Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads4_seed1340/log2.txt
CHANGED
|
@@ -394,3 +394,71 @@ max_steps: 8750
|
|
| 394 |
6500 val loss 5.7195
|
| 395 |
6500 val perplexity 304.7384
|
| 396 |
6500 train 5.640700 (lr=1.2766e-05) (hash(x)=151197095)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 394 |
6500 val loss 5.7195
|
| 395 |
6500 val perplexity 304.7384
|
| 396 |
6500 train 5.640700 (lr=1.2766e-05) (hash(x)=151197095)
|
| 397 |
+
6600 val loss 5.7169
|
| 398 |
+
6600 val perplexity 303.9669
|
| 399 |
+
6600 train 5.732614 (lr=1.2129e-05) (hash(x)=153269571)
|
| 400 |
+
6700 val loss 5.7108
|
| 401 |
+
6700 val perplexity 302.1052
|
| 402 |
+
6700 train 5.676517 (lr=1.1515e-05) (hash(x)=146111181)
|
| 403 |
+
6800 val loss 5.7027
|
| 404 |
+
6800 val perplexity 299.6802
|
| 405 |
+
6800 train 5.730567 (lr=1.0923e-05) (hash(x)=147269760)
|
| 406 |
+
6900 val loss 5.6987
|
| 407 |
+
6900 val perplexity 298.4663
|
| 408 |
+
6900 train 5.772451 (lr=1.0356e-05) (hash(x)=152912762)
|
| 409 |
+
7000 val loss 5.6943
|
| 410 |
+
7000 val perplexity 297.1726
|
| 411 |
+
7000 train 5.779076 (lr=9.8138e-06) (hash(x)=165412343)
|
| 412 |
+
7100 val loss 5.6852
|
| 413 |
+
7100 val perplexity 294.4802
|
| 414 |
+
7100 train 5.751966 (lr=9.2971e-06) (hash(x)=162866028)
|
| 415 |
+
7200 val loss 5.6813
|
| 416 |
+
7200 val perplexity 293.3378
|
| 417 |
+
7200 train 5.654007 (lr=8.8068e-06) (hash(x)=142998115)
|
| 418 |
+
7300 val loss 5.6792
|
| 419 |
+
7300 val perplexity 292.7240
|
| 420 |
+
7300 train 5.455004 (lr=8.3436e-06) (hash(x)=145486999)
|
| 421 |
+
7400 val loss 5.6735
|
| 422 |
+
7400 val perplexity 291.0537
|
| 423 |
+
7400 train 5.650209 (lr=7.9082e-06) (hash(x)=155325873)
|
| 424 |
+
7500 val loss 5.6699
|
| 425 |
+
7500 val perplexity 289.9946
|
| 426 |
+
7500 train 5.632772 (lr=7.5012e-06) (hash(x)=145131256)
|
| 427 |
+
7600 val loss 5.6748
|
| 428 |
+
7600 val perplexity 291.4411
|
| 429 |
+
7600 train 5.601090 (lr=7.1232e-06) (hash(x)=144008365)
|
| 430 |
+
7700 val loss 5.6636
|
| 431 |
+
7700 val perplexity 288.1982
|
| 432 |
+
7700 train 5.762614 (lr=6.7747e-06) (hash(x)=148848532)
|
| 433 |
+
7800 val loss 5.6601
|
| 434 |
+
7800 val perplexity 287.1645
|
| 435 |
+
7800 train 5.653588 (lr=6.4563e-06) (hash(x)=150391642)
|
| 436 |
+
7900 val loss 5.6601
|
| 437 |
+
7900 val perplexity 287.1902
|
| 438 |
+
7900 train 5.420237 (lr=6.1684e-06) (hash(x)=152191414)
|
| 439 |
+
8000 val loss 5.6555
|
| 440 |
+
8000 val perplexity 285.8464
|
| 441 |
+
8000 train 5.739616 (lr=5.9114e-06) (hash(x)=159755587)
|
| 442 |
+
8100 val loss 5.6527
|
| 443 |
+
8100 val perplexity 285.0644
|
| 444 |
+
8100 train 5.676317 (lr=5.6857e-06) (hash(x)=156664468)
|
| 445 |
+
8200 val loss 5.6514
|
| 446 |
+
8200 val perplexity 284.6804
|
| 447 |
+
8200 train 5.500314 (lr=5.4917e-06) (hash(x)=139457379)
|
| 448 |
+
8300 val loss 5.6558
|
| 449 |
+
8300 val perplexity 285.9390
|
| 450 |
+
8300 train 5.429895 (lr=5.3295e-06) (hash(x)=145478564)
|
| 451 |
+
8400 val loss 5.6459
|
| 452 |
+
8400 val perplexity 283.1393
|
| 453 |
+
8400 train 5.593821 (lr=5.1995e-06) (hash(x)=154982769)
|
| 454 |
+
8500 val loss 5.6441
|
| 455 |
+
8500 val perplexity 282.6278
|
| 456 |
+
8500 train 5.609265 (lr=5.1019e-06) (hash(x)=145798118)
|
| 457 |
+
8600 val loss 5.6431
|
| 458 |
+
8600 val perplexity 282.3228
|
| 459 |
+
8600 train 5.547587 (lr=5.0367e-06) (hash(x)=143231551)
|
| 460 |
+
8700 val loss 5.6465
|
| 461 |
+
8700 val perplexity 283.2940
|
| 462 |
+
8700 train 5.546406 (lr=5.0041e-06) (hash(x)=154780112)
|
| 463 |
+
8749 val loss 5.6392
|
| 464 |
+
8749 val perplexity 281.2369
|
attention_kindselective_n_heads4_seed1340/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:a0bd10bb2df6bd5756909d69ce4bdaf9422591d404a11e02efff77e578628753
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1340/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 sha256:8fffb58206c4306b292c27c51d9891b0e2f30c646a0532f242e921fcd55398a3
|
| 3 |
size 179406214
|