gsmyrnis commited on
Commit
0760072
·
verified ·
1 Parent(s): db79085

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d4930ec50561eab573ace0abd13b467d2be53a9291fb23c13be2e3479767c73
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea73a36efb9f18c9cdf9968d6e106bda9dea30a2ab316e54d5b6fc5c49f5e108
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f2054433a402ed5b5dbc74c0daf928ca33ece3a2706b50714f4794e8045028e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005b21f65962f7783667543afb667ceab9acb1ed1778dcc0f03d48757fd9bfcb
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0060d4870bfb3cd4ae52f6b68983bab9d0d54a3becdecf623376355a39fd2c95
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7b5600f295d324b27a63856d105e5ac562d130b9b7e3413ebc826979245c8c
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c12cbee74a4682ce8bbc14866c321bf2300a53c823002843a31e6eea00645ef
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a5ee1e67cd2448863420d341de64ad9d6334a9d4c96fd95b159931212d26cb4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -370,3 +370,174 @@
370
  {"current_steps": 3700, "total_steps": 5424, "loss": 0.3941, "lr": 2.775037089864054e-06, "epoch": 2.046082949308756, "percentage": 68.22, "elapsed_time": "17:17:36", "remaining_time": "8:03:27"}
371
  {"current_steps": 3710, "total_steps": 5424, "loss": 0.3981, "lr": 2.7462634220628146e-06, "epoch": 2.0516129032258066, "percentage": 68.4, "elapsed_time": "17:20:31", "remaining_time": "8:00:43"}
372
  {"current_steps": 3720, "total_steps": 5424, "loss": 0.4004, "lr": 2.7175831191933275e-06, "epoch": 2.057142857142857, "percentage": 68.58, "elapsed_time": "17:23:20", "remaining_time": "7:57:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
370
  {"current_steps": 3700, "total_steps": 5424, "loss": 0.3941, "lr": 2.775037089864054e-06, "epoch": 2.046082949308756, "percentage": 68.22, "elapsed_time": "17:17:36", "remaining_time": "8:03:27"}
371
  {"current_steps": 3710, "total_steps": 5424, "loss": 0.3981, "lr": 2.7462634220628146e-06, "epoch": 2.0516129032258066, "percentage": 68.4, "elapsed_time": "17:20:31", "remaining_time": "8:00:43"}
372
  {"current_steps": 3720, "total_steps": 5424, "loss": 0.4004, "lr": 2.7175831191933275e-06, "epoch": 2.057142857142857, "percentage": 68.58, "elapsed_time": "17:23:20", "remaining_time": "7:57:55"}
373
+ {"current_steps": 3730, "total_steps": 5424, "loss": 0.3934, "lr": 2.688997369386698e-06, "epoch": 2.0626728110599077, "percentage": 68.77, "elapsed_time": "17:26:07", "remaining_time": "7:55:06"}
374
+ {"current_steps": 3740, "total_steps": 5424, "loss": 0.394, "lr": 2.6605073568569993e-06, "epoch": 2.0682027649769585, "percentage": 68.95, "elapsed_time": "17:28:56", "remaining_time": "7:52:18"}
375
+ {"current_steps": 3750, "total_steps": 5424, "loss": 0.3989, "lr": 2.6321142618522288e-06, "epoch": 2.0737327188940093, "percentage": 69.14, "elapsed_time": "17:31:48", "remaining_time": "7:49:31"}
376
+ {"current_steps": 3760, "total_steps": 5424, "loss": 0.4019, "lr": 2.603819260605399e-06, "epoch": 2.0792626728110597, "percentage": 69.32, "elapsed_time": "17:34:32", "remaining_time": "7:46:41"}
377
+ {"current_steps": 3770, "total_steps": 5424, "loss": 0.4003, "lr": 2.5756235252858288e-06, "epoch": 2.0847926267281105, "percentage": 69.51, "elapsed_time": "17:37:20", "remaining_time": "7:43:53"}
378
+ {"current_steps": 3780, "total_steps": 5424, "loss": 0.4018, "lr": 2.5475282239505685e-06, "epoch": 2.0903225806451613, "percentage": 69.69, "elapsed_time": "17:40:08", "remaining_time": "7:41:04"}
379
+ {"current_steps": 3790, "total_steps": 5424, "loss": 0.4008, "lr": 2.5195345204960196e-06, "epoch": 2.095852534562212, "percentage": 69.87, "elapsed_time": "17:43:01", "remaining_time": "7:38:18"}
380
+ {"current_steps": 3800, "total_steps": 5424, "loss": 0.3876, "lr": 2.4916435746097166e-06, "epoch": 2.1013824884792625, "percentage": 70.06, "elapsed_time": "17:45:48", "remaining_time": "7:35:29"}
381
+ {"current_steps": 3810, "total_steps": 5424, "loss": 0.3982, "lr": 2.4638565417222816e-06, "epoch": 2.1069124423963133, "percentage": 70.24, "elapsed_time": "17:48:32", "remaining_time": "7:32:39"}
382
+ {"current_steps": 3820, "total_steps": 5424, "loss": 0.4073, "lr": 2.436174572959561e-06, "epoch": 2.112442396313364, "percentage": 70.43, "elapsed_time": "17:51:23", "remaining_time": "7:29:52"}
383
+ {"current_steps": 3830, "total_steps": 5424, "loss": 0.399, "lr": 2.408598815094944e-06, "epoch": 2.117972350230415, "percentage": 70.61, "elapsed_time": "17:54:09", "remaining_time": "7:27:03"}
384
+ {"current_steps": 3840, "total_steps": 5424, "loss": 0.4009, "lr": 2.381130410501845e-06, "epoch": 2.1235023041474657, "percentage": 70.8, "elapsed_time": "17:56:58", "remaining_time": "7:24:15"}
385
+ {"current_steps": 3850, "total_steps": 5424, "loss": 0.3967, "lr": 2.353770497106381e-06, "epoch": 2.129032258064516, "percentage": 70.98, "elapsed_time": "17:59:49", "remaining_time": "7:21:28"}
386
+ {"current_steps": 3860, "total_steps": 5424, "loss": 0.4001, "lr": 2.3265202083402376e-06, "epoch": 2.134562211981567, "percentage": 71.17, "elapsed_time": "18:02:41", "remaining_time": "7:18:41"}
387
+ {"current_steps": 3870, "total_steps": 5424, "loss": 0.4033, "lr": 2.299380673093712e-06, "epoch": 2.1400921658986176, "percentage": 71.35, "elapsed_time": "18:05:33", "remaining_time": "7:15:54"}
388
+ {"current_steps": 3880, "total_steps": 5424, "loss": 0.3994, "lr": 2.272353015668942e-06, "epoch": 2.145622119815668, "percentage": 71.53, "elapsed_time": "18:08:22", "remaining_time": "7:13:06"}
389
+ {"current_steps": 3890, "total_steps": 5424, "loss": 0.4014, "lr": 2.2454383557333358e-06, "epoch": 2.1511520737327188, "percentage": 71.72, "elapsed_time": "18:11:11", "remaining_time": "7:10:18"}
390
+ {"current_steps": 3900, "total_steps": 5424, "loss": 0.3998, "lr": 2.218637808273184e-06, "epoch": 2.1566820276497696, "percentage": 71.9, "elapsed_time": "18:13:57", "remaining_time": "7:07:29"}
391
+ {"current_steps": 3910, "total_steps": 5424, "loss": 0.405, "lr": 2.1919524835474713e-06, "epoch": 2.1622119815668204, "percentage": 72.09, "elapsed_time": "18:16:48", "remaining_time": "7:04:41"}
392
+ {"current_steps": 3920, "total_steps": 5424, "loss": 0.3896, "lr": 2.1653834870418807e-06, "epoch": 2.167741935483871, "percentage": 72.27, "elapsed_time": "18:19:38", "remaining_time": "7:01:54"}
393
+ {"current_steps": 3930, "total_steps": 5424, "loss": 0.4003, "lr": 2.1389319194230017e-06, "epoch": 2.1732718894009215, "percentage": 72.46, "elapsed_time": "18:22:26", "remaining_time": "6:59:05"}
394
+ {"current_steps": 3940, "total_steps": 5424, "loss": 0.4013, "lr": 2.1125988764927225e-06, "epoch": 2.1788018433179723, "percentage": 72.64, "elapsed_time": "18:25:18", "remaining_time": "6:56:18"}
395
+ {"current_steps": 3950, "total_steps": 5424, "loss": 0.3989, "lr": 2.0863854491428454e-06, "epoch": 2.184331797235023, "percentage": 72.82, "elapsed_time": "18:28:08", "remaining_time": "6:53:31"}
396
+ {"current_steps": 3960, "total_steps": 5424, "loss": 0.3921, "lr": 2.0602927233098908e-06, "epoch": 2.189861751152074, "percentage": 73.01, "elapsed_time": "18:30:56", "remaining_time": "6:50:42"}
397
+ {"current_steps": 3970, "total_steps": 5424, "loss": 0.4001, "lr": 2.034321779930109e-06, "epoch": 2.1953917050691243, "percentage": 73.19, "elapsed_time": "18:33:44", "remaining_time": "6:47:54"}
398
+ {"current_steps": 3980, "total_steps": 5424, "loss": 0.4049, "lr": 2.0084736948947027e-06, "epoch": 2.200921658986175, "percentage": 73.38, "elapsed_time": "18:36:28", "remaining_time": "6:45:04"}
399
+ {"current_steps": 3990, "total_steps": 5424, "loss": 0.4041, "lr": 1.982749539005254e-06, "epoch": 2.206451612903226, "percentage": 73.56, "elapsed_time": "18:39:20", "remaining_time": "6:42:17"}
400
+ {"current_steps": 4000, "total_steps": 5424, "loss": 0.3978, "lr": 1.9571503779293683e-06, "epoch": 2.2119815668202767, "percentage": 73.75, "elapsed_time": "18:42:01", "remaining_time": "6:39:26"}
401
+ {"current_steps": 4010, "total_steps": 5424, "loss": 0.406, "lr": 1.93167727215652e-06, "epoch": 2.217511520737327, "percentage": 73.93, "elapsed_time": "18:44:47", "remaining_time": "6:36:37"}
402
+ {"current_steps": 4020, "total_steps": 5424, "loss": 0.3956, "lr": 1.9063312769541348e-06, "epoch": 2.223041474654378, "percentage": 74.12, "elapsed_time": "18:47:30", "remaining_time": "6:33:47"}
403
+ {"current_steps": 4030, "total_steps": 5424, "loss": 0.3966, "lr": 1.8811134423238513e-06, "epoch": 2.2285714285714286, "percentage": 74.3, "elapsed_time": "18:50:11", "remaining_time": "6:30:56"}
404
+ {"current_steps": 4040, "total_steps": 5424, "loss": 0.4043, "lr": 1.8560248129580422e-06, "epoch": 2.2341013824884794, "percentage": 74.48, "elapsed_time": "18:53:00", "remaining_time": "6:28:08"}
405
+ {"current_steps": 4050, "total_steps": 5424, "loss": 0.4076, "lr": 1.8310664281965268e-06, "epoch": 2.23963133640553, "percentage": 74.67, "elapsed_time": "18:55:49", "remaining_time": "6:25:20"}
406
+ {"current_steps": 4060, "total_steps": 5424, "loss": 0.3972, "lr": 1.8062393219835173e-06, "epoch": 2.2451612903225806, "percentage": 74.85, "elapsed_time": "18:58:38", "remaining_time": "6:22:32"}
407
+ {"current_steps": 4070, "total_steps": 5424, "loss": 0.3945, "lr": 1.7815445228247851e-06, "epoch": 2.2506912442396314, "percentage": 75.04, "elapsed_time": "19:01:33", "remaining_time": "6:19:46"}
408
+ {"current_steps": 4080, "total_steps": 5424, "loss": 0.4033, "lr": 1.7569830537450533e-06, "epoch": 2.256221198156682, "percentage": 75.22, "elapsed_time": "19:04:26", "remaining_time": "6:16:59"}
409
+ {"current_steps": 4090, "total_steps": 5424, "loss": 0.3955, "lr": 1.732555932245616e-06, "epoch": 2.2617511520737326, "percentage": 75.41, "elapsed_time": "19:07:16", "remaining_time": "6:14:11"}
410
+ {"current_steps": 4100, "total_steps": 5424, "loss": 0.3953, "lr": 1.7082641702621856e-06, "epoch": 2.2672811059907834, "percentage": 75.59, "elapsed_time": "19:10:04", "remaining_time": "6:11:23"}
411
+ {"current_steps": 4110, "total_steps": 5424, "loss": 0.4021, "lr": 1.6841087741229745e-06, "epoch": 2.272811059907834, "percentage": 75.77, "elapsed_time": "19:12:46", "remaining_time": "6:08:33"}
412
+ {"current_steps": 4120, "total_steps": 5424, "loss": 0.4013, "lr": 1.660090744507003e-06, "epoch": 2.278341013824885, "percentage": 75.96, "elapsed_time": "19:15:29", "remaining_time": "6:05:43"}
413
+ {"current_steps": 4130, "total_steps": 5424, "loss": 0.4112, "lr": 1.6362110764026473e-06, "epoch": 2.2838709677419353, "percentage": 76.14, "elapsed_time": "19:18:17", "remaining_time": "6:02:54"}
414
+ {"current_steps": 4140, "total_steps": 5424, "loss": 0.3993, "lr": 1.6124707590664168e-06, "epoch": 2.289400921658986, "percentage": 76.33, "elapsed_time": "19:21:07", "remaining_time": "6:00:06"}
415
+ {"current_steps": 4150, "total_steps": 5424, "loss": 0.4078, "lr": 1.5888707759819766e-06, "epoch": 2.294930875576037, "percentage": 76.51, "elapsed_time": "19:23:58", "remaining_time": "5:57:19"}
416
+ {"current_steps": 4160, "total_steps": 5424, "loss": 0.3966, "lr": 1.5654121048194016e-06, "epoch": 2.3004608294930877, "percentage": 76.7, "elapsed_time": "19:26:45", "remaining_time": "5:54:31"}
417
+ {"current_steps": 4170, "total_steps": 5424, "loss": 0.3931, "lr": 1.5420957173946772e-06, "epoch": 2.305990783410138, "percentage": 76.88, "elapsed_time": "19:29:28", "remaining_time": "5:51:41"}
418
+ {"current_steps": 4180, "total_steps": 5424, "loss": 0.3963, "lr": 1.5189225796294383e-06, "epoch": 2.311520737327189, "percentage": 77.06, "elapsed_time": "19:32:09", "remaining_time": "5:48:50"}
419
+ {"current_steps": 4190, "total_steps": 5424, "loss": 0.3937, "lr": 1.4958936515109551e-06, "epoch": 2.3170506912442397, "percentage": 77.25, "elapsed_time": "19:34:56", "remaining_time": "5:46:02"}
420
+ {"current_steps": 4200, "total_steps": 5424, "loss": 0.4004, "lr": 1.4730098870523652e-06, "epoch": 2.3225806451612905, "percentage": 77.43, "elapsed_time": "19:37:48", "remaining_time": "5:43:14"}
421
+ {"current_steps": 4210, "total_steps": 5424, "loss": 0.4014, "lr": 1.450272234253149e-06, "epoch": 2.328110599078341, "percentage": 77.62, "elapsed_time": "19:40:36", "remaining_time": "5:40:26"}
422
+ {"current_steps": 4220, "total_steps": 5424, "loss": 0.399, "lr": 1.427681635059861e-06, "epoch": 2.3336405529953916, "percentage": 77.8, "elapsed_time": "19:43:26", "remaining_time": "5:37:38"}
423
+ {"current_steps": 4230, "total_steps": 5424, "loss": 0.3967, "lr": 1.4052390253271037e-06, "epoch": 2.3391705069124424, "percentage": 77.99, "elapsed_time": "19:46:15", "remaining_time": "5:34:50"}
424
+ {"current_steps": 4240, "total_steps": 5424, "loss": 0.4053, "lr": 1.3829453347787626e-06, "epoch": 2.3447004608294932, "percentage": 78.17, "elapsed_time": "19:49:05", "remaining_time": "5:32:03"}
425
+ {"current_steps": 4250, "total_steps": 5424, "loss": 0.3965, "lr": 1.3608014869694869e-06, "epoch": 2.3502304147465436, "percentage": 78.36, "elapsed_time": "19:51:57", "remaining_time": "5:29:15"}
426
+ {"current_steps": 4260, "total_steps": 5424, "loss": 0.408, "lr": 1.3388083992464335e-06, "epoch": 2.3557603686635944, "percentage": 78.54, "elapsed_time": "19:54:46", "remaining_time": "5:26:27"}
427
+ {"current_steps": 4270, "total_steps": 5424, "loss": 0.4036, "lr": 1.3169669827112603e-06, "epoch": 2.361290322580645, "percentage": 78.72, "elapsed_time": "19:57:33", "remaining_time": "5:23:39"}
428
+ {"current_steps": 4280, "total_steps": 5424, "loss": 0.3936, "lr": 1.2952781421823846e-06, "epoch": 2.366820276497696, "percentage": 78.91, "elapsed_time": "20:00:22", "remaining_time": "5:20:50"}
429
+ {"current_steps": 4290, "total_steps": 5424, "loss": 0.4006, "lr": 1.2737427761575006e-06, "epoch": 2.3723502304147464, "percentage": 79.09, "elapsed_time": "20:03:10", "remaining_time": "5:18:02"}
430
+ {"current_steps": 4300, "total_steps": 5424, "loss": 0.3994, "lr": 1.2523617767763535e-06, "epoch": 2.377880184331797, "percentage": 79.28, "elapsed_time": "20:05:56", "remaining_time": "5:15:13"}
431
+ {"current_steps": 4310, "total_steps": 5424, "loss": 0.4001, "lr": 1.2311360297837849e-06, "epoch": 2.383410138248848, "percentage": 79.46, "elapsed_time": "20:08:45", "remaining_time": "5:12:25"}
432
+ {"current_steps": 4320, "total_steps": 5424, "loss": 0.3924, "lr": 1.210066414493039e-06, "epoch": 2.3889400921658988, "percentage": 79.65, "elapsed_time": "20:11:35", "remaining_time": "5:09:37"}
433
+ {"current_steps": 4330, "total_steps": 5424, "loss": 0.4044, "lr": 1.1891538037493322e-06, "epoch": 2.394470046082949, "percentage": 79.83, "elapsed_time": "20:14:21", "remaining_time": "5:06:48"}
434
+ {"current_steps": 4340, "total_steps": 5424, "loss": 0.4017, "lr": 1.1683990638936981e-06, "epoch": 2.4, "percentage": 80.01, "elapsed_time": "20:17:10", "remaining_time": "5:04:00"}
435
+ {"current_steps": 4350, "total_steps": 5424, "loss": 0.401, "lr": 1.147803054727095e-06, "epoch": 2.4055299539170507, "percentage": 80.2, "elapsed_time": "20:20:03", "remaining_time": "5:01:13"}
436
+ {"current_steps": 4360, "total_steps": 5424, "loss": 0.4003, "lr": 1.1273666294747886e-06, "epoch": 2.4110599078341015, "percentage": 80.38, "elapsed_time": "20:22:57", "remaining_time": "4:58:26"}
437
+ {"current_steps": 4370, "total_steps": 5424, "loss": 0.3955, "lr": 1.1070906347510051e-06, "epoch": 2.4165898617511523, "percentage": 80.57, "elapsed_time": "20:25:50", "remaining_time": "4:55:39"}
438
+ {"current_steps": 4380, "total_steps": 5424, "loss": 0.3981, "lr": 1.0869759105238592e-06, "epoch": 2.4221198156682027, "percentage": 80.75, "elapsed_time": "20:28:36", "remaining_time": "4:52:50"}
439
+ {"current_steps": 4390, "total_steps": 5424, "loss": 0.3979, "lr": 1.0670232900805561e-06, "epoch": 2.4276497695852535, "percentage": 80.94, "elapsed_time": "20:31:24", "remaining_time": "4:50:02"}
440
+ {"current_steps": 4400, "total_steps": 5424, "loss": 0.398, "lr": 1.0472335999928712e-06, "epoch": 2.4331797235023043, "percentage": 81.12, "elapsed_time": "20:34:13", "remaining_time": "4:47:14"}
441
+ {"current_steps": 4410, "total_steps": 5424, "loss": 0.3928, "lr": 1.0276076600829094e-06, "epoch": 2.4387096774193546, "percentage": 81.31, "elapsed_time": "20:37:01", "remaining_time": "4:44:25"}
442
+ {"current_steps": 4420, "total_steps": 5424, "loss": 0.4051, "lr": 1.008146283389142e-06, "epoch": 2.4442396313364054, "percentage": 81.49, "elapsed_time": "20:39:52", "remaining_time": "4:41:38"}
443
+ {"current_steps": 4430, "total_steps": 5424, "loss": 0.4016, "lr": 9.888502761327235e-07, "epoch": 2.4497695852534562, "percentage": 81.67, "elapsed_time": "20:42:36", "remaining_time": "4:38:48"}
444
+ {"current_steps": 4440, "total_steps": 5424, "loss": 0.3955, "lr": 9.697204376840936e-07, "epoch": 2.455299539170507, "percentage": 81.86, "elapsed_time": "20:45:25", "remaining_time": "4:36:00"}
445
+ {"current_steps": 4450, "total_steps": 5424, "loss": 0.3999, "lr": 9.50757560529863e-07, "epoch": 2.460829493087558, "percentage": 82.04, "elapsed_time": "20:48:12", "remaining_time": "4:33:12"}
446
+ {"current_steps": 4460, "total_steps": 5424, "loss": 0.3976, "lr": 9.319624302399827e-07, "epoch": 2.466359447004608, "percentage": 82.23, "elapsed_time": "20:51:01", "remaining_time": "4:30:24"}
447
+ {"current_steps": 4470, "total_steps": 5424, "loss": 0.3959, "lr": 9.133358254351982e-07, "epoch": 2.471889400921659, "percentage": 82.41, "elapsed_time": "20:53:47", "remaining_time": "4:27:35"}
448
+ {"current_steps": 4480, "total_steps": 5424, "loss": 0.3999, "lr": 8.948785177547975e-07, "epoch": 2.47741935483871, "percentage": 82.6, "elapsed_time": "20:56:37", "remaining_time": "4:24:47"}
449
+ {"current_steps": 4490, "total_steps": 5424, "loss": 0.3943, "lr": 8.765912718246423e-07, "epoch": 2.48294930875576, "percentage": 82.78, "elapsed_time": "20:59:22", "remaining_time": "4:21:58"}
450
+ {"current_steps": 4500, "total_steps": 5424, "loss": 0.3979, "lr": 8.584748452254888e-07, "epoch": 2.488479262672811, "percentage": 82.96, "elapsed_time": "21:02:16", "remaining_time": "4:19:11"}
451
+ {"current_steps": 4510, "total_steps": 5424, "loss": 0.3942, "lr": 8.405299884616142e-07, "epoch": 2.4940092165898617, "percentage": 83.15, "elapsed_time": "21:05:05", "remaining_time": "4:16:23"}
452
+ {"current_steps": 4520, "total_steps": 5424, "loss": 0.4003, "lr": 8.227574449297137e-07, "epoch": 2.4995391705069125, "percentage": 83.33, "elapsed_time": "21:07:52", "remaining_time": "4:13:34"}
453
+ {"current_steps": 4530, "total_steps": 5424, "loss": 0.3952, "lr": 8.051579508881107e-07, "epoch": 2.5050691244239633, "percentage": 83.52, "elapsed_time": "21:10:40", "remaining_time": "4:10:46"}
454
+ {"current_steps": 4540, "total_steps": 5424, "loss": 0.4033, "lr": 7.877322354262545e-07, "epoch": 2.5105990783410137, "percentage": 83.7, "elapsed_time": "21:13:24", "remaining_time": "4:07:56"}
455
+ {"current_steps": 4550, "total_steps": 5424, "loss": 0.4005, "lr": 7.704810204345154e-07, "epoch": 2.5161290322580645, "percentage": 83.89, "elapsed_time": "21:16:10", "remaining_time": "4:05:08"}
456
+ {"current_steps": 4560, "total_steps": 5424, "loss": 0.3914, "lr": 7.534050205742827e-07, "epoch": 2.5216589861751153, "percentage": 84.07, "elapsed_time": "21:19:04", "remaining_time": "4:02:21"}
457
+ {"current_steps": 4570, "total_steps": 5424, "loss": 0.4032, "lr": 7.365049432483529e-07, "epoch": 2.5271889400921657, "percentage": 84.26, "elapsed_time": "21:21:51", "remaining_time": "3:59:32"}
458
+ {"current_steps": 4580, "total_steps": 5424, "loss": 0.4039, "lr": 7.19781488571632e-07, "epoch": 2.5327188940092165, "percentage": 84.44, "elapsed_time": "21:24:43", "remaining_time": "3:56:44"}
459
+ {"current_steps": 4590, "total_steps": 5424, "loss": 0.403, "lr": 7.032353493421213e-07, "epoch": 2.5382488479262673, "percentage": 84.62, "elapsed_time": "21:27:33", "remaining_time": "3:53:56"}
460
+ {"current_steps": 4600, "total_steps": 5424, "loss": 0.4, "lr": 6.868672110122271e-07, "epoch": 2.543778801843318, "percentage": 84.81, "elapsed_time": "21:30:24", "remaining_time": "3:51:08"}
461
+ {"current_steps": 4610, "total_steps": 5424, "loss": 0.4064, "lr": 6.706777516603636e-07, "epoch": 2.549308755760369, "percentage": 84.99, "elapsed_time": "21:33:16", "remaining_time": "3:48:21"}
462
+ {"current_steps": 4620, "total_steps": 5424, "loss": 0.398, "lr": 6.546676419628545e-07, "epoch": 2.554838709677419, "percentage": 85.18, "elapsed_time": "21:36:03", "remaining_time": "3:45:32"}
463
+ {"current_steps": 4630, "total_steps": 5424, "loss": 0.3958, "lr": 6.388375451661578e-07, "epoch": 2.56036866359447, "percentage": 85.36, "elapsed_time": "21:38:53", "remaining_time": "3:42:44"}
464
+ {"current_steps": 4640, "total_steps": 5424, "loss": 0.3983, "lr": 6.231881170593828e-07, "epoch": 2.565898617511521, "percentage": 85.55, "elapsed_time": "21:41:49", "remaining_time": "3:39:57"}
465
+ {"current_steps": 4650, "total_steps": 5424, "loss": 0.3993, "lr": 6.077200059471289e-07, "epoch": 2.571428571428571, "percentage": 85.73, "elapsed_time": "21:44:42", "remaining_time": "3:37:10"}
466
+ {"current_steps": 4660, "total_steps": 5424, "loss": 0.3856, "lr": 5.924338526226259e-07, "epoch": 2.576958525345622, "percentage": 85.91, "elapsed_time": "21:47:24", "remaining_time": "3:34:20"}
467
+ {"current_steps": 4670, "total_steps": 5424, "loss": 0.3943, "lr": 5.773302903411848e-07, "epoch": 2.5824884792626728, "percentage": 86.1, "elapsed_time": "21:50:13", "remaining_time": "3:31:32"}
468
+ {"current_steps": 4680, "total_steps": 5424, "loss": 0.3997, "lr": 5.624099447939696e-07, "epoch": 2.5880184331797236, "percentage": 86.28, "elapsed_time": "21:52:59", "remaining_time": "3:28:43"}
469
+ {"current_steps": 4690, "total_steps": 5424, "loss": 0.3914, "lr": 5.476734340820738e-07, "epoch": 2.5935483870967744, "percentage": 86.47, "elapsed_time": "21:55:45", "remaining_time": "3:25:55"}
470
+ {"current_steps": 4700, "total_steps": 5424, "loss": 0.4052, "lr": 5.331213686909159e-07, "epoch": 2.5990783410138247, "percentage": 86.65, "elapsed_time": "21:58:37", "remaining_time": "3:23:07"}
471
+ {"current_steps": 4710, "total_steps": 5424, "loss": 0.3987, "lr": 5.187543514649479e-07, "epoch": 2.6046082949308755, "percentage": 86.84, "elapsed_time": "22:01:21", "remaining_time": "3:20:18"}
472
+ {"current_steps": 4720, "total_steps": 5424, "loss": 0.4, "lr": 5.045729775826818e-07, "epoch": 2.6101382488479263, "percentage": 87.02, "elapsed_time": "22:04:10", "remaining_time": "3:17:30"}
473
+ {"current_steps": 4730, "total_steps": 5424, "loss": 0.4046, "lr": 4.905778345320339e-07, "epoch": 2.6156682027649767, "percentage": 87.21, "elapsed_time": "22:06:55", "remaining_time": "3:14:41"}
474
+ {"current_steps": 4740, "total_steps": 5424, "loss": 0.3989, "lr": 4.767695020859847e-07, "epoch": 2.6211981566820275, "percentage": 87.39, "elapsed_time": "22:09:49", "remaining_time": "3:11:53"}
475
+ {"current_steps": 4750, "total_steps": 5424, "loss": 0.3966, "lr": 4.6314855227856505e-07, "epoch": 2.6267281105990783, "percentage": 87.57, "elapsed_time": "22:12:31", "remaining_time": "3:09:04"}
476
+ {"current_steps": 4760, "total_steps": 5424, "loss": 0.3923, "lr": 4.497155493811539e-07, "epoch": 2.632258064516129, "percentage": 87.76, "elapsed_time": "22:15:10", "remaining_time": "3:06:15"}
477
+ {"current_steps": 4770, "total_steps": 5424, "loss": 0.3983, "lr": 4.3647104987910636e-07, "epoch": 2.63778801843318, "percentage": 87.94, "elapsed_time": "22:18:00", "remaining_time": "3:03:26"}
478
+ {"current_steps": 4780, "total_steps": 5424, "loss": 0.3925, "lr": 4.2341560244869797e-07, "epoch": 2.6433179723502302, "percentage": 88.13, "elapsed_time": "22:20:35", "remaining_time": "3:00:36"}
479
+ {"current_steps": 4790, "total_steps": 5424, "loss": 0.3986, "lr": 4.1054974793439504e-07, "epoch": 2.648847926267281, "percentage": 88.31, "elapsed_time": "22:23:18", "remaining_time": "2:57:47"}
480
+ {"current_steps": 4800, "total_steps": 5424, "loss": 0.3921, "lr": 3.978740193264524e-07, "epoch": 2.654377880184332, "percentage": 88.5, "elapsed_time": "22:26:06", "remaining_time": "2:54:59"}
481
+ {"current_steps": 4810, "total_steps": 5424, "loss": 0.3984, "lr": 3.853889417388279e-07, "epoch": 2.6599078341013827, "percentage": 88.68, "elapsed_time": "22:28:53", "remaining_time": "2:52:11"}
482
+ {"current_steps": 4820, "total_steps": 5424, "loss": 0.3977, "lr": 3.730950323874322e-07, "epoch": 2.6654377880184335, "percentage": 88.86, "elapsed_time": "22:31:39", "remaining_time": "2:49:22"}
483
+ {"current_steps": 4830, "total_steps": 5424, "loss": 0.4008, "lr": 3.6099280056870136e-07, "epoch": 2.670967741935484, "percentage": 89.05, "elapsed_time": "22:34:29", "remaining_time": "2:46:34"}
484
+ {"current_steps": 4840, "total_steps": 5424, "loss": 0.4006, "lr": 3.490827476385006e-07, "epoch": 2.6764976958525346, "percentage": 89.23, "elapsed_time": "22:37:10", "remaining_time": "2:43:45"}
485
+ {"current_steps": 4850, "total_steps": 5424, "loss": 0.3973, "lr": 3.373653669913479e-07, "epoch": 2.6820276497695854, "percentage": 89.42, "elapsed_time": "22:39:56", "remaining_time": "2:40:56"}
486
+ {"current_steps": 4860, "total_steps": 5424, "loss": 0.3921, "lr": 3.258411440399839e-07, "epoch": 2.6875576036866358, "percentage": 89.6, "elapsed_time": "22:42:43", "remaining_time": "2:38:08"}
487
+ {"current_steps": 4870, "total_steps": 5424, "loss": 0.401, "lr": 3.1451055619525495e-07, "epoch": 2.6930875576036866, "percentage": 89.79, "elapsed_time": "22:45:36", "remaining_time": "2:35:20"}
488
+ {"current_steps": 4880, "total_steps": 5424, "loss": 0.4003, "lr": 3.0337407284634023e-07, "epoch": 2.6986175115207374, "percentage": 89.97, "elapsed_time": "22:48:21", "remaining_time": "2:32:32"}
489
+ {"current_steps": 4890, "total_steps": 5424, "loss": 0.4003, "lr": 2.924321553413029e-07, "epoch": 2.704147465437788, "percentage": 90.15, "elapsed_time": "22:51:05", "remaining_time": "2:29:43"}
490
+ {"current_steps": 4900, "total_steps": 5424, "loss": 0.3932, "lr": 2.8168525696798287e-07, "epoch": 2.709677419354839, "percentage": 90.34, "elapsed_time": "22:53:54", "remaining_time": "2:26:55"}
491
+ {"current_steps": 4910, "total_steps": 5424, "loss": 0.3935, "lr": 2.7113382293521285e-07, "epoch": 2.7152073732718893, "percentage": 90.52, "elapsed_time": "22:56:48", "remaining_time": "2:24:07"}
492
+ {"current_steps": 4920, "total_steps": 5424, "loss": 0.4059, "lr": 2.607782903543782e-07, "epoch": 2.72073732718894, "percentage": 90.71, "elapsed_time": "22:59:37", "remaining_time": "2:21:19"}
493
+ {"current_steps": 4930, "total_steps": 5424, "loss": 0.3842, "lr": 2.5061908822131e-07, "epoch": 2.726267281105991, "percentage": 90.89, "elapsed_time": "23:02:22", "remaining_time": "2:18:31"}
494
+ {"current_steps": 4940, "total_steps": 5424, "loss": 0.3952, "lr": 2.406566373985075e-07, "epoch": 2.7317972350230413, "percentage": 91.08, "elapsed_time": "23:05:06", "remaining_time": "2:15:42"}
495
+ {"current_steps": 4950, "total_steps": 5424, "loss": 0.4097, "lr": 2.3089135059771007e-07, "epoch": 2.737327188940092, "percentage": 91.26, "elapsed_time": "23:07:52", "remaining_time": "2:12:54"}
496
+ {"current_steps": 4960, "total_steps": 5424, "loss": 0.402, "lr": 2.2132363236279654e-07, "epoch": 2.742857142857143, "percentage": 91.45, "elapsed_time": "23:10:44", "remaining_time": "2:10:06"}
497
+ {"current_steps": 4970, "total_steps": 5424, "loss": 0.3986, "lr": 2.1195387905302511e-07, "epoch": 2.7483870967741937, "percentage": 91.63, "elapsed_time": "23:13:25", "remaining_time": "2:07:17"}
498
+ {"current_steps": 4980, "total_steps": 5424, "loss": 0.3925, "lr": 2.0278247882661584e-07, "epoch": 2.7539170506912445, "percentage": 91.81, "elapsed_time": "23:16:13", "remaining_time": "2:04:28"}
499
+ {"current_steps": 4990, "total_steps": 5424, "loss": 0.3967, "lr": 1.9380981162466895e-07, "epoch": 2.759447004608295, "percentage": 92.0, "elapsed_time": "23:19:00", "remaining_time": "2:01:40"}
500
+ {"current_steps": 5000, "total_steps": 5424, "loss": 0.3958, "lr": 1.8503624915542805e-07, "epoch": 2.7649769585253456, "percentage": 92.18, "elapsed_time": "23:21:45", "remaining_time": "1:58:52"}
501
+ {"current_steps": 5010, "total_steps": 5424, "loss": 0.3972, "lr": 1.7646215487887587e-07, "epoch": 2.7705069124423964, "percentage": 92.37, "elapsed_time": "23:24:37", "remaining_time": "1:56:04"}
502
+ {"current_steps": 5020, "total_steps": 5424, "loss": 0.3954, "lr": 1.680878839916833e-07, "epoch": 2.776036866359447, "percentage": 92.55, "elapsed_time": "23:27:21", "remaining_time": "1:53:15"}
503
+ {"current_steps": 5030, "total_steps": 5424, "loss": 0.3909, "lr": 1.5991378341249032e-07, "epoch": 2.7815668202764976, "percentage": 92.74, "elapsed_time": "23:30:07", "remaining_time": "1:50:27"}
504
+ {"current_steps": 5040, "total_steps": 5424, "loss": 0.3987, "lr": 1.5194019176753615e-07, "epoch": 2.7870967741935484, "percentage": 92.92, "elapsed_time": "23:32:56", "remaining_time": "1:47:39"}
505
+ {"current_steps": 5050, "total_steps": 5424, "loss": 0.4025, "lr": 1.441674393766318e-07, "epoch": 2.792626728110599, "percentage": 93.1, "elapsed_time": "23:35:49", "remaining_time": "1:44:51"}
506
+ {"current_steps": 5060, "total_steps": 5424, "loss": 0.3959, "lr": 1.3659584823947524e-07, "epoch": 2.79815668202765, "percentage": 93.29, "elapsed_time": "23:38:40", "remaining_time": "1:42:03"}
507
+ {"current_steps": 5070, "total_steps": 5424, "loss": 0.3981, "lr": 1.2922573202231114e-07, "epoch": 2.8036866359447004, "percentage": 93.47, "elapsed_time": "23:41:19", "remaining_time": "1:39:14"}
508
+ {"current_steps": 5080, "total_steps": 5424, "loss": 0.4043, "lr": 1.2205739604493838e-07, "epoch": 2.809216589861751, "percentage": 93.66, "elapsed_time": "23:44:05", "remaining_time": "1:36:26"}
509
+ {"current_steps": 5090, "total_steps": 5424, "loss": 0.3903, "lr": 1.1509113726805965e-07, "epoch": 2.814746543778802, "percentage": 93.84, "elapsed_time": "23:46:49", "remaining_time": "1:33:37"}
510
+ {"current_steps": 5100, "total_steps": 5424, "loss": 0.3964, "lr": 1.0832724428098185e-07, "epoch": 2.8202764976958523, "percentage": 94.03, "elapsed_time": "23:49:35", "remaining_time": "1:30:49"}
511
+ {"current_steps": 5110, "total_steps": 5424, "loss": 0.3975, "lr": 1.0176599728965842e-07, "epoch": 2.825806451612903, "percentage": 94.21, "elapsed_time": "23:52:25", "remaining_time": "1:28:01"}
512
+ {"current_steps": 5120, "total_steps": 5424, "loss": 0.3966, "lr": 9.540766810508196e-08, "epoch": 2.831336405529954, "percentage": 94.4, "elapsed_time": "23:55:14", "remaining_time": "1:25:13"}
513
+ {"current_steps": 5130, "total_steps": 5424, "loss": 0.3974, "lr": 8.925252013202545e-08, "epoch": 2.8368663594470047, "percentage": 94.58, "elapsed_time": "23:58:02", "remaining_time": "1:22:24"}
514
+ {"current_steps": 5140, "total_steps": 5424, "loss": 0.3915, "lr": 8.330080835812826e-08, "epoch": 2.8423963133640555, "percentage": 94.76, "elapsed_time": "1 day, 0:00:56", "remaining_time": "1:19:36"}
515
+ {"current_steps": 5150, "total_steps": 5424, "loss": 0.3959, "lr": 7.75527793433345e-08, "epoch": 2.847926267281106, "percentage": 94.95, "elapsed_time": "1 day, 0:03:43", "remaining_time": "1:16:48"}
516
+ {"current_steps": 5160, "total_steps": 5424, "loss": 0.4048, "lr": 7.20086712096768e-08, "epoch": 2.8534562211981567, "percentage": 95.13, "elapsed_time": "1 day, 0:06:27", "remaining_time": "1:14:00"}
517
+ {"current_steps": 5170, "total_steps": 5424, "loss": 0.4008, "lr": 6.666871363141426e-08, "epoch": 2.8589861751152075, "percentage": 95.32, "elapsed_time": "1 day, 0:09:10", "remaining_time": "1:11:11"}
518
+ {"current_steps": 5180, "total_steps": 5424, "loss": 0.3943, "lr": 6.153312782551546e-08, "epoch": 2.864516129032258, "percentage": 95.5, "elapsed_time": "1 day, 0:11:59", "remaining_time": "1:08:23"}
519
+ {"current_steps": 5190, "total_steps": 5424, "loss": 0.4068, "lr": 5.6602126542496525e-08, "epoch": 2.8700460829493086, "percentage": 95.69, "elapsed_time": "1 day, 0:14:41", "remaining_time": "1:05:35"}
520
+ {"current_steps": 5200, "total_steps": 5424, "loss": 0.3978, "lr": 5.187591405760528e-08, "epoch": 2.8755760368663594, "percentage": 95.87, "elapsed_time": "1 day, 0:17:27", "remaining_time": "1:02:46"}
521
+ {"current_steps": 5210, "total_steps": 5424, "loss": 0.4013, "lr": 4.7354686162359165e-08, "epoch": 2.8811059907834102, "percentage": 96.05, "elapsed_time": "1 day, 0:20:10", "remaining_time": "0:59:58"}
522
+ {"current_steps": 5220, "total_steps": 5424, "loss": 0.3905, "lr": 4.3038630156436166e-08, "epoch": 2.886635944700461, "percentage": 96.24, "elapsed_time": "1 day, 0:23:00", "remaining_time": "0:57:10"}
523
+ {"current_steps": 5230, "total_steps": 5424, "loss": 0.393, "lr": 3.8927924839913257e-08, "epoch": 2.8921658986175114, "percentage": 96.42, "elapsed_time": "1 day, 0:25:47", "remaining_time": "0:54:22"}
524
+ {"current_steps": 5240, "total_steps": 5424, "loss": 0.4006, "lr": 3.502274050586063e-08, "epoch": 2.897695852534562, "percentage": 96.61, "elapsed_time": "1 day, 0:28:38", "remaining_time": "0:51:34"}
525
+ {"current_steps": 5250, "total_steps": 5424, "loss": 0.3978, "lr": 3.1323238933286814e-08, "epoch": 2.903225806451613, "percentage": 96.79, "elapsed_time": "1 day, 0:31:25", "remaining_time": "0:48:46"}
526
+ {"current_steps": 5260, "total_steps": 5424, "loss": 0.4029, "lr": 2.7829573380436793e-08, "epoch": 2.9087557603686633, "percentage": 96.98, "elapsed_time": "1 day, 0:34:11", "remaining_time": "0:45:57"}
527
+ {"current_steps": 5270, "total_steps": 5424, "loss": 0.3915, "lr": 2.4541888578442085e-08, "epoch": 2.914285714285714, "percentage": 97.16, "elapsed_time": "1 day, 0:36:53", "remaining_time": "0:43:09"}
528
+ {"current_steps": 5280, "total_steps": 5424, "loss": 0.392, "lr": 2.1460320725326113e-08, "epoch": 2.919815668202765, "percentage": 97.35, "elapsed_time": "1 day, 0:39:36", "remaining_time": "0:40:21"}
529
+ {"current_steps": 5290, "total_steps": 5424, "loss": 0.4023, "lr": 1.8584997480361467e-08, "epoch": 2.9253456221198157, "percentage": 97.53, "elapsed_time": "1 day, 0:42:24", "remaining_time": "0:37:33"}
530
+ {"current_steps": 5300, "total_steps": 5424, "loss": 0.3966, "lr": 1.5916037958781938e-08, "epoch": 2.9308755760368665, "percentage": 97.71, "elapsed_time": "1 day, 0:45:03", "remaining_time": "0:34:44"}
531
+ {"current_steps": 5310, "total_steps": 5424, "loss": 0.4018, "lr": 1.3453552726847008e-08, "epoch": 2.936405529953917, "percentage": 97.9, "elapsed_time": "1 day, 0:47:53", "remaining_time": "0:31:56"}
532
+ {"current_steps": 5320, "total_steps": 5424, "loss": 0.4027, "lr": 1.1197643797261626e-08, "epoch": 2.9419354838709677, "percentage": 98.08, "elapsed_time": "1 day, 0:50:32", "remaining_time": "0:29:08"}
533
+ {"current_steps": 5330, "total_steps": 5424, "loss": 0.4033, "lr": 9.148404624951812e-09, "epoch": 2.9474654377880185, "percentage": 98.27, "elapsed_time": "1 day, 0:53:17", "remaining_time": "0:26:20"}
534
+ {"current_steps": 5340, "total_steps": 5424, "loss": 0.3962, "lr": 7.3059201031899786e-09, "epoch": 2.952995391705069, "percentage": 98.45, "elapsed_time": "1 day, 0:55:59", "remaining_time": "0:23:31"}
535
+ {"current_steps": 5350, "total_steps": 5424, "loss": 0.4014, "lr": 5.670266560081628e-09, "epoch": 2.9585253456221197, "percentage": 98.64, "elapsed_time": "1 day, 0:58:47", "remaining_time": "0:20:43"}
536
+ {"current_steps": 5360, "total_steps": 5424, "loss": 0.4113, "lr": 4.241511755400662e-09, "epoch": 2.9640552995391705, "percentage": 98.82, "elapsed_time": "1 day, 1:01:41", "remaining_time": "0:17:55"}
537
+ {"current_steps": 5370, "total_steps": 5424, "loss": 0.3967, "lr": 3.0197148777838524e-09, "epoch": 2.9695852534562213, "percentage": 99.0, "elapsed_time": "1 day, 1:04:23", "remaining_time": "0:15:07"}
538
+ {"current_steps": 5380, "total_steps": 5424, "loss": 0.3993, "lr": 2.0049265422772414e-09, "epoch": 2.975115207373272, "percentage": 99.19, "elapsed_time": "1 day, 1:07:09", "remaining_time": "0:12:19"}
539
+ {"current_steps": 5390, "total_steps": 5424, "loss": 0.4024, "lr": 1.1971887882405997e-09, "epoch": 2.9806451612903224, "percentage": 99.37, "elapsed_time": "1 day, 1:10:02", "remaining_time": "0:09:31"}
540
+ {"current_steps": 5400, "total_steps": 5424, "loss": 0.4049, "lr": 5.965350776071521e-10, "epoch": 2.986175115207373, "percentage": 99.56, "elapsed_time": "1 day, 1:12:52", "remaining_time": "0:06:43"}
541
+ {"current_steps": 5410, "total_steps": 5424, "loss": 0.3993, "lr": 2.029902934941319e-10, "epoch": 2.991705069124424, "percentage": 99.74, "elapsed_time": "1 day, 1:15:40", "remaining_time": "0:03:55"}
542
+ {"current_steps": 5420, "total_steps": 5424, "loss": 0.3964, "lr": 1.6570739174714967e-11, "epoch": 2.9972350230414744, "percentage": 99.93, "elapsed_time": "1 day, 1:18:32", "remaining_time": "0:01:07"}
543
+ {"current_steps": 5424, "total_steps": 5424, "epoch": 2.999447004608295, "percentage": 100.0, "elapsed_time": "1 day, 1:22:23", "remaining_time": "0:00:00"}