Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads4_seed1344/log2.txt
CHANGED
|
@@ -451,3 +451,44 @@ max_steps: 8750
|
|
| 451 |
7400 val loss 5.8403
|
| 452 |
7400 val perplexity 343.8778
|
| 453 |
7400 train 5.662089 (lr=6.3266e-06) (hash(x)=145294178)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 451 |
7400 val loss 5.8403
|
| 452 |
7400 val perplexity 343.8778
|
| 453 |
7400 train 5.662089 (lr=6.3266e-06) (hash(x)=145294178)
|
| 454 |
+
7500 val loss 5.8383
|
| 455 |
+
7500 val perplexity 343.1886
|
| 456 |
+
7500 train 5.605683 (lr=6.0010e-06) (hash(x)=150573713)
|
| 457 |
+
7600 val loss 5.8350
|
| 458 |
+
7600 val perplexity 342.0600
|
| 459 |
+
7600 train 5.852287 (lr=5.6986e-06) (hash(x)=142771511)
|
| 460 |
+
7700 val loss 5.8286
|
| 461 |
+
7700 val perplexity 339.8656
|
| 462 |
+
7700 train 5.725527 (lr=5.4198e-06) (hash(x)=143602175)
|
| 463 |
+
7800 val loss 5.8250
|
| 464 |
+
7800 val perplexity 338.6624
|
| 465 |
+
7800 train 5.857786 (lr=5.1650e-06) (hash(x)=152379862)
|
| 466 |
+
7900 val loss 5.8238
|
| 467 |
+
7900 val perplexity 338.2581
|
| 468 |
+
7900 train 5.664768 (lr=4.9347e-06) (hash(x)=146655921)
|
| 469 |
+
8000 val loss 5.8242
|
| 470 |
+
8000 val perplexity 338.4018
|
| 471 |
+
8000 train 5.935122 (lr=4.7291e-06) (hash(x)=148262482)
|
| 472 |
+
8100 val loss 5.8166
|
| 473 |
+
8100 val perplexity 335.8375
|
| 474 |
+
8100 train 5.753369 (lr=4.5486e-06) (hash(x)=147683655)
|
| 475 |
+
8200 val loss 5.8155
|
| 476 |
+
8200 val perplexity 335.4515
|
| 477 |
+
8200 train 5.876520 (lr=4.3933e-06) (hash(x)=164975934)
|
| 478 |
+
8300 val loss 5.8120
|
| 479 |
+
8300 val perplexity 334.2799
|
| 480 |
+
8300 train 5.729677 (lr=4.2636e-06) (hash(x)=145300550)
|
| 481 |
+
8400 val loss 5.8100
|
| 482 |
+
8400 val perplexity 333.6333
|
| 483 |
+
8400 train 5.721456 (lr=4.1596e-06) (hash(x)=150679400)
|
| 484 |
+
8500 val loss 5.8102
|
| 485 |
+
8500 val perplexity 333.6947
|
| 486 |
+
8500 train 5.822725 (lr=4.0815e-06) (hash(x)=164109401)
|
| 487 |
+
8600 val loss 5.8071
|
| 488 |
+
8600 val perplexity 332.6415
|
| 489 |
+
8600 train 5.800099 (lr=4.0294e-06) (hash(x)=161036376)
|
| 490 |
+
8700 val loss 5.8029
|
| 491 |
+
8700 val perplexity 331.2553
|
| 492 |
+
8700 train 5.736811 (lr=4.0033e-06) (hash(x)=153828820)
|
| 493 |
+
8749 val loss 5.8012
|
| 494 |
+
8749 val perplexity 330.7012
|
attention_kindselective_n_heads4_seed1344/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 sha256:883f9a6eef276c05beb952634c52bbc6e83e399d790fd34ec66cd002ab63319e
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1344/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 sha256:11a8da35040e3dcb60b93f1d0e06cd32200bd13e83ffd949d3626688fcd9dd31
|
| 3 |
size 179406214
|