Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads4_seed1339/log2.txt
CHANGED
|
@@ -412,3 +412,65 @@ max_steps: 8750
|
|
| 412 |
6700 val loss 5.6888
|
| 413 |
6700 val perplexity 295.5327
|
| 414 |
6700 train 5.603293 (lr=1.1515e-05) (hash(x)=153018737)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 412 |
6700 val loss 5.6888
|
| 413 |
6700 val perplexity 295.5327
|
| 414 |
6700 train 5.603293 (lr=1.1515e-05) (hash(x)=153018737)
|
| 415 |
+
6800 val loss 5.6821
|
| 416 |
+
6800 val perplexity 293.5735
|
| 417 |
+
6800 train 5.600542 (lr=1.0923e-05) (hash(x)=155640155)
|
| 418 |
+
6900 val loss 5.6792
|
| 419 |
+
6900 val perplexity 292.7130
|
| 420 |
+
6900 train 5.647770 (lr=1.0356e-05) (hash(x)=153722115)
|
| 421 |
+
7000 val loss 5.6723
|
| 422 |
+
7000 val perplexity 290.7011
|
| 423 |
+
7000 train 5.584852 (lr=9.8138e-06) (hash(x)=146953450)
|
| 424 |
+
7100 val loss 5.6728
|
| 425 |
+
7100 val perplexity 290.8389
|
| 426 |
+
7100 train 5.512071 (lr=9.2971e-06) (hash(x)=137663885)
|
| 427 |
+
7200 val loss 5.6612
|
| 428 |
+
7200 val perplexity 287.4832
|
| 429 |
+
7200 train 5.725991 (lr=8.8068e-06) (hash(x)=146172950)
|
| 430 |
+
7300 val loss 5.6579
|
| 431 |
+
7300 val perplexity 286.5494
|
| 432 |
+
7300 train 5.547714 (lr=8.3436e-06) (hash(x)=150018163)
|
| 433 |
+
7400 val loss 5.6547
|
| 434 |
+
7400 val perplexity 285.6349
|
| 435 |
+
7400 train 5.652079 (lr=7.9082e-06) (hash(x)=145351166)
|
| 436 |
+
7500 val loss 5.6558
|
| 437 |
+
7500 val perplexity 285.9538
|
| 438 |
+
7500 train 5.439733 (lr=7.5012e-06) (hash(x)=145292116)
|
| 439 |
+
7600 val loss 5.6482
|
| 440 |
+
7600 val perplexity 283.7883
|
| 441 |
+
7600 train 5.567676 (lr=7.1232e-06) (hash(x)=150235132)
|
| 442 |
+
7700 val loss 5.6460
|
| 443 |
+
7700 val perplexity 283.1464
|
| 444 |
+
7700 train 5.560301 (lr=6.7747e-06) (hash(x)=154543455)
|
| 445 |
+
7800 val loss 5.6444
|
| 446 |
+
7800 val perplexity 282.7156
|
| 447 |
+
7800 train 5.542447 (lr=6.4563e-06) (hash(x)=142456852)
|
| 448 |
+
7900 val loss 5.6442
|
| 449 |
+
7900 val perplexity 282.6458
|
| 450 |
+
7900 train 5.425089 (lr=6.1684e-06) (hash(x)=147363479)
|
| 451 |
+
8000 val loss 5.6373
|
| 452 |
+
8000 val perplexity 280.7155
|
| 453 |
+
8000 train 5.670514 (lr=5.9114e-06) (hash(x)=156122973)
|
| 454 |
+
8100 val loss 5.6349
|
| 455 |
+
8100 val perplexity 280.0438
|
| 456 |
+
8100 train 5.677576 (lr=5.6857e-06) (hash(x)=156153179)
|
| 457 |
+
8200 val loss 5.6328
|
| 458 |
+
8200 val perplexity 279.4368
|
| 459 |
+
8200 train 5.678164 (lr=5.4917e-06) (hash(x)=146430698)
|
| 460 |
+
8300 val loss 5.6315
|
| 461 |
+
8300 val perplexity 279.0829
|
| 462 |
+
8300 train 5.499332 (lr=5.3295e-06) (hash(x)=143507257)
|
| 463 |
+
8400 val loss 5.6268
|
| 464 |
+
8400 val perplexity 277.7611
|
| 465 |
+
8400 train 5.664957 (lr=5.1995e-06) (hash(x)=166272643)
|
| 466 |
+
8500 val loss 5.6251
|
| 467 |
+
8500 val perplexity 277.3011
|
| 468 |
+
8500 train 5.523038 (lr=5.1019e-06) (hash(x)=143887848)
|
| 469 |
+
8600 val loss 5.6245
|
| 470 |
+
8600 val perplexity 277.1212
|
| 471 |
+
8600 train 5.663259 (lr=5.0367e-06) (hash(x)=156900341)
|
| 472 |
+
8700 val loss 5.6196
|
| 473 |
+
8700 val perplexity 275.7807
|
| 474 |
+
8700 train 5.859730 (lr=5.0041e-06) (hash(x)=146417632)
|
| 475 |
+
8749 val loss 5.6196
|
| 476 |
+
8749 val perplexity 275.7850
|
attention_kindselective_n_heads4_seed1339/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 sha256:28c1d46f1189bf9e6286f016e3f11c3fb23ed74390497e972b970bc6ca6c48a1
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1339/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:a4d7d46c996fb6999606ae1a98b752899b17ac1f319d229f6eb9b477ab5add1b
|
| 3 |
size 179406214
|