Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads4_seed1342/log2.txt
CHANGED
|
@@ -409,3 +409,65 @@ max_steps: 8750
|
|
| 409 |
6700 val loss 5.6444
|
| 410 |
6700 val perplexity 282.6929
|
| 411 |
6700 train 5.626853 (lr=1.1515e-05) (hash(x)=153333491)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 409 |
6700 val loss 5.6444
|
| 410 |
6700 val perplexity 282.6929
|
| 411 |
6700 train 5.626853 (lr=1.1515e-05) (hash(x)=153333491)
|
| 412 |
+
6800 val loss 5.6453
|
| 413 |
+
6800 val perplexity 282.9635
|
| 414 |
+
6800 train 5.398737 (lr=1.0923e-05) (hash(x)=150149382)
|
| 415 |
+
6900 val loss 5.6369
|
| 416 |
+
6900 val perplexity 280.5880
|
| 417 |
+
6900 train 5.727304 (lr=1.0356e-05) (hash(x)=152379767)
|
| 418 |
+
7000 val loss 5.6291
|
| 419 |
+
7000 val perplexity 278.4071
|
| 420 |
+
7000 train 5.677614 (lr=9.8138e-06) (hash(x)=150432537)
|
| 421 |
+
7100 val loss 5.6279
|
| 422 |
+
7100 val perplexity 278.0723
|
| 423 |
+
7100 train 5.507553 (lr=9.2971e-06) (hash(x)=148277836)
|
| 424 |
+
7200 val loss 5.6268
|
| 425 |
+
7200 val perplexity 277.7632
|
| 426 |
+
7200 train 5.624157 (lr=8.8068e-06) (hash(x)=168591659)
|
| 427 |
+
7300 val loss 5.6195
|
| 428 |
+
7300 val perplexity 275.7620
|
| 429 |
+
7300 train 5.602008 (lr=8.3436e-06) (hash(x)=152764851)
|
| 430 |
+
7400 val loss 5.6162
|
| 431 |
+
7400 val perplexity 274.8337
|
| 432 |
+
7400 train 5.581109 (lr=7.9082e-06) (hash(x)=142920131)
|
| 433 |
+
7500 val loss 5.6134
|
| 434 |
+
7500 val perplexity 274.0772
|
| 435 |
+
7500 train 5.612462 (lr=7.5012e-06) (hash(x)=146954649)
|
| 436 |
+
7600 val loss 5.6124
|
| 437 |
+
7600 val perplexity 273.7901
|
| 438 |
+
7600 train 5.388722 (lr=7.1232e-06) (hash(x)=144529566)
|
| 439 |
+
7700 val loss 5.6070
|
| 440 |
+
7700 val perplexity 272.3131
|
| 441 |
+
7700 train 5.565037 (lr=6.7747e-06) (hash(x)=142669945)
|
| 442 |
+
7800 val loss 5.6028
|
| 443 |
+
7800 val perplexity 271.1982
|
| 444 |
+
7800 train 5.664765 (lr=6.4563e-06) (hash(x)=161563764)
|
| 445 |
+
7900 val loss 5.6007
|
| 446 |
+
7900 val perplexity 270.6035
|
| 447 |
+
7900 train 5.400409 (lr=6.1684e-06) (hash(x)=141516532)
|
| 448 |
+
8000 val loss 5.6018
|
| 449 |
+
8000 val perplexity 270.9237
|
| 450 |
+
8000 train 5.473083 (lr=5.9114e-06) (hash(x)=152418457)
|
| 451 |
+
8100 val loss 5.5960
|
| 452 |
+
8100 val perplexity 269.3378
|
| 453 |
+
8100 train 5.576201 (lr=5.6857e-06) (hash(x)=161109470)
|
| 454 |
+
8200 val loss 5.5912
|
| 455 |
+
8200 val perplexity 268.0576
|
| 456 |
+
8200 train 5.706006 (lr=5.4917e-06) (hash(x)=154408822)
|
| 457 |
+
8300 val loss 5.5895
|
| 458 |
+
8300 val perplexity 267.6049
|
| 459 |
+
8300 train 5.478120 (lr=5.3295e-06) (hash(x)=146431691)
|
| 460 |
+
8400 val loss 5.5899
|
| 461 |
+
8400 val perplexity 267.7018
|
| 462 |
+
8400 train 5.372497 (lr=5.1995e-06) (hash(x)=150182527)
|
| 463 |
+
8500 val loss 5.5836
|
| 464 |
+
8500 val perplexity 266.0385
|
| 465 |
+
8500 train 5.651063 (lr=5.1019e-06) (hash(x)=154828709)
|
| 466 |
+
8600 val loss 5.5829
|
| 467 |
+
8600 val perplexity 265.8460
|
| 468 |
+
8600 train 5.502336 (lr=5.0367e-06) (hash(x)=154995428)
|
| 469 |
+
8700 val loss 5.5825
|
| 470 |
+
8700 val perplexity 265.7446
|
| 471 |
+
8700 train 5.482091 (lr=5.0041e-06) (hash(x)=142111043)
|
| 472 |
+
8749 val loss 5.5804
|
| 473 |
+
8749 val perplexity 265.1790
|
attention_kindselective_n_heads4_seed1342/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:c64de50d6baab738fd35d35d2e6dfc45c53988d4145bd8c7a0045ab9bbfb94f0
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1342/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 sha256:5b55767ecffb39585d3b9f4bc0d7a772f4b965b3c134e31bbc457729cd2f7fbd
|
| 3 |
size 179406214
|