sedrickkeh commited on
Commit
271e403
·
verified ·
1 Parent(s): b70266e

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 sha256:3a75bbc623ef4717a4a00937ffdff17cf3765d124675840f28e47a9c765965d8
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:367ca6f7b62bf1f3348c6d83334e18054c9c8141f0705b2608517e077e79b686
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:705a558c1c91877f1effb794e5bb1123ae1b6005b55d43acd63f8c60b3780995
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb0b3e1da7a246b808411d72328c3da628137e09347fca710dac61bb2beb3746
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a63ad7809807aa21daecaed4b9c578e5832abe808ee558d4d9a3207d54a8a0d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2abf516ae514ea13448522aab69087745c8ba4df578ae1da82ff7d9078370d1
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:ed863f35e77ccee56814d2b2c46c8377de364600896a8132842450ec147c529a
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace1c65afd035c15244f13699d877b008896f81098784668188682960fee8833
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -351,3 +351,173 @@
351
  {"current_steps": 351, "total_steps": 522, "loss": 0.4483, "lr": 2.936782637973044e-06, "epoch": 2.0133843212237093, "percentage": 67.24, "elapsed_time": "3:02:55", "remaining_time": "1:29:07"}
352
  {"current_steps": 352, "total_steps": 522, "loss": 0.4391, "lr": 2.9063211203011443e-06, "epoch": 2.019120458891013, "percentage": 67.43, "elapsed_time": "3:03:25", "remaining_time": "1:28:35"}
353
  {"current_steps": 353, "total_steps": 522, "loss": 0.4413, "lr": 2.8759535452146128e-06, "epoch": 2.024856596558317, "percentage": 67.62, "elapsed_time": "3:03:56", "remaining_time": "1:28:03"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
351
  {"current_steps": 351, "total_steps": 522, "loss": 0.4483, "lr": 2.936782637973044e-06, "epoch": 2.0133843212237093, "percentage": 67.24, "elapsed_time": "3:02:55", "remaining_time": "1:29:07"}
352
  {"current_steps": 352, "total_steps": 522, "loss": 0.4391, "lr": 2.9063211203011443e-06, "epoch": 2.019120458891013, "percentage": 67.43, "elapsed_time": "3:03:25", "remaining_time": "1:28:35"}
353
  {"current_steps": 353, "total_steps": 522, "loss": 0.4413, "lr": 2.8759535452146128e-06, "epoch": 2.024856596558317, "percentage": 67.62, "elapsed_time": "3:03:56", "remaining_time": "1:28:03"}
354
+ {"current_steps": 354, "total_steps": 522, "loss": 0.4178, "lr": 2.8456812752951483e-06, "epoch": 2.0305927342256216, "percentage": 67.82, "elapsed_time": "3:04:28", "remaining_time": "1:27:32"}
355
+ {"current_steps": 355, "total_steps": 522, "loss": 0.4108, "lr": 2.815505668848136e-06, "epoch": 2.0363288718929256, "percentage": 68.01, "elapsed_time": "3:05:03", "remaining_time": "1:27:03"}
356
+ {"current_steps": 356, "total_steps": 522, "loss": 0.4287, "lr": 2.785428079841709e-06, "epoch": 2.0420650095602295, "percentage": 68.2, "elapsed_time": "3:05:34", "remaining_time": "1:26:31"}
357
+ {"current_steps": 357, "total_steps": 522, "loss": 0.4554, "lr": 2.755449857845992e-06, "epoch": 2.0478011472275335, "percentage": 68.39, "elapsed_time": "3:06:10", "remaining_time": "1:26:02"}
358
+ {"current_steps": 358, "total_steps": 522, "loss": 0.4333, "lr": 2.725572347972558e-06, "epoch": 2.0535372848948374, "percentage": 68.58, "elapsed_time": "3:06:49", "remaining_time": "1:25:35"}
359
+ {"current_steps": 359, "total_steps": 522, "loss": 0.3632, "lr": 2.6957968908140546e-06, "epoch": 2.0592734225621414, "percentage": 68.77, "elapsed_time": "3:07:22", "remaining_time": "1:25:04"}
360
+ {"current_steps": 360, "total_steps": 522, "loss": 0.4386, "lr": 2.666124822384071e-06, "epoch": 2.0650095602294454, "percentage": 68.97, "elapsed_time": "3:07:54", "remaining_time": "1:24:33"}
361
+ {"current_steps": 361, "total_steps": 522, "loss": 0.3728, "lr": 2.636557474057173e-06, "epoch": 2.0707456978967493, "percentage": 69.16, "elapsed_time": "3:08:21", "remaining_time": "1:24:00"}
362
+ {"current_steps": 362, "total_steps": 522, "loss": 0.406, "lr": 2.607096172509187e-06, "epoch": 2.0764818355640537, "percentage": 69.35, "elapsed_time": "3:08:55", "remaining_time": "1:23:30"}
363
+ {"current_steps": 363, "total_steps": 522, "loss": 0.4789, "lr": 2.5777422396576503e-06, "epoch": 2.0822179732313577, "percentage": 69.54, "elapsed_time": "3:09:26", "remaining_time": "1:22:58"}
364
+ {"current_steps": 364, "total_steps": 522, "loss": 0.4052, "lr": 2.5484969926025114e-06, "epoch": 2.0879541108986617, "percentage": 69.73, "elapsed_time": "3:09:50", "remaining_time": "1:22:24"}
365
+ {"current_steps": 365, "total_steps": 522, "loss": 0.4542, "lr": 2.5193617435670244e-06, "epoch": 2.0936902485659656, "percentage": 69.92, "elapsed_time": "3:10:24", "remaining_time": "1:21:54"}
366
+ {"current_steps": 366, "total_steps": 522, "loss": 0.4266, "lr": 2.4903377998388783e-06, "epoch": 2.0994263862332696, "percentage": 70.11, "elapsed_time": "3:10:52", "remaining_time": "1:21:21"}
367
+ {"current_steps": 367, "total_steps": 522, "loss": 0.477, "lr": 2.461426463711535e-06, "epoch": 2.1051625239005736, "percentage": 70.31, "elapsed_time": "3:11:28", "remaining_time": "1:20:52"}
368
+ {"current_steps": 368, "total_steps": 522, "loss": 0.3927, "lr": 2.4326290324257896e-06, "epoch": 2.1108986615678775, "percentage": 70.5, "elapsed_time": "3:11:59", "remaining_time": "1:20:20"}
369
+ {"current_steps": 369, "total_steps": 522, "loss": 0.4252, "lr": 2.403946798111576e-06, "epoch": 2.1166347992351815, "percentage": 70.69, "elapsed_time": "3:12:29", "remaining_time": "1:19:48"}
370
+ {"current_steps": 370, "total_steps": 522, "loss": 0.4468, "lr": 2.37538104772998e-06, "epoch": 2.1223709369024855, "percentage": 70.88, "elapsed_time": "3:13:01", "remaining_time": "1:19:17"}
371
+ {"current_steps": 371, "total_steps": 522, "loss": 0.3703, "lr": 2.3469330630154974e-06, "epoch": 2.12810707456979, "percentage": 71.07, "elapsed_time": "3:13:26", "remaining_time": "1:18:43"}
372
+ {"current_steps": 372, "total_steps": 522, "loss": 0.4514, "lr": 2.318604120418521e-06, "epoch": 2.133843212237094, "percentage": 71.26, "elapsed_time": "3:13:54", "remaining_time": "1:18:11"}
373
+ {"current_steps": 373, "total_steps": 522, "loss": 0.3606, "lr": 2.2903954910480746e-06, "epoch": 2.139579349904398, "percentage": 71.46, "elapsed_time": "3:14:24", "remaining_time": "1:17:39"}
374
+ {"current_steps": 374, "total_steps": 522, "loss": 0.5376, "lr": 2.2623084406147643e-06, "epoch": 2.1453154875717018, "percentage": 71.65, "elapsed_time": "3:15:01", "remaining_time": "1:17:10"}
375
+ {"current_steps": 375, "total_steps": 522, "loss": 0.3552, "lr": 2.234344229374003e-06, "epoch": 2.1510516252390057, "percentage": 71.84, "elapsed_time": "3:15:25", "remaining_time": "1:16:36"}
376
+ {"current_steps": 376, "total_steps": 522, "loss": 0.4369, "lr": 2.2065041120694487e-06, "epoch": 2.1567877629063097, "percentage": 72.03, "elapsed_time": "3:15:57", "remaining_time": "1:16:05"}
377
+ {"current_steps": 377, "total_steps": 522, "loss": 0.4222, "lr": 2.178789337876716e-06, "epoch": 2.1625239005736137, "percentage": 72.22, "elapsed_time": "3:16:32", "remaining_time": "1:15:35"}
378
+ {"current_steps": 378, "total_steps": 522, "loss": 0.4288, "lr": 2.151201150347318e-06, "epoch": 2.1682600382409176, "percentage": 72.41, "elapsed_time": "3:17:09", "remaining_time": "1:15:06"}
379
+ {"current_steps": 379, "total_steps": 522, "loss": 0.3889, "lr": 2.123740787352872e-06, "epoch": 2.173996175908222, "percentage": 72.61, "elapsed_time": "3:17:29", "remaining_time": "1:14:30"}
380
+ {"current_steps": 380, "total_steps": 522, "loss": 0.3958, "lr": 2.096409481029556e-06, "epoch": 2.179732313575526, "percentage": 72.8, "elapsed_time": "3:18:01", "remaining_time": "1:13:59"}
381
+ {"current_steps": 381, "total_steps": 522, "loss": 0.4066, "lr": 2.069208457722828e-06, "epoch": 2.18546845124283, "percentage": 72.99, "elapsed_time": "3:18:29", "remaining_time": "1:13:27"}
382
+ {"current_steps": 382, "total_steps": 522, "loss": 0.4326, "lr": 2.042138937932388e-06, "epoch": 2.191204588910134, "percentage": 73.18, "elapsed_time": "3:18:58", "remaining_time": "1:12:55"}
383
+ {"current_steps": 383, "total_steps": 522, "loss": 0.4441, "lr": 2.015202136257432e-06, "epoch": 2.196940726577438, "percentage": 73.37, "elapsed_time": "3:19:30", "remaining_time": "1:12:24"}
384
+ {"current_steps": 384, "total_steps": 522, "loss": 0.417, "lr": 1.988399261342135e-06, "epoch": 2.202676864244742, "percentage": 73.56, "elapsed_time": "3:20:03", "remaining_time": "1:11:53"}
385
+ {"current_steps": 385, "total_steps": 522, "loss": 0.4227, "lr": 1.9617315158214363e-06, "epoch": 2.208413001912046, "percentage": 73.75, "elapsed_time": "3:20:36", "remaining_time": "1:11:23"}
386
+ {"current_steps": 386, "total_steps": 522, "loss": 0.4218, "lr": 1.935200096267064e-06, "epoch": 2.21414913957935, "percentage": 73.95, "elapsed_time": "3:21:06", "remaining_time": "1:10:51"}
387
+ {"current_steps": 387, "total_steps": 522, "loss": 0.4437, "lr": 1.908806193133855e-06, "epoch": 2.2198852772466537, "percentage": 74.14, "elapsed_time": "3:21:42", "remaining_time": "1:10:21"}
388
+ {"current_steps": 388, "total_steps": 522, "loss": 0.4634, "lr": 1.8825509907063328e-06, "epoch": 2.2256214149139577, "percentage": 74.33, "elapsed_time": "3:22:11", "remaining_time": "1:09:49"}
389
+ {"current_steps": 389, "total_steps": 522, "loss": 0.4139, "lr": 1.856435667045577e-06, "epoch": 2.231357552581262, "percentage": 74.52, "elapsed_time": "3:22:43", "remaining_time": "1:09:18"}
390
+ {"current_steps": 390, "total_steps": 522, "loss": 0.3866, "lr": 1.8304613939363531e-06, "epoch": 2.237093690248566, "percentage": 74.71, "elapsed_time": "3:23:12", "remaining_time": "1:08:46"}
391
+ {"current_steps": 391, "total_steps": 522, "loss": 0.399, "lr": 1.8046293368345485e-06, "epoch": 2.24282982791587, "percentage": 74.9, "elapsed_time": "3:23:43", "remaining_time": "1:08:15"}
392
+ {"current_steps": 392, "total_steps": 522, "loss": 0.4437, "lr": 1.7789406548148647e-06, "epoch": 2.248565965583174, "percentage": 75.1, "elapsed_time": "3:24:19", "remaining_time": "1:07:45"}
393
+ {"current_steps": 393, "total_steps": 522, "loss": 0.4779, "lr": 1.7533965005188242e-06, "epoch": 2.254302103250478, "percentage": 75.29, "elapsed_time": "3:24:52", "remaining_time": "1:07:14"}
394
+ {"current_steps": 394, "total_steps": 522, "loss": 0.4178, "lr": 1.7279980201030382e-06, "epoch": 2.260038240917782, "percentage": 75.48, "elapsed_time": "3:25:20", "remaining_time": "1:06:42"}
395
+ {"current_steps": 395, "total_steps": 522, "loss": 0.4588, "lr": 1.7027463531877897e-06, "epoch": 2.265774378585086, "percentage": 75.67, "elapsed_time": "3:25:49", "remaining_time": "1:06:10"}
396
+ {"current_steps": 396, "total_steps": 522, "loss": 0.4099, "lr": 1.677642632805892e-06, "epoch": 2.27151051625239, "percentage": 75.86, "elapsed_time": "3:26:20", "remaining_time": "1:05:39"}
397
+ {"current_steps": 397, "total_steps": 522, "loss": 0.4204, "lr": 1.6526879853518558e-06, "epoch": 2.2772466539196943, "percentage": 76.05, "elapsed_time": "3:26:44", "remaining_time": "1:05:05"}
398
+ {"current_steps": 398, "total_steps": 522, "loss": 0.4375, "lr": 1.6278835305313462e-06, "epoch": 2.2829827915869982, "percentage": 76.25, "elapsed_time": "3:27:11", "remaining_time": "1:04:33"}
399
+ {"current_steps": 399, "total_steps": 522, "loss": 0.4384, "lr": 1.6032303813109368e-06, "epoch": 2.288718929254302, "percentage": 76.44, "elapsed_time": "3:27:44", "remaining_time": "1:04:02"}
400
+ {"current_steps": 400, "total_steps": 522, "loss": 0.4333, "lr": 1.578729643868181e-06, "epoch": 2.294455066921606, "percentage": 76.63, "elapsed_time": "3:28:14", "remaining_time": "1:03:30"}
401
+ {"current_steps": 401, "total_steps": 522, "loss": 0.445, "lr": 1.5543824175419691e-06, "epoch": 2.30019120458891, "percentage": 76.82, "elapsed_time": "3:28:44", "remaining_time": "1:02:59"}
402
+ {"current_steps": 402, "total_steps": 522, "loss": 0.4125, "lr": 1.5301897947832063e-06, "epoch": 2.305927342256214, "percentage": 77.01, "elapsed_time": "3:29:18", "remaining_time": "1:02:28"}
403
+ {"current_steps": 403, "total_steps": 522, "loss": 0.4515, "lr": 1.5061528611057917e-06, "epoch": 2.311663479923518, "percentage": 77.2, "elapsed_time": "3:29:47", "remaining_time": "1:01:56"}
404
+ {"current_steps": 404, "total_steps": 522, "loss": 0.4447, "lr": 1.4822726950379207e-06, "epoch": 2.317399617590822, "percentage": 77.39, "elapsed_time": "3:30:18", "remaining_time": "1:01:25"}
405
+ {"current_steps": 405, "total_steps": 522, "loss": 0.4062, "lr": 1.4585503680736756e-06, "epoch": 2.323135755258126, "percentage": 77.59, "elapsed_time": "3:30:50", "remaining_time": "1:00:54"}
406
+ {"current_steps": 406, "total_steps": 522, "loss": 0.3763, "lr": 1.4349869446249664e-06, "epoch": 2.3288718929254304, "percentage": 77.78, "elapsed_time": "3:31:16", "remaining_time": "1:00:21"}
407
+ {"current_steps": 407, "total_steps": 522, "loss": 0.3876, "lr": 1.4115834819737534e-06, "epoch": 2.3346080305927344, "percentage": 77.97, "elapsed_time": "3:31:43", "remaining_time": "0:59:49"}
408
+ {"current_steps": 408, "total_steps": 522, "loss": 0.4269, "lr": 1.3883410302246237e-06, "epoch": 2.3403441682600383, "percentage": 78.16, "elapsed_time": "3:32:09", "remaining_time": "0:59:16"}
409
+ {"current_steps": 409, "total_steps": 522, "loss": 0.3877, "lr": 1.3652606322576606e-06, "epoch": 2.3460803059273423, "percentage": 78.35, "elapsed_time": "3:32:39", "remaining_time": "0:58:45"}
410
+ {"current_steps": 410, "total_steps": 522, "loss": 0.4209, "lr": 1.3423433236816563e-06, "epoch": 2.3518164435946463, "percentage": 78.54, "elapsed_time": "3:33:10", "remaining_time": "0:58:13"}
411
+ {"current_steps": 411, "total_steps": 522, "loss": 0.4125, "lr": 1.3195901327876426e-06, "epoch": 2.35755258126195, "percentage": 78.74, "elapsed_time": "3:33:36", "remaining_time": "0:57:41"}
412
+ {"current_steps": 412, "total_steps": 522, "loss": 0.4581, "lr": 1.2970020805027555e-06, "epoch": 2.363288718929254, "percentage": 78.93, "elapsed_time": "3:34:09", "remaining_time": "0:57:10"}
413
+ {"current_steps": 413, "total_steps": 522, "loss": 0.4004, "lr": 1.2745801803444192e-06, "epoch": 2.369024856596558, "percentage": 79.12, "elapsed_time": "3:34:34", "remaining_time": "0:56:37"}
414
+ {"current_steps": 414, "total_steps": 522, "loss": 0.4178, "lr": 1.25232543837488e-06, "epoch": 2.3747609942638626, "percentage": 79.31, "elapsed_time": "3:35:06", "remaining_time": "0:56:07"}
415
+ {"current_steps": 415, "total_steps": 522, "loss": 0.4433, "lr": 1.2302388531560515e-06, "epoch": 2.3804971319311665, "percentage": 79.5, "elapsed_time": "3:35:40", "remaining_time": "0:55:36"}
416
+ {"current_steps": 416, "total_steps": 522, "loss": 0.4354, "lr": 1.2083214157047257e-06, "epoch": 2.3862332695984705, "percentage": 79.69, "elapsed_time": "3:36:10", "remaining_time": "0:55:04"}
417
+ {"current_steps": 417, "total_steps": 522, "loss": 0.4344, "lr": 1.186574109448091e-06, "epoch": 2.3919694072657744, "percentage": 79.89, "elapsed_time": "3:36:42", "remaining_time": "0:54:33"}
418
+ {"current_steps": 418, "total_steps": 522, "loss": 0.4338, "lr": 1.164997910179615e-06, "epoch": 2.3977055449330784, "percentage": 80.08, "elapsed_time": "3:37:12", "remaining_time": "0:54:02"}
419
+ {"current_steps": 419, "total_steps": 522, "loss": 0.4127, "lr": 1.1435937860152579e-06, "epoch": 2.4034416826003824, "percentage": 80.27, "elapsed_time": "3:37:44", "remaining_time": "0:53:31"}
420
+ {"current_steps": 420, "total_steps": 522, "loss": 0.4587, "lr": 1.1223626973500395e-06, "epoch": 2.4091778202676863, "percentage": 80.46, "elapsed_time": "3:38:17", "remaining_time": "0:53:00"}
421
+ {"current_steps": 421, "total_steps": 522, "loss": 0.3966, "lr": 1.1013055968149343e-06, "epoch": 2.4149139579349903, "percentage": 80.65, "elapsed_time": "3:38:47", "remaining_time": "0:52:29"}
422
+ {"current_steps": 422, "total_steps": 522, "loss": 0.4667, "lr": 1.0804234292341426e-06, "epoch": 2.4206500956022943, "percentage": 80.84, "elapsed_time": "3:39:21", "remaining_time": "0:51:58"}
423
+ {"current_steps": 423, "total_steps": 522, "loss": 0.4016, "lr": 1.0597171315826805e-06, "epoch": 2.4263862332695982, "percentage": 81.03, "elapsed_time": "3:39:51", "remaining_time": "0:51:27"}
424
+ {"current_steps": 424, "total_steps": 522, "loss": 0.3954, "lr": 1.0391876329443534e-06, "epoch": 2.4321223709369026, "percentage": 81.23, "elapsed_time": "3:40:20", "remaining_time": "0:50:55"}
425
+ {"current_steps": 425, "total_steps": 522, "loss": 0.4407, "lr": 1.0188358544700583e-06, "epoch": 2.4378585086042066, "percentage": 81.42, "elapsed_time": "3:40:54", "remaining_time": "0:50:25"}
426
+ {"current_steps": 426, "total_steps": 522, "loss": 0.4145, "lr": 9.986627093364542e-07, "epoch": 2.4435946462715106, "percentage": 81.61, "elapsed_time": "3:41:25", "remaining_time": "0:49:54"}
427
+ {"current_steps": 427, "total_steps": 522, "loss": 0.4705, "lr": 9.786691027049893e-07, "epoch": 2.4493307839388145, "percentage": 81.8, "elapsed_time": "3:42:00", "remaining_time": "0:49:23"}
428
+ {"current_steps": 428, "total_steps": 522, "loss": 0.4221, "lr": 9.588559316812906e-07, "epoch": 2.4550669216061185, "percentage": 81.99, "elapsed_time": "3:42:26", "remaining_time": "0:48:51"}
429
+ {"current_steps": 429, "total_steps": 522, "loss": 0.4639, "lr": 9.392240852749007e-07, "epoch": 2.4608030592734225, "percentage": 82.18, "elapsed_time": "3:42:54", "remaining_time": "0:48:19"}
430
+ {"current_steps": 430, "total_steps": 522, "loss": 0.3925, "lr": 9.197744443594003e-07, "epoch": 2.4665391969407264, "percentage": 82.38, "elapsed_time": "3:43:25", "remaining_time": "0:47:48"}
431
+ {"current_steps": 431, "total_steps": 522, "loss": 0.4398, "lr": 9.005078816328772e-07, "epoch": 2.472275334608031, "percentage": 82.57, "elapsed_time": "3:43:58", "remaining_time": "0:47:17"}
432
+ {"current_steps": 432, "total_steps": 522, "loss": 0.4272, "lr": 8.814252615787661e-07, "epoch": 2.478011472275335, "percentage": 82.76, "elapsed_time": "3:44:33", "remaining_time": "0:46:46"}
433
+ {"current_steps": 433, "total_steps": 522, "loss": 0.4836, "lr": 8.625274404270662e-07, "epoch": 2.4837476099426388, "percentage": 82.95, "elapsed_time": "3:45:01", "remaining_time": "0:46:15"}
434
+ {"current_steps": 434, "total_steps": 522, "loss": 0.4257, "lr": 8.438152661159165e-07, "epoch": 2.4894837476099427, "percentage": 83.14, "elapsed_time": "3:45:33", "remaining_time": "0:45:44"}
435
+ {"current_steps": 435, "total_steps": 522, "loss": 0.4143, "lr": 8.252895782535569e-07, "epoch": 2.4952198852772467, "percentage": 83.33, "elapsed_time": "3:46:03", "remaining_time": "0:45:12"}
436
+ {"current_steps": 436, "total_steps": 522, "loss": 0.4174, "lr": 8.069512080806441e-07, "epoch": 2.5009560229445507, "percentage": 83.52, "elapsed_time": "3:46:39", "remaining_time": "0:44:42"}
437
+ {"current_steps": 437, "total_steps": 522, "loss": 0.4212, "lr": 7.88800978432967e-07, "epoch": 2.5066921606118546, "percentage": 83.72, "elapsed_time": "3:47:12", "remaining_time": "0:44:11"}
438
+ {"current_steps": 438, "total_steps": 522, "loss": 0.428, "lr": 7.708397037045129e-07, "epoch": 2.5124282982791586, "percentage": 83.91, "elapsed_time": "3:47:42", "remaining_time": "0:43:40"}
439
+ {"current_steps": 439, "total_steps": 522, "loss": 0.4209, "lr": 7.530681898109393e-07, "epoch": 2.5181644359464626, "percentage": 84.1, "elapsed_time": "3:48:13", "remaining_time": "0:43:08"}
440
+ {"current_steps": 440, "total_steps": 522, "loss": 0.4821, "lr": 7.35487234153402e-07, "epoch": 2.5239005736137665, "percentage": 84.29, "elapsed_time": "3:48:48", "remaining_time": "0:42:38"}
441
+ {"current_steps": 441, "total_steps": 522, "loss": 0.451, "lr": 7.180976255827809e-07, "epoch": 2.5296367112810705, "percentage": 84.48, "elapsed_time": "3:49:19", "remaining_time": "0:42:07"}
442
+ {"current_steps": 442, "total_steps": 522, "loss": 0.3786, "lr": 7.009001443642843e-07, "epoch": 2.535372848948375, "percentage": 84.67, "elapsed_time": "3:49:55", "remaining_time": "0:41:36"}
443
+ {"current_steps": 443, "total_steps": 522, "loss": 0.4098, "lr": 6.838955621424404e-07, "epoch": 2.541108986615679, "percentage": 84.87, "elapsed_time": "3:50:25", "remaining_time": "0:41:05"}
444
+ {"current_steps": 444, "total_steps": 522, "loss": 0.4139, "lr": 6.67084641906468e-07, "epoch": 2.546845124282983, "percentage": 85.06, "elapsed_time": "3:50:57", "remaining_time": "0:40:34"}
445
+ {"current_steps": 445, "total_steps": 522, "loss": 0.4523, "lr": 6.50468137956049e-07, "epoch": 2.552581261950287, "percentage": 85.25, "elapsed_time": "3:51:30", "remaining_time": "0:40:03"}
446
+ {"current_steps": 446, "total_steps": 522, "loss": 0.4159, "lr": 6.340467958674762e-07, "epoch": 2.5583173996175907, "percentage": 85.44, "elapsed_time": "3:52:00", "remaining_time": "0:39:32"}
447
+ {"current_steps": 447, "total_steps": 522, "loss": 0.405, "lr": 6.178213524602061e-07, "epoch": 2.5640535372848947, "percentage": 85.63, "elapsed_time": "3:52:26", "remaining_time": "0:39:00"}
448
+ {"current_steps": 448, "total_steps": 522, "loss": 0.4377, "lr": 6.017925357637932e-07, "epoch": 2.569789674952199, "percentage": 85.82, "elapsed_time": "3:53:03", "remaining_time": "0:38:29"}
449
+ {"current_steps": 449, "total_steps": 522, "loss": 0.3817, "lr": 5.859610649852249e-07, "epoch": 2.575525812619503, "percentage": 86.02, "elapsed_time": "3:53:30", "remaining_time": "0:37:57"}
450
+ {"current_steps": 450, "total_steps": 522, "loss": 0.3798, "lr": 5.703276504766514e-07, "epoch": 2.581261950286807, "percentage": 86.21, "elapsed_time": "3:54:00", "remaining_time": "0:37:26"}
451
+ {"current_steps": 451, "total_steps": 522, "loss": 0.4653, "lr": 5.548929937035147e-07, "epoch": 2.586998087954111, "percentage": 86.4, "elapsed_time": "3:54:26", "remaining_time": "0:36:54"}
452
+ {"current_steps": 452, "total_steps": 522, "loss": 0.4202, "lr": 5.396577872130676e-07, "epoch": 2.592734225621415, "percentage": 86.59, "elapsed_time": "3:55:01", "remaining_time": "0:36:23"}
453
+ {"current_steps": 453, "total_steps": 522, "loss": 0.441, "lr": 5.246227146033089e-07, "epoch": 2.598470363288719, "percentage": 86.78, "elapsed_time": "3:55:35", "remaining_time": "0:35:53"}
454
+ {"current_steps": 454, "total_steps": 522, "loss": 0.4041, "lr": 5.097884504922996e-07, "epoch": 2.604206500956023, "percentage": 86.97, "elapsed_time": "3:56:06", "remaining_time": "0:35:21"}
455
+ {"current_steps": 455, "total_steps": 522, "loss": 0.4596, "lr": 4.951556604879049e-07, "epoch": 2.609942638623327, "percentage": 87.16, "elapsed_time": "3:56:34", "remaining_time": "0:34:50"}
456
+ {"current_steps": 456, "total_steps": 522, "loss": 0.4258, "lr": 4.807250011579168e-07, "epoch": 2.615678776290631, "percentage": 87.36, "elapsed_time": "3:57:06", "remaining_time": "0:34:19"}
457
+ {"current_steps": 457, "total_steps": 522, "loss": 0.3918, "lr": 4.6649712000060297e-07, "epoch": 2.621414913957935, "percentage": 87.55, "elapsed_time": "3:57:39", "remaining_time": "0:33:48"}
458
+ {"current_steps": 458, "total_steps": 522, "loss": 0.3857, "lr": 4.5247265541564836e-07, "epoch": 2.6271510516252388, "percentage": 87.74, "elapsed_time": "3:58:10", "remaining_time": "0:33:16"}
459
+ {"current_steps": 459, "total_steps": 522, "loss": 0.445, "lr": 4.386522366755169e-07, "epoch": 2.632887189292543, "percentage": 87.93, "elapsed_time": "3:58:43", "remaining_time": "0:32:45"}
460
+ {"current_steps": 460, "total_steps": 522, "loss": 0.4559, "lr": 4.250364838972065e-07, "epoch": 2.638623326959847, "percentage": 88.12, "elapsed_time": "3:59:17", "remaining_time": "0:32:15"}
461
+ {"current_steps": 461, "total_steps": 522, "loss": 0.4201, "lr": 4.116260080144352e-07, "epoch": 2.644359464627151, "percentage": 88.31, "elapsed_time": "3:59:42", "remaining_time": "0:31:43"}
462
+ {"current_steps": 462, "total_steps": 522, "loss": 0.4121, "lr": 3.98421410750221e-07, "epoch": 2.650095602294455, "percentage": 88.51, "elapsed_time": "4:00:13", "remaining_time": "0:31:11"}
463
+ {"current_steps": 463, "total_steps": 522, "loss": 0.4465, "lr": 3.854232845898859e-07, "epoch": 2.655831739961759, "percentage": 88.7, "elapsed_time": "4:00:38", "remaining_time": "0:30:39"}
464
+ {"current_steps": 464, "total_steps": 522, "loss": 0.4201, "lr": 3.7263221275447125e-07, "epoch": 2.661567877629063, "percentage": 88.89, "elapsed_time": "4:01:10", "remaining_time": "0:30:08"}
465
+ {"current_steps": 465, "total_steps": 522, "loss": 0.4099, "lr": 3.60048769174568e-07, "epoch": 2.667304015296367, "percentage": 89.08, "elapsed_time": "4:01:42", "remaining_time": "0:29:37"}
466
+ {"current_steps": 466, "total_steps": 522, "loss": 0.4141, "lr": 3.4767351846456744e-07, "epoch": 2.6730401529636714, "percentage": 89.27, "elapsed_time": "4:02:14", "remaining_time": "0:29:06"}
467
+ {"current_steps": 467, "total_steps": 522, "loss": 0.4354, "lr": 3.355070158973212e-07, "epoch": 2.6787762906309753, "percentage": 89.46, "elapsed_time": "4:02:46", "remaining_time": "0:28:35"}
468
+ {"current_steps": 468, "total_steps": 522, "loss": 0.456, "lr": 3.235498073792342e-07, "epoch": 2.6845124282982793, "percentage": 89.66, "elapsed_time": "4:03:15", "remaining_time": "0:28:04"}
469
+ {"current_steps": 469, "total_steps": 522, "loss": 0.4113, "lr": 3.118024294257621e-07, "epoch": 2.6902485659655833, "percentage": 89.85, "elapsed_time": "4:03:43", "remaining_time": "0:27:32"}
470
+ {"current_steps": 470, "total_steps": 522, "loss": 0.4123, "lr": 3.002654091373453e-07, "epoch": 2.6959847036328872, "percentage": 90.04, "elapsed_time": "4:04:11", "remaining_time": "0:27:01"}
471
+ {"current_steps": 471, "total_steps": 522, "loss": 0.4167, "lr": 2.889392641757527e-07, "epoch": 2.701720841300191, "percentage": 90.23, "elapsed_time": "4:04:45", "remaining_time": "0:26:30"}
472
+ {"current_steps": 472, "total_steps": 522, "loss": 0.4604, "lr": 2.778245027408566e-07, "epoch": 2.707456978967495, "percentage": 90.42, "elapsed_time": "4:05:15", "remaining_time": "0:25:58"}
473
+ {"current_steps": 473, "total_steps": 522, "loss": 0.4442, "lr": 2.669216235478295e-07, "epoch": 2.713193116634799, "percentage": 90.61, "elapsed_time": "4:05:49", "remaining_time": "0:25:27"}
474
+ {"current_steps": 474, "total_steps": 522, "loss": 0.4619, "lr": 2.562311158047692e-07, "epoch": 2.718929254302103, "percentage": 90.8, "elapsed_time": "4:06:22", "remaining_time": "0:24:57"}
475
+ {"current_steps": 475, "total_steps": 522, "loss": 0.4034, "lr": 2.45753459190744e-07, "epoch": 2.724665391969407, "percentage": 91.0, "elapsed_time": "4:06:55", "remaining_time": "0:24:25"}
476
+ {"current_steps": 476, "total_steps": 522, "loss": 0.4522, "lr": 2.354891238342738e-07, "epoch": 2.730401529636711, "percentage": 91.19, "elapsed_time": "4:07:27", "remaining_time": "0:23:54"}
477
+ {"current_steps": 477, "total_steps": 522, "loss": 0.4176, "lr": 2.254385702922318e-07, "epoch": 2.7361376673040154, "percentage": 91.38, "elapsed_time": "4:07:54", "remaining_time": "0:23:23"}
478
+ {"current_steps": 478, "total_steps": 522, "loss": 0.3383, "lr": 2.1560224952918373e-07, "epoch": 2.7418738049713194, "percentage": 91.57, "elapsed_time": "4:08:19", "remaining_time": "0:22:51"}
479
+ {"current_steps": 479, "total_steps": 522, "loss": 0.4271, "lr": 2.0598060289714893e-07, "epoch": 2.7476099426386233, "percentage": 91.76, "elapsed_time": "4:08:43", "remaining_time": "0:22:19"}
480
+ {"current_steps": 480, "total_steps": 522, "loss": 0.4254, "lr": 1.9657406211579966e-07, "epoch": 2.7533460803059273, "percentage": 91.95, "elapsed_time": "4:09:11", "remaining_time": "0:21:48"}
481
+ {"current_steps": 481, "total_steps": 522, "loss": 0.4076, "lr": 1.8738304925308926e-07, "epoch": 2.7590822179732313, "percentage": 92.15, "elapsed_time": "4:09:47", "remaining_time": "0:21:17"}
482
+ {"current_steps": 482, "total_steps": 522, "loss": 0.4472, "lr": 1.7840797670631572e-07, "epoch": 2.7648183556405352, "percentage": 92.34, "elapsed_time": "4:10:21", "remaining_time": "0:20:46"}
483
+ {"current_steps": 483, "total_steps": 522, "loss": 0.4433, "lr": 1.6964924718361364e-07, "epoch": 2.7705544933078396, "percentage": 92.53, "elapsed_time": "4:10:54", "remaining_time": "0:20:15"}
484
+ {"current_steps": 484, "total_steps": 522, "loss": 0.4017, "lr": 1.6110725368589041e-07, "epoch": 2.7762906309751436, "percentage": 92.72, "elapsed_time": "4:11:26", "remaining_time": "0:19:44"}
485
+ {"current_steps": 485, "total_steps": 522, "loss": 0.4079, "lr": 1.5278237948918585e-07, "epoch": 2.7820267686424476, "percentage": 92.91, "elapsed_time": "4:11:59", "remaining_time": "0:19:13"}
486
+ {"current_steps": 486, "total_steps": 522, "loss": 0.425, "lr": 1.4467499812748143e-07, "epoch": 2.7877629063097515, "percentage": 93.1, "elapsed_time": "4:12:32", "remaining_time": "0:18:42"}
487
+ {"current_steps": 487, "total_steps": 522, "loss": 0.4085, "lr": 1.3678547337593494e-07, "epoch": 2.7934990439770555, "percentage": 93.3, "elapsed_time": "4:13:05", "remaining_time": "0:18:11"}
488
+ {"current_steps": 488, "total_steps": 522, "loss": 0.4555, "lr": 1.2911415923456017e-07, "epoch": 2.7992351816443595, "percentage": 93.49, "elapsed_time": "4:13:36", "remaining_time": "0:17:40"}
489
+ {"current_steps": 489, "total_steps": 522, "loss": 0.4062, "lr": 1.2166139991234227e-07, "epoch": 2.8049713193116634, "percentage": 93.68, "elapsed_time": "4:14:06", "remaining_time": "0:17:08"}
490
+ {"current_steps": 490, "total_steps": 522, "loss": 0.428, "lr": 1.1442752981179527e-07, "epoch": 2.8107074569789674, "percentage": 93.87, "elapsed_time": "4:14:37", "remaining_time": "0:16:37"}
491
+ {"current_steps": 491, "total_steps": 522, "loss": 0.4543, "lr": 1.0741287351395402e-07, "epoch": 2.8164435946462714, "percentage": 94.06, "elapsed_time": "4:15:11", "remaining_time": "0:16:06"}
492
+ {"current_steps": 492, "total_steps": 522, "loss": 0.4423, "lr": 1.0061774576381411e-07, "epoch": 2.8221797323135753, "percentage": 94.25, "elapsed_time": "4:15:39", "remaining_time": "0:15:35"}
493
+ {"current_steps": 493, "total_steps": 522, "loss": 0.4695, "lr": 9.404245145620717e-08, "epoch": 2.8279158699808793, "percentage": 94.44, "elapsed_time": "4:16:11", "remaining_time": "0:15:04"}
494
+ {"current_steps": 494, "total_steps": 522, "loss": 0.3969, "lr": 8.768728562211948e-08, "epoch": 2.8336520076481837, "percentage": 94.64, "elapsed_time": "4:16:42", "remaining_time": "0:14:33"}
495
+ {"current_steps": 495, "total_steps": 522, "loss": 0.4468, "lr": 8.155253341545655e-08, "epoch": 2.8393881453154877, "percentage": 94.83, "elapsed_time": "4:17:16", "remaining_time": "0:14:02"}
496
+ {"current_steps": 496, "total_steps": 522, "loss": 0.4395, "lr": 7.563847010024716e-08, "epoch": 2.8451242829827916, "percentage": 95.02, "elapsed_time": "4:17:50", "remaining_time": "0:13:30"}
497
+ {"current_steps": 497, "total_steps": 522, "loss": 0.433, "lr": 6.994536103829164e-08, "epoch": 2.8508604206500956, "percentage": 95.21, "elapsed_time": "4:18:25", "remaining_time": "0:12:59"}
498
+ {"current_steps": 498, "total_steps": 522, "loss": 0.3423, "lr": 6.447346167725688e-08, "epoch": 2.8565965583173996, "percentage": 95.4, "elapsed_time": "4:18:52", "remaining_time": "0:12:28"}
499
+ {"current_steps": 499, "total_steps": 522, "loss": 0.5027, "lr": 5.9223017539213335e-08, "epoch": 2.8623326959847035, "percentage": 95.59, "elapsed_time": "4:19:22", "remaining_time": "0:11:57"}
500
+ {"current_steps": 500, "total_steps": 522, "loss": 0.4022, "lr": 5.4194264209617705e-08, "epoch": 2.8680688336520075, "percentage": 95.79, "elapsed_time": "4:19:57", "remaining_time": "0:11:26"}
501
+ {"current_steps": 501, "total_steps": 522, "loss": 0.4199, "lr": 4.9387427326745287e-08, "epoch": 2.873804971319312, "percentage": 95.98, "elapsed_time": "4:20:26", "remaining_time": "0:10:55"}
502
+ {"current_steps": 502, "total_steps": 522, "loss": 0.4121, "lr": 4.4802722571561374e-08, "epoch": 2.879541108986616, "percentage": 96.17, "elapsed_time": "4:20:50", "remaining_time": "0:10:23"}
503
+ {"current_steps": 503, "total_steps": 522, "loss": 0.4417, "lr": 4.044035565804793e-08, "epoch": 2.88527724665392, "percentage": 96.36, "elapsed_time": "4:21:26", "remaining_time": "0:09:52"}
504
+ {"current_steps": 504, "total_steps": 522, "loss": 0.3664, "lr": 3.6300522323969855e-08, "epoch": 2.891013384321224, "percentage": 96.55, "elapsed_time": "4:21:52", "remaining_time": "0:09:21"}
505
+ {"current_steps": 505, "total_steps": 522, "loss": 0.3832, "lr": 3.2383408322095856e-08, "epoch": 2.8967495219885278, "percentage": 96.74, "elapsed_time": "4:22:23", "remaining_time": "0:08:49"}
506
+ {"current_steps": 506, "total_steps": 522, "loss": 0.509, "lr": 2.8689189411859607e-08, "epoch": 2.9024856596558317, "percentage": 96.93, "elapsed_time": "4:22:55", "remaining_time": "0:08:18"}
507
+ {"current_steps": 507, "total_steps": 522, "loss": 0.4656, "lr": 2.5218031351478268e-08, "epoch": 2.9082217973231357, "percentage": 97.13, "elapsed_time": "4:23:29", "remaining_time": "0:07:47"}
508
+ {"current_steps": 508, "total_steps": 522, "loss": 0.3807, "lr": 2.1970089890509527e-08, "epoch": 2.9139579349904396, "percentage": 97.32, "elapsed_time": "4:24:00", "remaining_time": "0:07:16"}
509
+ {"current_steps": 509, "total_steps": 522, "loss": 0.4028, "lr": 1.8945510762868325e-08, "epoch": 2.9196940726577436, "percentage": 97.51, "elapsed_time": "4:24:37", "remaining_time": "0:06:45"}
510
+ {"current_steps": 510, "total_steps": 522, "loss": 0.4542, "lr": 1.614442968028429e-08, "epoch": 2.9254302103250476, "percentage": 97.7, "elapsed_time": "4:25:02", "remaining_time": "0:06:14"}
511
+ {"current_steps": 511, "total_steps": 522, "loss": 0.4115, "lr": 1.3566972326214956e-08, "epoch": 2.9311663479923515, "percentage": 97.89, "elapsed_time": "4:25:34", "remaining_time": "0:05:43"}
512
+ {"current_steps": 512, "total_steps": 522, "loss": 0.4275, "lr": 1.1213254350202486e-08, "epoch": 2.936902485659656, "percentage": 98.08, "elapsed_time": "4:26:09", "remaining_time": "0:05:11"}
513
+ {"current_steps": 513, "total_steps": 522, "loss": 0.3794, "lr": 9.083381362690603e-09, "epoch": 2.94263862332696, "percentage": 98.28, "elapsed_time": "4:26:36", "remaining_time": "0:04:40"}
514
+ {"current_steps": 514, "total_steps": 522, "loss": 0.4431, "lr": 7.177448930279496e-09, "epoch": 2.948374760994264, "percentage": 98.47, "elapsed_time": "4:27:05", "remaining_time": "0:04:09"}
515
+ {"current_steps": 515, "total_steps": 522, "loss": 0.4194, "lr": 5.495542571443135e-09, "epoch": 2.954110898661568, "percentage": 98.66, "elapsed_time": "4:27:33", "remaining_time": "0:03:38"}
516
+ {"current_steps": 516, "total_steps": 522, "loss": 0.4017, "lr": 4.037737752686788e-09, "epoch": 2.959847036328872, "percentage": 98.85, "elapsed_time": "4:28:06", "remaining_time": "0:03:07"}
517
+ {"current_steps": 517, "total_steps": 522, "loss": 0.3922, "lr": 2.8040998851674996e-09, "epoch": 2.9655831739961758, "percentage": 99.04, "elapsed_time": "4:28:32", "remaining_time": "0:02:35"}
518
+ {"current_steps": 518, "total_steps": 522, "loss": 0.4629, "lr": 1.7946843217514498e-09, "epoch": 2.97131931166348, "percentage": 99.23, "elapsed_time": "4:29:07", "remaining_time": "0:02:04"}
519
+ {"current_steps": 519, "total_steps": 522, "loss": 0.3818, "lr": 1.009536354537044e-09, "epoch": 2.977055449330784, "percentage": 99.43, "elapsed_time": "4:29:39", "remaining_time": "0:01:33"}
520
+ {"current_steps": 520, "total_steps": 522, "loss": 0.444, "lr": 4.486912128182086e-10, "epoch": 2.982791586998088, "percentage": 99.62, "elapsed_time": "4:30:12", "remaining_time": "0:01:02"}
521
+ {"current_steps": 521, "total_steps": 522, "loss": 0.4401, "lr": 1.1217406150676457e-10, "epoch": 2.988527724665392, "percentage": 99.81, "elapsed_time": "4:30:41", "remaining_time": "0:00:31"}
522
+ {"current_steps": 522, "total_steps": 522, "loss": 0.3971, "lr": 0.0, "epoch": 2.994263862332696, "percentage": 100.0, "elapsed_time": "4:31:11", "remaining_time": "0:00:00"}
523
+ {"current_steps": 522, "total_steps": 522, "epoch": 2.994263862332696, "percentage": 100.0, "elapsed_time": "4:32:36", "remaining_time": "0:00:00"}