sedrickkeh commited on
Commit
2e8715b
·
verified ·
1 Parent(s): 7266d06

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 sha256:63369b4c9920c058fa1fb97e31c2a4e134d55aa754748ff280cbb0a73bc7802a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3dc59e3a8513ae17fa16125d20bebd621185d2fcc5940707da9f239699c99d8
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:e02fe7409ac20dba0e6b6d33ed3875c768f6d2f6b80d30c8c798046f3e199e9b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79829bc6e5015cc4c5de5975b6d061becd14055137fc7e492a20bc3e87526ecd
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e06ff5c3db6321b86182641bb7064b92f72f8b4e3c85a198e3f01180abfa25c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7d8967f03d5729df50f2d47556e9fce4dbb14b773314a0568c8ad2666430f2
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:177ffe80716f86176cc7cdcb7e8d4aa4ff0911ca76edc30a0394868f8a89ee60
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde52134b9879bd78ea812e43300bfe092f1e343db49566a51ce9f7394053589
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -356,3 +356,168 @@
356
  {"current_steps": 356, "total_steps": 522, "loss": 0.3104, "lr": 1.1141712319366835e-05, "epoch": 2.0420650095602295, "percentage": 68.2, "elapsed_time": "1:36:59", "remaining_time": "0:45:13"}
357
  {"current_steps": 357, "total_steps": 522, "loss": 0.3355, "lr": 1.1021799431383969e-05, "epoch": 2.0478011472275335, "percentage": 68.39, "elapsed_time": "1:37:18", "remaining_time": "0:44:58"}
358
  {"current_steps": 358, "total_steps": 522, "loss": 0.3181, "lr": 1.0902289391890232e-05, "epoch": 2.0535372848948374, "percentage": 68.58, "elapsed_time": "1:37:38", "remaining_time": "0:44:43"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
356
  {"current_steps": 356, "total_steps": 522, "loss": 0.3104, "lr": 1.1141712319366835e-05, "epoch": 2.0420650095602295, "percentage": 68.2, "elapsed_time": "1:36:59", "remaining_time": "0:45:13"}
357
  {"current_steps": 357, "total_steps": 522, "loss": 0.3355, "lr": 1.1021799431383969e-05, "epoch": 2.0478011472275335, "percentage": 68.39, "elapsed_time": "1:37:18", "remaining_time": "0:44:58"}
358
  {"current_steps": 358, "total_steps": 522, "loss": 0.3181, "lr": 1.0902289391890232e-05, "epoch": 2.0535372848948374, "percentage": 68.58, "elapsed_time": "1:37:38", "remaining_time": "0:44:43"}
359
+ {"current_steps": 359, "total_steps": 522, "loss": 0.255, "lr": 1.0783187563256218e-05, "epoch": 2.0592734225621414, "percentage": 68.77, "elapsed_time": "1:37:55", "remaining_time": "0:44:27"}
360
+ {"current_steps": 360, "total_steps": 522, "loss": 0.3179, "lr": 1.0664499289536283e-05, "epoch": 2.0650095602294454, "percentage": 68.97, "elapsed_time": "1:38:11", "remaining_time": "0:44:11"}
361
+ {"current_steps": 361, "total_steps": 522, "loss": 0.2607, "lr": 1.0546229896228692e-05, "epoch": 2.0707456978967493, "percentage": 69.16, "elapsed_time": "1:38:25", "remaining_time": "0:43:53"}
362
+ {"current_steps": 362, "total_steps": 522, "loss": 0.2878, "lr": 1.0428384690036749e-05, "epoch": 2.0764818355640537, "percentage": 69.35, "elapsed_time": "1:38:43", "remaining_time": "0:43:38"}
363
+ {"current_steps": 363, "total_steps": 522, "loss": 0.3607, "lr": 1.0310968958630601e-05, "epoch": 2.0822179732313577, "percentage": 69.54, "elapsed_time": "1:38:59", "remaining_time": "0:43:21"}
364
+ {"current_steps": 364, "total_steps": 522, "loss": 0.2914, "lr": 1.0193987970410046e-05, "epoch": 2.0879541108986617, "percentage": 69.73, "elapsed_time": "1:39:10", "remaining_time": "0:43:03"}
365
+ {"current_steps": 365, "total_steps": 522, "loss": 0.3372, "lr": 1.0077446974268098e-05, "epoch": 2.0936902485659656, "percentage": 69.92, "elapsed_time": "1:39:28", "remaining_time": "0:42:47"}
366
+ {"current_steps": 366, "total_steps": 522, "loss": 0.311, "lr": 9.961351199355513e-06, "epoch": 2.0994263862332696, "percentage": 70.11, "elapsed_time": "1:39:42", "remaining_time": "0:42:29"}
367
+ {"current_steps": 367, "total_steps": 522, "loss": 0.3563, "lr": 9.84570585484614e-06, "epoch": 2.1051625239005736, "percentage": 70.31, "elapsed_time": "1:40:01", "remaining_time": "0:42:14"}
368
+ {"current_steps": 368, "total_steps": 522, "loss": 0.2871, "lr": 9.730516129703158e-06, "epoch": 2.1108986615678775, "percentage": 70.5, "elapsed_time": "1:40:16", "remaining_time": "0:41:57"}
369
+ {"current_steps": 369, "total_steps": 522, "loss": 0.3125, "lr": 9.615787192446304e-06, "epoch": 2.1166347992351815, "percentage": 70.69, "elapsed_time": "1:40:31", "remaining_time": "0:41:40"}
370
+ {"current_steps": 370, "total_steps": 522, "loss": 0.3254, "lr": 9.50152419091992e-06, "epoch": 2.1223709369024855, "percentage": 70.88, "elapsed_time": "1:40:48", "remaining_time": "0:41:24"}
371
+ {"current_steps": 371, "total_steps": 522, "loss": 0.2669, "lr": 9.38773225206199e-06, "epoch": 2.12810707456979, "percentage": 71.07, "elapsed_time": "1:41:00", "remaining_time": "0:41:06"}
372
+ {"current_steps": 372, "total_steps": 522, "loss": 0.334, "lr": 9.274416481674084e-06, "epoch": 2.133843212237094, "percentage": 71.26, "elapsed_time": "1:41:15", "remaining_time": "0:40:49"}
373
+ {"current_steps": 373, "total_steps": 522, "loss": 0.2568, "lr": 9.161581964192298e-06, "epoch": 2.139579349904398, "percentage": 71.46, "elapsed_time": "1:41:30", "remaining_time": "0:40:32"}
374
+ {"current_steps": 374, "total_steps": 522, "loss": 0.4001, "lr": 9.049233762459057e-06, "epoch": 2.1453154875717018, "percentage": 71.65, "elapsed_time": "1:41:49", "remaining_time": "0:40:17"}
375
+ {"current_steps": 375, "total_steps": 522, "loss": 0.2447, "lr": 8.937376917496012e-06, "epoch": 2.1510516252390057, "percentage": 71.84, "elapsed_time": "1:42:01", "remaining_time": "0:39:59"}
376
+ {"current_steps": 376, "total_steps": 522, "loss": 0.3157, "lr": 8.826016448277795e-06, "epoch": 2.1567877629063097, "percentage": 72.03, "elapsed_time": "1:42:17", "remaining_time": "0:39:43"}
377
+ {"current_steps": 377, "total_steps": 522, "loss": 0.2992, "lr": 8.715157351506864e-06, "epoch": 2.1625239005736137, "percentage": 72.22, "elapsed_time": "1:42:36", "remaining_time": "0:39:27"}
378
+ {"current_steps": 378, "total_steps": 522, "loss": 0.3132, "lr": 8.604804601389271e-06, "epoch": 2.1682600382409176, "percentage": 72.41, "elapsed_time": "1:42:56", "remaining_time": "0:39:12"}
379
+ {"current_steps": 379, "total_steps": 522, "loss": 0.2712, "lr": 8.494963149411489e-06, "epoch": 2.173996175908222, "percentage": 72.61, "elapsed_time": "1:43:05", "remaining_time": "0:38:53"}
380
+ {"current_steps": 380, "total_steps": 522, "loss": 0.2803, "lr": 8.385637924118224e-06, "epoch": 2.179732313575526, "percentage": 72.8, "elapsed_time": "1:43:21", "remaining_time": "0:38:37"}
381
+ {"current_steps": 381, "total_steps": 522, "loss": 0.2937, "lr": 8.276833830891312e-06, "epoch": 2.18546845124283, "percentage": 72.99, "elapsed_time": "1:43:35", "remaining_time": "0:38:20"}
382
+ {"current_steps": 382, "total_steps": 522, "loss": 0.3159, "lr": 8.168555751729552e-06, "epoch": 2.191204588910134, "percentage": 73.18, "elapsed_time": "1:43:50", "remaining_time": "0:38:03"}
383
+ {"current_steps": 383, "total_steps": 522, "loss": 0.3159, "lr": 8.060808545029727e-06, "epoch": 2.196940726577438, "percentage": 73.37, "elapsed_time": "1:44:07", "remaining_time": "0:37:47"}
384
+ {"current_steps": 384, "total_steps": 522, "loss": 0.3051, "lr": 7.95359704536854e-06, "epoch": 2.202676864244742, "percentage": 73.56, "elapsed_time": "1:44:24", "remaining_time": "0:37:31"}
385
+ {"current_steps": 385, "total_steps": 522, "loss": 0.3082, "lr": 7.846926063285745e-06, "epoch": 2.208413001912046, "percentage": 73.75, "elapsed_time": "1:44:42", "remaining_time": "0:37:15"}
386
+ {"current_steps": 386, "total_steps": 522, "loss": 0.3044, "lr": 7.740800385068256e-06, "epoch": 2.21414913957935, "percentage": 73.95, "elapsed_time": "1:44:57", "remaining_time": "0:36:58"}
387
+ {"current_steps": 387, "total_steps": 522, "loss": 0.3192, "lr": 7.63522477253542e-06, "epoch": 2.2198852772466537, "percentage": 74.14, "elapsed_time": "1:45:16", "remaining_time": "0:36:43"}
388
+ {"current_steps": 388, "total_steps": 522, "loss": 0.3374, "lr": 7.530203962825331e-06, "epoch": 2.2256214149139577, "percentage": 74.33, "elapsed_time": "1:45:31", "remaining_time": "0:36:26"}
389
+ {"current_steps": 389, "total_steps": 522, "loss": 0.3056, "lr": 7.425742668182308e-06, "epoch": 2.231357552581262, "percentage": 74.52, "elapsed_time": "1:45:48", "remaining_time": "0:36:10"}
390
+ {"current_steps": 390, "total_steps": 522, "loss": 0.2674, "lr": 7.3218455757454125e-06, "epoch": 2.237093690248566, "percentage": 74.71, "elapsed_time": "1:46:02", "remaining_time": "0:35:53"}
391
+ {"current_steps": 391, "total_steps": 522, "loss": 0.2843, "lr": 7.218517347338194e-06, "epoch": 2.24282982791587, "percentage": 74.9, "elapsed_time": "1:46:18", "remaining_time": "0:35:37"}
392
+ {"current_steps": 392, "total_steps": 522, "loss": 0.3234, "lr": 7.115762619259459e-06, "epoch": 2.248565965583174, "percentage": 75.1, "elapsed_time": "1:46:38", "remaining_time": "0:35:21"}
393
+ {"current_steps": 393, "total_steps": 522, "loss": 0.3573, "lr": 7.013586002075297e-06, "epoch": 2.254302103250478, "percentage": 75.29, "elapsed_time": "1:46:55", "remaining_time": "0:35:05"}
394
+ {"current_steps": 394, "total_steps": 522, "loss": 0.3053, "lr": 6.911992080412153e-06, "epoch": 2.260038240917782, "percentage": 75.48, "elapsed_time": "1:47:09", "remaining_time": "0:34:48"}
395
+ {"current_steps": 395, "total_steps": 522, "loss": 0.3411, "lr": 6.810985412751159e-06, "epoch": 2.265774378585086, "percentage": 75.67, "elapsed_time": "1:47:24", "remaining_time": "0:34:31"}
396
+ {"current_steps": 396, "total_steps": 522, "loss": 0.2988, "lr": 6.710570531223568e-06, "epoch": 2.27151051625239, "percentage": 75.86, "elapsed_time": "1:47:40", "remaining_time": "0:34:15"}
397
+ {"current_steps": 397, "total_steps": 522, "loss": 0.2987, "lr": 6.610751941407423e-06, "epoch": 2.2772466539196943, "percentage": 76.05, "elapsed_time": "1:47:51", "remaining_time": "0:33:57"}
398
+ {"current_steps": 398, "total_steps": 522, "loss": 0.3126, "lr": 6.511534122125385e-06, "epoch": 2.2829827915869982, "percentage": 76.25, "elapsed_time": "1:48:05", "remaining_time": "0:33:40"}
399
+ {"current_steps": 399, "total_steps": 522, "loss": 0.3179, "lr": 6.412921525243747e-06, "epoch": 2.288718929254302, "percentage": 76.44, "elapsed_time": "1:48:22", "remaining_time": "0:33:24"}
400
+ {"current_steps": 400, "total_steps": 522, "loss": 0.3213, "lr": 6.314918575472724e-06, "epoch": 2.294455066921606, "percentage": 76.63, "elapsed_time": "1:48:38", "remaining_time": "0:33:07"}
401
+ {"current_steps": 401, "total_steps": 522, "loss": 0.3267, "lr": 6.2175296701678765e-06, "epoch": 2.30019120458891, "percentage": 76.82, "elapsed_time": "1:48:53", "remaining_time": "0:32:51"}
402
+ {"current_steps": 402, "total_steps": 522, "loss": 0.3022, "lr": 6.120759179132825e-06, "epoch": 2.305927342256214, "percentage": 77.01, "elapsed_time": "1:49:11", "remaining_time": "0:32:35"}
403
+ {"current_steps": 403, "total_steps": 522, "loss": 0.3331, "lr": 6.024611444423167e-06, "epoch": 2.311663479923518, "percentage": 77.2, "elapsed_time": "1:49:26", "remaining_time": "0:32:19"}
404
+ {"current_steps": 404, "total_steps": 522, "loss": 0.3235, "lr": 5.929090780151683e-06, "epoch": 2.317399617590822, "percentage": 77.39, "elapsed_time": "1:49:42", "remaining_time": "0:32:02"}
405
+ {"current_steps": 405, "total_steps": 522, "loss": 0.2911, "lr": 5.8342014722947025e-06, "epoch": 2.323135755258126, "percentage": 77.59, "elapsed_time": "1:49:59", "remaining_time": "0:31:46"}
406
+ {"current_steps": 406, "total_steps": 522, "loss": 0.2625, "lr": 5.739947778499866e-06, "epoch": 2.3288718929254304, "percentage": 77.78, "elapsed_time": "1:50:12", "remaining_time": "0:31:29"}
407
+ {"current_steps": 407, "total_steps": 522, "loss": 0.2686, "lr": 5.6463339278950135e-06, "epoch": 2.3346080305927344, "percentage": 77.97, "elapsed_time": "1:50:26", "remaining_time": "0:31:12"}
408
+ {"current_steps": 408, "total_steps": 522, "loss": 0.3078, "lr": 5.553364120898495e-06, "epoch": 2.3403441682600383, "percentage": 78.16, "elapsed_time": "1:50:38", "remaining_time": "0:30:54"}
409
+ {"current_steps": 409, "total_steps": 522, "loss": 0.2669, "lr": 5.461042529030643e-06, "epoch": 2.3460803059273423, "percentage": 78.35, "elapsed_time": "1:50:53", "remaining_time": "0:30:38"}
410
+ {"current_steps": 410, "total_steps": 522, "loss": 0.3035, "lr": 5.369373294726625e-06, "epoch": 2.3518164435946463, "percentage": 78.54, "elapsed_time": "1:51:09", "remaining_time": "0:30:21"}
411
+ {"current_steps": 411, "total_steps": 522, "loss": 0.2959, "lr": 5.2783605311505705e-06, "epoch": 2.35755258126195, "percentage": 78.74, "elapsed_time": "1:51:23", "remaining_time": "0:30:04"}
412
+ {"current_steps": 412, "total_steps": 522, "loss": 0.3271, "lr": 5.188008322011022e-06, "epoch": 2.363288718929254, "percentage": 78.93, "elapsed_time": "1:51:40", "remaining_time": "0:29:48"}
413
+ {"current_steps": 413, "total_steps": 522, "loss": 0.2821, "lr": 5.098320721377677e-06, "epoch": 2.369024856596558, "percentage": 79.12, "elapsed_time": "1:51:52", "remaining_time": "0:29:31"}
414
+ {"current_steps": 414, "total_steps": 522, "loss": 0.2978, "lr": 5.00930175349952e-06, "epoch": 2.3747609942638626, "percentage": 79.31, "elapsed_time": "1:52:09", "remaining_time": "0:29:15"}
415
+ {"current_steps": 415, "total_steps": 522, "loss": 0.3298, "lr": 4.920955412624206e-06, "epoch": 2.3804971319311665, "percentage": 79.5, "elapsed_time": "1:52:27", "remaining_time": "0:28:59"}
416
+ {"current_steps": 416, "total_steps": 522, "loss": 0.3205, "lr": 4.833285662818903e-06, "epoch": 2.3862332695984705, "percentage": 79.69, "elapsed_time": "1:52:42", "remaining_time": "0:28:43"}
417
+ {"current_steps": 417, "total_steps": 522, "loss": 0.3073, "lr": 4.746296437792364e-06, "epoch": 2.3919694072657744, "percentage": 79.89, "elapsed_time": "1:52:59", "remaining_time": "0:28:27"}
418
+ {"current_steps": 418, "total_steps": 522, "loss": 0.3132, "lr": 4.65999164071846e-06, "epoch": 2.3977055449330784, "percentage": 80.08, "elapsed_time": "1:53:15", "remaining_time": "0:28:10"}
419
+ {"current_steps": 419, "total_steps": 522, "loss": 0.2999, "lr": 4.5743751440610315e-06, "epoch": 2.4034416826003824, "percentage": 80.27, "elapsed_time": "1:53:31", "remaining_time": "0:27:54"}
420
+ {"current_steps": 420, "total_steps": 522, "loss": 0.3396, "lr": 4.489450789400158e-06, "epoch": 2.4091778202676863, "percentage": 80.46, "elapsed_time": "1:53:49", "remaining_time": "0:27:38"}
421
+ {"current_steps": 421, "total_steps": 522, "loss": 0.2785, "lr": 4.405222387259737e-06, "epoch": 2.4149139579349903, "percentage": 80.65, "elapsed_time": "1:54:04", "remaining_time": "0:27:22"}
422
+ {"current_steps": 422, "total_steps": 522, "loss": 0.3396, "lr": 4.32169371693657e-06, "epoch": 2.4206500956022943, "percentage": 80.84, "elapsed_time": "1:54:22", "remaining_time": "0:27:06"}
423
+ {"current_steps": 423, "total_steps": 522, "loss": 0.2888, "lr": 4.238868526330722e-06, "epoch": 2.4263862332695982, "percentage": 81.03, "elapsed_time": "1:54:37", "remaining_time": "0:26:49"}
424
+ {"current_steps": 424, "total_steps": 522, "loss": 0.2814, "lr": 4.156750531777414e-06, "epoch": 2.4321223709369026, "percentage": 81.23, "elapsed_time": "1:54:51", "remaining_time": "0:26:32"}
425
+ {"current_steps": 425, "total_steps": 522, "loss": 0.3166, "lr": 4.075343417880233e-06, "epoch": 2.4378585086042066, "percentage": 81.42, "elapsed_time": "1:55:10", "remaining_time": "0:26:17"}
426
+ {"current_steps": 426, "total_steps": 522, "loss": 0.2981, "lr": 3.994650837345817e-06, "epoch": 2.4435946462715106, "percentage": 81.61, "elapsed_time": "1:55:26", "remaining_time": "0:26:00"}
427
+ {"current_steps": 427, "total_steps": 522, "loss": 0.3439, "lr": 3.914676410819957e-06, "epoch": 2.4493307839388145, "percentage": 81.8, "elapsed_time": "1:55:44", "remaining_time": "0:25:45"}
428
+ {"current_steps": 428, "total_steps": 522, "loss": 0.3026, "lr": 3.835423726725162e-06, "epoch": 2.4550669216061185, "percentage": 81.99, "elapsed_time": "1:55:56", "remaining_time": "0:25:27"}
429
+ {"current_steps": 429, "total_steps": 522, "loss": 0.3366, "lr": 3.7568963410996028e-06, "epoch": 2.4608030592734225, "percentage": 82.18, "elapsed_time": "1:56:11", "remaining_time": "0:25:11"}
430
+ {"current_steps": 430, "total_steps": 522, "loss": 0.2838, "lr": 3.6790977774376013e-06, "epoch": 2.4665391969407264, "percentage": 82.38, "elapsed_time": "1:56:27", "remaining_time": "0:24:54"}
431
+ {"current_steps": 431, "total_steps": 522, "loss": 0.3133, "lr": 3.6020315265315087e-06, "epoch": 2.472275334608031, "percentage": 82.57, "elapsed_time": "1:56:44", "remaining_time": "0:24:38"}
432
+ {"current_steps": 432, "total_steps": 522, "loss": 0.3132, "lr": 3.5257010463150642e-06, "epoch": 2.478011472275335, "percentage": 82.76, "elapsed_time": "1:57:04", "remaining_time": "0:24:23"}
433
+ {"current_steps": 433, "total_steps": 522, "loss": 0.3567, "lr": 3.4501097617082648e-06, "epoch": 2.4837476099426388, "percentage": 82.95, "elapsed_time": "1:57:17", "remaining_time": "0:24:06"}
434
+ {"current_steps": 434, "total_steps": 522, "loss": 0.3047, "lr": 3.375261064463666e-06, "epoch": 2.4894837476099427, "percentage": 83.14, "elapsed_time": "1:57:34", "remaining_time": "0:23:50"}
435
+ {"current_steps": 435, "total_steps": 522, "loss": 0.3054, "lr": 3.3011583130142277e-06, "epoch": 2.4952198852772467, "percentage": 83.33, "elapsed_time": "1:57:50", "remaining_time": "0:23:34"}
436
+ {"current_steps": 436, "total_steps": 522, "loss": 0.3002, "lr": 3.2278048323225764e-06, "epoch": 2.5009560229445507, "percentage": 83.52, "elapsed_time": "1:58:10", "remaining_time": "0:23:18"}
437
+ {"current_steps": 437, "total_steps": 522, "loss": 0.3145, "lr": 3.155203913731868e-06, "epoch": 2.5066921606118546, "percentage": 83.72, "elapsed_time": "1:58:27", "remaining_time": "0:23:02"}
438
+ {"current_steps": 438, "total_steps": 522, "loss": 0.316, "lr": 3.0833588148180516e-06, "epoch": 2.5124282982791586, "percentage": 83.91, "elapsed_time": "1:58:42", "remaining_time": "0:22:45"}
439
+ {"current_steps": 439, "total_steps": 522, "loss": 0.3052, "lr": 3.0122727592437574e-06, "epoch": 2.5181644359464626, "percentage": 84.1, "elapsed_time": "1:58:57", "remaining_time": "0:22:29"}
440
+ {"current_steps": 440, "total_steps": 522, "loss": 0.3584, "lr": 2.941948936613608e-06, "epoch": 2.5239005736137665, "percentage": 84.29, "elapsed_time": "1:59:16", "remaining_time": "0:22:13"}
441
+ {"current_steps": 441, "total_steps": 522, "loss": 0.3323, "lr": 2.8723905023311237e-06, "epoch": 2.5296367112810705, "percentage": 84.48, "elapsed_time": "1:59:33", "remaining_time": "0:21:57"}
442
+ {"current_steps": 442, "total_steps": 522, "loss": 0.27, "lr": 2.8036005774571373e-06, "epoch": 2.535372848948375, "percentage": 84.67, "elapsed_time": "1:59:52", "remaining_time": "0:21:41"}
443
+ {"current_steps": 443, "total_steps": 522, "loss": 0.2927, "lr": 2.7355822485697615e-06, "epoch": 2.541108986615679, "percentage": 84.87, "elapsed_time": "2:00:08", "remaining_time": "0:21:25"}
444
+ {"current_steps": 444, "total_steps": 522, "loss": 0.2917, "lr": 2.668338567625872e-06, "epoch": 2.546845124282983, "percentage": 85.06, "elapsed_time": "2:00:25", "remaining_time": "0:21:09"}
445
+ {"current_steps": 445, "total_steps": 522, "loss": 0.3305, "lr": 2.601872551824196e-06, "epoch": 2.552581261950287, "percentage": 85.25, "elapsed_time": "2:00:42", "remaining_time": "0:20:53"}
446
+ {"current_steps": 446, "total_steps": 522, "loss": 0.3036, "lr": 2.536187183469905e-06, "epoch": 2.5583173996175907, "percentage": 85.44, "elapsed_time": "2:00:57", "remaining_time": "0:20:36"}
447
+ {"current_steps": 447, "total_steps": 522, "loss": 0.296, "lr": 2.4712854098408245e-06, "epoch": 2.5640535372848947, "percentage": 85.63, "elapsed_time": "2:01:11", "remaining_time": "0:20:20"}
448
+ {"current_steps": 448, "total_steps": 522, "loss": 0.3165, "lr": 2.407170143055173e-06, "epoch": 2.569789674952199, "percentage": 85.82, "elapsed_time": "2:01:31", "remaining_time": "0:20:04"}
449
+ {"current_steps": 449, "total_steps": 522, "loss": 0.2685, "lr": 2.3438442599408995e-06, "epoch": 2.575525812619503, "percentage": 86.02, "elapsed_time": "2:01:43", "remaining_time": "0:19:47"}
450
+ {"current_steps": 450, "total_steps": 522, "loss": 0.2677, "lr": 2.2813106019066055e-06, "epoch": 2.581261950286807, "percentage": 86.21, "elapsed_time": "2:01:58", "remaining_time": "0:19:30"}
451
+ {"current_steps": 451, "total_steps": 522, "loss": 0.3382, "lr": 2.219571974814059e-06, "epoch": 2.586998087954111, "percentage": 86.4, "elapsed_time": "2:02:12", "remaining_time": "0:19:14"}
452
+ {"current_steps": 452, "total_steps": 522, "loss": 0.2952, "lr": 2.1586311488522705e-06, "epoch": 2.592734225621415, "percentage": 86.59, "elapsed_time": "2:02:30", "remaining_time": "0:18:58"}
453
+ {"current_steps": 453, "total_steps": 522, "loss": 0.322, "lr": 2.0984908584132356e-06, "epoch": 2.598470363288719, "percentage": 86.78, "elapsed_time": "2:02:48", "remaining_time": "0:18:42"}
454
+ {"current_steps": 454, "total_steps": 522, "loss": 0.2895, "lr": 2.0391538019691983e-06, "epoch": 2.604206500956023, "percentage": 86.97, "elapsed_time": "2:03:04", "remaining_time": "0:18:26"}
455
+ {"current_steps": 455, "total_steps": 522, "loss": 0.3372, "lr": 1.9806226419516195e-06, "epoch": 2.609942638623327, "percentage": 87.16, "elapsed_time": "2:03:19", "remaining_time": "0:18:09"}
456
+ {"current_steps": 456, "total_steps": 522, "loss": 0.2956, "lr": 1.922900004631667e-06, "epoch": 2.615678776290631, "percentage": 87.36, "elapsed_time": "2:03:35", "remaining_time": "0:17:53"}
457
+ {"current_steps": 457, "total_steps": 522, "loss": 0.281, "lr": 1.8659884800024119e-06, "epoch": 2.621414913957935, "percentage": 87.55, "elapsed_time": "2:03:53", "remaining_time": "0:17:37"}
458
+ {"current_steps": 458, "total_steps": 522, "loss": 0.2779, "lr": 1.8098906216625934e-06, "epoch": 2.6271510516252388, "percentage": 87.74, "elapsed_time": "2:04:09", "remaining_time": "0:17:20"}
459
+ {"current_steps": 459, "total_steps": 522, "loss": 0.3322, "lr": 1.7546089467020677e-06, "epoch": 2.632887189292543, "percentage": 87.93, "elapsed_time": "2:04:26", "remaining_time": "0:17:04"}
460
+ {"current_steps": 460, "total_steps": 522, "loss": 0.333, "lr": 1.700145935588826e-06, "epoch": 2.638623326959847, "percentage": 88.12, "elapsed_time": "2:04:44", "remaining_time": "0:16:48"}
461
+ {"current_steps": 461, "total_steps": 522, "loss": 0.3012, "lr": 1.6465040320577408e-06, "epoch": 2.644359464627151, "percentage": 88.31, "elapsed_time": "2:04:56", "remaining_time": "0:16:31"}
462
+ {"current_steps": 462, "total_steps": 522, "loss": 0.2875, "lr": 1.593685643000884e-06, "epoch": 2.650095602294455, "percentage": 88.51, "elapsed_time": "2:05:12", "remaining_time": "0:16:15"}
463
+ {"current_steps": 463, "total_steps": 522, "loss": 0.3258, "lr": 1.5416931383595436e-06, "epoch": 2.655831739961759, "percentage": 88.7, "elapsed_time": "2:05:25", "remaining_time": "0:15:58"}
464
+ {"current_steps": 464, "total_steps": 522, "loss": 0.3027, "lr": 1.490528851017885e-06, "epoch": 2.661567877629063, "percentage": 88.89, "elapsed_time": "2:05:41", "remaining_time": "0:15:42"}
465
+ {"current_steps": 465, "total_steps": 522, "loss": 0.2916, "lr": 1.440195076698272e-06, "epoch": 2.667304015296367, "percentage": 89.08, "elapsed_time": "2:05:58", "remaining_time": "0:15:26"}
466
+ {"current_steps": 466, "total_steps": 522, "loss": 0.2863, "lr": 1.3906940738582698e-06, "epoch": 2.6730401529636714, "percentage": 89.27, "elapsed_time": "2:06:14", "remaining_time": "0:15:10"}
467
+ {"current_steps": 467, "total_steps": 522, "loss": 0.3104, "lr": 1.3420280635892847e-06, "epoch": 2.6787762906309753, "percentage": 89.46, "elapsed_time": "2:06:31", "remaining_time": "0:14:54"}
468
+ {"current_steps": 468, "total_steps": 522, "loss": 0.3303, "lr": 1.2941992295169369e-06, "epoch": 2.6845124282982793, "percentage": 89.66, "elapsed_time": "2:06:45", "remaining_time": "0:14:37"}
469
+ {"current_steps": 469, "total_steps": 522, "loss": 0.2923, "lr": 1.2472097177030485e-06, "epoch": 2.6902485659655833, "percentage": 89.85, "elapsed_time": "2:07:00", "remaining_time": "0:14:21"}
470
+ {"current_steps": 470, "total_steps": 522, "loss": 0.3006, "lr": 1.2010616365493811e-06, "epoch": 2.6959847036328872, "percentage": 90.04, "elapsed_time": "2:07:14", "remaining_time": "0:14:04"}
471
+ {"current_steps": 471, "total_steps": 522, "loss": 0.2936, "lr": 1.1557570567030108e-06, "epoch": 2.701720841300191, "percentage": 90.23, "elapsed_time": "2:07:32", "remaining_time": "0:13:48"}
472
+ {"current_steps": 472, "total_steps": 522, "loss": 0.3341, "lr": 1.1112980109634263e-06, "epoch": 2.707456978967495, "percentage": 90.42, "elapsed_time": "2:07:47", "remaining_time": "0:13:32"}
473
+ {"current_steps": 473, "total_steps": 522, "loss": 0.318, "lr": 1.067686494191318e-06, "epoch": 2.713193116634799, "percentage": 90.61, "elapsed_time": "2:08:05", "remaining_time": "0:13:16"}
474
+ {"current_steps": 474, "total_steps": 522, "loss": 0.3299, "lr": 1.0249244632190769e-06, "epoch": 2.718929254302103, "percentage": 90.8, "elapsed_time": "2:08:22", "remaining_time": "0:13:00"}
475
+ {"current_steps": 475, "total_steps": 522, "loss": 0.2836, "lr": 9.83013836762976e-07, "epoch": 2.724665391969407, "percentage": 91.0, "elapsed_time": "2:08:39", "remaining_time": "0:12:43"}
476
+ {"current_steps": 476, "total_steps": 522, "loss": 0.3298, "lr": 9.419564953370952e-07, "epoch": 2.730401529636711, "percentage": 91.19, "elapsed_time": "2:08:56", "remaining_time": "0:12:27"}
477
+ {"current_steps": 477, "total_steps": 522, "loss": 0.3033, "lr": 9.017542811689272e-07, "epoch": 2.7361376673040154, "percentage": 91.38, "elapsed_time": "2:09:09", "remaining_time": "0:12:11"}
478
+ {"current_steps": 478, "total_steps": 522, "loss": 0.2356, "lr": 8.624089981167349e-07, "epoch": 2.7418738049713194, "percentage": 91.57, "elapsed_time": "2:09:22", "remaining_time": "0:11:54"}
479
+ {"current_steps": 479, "total_steps": 522, "loss": 0.3049, "lr": 8.239224115885957e-07, "epoch": 2.7476099426386233, "percentage": 91.76, "elapsed_time": "2:09:33", "remaining_time": "0:11:37"}
480
+ {"current_steps": 480, "total_steps": 522, "loss": 0.3063, "lr": 7.862962484631986e-07, "epoch": 2.7533460803059273, "percentage": 91.95, "elapsed_time": "2:09:46", "remaining_time": "0:11:21"}
481
+ {"current_steps": 481, "total_steps": 522, "loss": 0.2886, "lr": 7.49532197012357e-07, "epoch": 2.7590822179732313, "percentage": 92.15, "elapsed_time": "2:10:06", "remaining_time": "0:11:05"}
482
+ {"current_steps": 482, "total_steps": 522, "loss": 0.327, "lr": 7.136319068252629e-07, "epoch": 2.7648183556405352, "percentage": 92.34, "elapsed_time": "2:10:24", "remaining_time": "0:10:49"}
483
+ {"current_steps": 483, "total_steps": 522, "loss": 0.3239, "lr": 6.785969887344546e-07, "epoch": 2.7705544933078396, "percentage": 92.53, "elapsed_time": "2:10:41", "remaining_time": "0:10:33"}
484
+ {"current_steps": 484, "total_steps": 522, "loss": 0.2923, "lr": 6.444290147435617e-07, "epoch": 2.7762906309751436, "percentage": 92.72, "elapsed_time": "2:10:57", "remaining_time": "0:10:16"}
485
+ {"current_steps": 485, "total_steps": 522, "loss": 0.2962, "lr": 6.111295179567434e-07, "epoch": 2.7820267686424476, "percentage": 92.91, "elapsed_time": "2:11:15", "remaining_time": "0:10:00"}
486
+ {"current_steps": 486, "total_steps": 522, "loss": 0.3019, "lr": 5.786999925099257e-07, "epoch": 2.7877629063097515, "percentage": 93.1, "elapsed_time": "2:11:32", "remaining_time": "0:09:44"}
487
+ {"current_steps": 487, "total_steps": 522, "loss": 0.2949, "lr": 5.471418935037398e-07, "epoch": 2.7934990439770555, "percentage": 93.3, "elapsed_time": "2:11:50", "remaining_time": "0:09:28"}
488
+ {"current_steps": 488, "total_steps": 522, "loss": 0.3396, "lr": 5.164566369382407e-07, "epoch": 2.7992351816443595, "percentage": 93.49, "elapsed_time": "2:12:05", "remaining_time": "0:09:12"}
489
+ {"current_steps": 489, "total_steps": 522, "loss": 0.2909, "lr": 4.866455996493691e-07, "epoch": 2.8049713193116634, "percentage": 93.68, "elapsed_time": "2:12:21", "remaining_time": "0:08:55"}
490
+ {"current_steps": 490, "total_steps": 522, "loss": 0.3128, "lr": 4.577101192471811e-07, "epoch": 2.8107074569789674, "percentage": 93.87, "elapsed_time": "2:12:37", "remaining_time": "0:08:39"}
491
+ {"current_steps": 491, "total_steps": 522, "loss": 0.3299, "lr": 4.296514940558161e-07, "epoch": 2.8164435946462714, "percentage": 94.06, "elapsed_time": "2:12:55", "remaining_time": "0:08:23"}
492
+ {"current_steps": 492, "total_steps": 522, "loss": 0.3237, "lr": 4.0247098305525645e-07, "epoch": 2.8221797323135753, "percentage": 94.25, "elapsed_time": "2:13:09", "remaining_time": "0:08:07"}
493
+ {"current_steps": 493, "total_steps": 522, "loss": 0.3431, "lr": 3.7616980582482866e-07, "epoch": 2.8279158699808793, "percentage": 94.44, "elapsed_time": "2:13:26", "remaining_time": "0:07:50"}
494
+ {"current_steps": 494, "total_steps": 522, "loss": 0.279, "lr": 3.507491424884779e-07, "epoch": 2.8336520076481837, "percentage": 94.64, "elapsed_time": "2:13:42", "remaining_time": "0:07:34"}
495
+ {"current_steps": 495, "total_steps": 522, "loss": 0.3258, "lr": 3.262101336618262e-07, "epoch": 2.8393881453154877, "percentage": 94.83, "elapsed_time": "2:14:00", "remaining_time": "0:07:18"}
496
+ {"current_steps": 496, "total_steps": 522, "loss": 0.3202, "lr": 3.0255388040098864e-07, "epoch": 2.8451242829827916, "percentage": 95.02, "elapsed_time": "2:14:18", "remaining_time": "0:07:02"}
497
+ {"current_steps": 497, "total_steps": 522, "loss": 0.3105, "lr": 2.7978144415316656e-07, "epoch": 2.8508604206500956, "percentage": 95.21, "elapsed_time": "2:14:36", "remaining_time": "0:06:46"}
498
+ {"current_steps": 498, "total_steps": 522, "loss": 0.2349, "lr": 2.5789384670902753e-07, "epoch": 2.8565965583173996, "percentage": 95.4, "elapsed_time": "2:14:50", "remaining_time": "0:06:29"}
499
+ {"current_steps": 499, "total_steps": 522, "loss": 0.3767, "lr": 2.3689207015685334e-07, "epoch": 2.8623326959847035, "percentage": 95.59, "elapsed_time": "2:15:05", "remaining_time": "0:06:13"}
500
+ {"current_steps": 500, "total_steps": 522, "loss": 0.2827, "lr": 2.1677705683847082e-07, "epoch": 2.8680688336520075, "percentage": 95.79, "elapsed_time": "2:15:24", "remaining_time": "0:05:57"}
501
+ {"current_steps": 501, "total_steps": 522, "loss": 0.2988, "lr": 1.9754970930698115e-07, "epoch": 2.873804971319312, "percentage": 95.98, "elapsed_time": "2:15:39", "remaining_time": "0:05:41"}
502
+ {"current_steps": 502, "total_steps": 522, "loss": 0.2925, "lr": 1.792108902862455e-07, "epoch": 2.879541108986616, "percentage": 96.17, "elapsed_time": "2:15:51", "remaining_time": "0:05:24"}
503
+ {"current_steps": 503, "total_steps": 522, "loss": 0.3148, "lr": 1.6176142263219173e-07, "epoch": 2.88527724665392, "percentage": 96.36, "elapsed_time": "2:16:10", "remaining_time": "0:05:08"}
504
+ {"current_steps": 504, "total_steps": 522, "loss": 0.2563, "lr": 1.4520208929587942e-07, "epoch": 2.891013384321224, "percentage": 96.55, "elapsed_time": "2:16:23", "remaining_time": "0:04:52"}
505
+ {"current_steps": 505, "total_steps": 522, "loss": 0.2708, "lr": 1.2953363328838342e-07, "epoch": 2.8967495219885278, "percentage": 96.74, "elapsed_time": "2:16:39", "remaining_time": "0:04:36"}
506
+ {"current_steps": 506, "total_steps": 522, "loss": 0.3803, "lr": 1.1475675764743843e-07, "epoch": 2.9024856596558317, "percentage": 96.93, "elapsed_time": "2:16:55", "remaining_time": "0:04:19"}
507
+ {"current_steps": 507, "total_steps": 522, "loss": 0.3431, "lr": 1.0087212540591307e-07, "epoch": 2.9082217973231357, "percentage": 97.13, "elapsed_time": "2:17:13", "remaining_time": "0:04:03"}
508
+ {"current_steps": 508, "total_steps": 522, "loss": 0.27, "lr": 8.78803595620381e-08, "epoch": 2.9139579349904396, "percentage": 97.32, "elapsed_time": "2:17:30", "remaining_time": "0:03:47"}
509
+ {"current_steps": 509, "total_steps": 522, "loss": 0.2853, "lr": 7.57820430514733e-08, "epoch": 2.9196940726577436, "percentage": 97.51, "elapsed_time": "2:17:49", "remaining_time": "0:03:31"}
510
+ {"current_steps": 510, "total_steps": 522, "loss": 0.3274, "lr": 6.457771872113716e-08, "epoch": 2.9254302103250476, "percentage": 97.7, "elapsed_time": "2:18:01", "remaining_time": "0:03:14"}
511
+ {"current_steps": 511, "total_steps": 522, "loss": 0.2917, "lr": 5.4267889304859824e-08, "epoch": 2.9311663479923515, "percentage": 97.89, "elapsed_time": "2:18:18", "remaining_time": "0:02:58"}
512
+ {"current_steps": 512, "total_steps": 522, "loss": 0.3029, "lr": 4.485301740080994e-08, "epoch": 2.936902485659656, "percentage": 98.08, "elapsed_time": "2:18:36", "remaining_time": "0:02:42"}
513
+ {"current_steps": 513, "total_steps": 522, "loss": 0.2627, "lr": 3.633352545076241e-08, "epoch": 2.94263862332696, "percentage": 98.28, "elapsed_time": "2:18:50", "remaining_time": "0:02:26"}
514
+ {"current_steps": 514, "total_steps": 522, "loss": 0.3265, "lr": 2.8709795721117984e-08, "epoch": 2.948374760994264, "percentage": 98.47, "elapsed_time": "2:19:04", "remaining_time": "0:02:09"}
515
+ {"current_steps": 515, "total_steps": 522, "loss": 0.3039, "lr": 2.198217028577254e-08, "epoch": 2.954110898661568, "percentage": 98.66, "elapsed_time": "2:19:18", "remaining_time": "0:01:53"}
516
+ {"current_steps": 516, "total_steps": 522, "loss": 0.2785, "lr": 1.6150951010747152e-08, "epoch": 2.959847036328872, "percentage": 98.85, "elapsed_time": "2:19:34", "remaining_time": "0:01:37"}
517
+ {"current_steps": 517, "total_steps": 522, "loss": 0.2788, "lr": 1.1216399540669998e-08, "epoch": 2.9655831739961758, "percentage": 99.04, "elapsed_time": "2:19:48", "remaining_time": "0:01:21"}
518
+ {"current_steps": 518, "total_steps": 522, "loss": 0.3469, "lr": 7.178737287005799e-09, "epoch": 2.97131931166348, "percentage": 99.23, "elapsed_time": "2:20:06", "remaining_time": "0:01:04"}
519
+ {"current_steps": 519, "total_steps": 522, "loss": 0.2671, "lr": 4.038145418148176e-09, "epoch": 2.977055449330784, "percentage": 99.43, "elapsed_time": "2:20:23", "remaining_time": "0:00:48"}
520
+ {"current_steps": 520, "total_steps": 522, "loss": 0.32, "lr": 1.7947648512728343e-09, "epoch": 2.982791586998088, "percentage": 99.62, "elapsed_time": "2:20:40", "remaining_time": "0:00:32"}
521
+ {"current_steps": 521, "total_steps": 522, "loss": 0.3146, "lr": 4.486962460270583e-10, "epoch": 2.988527724665392, "percentage": 99.81, "elapsed_time": "2:20:55", "remaining_time": "0:00:16"}
522
+ {"current_steps": 522, "total_steps": 522, "loss": 0.2861, "lr": 0.0, "epoch": 2.994263862332696, "percentage": 100.0, "elapsed_time": "2:21:11", "remaining_time": "0:00:00"}
523
+ {"current_steps": 522, "total_steps": 522, "epoch": 2.994263862332696, "percentage": 100.0, "elapsed_time": "2:22:39", "remaining_time": "0:00:00"}