Epoch 200 - 67.05% acc
Browse files
weights/run_001_v2_wormhole_d512_4layer_20251130_022121/best.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 69963796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a482d02ed275dfa644e4ca7ea64d1648a50cf314d7413bf9e222b8e929914434
|
| 3 |
size 69963796
|
weights/run_001_v2_wormhole_d512_4layer_20251130_022121/tensorboard/events.out.tfevents.1764469305.c46210e51d85.2903.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15cb62eb5d1aff9e4bd4cad4b2e0b662299d354fd68a07c013b4a17adddcc836
|
| 3 |
+
size 819230
|
weights/run_001_v2_wormhole_d512_4layer_20251130_022121/training_history.json
CHANGED
|
@@ -188,7 +188,17 @@
|
|
| 188 |
3.647988961598812,
|
| 189 |
3.44115648942116,
|
| 190 |
3.5505316446989013,
|
| 191 |
-
3.330778726706138
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 192 |
],
|
| 193 |
"ce": [
|
| 194 |
4.461190643066015,
|
|
@@ -379,7 +389,17 @@
|
|
| 379 |
1.6155734103459578,
|
| 380 |
1.4767984362748954,
|
| 381 |
1.5975997496109742,
|
| 382 |
-
1.4968816588322322
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 383 |
],
|
| 384 |
"contrast": [
|
| 385 |
4.598483383961213,
|
|
@@ -570,7 +590,17 @@
|
|
| 570 |
2.032415588391133,
|
| 571 |
1.964358079739106,
|
| 572 |
1.9529318985266564,
|
| 573 |
-
1.8338970596973712
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 574 |
],
|
| 575 |
"lr": [
|
| 576 |
2.9999999999999997e-05,
|
|
@@ -761,6 +791,16 @@
|
|
| 761 |
1.5134556848374758e-06,
|
| 762 |
1.3286790323914947e-06,
|
| 763 |
1.1849114449367806e-06,
|
| 764 |
-
1.0821922270962664e-06
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 765 |
]
|
| 766 |
}
|
|
|
|
| 188 |
3.647988961598812,
|
| 189 |
3.44115648942116,
|
| 190 |
3.5505316446989013,
|
| 191 |
+
3.330778726706138,
|
| 192 |
+
3.4423313472515495,
|
| 193 |
+
3.436019718188506,
|
| 194 |
+
3.1792961883239257,
|
| 195 |
+
3.4502090813257755,
|
| 196 |
+
3.369716432919869,
|
| 197 |
+
3.4693310332603944,
|
| 198 |
+
3.468750510154626,
|
| 199 |
+
3.2626821064032043,
|
| 200 |
+
3.4209925189996375,
|
| 201 |
+
3.258312143270786
|
| 202 |
],
|
| 203 |
"ce": [
|
| 204 |
4.461190643066015,
|
|
|
|
| 389 |
1.6155734103459578,
|
| 390 |
1.4767984362748954,
|
| 391 |
1.5975997496109742,
|
| 392 |
+
1.4968816588322322,
|
| 393 |
+
1.5467539202708465,
|
| 394 |
+
1.483526768287023,
|
| 395 |
+
1.4398977349201838,
|
| 396 |
+
1.4325734826998833,
|
| 397 |
+
1.559209577471782,
|
| 398 |
+
1.5612513733979982,
|
| 399 |
+
1.5389799654483796,
|
| 400 |
+
1.4002321782784584,
|
| 401 |
+
1.4625379075606664,
|
| 402 |
+
1.4116449466118446
|
| 403 |
],
|
| 404 |
"contrast": [
|
| 405 |
4.598483383961213,
|
|
|
|
| 590 |
2.032415588391133,
|
| 591 |
1.964358079739106,
|
| 592 |
1.9529318985266564,
|
| 593 |
+
1.8338970596973712,
|
| 594 |
+
1.8955774230834765,
|
| 595 |
+
1.9524929550213692,
|
| 596 |
+
1.7393984741125352,
|
| 597 |
+
2.017635612304394,
|
| 598 |
+
1.8105068715719077,
|
| 599 |
+
1.9080796706370817,
|
| 600 |
+
1.9297705620527268,
|
| 601 |
+
1.862449910549017,
|
| 602 |
+
1.9584546154890305,
|
| 603 |
+
1.846667198340098
|
| 604 |
],
|
| 605 |
"lr": [
|
| 606 |
2.9999999999999997e-05,
|
|
|
|
| 791 |
1.5134556848374758e-06,
|
| 792 |
1.3286790323914947e-06,
|
| 793 |
1.1849114449367806e-06,
|
| 794 |
+
1.0821922270962664e-06,
|
| 795 |
+
1.0205494612784436e-06,
|
| 796 |
+
1e-06,
|
| 797 |
+
1.0204359036258838e-06,
|
| 798 |
+
1.0817380275315555e-06,
|
| 799 |
+
1.1838896123284415e-06,
|
| 800 |
+
1.3268627307932066e-06,
|
| 801 |
+
1.5106182955028572e-06,
|
| 802 |
+
1.7351060695207923e-06,
|
| 803 |
+
2.00026468013108e-06,
|
| 804 |
+
2.306021635617207e-06
|
| 805 |
]
|
| 806 |
}
|