Saving weights and logs of step 315000

checkpoint_315000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1b00184c288db635f28f4d12229218acbdca5b3cfcde5ba46ec09b9eb29bfb
+size 1530270447

events.out.tfevents.1626429561.t1v-n-f5c06ea1-w-0.782479.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b72157fe2234d1ca845b2720e384e5e646ba4e309505224bfa7b6bacb05ae5
-size 11342116
+oid sha256:0dfd97eaf4cc0a53b9da14bec5ce1bed8204f791c1cc01b5f8e10574c521ab5b
+size 13538170

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a08bc06de8e2261ead63b6966f3532eeab82b895ad375a7789666478594b6200
+oid sha256:ac92325730ea7333b5d45a9fa077b185498b80875fc86bed0ba9cf8e12b5fe2f
 size 510090043

wandb/run-20210716_095921-13hxxunp/files/output.log

@@ -8830,3 +8830,1672 @@ Training...: 75414it [8:49:20,  4.16it/s]
 
 
 
+Training...: 75449it [8:49:26,  2.67it/s]
+
+
+
+
+
+Training...: 75514it [8:50:00,  4.14it/s]
+
+
+
+Training...: 75549it [8:50:06,  2.67it/s]
+
+
+
+
+
+
+Training...: 75606it [8:50:40,  1.09it/s]
+
+
+
+
+
+Training...: 75656it [8:51:00,  1.09it/s]
+
+
+
+
+Training...: 75699it [8:51:06,  2.69it/s]
+
+
+
+
+
+
+Training...: 75758it [8:51:40,  1.59it/s]
+
+
+
+
+Training...: 75799it [8:51:46,  2.67it/s]
+
+
+
+
+
+Training...: 75849it [8:52:06,  2.70it/s]
+
+
+
+
+
+
+Training...: 75910it [8:52:40,  2.26it/s]
+
+
+
+
+
+Training...: 75962it [8:53:00,  3.10it/s]
+
+
+
+
+Training...: 75999it [8:53:06,  2.67it/s]
+
+
+
+
+
+Training...: 76049it [8:53:26,  2.68it/s]
+
+
+
+
+Training...: 76099it [8:53:46,  2.74it/s]
+
+
+
+
+
+Training...: 76149it [8:54:07,  2.68it/s]
+
+
+
+
+
+Training...: 76199it [8:54:27,  2.71it/s]
+
+
+
+
+
+
+Training...: 76256it [8:55:00,  1.08it/s]
+
+
+
+
+Training...: 76299it [8:55:07,  2.77it/s]
+
+
+
+
+
+Training...: 76349it [8:55:27,  2.68it/s]
+
+
+
+
+
+Training...: 76399it [8:55:47,  2.68it/s]
+
+
+
+
+
+Training...: 76449it [8:56:07,  2.71it/s]
+
+
+
+
+
+Training...: 76499it [8:56:27,  2.67it/s]
+
+
+
+
+
+Training...: 76549it [8:56:47,  2.68it/s]
+
+
+
+
+
+Training...: 76599it [8:57:07,  2.69it/s]
+
+
+
+
+
+Training...: 76649it [8:57:27,  2.68it/s]
+
+
+
+
+
+Training...: 76699it [8:57:47,  2.72it/s]
+
+
+
+
+
+Training...: 76749it [8:58:07,  2.68it/s]
+
+
+
+
+
+Training...: 76799it [8:58:27,  2.70it/s]
+
+
+
+
+
+Training...: 76849it [8:58:47,  2.67it/s]
+
+
+
+
+Training...: 76899it [8:59:07,  2.67it/s]
+
+
+
+
+Training...: 76949it [8:59:27,  2.71it/s]
+
+
+
+
+
+Training...: 76999it [8:59:47,  2.66it/s]
+
+
+
+
+Training...: 77049it [9:00:07,  2.70it/s]
+
+
+
+
+
+Training...: 77099it [9:00:27,  2.68it/s]
+
+
+
+
+
+Training...: 77149it [9:00:47,  2.69it/s]
+
+
+
+
+
+Training...: 77199it [9:01:08,  2.71it/s]
+
+
+
+
+
+Training...: 77249it [9:01:28,  2.68it/s]
+
+
+
+
+
+
+Training...: 77308it [9:02:01,  1.58it/s]
+
+
+
+
+Training...: 77349it [9:02:08,  2.68it/s]
+
+
+
+
+
+Training...: 77399it [9:02:28,  2.68it/s]
+
+
+
+
+
+Training...: 77449it [9:02:48,  2.68it/s]
+
+
+
+
+
+Training...: 77499it [9:03:08,  2.66it/s]
+
+
+
+
+Training...: 77549it [9:03:28,  2.71it/s]
+
+
+
+
+Training...: 77599it [9:03:48,  2.68it/s]
+
+
+
+
+
+
+Training...: 77656it [9:04:21,  1.09it/s]
+
+
+
+
+Training...: 77699it [9:04:28,  2.68it/s]
+
+
+
+
+
+Training...: 77749it [9:04:48,  2.68it/s]
+
+
+
+
+
+Training...: 77799it [9:05:08,  2.71it/s]
+
+
+
+
+
+Training...: 77862it [9:05:42,  3.03it/s]
+
+
+
+
+Training...: 77914it [9:06:02,  4.12it/s]
+
+
+
+
+Training...: 77949it [9:06:08,  2.68it/s]
+
+
+
+
+
+Training...: 77999it [9:06:28,  2.68it/s]
+
+
+
+
+
+Training...: 78049it [9:06:48,  2.71it/s]
+
+
+
+
+
+Training...: 78099it [9:07:08,  2.68it/s]
+
+
+
+
+
+Training...: 78149it [9:07:28,  2.71it/s]
+
+
+
+
+
+Training...: 78199it [9:07:48,  2.68it/s]
+
+
+
+
+
+Training...: 78249it [9:08:08,  2.68it/s]
+
+
+
+
+Training...: 78299it [9:08:28,  2.72it/s]
+
+
+
+
+Training...: 78349it [9:08:48,  2.68it/s]
+
+
+
+
+
+Training...: 78399it [9:09:09,  2.70it/s]
+
+
+
+
+
+Training...: 78449it [9:09:29,  2.68it/s]
+
+
+
+
+
+Training...: 78499it [9:09:49,  2.68it/s]
+
+
+
+
+Training...: 78549it [9:10:09,  2.74it/s]
+
+
+
+
+Training...: 78599it [9:10:29,  2.69it/s]
+
+
+
+
+
+Training...: 78649it [9:10:49,  2.71it/s]
+
+
+
+
+
+Training...: 78699it [9:11:09,  2.68it/s]
+
+
+
+
+
+Training...: 78749it [9:11:29,  2.74it/s]
+
+
+
+
+
+Training...: 78799it [9:11:49,  2.68it/s]
+
+
+
+
+
+Training...: 78849it [9:12:09,  2.67it/s]
+
+
+
+
+
+Training...: 78899it [9:12:29,  2.71it/s]
+
+
+
+
+
+Training...: 78949it [9:12:49,  2.68it/s]
+
+
+
+
+Training...: 78999it [9:13:09,  2.68it/s]
+
+
+
+
+Training...: 79049it [9:13:29,  2.68it/s]
+
+
+
+
+Training...: 79099it [9:13:49,  2.68it/s]
+
+
+
+
+
+Training...: 79149it [9:14:09,  2.70it/s]
+
+
+
+
+
+Training...: 79199it [9:14:29,  2.68it/s]
+
+
+
+
+
+Training...: 79249it [9:14:49,  2.71it/s]
+
+
+
+
+
+Training...: 79299it [9:15:09,  2.68it/s]
+
+
+
+
+Training...: 79349it [9:15:29,  2.67it/s]
+
+
+
+
+Training...: 79399it [9:15:49,  2.72it/s]
+
+
+
+
+Training...: 79449it [9:16:09,  2.67it/s]
+
+
+
+
+Training...: 79499it [9:16:29,  2.70it/s]
+
+
+
+
+Training...: 79549it [9:16:49,  2.68it/s]
+
+
+
+
+Training...: 79599it [9:17:10,  2.68it/s]
+
+
+
+
+
+
+Training...: 79658it [9:17:43,  1.59it/s]
+
+
+
+
+
+Training...: 79708it [9:18:03,  1.58it/s]
+
+
+
+
+
+Training...: 79760it [9:18:23,  2.25it/s]
+
+
+
+
+
+Training...: 79810it [9:18:43,  2.26it/s]
+
+
+
+
+
+Training...: 79860it [9:19:04,  2.25it/s]
+
+
+
+
+Training...: 79899it [9:19:10,  2.67it/s]
+
+
+
+
+
+Training...: 79949it [9:19:30,  2.67it/s]
+
+
+
+
+Training...: 79999it [9:19:50,  2.72it/s]
+
+
+
+
+Training...: 80049it [9:20:10,  2.68it/s]
+
+
+
+
+Training...: 80099it [9:20:30,  2.67it/s]
+
+
+
+
+Training...: 80149it [9:20:50,  2.67it/s]
+
+
+
+
+Training...: 80199it [9:21:10,  2.66it/s]
+
+
+
+
+
+Training...: 80266it [9:21:44,  5.37it/s]
+
+
+
+
+Training...: 80299it [9:21:50,  2.67it/s]
+
+
+
+
+
+
+Training...: 80360it [9:22:24,  2.26it/s]
+
+
+
+
+
+Training...: 80412it [9:22:44,  3.11it/s]
+
+
+
+
+
+Training...: 80460it [9:23:04,  2.26it/s]
+
+
+
+
+Training...: 80514it [9:23:24,  4.16it/s]
+
+
+
+
+Training...: 80564it [9:23:44,  4.09it/s]
+
+
+
+
+
+Training...: 80606it [9:24:04,  1.09it/s]
+
+
+
+
+Training...: 80649it [9:24:10,  2.68it/s]
+
+
+
+
+
+
+Training...: 80704it [9:24:44,  1.39s/it]
+
+
+
+
+Training...: 80749it [9:24:50,  2.71it/s]
+
+
+
+
+
+Training...: 80799it [9:25:11,  2.67it/s]
+
+
+
+
+
+Training...: 80849it [9:25:31,  2.72it/s]
+
+
+
+
+
+Training...: 80899it [9:25:51,  2.69it/s]
+
+
+
+
+
+Training...: 80949it [9:26:11,  2.67it/s]
+
+
+
+
+Training...: 80999it [9:26:31,  2.74it/s]
+Training...: 80999it [9:26:44,  2.74it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...: 81049it [9:27:55,  2.69it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81099it [9:28:15,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81149it [9:28:35,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81199it [9:28:55,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81249it [9:29:15,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81299it [9:29:35,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81349it [9:29:55,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81399it [9:30:15,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81449it [9:30:35,  2.64it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81499it [9:30:55,  2.69it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81549it [9:31:15,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81599it [9:31:35,  2.71it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81649it [9:31:55,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81699it [9:32:15,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81749it [9:32:35,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81799it [9:32:55,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81849it [9:33:15,  2.72it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81899it [9:33:35,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81949it [9:33:55,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 81999it [9:34:15,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82049it [9:34:36,  2.29it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82099it [9:34:56,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82149it [9:35:16,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82199it [9:35:36,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82249it [9:35:56,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82299it [9:36:16,  2.78it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82349it [9:36:36,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82399it [9:36:56,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82449it [9:37:16,  2.72it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82499it [9:37:36,  2.66it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82549it [9:37:56,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82599it [9:38:16,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82649it [9:38:36,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82699it [9:38:56,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82749it [9:39:16,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82799it [9:39:36,  2.69it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82849it [9:39:56,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82899it [9:40:16,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82949it [9:40:36,  2.71it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 82999it [9:40:56,  2.67it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 83049it [9:41:16,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 83099it [9:41:36,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 83149it [9:41:56,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 83199it [9:42:16,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 83249it [9:42:36,  2.68it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 83299it [9:42:57,  2.70it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83350it [9:43:30,  4.01s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83400it [9:43:50,  4.01s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83452it [9:44:10,  2.25s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83502it [9:44:30,  2.25s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83552it [9:44:50,  2.24s/it]████████████████████��████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83602it [9:45:10,  2.25s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83654it [9:45:30,  1.40s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83704it [9:45:50,  1.41s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83756it [9:46:11,  1.09it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83802it [9:46:30,  2.24s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83852it [9:46:50,  2.25s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83904it [9:47:11,  1.39s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 83954it [9:47:31,  1.39s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84006it [9:47:51,  1.08it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84056it [9:48:11,  1.09it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84108it [9:48:31,  1.59it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84162it [9:48:51,  3.09it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 84212it [9:49:11,  3.09it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84252it [9:49:31,  2.24s/it]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84308it [9:49:51,  1.59it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84358it [9:50:11,  1.59it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84410it [9:50:31,  2.26it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84460it [9:50:51,  2.24it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84510it [9:51:11,  2.26it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84560it [9:51:31,  2.24it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84610it [9:51:52,  2.21it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84662it [9:52:12,  3.08it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 84712it [9:52:32,  3.09it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 84766it [9:52:52,  5.37it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 84816it [9:53:12,  5.36it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 84858it [9:53:32,  1.58it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 84912it [9:53:52,  3.09it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 84962it [9:54:12,  3.04it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85016it [9:54:32,  5.28it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85066it [9:54:52,  5.24it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85113it [9:55:12,  3.52it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85168it [9:55:33,  6.46it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 85212it [9:55:52,  3.09it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85264it [9:56:12,  4.14it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85314it [9:56:32,  4.11it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85364it [9:56:53,  3.92it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85418it [9:57:13,  6.61it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85466it [9:57:33,  5.12it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85518it [9:57:53,  6.44it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85568it [9:58:13,  6.64it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85608it [9:58:32,  1.54it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85662it [9:58:53,  3.08it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85714it [9:59:13,  4.13it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85764it [9:59:33,  4.17it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85814it [9:59:53,  4.12it/s]█████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85864it [10:00:13,  4.06it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85916it [10:00:33,  5.23it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 85966it [10:00:53,  5.28it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86018it [10:01:13,  6.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86068it [10:01:33,  6.70it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86120it [10:01:53,  7.88it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86172it [10:02:14,  9.48it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86212it [10:02:33,  3.06it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86267it [10:02:53,  6.52it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86318it [10:03:13,  6.82it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86368it [10:03:33,  6.78it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86420it [10:03:54,  8.23it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86466it [10:04:14,  4.96it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86520it [10:04:34,  8.10it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86570it [10:04:54,  7.88it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86622it [10:05:14,  9.17it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86664it [10:05:34,  4.04it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86712it [10:05:54,  3.77it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86766it [10:06:14,  5.39it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86816it [10:06:34,  5.26it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86868it [10:06:54,  6.80it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86918it [10:07:14,  6.60it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 86970it [10:07:34,  8.21it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+Training...: 86999it [10:07:53,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+Evaluating ...:   4%|██▎                                                   | 21/500 [00:00<00:20, 23.05it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...: 87049it [10:09:04,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 87099it [10:09:24,  2.71it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87150it [10:09:57,  4.01s/it]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87200it [10:10:17,  4.01s/it]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87252it [10:10:37,  2.25s/it]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87302it [10:10:57,  2.24s/it]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87352it [10:11:17,  2.25s/it]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87404it [10:11:37,  1.40s/it]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 87449it [10:11:44,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 87499it [10:12:04,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87549it [10:12:24,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+
+Training...: 87610it [10:12:58,  2.22it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 87649it [10:13:04,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87699it [10:13:24,  2.70it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+
+Training...: 87754it [10:13:58,  1.40s/it]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 87799it [10:14:04,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87849it [10:14:24,  2.70it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87899it [10:14:44,  2.65it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87949it [10:15:04,  2.71it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 87999it [10:15:24,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88049it [10:15:44,  2.79it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88099it [10:16:05,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88149it [10:16:25,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88199it [10:16:45,  2.70it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88249it [10:17:05,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88299it [10:17:25,  2.70it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88349it [10:17:45,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 88399it [10:18:05,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 88449it [10:18:25,  2.71it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88499it [10:18:45,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88549it [10:19:05,  2.64it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88599it [10:19:25,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88649it [10:19:45,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 88699it [10:20:05,  2.71it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88749it [10:20:25,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88799it [10:20:45,  2.71it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88849it [10:21:05,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88899it [10:21:25,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88949it [10:21:45,  2.74it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 88999it [10:22:05,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89049it [10:22:25,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89099it [10:22:45,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 89149it [10:23:05,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 89199it [10:23:25,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 89249it [10:23:45,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 89299it [10:24:06,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 89349it [10:24:26,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 89399it [10:24:46,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+
+Training...: 89449it [10:25:06,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89499it [10:25:26,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89549it [10:25:46,  2.71it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89599it [10:26:06,  2.66it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89649it [10:26:26,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89699it [10:26:46,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89749it [10:27:06,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89799it [10:27:26,  2.75it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89849it [10:27:46,  2.67it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89899it [10:28:06,  2.69it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89949it [10:28:26,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+
+
+Training...: 89999it [10:28:46,  2.68it/s]████████████████████████████████| 500/500 [00:59<00:00,  7.90it/s]
+
+
+[20:34:21] - INFO - absl - Saved checkpoint at checkpoint_315000██████████| 500/500 [00:59<00:00,  7.90it/s]
+[20:34:23] - INFO - huggingface_hub.repository - git version 2.25.1
+git-lfs/2.9.2 (GitHub; linux amd64; go 1.13.5)

wandb/run-20210716_095921-13hxxunp/files/wandb-summary.json

@@ -1 +1 @@
-{"training_step": 300400, "learning_rate": 2.5032584744622e-05, "train_loss": 2.003246307373047, "_runtime": 32112, "_timestamp": 1626461674, "_step": 1520, "eval_step": 300000, "eval_accuracy": 0.6334131956100464, "eval_loss": 1.8694549798965454}
+{"training_step": 315000, "learning_rate": 2.4782844775472768e-05, "train_loss": 1.9440785646438599, "_runtime": 38092, "_timestamp": 1626467654, "_step": 1814, "eval_step": 312000, "eval_accuracy": 0.6361072659492493, "eval_loss": 1.8521945476531982}