Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads4_seed1341/log2.txt
CHANGED
|
@@ -412,3 +412,65 @@ max_steps: 8750
|
|
| 412 |
6700 val loss 5.6928
|
| 413 |
6700 val perplexity 296.7115
|
| 414 |
6700 train 5.493250 (lr=1.1515e-05) (hash(x)=146268592)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 412 |
6700 val loss 5.6928
|
| 413 |
6700 val perplexity 296.7115
|
| 414 |
6700 train 5.493250 (lr=1.1515e-05) (hash(x)=146268592)
|
| 415 |
+
6800 val loss 5.6825
|
| 416 |
+
6800 val perplexity 293.6945
|
| 417 |
+
6800 train 5.628151 (lr=1.0923e-05) (hash(x)=152676836)
|
| 418 |
+
6900 val loss 5.6746
|
| 419 |
+
6900 val perplexity 291.3775
|
| 420 |
+
6900 train 5.592096 (lr=1.0356e-05) (hash(x)=134657776)
|
| 421 |
+
7000 val loss 5.6738
|
| 422 |
+
7000 val perplexity 291.1277
|
| 423 |
+
7000 train 5.625089 (lr=9.8138e-06) (hash(x)=166721861)
|
| 424 |
+
7100 val loss 5.6712
|
| 425 |
+
7100 val perplexity 290.3784
|
| 426 |
+
7100 train 5.471138 (lr=9.2971e-06) (hash(x)=135496702)
|
| 427 |
+
7200 val loss 5.6675
|
| 428 |
+
7200 val perplexity 289.3047
|
| 429 |
+
7200 train 5.778218 (lr=8.8068e-06) (hash(x)=155567461)
|
| 430 |
+
7300 val loss 5.6589
|
| 431 |
+
7300 val perplexity 286.8447
|
| 432 |
+
7300 train 5.459130 (lr=8.3436e-06) (hash(x)=142803829)
|
| 433 |
+
7400 val loss 5.6582
|
| 434 |
+
7400 val perplexity 286.6350
|
| 435 |
+
7400 train 5.478490 (lr=7.9082e-06) (hash(x)=145294178)
|
| 436 |
+
7500 val loss 5.6553
|
| 437 |
+
7500 val perplexity 285.8107
|
| 438 |
+
7500 train 5.411656 (lr=7.5012e-06) (hash(x)=150573713)
|
| 439 |
+
7600 val loss 5.6530
|
| 440 |
+
7600 val perplexity 285.1458
|
| 441 |
+
7600 train 5.668416 (lr=7.1232e-06) (hash(x)=142771511)
|
| 442 |
+
7700 val loss 5.6466
|
| 443 |
+
7700 val perplexity 283.3324
|
| 444 |
+
7700 train 5.552392 (lr=6.7747e-06) (hash(x)=143602175)
|
| 445 |
+
7800 val loss 5.6435
|
| 446 |
+
7800 val perplexity 282.4496
|
| 447 |
+
7800 train 5.698727 (lr=6.4563e-06) (hash(x)=152379862)
|
| 448 |
+
7900 val loss 5.6427
|
| 449 |
+
7900 val perplexity 282.2134
|
| 450 |
+
7900 train 5.463721 (lr=6.1684e-06) (hash(x)=146655921)
|
| 451 |
+
8000 val loss 5.6430
|
| 452 |
+
8000 val perplexity 282.2946
|
| 453 |
+
8000 train 5.779183 (lr=5.9114e-06) (hash(x)=148262482)
|
| 454 |
+
8100 val loss 5.6351
|
| 455 |
+
8100 val perplexity 280.0877
|
| 456 |
+
8100 train 5.579781 (lr=5.6857e-06) (hash(x)=147683655)
|
| 457 |
+
8200 val loss 5.6347
|
| 458 |
+
8200 val perplexity 279.9642
|
| 459 |
+
8200 train 5.747372 (lr=5.4917e-06) (hash(x)=157312987)
|
| 460 |
+
8300 val loss 5.6320
|
| 461 |
+
8300 val perplexity 279.2189
|
| 462 |
+
8300 train 5.594587 (lr=5.3295e-06) (hash(x)=141107543)
|
| 463 |
+
8400 val loss 5.6274
|
| 464 |
+
8400 val perplexity 277.9336
|
| 465 |
+
8400 train 5.622123 (lr=5.1995e-06) (hash(x)=141323024)
|
| 466 |
+
8500 val loss 5.6254
|
| 467 |
+
8500 val perplexity 277.3963
|
| 468 |
+
8500 train 5.598778 (lr=5.1019e-06) (hash(x)=150696521)
|
| 469 |
+
8600 val loss 5.6246
|
| 470 |
+
8600 val perplexity 277.1568
|
| 471 |
+
8600 train 5.568236 (lr=5.0367e-06) (hash(x)=162288191)
|
| 472 |
+
8700 val loss 5.6214
|
| 473 |
+
8700 val perplexity 276.2682
|
| 474 |
+
8700 train 5.487337 (lr=5.0041e-06) (hash(x)=152860941)
|
| 475 |
+
8749 val loss 5.6205
|
| 476 |
+
8749 val perplexity 276.0402
|
attention_kindselective_n_heads4_seed1341/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:ed0dcb5d343458d407779e590b050be53e5b8310ad8f034f32c18a7b9fe44301
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1341/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:a7c58c6893213b5eb99fd4135d3c6ce96bb74c5d8052222ff21a834154e88aea
|
| 3 |
size 179406214
|