Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads4_seed1345/log2.txt
CHANGED
|
@@ -403,3 +403,68 @@ max_steps: 8750
|
|
| 403 |
6600 val loss 5.5983
|
| 404 |
6600 val perplexity 269.9799
|
| 405 |
6600 train 5.537288 (lr=1.2129e-05) (hash(x)=142131981)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 403 |
6600 val loss 5.5983
|
| 404 |
6600 val perplexity 269.9799
|
| 405 |
6600 train 5.537288 (lr=1.2129e-05) (hash(x)=142131981)
|
| 406 |
+
6700 val loss 5.5893
|
| 407 |
+
6700 val perplexity 267.5391
|
| 408 |
+
6700 train 5.698772 (lr=1.1515e-05) (hash(x)=154916248)
|
| 409 |
+
6800 val loss 5.5903
|
| 410 |
+
6800 val perplexity 267.8165
|
| 411 |
+
6800 train 5.591829 (lr=1.0923e-05) (hash(x)=147996387)
|
| 412 |
+
6900 val loss 5.5834
|
| 413 |
+
6900 val perplexity 265.9748
|
| 414 |
+
6900 train 5.607487 (lr=1.0356e-05) (hash(x)=153422428)
|
| 415 |
+
7000 val loss 5.5752
|
| 416 |
+
7000 val perplexity 263.8125
|
| 417 |
+
7000 train 5.598151 (lr=9.8138e-06) (hash(x)=174135078)
|
| 418 |
+
7100 val loss 5.5740
|
| 419 |
+
7100 val perplexity 263.4814
|
| 420 |
+
7100 train 5.648017 (lr=9.2971e-06) (hash(x)=160382475)
|
| 421 |
+
7200 val loss 5.5686
|
| 422 |
+
7200 val perplexity 262.0726
|
| 423 |
+
7200 train 5.660019 (lr=8.8068e-06) (hash(x)=155310085)
|
| 424 |
+
7300 val loss 5.5638
|
| 425 |
+
7300 val perplexity 260.8198
|
| 426 |
+
7300 train 5.702147 (lr=8.3436e-06) (hash(x)=159329031)
|
| 427 |
+
7400 val loss 5.5613
|
| 428 |
+
7400 val perplexity 260.1701
|
| 429 |
+
7400 train 5.505960 (lr=7.9082e-06) (hash(x)=151577269)
|
| 430 |
+
7500 val loss 5.5595
|
| 431 |
+
7500 val perplexity 259.6977
|
| 432 |
+
7500 train 5.610840 (lr=7.5012e-06) (hash(x)=160620287)
|
| 433 |
+
7600 val loss 5.5536
|
| 434 |
+
7600 val perplexity 258.1681
|
| 435 |
+
7600 train 5.438733 (lr=7.1232e-06) (hash(x)=143711597)
|
| 436 |
+
7700 val loss 5.5523
|
| 437 |
+
7700 val perplexity 257.8305
|
| 438 |
+
7700 train 5.543999 (lr=6.7747e-06) (hash(x)=149243577)
|
| 439 |
+
7800 val loss 5.5501
|
| 440 |
+
7800 val perplexity 257.2609
|
| 441 |
+
7800 train 5.535831 (lr=6.4563e-06) (hash(x)=147677247)
|
| 442 |
+
7900 val loss 5.5438
|
| 443 |
+
7900 val perplexity 255.6460
|
| 444 |
+
7900 train 5.489839 (lr=6.1684e-06) (hash(x)=145801236)
|
| 445 |
+
8000 val loss 5.5434
|
| 446 |
+
8000 val perplexity 255.5333
|
| 447 |
+
8000 train 5.662671 (lr=5.9114e-06) (hash(x)=158007655)
|
| 448 |
+
8100 val loss 5.5417
|
| 449 |
+
8100 val perplexity 255.1080
|
| 450 |
+
8100 train 5.596391 (lr=5.6857e-06) (hash(x)=158030048)
|
| 451 |
+
8200 val loss 5.5377
|
| 452 |
+
8200 val perplexity 254.0914
|
| 453 |
+
8200 train 5.387879 (lr=5.4917e-06) (hash(x)=150674725)
|
| 454 |
+
8300 val loss 5.5367
|
| 455 |
+
8300 val perplexity 253.8395
|
| 456 |
+
8300 train 5.435452 (lr=5.3295e-06) (hash(x)=150805711)
|
| 457 |
+
8400 val loss 5.5326
|
| 458 |
+
8400 val perplexity 252.8029
|
| 459 |
+
8400 train 5.404875 (lr=5.1995e-06) (hash(x)=138396210)
|
| 460 |
+
8500 val loss 5.5328
|
| 461 |
+
8500 val perplexity 252.8460
|
| 462 |
+
8500 train 5.411557 (lr=5.1019e-06) (hash(x)=156172740)
|
| 463 |
+
8600 val loss 5.5295
|
| 464 |
+
8600 val perplexity 252.0196
|
| 465 |
+
8600 train 5.562200 (lr=5.0367e-06) (hash(x)=154911352)
|
| 466 |
+
8700 val loss 5.5264
|
| 467 |
+
8700 val perplexity 251.2275
|
| 468 |
+
8700 train 5.586018 (lr=5.0041e-06) (hash(x)=153446789)
|
| 469 |
+
8749 val loss 5.5250
|
| 470 |
+
8749 val perplexity 250.8740
|
attention_kindselective_n_heads4_seed1345/model_08749.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 92843394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2bb623dddd3faa4a09d256c50c49812e2dbc40e5f8b494fa876509fc1de1941
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1345/optimizer_08749.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 179406214
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:391d8a37df688a415cac09b4f1d8971bb40a6a43831e9ac2785edd05fe4ebc85
|
| 3 |
size 179406214
|