Training in progress, epoch 3
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f2847db22199909f646da9598708ba8a76fca89963331733640a896c01fbdaa
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78120afa70a3ba8c9d1ae5147f81ce5b27ba5d87edfb5db259f9ec8b30581096
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d4cb7412ebe98a1ee942e05fd6ca6b203ab00227bbca66de73d4314b59917f0
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6720f03e4311ee6116ffb1d26a365add8ca6cf2939801f7634c94900f58c7104
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -484,3 +484,164 @@
|
|
| 484 |
{"current_steps": 484, "total_steps": 805, "loss": 1.632, "lr": 3.292116578150298e-05, "epoch": 3.001545595054096, "percentage": 60.12, "elapsed_time": "7:05:13", "remaining_time": "4:42:01"}
|
| 485 |
{"current_steps": 485, "total_steps": 805, "loss": 0.8917, "lr": 3.2750403897190856e-05, "epoch": 3.007727975270479, "percentage": 60.25, "elapsed_time": "7:06:05", "remaining_time": "4:41:07"}
|
| 486 |
{"current_steps": 486, "total_steps": 805, "loss": 0.8802, "lr": 3.2579778513850405e-05, "epoch": 3.0139103554868623, "percentage": 60.37, "elapsed_time": "7:06:56", "remaining_time": "4:40:13"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 484 |
{"current_steps": 484, "total_steps": 805, "loss": 1.632, "lr": 3.292116578150298e-05, "epoch": 3.001545595054096, "percentage": 60.12, "elapsed_time": "7:05:13", "remaining_time": "4:42:01"}
|
| 485 |
{"current_steps": 485, "total_steps": 805, "loss": 0.8917, "lr": 3.2750403897190856e-05, "epoch": 3.007727975270479, "percentage": 60.25, "elapsed_time": "7:06:05", "remaining_time": "4:41:07"}
|
| 486 |
{"current_steps": 486, "total_steps": 805, "loss": 0.8802, "lr": 3.2579778513850405e-05, "epoch": 3.0139103554868623, "percentage": 60.37, "elapsed_time": "7:06:56", "remaining_time": "4:40:13"}
|
| 487 |
+
{"current_steps": 487, "total_steps": 805, "loss": 0.9013, "lr": 3.240929284414762e-05, "epoch": 3.020092735703246, "percentage": 60.5, "elapsed_time": "7:07:47", "remaining_time": "4:39:20"}
|
| 488 |
+
{"current_steps": 488, "total_steps": 805, "loss": 0.876, "lr": 3.223895009811777e-05, "epoch": 3.026275115919629, "percentage": 60.62, "elapsed_time": "7:08:38", "remaining_time": "4:38:26"}
|
| 489 |
+
{"current_steps": 489, "total_steps": 805, "loss": 0.8888, "lr": 3.2068753483105165e-05, "epoch": 3.0324574961360122, "percentage": 60.75, "elapsed_time": "7:09:29", "remaining_time": "4:37:32"}
|
| 490 |
+
{"current_steps": 490, "total_steps": 805, "loss": 0.9015, "lr": 3.189870620370256e-05, "epoch": 3.038639876352396, "percentage": 60.87, "elapsed_time": "7:10:20", "remaining_time": "4:36:39"}
|
| 491 |
+
{"current_steps": 491, "total_steps": 805, "loss": 0.8858, "lr": 3.1728811461690904e-05, "epoch": 3.044822256568779, "percentage": 60.99, "elapsed_time": "7:11:14", "remaining_time": "4:35:46"}
|
| 492 |
+
{"current_steps": 492, "total_steps": 805, "loss": 0.8971, "lr": 3.155907245597912e-05, "epoch": 3.051004636785162, "percentage": 61.12, "elapsed_time": "7:12:21", "remaining_time": "4:35:03"}
|
| 493 |
+
{"current_steps": 493, "total_steps": 805, "loss": 0.8913, "lr": 3.138949238254375e-05, "epoch": 3.0571870170015454, "percentage": 61.24, "elapsed_time": "7:13:14", "remaining_time": "4:34:10"}
|
| 494 |
+
{"current_steps": 494, "total_steps": 805, "loss": 0.8996, "lr": 3.122007443436885e-05, "epoch": 3.063369397217929, "percentage": 61.37, "elapsed_time": "7:14:05", "remaining_time": "4:33:17"}
|
| 495 |
+
{"current_steps": 495, "total_steps": 805, "loss": 0.8889, "lr": 3.105082180138585e-05, "epoch": 3.069551777434312, "percentage": 61.49, "elapsed_time": "7:14:56", "remaining_time": "4:32:23"}
|
| 496 |
+
{"current_steps": 496, "total_steps": 805, "loss": 0.8964, "lr": 3.0881737670413534e-05, "epoch": 3.0757341576506954, "percentage": 61.61, "elapsed_time": "7:15:47", "remaining_time": "4:31:29"}
|
| 497 |
+
{"current_steps": 497, "total_steps": 805, "loss": 0.8794, "lr": 3.071282522509798e-05, "epoch": 3.081916537867079, "percentage": 61.74, "elapsed_time": "7:16:38", "remaining_time": "4:30:35"}
|
| 498 |
+
{"current_steps": 498, "total_steps": 805, "loss": 0.8957, "lr": 3.054408764585261e-05, "epoch": 3.088098918083462, "percentage": 61.86, "elapsed_time": "7:17:29", "remaining_time": "4:29:42"}
|
| 499 |
+
{"current_steps": 499, "total_steps": 805, "loss": 0.8786, "lr": 3.037552810979836e-05, "epoch": 3.0942812982998453, "percentage": 61.99, "elapsed_time": "7:18:20", "remaining_time": "4:28:48"}
|
| 500 |
+
{"current_steps": 500, "total_steps": 805, "loss": 0.8884, "lr": 3.020714979070385e-05, "epoch": 3.100463678516229, "percentage": 62.11, "elapsed_time": "7:19:11", "remaining_time": "4:27:54"}
|
| 501 |
+
{"current_steps": 501, "total_steps": 805, "loss": 0.8846, "lr": 3.0038955858925556e-05, "epoch": 3.106646058732612, "percentage": 62.24, "elapsed_time": "7:20:03", "remaining_time": "4:27:01"}
|
| 502 |
+
{"current_steps": 502, "total_steps": 805, "loss": 0.8942, "lr": 2.9870949481348214e-05, "epoch": 3.1128284389489953, "percentage": 62.36, "elapsed_time": "7:20:54", "remaining_time": "4:26:07"}
|
| 503 |
+
{"current_steps": 503, "total_steps": 805, "loss": 0.8915, "lr": 2.9703133821325125e-05, "epoch": 3.1190108191653785, "percentage": 62.48, "elapsed_time": "7:21:45", "remaining_time": "4:25:13"}
|
| 504 |
+
{"current_steps": 504, "total_steps": 805, "loss": 0.8885, "lr": 2.953551203861863e-05, "epoch": 3.125193199381762, "percentage": 62.61, "elapsed_time": "7:22:36", "remaining_time": "4:24:20"}
|
| 505 |
+
{"current_steps": 505, "total_steps": 805, "loss": 0.8844, "lr": 2.9368087289340575e-05, "epoch": 3.1313755795981453, "percentage": 62.73, "elapsed_time": "7:23:27", "remaining_time": "4:23:26"}
|
| 506 |
+
{"current_steps": 506, "total_steps": 805, "loss": 0.8929, "lr": 2.9200862725892897e-05, "epoch": 3.1375579598145285, "percentage": 62.86, "elapsed_time": "7:24:21", "remaining_time": "4:22:34"}
|
| 507 |
+
{"current_steps": 507, "total_steps": 805, "loss": 0.8874, "lr": 2.903384149690834e-05, "epoch": 3.143740340030912, "percentage": 62.98, "elapsed_time": "7:25:28", "remaining_time": "4:21:50"}
|
| 508 |
+
{"current_steps": 508, "total_steps": 805, "loss": 0.8876, "lr": 2.8867026747191054e-05, "epoch": 3.1499227202472952, "percentage": 63.11, "elapsed_time": "7:26:21", "remaining_time": "4:20:57"}
|
| 509 |
+
{"current_steps": 509, "total_steps": 805, "loss": 0.8958, "lr": 2.8700421617657446e-05, "epoch": 3.1561051004636784, "percentage": 63.23, "elapsed_time": "7:27:12", "remaining_time": "4:20:04"}
|
| 510 |
+
{"current_steps": 510, "total_steps": 805, "loss": 0.8952, "lr": 2.853402924527708e-05, "epoch": 3.162287480680062, "percentage": 63.35, "elapsed_time": "7:28:04", "remaining_time": "4:19:10"}
|
| 511 |
+
{"current_steps": 511, "total_steps": 805, "loss": 0.8783, "lr": 2.8367852763013508e-05, "epoch": 3.1684698608964452, "percentage": 63.48, "elapsed_time": "7:28:55", "remaining_time": "4:18:16"}
|
| 512 |
+
{"current_steps": 512, "total_steps": 805, "loss": 0.8885, "lr": 2.8201895299765358e-05, "epoch": 3.1746522411128284, "percentage": 63.6, "elapsed_time": "7:29:46", "remaining_time": "4:17:23"}
|
| 513 |
+
{"current_steps": 513, "total_steps": 805, "loss": 0.8781, "lr": 2.803615998030738e-05, "epoch": 3.1808346213292116, "percentage": 63.73, "elapsed_time": "7:30:37", "remaining_time": "4:16:29"}
|
| 514 |
+
{"current_steps": 514, "total_steps": 805, "loss": 0.896, "lr": 2.787064992523169e-05, "epoch": 3.187017001545595, "percentage": 63.85, "elapsed_time": "7:31:28", "remaining_time": "4:15:36"}
|
| 515 |
+
{"current_steps": 515, "total_steps": 805, "loss": 0.8977, "lr": 2.7705368250888892e-05, "epoch": 3.1931993817619784, "percentage": 63.98, "elapsed_time": "7:32:19", "remaining_time": "4:14:42"}
|
| 516 |
+
{"current_steps": 516, "total_steps": 805, "loss": 0.8809, "lr": 2.7540318069329468e-05, "epoch": 3.1993817619783615, "percentage": 64.1, "elapsed_time": "7:33:11", "remaining_time": "4:13:49"}
|
| 517 |
+
{"current_steps": 517, "total_steps": 805, "loss": 0.8852, "lr": 2.7375502488245218e-05, "epoch": 3.205564142194745, "percentage": 64.22, "elapsed_time": "7:34:02", "remaining_time": "4:12:55"}
|
| 518 |
+
{"current_steps": 518, "total_steps": 805, "loss": 0.8843, "lr": 2.7210924610910658e-05, "epoch": 3.2117465224111283, "percentage": 64.35, "elapsed_time": "7:34:53", "remaining_time": "4:12:02"}
|
| 519 |
+
{"current_steps": 519, "total_steps": 805, "loss": 0.8912, "lr": 2.7046587536124656e-05, "epoch": 3.2179289026275115, "percentage": 64.47, "elapsed_time": "7:35:44", "remaining_time": "4:11:08"}
|
| 520 |
+
{"current_steps": 520, "total_steps": 805, "loss": 0.8902, "lr": 2.6882494358152055e-05, "epoch": 3.2241112828438947, "percentage": 64.6, "elapsed_time": "7:36:35", "remaining_time": "4:10:14"}
|
| 521 |
+
{"current_steps": 521, "total_steps": 805, "loss": 0.8931, "lr": 2.6718648166665445e-05, "epoch": 3.2302936630602783, "percentage": 64.72, "elapsed_time": "7:37:29", "remaining_time": "4:09:23"}
|
| 522 |
+
{"current_steps": 522, "total_steps": 805, "loss": 0.8799, "lr": 2.6555052046686943e-05, "epoch": 3.2364760432766615, "percentage": 64.84, "elapsed_time": "7:38:36", "remaining_time": "4:08:37"}
|
| 523 |
+
{"current_steps": 523, "total_steps": 805, "loss": 0.9015, "lr": 2.6391709078530106e-05, "epoch": 3.2426584234930447, "percentage": 64.97, "elapsed_time": "7:39:30", "remaining_time": "4:07:45"}
|
| 524 |
+
{"current_steps": 524, "total_steps": 805, "loss": 0.8869, "lr": 2.6228622337742016e-05, "epoch": 3.2488408037094283, "percentage": 65.09, "elapsed_time": "7:40:21", "remaining_time": "4:06:52"}
|
| 525 |
+
{"current_steps": 525, "total_steps": 805, "loss": 0.8921, "lr": 2.606579489504526e-05, "epoch": 3.2550231839258115, "percentage": 65.22, "elapsed_time": "7:41:12", "remaining_time": "4:05:58"}
|
| 526 |
+
{"current_steps": 526, "total_steps": 805, "loss": 0.8969, "lr": 2.590322981628016e-05, "epoch": 3.2612055641421946, "percentage": 65.34, "elapsed_time": "7:42:03", "remaining_time": "4:05:05"}
|
| 527 |
+
{"current_steps": 527, "total_steps": 805, "loss": 0.8839, "lr": 2.5740930162347053e-05, "epoch": 3.2673879443585783, "percentage": 65.47, "elapsed_time": "7:42:54", "remaining_time": "4:04:11"}
|
| 528 |
+
{"current_steps": 528, "total_steps": 805, "loss": 0.8927, "lr": 2.5578898989148692e-05, "epoch": 3.2735703245749614, "percentage": 65.59, "elapsed_time": "7:43:45", "remaining_time": "4:03:17"}
|
| 529 |
+
{"current_steps": 529, "total_steps": 805, "loss": 0.8889, "lr": 2.5417139347532625e-05, "epoch": 3.2797527047913446, "percentage": 65.71, "elapsed_time": "7:44:36", "remaining_time": "4:02:24"}
|
| 530 |
+
{"current_steps": 530, "total_steps": 805, "loss": 0.8893, "lr": 2.525565428323379e-05, "epoch": 3.285935085007728, "percentage": 65.84, "elapsed_time": "7:45:27", "remaining_time": "4:01:30"}
|
| 531 |
+
{"current_steps": 531, "total_steps": 805, "loss": 0.8989, "lr": 2.509444683681722e-05, "epoch": 3.2921174652241114, "percentage": 65.96, "elapsed_time": "7:46:18", "remaining_time": "4:00:37"}
|
| 532 |
+
{"current_steps": 532, "total_steps": 805, "loss": 0.8795, "lr": 2.49335200436207e-05, "epoch": 3.2982998454404946, "percentage": 66.09, "elapsed_time": "7:47:09", "remaining_time": "3:59:43"}
|
| 533 |
+
{"current_steps": 533, "total_steps": 805, "loss": 0.909, "lr": 2.4772876933697658e-05, "epoch": 3.3044822256568778, "percentage": 66.21, "elapsed_time": "7:48:01", "remaining_time": "3:58:50"}
|
| 534 |
+
{"current_steps": 534, "total_steps": 805, "loss": 0.8966, "lr": 2.461252053176015e-05, "epoch": 3.3106646058732614, "percentage": 66.34, "elapsed_time": "7:48:52", "remaining_time": "3:57:56"}
|
| 535 |
+
{"current_steps": 535, "total_steps": 805, "loss": 0.904, "lr": 2.4452453857121846e-05, "epoch": 3.3168469860896446, "percentage": 66.46, "elapsed_time": "7:49:43", "remaining_time": "3:57:03"}
|
| 536 |
+
{"current_steps": 536, "total_steps": 805, "loss": 0.8709, "lr": 2.429267992364123e-05, "epoch": 3.3230293663060277, "percentage": 66.58, "elapsed_time": "7:50:37", "remaining_time": "3:56:11"}
|
| 537 |
+
{"current_steps": 537, "total_steps": 805, "loss": 0.886, "lr": 2.413320173966481e-05, "epoch": 3.329211746522411, "percentage": 66.71, "elapsed_time": "7:51:42", "remaining_time": "3:55:24"}
|
| 538 |
+
{"current_steps": 538, "total_steps": 805, "loss": 0.8994, "lr": 2.3974022307970488e-05, "epoch": 3.3353941267387945, "percentage": 66.83, "elapsed_time": "7:52:35", "remaining_time": "3:54:32"}
|
| 539 |
+
{"current_steps": 539, "total_steps": 805, "loss": 0.8928, "lr": 2.3815144625711063e-05, "epoch": 3.3415765069551777, "percentage": 66.96, "elapsed_time": "7:53:26", "remaining_time": "3:53:38"}
|
| 540 |
+
{"current_steps": 540, "total_steps": 805, "loss": 0.8952, "lr": 2.3656571684357736e-05, "epoch": 3.347758887171561, "percentage": 67.08, "elapsed_time": "7:54:18", "remaining_time": "3:52:45"}
|
| 541 |
+
{"current_steps": 541, "total_steps": 805, "loss": 0.8789, "lr": 2.34983064696438e-05, "epoch": 3.3539412673879445, "percentage": 67.2, "elapsed_time": "7:55:09", "remaining_time": "3:51:52"}
|
| 542 |
+
{"current_steps": 542, "total_steps": 805, "loss": 0.8904, "lr": 2.3340351961508495e-05, "epoch": 3.3601236476043277, "percentage": 67.33, "elapsed_time": "7:56:00", "remaining_time": "3:50:58"}
|
| 543 |
+
{"current_steps": 543, "total_steps": 805, "loss": 0.8853, "lr": 2.318271113404075e-05, "epoch": 3.366306027820711, "percentage": 67.45, "elapsed_time": "7:56:51", "remaining_time": "3:50:05"}
|
| 544 |
+
{"current_steps": 544, "total_steps": 805, "loss": 0.9049, "lr": 2.3025386955423342e-05, "epoch": 3.3724884080370945, "percentage": 67.58, "elapsed_time": "7:57:42", "remaining_time": "3:49:11"}
|
| 545 |
+
{"current_steps": 545, "total_steps": 805, "loss": 0.8876, "lr": 2.2868382387876905e-05, "epoch": 3.3786707882534777, "percentage": 67.7, "elapsed_time": "7:58:33", "remaining_time": "3:48:18"}
|
| 546 |
+
{"current_steps": 546, "total_steps": 805, "loss": 0.9025, "lr": 2.2711700387604223e-05, "epoch": 3.384853168469861, "percentage": 67.83, "elapsed_time": "7:59:24", "remaining_time": "3:47:24"}
|
| 547 |
+
{"current_steps": 547, "total_steps": 805, "loss": 0.8939, "lr": 2.255534390473451e-05, "epoch": 3.391035548686244, "percentage": 67.95, "elapsed_time": "8:00:16", "remaining_time": "3:46:31"}
|
| 548 |
+
{"current_steps": 548, "total_steps": 805, "loss": 0.8987, "lr": 2.2399315883267853e-05, "epoch": 3.3972179289026276, "percentage": 68.07, "elapsed_time": "8:01:07", "remaining_time": "3:45:38"}
|
| 549 |
+
{"current_steps": 549, "total_steps": 805, "loss": 0.8893, "lr": 2.2243619261019918e-05, "epoch": 3.403400309119011, "percentage": 68.2, "elapsed_time": "8:01:58", "remaining_time": "3:44:44"}
|
| 550 |
+
{"current_steps": 550, "total_steps": 805, "loss": 0.9041, "lr": 2.2088256969566413e-05, "epoch": 3.409582689335394, "percentage": 68.32, "elapsed_time": "8:02:49", "remaining_time": "3:43:51"}
|
| 551 |
+
{"current_steps": 551, "total_steps": 805, "loss": 0.8855, "lr": 2.1933231934188104e-05, "epoch": 3.4157650695517776, "percentage": 68.45, "elapsed_time": "8:03:43", "remaining_time": "3:42:59"}
|
| 552 |
+
{"current_steps": 552, "total_steps": 805, "loss": 0.8954, "lr": 2.1778547073815554e-05, "epoch": 3.421947449768161, "percentage": 68.57, "elapsed_time": "8:04:49", "remaining_time": "3:42:12"}
|
| 553 |
+
{"current_steps": 553, "total_steps": 805, "loss": 0.8951, "lr": 2.1624205300974346e-05, "epoch": 3.428129829984544, "percentage": 68.7, "elapsed_time": "8:05:43", "remaining_time": "3:41:20"}
|
| 554 |
+
{"current_steps": 554, "total_steps": 805, "loss": 0.891, "lr": 2.1470209521730064e-05, "epoch": 3.434312210200927, "percentage": 68.82, "elapsed_time": "8:06:34", "remaining_time": "3:40:26"}
|
| 555 |
+
{"current_steps": 555, "total_steps": 805, "loss": 0.9102, "lr": 2.131656263563369e-05, "epoch": 3.4404945904173108, "percentage": 68.94, "elapsed_time": "8:07:25", "remaining_time": "3:39:33"}
|
| 556 |
+
{"current_steps": 556, "total_steps": 805, "loss": 0.9022, "lr": 2.1163267535666994e-05, "epoch": 3.446676970633694, "percentage": 69.07, "elapsed_time": "8:08:16", "remaining_time": "3:38:40"}
|
| 557 |
+
{"current_steps": 557, "total_steps": 805, "loss": 0.8797, "lr": 2.1010327108188037e-05, "epoch": 3.452859350850077, "percentage": 69.19, "elapsed_time": "8:09:08", "remaining_time": "3:37:47"}
|
| 558 |
+
{"current_steps": 558, "total_steps": 805, "loss": 0.9014, "lr": 2.0857744232876797e-05, "epoch": 3.4590417310664607, "percentage": 69.32, "elapsed_time": "8:09:59", "remaining_time": "3:36:53"}
|
| 559 |
+
{"current_steps": 559, "total_steps": 805, "loss": 0.893, "lr": 2.070552178268102e-05, "epoch": 3.465224111282844, "percentage": 69.44, "elapsed_time": "8:10:50", "remaining_time": "3:36:00"}
|
| 560 |
+
{"current_steps": 560, "total_steps": 805, "loss": 0.8872, "lr": 2.0553662623762105e-05, "epoch": 3.471406491499227, "percentage": 69.57, "elapsed_time": "8:11:42", "remaining_time": "3:35:07"}
|
| 561 |
+
{"current_steps": 561, "total_steps": 805, "loss": 0.8975, "lr": 2.040216961544109e-05, "epoch": 3.4775888717156107, "percentage": 69.69, "elapsed_time": "8:12:33", "remaining_time": "3:34:13"}
|
| 562 |
+
{"current_steps": 562, "total_steps": 805, "loss": 0.8918, "lr": 2.0251045610144865e-05, "epoch": 3.483771251931994, "percentage": 69.81, "elapsed_time": "8:13:24", "remaining_time": "3:33:20"}
|
| 563 |
+
{"current_steps": 563, "total_steps": 805, "loss": 0.8703, "lr": 2.0100293453352446e-05, "epoch": 3.489953632148377, "percentage": 69.94, "elapsed_time": "8:14:15", "remaining_time": "3:32:27"}
|
| 564 |
+
{"current_steps": 564, "total_steps": 805, "loss": 0.8794, "lr": 1.9949915983541405e-05, "epoch": 3.4961360123647607, "percentage": 70.06, "elapsed_time": "8:15:06", "remaining_time": "3:31:33"}
|
| 565 |
+
{"current_steps": 565, "total_steps": 805, "loss": 0.8844, "lr": 1.9799916032134384e-05, "epoch": 3.502318392581144, "percentage": 70.19, "elapsed_time": "8:15:57", "remaining_time": "3:30:40"}
|
| 566 |
+
{"current_steps": 566, "total_steps": 805, "loss": 0.8934, "lr": 1.9650296423445865e-05, "epoch": 3.508500772797527, "percentage": 70.31, "elapsed_time": "8:16:52", "remaining_time": "3:29:48"}
|
| 567 |
+
{"current_steps": 567, "total_steps": 805, "loss": 0.8951, "lr": 1.9501059974628923e-05, "epoch": 3.51468315301391, "percentage": 70.43, "elapsed_time": "8:17:58", "remaining_time": "3:29:01"}
|
| 568 |
+
{"current_steps": 568, "total_steps": 805, "loss": 0.8931, "lr": 1.9352209495622215e-05, "epoch": 3.5208655332302934, "percentage": 70.56, "elapsed_time": "8:18:52", "remaining_time": "3:28:09"}
|
| 569 |
+
{"current_steps": 569, "total_steps": 805, "loss": 0.894, "lr": 1.920374778909702e-05, "epoch": 3.527047913446677, "percentage": 70.68, "elapsed_time": "8:19:43", "remaining_time": "3:27:16"}
|
| 570 |
+
{"current_steps": 570, "total_steps": 805, "loss": 0.8854, "lr": 1.9055677650404598e-05, "epoch": 3.53323029366306, "percentage": 70.81, "elapsed_time": "8:20:35", "remaining_time": "3:26:22"}
|
| 571 |
+
{"current_steps": 571, "total_steps": 805, "loss": 0.8912, "lr": 1.890800186752336e-05, "epoch": 3.5394126738794434, "percentage": 70.93, "elapsed_time": "8:21:26", "remaining_time": "3:25:29"}
|
| 572 |
+
{"current_steps": 572, "total_steps": 805, "loss": 0.8984, "lr": 1.8760723221006577e-05, "epoch": 3.545595054095827, "percentage": 71.06, "elapsed_time": "8:22:17", "remaining_time": "3:24:36"}
|
| 573 |
+
{"current_steps": 573, "total_steps": 805, "loss": 0.8957, "lr": 1.861384448392984e-05, "epoch": 3.55177743431221, "percentage": 71.18, "elapsed_time": "8:23:08", "remaining_time": "3:23:42"}
|
| 574 |
+
{"current_steps": 574, "total_steps": 805, "loss": 0.8882, "lr": 1.8467368421839045e-05, "epoch": 3.5579598145285933, "percentage": 71.3, "elapsed_time": "8:23:59", "remaining_time": "3:22:49"}
|
| 575 |
+
{"current_steps": 575, "total_steps": 805, "loss": 0.8837, "lr": 1.832129779269811e-05, "epoch": 3.564142194744977, "percentage": 71.43, "elapsed_time": "8:24:51", "remaining_time": "3:21:56"}
|
| 576 |
+
{"current_steps": 576, "total_steps": 805, "loss": 0.8705, "lr": 1.817563534683722e-05, "epoch": 3.57032457496136, "percentage": 71.55, "elapsed_time": "8:25:42", "remaining_time": "3:21:03"}
|
| 577 |
+
{"current_steps": 577, "total_steps": 805, "loss": 0.8814, "lr": 1.8030383826900935e-05, "epoch": 3.5765069551777433, "percentage": 71.68, "elapsed_time": "8:26:33", "remaining_time": "3:20:09"}
|
| 578 |
+
{"current_steps": 578, "total_steps": 805, "loss": 0.8981, "lr": 1.7885545967796606e-05, "epoch": 3.582689335394127, "percentage": 71.8, "elapsed_time": "8:27:24", "remaining_time": "3:19:16"}
|
| 579 |
+
{"current_steps": 579, "total_steps": 805, "loss": 0.8901, "lr": 1.7741124496642862e-05, "epoch": 3.58887171561051, "percentage": 71.93, "elapsed_time": "8:28:15", "remaining_time": "3:18:23"}
|
| 580 |
+
{"current_steps": 580, "total_steps": 805, "loss": 0.8666, "lr": 1.7597122132718202e-05, "epoch": 3.5950540958268933, "percentage": 72.05, "elapsed_time": "8:29:06", "remaining_time": "3:17:30"}
|
| 581 |
+
{"current_steps": 581, "total_steps": 805, "loss": 0.8936, "lr": 1.7453541587409963e-05, "epoch": 3.601236476043277, "percentage": 72.17, "elapsed_time": "8:30:01", "remaining_time": "3:16:38"}
|
| 582 |
+
{"current_steps": 582, "total_steps": 805, "loss": 0.8898, "lr": 1.731038556416304e-05, "epoch": 3.60741885625966, "percentage": 72.3, "elapsed_time": "8:31:06", "remaining_time": "3:15:50"}
|
| 583 |
+
{"current_steps": 583, "total_steps": 805, "loss": 0.8905, "lr": 1.716765675842919e-05, "epoch": 3.6136012364760433, "percentage": 72.42, "elapsed_time": "8:31:59", "remaining_time": "3:14:57"}
|
| 584 |
+
{"current_steps": 584, "total_steps": 805, "loss": 0.8945, "lr": 1.70253578576161e-05, "epoch": 3.6197836166924264, "percentage": 72.55, "elapsed_time": "8:32:51", "remaining_time": "3:14:04"}
|
| 585 |
+
{"current_steps": 585, "total_steps": 805, "loss": 0.8839, "lr": 1.688349154103699e-05, "epoch": 3.62596599690881, "percentage": 72.67, "elapsed_time": "8:33:42", "remaining_time": "3:13:11"}
|
| 586 |
+
{"current_steps": 586, "total_steps": 805, "loss": 0.8747, "lr": 1.6742060479859944e-05, "epoch": 3.6321483771251932, "percentage": 72.8, "elapsed_time": "8:34:34", "remaining_time": "3:12:18"}
|
| 587 |
+
{"current_steps": 587, "total_steps": 805, "loss": 0.8863, "lr": 1.6601067337057783e-05, "epoch": 3.6383307573415764, "percentage": 72.92, "elapsed_time": "8:35:25", "remaining_time": "3:11:25"}
|
| 588 |
+
{"current_steps": 588, "total_steps": 805, "loss": 0.8978, "lr": 1.6460514767357855e-05, "epoch": 3.6445131375579596, "percentage": 73.04, "elapsed_time": "8:36:16", "remaining_time": "3:10:31"}
|
| 589 |
+
{"current_steps": 589, "total_steps": 805, "loss": 0.8796, "lr": 1.6320405417192066e-05, "epoch": 3.650695517774343, "percentage": 73.17, "elapsed_time": "8:37:07", "remaining_time": "3:09:38"}
|
| 590 |
+
{"current_steps": 590, "total_steps": 805, "loss": 0.8962, "lr": 1.618074192464699e-05, "epoch": 3.6568778979907264, "percentage": 73.29, "elapsed_time": "8:37:59", "remaining_time": "3:08:45"}
|
| 591 |
+
{"current_steps": 591, "total_steps": 805, "loss": 0.8965, "lr": 1.6041526919414318e-05, "epoch": 3.6630602782071096, "percentage": 73.42, "elapsed_time": "8:38:50", "remaining_time": "3:07:52"}
|
| 592 |
+
{"current_steps": 592, "total_steps": 805, "loss": 0.8912, "lr": 1.5902763022741247e-05, "epoch": 3.669242658423493, "percentage": 73.54, "elapsed_time": "8:39:41", "remaining_time": "3:06:59"}
|
| 593 |
+
{"current_steps": 593, "total_steps": 805, "loss": 0.8974, "lr": 1.576445284738116e-05, "epoch": 3.6754250386398764, "percentage": 73.66, "elapsed_time": "8:40:33", "remaining_time": "3:06:05"}
|
| 594 |
+
{"current_steps": 594, "total_steps": 805, "loss": 0.8932, "lr": 1.5626598997544422e-05, "epoch": 3.6816074188562595, "percentage": 73.79, "elapsed_time": "8:41:24", "remaining_time": "3:05:12"}
|
| 595 |
+
{"current_steps": 595, "total_steps": 805, "loss": 0.8966, "lr": 1.548920406884935e-05, "epoch": 3.687789799072643, "percentage": 73.91, "elapsed_time": "8:42:15", "remaining_time": "3:04:19"}
|
| 596 |
+
{"current_steps": 596, "total_steps": 805, "loss": 0.8927, "lr": 1.5352270648273363e-05, "epoch": 3.6939721792890263, "percentage": 74.04, "elapsed_time": "8:43:09", "remaining_time": "3:03:27"}
|
| 597 |
+
{"current_steps": 597, "total_steps": 805, "loss": 0.8917, "lr": 1.5215801314104202e-05, "epoch": 3.7001545595054095, "percentage": 74.16, "elapsed_time": "8:44:16", "remaining_time": "3:02:39"}
|
| 598 |
+
{"current_steps": 598, "total_steps": 805, "loss": 0.8907, "lr": 1.5079798635891468e-05, "epoch": 3.706336939721793, "percentage": 74.29, "elapsed_time": "8:45:10", "remaining_time": "3:01:47"}
|
| 599 |
+
{"current_steps": 599, "total_steps": 805, "loss": 0.9016, "lr": 1.4944265174398203e-05, "epoch": 3.7125193199381763, "percentage": 74.41, "elapsed_time": "8:46:01", "remaining_time": "3:00:54"}
|
| 600 |
+
{"current_steps": 600, "total_steps": 805, "loss": 0.8811, "lr": 1.4809203481552681e-05, "epoch": 3.7187017001545595, "percentage": 74.53, "elapsed_time": "8:46:52", "remaining_time": "3:00:00"}
|
| 601 |
+
{"current_steps": 601, "total_steps": 805, "loss": 0.8811, "lr": 1.4674616100400303e-05, "epoch": 3.7248840803709427, "percentage": 74.66, "elapsed_time": "8:47:43", "remaining_time": "2:59:07"}
|
| 602 |
+
{"current_steps": 602, "total_steps": 805, "loss": 0.8996, "lr": 1.4540505565055858e-05, "epoch": 3.7310664605873263, "percentage": 74.78, "elapsed_time": "8:48:34", "remaining_time": "2:58:14"}
|
| 603 |
+
{"current_steps": 603, "total_steps": 805, "loss": 0.9037, "lr": 1.4406874400655615e-05, "epoch": 3.7372488408037094, "percentage": 74.91, "elapsed_time": "8:49:26", "remaining_time": "2:57:21"}
|
| 604 |
+
{"current_steps": 604, "total_steps": 805, "loss": 0.8851, "lr": 1.427372512330996e-05, "epoch": 3.7434312210200926, "percentage": 75.03, "elapsed_time": "8:50:17", "remaining_time": "2:56:28"}
|
| 605 |
+
{"current_steps": 605, "total_steps": 805, "loss": 0.8954, "lr": 1.4141060240055859e-05, "epoch": 3.749613601236476, "percentage": 75.16, "elapsed_time": "8:51:08", "remaining_time": "2:55:35"}
|
| 606 |
+
{"current_steps": 606, "total_steps": 805, "loss": 0.8808, "lr": 1.400888224880983e-05, "epoch": 3.7557959814528594, "percentage": 75.28, "elapsed_time": "8:52:00", "remaining_time": "2:54:42"}
|
| 607 |
+
{"current_steps": 607, "total_steps": 805, "loss": 0.8982, "lr": 1.3877193638320718e-05, "epoch": 3.7619783616692426, "percentage": 75.4, "elapsed_time": "8:52:51", "remaining_time": "2:53:48"}
|
| 608 |
+
{"current_steps": 608, "total_steps": 805, "loss": 0.8701, "lr": 1.3745996888122992e-05, "epoch": 3.7681607418856258, "percentage": 75.53, "elapsed_time": "8:53:42", "remaining_time": "2:52:55"}
|
| 609 |
+
{"current_steps": 609, "total_steps": 805, "loss": 0.8843, "lr": 1.361529446848998e-05, "epoch": 3.7743431221020094, "percentage": 75.65, "elapsed_time": "8:54:33", "remaining_time": "2:52:02"}
|
| 610 |
+
{"current_steps": 610, "total_steps": 805, "loss": 0.8966, "lr": 1.3485088840387369e-05, "epoch": 3.7805255023183926, "percentage": 75.78, "elapsed_time": "8:55:24", "remaining_time": "2:51:09"}
|
| 611 |
+
{"current_steps": 611, "total_steps": 805, "loss": 0.8846, "lr": 1.3355382455426892e-05, "epoch": 3.7867078825347757, "percentage": 75.9, "elapsed_time": "8:56:20", "remaining_time": "2:50:17"}
|
| 612 |
+
{"current_steps": 612, "total_steps": 805, "loss": 0.8846, "lr": 1.3226177755820087e-05, "epoch": 3.7928902627511594, "percentage": 76.02, "elapsed_time": "8:57:26", "remaining_time": "2:49:29"}
|
| 613 |
+
{"current_steps": 613, "total_steps": 805, "loss": 0.8855, "lr": 1.3097477174332482e-05, "epoch": 3.7990726429675425, "percentage": 76.15, "elapsed_time": "8:58:18", "remaining_time": "2:48:36"}
|
| 614 |
+
{"current_steps": 614, "total_steps": 805, "loss": 0.894, "lr": 1.296928313423758e-05, "epoch": 3.8052550231839257, "percentage": 76.27, "elapsed_time": "8:59:10", "remaining_time": "2:47:43"}
|
| 615 |
+
{"current_steps": 615, "total_steps": 805, "loss": 0.8847, "lr": 1.2841598049271395e-05, "epoch": 3.8114374034003093, "percentage": 76.4, "elapsed_time": "9:00:01", "remaining_time": "2:46:50"}
|
| 616 |
+
{"current_steps": 616, "total_steps": 805, "loss": 0.882, "lr": 1.271442432358688e-05, "epoch": 3.8176197836166925, "percentage": 76.52, "elapsed_time": "9:00:52", "remaining_time": "2:45:57"}
|
| 617 |
+
{"current_steps": 617, "total_steps": 805, "loss": 0.897, "lr": 1.2587764351708813e-05, "epoch": 3.8238021638330757, "percentage": 76.65, "elapsed_time": "9:01:43", "remaining_time": "2:45:03"}
|
| 618 |
+
{"current_steps": 618, "total_steps": 805, "loss": 0.8947, "lr": 1.2461620518488533e-05, "epoch": 3.8299845440494593, "percentage": 76.77, "elapsed_time": "9:02:35", "remaining_time": "2:44:10"}
|
| 619 |
+
{"current_steps": 619, "total_steps": 805, "loss": 0.8888, "lr": 1.2335995199059175e-05, "epoch": 3.8361669242658425, "percentage": 76.89, "elapsed_time": "9:03:26", "remaining_time": "2:43:17"}
|
| 620 |
+
{"current_steps": 620, "total_steps": 805, "loss": 0.8865, "lr": 1.2210890758790877e-05, "epoch": 3.8423493044822257, "percentage": 77.02, "elapsed_time": "9:04:17", "remaining_time": "2:42:24"}
|
| 621 |
+
{"current_steps": 621, "total_steps": 805, "loss": 0.8735, "lr": 1.2086309553246282e-05, "epoch": 3.848531684698609, "percentage": 77.14, "elapsed_time": "9:05:09", "remaining_time": "2:41:31"}
|
| 622 |
+
{"current_steps": 622, "total_steps": 805, "loss": 0.8975, "lr": 1.1962253928136129e-05, "epoch": 3.854714064914992, "percentage": 77.27, "elapsed_time": "9:06:00", "remaining_time": "2:40:38"}
|
| 623 |
+
{"current_steps": 623, "total_steps": 805, "loss": 0.8994, "lr": 1.1838726219275163e-05, "epoch": 3.8608964451313756, "percentage": 77.39, "elapsed_time": "9:06:51", "remaining_time": "2:39:45"}
|
| 624 |
+
{"current_steps": 624, "total_steps": 805, "loss": 0.8795, "lr": 1.1715728752538103e-05, "epoch": 3.867078825347759, "percentage": 77.52, "elapsed_time": "9:07:43", "remaining_time": "2:38:52"}
|
| 625 |
+
{"current_steps": 625, "total_steps": 805, "loss": 0.8846, "lr": 1.1593263843815854e-05, "epoch": 3.873261205564142, "percentage": 77.64, "elapsed_time": "9:08:34", "remaining_time": "2:37:59"}
|
| 626 |
+
{"current_steps": 626, "total_steps": 805, "loss": 0.8813, "lr": 1.1471333798971922e-05, "epoch": 3.8794435857805256, "percentage": 77.76, "elapsed_time": "9:09:29", "remaining_time": "2:37:07"}
|
| 627 |
+
{"current_steps": 627, "total_steps": 805, "loss": 0.88, "lr": 1.1349940913798978e-05, "epoch": 3.885625965996909, "percentage": 77.89, "elapsed_time": "9:10:35", "remaining_time": "2:36:18"}
|
| 628 |
+
{"current_steps": 628, "total_steps": 805, "loss": 0.8961, "lr": 1.1229087473975641e-05, "epoch": 3.891808346213292, "percentage": 78.01, "elapsed_time": "9:11:28", "remaining_time": "2:35:26"}
|
| 629 |
+
{"current_steps": 629, "total_steps": 805, "loss": 0.8748, "lr": 1.1108775755023422e-05, "epoch": 3.8979907264296756, "percentage": 78.14, "elapsed_time": "9:12:20", "remaining_time": "2:34:32"}
|
| 630 |
+
{"current_steps": 630, "total_steps": 805, "loss": 0.8935, "lr": 1.0989008022263906e-05, "epoch": 3.9041731066460588, "percentage": 78.26, "elapsed_time": "9:13:11", "remaining_time": "2:33:39"}
|
| 631 |
+
{"current_steps": 631, "total_steps": 805, "loss": 0.8852, "lr": 1.08697865307761e-05, "epoch": 3.910355486862442, "percentage": 78.39, "elapsed_time": "9:14:02", "remaining_time": "2:32:46"}
|
| 632 |
+
{"current_steps": 632, "total_steps": 805, "loss": 0.9049, "lr": 1.0751113525353957e-05, "epoch": 3.9165378670788256, "percentage": 78.51, "elapsed_time": "9:14:54", "remaining_time": "2:31:53"}
|
| 633 |
+
{"current_steps": 633, "total_steps": 805, "loss": 0.8931, "lr": 1.0632991240464068e-05, "epoch": 3.9227202472952087, "percentage": 78.63, "elapsed_time": "9:15:45", "remaining_time": "2:31:00"}
|
| 634 |
+
{"current_steps": 634, "total_steps": 805, "loss": 0.888, "lr": 1.0515421900203714e-05, "epoch": 3.928902627511592, "percentage": 78.76, "elapsed_time": "9:16:36", "remaining_time": "2:30:07"}
|
| 635 |
+
{"current_steps": 635, "total_steps": 805, "loss": 0.8984, "lr": 1.0398407718258836e-05, "epoch": 3.9350850077279755, "percentage": 78.88, "elapsed_time": "9:17:27", "remaining_time": "2:29:14"}
|
| 636 |
+
{"current_steps": 636, "total_steps": 805, "loss": 0.9026, "lr": 1.028195089786248e-05, "epoch": 3.9412673879443587, "percentage": 79.01, "elapsed_time": "9:18:18", "remaining_time": "2:28:21"}
|
| 637 |
+
{"current_steps": 637, "total_steps": 805, "loss": 0.8875, "lr": 1.0166053631753204e-05, "epoch": 3.947449768160742, "percentage": 79.13, "elapsed_time": "9:19:10", "remaining_time": "2:27:28"}
|
| 638 |
+
{"current_steps": 638, "total_steps": 805, "loss": 0.8929, "lr": 1.0050718102133916e-05, "epoch": 3.953632148377125, "percentage": 79.25, "elapsed_time": "9:20:01", "remaining_time": "2:26:35"}
|
| 639 |
+
{"current_steps": 639, "total_steps": 805, "loss": 0.8825, "lr": 9.935946480630658e-06, "epoch": 3.9598145285935082, "percentage": 79.38, "elapsed_time": "9:20:52", "remaining_time": "2:25:42"}
|
| 640 |
+
{"current_steps": 640, "total_steps": 805, "loss": 0.8982, "lr": 9.82174092825181e-06, "epoch": 3.965996908809892, "percentage": 79.5, "elapsed_time": "9:21:43", "remaining_time": "2:24:49"}
|
| 641 |
+
{"current_steps": 641, "total_steps": 805, "loss": 0.8939, "lr": 9.708103595347352e-06, "epoch": 3.972179289026275, "percentage": 79.63, "elapsed_time": "9:22:38", "remaining_time": "2:23:57"}
|
| 642 |
+
{"current_steps": 642, "total_steps": 805, "loss": 0.8843, "lr": 9.595036621568398e-06, "epoch": 3.978361669242658, "percentage": 79.75, "elapsed_time": "9:23:43", "remaining_time": "2:23:07"}
|
| 643 |
+
{"current_steps": 643, "total_steps": 805, "loss": 0.8987, "lr": 9.482542135826916e-06, "epoch": 3.984544049459042, "percentage": 79.88, "elapsed_time": "9:24:36", "remaining_time": "2:22:15"}
|
| 644 |
+
{"current_steps": 644, "total_steps": 805, "loss": 0.8774, "lr": 9.370622256255571e-06, "epoch": 3.990726429675425, "percentage": 80.0, "elapsed_time": "9:25:27", "remaining_time": "2:21:21"}
|
| 645 |
+
{"current_steps": 645, "total_steps": 805, "loss": 1.5557, "lr": 9.259279090167994e-06, "epoch": 3.996908809891808, "percentage": 80.12, "elapsed_time": "9:26:18", "remaining_time": "2:20:28"}
|
| 646 |
+
{"current_steps": 646, "total_steps": 805, "loss": 0.87, "lr": 9.148514734018917e-06, "epoch": 4.006182380216384, "percentage": 80.25, "elapsed_time": "9:28:32", "remaining_time": "2:19:56"}
|
| 647 |
+
{"current_steps": 647, "total_steps": 805, "loss": 0.8649, "lr": 9.038331273364869e-06, "epoch": 4.012364760432766, "percentage": 80.37, "elapsed_time": "9:29:24", "remaining_time": "2:19:03"}
|