|
2.674 |
|
|
2.596 |
|
|
2.519 |
|
|
2.441 |
|
|
2.364 | *
|
|
2.286 |
|
|
2.209 |
|
|
2.132 | *
|
|
2.054 |
|
|
1.977 | *
|
|
1.899 | **
|
|
1.822 | * **
|
|
1.744 | . * ** *
|
|
1.667 | . ** * ** * *
|
|
1.590 | * ** * ** * ** *
|
|
1.512 | ** * ** * ** *
|
|
+----------------------------------------------------------------
|
|
500 19500
|
|
legend: '.' train '*' val (x: iter, y: loss)
|