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:e9f71a7c3dd627d9ffa2d2d3057269e4049921f02f84c89a2c64f864676b209f
|
| 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 sha256:6c92b7dee106d9ffb414d24404cd9db26f2342bcd28ae4afa6c6e575d9a9e1c6
|
| 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 sha256:3d41c4107cf7ab2a70d04d024055e50be22ec12e2a55d9a970255255998787d7
|
| 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 sha256:577e9f9bc99633cbe6f36d5d542152979b326906e7e3d82ea5d839d93f892c19
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -497,3 +497,250 @@
|
|
| 497 |
{"current_steps": 497, "total_steps": 1235, "loss": 0.26, "lr": 2.9918260112819952e-05, "epoch": 2.012151898734177, "percentage": 40.24, "elapsed_time": "3:09:14", "remaining_time": "4:41:00"}
|
| 498 |
{"current_steps": 498, "total_steps": 1235, "loss": 0.2416, "lr": 2.9869110322714778e-05, "epoch": 2.0162025316455696, "percentage": 40.32, "elapsed_time": "3:09:36", "remaining_time": "4:40:36"}
|
| 499 |
{"current_steps": 499, "total_steps": 1235, "loss": 0.2402, "lr": 2.9819881619466447e-05, "epoch": 2.020253164556962, "percentage": 40.4, "elapsed_time": "3:10:00", "remaining_time": "4:40:14"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 497 |
{"current_steps": 497, "total_steps": 1235, "loss": 0.26, "lr": 2.9918260112819952e-05, "epoch": 2.012151898734177, "percentage": 40.24, "elapsed_time": "3:09:14", "remaining_time": "4:41:00"}
|
| 498 |
{"current_steps": 498, "total_steps": 1235, "loss": 0.2416, "lr": 2.9869110322714778e-05, "epoch": 2.0162025316455696, "percentage": 40.32, "elapsed_time": "3:09:36", "remaining_time": "4:40:36"}
|
| 499 |
{"current_steps": 499, "total_steps": 1235, "loss": 0.2402, "lr": 2.9819881619466447e-05, "epoch": 2.020253164556962, "percentage": 40.4, "elapsed_time": "3:10:00", "remaining_time": "4:40:14"}
|
| 500 |
+
{"current_steps": 500, "total_steps": 1235, "loss": 0.2558, "lr": 2.9770574396706364e-05, "epoch": 2.0243037974683546, "percentage": 40.49, "elapsed_time": "3:10:22", "remaining_time": "4:39:51"}
|
| 501 |
+
{"current_steps": 501, "total_steps": 1235, "loss": 0.2475, "lr": 2.972118904869376e-05, "epoch": 2.0283544303797467, "percentage": 40.57, "elapsed_time": "3:10:43", "remaining_time": "4:39:25"}
|
| 502 |
+
{"current_steps": 502, "total_steps": 1235, "loss": 0.2527, "lr": 2.9671725970312563e-05, "epoch": 2.0324050632911392, "percentage": 40.65, "elapsed_time": "3:11:03", "remaining_time": "4:38:58"}
|
| 503 |
+
{"current_steps": 503, "total_steps": 1235, "loss": 0.25, "lr": 2.9622185557068238e-05, "epoch": 2.0364556962025318, "percentage": 40.73, "elapsed_time": "3:11:25", "remaining_time": "4:38:34"}
|
| 504 |
+
{"current_steps": 504, "total_steps": 1235, "loss": 0.2439, "lr": 2.95725682050846e-05, "epoch": 2.0405063291139243, "percentage": 40.81, "elapsed_time": "3:11:49", "remaining_time": "4:38:12"}
|
| 505 |
+
{"current_steps": 505, "total_steps": 1235, "loss": 0.2498, "lr": 2.9522874311100684e-05, "epoch": 2.0445569620253163, "percentage": 40.89, "elapsed_time": "3:12:12", "remaining_time": "4:37:50"}
|
| 506 |
+
{"current_steps": 506, "total_steps": 1235, "loss": 0.2443, "lr": 2.9473104272467526e-05, "epoch": 2.048607594936709, "percentage": 40.97, "elapsed_time": "3:12:35", "remaining_time": "4:37:27"}
|
| 507 |
+
{"current_steps": 507, "total_steps": 1235, "loss": 0.2571, "lr": 2.942325848714505e-05, "epoch": 2.0526582278481014, "percentage": 41.05, "elapsed_time": "3:12:56", "remaining_time": "4:37:03"}
|
| 508 |
+
{"current_steps": 508, "total_steps": 1235, "loss": 0.2512, "lr": 2.9373337353698804e-05, "epoch": 2.056708860759494, "percentage": 41.13, "elapsed_time": "3:13:17", "remaining_time": "4:36:37"}
|
| 509 |
+
{"current_steps": 509, "total_steps": 1235, "loss": 0.2508, "lr": 2.932334127129686e-05, "epoch": 2.060759493670886, "percentage": 41.21, "elapsed_time": "3:13:39", "remaining_time": "4:36:12"}
|
| 510 |
+
{"current_steps": 510, "total_steps": 1235, "loss": 0.2522, "lr": 2.9273270639706547e-05, "epoch": 2.0648101265822785, "percentage": 41.3, "elapsed_time": "3:14:01", "remaining_time": "4:35:49"}
|
| 511 |
+
{"current_steps": 511, "total_steps": 1235, "loss": 0.2594, "lr": 2.922312585929131e-05, "epoch": 2.068860759493671, "percentage": 41.38, "elapsed_time": "3:14:23", "remaining_time": "4:35:25"}
|
| 512 |
+
{"current_steps": 512, "total_steps": 1235, "loss": 0.2598, "lr": 2.9172907331007478e-05, "epoch": 2.0729113924050635, "percentage": 41.46, "elapsed_time": "3:14:45", "remaining_time": "4:35:01"}
|
| 513 |
+
{"current_steps": 513, "total_steps": 1235, "loss": 0.2554, "lr": 2.9122615456401053e-05, "epoch": 2.0769620253164556, "percentage": 41.54, "elapsed_time": "3:15:06", "remaining_time": "4:34:36"}
|
| 514 |
+
{"current_steps": 514, "total_steps": 1235, "loss": 0.2596, "lr": 2.9072250637604535e-05, "epoch": 2.081012658227848, "percentage": 41.62, "elapsed_time": "3:15:28", "remaining_time": "4:34:12"}
|
| 515 |
+
{"current_steps": 515, "total_steps": 1235, "loss": 0.2581, "lr": 2.9021813277333667e-05, "epoch": 2.0850632911392406, "percentage": 41.7, "elapsed_time": "3:15:50", "remaining_time": "4:33:47"}
|
| 516 |
+
{"current_steps": 516, "total_steps": 1235, "loss": 0.2486, "lr": 2.8971303778884244e-05, "epoch": 2.089113924050633, "percentage": 41.78, "elapsed_time": "3:16:12", "remaining_time": "4:33:24"}
|
| 517 |
+
{"current_steps": 517, "total_steps": 1235, "loss": 0.2616, "lr": 2.8920722546128863e-05, "epoch": 2.093164556962025, "percentage": 41.86, "elapsed_time": "3:16:34", "remaining_time": "4:33:00"}
|
| 518 |
+
{"current_steps": 518, "total_steps": 1235, "loss": 0.247, "lr": 2.887006998351372e-05, "epoch": 2.0972151898734177, "percentage": 41.94, "elapsed_time": "3:16:56", "remaining_time": "4:32:35"}
|
| 519 |
+
{"current_steps": 519, "total_steps": 1235, "loss": 0.2515, "lr": 2.881934649605535e-05, "epoch": 2.1012658227848102, "percentage": 42.02, "elapsed_time": "3:17:19", "remaining_time": "4:32:13"}
|
| 520 |
+
{"current_steps": 520, "total_steps": 1235, "loss": 0.2643, "lr": 2.8768552489337408e-05, "epoch": 2.1053164556962027, "percentage": 42.11, "elapsed_time": "3:17:41", "remaining_time": "4:31:50"}
|
| 521 |
+
{"current_steps": 521, "total_steps": 1235, "loss": 0.2555, "lr": 2.8717688369507425e-05, "epoch": 2.109367088607595, "percentage": 42.19, "elapsed_time": "3:18:02", "remaining_time": "4:31:24"}
|
| 522 |
+
{"current_steps": 522, "total_steps": 1235, "loss": 0.2596, "lr": 2.8666754543273535e-05, "epoch": 2.1134177215189873, "percentage": 42.27, "elapsed_time": "3:18:25", "remaining_time": "4:31:01"}
|
| 523 |
+
{"current_steps": 523, "total_steps": 1235, "loss": 0.2614, "lr": 2.8615751417901273e-05, "epoch": 2.11746835443038, "percentage": 42.35, "elapsed_time": "3:18:46", "remaining_time": "4:30:35"}
|
| 524 |
+
{"current_steps": 524, "total_steps": 1235, "loss": 0.2537, "lr": 2.856467940121025e-05, "epoch": 2.1215189873417724, "percentage": 42.43, "elapsed_time": "3:19:09", "remaining_time": "4:30:13"}
|
| 525 |
+
{"current_steps": 525, "total_steps": 1235, "loss": 0.254, "lr": 2.8513538901570964e-05, "epoch": 2.1255696202531644, "percentage": 42.51, "elapsed_time": "3:19:31", "remaining_time": "4:29:49"}
|
| 526 |
+
{"current_steps": 526, "total_steps": 1235, "loss": 0.25, "lr": 2.846233032790149e-05, "epoch": 2.129620253164557, "percentage": 42.59, "elapsed_time": "3:19:53", "remaining_time": "4:29:25"}
|
| 527 |
+
{"current_steps": 527, "total_steps": 1235, "loss": 0.2534, "lr": 2.84110540896642e-05, "epoch": 2.1336708860759495, "percentage": 42.67, "elapsed_time": "3:20:15", "remaining_time": "4:29:02"}
|
| 528 |
+
{"current_steps": 528, "total_steps": 1235, "loss": 0.2408, "lr": 2.8359710596862555e-05, "epoch": 2.137721518987342, "percentage": 42.75, "elapsed_time": "3:20:36", "remaining_time": "4:28:37"}
|
| 529 |
+
{"current_steps": 529, "total_steps": 1235, "loss": 0.2419, "lr": 2.8308300260037734e-05, "epoch": 2.141772151898734, "percentage": 42.83, "elapsed_time": "3:20:59", "remaining_time": "4:28:14"}
|
| 530 |
+
{"current_steps": 530, "total_steps": 1235, "loss": 0.245, "lr": 2.8256823490265424e-05, "epoch": 2.1458227848101266, "percentage": 42.91, "elapsed_time": "3:21:22", "remaining_time": "4:27:52"}
|
| 531 |
+
{"current_steps": 531, "total_steps": 1235, "loss": 0.2508, "lr": 2.8205280699152515e-05, "epoch": 2.149873417721519, "percentage": 43.0, "elapsed_time": "3:21:45", "remaining_time": "4:27:29"}
|
| 532 |
+
{"current_steps": 532, "total_steps": 1235, "loss": 0.2605, "lr": 2.8153672298833777e-05, "epoch": 2.1539240506329116, "percentage": 43.08, "elapsed_time": "3:22:07", "remaining_time": "4:27:05"}
|
| 533 |
+
{"current_steps": 533, "total_steps": 1235, "loss": 0.254, "lr": 2.8101998701968615e-05, "epoch": 2.1579746835443037, "percentage": 43.16, "elapsed_time": "3:22:31", "remaining_time": "4:26:44"}
|
| 534 |
+
{"current_steps": 534, "total_steps": 1235, "loss": 0.2559, "lr": 2.805026032173773e-05, "epoch": 2.162025316455696, "percentage": 43.24, "elapsed_time": "3:22:53", "remaining_time": "4:26:20"}
|
| 535 |
+
{"current_steps": 535, "total_steps": 1235, "loss": 0.2571, "lr": 2.7998457571839832e-05, "epoch": 2.1660759493670887, "percentage": 43.32, "elapsed_time": "3:23:16", "remaining_time": "4:25:57"}
|
| 536 |
+
{"current_steps": 536, "total_steps": 1235, "loss": 0.2502, "lr": 2.7946590866488322e-05, "epoch": 2.170126582278481, "percentage": 43.4, "elapsed_time": "3:23:37", "remaining_time": "4:25:33"}
|
| 537 |
+
{"current_steps": 537, "total_steps": 1235, "loss": 0.2583, "lr": 2.7894660620408e-05, "epoch": 2.1741772151898733, "percentage": 43.48, "elapsed_time": "3:24:00", "remaining_time": "4:25:10"}
|
| 538 |
+
{"current_steps": 538, "total_steps": 1235, "loss": 0.2546, "lr": 2.784266724883173e-05, "epoch": 2.178227848101266, "percentage": 43.56, "elapsed_time": "3:24:23", "remaining_time": "4:24:47"}
|
| 539 |
+
{"current_steps": 539, "total_steps": 1235, "loss": 0.2551, "lr": 2.7790611167497128e-05, "epoch": 2.1822784810126583, "percentage": 43.64, "elapsed_time": "3:24:44", "remaining_time": "4:24:22"}
|
| 540 |
+
{"current_steps": 540, "total_steps": 1235, "loss": 0.2522, "lr": 2.7738492792643224e-05, "epoch": 2.186329113924051, "percentage": 43.72, "elapsed_time": "3:25:06", "remaining_time": "4:23:59"}
|
| 541 |
+
{"current_steps": 541, "total_steps": 1235, "loss": 0.2554, "lr": 2.768631254100716e-05, "epoch": 2.190379746835443, "percentage": 43.81, "elapsed_time": "3:25:28", "remaining_time": "4:23:35"}
|
| 542 |
+
{"current_steps": 542, "total_steps": 1235, "loss": 0.2486, "lr": 2.7634070829820836e-05, "epoch": 2.1944303797468354, "percentage": 43.89, "elapsed_time": "3:25:50", "remaining_time": "4:23:11"}
|
| 543 |
+
{"current_steps": 543, "total_steps": 1235, "loss": 0.2373, "lr": 2.7581768076807592e-05, "epoch": 2.198481012658228, "percentage": 43.97, "elapsed_time": "3:26:13", "remaining_time": "4:22:48"}
|
| 544 |
+
{"current_steps": 544, "total_steps": 1235, "loss": 0.2448, "lr": 2.7529404700178832e-05, "epoch": 2.2025316455696204, "percentage": 44.05, "elapsed_time": "3:26:34", "remaining_time": "4:22:23"}
|
| 545 |
+
{"current_steps": 545, "total_steps": 1235, "loss": 0.2586, "lr": 2.7476981118630735e-05, "epoch": 2.2065822784810125, "percentage": 44.13, "elapsed_time": "3:26:56", "remaining_time": "4:21:59"}
|
| 546 |
+
{"current_steps": 546, "total_steps": 1235, "loss": 0.2536, "lr": 2.742449775134085e-05, "epoch": 2.210632911392405, "percentage": 44.21, "elapsed_time": "3:27:19", "remaining_time": "4:21:37"}
|
| 547 |
+
{"current_steps": 547, "total_steps": 1235, "loss": 0.2601, "lr": 2.7371955017964788e-05, "epoch": 2.2146835443037975, "percentage": 44.29, "elapsed_time": "3:27:41", "remaining_time": "4:21:13"}
|
| 548 |
+
{"current_steps": 548, "total_steps": 1235, "loss": 0.2459, "lr": 2.7319353338632845e-05, "epoch": 2.21873417721519, "percentage": 44.37, "elapsed_time": "3:28:03", "remaining_time": "4:20:49"}
|
| 549 |
+
{"current_steps": 549, "total_steps": 1235, "loss": 0.2419, "lr": 2.7266693133946645e-05, "epoch": 2.222784810126582, "percentage": 44.45, "elapsed_time": "3:28:26", "remaining_time": "4:20:27"}
|
| 550 |
+
{"current_steps": 550, "total_steps": 1235, "loss": 0.2625, "lr": 2.7213974824975785e-05, "epoch": 2.2268354430379746, "percentage": 44.53, "elapsed_time": "3:28:50", "remaining_time": "4:20:05"}
|
| 551 |
+
{"current_steps": 551, "total_steps": 1235, "loss": 0.255, "lr": 2.7161198833254464e-05, "epoch": 2.230886075949367, "percentage": 44.62, "elapsed_time": "3:29:14", "remaining_time": "4:19:44"}
|
| 552 |
+
{"current_steps": 552, "total_steps": 1235, "loss": 0.2616, "lr": 2.7108365580778095e-05, "epoch": 2.2349367088607597, "percentage": 44.7, "elapsed_time": "3:29:36", "remaining_time": "4:19:21"}
|
| 553 |
+
{"current_steps": 553, "total_steps": 1235, "loss": 0.2682, "lr": 2.705547548999996e-05, "epoch": 2.2389873417721518, "percentage": 44.78, "elapsed_time": "3:29:57", "remaining_time": "4:18:56"}
|
| 554 |
+
{"current_steps": 554, "total_steps": 1235, "loss": 0.2525, "lr": 2.7002528983827817e-05, "epoch": 2.2430379746835443, "percentage": 44.86, "elapsed_time": "3:30:20", "remaining_time": "4:18:33"}
|
| 555 |
+
{"current_steps": 555, "total_steps": 1235, "loss": 0.2556, "lr": 2.6949526485620517e-05, "epoch": 2.247088607594937, "percentage": 44.94, "elapsed_time": "3:30:41", "remaining_time": "4:18:08"}
|
| 556 |
+
{"current_steps": 556, "total_steps": 1235, "loss": 0.2494, "lr": 2.6896468419184623e-05, "epoch": 2.2511392405063293, "percentage": 45.02, "elapsed_time": "3:31:03", "remaining_time": "4:17:44"}
|
| 557 |
+
{"current_steps": 557, "total_steps": 1235, "loss": 0.2651, "lr": 2.6843355208771024e-05, "epoch": 2.2551898734177214, "percentage": 45.1, "elapsed_time": "3:31:26", "remaining_time": "4:17:22"}
|
| 558 |
+
{"current_steps": 558, "total_steps": 1235, "loss": 0.2478, "lr": 2.6790187279071536e-05, "epoch": 2.259240506329114, "percentage": 45.18, "elapsed_time": "3:31:49", "remaining_time": "4:16:59"}
|
| 559 |
+
{"current_steps": 559, "total_steps": 1235, "loss": 0.2453, "lr": 2.67369650552155e-05, "epoch": 2.2632911392405064, "percentage": 45.26, "elapsed_time": "3:32:10", "remaining_time": "4:16:34"}
|
| 560 |
+
{"current_steps": 560, "total_steps": 1235, "loss": 0.2471, "lr": 2.6683688962766407e-05, "epoch": 2.267341772151899, "percentage": 45.34, "elapsed_time": "3:32:31", "remaining_time": "4:16:10"}
|
| 561 |
+
{"current_steps": 561, "total_steps": 1235, "loss": 0.2573, "lr": 2.6630359427718468e-05, "epoch": 2.271392405063291, "percentage": 45.43, "elapsed_time": "3:32:53", "remaining_time": "4:15:46"}
|
| 562 |
+
{"current_steps": 562, "total_steps": 1235, "loss": 0.2519, "lr": 2.6576976876493225e-05, "epoch": 2.2754430379746835, "percentage": 45.51, "elapsed_time": "3:33:15", "remaining_time": "4:15:22"}
|
| 563 |
+
{"current_steps": 563, "total_steps": 1235, "loss": 0.2545, "lr": 2.652354173593614e-05, "epoch": 2.279493670886076, "percentage": 45.59, "elapsed_time": "3:33:38", "remaining_time": "4:15:00"}
|
| 564 |
+
{"current_steps": 564, "total_steps": 1235, "loss": 0.2509, "lr": 2.647005443331317e-05, "epoch": 2.2835443037974685, "percentage": 45.67, "elapsed_time": "3:34:01", "remaining_time": "4:14:37"}
|
| 565 |
+
{"current_steps": 565, "total_steps": 1235, "loss": 0.2561, "lr": 2.6416515396307354e-05, "epoch": 2.2875949367088606, "percentage": 45.75, "elapsed_time": "3:34:25", "remaining_time": "4:14:15"}
|
| 566 |
+
{"current_steps": 566, "total_steps": 1235, "loss": 0.2428, "lr": 2.636292505301542e-05, "epoch": 2.291645569620253, "percentage": 45.83, "elapsed_time": "3:34:46", "remaining_time": "4:13:51"}
|
| 567 |
+
{"current_steps": 567, "total_steps": 1235, "loss": 0.2616, "lr": 2.630928383194431e-05, "epoch": 2.2956962025316456, "percentage": 45.91, "elapsed_time": "3:35:10", "remaining_time": "4:13:29"}
|
| 568 |
+
{"current_steps": 568, "total_steps": 1235, "loss": 0.2431, "lr": 2.625559216200781e-05, "epoch": 2.299746835443038, "percentage": 45.99, "elapsed_time": "3:35:31", "remaining_time": "4:13:05"}
|
| 569 |
+
{"current_steps": 569, "total_steps": 1235, "loss": 0.2492, "lr": 2.620185047252308e-05, "epoch": 2.3037974683544302, "percentage": 46.07, "elapsed_time": "3:35:53", "remaining_time": "4:12:42"}
|
| 570 |
+
{"current_steps": 570, "total_steps": 1235, "loss": 0.2513, "lr": 2.614805919320723e-05, "epoch": 2.3078481012658227, "percentage": 46.15, "elapsed_time": "3:36:17", "remaining_time": "4:12:20"}
|
| 571 |
+
{"current_steps": 571, "total_steps": 1235, "loss": 0.2371, "lr": 2.6094218754173895e-05, "epoch": 2.3118987341772153, "percentage": 46.23, "elapsed_time": "3:36:41", "remaining_time": "4:11:59"}
|
| 572 |
+
{"current_steps": 572, "total_steps": 1235, "loss": 0.2615, "lr": 2.60403295859298e-05, "epoch": 2.3159493670886078, "percentage": 46.32, "elapsed_time": "3:37:05", "remaining_time": "4:11:37"}
|
| 573 |
+
{"current_steps": 573, "total_steps": 1235, "loss": 0.2513, "lr": 2.5986392119371297e-05, "epoch": 2.32, "percentage": 46.4, "elapsed_time": "3:37:26", "remaining_time": "4:11:12"}
|
| 574 |
+
{"current_steps": 574, "total_steps": 1235, "loss": 0.262, "lr": 2.5932406785780928e-05, "epoch": 2.3240506329113924, "percentage": 46.48, "elapsed_time": "3:37:48", "remaining_time": "4:10:48"}
|
| 575 |
+
{"current_steps": 575, "total_steps": 1235, "loss": 0.2563, "lr": 2.5878374016823987e-05, "epoch": 2.328101265822785, "percentage": 46.56, "elapsed_time": "3:38:10", "remaining_time": "4:10:25"}
|
| 576 |
+
{"current_steps": 576, "total_steps": 1235, "loss": 0.2551, "lr": 2.5824294244545045e-05, "epoch": 2.3321518987341774, "percentage": 46.64, "elapsed_time": "3:38:34", "remaining_time": "4:10:04"}
|
| 577 |
+
{"current_steps": 577, "total_steps": 1235, "loss": 0.2413, "lr": 2.577016790136453e-05, "epoch": 2.3362025316455695, "percentage": 46.72, "elapsed_time": "3:38:56", "remaining_time": "4:09:40"}
|
| 578 |
+
{"current_steps": 578, "total_steps": 1235, "loss": 0.2561, "lr": 2.5715995420075225e-05, "epoch": 2.340253164556962, "percentage": 46.8, "elapsed_time": "3:39:16", "remaining_time": "4:09:15"}
|
| 579 |
+
{"current_steps": 579, "total_steps": 1235, "loss": 0.2575, "lr": 2.5661777233838864e-05, "epoch": 2.3443037974683545, "percentage": 46.88, "elapsed_time": "3:39:40", "remaining_time": "4:08:52"}
|
| 580 |
+
{"current_steps": 580, "total_steps": 1235, "loss": 0.263, "lr": 2.5607513776182616e-05, "epoch": 2.348354430379747, "percentage": 46.96, "elapsed_time": "3:40:01", "remaining_time": "4:08:28"}
|
| 581 |
+
{"current_steps": 581, "total_steps": 1235, "loss": 0.2498, "lr": 2.5553205480995633e-05, "epoch": 2.352405063291139, "percentage": 47.04, "elapsed_time": "3:40:24", "remaining_time": "4:08:06"}
|
| 582 |
+
{"current_steps": 582, "total_steps": 1235, "loss": 0.2516, "lr": 2.5498852782525604e-05, "epoch": 2.3564556962025316, "percentage": 47.13, "elapsed_time": "3:40:45", "remaining_time": "4:07:41"}
|
| 583 |
+
{"current_steps": 583, "total_steps": 1235, "loss": 0.2633, "lr": 2.5444456115375252e-05, "epoch": 2.360506329113924, "percentage": 47.21, "elapsed_time": "3:41:08", "remaining_time": "4:07:18"}
|
| 584 |
+
{"current_steps": 584, "total_steps": 1235, "loss": 0.2627, "lr": 2.539001591449889e-05, "epoch": 2.3645569620253166, "percentage": 47.29, "elapsed_time": "3:41:31", "remaining_time": "4:06:56"}
|
| 585 |
+
{"current_steps": 585, "total_steps": 1235, "loss": 0.2553, "lr": 2.53355326151989e-05, "epoch": 2.3686075949367087, "percentage": 47.37, "elapsed_time": "3:41:52", "remaining_time": "4:06:31"}
|
| 586 |
+
{"current_steps": 586, "total_steps": 1235, "loss": 0.2764, "lr": 2.5281006653122288e-05, "epoch": 2.372658227848101, "percentage": 47.45, "elapsed_time": "3:42:15", "remaining_time": "4:06:09"}
|
| 587 |
+
{"current_steps": 587, "total_steps": 1235, "loss": 0.2638, "lr": 2.5226438464257217e-05, "epoch": 2.3767088607594937, "percentage": 47.53, "elapsed_time": "3:42:37", "remaining_time": "4:05:45"}
|
| 588 |
+
{"current_steps": 588, "total_steps": 1235, "loss": 0.2603, "lr": 2.5171828484929447e-05, "epoch": 2.3807594936708862, "percentage": 47.61, "elapsed_time": "3:43:01", "remaining_time": "4:05:23"}
|
| 589 |
+
{"current_steps": 589, "total_steps": 1235, "loss": 0.2558, "lr": 2.5117177151798934e-05, "epoch": 2.3848101265822783, "percentage": 47.69, "elapsed_time": "3:43:24", "remaining_time": "4:05:01"}
|
| 590 |
+
{"current_steps": 590, "total_steps": 1235, "loss": 0.2631, "lr": 2.506248490185627e-05, "epoch": 2.388860759493671, "percentage": 47.77, "elapsed_time": "3:43:45", "remaining_time": "4:04:37"}
|
| 591 |
+
{"current_steps": 591, "total_steps": 1235, "loss": 0.261, "lr": 2.500775217241923e-05, "epoch": 2.3929113924050633, "percentage": 47.85, "elapsed_time": "3:44:08", "remaining_time": "4:04:14"}
|
| 592 |
+
{"current_steps": 592, "total_steps": 1235, "loss": 0.2537, "lr": 2.4952979401129266e-05, "epoch": 2.396962025316456, "percentage": 47.94, "elapsed_time": "3:44:30", "remaining_time": "4:03:51"}
|
| 593 |
+
{"current_steps": 593, "total_steps": 1235, "loss": 0.257, "lr": 2.4898167025948e-05, "epoch": 2.401012658227848, "percentage": 48.02, "elapsed_time": "3:44:53", "remaining_time": "4:03:28"}
|
| 594 |
+
{"current_steps": 594, "total_steps": 1235, "loss": 0.2577, "lr": 2.4843315485153703e-05, "epoch": 2.4050632911392404, "percentage": 48.1, "elapsed_time": "3:45:16", "remaining_time": "4:03:05"}
|
| 595 |
+
{"current_steps": 595, "total_steps": 1235, "loss": 0.2618, "lr": 2.4788425217337856e-05, "epoch": 2.409113924050633, "percentage": 48.18, "elapsed_time": "3:45:36", "remaining_time": "4:02:40"}
|
| 596 |
+
{"current_steps": 596, "total_steps": 1235, "loss": 0.2501, "lr": 2.4733496661401572e-05, "epoch": 2.4131645569620255, "percentage": 48.26, "elapsed_time": "3:45:58", "remaining_time": "4:02:17"}
|
| 597 |
+
{"current_steps": 597, "total_steps": 1235, "loss": 0.2604, "lr": 2.4678530256552114e-05, "epoch": 2.4172151898734175, "percentage": 48.34, "elapsed_time": "3:46:22", "remaining_time": "4:01:55"}
|
| 598 |
+
{"current_steps": 598, "total_steps": 1235, "loss": 0.265, "lr": 2.46235264422994e-05, "epoch": 2.42126582278481, "percentage": 48.42, "elapsed_time": "3:46:45", "remaining_time": "4:01:32"}
|
| 599 |
+
{"current_steps": 599, "total_steps": 1235, "loss": 0.2584, "lr": 2.4568485658452452e-05, "epoch": 2.4253164556962026, "percentage": 48.5, "elapsed_time": "3:47:07", "remaining_time": "4:01:09"}
|
| 600 |
+
{"current_steps": 600, "total_steps": 1235, "loss": 0.25, "lr": 2.451340834511592e-05, "epoch": 2.429367088607595, "percentage": 48.58, "elapsed_time": "3:47:30", "remaining_time": "4:00:46"}
|
| 601 |
+
{"current_steps": 601, "total_steps": 1235, "loss": 0.2637, "lr": 2.4458294942686528e-05, "epoch": 2.433417721518987, "percentage": 48.66, "elapsed_time": "3:47:52", "remaining_time": "4:00:22"}
|
| 602 |
+
{"current_steps": 602, "total_steps": 1235, "loss": 0.2478, "lr": 2.440314589184958e-05, "epoch": 2.4374683544303797, "percentage": 48.74, "elapsed_time": "3:48:14", "remaining_time": "3:59:59"}
|
| 603 |
+
{"current_steps": 603, "total_steps": 1235, "loss": 0.2592, "lr": 2.434796163357541e-05, "epoch": 2.441518987341772, "percentage": 48.83, "elapsed_time": "3:48:37", "remaining_time": "3:59:36"}
|
| 604 |
+
{"current_steps": 604, "total_steps": 1235, "loss": 0.2454, "lr": 2.429274260911588e-05, "epoch": 2.4455696202531647, "percentage": 48.91, "elapsed_time": "3:48:57", "remaining_time": "3:59:11"}
|
| 605 |
+
{"current_steps": 605, "total_steps": 1235, "loss": 0.2531, "lr": 2.423748926000084e-05, "epoch": 2.449620253164557, "percentage": 48.99, "elapsed_time": "3:49:17", "remaining_time": "3:58:45"}
|
| 606 |
+
{"current_steps": 606, "total_steps": 1235, "loss": 0.2507, "lr": 2.418220202803459e-05, "epoch": 2.4536708860759493, "percentage": 49.07, "elapsed_time": "3:49:38", "remaining_time": "3:58:21"}
|
| 607 |
+
{"current_steps": 607, "total_steps": 1235, "loss": 0.2587, "lr": 2.412688135529237e-05, "epoch": 2.457721518987342, "percentage": 49.15, "elapsed_time": "3:50:01", "remaining_time": "3:57:58"}
|
| 608 |
+
{"current_steps": 608, "total_steps": 1235, "loss": 0.2555, "lr": 2.4071527684116807e-05, "epoch": 2.4617721518987343, "percentage": 49.23, "elapsed_time": "3:50:26", "remaining_time": "3:57:38"}
|
| 609 |
+
{"current_steps": 609, "total_steps": 1235, "loss": 0.263, "lr": 2.4016141457114372e-05, "epoch": 2.4658227848101264, "percentage": 49.31, "elapsed_time": "3:50:49", "remaining_time": "3:57:16"}
|
| 610 |
+
{"current_steps": 610, "total_steps": 1235, "loss": 0.2536, "lr": 2.396072311715187e-05, "epoch": 2.469873417721519, "percentage": 49.39, "elapsed_time": "3:51:10", "remaining_time": "3:56:51"}
|
| 611 |
+
{"current_steps": 611, "total_steps": 1235, "loss": 0.2616, "lr": 2.3905273107352863e-05, "epoch": 2.4739240506329114, "percentage": 49.47, "elapsed_time": "3:51:32", "remaining_time": "3:56:27"}
|
| 612 |
+
{"current_steps": 612, "total_steps": 1235, "loss": 0.2507, "lr": 2.3849791871094157e-05, "epoch": 2.477974683544304, "percentage": 49.55, "elapsed_time": "3:51:55", "remaining_time": "3:56:05"}
|
| 613 |
+
{"current_steps": 613, "total_steps": 1235, "loss": 0.2675, "lr": 2.379427985200223e-05, "epoch": 2.482025316455696, "percentage": 49.64, "elapsed_time": "3:52:16", "remaining_time": "3:55:40"}
|
| 614 |
+
{"current_steps": 614, "total_steps": 1235, "loss": 0.257, "lr": 2.373873749394972e-05, "epoch": 2.4860759493670885, "percentage": 49.72, "elapsed_time": "3:52:37", "remaining_time": "3:55:16"}
|
| 615 |
+
{"current_steps": 615, "total_steps": 1235, "loss": 0.2532, "lr": 2.3683165241051836e-05, "epoch": 2.490126582278481, "percentage": 49.8, "elapsed_time": "3:52:59", "remaining_time": "3:54:53"}
|
| 616 |
+
{"current_steps": 616, "total_steps": 1235, "loss": 0.2539, "lr": 2.3627563537662823e-05, "epoch": 2.4941772151898736, "percentage": 49.88, "elapsed_time": "3:53:21", "remaining_time": "3:54:29"}
|
| 617 |
+
{"current_steps": 617, "total_steps": 1235, "loss": 0.2653, "lr": 2.3571932828372433e-05, "epoch": 2.4982278481012656, "percentage": 49.96, "elapsed_time": "3:53:44", "remaining_time": "3:54:07"}
|
| 618 |
+
{"current_steps": 618, "total_steps": 1235, "loss": 0.2655, "lr": 2.351627355800233e-05, "epoch": 2.502278481012658, "percentage": 50.04, "elapsed_time": "3:54:05", "remaining_time": "3:53:42"}
|
| 619 |
+
{"current_steps": 619, "total_steps": 1235, "loss": 0.2591, "lr": 2.346058617160256e-05, "epoch": 2.5063291139240507, "percentage": 50.12, "elapsed_time": "3:54:27", "remaining_time": "3:53:19"}
|
| 620 |
+
{"current_steps": 620, "total_steps": 1235, "loss": 0.2548, "lr": 2.3404871114447976e-05, "epoch": 2.510379746835443, "percentage": 50.2, "elapsed_time": "3:54:50", "remaining_time": "3:52:56"}
|
| 621 |
+
{"current_steps": 621, "total_steps": 1235, "loss": 0.2701, "lr": 2.334912883203469e-05, "epoch": 2.5144303797468357, "percentage": 50.28, "elapsed_time": "3:55:12", "remaining_time": "3:52:33"}
|
| 622 |
+
{"current_steps": 622, "total_steps": 1235, "loss": 0.2661, "lr": 2.3293359770076505e-05, "epoch": 2.5184810126582278, "percentage": 50.36, "elapsed_time": "3:55:33", "remaining_time": "3:52:09"}
|
| 623 |
+
{"current_steps": 623, "total_steps": 1235, "loss": 0.2605, "lr": 2.323756437450136e-05, "epoch": 2.5225316455696203, "percentage": 50.45, "elapsed_time": "3:55:57", "remaining_time": "3:51:47"}
|
| 624 |
+
{"current_steps": 624, "total_steps": 1235, "loss": 0.2557, "lr": 2.3181743091447754e-05, "epoch": 2.526582278481013, "percentage": 50.53, "elapsed_time": "3:56:20", "remaining_time": "3:51:25"}
|
| 625 |
+
{"current_steps": 625, "total_steps": 1235, "loss": 0.2612, "lr": 2.3125896367261164e-05, "epoch": 2.530632911392405, "percentage": 50.61, "elapsed_time": "3:56:44", "remaining_time": "3:51:03"}
|
| 626 |
+
{"current_steps": 626, "total_steps": 1235, "loss": 0.2582, "lr": 2.307002464849052e-05, "epoch": 2.5346835443037974, "percentage": 50.69, "elapsed_time": "3:57:05", "remaining_time": "3:50:38"}
|
| 627 |
+
{"current_steps": 627, "total_steps": 1235, "loss": 0.2539, "lr": 2.30141283818846e-05, "epoch": 2.53873417721519, "percentage": 50.77, "elapsed_time": "3:57:26", "remaining_time": "3:50:14"}
|
| 628 |
+
{"current_steps": 628, "total_steps": 1235, "loss": 0.2514, "lr": 2.2958208014388462e-05, "epoch": 2.5427848101265824, "percentage": 50.85, "elapsed_time": "3:57:50", "remaining_time": "3:49:53"}
|
| 629 |
+
{"current_steps": 629, "total_steps": 1235, "loss": 0.2462, "lr": 2.2902263993139857e-05, "epoch": 2.546835443037975, "percentage": 50.93, "elapsed_time": "3:58:13", "remaining_time": "3:49:30"}
|
| 630 |
+
{"current_steps": 630, "total_steps": 1235, "loss": 0.2467, "lr": 2.2846296765465708e-05, "epoch": 2.550886075949367, "percentage": 51.01, "elapsed_time": "3:58:36", "remaining_time": "3:49:08"}
|
| 631 |
+
{"current_steps": 631, "total_steps": 1235, "loss": 0.2577, "lr": 2.2790306778878465e-05, "epoch": 2.5549367088607595, "percentage": 51.09, "elapsed_time": "3:58:57", "remaining_time": "3:48:43"}
|
| 632 |
+
{"current_steps": 632, "total_steps": 1235, "loss": 0.2535, "lr": 2.273429448107257e-05, "epoch": 2.558987341772152, "percentage": 51.17, "elapsed_time": "3:59:21", "remaining_time": "3:48:22"}
|
| 633 |
+
{"current_steps": 633, "total_steps": 1235, "loss": 0.2573, "lr": 2.2678260319920868e-05, "epoch": 2.563037974683544, "percentage": 51.26, "elapsed_time": "3:59:43", "remaining_time": "3:47:59"}
|
| 634 |
+
{"current_steps": 634, "total_steps": 1235, "loss": 0.2544, "lr": 2.262220474347102e-05, "epoch": 2.5670886075949366, "percentage": 51.34, "elapsed_time": "4:00:06", "remaining_time": "3:47:36"}
|
| 635 |
+
{"current_steps": 635, "total_steps": 1235, "loss": 0.2553, "lr": 2.2566128199941918e-05, "epoch": 2.571139240506329, "percentage": 51.42, "elapsed_time": "4:00:28", "remaining_time": "3:47:12"}
|
| 636 |
+
{"current_steps": 636, "total_steps": 1235, "loss": 0.2625, "lr": 2.2510031137720104e-05, "epoch": 2.5751898734177217, "percentage": 51.5, "elapsed_time": "4:00:51", "remaining_time": "3:46:51"}
|
| 637 |
+
{"current_steps": 637, "total_steps": 1235, "loss": 0.2546, "lr": 2.2453914005356206e-05, "epoch": 2.579240506329114, "percentage": 51.58, "elapsed_time": "4:01:14", "remaining_time": "3:46:28"}
|
| 638 |
+
{"current_steps": 638, "total_steps": 1235, "loss": 0.2544, "lr": 2.2397777251561302e-05, "epoch": 2.5832911392405062, "percentage": 51.66, "elapsed_time": "4:01:36", "remaining_time": "3:46:04"}
|
| 639 |
+
{"current_steps": 639, "total_steps": 1235, "loss": 0.2466, "lr": 2.2341621325203393e-05, "epoch": 2.5873417721518988, "percentage": 51.74, "elapsed_time": "4:01:56", "remaining_time": "3:45:39"}
|
| 640 |
+
{"current_steps": 640, "total_steps": 1235, "loss": 0.2637, "lr": 2.2285446675303764e-05, "epoch": 2.5913924050632913, "percentage": 51.82, "elapsed_time": "4:02:18", "remaining_time": "3:45:16"}
|
| 641 |
+
{"current_steps": 641, "total_steps": 1235, "loss": 0.2601, "lr": 2.2229253751033423e-05, "epoch": 2.5954430379746833, "percentage": 51.9, "elapsed_time": "4:02:42", "remaining_time": "3:44:54"}
|
| 642 |
+
{"current_steps": 642, "total_steps": 1235, "loss": 0.262, "lr": 2.2173043001709492e-05, "epoch": 2.599493670886076, "percentage": 51.98, "elapsed_time": "4:03:04", "remaining_time": "3:44:31"}
|
| 643 |
+
{"current_steps": 643, "total_steps": 1235, "loss": 0.264, "lr": 2.2116814876791627e-05, "epoch": 2.6035443037974684, "percentage": 52.06, "elapsed_time": "4:03:27", "remaining_time": "3:44:09"}
|
| 644 |
+
{"current_steps": 644, "total_steps": 1235, "loss": 0.262, "lr": 2.2060569825878413e-05, "epoch": 2.607594936708861, "percentage": 52.15, "elapsed_time": "4:03:48", "remaining_time": "3:43:44"}
|
| 645 |
+
{"current_steps": 645, "total_steps": 1235, "loss": 0.2516, "lr": 2.2004308298703777e-05, "epoch": 2.6116455696202534, "percentage": 52.23, "elapsed_time": "4:04:09", "remaining_time": "3:43:20"}
|
| 646 |
+
{"current_steps": 646, "total_steps": 1235, "loss": 0.2586, "lr": 2.1948030745133396e-05, "epoch": 2.6156962025316455, "percentage": 52.31, "elapsed_time": "4:04:32", "remaining_time": "3:42:57"}
|
| 647 |
+
{"current_steps": 647, "total_steps": 1235, "loss": 0.2514, "lr": 2.1891737615161083e-05, "epoch": 2.619746835443038, "percentage": 52.39, "elapsed_time": "4:04:53", "remaining_time": "3:42:34"}
|
| 648 |
+
{"current_steps": 648, "total_steps": 1235, "loss": 0.2541, "lr": 2.1835429358905218e-05, "epoch": 2.6237974683544305, "percentage": 52.47, "elapsed_time": "4:05:16", "remaining_time": "3:42:11"}
|
| 649 |
+
{"current_steps": 649, "total_steps": 1235, "loss": 0.2629, "lr": 2.17791064266051e-05, "epoch": 2.6278481012658226, "percentage": 52.55, "elapsed_time": "4:05:39", "remaining_time": "3:41:48"}
|
| 650 |
+
{"current_steps": 650, "total_steps": 1235, "loss": 0.2504, "lr": 2.172276926861741e-05, "epoch": 2.631898734177215, "percentage": 52.63, "elapsed_time": "4:06:02", "remaining_time": "3:41:26"}
|
| 651 |
+
{"current_steps": 651, "total_steps": 1235, "loss": 0.2579, "lr": 2.166641833541255e-05, "epoch": 2.6359493670886076, "percentage": 52.71, "elapsed_time": "4:06:24", "remaining_time": "3:41:02"}
|
| 652 |
+
{"current_steps": 652, "total_steps": 1235, "loss": 0.2448, "lr": 2.161005407757109e-05, "epoch": 2.64, "percentage": 52.79, "elapsed_time": "4:06:47", "remaining_time": "3:40:40"}
|
| 653 |
+
{"current_steps": 653, "total_steps": 1235, "loss": 0.2676, "lr": 2.155367694578013e-05, "epoch": 2.6440506329113926, "percentage": 52.87, "elapsed_time": "4:07:11", "remaining_time": "3:40:18"}
|
| 654 |
+
{"current_steps": 654, "total_steps": 1235, "loss": 0.2576, "lr": 2.1497287390829712e-05, "epoch": 2.6481012658227847, "percentage": 52.96, "elapsed_time": "4:07:33", "remaining_time": "3:39:55"}
|
| 655 |
+
{"current_steps": 655, "total_steps": 1235, "loss": 0.2583, "lr": 2.1440885863609208e-05, "epoch": 2.6521518987341772, "percentage": 53.04, "elapsed_time": "4:07:56", "remaining_time": "3:39:32"}
|
| 656 |
+
{"current_steps": 656, "total_steps": 1235, "loss": 0.2556, "lr": 2.1384472815103737e-05, "epoch": 2.6562025316455697, "percentage": 53.12, "elapsed_time": "4:08:17", "remaining_time": "3:39:09"}
|
| 657 |
+
{"current_steps": 657, "total_steps": 1235, "loss": 0.2554, "lr": 2.1328048696390534e-05, "epoch": 2.660253164556962, "percentage": 53.2, "elapsed_time": "4:08:40", "remaining_time": "3:38:46"}
|
| 658 |
+
{"current_steps": 658, "total_steps": 1235, "loss": 0.2415, "lr": 2.1271613958635342e-05, "epoch": 2.6643037974683543, "percentage": 53.28, "elapsed_time": "4:09:03", "remaining_time": "3:38:24"}
|
| 659 |
+
{"current_steps": 659, "total_steps": 1235, "loss": 0.2455, "lr": 2.1215169053088825e-05, "epoch": 2.668354430379747, "percentage": 53.36, "elapsed_time": "4:09:26", "remaining_time": "3:38:01"}
|
| 660 |
+
{"current_steps": 660, "total_steps": 1235, "loss": 0.2698, "lr": 2.1158714431082937e-05, "epoch": 2.6724050632911394, "percentage": 53.44, "elapsed_time": "4:09:50", "remaining_time": "3:37:39"}
|
| 661 |
+
{"current_steps": 661, "total_steps": 1235, "loss": 0.2611, "lr": 2.110225054402733e-05, "epoch": 2.676455696202532, "percentage": 53.52, "elapsed_time": "4:10:11", "remaining_time": "3:37:15"}
|
| 662 |
+
{"current_steps": 662, "total_steps": 1235, "loss": 0.2531, "lr": 2.1045777843405747e-05, "epoch": 2.680506329113924, "percentage": 53.6, "elapsed_time": "4:10:32", "remaining_time": "3:36:51"}
|
| 663 |
+
{"current_steps": 663, "total_steps": 1235, "loss": 0.2579, "lr": 2.09892967807724e-05, "epoch": 2.6845569620253165, "percentage": 53.68, "elapsed_time": "4:10:54", "remaining_time": "3:36:28"}
|
| 664 |
+
{"current_steps": 664, "total_steps": 1235, "loss": 0.2615, "lr": 2.093280780774835e-05, "epoch": 2.688607594936709, "percentage": 53.77, "elapsed_time": "4:11:18", "remaining_time": "3:36:06"}
|
| 665 |
+
{"current_steps": 665, "total_steps": 1235, "loss": 0.2502, "lr": 2.087631137601793e-05, "epoch": 2.692658227848101, "percentage": 53.85, "elapsed_time": "4:11:40", "remaining_time": "3:35:43"}
|
| 666 |
+
{"current_steps": 666, "total_steps": 1235, "loss": 0.2639, "lr": 2.0819807937325104e-05, "epoch": 2.6967088607594936, "percentage": 53.93, "elapsed_time": "4:12:02", "remaining_time": "3:35:19"}
|
| 667 |
+
{"current_steps": 667, "total_steps": 1235, "loss": 0.2619, "lr": 2.0763297943469847e-05, "epoch": 2.700759493670886, "percentage": 54.01, "elapsed_time": "4:12:26", "remaining_time": "3:34:58"}
|
| 668 |
+
{"current_steps": 668, "total_steps": 1235, "loss": 0.2403, "lr": 2.070678184630458e-05, "epoch": 2.7048101265822786, "percentage": 54.09, "elapsed_time": "4:12:48", "remaining_time": "3:34:34"}
|
| 669 |
+
{"current_steps": 669, "total_steps": 1235, "loss": 0.246, "lr": 2.06502600977305e-05, "epoch": 2.708860759493671, "percentage": 54.17, "elapsed_time": "4:13:11", "remaining_time": "3:34:12"}
|
| 670 |
+
{"current_steps": 670, "total_steps": 1235, "loss": 0.2603, "lr": 2.0593733149694008e-05, "epoch": 2.712911392405063, "percentage": 54.25, "elapsed_time": "4:13:34", "remaining_time": "3:33:50"}
|
| 671 |
+
{"current_steps": 671, "total_steps": 1235, "loss": 0.2572, "lr": 2.0537201454183074e-05, "epoch": 2.7169620253164557, "percentage": 54.33, "elapsed_time": "4:13:58", "remaining_time": "3:33:28"}
|
| 672 |
+
{"current_steps": 672, "total_steps": 1235, "loss": 0.2532, "lr": 2.0480665463223626e-05, "epoch": 2.721012658227848, "percentage": 54.41, "elapsed_time": "4:14:22", "remaining_time": "3:33:06"}
|
| 673 |
+
{"current_steps": 673, "total_steps": 1235, "loss": 0.2631, "lr": 2.042412562887594e-05, "epoch": 2.7250632911392403, "percentage": 54.49, "elapsed_time": "4:14:46", "remaining_time": "3:32:45"}
|
| 674 |
+
{"current_steps": 674, "total_steps": 1235, "loss": 0.2656, "lr": 2.0367582403231033e-05, "epoch": 2.729113924050633, "percentage": 54.57, "elapsed_time": "4:15:08", "remaining_time": "3:32:22"}
|
| 675 |
+
{"current_steps": 675, "total_steps": 1235, "loss": 0.2571, "lr": 2.0311036238407023e-05, "epoch": 2.7331645569620253, "percentage": 54.66, "elapsed_time": "4:15:30", "remaining_time": "3:31:58"}
|
| 676 |
+
{"current_steps": 676, "total_steps": 1235, "loss": 0.2629, "lr": 2.0254487586545534e-05, "epoch": 2.737215189873418, "percentage": 54.74, "elapsed_time": "4:15:52", "remaining_time": "3:31:35"}
|
| 677 |
+
{"current_steps": 677, "total_steps": 1235, "loss": 0.2451, "lr": 2.0197936899808088e-05, "epoch": 2.7412658227848103, "percentage": 54.82, "elapsed_time": "4:16:15", "remaining_time": "3:31:13"}
|
| 678 |
+
{"current_steps": 678, "total_steps": 1235, "loss": 0.2582, "lr": 2.0141384630372466e-05, "epoch": 2.7453164556962024, "percentage": 54.9, "elapsed_time": "4:16:38", "remaining_time": "3:30:50"}
|
| 679 |
+
{"current_steps": 679, "total_steps": 1235, "loss": 0.2484, "lr": 2.0084831230429106e-05, "epoch": 2.749367088607595, "percentage": 54.98, "elapsed_time": "4:17:02", "remaining_time": "3:30:28"}
|
| 680 |
+
{"current_steps": 680, "total_steps": 1235, "loss": 0.2482, "lr": 2.0028277152177492e-05, "epoch": 2.7534177215189874, "percentage": 55.06, "elapsed_time": "4:17:26", "remaining_time": "3:30:06"}
|
| 681 |
+
{"current_steps": 681, "total_steps": 1235, "loss": 0.243, "lr": 1.9971722847822518e-05, "epoch": 2.7574683544303795, "percentage": 55.14, "elapsed_time": "4:17:47", "remaining_time": "3:29:43"}
|
| 682 |
+
{"current_steps": 682, "total_steps": 1235, "loss": 0.2567, "lr": 1.99151687695709e-05, "epoch": 2.761518987341772, "percentage": 55.22, "elapsed_time": "4:18:08", "remaining_time": "3:29:18"}
|
| 683 |
+
{"current_steps": 683, "total_steps": 1235, "loss": 0.2598, "lr": 1.9858615369627537e-05, "epoch": 2.7655696202531646, "percentage": 55.3, "elapsed_time": "4:18:30", "remaining_time": "3:28:55"}
|
| 684 |
+
{"current_steps": 684, "total_steps": 1235, "loss": 0.2679, "lr": 1.9802063100191916e-05, "epoch": 2.769620253164557, "percentage": 55.38, "elapsed_time": "4:18:53", "remaining_time": "3:28:33"}
|
| 685 |
+
{"current_steps": 685, "total_steps": 1235, "loss": 0.2539, "lr": 1.974551241345447e-05, "epoch": 2.7736708860759496, "percentage": 55.47, "elapsed_time": "4:19:15", "remaining_time": "3:28:09"}
|
| 686 |
+
{"current_steps": 686, "total_steps": 1235, "loss": 0.2547, "lr": 1.9688963761592984e-05, "epoch": 2.7777215189873417, "percentage": 55.55, "elapsed_time": "4:19:36", "remaining_time": "3:27:45"}
|
| 687 |
+
{"current_steps": 687, "total_steps": 1235, "loss": 0.2604, "lr": 1.963241759676897e-05, "epoch": 2.781772151898734, "percentage": 55.63, "elapsed_time": "4:19:58", "remaining_time": "3:27:22"}
|
| 688 |
+
{"current_steps": 688, "total_steps": 1235, "loss": 0.2405, "lr": 1.9575874371124066e-05, "epoch": 2.7858227848101267, "percentage": 55.71, "elapsed_time": "4:20:19", "remaining_time": "3:26:58"}
|
| 689 |
+
{"current_steps": 689, "total_steps": 1235, "loss": 0.2543, "lr": 1.951933453677638e-05, "epoch": 2.7898734177215188, "percentage": 55.79, "elapsed_time": "4:20:41", "remaining_time": "3:26:35"}
|
| 690 |
+
{"current_steps": 690, "total_steps": 1235, "loss": 0.2635, "lr": 1.9462798545816932e-05, "epoch": 2.7939240506329113, "percentage": 55.87, "elapsed_time": "4:21:04", "remaining_time": "3:26:12"}
|
| 691 |
+
{"current_steps": 691, "total_steps": 1235, "loss": 0.2556, "lr": 1.9406266850305996e-05, "epoch": 2.797974683544304, "percentage": 55.95, "elapsed_time": "4:21:27", "remaining_time": "3:25:50"}
|
| 692 |
+
{"current_steps": 692, "total_steps": 1235, "loss": 0.2447, "lr": 1.9349739902269503e-05, "epoch": 2.8020253164556963, "percentage": 56.03, "elapsed_time": "4:21:51", "remaining_time": "3:25:28"}
|
| 693 |
+
{"current_steps": 693, "total_steps": 1235, "loss": 0.2623, "lr": 1.9293218153695425e-05, "epoch": 2.806075949367089, "percentage": 56.11, "elapsed_time": "4:22:14", "remaining_time": "3:25:06"}
|
| 694 |
+
{"current_steps": 694, "total_steps": 1235, "loss": 0.2515, "lr": 1.9236702056530153e-05, "epoch": 2.810126582278481, "percentage": 56.19, "elapsed_time": "4:22:35", "remaining_time": "3:24:41"}
|
| 695 |
+
{"current_steps": 695, "total_steps": 1235, "loss": 0.2639, "lr": 1.9180192062674907e-05, "epoch": 2.8141772151898734, "percentage": 56.28, "elapsed_time": "4:22:56", "remaining_time": "3:24:18"}
|
| 696 |
+
{"current_steps": 696, "total_steps": 1235, "loss": 0.2522, "lr": 1.9123688623982076e-05, "epoch": 2.818227848101266, "percentage": 56.36, "elapsed_time": "4:23:17", "remaining_time": "3:23:54"}
|
| 697 |
+
{"current_steps": 697, "total_steps": 1235, "loss": 0.2406, "lr": 1.906719219225165e-05, "epoch": 2.822278481012658, "percentage": 56.44, "elapsed_time": "4:23:39", "remaining_time": "3:23:30"}
|
| 698 |
+
{"current_steps": 698, "total_steps": 1235, "loss": 0.2527, "lr": 1.9010703219227603e-05, "epoch": 2.8263291139240505, "percentage": 56.52, "elapsed_time": "4:24:01", "remaining_time": "3:23:07"}
|
| 699 |
+
{"current_steps": 699, "total_steps": 1235, "loss": 0.265, "lr": 1.8954222156594256e-05, "epoch": 2.830379746835443, "percentage": 56.6, "elapsed_time": "4:24:24", "remaining_time": "3:22:44"}
|
| 700 |
+
{"current_steps": 700, "total_steps": 1235, "loss": 0.2527, "lr": 1.8897749455972673e-05, "epoch": 2.8344303797468355, "percentage": 56.68, "elapsed_time": "4:24:46", "remaining_time": "3:22:21"}
|
| 701 |
+
{"current_steps": 701, "total_steps": 1235, "loss": 0.2478, "lr": 1.884128556891707e-05, "epoch": 2.838481012658228, "percentage": 56.76, "elapsed_time": "4:25:06", "remaining_time": "3:21:57"}
|
| 702 |
+
{"current_steps": 702, "total_steps": 1235, "loss": 0.2482, "lr": 1.878483094691119e-05, "epoch": 2.84253164556962, "percentage": 56.84, "elapsed_time": "4:25:28", "remaining_time": "3:21:33"}
|
| 703 |
+
{"current_steps": 703, "total_steps": 1235, "loss": 0.2544, "lr": 1.8728386041364664e-05, "epoch": 2.8465822784810126, "percentage": 56.92, "elapsed_time": "4:25:50", "remaining_time": "3:21:10"}
|
| 704 |
+
{"current_steps": 704, "total_steps": 1235, "loss": 0.2436, "lr": 1.867195130360947e-05, "epoch": 2.850632911392405, "percentage": 57.0, "elapsed_time": "4:26:13", "remaining_time": "3:20:48"}
|
| 705 |
+
{"current_steps": 705, "total_steps": 1235, "loss": 0.2527, "lr": 1.8615527184896263e-05, "epoch": 2.8546835443037972, "percentage": 57.09, "elapsed_time": "4:26:34", "remaining_time": "3:20:24"}
|
| 706 |
+
{"current_steps": 706, "total_steps": 1235, "loss": 0.248, "lr": 1.8559114136390795e-05, "epoch": 2.8587341772151897, "percentage": 57.17, "elapsed_time": "4:26:58", "remaining_time": "3:20:02"}
|
| 707 |
+
{"current_steps": 707, "total_steps": 1235, "loss": 0.2539, "lr": 1.8502712609170298e-05, "epoch": 2.8627848101265823, "percentage": 57.25, "elapsed_time": "4:27:22", "remaining_time": "3:19:40"}
|
| 708 |
+
{"current_steps": 708, "total_steps": 1235, "loss": 0.2603, "lr": 1.8446323054219876e-05, "epoch": 2.8668354430379748, "percentage": 57.33, "elapsed_time": "4:27:45", "remaining_time": "3:19:18"}
|
| 709 |
+
{"current_steps": 709, "total_steps": 1235, "loss": 0.2494, "lr": 1.838994592242891e-05, "epoch": 2.8708860759493673, "percentage": 57.41, "elapsed_time": "4:28:06", "remaining_time": "3:18:54"}
|
| 710 |
+
{"current_steps": 710, "total_steps": 1235, "loss": 0.2399, "lr": 1.8333581664587453e-05, "epoch": 2.8749367088607594, "percentage": 57.49, "elapsed_time": "4:28:29", "remaining_time": "3:18:31"}
|
| 711 |
+
{"current_steps": 711, "total_steps": 1235, "loss": 0.2535, "lr": 1.8277230731382593e-05, "epoch": 2.878987341772152, "percentage": 57.57, "elapsed_time": "4:28:53", "remaining_time": "3:18:10"}
|
| 712 |
+
{"current_steps": 712, "total_steps": 1235, "loss": 0.2419, "lr": 1.82208935733949e-05, "epoch": 2.8830379746835444, "percentage": 57.65, "elapsed_time": "4:29:16", "remaining_time": "3:17:47"}
|
| 713 |
+
{"current_steps": 713, "total_steps": 1235, "loss": 0.2588, "lr": 1.8164570641094793e-05, "epoch": 2.8870886075949365, "percentage": 57.73, "elapsed_time": "4:29:38", "remaining_time": "3:17:24"}
|
| 714 |
+
{"current_steps": 714, "total_steps": 1235, "loss": 0.2436, "lr": 1.810826238483892e-05, "epoch": 2.891139240506329, "percentage": 57.81, "elapsed_time": "4:30:02", "remaining_time": "3:17:02"}
|
| 715 |
+
{"current_steps": 715, "total_steps": 1235, "loss": 0.2537, "lr": 1.8051969254866608e-05, "epoch": 2.8951898734177215, "percentage": 57.89, "elapsed_time": "4:30:26", "remaining_time": "3:16:41"}
|
| 716 |
+
{"current_steps": 716, "total_steps": 1235, "loss": 0.2657, "lr": 1.7995691701296226e-05, "epoch": 2.899240506329114, "percentage": 57.98, "elapsed_time": "4:30:50", "remaining_time": "3:16:19"}
|
| 717 |
+
{"current_steps": 717, "total_steps": 1235, "loss": 0.2472, "lr": 1.7939430174121593e-05, "epoch": 2.9032911392405065, "percentage": 58.06, "elapsed_time": "4:31:13", "remaining_time": "3:15:56"}
|
| 718 |
+
{"current_steps": 718, "total_steps": 1235, "loss": 0.262, "lr": 1.788318512320838e-05, "epoch": 2.9073417721518986, "percentage": 58.14, "elapsed_time": "4:31:35", "remaining_time": "3:15:33"}
|
| 719 |
+
{"current_steps": 719, "total_steps": 1235, "loss": 0.239, "lr": 1.782695699829051e-05, "epoch": 2.911392405063291, "percentage": 58.22, "elapsed_time": "4:31:55", "remaining_time": "3:15:09"}
|
| 720 |
+
{"current_steps": 720, "total_steps": 1235, "loss": 0.2532, "lr": 1.7770746248966587e-05, "epoch": 2.9154430379746836, "percentage": 58.3, "elapsed_time": "4:32:18", "remaining_time": "3:14:46"}
|
| 721 |
+
{"current_steps": 721, "total_steps": 1235, "loss": 0.2698, "lr": 1.7714553324696243e-05, "epoch": 2.9194936708860757, "percentage": 58.38, "elapsed_time": "4:32:39", "remaining_time": "3:14:22"}
|
| 722 |
+
{"current_steps": 722, "total_steps": 1235, "loss": 0.2622, "lr": 1.7658378674796614e-05, "epoch": 2.923544303797468, "percentage": 58.46, "elapsed_time": "4:33:01", "remaining_time": "3:13:59"}
|
| 723 |
+
{"current_steps": 723, "total_steps": 1235, "loss": 0.2644, "lr": 1.76022227484387e-05, "epoch": 2.9275949367088607, "percentage": 58.54, "elapsed_time": "4:33:23", "remaining_time": "3:13:36"}
|
| 724 |
+
{"current_steps": 724, "total_steps": 1235, "loss": 0.2476, "lr": 1.7546085994643807e-05, "epoch": 2.9316455696202532, "percentage": 58.62, "elapsed_time": "4:33:45", "remaining_time": "3:13:13"}
|
| 725 |
+
{"current_steps": 725, "total_steps": 1235, "loss": 0.2401, "lr": 1.7489968862279902e-05, "epoch": 2.9356962025316458, "percentage": 58.7, "elapsed_time": "4:34:10", "remaining_time": "3:12:52"}
|
| 726 |
+
{"current_steps": 726, "total_steps": 1235, "loss": 0.2653, "lr": 1.743387180005809e-05, "epoch": 2.939746835443038, "percentage": 58.79, "elapsed_time": "4:34:34", "remaining_time": "3:12:30"}
|
| 727 |
+
{"current_steps": 727, "total_steps": 1235, "loss": 0.2646, "lr": 1.737779525652899e-05, "epoch": 2.9437974683544303, "percentage": 58.87, "elapsed_time": "4:34:57", "remaining_time": "3:12:07"}
|
| 728 |
+
{"current_steps": 728, "total_steps": 1235, "loss": 0.2597, "lr": 1.732173968007914e-05, "epoch": 2.947848101265823, "percentage": 58.95, "elapsed_time": "4:35:20", "remaining_time": "3:11:45"}
|
| 729 |
+
{"current_steps": 729, "total_steps": 1235, "loss": 0.2485, "lr": 1.7265705518927437e-05, "epoch": 2.951898734177215, "percentage": 59.03, "elapsed_time": "4:35:42", "remaining_time": "3:11:22"}
|
| 730 |
+
{"current_steps": 730, "total_steps": 1235, "loss": 0.254, "lr": 1.7209693221121542e-05, "epoch": 2.9559493670886074, "percentage": 59.11, "elapsed_time": "4:36:05", "remaining_time": "3:10:59"}
|
| 731 |
+
{"current_steps": 731, "total_steps": 1235, "loss": 0.2468, "lr": 1.7153703234534302e-05, "epoch": 2.96, "percentage": 59.19, "elapsed_time": "4:36:26", "remaining_time": "3:10:36"}
|
| 732 |
+
{"current_steps": 732, "total_steps": 1235, "loss": 0.2595, "lr": 1.709773600686015e-05, "epoch": 2.9640506329113925, "percentage": 59.27, "elapsed_time": "4:36:49", "remaining_time": "3:10:13"}
|
| 733 |
+
{"current_steps": 733, "total_steps": 1235, "loss": 0.2487, "lr": 1.7041791985611548e-05, "epoch": 2.968101265822785, "percentage": 59.35, "elapsed_time": "4:37:10", "remaining_time": "3:09:49"}
|
| 734 |
+
{"current_steps": 734, "total_steps": 1235, "loss": 0.2452, "lr": 1.69858716181154e-05, "epoch": 2.972151898734177, "percentage": 59.43, "elapsed_time": "4:37:33", "remaining_time": "3:09:26"}
|
| 735 |
+
{"current_steps": 735, "total_steps": 1235, "loss": 0.2444, "lr": 1.692997535150948e-05, "epoch": 2.9762025316455696, "percentage": 59.51, "elapsed_time": "4:37:57", "remaining_time": "3:09:04"}
|
| 736 |
+
{"current_steps": 736, "total_steps": 1235, "loss": 0.2538, "lr": 1.687410363273884e-05, "epoch": 2.980253164556962, "percentage": 59.6, "elapsed_time": "4:38:18", "remaining_time": "3:08:41"}
|
| 737 |
+
{"current_steps": 737, "total_steps": 1235, "loss": 0.2593, "lr": 1.6818256908552257e-05, "epoch": 2.984303797468354, "percentage": 59.68, "elapsed_time": "4:38:41", "remaining_time": "3:08:18"}
|
| 738 |
+
{"current_steps": 738, "total_steps": 1235, "loss": 0.2453, "lr": 1.6762435625498646e-05, "epoch": 2.9883544303797467, "percentage": 59.76, "elapsed_time": "4:39:04", "remaining_time": "3:07:56"}
|
| 739 |
+
{"current_steps": 739, "total_steps": 1235, "loss": 0.2662, "lr": 1.67066402299235e-05, "epoch": 2.992405063291139, "percentage": 59.84, "elapsed_time": "4:39:26", "remaining_time": "3:07:33"}
|
| 740 |
+
{"current_steps": 740, "total_steps": 1235, "loss": 0.2544, "lr": 1.6650871167965313e-05, "epoch": 2.9964556962025317, "percentage": 59.92, "elapsed_time": "4:39:48", "remaining_time": "3:07:10"}
|
| 741 |
+
{"current_steps": 741, "total_steps": 1235, "loss": 0.2518, "lr": 1.6595128885552028e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "4:40:07", "remaining_time": "3:06:44"}
|
| 742 |
+
{"current_steps": 742, "total_steps": 1235, "loss": 0.1875, "lr": 1.653941382839745e-05, "epoch": 3.0040506329113925, "percentage": 60.08, "elapsed_time": "4:41:20", "remaining_time": "3:06:55"}
|
| 743 |
+
{"current_steps": 743, "total_steps": 1235, "loss": 0.1707, "lr": 1.6483726441997673e-05, "epoch": 3.008101265822785, "percentage": 60.16, "elapsed_time": "4:41:42", "remaining_time": "3:06:32"}
|
| 744 |
+
{"current_steps": 744, "total_steps": 1235, "loss": 0.1798, "lr": 1.642806717162757e-05, "epoch": 3.012151898734177, "percentage": 60.24, "elapsed_time": "4:42:04", "remaining_time": "3:06:09"}
|
| 745 |
+
{"current_steps": 745, "total_steps": 1235, "loss": 0.1797, "lr": 1.637243646233718e-05, "epoch": 3.0162025316455696, "percentage": 60.32, "elapsed_time": "4:42:25", "remaining_time": "3:05:45"}
|
| 746 |
+
{"current_steps": 746, "total_steps": 1235, "loss": 0.1723, "lr": 1.6316834758948174e-05, "epoch": 3.020253164556962, "percentage": 60.4, "elapsed_time": "4:42:48", "remaining_time": "3:05:22"}
|