Upload folder using huggingface_hub
Browse files- checkpoints/main.log +49 -0
checkpoints/main.log
CHANGED
|
@@ -486,3 +486,52 @@ Mixed precision type: bf16
|
|
| 486 |
[2024-08-07 14:58:39,380][Main][INFO] - [train] Step 21500 out of 25000 | Loss --> 0.576 | Grad_l2 --> 0.173 | Weights_l2 --> 47141.247 | Lr --> 0.000 | Seconds_per_step --> 1.726 |
|
| 487 |
[2024-08-07 15:00:05,026][Main][INFO] - [train] Step 21550 out of 25000 | Loss --> 0.588 | Grad_l2 --> 0.161 | Weights_l2 --> 47141.109 | Lr --> 0.000 | Seconds_per_step --> 1.713 |
|
| 488 |
[2024-08-07 15:01:33,627][Main][INFO] - [train] Step 21600 out of 25000 | Loss --> 0.572 | Grad_l2 --> 0.143 | Weights_l2 --> 47140.972 | Lr --> 0.000 | Seconds_per_step --> 1.772 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 486 |
[2024-08-07 14:58:39,380][Main][INFO] - [train] Step 21500 out of 25000 | Loss --> 0.576 | Grad_l2 --> 0.173 | Weights_l2 --> 47141.247 | Lr --> 0.000 | Seconds_per_step --> 1.726 |
|
| 487 |
[2024-08-07 15:00:05,026][Main][INFO] - [train] Step 21550 out of 25000 | Loss --> 0.588 | Grad_l2 --> 0.161 | Weights_l2 --> 47141.109 | Lr --> 0.000 | Seconds_per_step --> 1.713 |
|
| 488 |
[2024-08-07 15:01:33,627][Main][INFO] - [train] Step 21600 out of 25000 | Loss --> 0.572 | Grad_l2 --> 0.143 | Weights_l2 --> 47140.972 | Lr --> 0.000 | Seconds_per_step --> 1.772 |
|
| 489 |
+
[2024-08-07 15:02:59,931][Main][INFO] - [train] Step 21650 out of 25000 | Loss --> 0.550 | Grad_l2 --> 0.162 | Weights_l2 --> 47140.835 | Lr --> 0.000 | Seconds_per_step --> 1.726 |
|
| 490 |
+
[2024-08-07 15:04:25,989][Main][INFO] - [train] Step 21700 out of 25000 | Loss --> 0.546 | Grad_l2 --> 0.141 | Weights_l2 --> 47140.697 | Lr --> 0.000 | Seconds_per_step --> 1.721 |
|
| 491 |
+
[2024-08-07 15:05:54,653][Main][INFO] - [train] Step 21750 out of 25000 | Loss --> 0.563 | Grad_l2 --> 0.190 | Weights_l2 --> 47140.560 | Lr --> 0.000 | Seconds_per_step --> 1.773 |
|
| 492 |
+
[2024-08-07 15:07:20,787][Main][INFO] - [train] Step 21800 out of 25000 | Loss --> 0.544 | Grad_l2 --> 0.146 | Weights_l2 --> 47140.423 | Lr --> 0.000 | Seconds_per_step --> 1.723 |
|
| 493 |
+
[2024-08-07 15:08:46,493][Main][INFO] - [train] Step 21850 out of 25000 | Loss --> 0.530 | Grad_l2 --> 0.152 | Weights_l2 --> 47140.285 | Lr --> 0.000 | Seconds_per_step --> 1.714 |
|
| 494 |
+
[2024-08-07 15:10:14,807][Main][INFO] - [train] Step 21900 out of 25000 | Loss --> 0.550 | Grad_l2 --> 0.141 | Weights_l2 --> 47140.148 | Lr --> 0.000 | Seconds_per_step --> 1.766 |
|
| 495 |
+
[2024-08-07 15:11:41,045][Main][INFO] - [train] Step 21950 out of 25000 | Loss --> 0.583 | Grad_l2 --> 0.156 | Weights_l2 --> 47140.011 | Lr --> 0.000 | Seconds_per_step --> 1.725 |
|
| 496 |
+
[2024-08-07 15:13:07,027][Main][INFO] - [train] Step 22000 out of 25000 | Loss --> 0.571 | Grad_l2 --> 0.173 | Weights_l2 --> 47139.873 | Lr --> 0.000 | Seconds_per_step --> 1.720 |
|
| 497 |
+
[2024-08-07 15:14:35,682][Main][INFO] - [train] Step 22050 out of 25000 | Loss --> 0.557 | Grad_l2 --> 0.141 | Weights_l2 --> 47139.736 | Lr --> 0.000 | Seconds_per_step --> 1.773 |
|
| 498 |
+
[2024-08-07 15:16:01,234][Main][INFO] - [train] Step 22100 out of 25000 | Loss --> 0.585 | Grad_l2 --> 0.152 | Weights_l2 --> 47139.599 | Lr --> 0.000 | Seconds_per_step --> 1.711 |
|
| 499 |
+
[2024-08-07 15:17:27,093][Main][INFO] - [train] Step 22150 out of 25000 | Loss --> 0.575 | Grad_l2 --> 0.177 | Weights_l2 --> 47139.461 | Lr --> 0.000 | Seconds_per_step --> 1.717 |
|
| 500 |
+
[2024-08-07 15:18:55,890][Main][INFO] - [train] Step 22200 out of 25000 | Loss --> 0.571 | Grad_l2 --> 0.152 | Weights_l2 --> 47139.324 | Lr --> 0.000 | Seconds_per_step --> 1.776 |
|
| 501 |
+
[2024-08-07 15:20:22,205][Main][INFO] - [train] Step 22250 out of 25000 | Loss --> 0.547 | Grad_l2 --> 0.148 | Weights_l2 --> 47139.187 | Lr --> 0.000 | Seconds_per_step --> 1.726 |
|
| 502 |
+
[2024-08-07 15:21:48,125][Main][INFO] - [train] Step 22300 out of 25000 | Loss --> 0.526 | Grad_l2 --> 0.159 | Weights_l2 --> 47139.049 | Lr --> 0.000 | Seconds_per_step --> 1.718 |
|
| 503 |
+
[2024-08-07 15:23:16,919][Main][INFO] - [train] Step 22350 out of 25000 | Loss --> 0.544 | Grad_l2 --> 0.136 | Weights_l2 --> 47138.912 | Lr --> 0.000 | Seconds_per_step --> 1.776 |
|
| 504 |
+
[2024-08-07 15:24:42,706][Main][INFO] - [train] Step 22400 out of 25000 | Loss --> 0.523 | Grad_l2 --> 0.149 | Weights_l2 --> 47138.779 | Lr --> 0.000 | Seconds_per_step --> 1.716 |
|
| 505 |
+
[2024-08-07 15:26:08,493][Main][INFO] - [train] Step 22450 out of 25000 | Loss --> 0.532 | Grad_l2 --> 0.150 | Weights_l2 --> 47138.641 | Lr --> 0.000 | Seconds_per_step --> 1.716 |
|
| 506 |
+
[2024-08-07 15:27:37,183][Main][INFO] - [train] Step 22500 out of 25000 | Loss --> 0.551 | Grad_l2 --> 0.138 | Weights_l2 --> 47138.504 | Lr --> 0.000 | Seconds_per_step --> 1.774 |
|
| 507 |
+
[2024-08-07 15:29:03,362][Main][INFO] - [train] Step 22550 out of 25000 | Loss --> 0.534 | Grad_l2 --> 0.140 | Weights_l2 --> 47138.367 | Lr --> 0.000 | Seconds_per_step --> 1.724 |
|
| 508 |
+
[2024-08-07 15:30:29,354][Main][INFO] - [train] Step 22600 out of 25000 | Loss --> 0.518 | Grad_l2 --> 0.151 | Weights_l2 --> 47138.229 | Lr --> 0.000 | Seconds_per_step --> 1.720 |
|
| 509 |
+
[2024-08-07 15:31:58,038][Main][INFO] - [train] Step 22650 out of 25000 | Loss --> 0.507 | Grad_l2 --> 0.147 | Weights_l2 --> 47138.092 | Lr --> 0.000 | Seconds_per_step --> 1.774 |
|
| 510 |
+
[2024-08-07 15:33:24,401][Main][INFO] - [train] Step 22700 out of 25000 | Loss --> 0.533 | Grad_l2 --> 0.153 | Weights_l2 --> 47137.955 | Lr --> 0.000 | Seconds_per_step --> 1.727 |
|
| 511 |
+
[2024-08-07 15:34:53,188][Main][INFO] - [train] Step 22750 out of 25000 | Loss --> 0.550 | Grad_l2 --> 0.174 | Weights_l2 --> 47137.821 | Lr --> 0.000 | Seconds_per_step --> 1.776 |
|
| 512 |
+
[2024-08-07 15:36:19,308][Main][INFO] - [train] Step 22800 out of 25000 | Loss --> 0.537 | Grad_l2 --> 0.166 | Weights_l2 --> 47137.684 | Lr --> 0.000 | Seconds_per_step --> 1.722 |
|
| 513 |
+
[2024-08-07 15:37:46,010][Main][INFO] - [train] Step 22850 out of 25000 | Loss --> 0.514 | Grad_l2 --> 0.134 | Weights_l2 --> 47137.547 | Lr --> 0.000 | Seconds_per_step --> 1.734 |
|
| 514 |
+
[2024-08-07 15:39:14,940][Main][INFO] - [train] Step 22900 out of 25000 | Loss --> 0.520 | Grad_l2 --> 0.151 | Weights_l2 --> 47137.409 | Lr --> 0.000 | Seconds_per_step --> 1.779 |
|
| 515 |
+
[2024-08-07 15:40:41,381][Main][INFO] - [train] Step 22950 out of 25000 | Loss --> 0.525 | Grad_l2 --> 0.145 | Weights_l2 --> 47137.272 | Lr --> 0.000 | Seconds_per_step --> 1.729 |
|
| 516 |
+
[2024-08-07 15:42:07,321][Main][INFO] - [train] Step 23000 out of 25000 | Loss --> 0.495 | Grad_l2 --> 0.174 | Weights_l2 --> 47137.135 | Lr --> 0.000 | Seconds_per_step --> 1.719 |
|
| 517 |
+
[2024-08-07 15:43:36,566][Main][INFO] - [train] Step 23050 out of 25000 | Loss --> 0.509 | Grad_l2 --> 0.164 | Weights_l2 --> 47137.001 | Lr --> 0.000 | Seconds_per_step --> 1.785 |
|
| 518 |
+
[2024-08-07 15:45:02,598][Main][INFO] - [train] Step 23100 out of 25000 | Loss --> 0.526 | Grad_l2 --> 0.144 | Weights_l2 --> 47136.860 | Lr --> 0.000 | Seconds_per_step --> 1.721 |
|
| 519 |
+
[2024-08-07 15:46:28,802][Main][INFO] - [train] Step 23150 out of 25000 | Loss --> 0.503 | Grad_l2 --> 0.162 | Weights_l2 --> 47136.723 | Lr --> 0.000 | Seconds_per_step --> 1.724 |
|
| 520 |
+
[2024-08-07 15:47:57,263][Main][INFO] - [train] Step 23200 out of 25000 | Loss --> 0.534 | Grad_l2 --> 0.158 | Weights_l2 --> 47136.585 | Lr --> 0.000 | Seconds_per_step --> 1.769 |
|
| 521 |
+
[2024-08-07 15:49:23,486][Main][INFO] - [train] Step 23250 out of 25000 | Loss --> 0.482 | Grad_l2 --> 0.129 | Weights_l2 --> 47136.448 | Lr --> 0.000 | Seconds_per_step --> 1.724 |
|
| 522 |
+
[2024-08-07 15:50:49,406][Main][INFO] - [train] Step 23300 out of 25000 | Loss --> 0.522 | Grad_l2 --> 0.144 | Weights_l2 --> 47136.315 | Lr --> 0.000 | Seconds_per_step --> 1.718 |
|
| 523 |
+
[2024-08-07 15:52:17,839][Main][INFO] - [train] Step 23350 out of 25000 | Loss --> 0.509 | Grad_l2 --> 0.162 | Weights_l2 --> 47136.177 | Lr --> 0.000 | Seconds_per_step --> 1.769 |
|
| 524 |
+
[2024-08-07 15:53:43,781][Main][INFO] - [train] Step 23400 out of 25000 | Loss --> 0.507 | Grad_l2 --> 0.168 | Weights_l2 --> 47136.036 | Lr --> 0.000 | Seconds_per_step --> 1.719 |
|
| 525 |
+
[2024-08-07 15:55:09,882][Main][INFO] - [train] Step 23450 out of 25000 | Loss --> 0.505 | Grad_l2 --> 0.152 | Weights_l2 --> 47135.903 | Lr --> 0.000 | Seconds_per_step --> 1.722 |
|
| 526 |
+
[2024-08-07 15:56:38,610][Main][INFO] - [train] Step 23500 out of 25000 | Loss --> 0.491 | Grad_l2 --> 0.245 | Weights_l2 --> 47135.765 | Lr --> 0.000 | Seconds_per_step --> 1.775 |
|
| 527 |
+
[2024-08-07 15:58:04,564][Main][INFO] - [train] Step 23550 out of 25000 | Loss --> 0.515 | Grad_l2 --> 0.170 | Weights_l2 --> 47135.628 | Lr --> 0.000 | Seconds_per_step --> 1.719 |
|
| 528 |
+
[2024-08-07 15:59:30,685][Main][INFO] - [train] Step 23600 out of 25000 | Loss --> 0.523 | Grad_l2 --> 0.152 | Weights_l2 --> 47135.491 | Lr --> 0.000 | Seconds_per_step --> 1.722 |
|
| 529 |
+
[2024-08-07 16:00:59,511][Main][INFO] - [train] Step 23650 out of 25000 | Loss --> 0.490 | Grad_l2 --> 0.158 | Weights_l2 --> 47135.353 | Lr --> 0.000 | Seconds_per_step --> 1.777 |
|
| 530 |
+
[2024-08-07 16:02:25,509][Main][INFO] - [train] Step 23700 out of 25000 | Loss --> 0.496 | Grad_l2 --> 0.129 | Weights_l2 --> 47135.216 | Lr --> 0.000 | Seconds_per_step --> 1.720 |
|
| 531 |
+
[2024-08-07 16:03:51,651][Main][INFO] - [train] Step 23750 out of 25000 | Loss --> 0.498 | Grad_l2 --> 0.172 | Weights_l2 --> 47135.079 | Lr --> 0.000 | Seconds_per_step --> 1.723 |
|
| 532 |
+
[2024-08-07 16:05:20,071][Main][INFO] - [train] Step 23800 out of 25000 | Loss --> 0.504 | Grad_l2 --> 0.142 | Weights_l2 --> 47134.942 | Lr --> 0.000 | Seconds_per_step --> 1.768 |
|
| 533 |
+
[2024-08-07 16:06:46,001][Main][INFO] - [train] Step 23850 out of 25000 | Loss --> 0.502 | Grad_l2 --> 0.134 | Weights_l2 --> 47134.804 | Lr --> 0.000 | Seconds_per_step --> 1.719 |
|
| 534 |
+
[2024-08-07 16:08:12,045][Main][INFO] - [train] Step 23900 out of 25000 | Loss --> 0.530 | Grad_l2 --> 0.156 | Weights_l2 --> 47134.667 | Lr --> 0.000 | Seconds_per_step --> 1.721 |
|
| 535 |
+
[2024-08-07 16:09:40,623][Main][INFO] - [train] Step 23950 out of 25000 | Loss --> 0.510 | Grad_l2 --> 0.145 | Weights_l2 --> 47134.530 | Lr --> 0.000 | Seconds_per_step --> 1.772 |
|
| 536 |
+
[2024-08-07 16:11:06,712][Main][INFO] - [train] Step 24000 out of 25000 | Loss --> 0.507 | Grad_l2 --> 0.138 | Weights_l2 --> 47134.392 | Lr --> 0.000 | Seconds_per_step --> 1.722 |
|
| 537 |
+
[2024-08-07 16:11:11,695][Main][INFO] - [eval] Step 24000 out of 25000 | Loss --> 0.797 | Accuracy --> 0.851 | Time --> 4.979 |
|