Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads4_seed1343/log2.txt
CHANGED
|
@@ -400,3 +400,71 @@ max_steps: 8750
|
|
| 400 |
6500 train 5.650785 (lr=1.2766e-05) (hash(x)=144616373)
|
| 401 |
8749 val loss 5.6585
|
| 402 |
8749 val perplexity 286.7288
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 400 |
6500 train 5.650785 (lr=1.2766e-05) (hash(x)=144616373)
|
| 401 |
8749 val loss 5.6585
|
| 402 |
8749 val perplexity 286.7288
|
| 403 |
+
6600 val loss 5.6621
|
| 404 |
+
6600 val perplexity 287.7638
|
| 405 |
+
6600 train 5.484093 (lr=1.2129e-05) (hash(x)=145266452)
|
| 406 |
+
6700 val loss 5.6560
|
| 407 |
+
6700 val perplexity 286.0123
|
| 408 |
+
6700 train 5.652499 (lr=1.1515e-05) (hash(x)=149952261)
|
| 409 |
+
6800 val loss 5.6499
|
| 410 |
+
6800 val perplexity 284.2496
|
| 411 |
+
6800 train 5.533232 (lr=1.0923e-05) (hash(x)=143351199)
|
| 412 |
+
6900 val loss 5.6497
|
| 413 |
+
6900 val perplexity 284.1957
|
| 414 |
+
6900 train 5.607444 (lr=1.0356e-05) (hash(x)=156055618)
|
| 415 |
+
7000 val loss 5.6418
|
| 416 |
+
7000 val perplexity 281.9726
|
| 417 |
+
7000 train 5.713253 (lr=9.8138e-06) (hash(x)=164290908)
|
| 418 |
+
7100 val loss 5.6384
|
| 419 |
+
7100 val perplexity 281.0004
|
| 420 |
+
7100 train 5.740729 (lr=9.2971e-06) (hash(x)=150263832)
|
| 421 |
+
7200 val loss 5.6352
|
| 422 |
+
7200 val perplexity 280.1169
|
| 423 |
+
7200 train 5.315210 (lr=8.8068e-06) (hash(x)=139219680)
|
| 424 |
+
7300 val loss 5.6297
|
| 425 |
+
7300 val perplexity 278.5819
|
| 426 |
+
7300 train 5.575299 (lr=8.3436e-06) (hash(x)=150662994)
|
| 427 |
+
7400 val loss 5.6261
|
| 428 |
+
7400 val perplexity 277.5779
|
| 429 |
+
7400 train 5.465163 (lr=7.9082e-06) (hash(x)=139007967)
|
| 430 |
+
7500 val loss 5.6249
|
| 431 |
+
7500 val perplexity 277.2398
|
| 432 |
+
7500 train 5.455156 (lr=7.5012e-06) (hash(x)=138142461)
|
| 433 |
+
7600 val loss 5.6196
|
| 434 |
+
7600 val perplexity 275.7852
|
| 435 |
+
7600 train 5.530750 (lr=7.1232e-06) (hash(x)=150023998)
|
| 436 |
+
7700 val loss 5.6152
|
| 437 |
+
7700 val perplexity 274.5555
|
| 438 |
+
7700 train 5.509050 (lr=6.7747e-06) (hash(x)=143393355)
|
| 439 |
+
7800 val loss 5.6149
|
| 440 |
+
7800 val perplexity 274.4759
|
| 441 |
+
7800 train 5.480126 (lr=6.4563e-06) (hash(x)=144916472)
|
| 442 |
+
7900 val loss 5.6097
|
| 443 |
+
7900 val perplexity 273.0717
|
| 444 |
+
7900 train 5.565450 (lr=6.1684e-06) (hash(x)=150236934)
|
| 445 |
+
8000 val loss 5.6071
|
| 446 |
+
8000 val perplexity 272.3544
|
| 447 |
+
8000 train 5.608926 (lr=5.9114e-06) (hash(x)=146536422)
|
| 448 |
+
8100 val loss 5.6069
|
| 449 |
+
8100 val perplexity 272.3043
|
| 450 |
+
8100 train 5.441198 (lr=5.6857e-06) (hash(x)=151300857)
|
| 451 |
+
8200 val loss 5.6050
|
| 452 |
+
8200 val perplexity 271.7760
|
| 453 |
+
8200 train 5.634646 (lr=5.4917e-06) (hash(x)=160351956)
|
| 454 |
+
8300 val loss 5.6014
|
| 455 |
+
8300 val perplexity 270.8028
|
| 456 |
+
8300 train 5.654285 (lr=5.3295e-06) (hash(x)=150514540)
|
| 457 |
+
8400 val loss 5.5999
|
| 458 |
+
8400 val perplexity 270.4036
|
| 459 |
+
8400 train 5.547650 (lr=5.1995e-06) (hash(x)=155904762)
|
| 460 |
+
8500 val loss 5.5998
|
| 461 |
+
8500 val perplexity 270.3614
|
| 462 |
+
8500 train 5.406527 (lr=5.1019e-06) (hash(x)=146923196)
|
| 463 |
+
8600 val loss 5.5961
|
| 464 |
+
8600 val perplexity 269.3655
|
| 465 |
+
8600 train 5.577782 (lr=5.0367e-06) (hash(x)=138977080)
|
| 466 |
+
8700 val loss 5.5944
|
| 467 |
+
8700 val perplexity 268.9079
|
| 468 |
+
8700 train 5.395451 (lr=5.0041e-06) (hash(x)=146442792)
|
| 469 |
+
8749 val loss 5.5935
|
| 470 |
+
8749 val perplexity 268.6727
|
attention_kindselective_n_heads4_seed1343/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 sha256:79630c585ae01a12e0da13e054f4d31bdbcb07132557794724704b86dc5f2eb8
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1343/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 sha256:496cc404e3f894099d946fd893c46f5c9984530da6547230964b29331cc3799f
|
| 3 |
size 179406214
|