liangyuch commited on
Commit
a7a22ba
·
verified ·
1 Parent(s): 70e28ef

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:bb7395f9a8769832c59d5267f088b81035df74506d1b79d4ff62acb06abb67c8
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5275774548815fbde694174ffbd2f2a23785cc7ffc3c586488487b8dead66a79
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20af83944a10ea6fbb8544e6dc0796154cad5fcb1c4364fd732de8442eab92dd
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a606763a439a5ff63fd4e80e3a7541c3fbca3f7f571b06b4489e339849cc19a4
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:d6906b5b2b1b4e743592c729a1754d86a1894c63ce556842e078fa39486874d2
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e13bca780e44b939fc8ca9c2ce66b299ec65776273b1f218e8f8eb9629b1f9
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:b0a3ed6baa2e0922f92fc38d07ba7ac46249cf30d286332ee0e82ced84dd3000
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5a758007ebc3c84840603832ad45a7e069e2dc2833caadaa846c7de71e8c15
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -363,3 +363,158 @@
363
  {"current_steps": 363, "total_steps": 519, "loss": 0.5211, "lr": 2.53893943188118e-06, "epoch": 2.098265895953757, "percentage": 69.94, "elapsed_time": "0:38:48", "remaining_time": "0:16:40"}
364
  {"current_steps": 364, "total_steps": 519, "loss": 0.5555, "lr": 2.5097161239717975e-06, "epoch": 2.1040462427745665, "percentage": 70.13, "elapsed_time": "0:38:55", "remaining_time": "0:16:34"}
365
  {"current_steps": 365, "total_steps": 519, "loss": 0.6461, "lr": 2.4806055132824186e-06, "epoch": 2.1098265895953756, "percentage": 70.33, "elapsed_time": "0:39:01", "remaining_time": "0:16:27"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
363
  {"current_steps": 363, "total_steps": 519, "loss": 0.5211, "lr": 2.53893943188118e-06, "epoch": 2.098265895953757, "percentage": 69.94, "elapsed_time": "0:38:48", "remaining_time": "0:16:40"}
364
  {"current_steps": 364, "total_steps": 519, "loss": 0.5555, "lr": 2.5097161239717975e-06, "epoch": 2.1040462427745665, "percentage": 70.13, "elapsed_time": "0:38:55", "remaining_time": "0:16:34"}
365
  {"current_steps": 365, "total_steps": 519, "loss": 0.6461, "lr": 2.4806055132824186e-06, "epoch": 2.1098265895953756, "percentage": 70.33, "elapsed_time": "0:39:01", "remaining_time": "0:16:27"}
366
+ {"current_steps": 366, "total_steps": 519, "loss": 0.496, "lr": 2.4516089172069852e-06, "epoch": 2.115606936416185, "percentage": 70.52, "elapsed_time": "0:39:05", "remaining_time": "0:16:20"}
367
+ {"current_steps": 367, "total_steps": 519, "loss": 0.6613, "lr": 2.422727647979734e-06, "epoch": 2.121387283236994, "percentage": 70.71, "elapsed_time": "0:39:12", "remaining_time": "0:16:14"}
368
+ {"current_steps": 368, "total_steps": 519, "loss": 0.4495, "lr": 2.393963012615817e-06, "epoch": 2.1271676300578033, "percentage": 70.91, "elapsed_time": "0:39:19", "remaining_time": "0:16:08"}
369
+ {"current_steps": 369, "total_steps": 519, "loss": 0.5333, "lr": 2.365316312852144e-06, "epoch": 2.132947976878613, "percentage": 71.1, "elapsed_time": "0:39:25", "remaining_time": "0:16:01"}
370
+ {"current_steps": 370, "total_steps": 519, "loss": 0.523, "lr": 2.336788845088478e-06, "epoch": 2.138728323699422, "percentage": 71.29, "elapsed_time": "0:39:30", "remaining_time": "0:15:54"}
371
+ {"current_steps": 371, "total_steps": 519, "loss": 0.4837, "lr": 2.308381900328767e-06, "epoch": 2.1445086705202314, "percentage": 71.48, "elapsed_time": "0:39:33", "remaining_time": "0:15:46"}
372
+ {"current_steps": 372, "total_steps": 519, "loss": 0.4845, "lr": 2.2800967641227127e-06, "epoch": 2.1502890173410405, "percentage": 71.68, "elapsed_time": "0:39:37", "remaining_time": "0:15:39"}
373
+ {"current_steps": 373, "total_steps": 519, "loss": 0.5861, "lr": 2.2519347165076067e-06, "epoch": 2.1560693641618496, "percentage": 71.87, "elapsed_time": "0:39:42", "remaining_time": "0:15:32"}
374
+ {"current_steps": 374, "total_steps": 519, "loss": 0.4178, "lr": 2.223897031950386e-06, "epoch": 2.161849710982659, "percentage": 72.06, "elapsed_time": "0:39:45", "remaining_time": "0:15:24"}
375
+ {"current_steps": 375, "total_steps": 519, "loss": 0.4706, "lr": 2.195984979289974e-06, "epoch": 2.167630057803468, "percentage": 72.25, "elapsed_time": "0:39:49", "remaining_time": "0:15:17"}
376
+ {"current_steps": 376, "total_steps": 519, "loss": 0.4277, "lr": 2.1681998216798476e-06, "epoch": 2.1734104046242773, "percentage": 72.45, "elapsed_time": "0:39:55", "remaining_time": "0:15:11"}
377
+ {"current_steps": 377, "total_steps": 519, "loss": 0.4447, "lr": 2.140542816530882e-06, "epoch": 2.179190751445087, "percentage": 72.64, "elapsed_time": "0:39:59", "remaining_time": "0:15:03"}
378
+ {"current_steps": 378, "total_steps": 519, "loss": 0.5207, "lr": 2.1130152154544346e-06, "epoch": 2.184971098265896, "percentage": 72.83, "elapsed_time": "0:40:05", "remaining_time": "0:14:57"}
379
+ {"current_steps": 379, "total_steps": 519, "loss": 0.5315, "lr": 2.0856182642057182e-06, "epoch": 2.1907514450867054, "percentage": 73.03, "elapsed_time": "0:40:12", "remaining_time": "0:14:51"}
380
+ {"current_steps": 380, "total_steps": 519, "loss": 0.4879, "lr": 2.058353202627417e-06, "epoch": 2.1965317919075145, "percentage": 73.22, "elapsed_time": "0:40:18", "remaining_time": "0:14:44"}
381
+ {"current_steps": 381, "total_steps": 519, "loss": 0.497, "lr": 2.0312212645935755e-06, "epoch": 2.2023121387283235, "percentage": 73.41, "elapsed_time": "0:40:24", "remaining_time": "0:14:38"}
382
+ {"current_steps": 382, "total_steps": 519, "loss": 0.6146, "lr": 2.0042236779537668e-06, "epoch": 2.208092485549133, "percentage": 73.6, "elapsed_time": "0:40:31", "remaining_time": "0:14:31"}
383
+ {"current_steps": 383, "total_steps": 519, "loss": 0.5428, "lr": 1.977361664477518e-06, "epoch": 2.213872832369942, "percentage": 73.8, "elapsed_time": "0:40:38", "remaining_time": "0:14:25"}
384
+ {"current_steps": 384, "total_steps": 519, "loss": 0.5739, "lr": 1.950636439799029e-06, "epoch": 2.2196531791907512, "percentage": 73.99, "elapsed_time": "0:40:44", "remaining_time": "0:14:19"}
385
+ {"current_steps": 385, "total_steps": 519, "loss": 0.4031, "lr": 1.924049213362153e-06, "epoch": 2.2254335260115607, "percentage": 74.18, "elapsed_time": "0:40:50", "remaining_time": "0:14:12"}
386
+ {"current_steps": 386, "total_steps": 519, "loss": 0.5596, "lr": 1.8976011883656632e-06, "epoch": 2.23121387283237, "percentage": 74.37, "elapsed_time": "0:40:55", "remaining_time": "0:14:05"}
387
+ {"current_steps": 387, "total_steps": 519, "loss": 0.5486, "lr": 1.8712935617088067e-06, "epoch": 2.2369942196531793, "percentage": 74.57, "elapsed_time": "0:41:02", "remaining_time": "0:13:59"}
388
+ {"current_steps": 388, "total_steps": 519, "loss": 0.6458, "lr": 1.8451275239371337e-06, "epoch": 2.2427745664739884, "percentage": 74.76, "elapsed_time": "0:41:10", "remaining_time": "0:13:54"}
389
+ {"current_steps": 389, "total_steps": 519, "loss": 0.4581, "lr": 1.8191042591886198e-06, "epoch": 2.2485549132947975, "percentage": 74.95, "elapsed_time": "0:41:16", "remaining_time": "0:13:47"}
390
+ {"current_steps": 390, "total_steps": 519, "loss": 0.6904, "lr": 1.7932249451400863e-06, "epoch": 2.254335260115607, "percentage": 75.14, "elapsed_time": "0:41:22", "remaining_time": "0:13:41"}
391
+ {"current_steps": 391, "total_steps": 519, "loss": 0.3941, "lr": 1.767490752953896e-06, "epoch": 2.260115606936416, "percentage": 75.34, "elapsed_time": "0:41:27", "remaining_time": "0:13:34"}
392
+ {"current_steps": 392, "total_steps": 519, "loss": 0.5507, "lr": 1.7419028472249566e-06, "epoch": 2.2658959537572256, "percentage": 75.53, "elapsed_time": "0:41:35", "remaining_time": "0:13:28"}
393
+ {"current_steps": 393, "total_steps": 519, "loss": 0.5287, "lr": 1.7164623859280144e-06, "epoch": 2.2716763005780347, "percentage": 75.72, "elapsed_time": "0:41:43", "remaining_time": "0:13:22"}
394
+ {"current_steps": 394, "total_steps": 519, "loss": 0.5368, "lr": 1.6911705203652506e-06, "epoch": 2.277456647398844, "percentage": 75.92, "elapsed_time": "0:41:48", "remaining_time": "0:13:15"}
395
+ {"current_steps": 395, "total_steps": 519, "loss": 0.4684, "lr": 1.6660283951141847e-06, "epoch": 2.2832369942196533, "percentage": 76.11, "elapsed_time": "0:41:55", "remaining_time": "0:13:09"}
396
+ {"current_steps": 396, "total_steps": 519, "loss": 0.5993, "lr": 1.641037147975872e-06, "epoch": 2.2890173410404624, "percentage": 76.3, "elapsed_time": "0:42:00", "remaining_time": "0:13:02"}
397
+ {"current_steps": 397, "total_steps": 519, "loss": 0.5794, "lr": 1.616197909923412e-06, "epoch": 2.294797687861272, "percentage": 76.49, "elapsed_time": "0:42:07", "remaining_time": "0:12:56"}
398
+ {"current_steps": 398, "total_steps": 519, "loss": 0.4806, "lr": 1.591511805050772e-06, "epoch": 2.300578034682081, "percentage": 76.69, "elapsed_time": "0:42:15", "remaining_time": "0:12:50"}
399
+ {"current_steps": 399, "total_steps": 519, "loss": 0.502, "lr": 1.5669799505219069e-06, "epoch": 2.30635838150289, "percentage": 76.88, "elapsed_time": "0:42:20", "remaining_time": "0:12:44"}
400
+ {"current_steps": 400, "total_steps": 519, "loss": 0.4041, "lr": 1.542603456520214e-06, "epoch": 2.3121387283236996, "percentage": 77.07, "elapsed_time": "0:42:25", "remaining_time": "0:12:37"}
401
+ {"current_steps": 401, "total_steps": 519, "loss": 0.5262, "lr": 1.5183834261982804e-06, "epoch": 2.3179190751445087, "percentage": 77.26, "elapsed_time": "0:42:32", "remaining_time": "0:12:31"}
402
+ {"current_steps": 402, "total_steps": 519, "loss": 0.5337, "lr": 1.4943209556279698e-06, "epoch": 2.3236994219653178, "percentage": 77.46, "elapsed_time": "0:42:39", "remaining_time": "0:12:25"}
403
+ {"current_steps": 403, "total_steps": 519, "loss": 0.5113, "lr": 1.4704171337508144e-06, "epoch": 2.3294797687861273, "percentage": 77.65, "elapsed_time": "0:42:48", "remaining_time": "0:12:19"}
404
+ {"current_steps": 404, "total_steps": 519, "loss": 0.5875, "lr": 1.4466730423287385e-06, "epoch": 2.3352601156069364, "percentage": 77.84, "elapsed_time": "0:42:56", "remaining_time": "0:12:13"}
405
+ {"current_steps": 405, "total_steps": 519, "loss": 0.396, "lr": 1.423089755895095e-06, "epoch": 2.3410404624277454, "percentage": 78.03, "elapsed_time": "0:42:59", "remaining_time": "0:12:06"}
406
+ {"current_steps": 406, "total_steps": 519, "loss": 0.4239, "lr": 1.399668341706053e-06, "epoch": 2.346820809248555, "percentage": 78.23, "elapsed_time": "0:43:04", "remaining_time": "0:11:59"}
407
+ {"current_steps": 407, "total_steps": 519, "loss": 0.5631, "lr": 1.3764098596922865e-06, "epoch": 2.352601156069364, "percentage": 78.42, "elapsed_time": "0:43:11", "remaining_time": "0:11:53"}
408
+ {"current_steps": 408, "total_steps": 519, "loss": 0.4963, "lr": 1.3533153624110097e-06, "epoch": 2.3583815028901736, "percentage": 78.61, "elapsed_time": "0:43:16", "remaining_time": "0:11:46"}
409
+ {"current_steps": 409, "total_steps": 519, "loss": 0.5263, "lr": 1.3303858949983495e-06, "epoch": 2.3641618497109826, "percentage": 78.81, "elapsed_time": "0:43:22", "remaining_time": "0:11:39"}
410
+ {"current_steps": 410, "total_steps": 519, "loss": 0.6329, "lr": 1.3076224951220413e-06, "epoch": 2.3699421965317917, "percentage": 79.0, "elapsed_time": "0:43:30", "remaining_time": "0:11:33"}
411
+ {"current_steps": 411, "total_steps": 519, "loss": 0.4078, "lr": 1.2850261929344748e-06, "epoch": 2.3757225433526012, "percentage": 79.19, "elapsed_time": "0:43:35", "remaining_time": "0:11:27"}
412
+ {"current_steps": 412, "total_steps": 519, "loss": 0.5412, "lr": 1.2625980110260711e-06, "epoch": 2.3815028901734103, "percentage": 79.38, "elapsed_time": "0:43:39", "remaining_time": "0:11:20"}
413
+ {"current_steps": 413, "total_steps": 519, "loss": 0.4662, "lr": 1.2403389643790086e-06, "epoch": 2.38728323699422, "percentage": 79.58, "elapsed_time": "0:43:48", "remaining_time": "0:11:14"}
414
+ {"current_steps": 414, "total_steps": 519, "loss": 0.4992, "lr": 1.2182500603212882e-06, "epoch": 2.393063583815029, "percentage": 79.77, "elapsed_time": "0:43:54", "remaining_time": "0:11:08"}
415
+ {"current_steps": 415, "total_steps": 519, "loss": 0.5274, "lr": 1.1963322984811454e-06, "epoch": 2.398843930635838, "percentage": 79.96, "elapsed_time": "0:43:59", "remaining_time": "0:11:01"}
416
+ {"current_steps": 416, "total_steps": 519, "loss": 0.643, "lr": 1.1745866707418146e-06, "epoch": 2.4046242774566475, "percentage": 80.15, "elapsed_time": "0:44:07", "remaining_time": "0:10:55"}
417
+ {"current_steps": 417, "total_steps": 519, "loss": 0.4825, "lr": 1.1530141611966438e-06, "epoch": 2.4104046242774566, "percentage": 80.35, "elapsed_time": "0:44:12", "remaining_time": "0:10:48"}
418
+ {"current_steps": 418, "total_steps": 519, "loss": 0.6665, "lr": 1.1316157461045553e-06, "epoch": 2.416184971098266, "percentage": 80.54, "elapsed_time": "0:44:19", "remaining_time": "0:10:42"}
419
+ {"current_steps": 419, "total_steps": 519, "loss": 0.6534, "lr": 1.1103923938458677e-06, "epoch": 2.421965317919075, "percentage": 80.73, "elapsed_time": "0:44:24", "remaining_time": "0:10:35"}
420
+ {"current_steps": 420, "total_steps": 519, "loss": 0.5104, "lr": 1.0893450648784736e-06, "epoch": 2.4277456647398843, "percentage": 80.92, "elapsed_time": "0:44:31", "remaining_time": "0:10:29"}
421
+ {"current_steps": 421, "total_steps": 519, "loss": 0.3761, "lr": 1.0684747116943683e-06, "epoch": 2.433526011560694, "percentage": 81.12, "elapsed_time": "0:44:36", "remaining_time": "0:10:23"}
422
+ {"current_steps": 422, "total_steps": 519, "loss": 0.4899, "lr": 1.04778227877655e-06, "epoch": 2.439306358381503, "percentage": 81.31, "elapsed_time": "0:44:42", "remaining_time": "0:10:16"}
423
+ {"current_steps": 423, "total_steps": 519, "loss": 0.6117, "lr": 1.0272687025562794e-06, "epoch": 2.445086705202312, "percentage": 81.5, "elapsed_time": "0:44:50", "remaining_time": "0:10:10"}
424
+ {"current_steps": 424, "total_steps": 519, "loss": 0.4986, "lr": 1.006934911370696e-06, "epoch": 2.4508670520231215, "percentage": 81.7, "elapsed_time": "0:44:54", "remaining_time": "0:10:03"}
425
+ {"current_steps": 425, "total_steps": 519, "loss": 0.5369, "lr": 9.867818254208122e-07, "epoch": 2.4566473988439306, "percentage": 81.89, "elapsed_time": "0:45:00", "remaining_time": "0:09:57"}
426
+ {"current_steps": 426, "total_steps": 519, "loss": 0.4081, "lr": 9.668103567298615e-07, "epoch": 2.4624277456647397, "percentage": 82.08, "elapsed_time": "0:45:04", "remaining_time": "0:09:50"}
427
+ {"current_steps": 427, "total_steps": 519, "loss": 0.4613, "lr": 9.470214091020358e-07, "epoch": 2.468208092485549, "percentage": 82.27, "elapsed_time": "0:45:11", "remaining_time": "0:09:44"}
428
+ {"current_steps": 428, "total_steps": 519, "loss": 0.6163, "lr": 9.274158780815767e-07, "epoch": 2.4739884393063583, "percentage": 82.47, "elapsed_time": "0:45:19", "remaining_time": "0:09:38"}
429
+ {"current_steps": 429, "total_steps": 519, "loss": 0.3661, "lr": 9.079946509122473e-07, "epoch": 2.479768786127168, "percentage": 82.66, "elapsed_time": "0:45:25", "remaining_time": "0:09:31"}
430
+ {"current_steps": 430, "total_steps": 519, "loss": 0.6345, "lr": 8.887586064971859e-07, "epoch": 2.485549132947977, "percentage": 82.85, "elapsed_time": "0:45:30", "remaining_time": "0:09:25"}
431
+ {"current_steps": 431, "total_steps": 519, "loss": 0.416, "lr": 8.697086153591289e-07, "epoch": 2.491329479768786, "percentage": 83.04, "elapsed_time": "0:45:35", "remaining_time": "0:09:18"}
432
+ {"current_steps": 432, "total_steps": 519, "loss": 0.4818, "lr": 8.508455396010096e-07, "epoch": 2.4971098265895955, "percentage": 83.24, "elapsed_time": "0:45:42", "remaining_time": "0:09:12"}
433
+ {"current_steps": 433, "total_steps": 519, "loss": 0.5282, "lr": 8.321702328669534e-07, "epoch": 2.5028901734104045, "percentage": 83.43, "elapsed_time": "0:45:50", "remaining_time": "0:09:06"}
434
+ {"current_steps": 434, "total_steps": 519, "loss": 0.4428, "lr": 8.136835403036413e-07, "epoch": 2.508670520231214, "percentage": 83.62, "elapsed_time": "0:45:54", "remaining_time": "0:08:59"}
435
+ {"current_steps": 435, "total_steps": 519, "loss": 0.5345, "lr": 7.95386298522065e-07, "epoch": 2.514450867052023, "percentage": 83.82, "elapsed_time": "0:45:59", "remaining_time": "0:08:52"}
436
+ {"current_steps": 436, "total_steps": 519, "loss": 0.4737, "lr": 7.772793355596597e-07, "epoch": 2.520231213872832, "percentage": 84.01, "elapsed_time": "0:46:05", "remaining_time": "0:08:46"}
437
+ {"current_steps": 437, "total_steps": 519, "loss": 0.5381, "lr": 7.593634708428438e-07, "epoch": 2.5260115606936417, "percentage": 84.2, "elapsed_time": "0:46:12", "remaining_time": "0:08:40"}
438
+ {"current_steps": 438, "total_steps": 519, "loss": 0.5094, "lr": 7.416395151499223e-07, "epoch": 2.531791907514451, "percentage": 84.39, "elapsed_time": "0:46:17", "remaining_time": "0:08:33"}
439
+ {"current_steps": 439, "total_steps": 519, "loss": 0.4759, "lr": 7.241082705744057e-07, "epoch": 2.5375722543352603, "percentage": 84.59, "elapsed_time": "0:46:23", "remaining_time": "0:08:27"}
440
+ {"current_steps": 440, "total_steps": 519, "loss": 0.5029, "lr": 7.067705304887074e-07, "epoch": 2.5433526011560694, "percentage": 84.78, "elapsed_time": "0:46:30", "remaining_time": "0:08:21"}
441
+ {"current_steps": 441, "total_steps": 519, "loss": 0.5204, "lr": 6.896270795082394e-07, "epoch": 2.5491329479768785, "percentage": 84.97, "elapsed_time": "0:46:35", "remaining_time": "0:08:14"}
442
+ {"current_steps": 442, "total_steps": 519, "loss": 0.3755, "lr": 6.726786934559048e-07, "epoch": 2.5549132947976876, "percentage": 85.16, "elapsed_time": "0:46:40", "remaining_time": "0:08:07"}
443
+ {"current_steps": 443, "total_steps": 519, "loss": 0.5367, "lr": 6.559261393269872e-07, "epoch": 2.560693641618497, "percentage": 85.36, "elapsed_time": "0:46:47", "remaining_time": "0:08:01"}
444
+ {"current_steps": 444, "total_steps": 519, "loss": 0.3622, "lr": 6.39370175254444e-07, "epoch": 2.5664739884393066, "percentage": 85.55, "elapsed_time": "0:46:50", "remaining_time": "0:07:54"}
445
+ {"current_steps": 445, "total_steps": 519, "loss": 0.3243, "lr": 6.230115504745954e-07, "epoch": 2.5722543352601157, "percentage": 85.74, "elapsed_time": "0:46:57", "remaining_time": "0:07:48"}
446
+ {"current_steps": 446, "total_steps": 519, "loss": 0.5981, "lr": 6.06851005293217e-07, "epoch": 2.578034682080925, "percentage": 85.93, "elapsed_time": "0:47:06", "remaining_time": "0:07:42"}
447
+ {"current_steps": 447, "total_steps": 519, "loss": 0.4066, "lr": 5.908892710520375e-07, "epoch": 2.583815028901734, "percentage": 86.13, "elapsed_time": "0:47:11", "remaining_time": "0:07:36"}
448
+ {"current_steps": 448, "total_steps": 519, "loss": 0.4559, "lr": 5.75127070095643e-07, "epoch": 2.5895953757225434, "percentage": 86.32, "elapsed_time": "0:47:17", "remaining_time": "0:07:29"}
449
+ {"current_steps": 449, "total_steps": 519, "loss": 0.4375, "lr": 5.595651157387855e-07, "epoch": 2.5953757225433525, "percentage": 86.51, "elapsed_time": "0:47:23", "remaining_time": "0:07:23"}
450
+ {"current_steps": 450, "total_steps": 519, "loss": 0.5388, "lr": 5.442041122341057e-07, "epoch": 2.601156069364162, "percentage": 86.71, "elapsed_time": "0:47:29", "remaining_time": "0:07:16"}
451
+ {"current_steps": 451, "total_steps": 519, "loss": 0.7152, "lr": 5.290447547402594e-07, "epoch": 2.606936416184971, "percentage": 86.9, "elapsed_time": "0:47:36", "remaining_time": "0:07:10"}
452
+ {"current_steps": 452, "total_steps": 519, "loss": 0.5358, "lr": 5.14087729290459e-07, "epoch": 2.61271676300578, "percentage": 87.09, "elapsed_time": "0:47:44", "remaining_time": "0:07:04"}
453
+ {"current_steps": 453, "total_steps": 519, "loss": 0.4932, "lr": 4.993337127614273e-07, "epoch": 2.6184971098265897, "percentage": 87.28, "elapsed_time": "0:47:51", "remaining_time": "0:06:58"}
454
+ {"current_steps": 454, "total_steps": 519, "loss": 0.6222, "lr": 4.847833728427636e-07, "epoch": 2.6242774566473988, "percentage": 87.48, "elapsed_time": "0:48:00", "remaining_time": "0:06:52"}
455
+ {"current_steps": 455, "total_steps": 519, "loss": 0.3938, "lr": 4.7043736800673254e-07, "epoch": 2.6300578034682083, "percentage": 87.67, "elapsed_time": "0:48:04", "remaining_time": "0:06:45"}
456
+ {"current_steps": 456, "total_steps": 519, "loss": 0.4261, "lr": 4.5629634747845764e-07, "epoch": 2.6358381502890174, "percentage": 87.86, "elapsed_time": "0:48:11", "remaining_time": "0:06:39"}
457
+ {"current_steps": 457, "total_steps": 519, "loss": 0.6234, "lr": 4.423609512065485e-07, "epoch": 2.6416184971098264, "percentage": 88.05, "elapsed_time": "0:48:18", "remaining_time": "0:06:33"}
458
+ {"current_steps": 458, "total_steps": 519, "loss": 0.6352, "lr": 4.2863180983413744e-07, "epoch": 2.647398843930636, "percentage": 88.25, "elapsed_time": "0:48:24", "remaining_time": "0:06:26"}
459
+ {"current_steps": 459, "total_steps": 519, "loss": 0.5297, "lr": 4.1510954467033457e-07, "epoch": 2.653179190751445, "percentage": 88.44, "elapsed_time": "0:48:30", "remaining_time": "0:06:20"}
460
+ {"current_steps": 460, "total_steps": 519, "loss": 0.5252, "lr": 4.0179476766211865e-07, "epoch": 2.6589595375722546, "percentage": 88.63, "elapsed_time": "0:48:38", "remaining_time": "0:06:14"}
461
+ {"current_steps": 461, "total_steps": 519, "loss": 0.5306, "lr": 3.8868808136663995e-07, "epoch": 2.6647398843930636, "percentage": 88.82, "elapsed_time": "0:48:45", "remaining_time": "0:06:08"}
462
+ {"current_steps": 462, "total_steps": 519, "loss": 0.5379, "lr": 3.757900789239516e-07, "epoch": 2.6705202312138727, "percentage": 89.02, "elapsed_time": "0:48:55", "remaining_time": "0:06:02"}
463
+ {"current_steps": 463, "total_steps": 519, "loss": 0.4335, "lr": 3.631013440301645e-07, "epoch": 2.6763005780346822, "percentage": 89.21, "elapsed_time": "0:48:59", "remaining_time": "0:05:55"}
464
+ {"current_steps": 464, "total_steps": 519, "loss": 0.5133, "lr": 3.50622450911039e-07, "epoch": 2.6820809248554913, "percentage": 89.4, "elapsed_time": "0:49:04", "remaining_time": "0:05:49"}
465
+ {"current_steps": 465, "total_steps": 519, "loss": 0.5014, "lr": 3.383539642959915e-07, "epoch": 2.687861271676301, "percentage": 89.6, "elapsed_time": "0:49:10", "remaining_time": "0:05:42"}
466
+ {"current_steps": 466, "total_steps": 519, "loss": 0.4342, "lr": 3.262964393925433e-07, "epoch": 2.69364161849711, "percentage": 89.79, "elapsed_time": "0:49:14", "remaining_time": "0:05:35"}
467
+ {"current_steps": 467, "total_steps": 519, "loss": 0.4172, "lr": 3.144504218611899e-07, "epoch": 2.699421965317919, "percentage": 89.98, "elapsed_time": "0:49:19", "remaining_time": "0:05:29"}
468
+ {"current_steps": 468, "total_steps": 519, "loss": 0.5408, "lr": 3.028164477907125e-07, "epoch": 2.705202312138728, "percentage": 90.17, "elapsed_time": "0:49:25", "remaining_time": "0:05:23"}
469
+ {"current_steps": 469, "total_steps": 519, "loss": 0.5264, "lr": 2.913950436739116e-07, "epoch": 2.7109826589595376, "percentage": 90.37, "elapsed_time": "0:49:34", "remaining_time": "0:05:17"}
470
+ {"current_steps": 470, "total_steps": 519, "loss": 0.5537, "lr": 2.8018672638378486e-07, "epoch": 2.7167630057803467, "percentage": 90.56, "elapsed_time": "0:49:38", "remaining_time": "0:05:10"}
471
+ {"current_steps": 471, "total_steps": 519, "loss": 0.598, "lr": 2.6919200315013606e-07, "epoch": 2.722543352601156, "percentage": 90.75, "elapsed_time": "0:49:44", "remaining_time": "0:05:04"}
472
+ {"current_steps": 472, "total_steps": 519, "loss": 0.3216, "lr": 2.5841137153661765e-07, "epoch": 2.7283236994219653, "percentage": 90.94, "elapsed_time": "0:49:49", "remaining_time": "0:04:57"}
473
+ {"current_steps": 473, "total_steps": 519, "loss": 0.5108, "lr": 2.4784531941821675e-07, "epoch": 2.7341040462427744, "percentage": 91.14, "elapsed_time": "0:49:55", "remaining_time": "0:04:51"}
474
+ {"current_steps": 474, "total_steps": 519, "loss": 0.4978, "lr": 2.3749432495917546e-07, "epoch": 2.739884393063584, "percentage": 91.33, "elapsed_time": "0:50:01", "remaining_time": "0:04:44"}
475
+ {"current_steps": 475, "total_steps": 519, "loss": 0.4321, "lr": 2.2735885659134927e-07, "epoch": 2.745664739884393, "percentage": 91.52, "elapsed_time": "0:50:06", "remaining_time": "0:04:38"}
476
+ {"current_steps": 476, "total_steps": 519, "loss": 0.5351, "lr": 2.1743937299301242e-07, "epoch": 2.7514450867052025, "percentage": 91.71, "elapsed_time": "0:50:13", "remaining_time": "0:04:32"}
477
+ {"current_steps": 477, "total_steps": 519, "loss": 0.519, "lr": 2.0773632306809622e-07, "epoch": 2.7572254335260116, "percentage": 91.91, "elapsed_time": "0:50:19", "remaining_time": "0:04:25"}
478
+ {"current_steps": 478, "total_steps": 519, "loss": 0.4933, "lr": 1.9825014592587844e-07, "epoch": 2.7630057803468207, "percentage": 92.1, "elapsed_time": "0:50:24", "remaining_time": "0:04:19"}
479
+ {"current_steps": 479, "total_steps": 519, "loss": 0.4666, "lr": 1.889812708611083e-07, "epoch": 2.76878612716763, "percentage": 92.29, "elapsed_time": "0:50:28", "remaining_time": "0:04:12"}
480
+ {"current_steps": 480, "total_steps": 519, "loss": 0.5676, "lr": 1.7993011733458077e-07, "epoch": 2.7745664739884393, "percentage": 92.49, "elapsed_time": "0:50:34", "remaining_time": "0:04:06"}
481
+ {"current_steps": 481, "total_steps": 519, "loss": 0.5911, "lr": 1.7109709495415073e-07, "epoch": 2.7803468208092488, "percentage": 92.68, "elapsed_time": "0:50:41", "remaining_time": "0:04:00"}
482
+ {"current_steps": 482, "total_steps": 519, "loss": 0.4786, "lr": 1.624826034562016e-07, "epoch": 2.786127167630058, "percentage": 92.87, "elapsed_time": "0:50:46", "remaining_time": "0:03:53"}
483
+ {"current_steps": 483, "total_steps": 519, "loss": 0.4978, "lr": 1.5408703268754988e-07, "epoch": 2.791907514450867, "percentage": 93.06, "elapsed_time": "0:50:53", "remaining_time": "0:03:47"}
484
+ {"current_steps": 484, "total_steps": 519, "loss": 0.7086, "lr": 1.459107625878059e-07, "epoch": 2.7976878612716765, "percentage": 93.26, "elapsed_time": "0:51:01", "remaining_time": "0:03:41"}
485
+ {"current_steps": 485, "total_steps": 519, "loss": 0.441, "lr": 1.3795416317218036e-07, "epoch": 2.8034682080924855, "percentage": 93.45, "elapsed_time": "0:51:05", "remaining_time": "0:03:34"}
486
+ {"current_steps": 486, "total_steps": 519, "loss": 0.4577, "lr": 1.3021759451473548e-07, "epoch": 2.809248554913295, "percentage": 93.64, "elapsed_time": "0:51:11", "remaining_time": "0:03:28"}
487
+ {"current_steps": 487, "total_steps": 519, "loss": 0.4894, "lr": 1.2270140673209473e-07, "epoch": 2.815028901734104, "percentage": 93.83, "elapsed_time": "0:51:15", "remaining_time": "0:03:22"}
488
+ {"current_steps": 488, "total_steps": 519, "loss": 0.4831, "lr": 1.1540593996759441e-07, "epoch": 2.820809248554913, "percentage": 94.03, "elapsed_time": "0:51:21", "remaining_time": "0:03:15"}
489
+ {"current_steps": 489, "total_steps": 519, "loss": 0.4427, "lr": 1.0833152437589423e-07, "epoch": 2.8265895953757223, "percentage": 94.22, "elapsed_time": "0:51:27", "remaining_time": "0:03:09"}
490
+ {"current_steps": 490, "total_steps": 519, "loss": 0.6623, "lr": 1.0147848010803319e-07, "epoch": 2.832369942196532, "percentage": 94.41, "elapsed_time": "0:51:33", "remaining_time": "0:03:03"}
491
+ {"current_steps": 491, "total_steps": 519, "loss": 0.349, "lr": 9.484711729694229e-08, "epoch": 2.838150289017341, "percentage": 94.61, "elapsed_time": "0:51:36", "remaining_time": "0:02:56"}
492
+ {"current_steps": 492, "total_steps": 519, "loss": 0.3654, "lr": 8.8437736043408e-08, "epoch": 2.8439306358381504, "percentage": 94.8, "elapsed_time": "0:51:42", "remaining_time": "0:02:50"}
493
+ {"current_steps": 493, "total_steps": 519, "loss": 0.5365, "lr": 8.225062640249636e-08, "epoch": 2.8497109826589595, "percentage": 94.99, "elapsed_time": "0:51:49", "remaining_time": "0:02:43"}
494
+ {"current_steps": 494, "total_steps": 519, "loss": 0.5066, "lr": 7.628606837041974e-08, "epoch": 2.8554913294797686, "percentage": 95.18, "elapsed_time": "0:51:54", "remaining_time": "0:02:37"}
495
+ {"current_steps": 495, "total_steps": 519, "loss": 0.5115, "lr": 7.05443318718707e-08, "epoch": 2.861271676300578, "percentage": 95.38, "elapsed_time": "0:52:00", "remaining_time": "0:02:31"}
496
+ {"current_steps": 496, "total_steps": 519, "loss": 0.4359, "lr": 6.502567674780524e-08, "epoch": 2.867052023121387, "percentage": 95.57, "elapsed_time": "0:52:07", "remaining_time": "0:02:25"}
497
+ {"current_steps": 497, "total_steps": 519, "loss": 0.5456, "lr": 5.973035274368266e-08, "epoch": 2.8728323699421967, "percentage": 95.76, "elapsed_time": "0:52:13", "remaining_time": "0:02:18"}
498
+ {"current_steps": 498, "total_steps": 519, "loss": 0.4307, "lr": 5.465859949816299e-08, "epoch": 2.878612716763006, "percentage": 95.95, "elapsed_time": "0:52:18", "remaining_time": "0:02:12"}
499
+ {"current_steps": 499, "total_steps": 519, "loss": 0.4317, "lr": 4.981064653226564e-08, "epoch": 2.884393063583815, "percentage": 96.15, "elapsed_time": "0:52:26", "remaining_time": "0:02:06"}
500
+ {"current_steps": 500, "total_steps": 519, "loss": 0.4231, "lr": 4.5186713238979385e-08, "epoch": 2.8901734104046244, "percentage": 96.34, "elapsed_time": "0:52:32", "remaining_time": "0:01:59"}
501
+ {"current_steps": 501, "total_steps": 519, "loss": 0.4358, "lr": 4.078700887333365e-08, "epoch": 2.8959537572254335, "percentage": 96.53, "elapsed_time": "0:52:36", "remaining_time": "0:01:53"}
502
+ {"current_steps": 502, "total_steps": 519, "loss": 0.4707, "lr": 3.6611732542931044e-08, "epoch": 2.901734104046243, "percentage": 96.72, "elapsed_time": "0:52:40", "remaining_time": "0:01:47"}
503
+ {"current_steps": 503, "total_steps": 519, "loss": 0.58, "lr": 3.266107319893463e-08, "epoch": 2.907514450867052, "percentage": 96.92, "elapsed_time": "0:52:46", "remaining_time": "0:01:40"}
504
+ {"current_steps": 504, "total_steps": 519, "loss": 0.4633, "lr": 2.89352096275175e-08, "epoch": 2.913294797687861, "percentage": 97.11, "elapsed_time": "0:52:52", "remaining_time": "0:01:34"}
505
+ {"current_steps": 505, "total_steps": 519, "loss": 0.4791, "lr": 2.5434310441773135e-08, "epoch": 2.9190751445086707, "percentage": 97.3, "elapsed_time": "0:52:59", "remaining_time": "0:01:28"}
506
+ {"current_steps": 506, "total_steps": 519, "loss": 0.5138, "lr": 2.2158534074083193e-08, "epoch": 2.9248554913294798, "percentage": 97.5, "elapsed_time": "0:53:06", "remaining_time": "0:01:21"}
507
+ {"current_steps": 507, "total_steps": 519, "loss": 0.4747, "lr": 1.910802876894824e-08, "epoch": 2.9306358381502893, "percentage": 97.69, "elapsed_time": "0:53:13", "remaining_time": "0:01:15"}
508
+ {"current_steps": 508, "total_steps": 519, "loss": 0.5382, "lr": 1.6282932576279775e-08, "epoch": 2.9364161849710984, "percentage": 97.88, "elapsed_time": "0:53:18", "remaining_time": "0:01:09"}
509
+ {"current_steps": 509, "total_steps": 519, "loss": 0.4795, "lr": 1.3683373345150796e-08, "epoch": 2.9421965317919074, "percentage": 98.07, "elapsed_time": "0:53:26", "remaining_time": "0:01:02"}
510
+ {"current_steps": 510, "total_steps": 519, "loss": 0.3789, "lr": 1.1309468718013194e-08, "epoch": 2.9479768786127165, "percentage": 98.27, "elapsed_time": "0:53:30", "remaining_time": "0:00:56"}
511
+ {"current_steps": 511, "total_steps": 519, "loss": 0.5196, "lr": 9.16132612537035e-09, "epoch": 2.953757225433526, "percentage": 98.46, "elapsed_time": "0:53:38", "remaining_time": "0:00:50"}
512
+ {"current_steps": 512, "total_steps": 519, "loss": 0.5751, "lr": 7.2390427809176934e-09, "epoch": 2.959537572254335, "percentage": 98.65, "elapsed_time": "0:53:42", "remaining_time": "0:00:44"}
513
+ {"current_steps": 513, "total_steps": 519, "loss": 0.7386, "lr": 5.542705677143434e-09, "epoch": 2.9653179190751446, "percentage": 98.84, "elapsed_time": "0:53:51", "remaining_time": "0:00:37"}
514
+ {"current_steps": 514, "total_steps": 519, "loss": 0.4838, "lr": 4.072391581388946e-09, "epoch": 2.9710982658959537, "percentage": 99.04, "elapsed_time": "0:53:57", "remaining_time": "0:00:31"}
515
+ {"current_steps": 515, "total_steps": 519, "loss": 0.442, "lr": 2.8281670323798693e-09, "epoch": 2.976878612716763, "percentage": 99.23, "elapsed_time": "0:54:03", "remaining_time": "0:00:25"}
516
+ {"current_steps": 516, "total_steps": 519, "loss": 0.4679, "lr": 1.8100883372085266e-09, "epoch": 2.9826589595375723, "percentage": 99.42, "elapsed_time": "0:54:09", "remaining_time": "0:00:18"}
517
+ {"current_steps": 517, "total_steps": 519, "loss": 0.5389, "lr": 1.0182015687909552e-09, "epoch": 2.9884393063583814, "percentage": 99.61, "elapsed_time": "0:54:16", "remaining_time": "0:00:12"}
518
+ {"current_steps": 518, "total_steps": 519, "loss": 0.5033, "lr": 4.5254256377913474e-10, "epoch": 2.994219653179191, "percentage": 99.81, "elapsed_time": "0:54:20", "remaining_time": "0:00:06"}
519
+ {"current_steps": 519, "total_steps": 519, "loss": 0.4207, "lr": 1.1313692094117034e-10, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:54:28", "remaining_time": "0:00:00"}
520
+ {"current_steps": 519, "total_steps": 519, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:56:01", "remaining_time": "0:00:00"}