sedrickkeh commited on
Commit
9a7f4e8
·
verified ·
1 Parent(s): 4b4e4c5

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 sha256:2557489fbf3c609c6af607c46ecbe22798239a679183bfc1af3ca6b5d95d6432
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e5d9c4414ffcc74042c09da8057253cac8c18df286a1290f2fa72379b8756d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc114b2684cf4715469b3c923b550fec20aebb85a9064be89275219dcfe6558
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:166eeaa258435c571540b3056130f8e89b5501a4b4512cc82dc6e1d78f9afe61
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:ab3260ae411e40178798d4d446ca83b67bf9ad4b63d899f67f8ec03268d6e48e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd529e69f8adf2917cd5fbf03bff38b8c8c5ccd119b12144f24e39481241fd5
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40b84d5da9ed43b1973cbeaae626ff6a3a20b4694a7918c1ab3f79c9caf74754
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86ebd62fa5c62f98da819113be81a5232f5f03d03837fe554f3ca6682283295
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -356,3 +356,168 @@
356
  {"current_steps": 356, "total_steps": 522, "loss": 0.3708, "lr": 5.570856159683418e-06, "epoch": 2.0420650095602295, "percentage": 68.2, "elapsed_time": "1:36:51", "remaining_time": "0:45:10"}
357
  {"current_steps": 357, "total_steps": 522, "loss": 0.3954, "lr": 5.510899715691984e-06, "epoch": 2.0478011472275335, "percentage": 68.39, "elapsed_time": "1:37:11", "remaining_time": "0:44:55"}
358
  {"current_steps": 358, "total_steps": 522, "loss": 0.3767, "lr": 5.451144695945116e-06, "epoch": 2.0535372848948374, "percentage": 68.58, "elapsed_time": "1:37:31", "remaining_time": "0:44:40"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
356
  {"current_steps": 356, "total_steps": 522, "loss": 0.3708, "lr": 5.570856159683418e-06, "epoch": 2.0420650095602295, "percentage": 68.2, "elapsed_time": "1:36:51", "remaining_time": "0:45:10"}
357
  {"current_steps": 357, "total_steps": 522, "loss": 0.3954, "lr": 5.510899715691984e-06, "epoch": 2.0478011472275335, "percentage": 68.39, "elapsed_time": "1:37:11", "remaining_time": "0:44:55"}
358
  {"current_steps": 358, "total_steps": 522, "loss": 0.3767, "lr": 5.451144695945116e-06, "epoch": 2.0535372848948374, "percentage": 68.58, "elapsed_time": "1:37:31", "remaining_time": "0:44:40"}
359
+ {"current_steps": 359, "total_steps": 522, "loss": 0.3096, "lr": 5.391593781628109e-06, "epoch": 2.0592734225621414, "percentage": 68.77, "elapsed_time": "1:37:47", "remaining_time": "0:44:24"}
360
+ {"current_steps": 360, "total_steps": 522, "loss": 0.3795, "lr": 5.332249644768142e-06, "epoch": 2.0650095602294454, "percentage": 68.97, "elapsed_time": "1:38:04", "remaining_time": "0:44:07"}
361
+ {"current_steps": 361, "total_steps": 522, "loss": 0.3177, "lr": 5.273114948114346e-06, "epoch": 2.0707456978967493, "percentage": 69.16, "elapsed_time": "1:38:17", "remaining_time": "0:43:50"}
362
+ {"current_steps": 362, "total_steps": 522, "loss": 0.3515, "lr": 5.214192345018374e-06, "epoch": 2.0764818355640537, "percentage": 69.35, "elapsed_time": "1:38:35", "remaining_time": "0:43:34"}
363
+ {"current_steps": 363, "total_steps": 522, "loss": 0.4205, "lr": 5.1554844793153005e-06, "epoch": 2.0822179732313577, "percentage": 69.54, "elapsed_time": "1:38:51", "remaining_time": "0:43:18"}
364
+ {"current_steps": 364, "total_steps": 522, "loss": 0.3495, "lr": 5.096993985205023e-06, "epoch": 2.0879541108986617, "percentage": 69.73, "elapsed_time": "1:39:03", "remaining_time": "0:42:59"}
365
+ {"current_steps": 365, "total_steps": 522, "loss": 0.3969, "lr": 5.038723487134049e-06, "epoch": 2.0936902485659656, "percentage": 69.92, "elapsed_time": "1:39:20", "remaining_time": "0:42:43"}
366
+ {"current_steps": 366, "total_steps": 522, "loss": 0.37, "lr": 4.9806755996777565e-06, "epoch": 2.0994263862332696, "percentage": 70.11, "elapsed_time": "1:39:34", "remaining_time": "0:42:26"}
367
+ {"current_steps": 367, "total_steps": 522, "loss": 0.4183, "lr": 4.92285292742307e-06, "epoch": 2.1051625239005736, "percentage": 70.31, "elapsed_time": "1:39:53", "remaining_time": "0:42:11"}
368
+ {"current_steps": 368, "total_steps": 522, "loss": 0.3405, "lr": 4.865258064851579e-06, "epoch": 2.1108986615678775, "percentage": 70.5, "elapsed_time": "1:40:08", "remaining_time": "0:41:54"}
369
+ {"current_steps": 369, "total_steps": 522, "loss": 0.3702, "lr": 4.807893596223152e-06, "epoch": 2.1166347992351815, "percentage": 70.69, "elapsed_time": "1:40:23", "remaining_time": "0:41:37"}
370
+ {"current_steps": 370, "total_steps": 522, "loss": 0.3882, "lr": 4.75076209545996e-06, "epoch": 2.1223709369024855, "percentage": 70.88, "elapsed_time": "1:40:40", "remaining_time": "0:41:21"}
371
+ {"current_steps": 371, "total_steps": 522, "loss": 0.3192, "lr": 4.693866126030995e-06, "epoch": 2.12810707456979, "percentage": 71.07, "elapsed_time": "1:40:52", "remaining_time": "0:41:03"}
372
+ {"current_steps": 372, "total_steps": 522, "loss": 0.3954, "lr": 4.637208240837042e-06, "epoch": 2.133843212237094, "percentage": 71.26, "elapsed_time": "1:41:07", "remaining_time": "0:40:46"}
373
+ {"current_steps": 373, "total_steps": 522, "loss": 0.3096, "lr": 4.580790982096149e-06, "epoch": 2.139579349904398, "percentage": 71.46, "elapsed_time": "1:41:22", "remaining_time": "0:40:29"}
374
+ {"current_steps": 374, "total_steps": 522, "loss": 0.4717, "lr": 4.5246168812295286e-06, "epoch": 2.1453154875717018, "percentage": 71.65, "elapsed_time": "1:41:41", "remaining_time": "0:40:14"}
375
+ {"current_steps": 375, "total_steps": 522, "loss": 0.2981, "lr": 4.468688458748006e-06, "epoch": 2.1510516252390057, "percentage": 71.84, "elapsed_time": "1:41:53", "remaining_time": "0:39:56"}
376
+ {"current_steps": 376, "total_steps": 522, "loss": 0.3767, "lr": 4.4130082241388974e-06, "epoch": 2.1567877629063097, "percentage": 72.03, "elapsed_time": "1:42:09", "remaining_time": "0:39:40"}
377
+ {"current_steps": 377, "total_steps": 522, "loss": 0.3631, "lr": 4.357578675753432e-06, "epoch": 2.1625239005736137, "percentage": 72.22, "elapsed_time": "1:42:28", "remaining_time": "0:39:24"}
378
+ {"current_steps": 378, "total_steps": 522, "loss": 0.3738, "lr": 4.302402300694636e-06, "epoch": 2.1682600382409176, "percentage": 72.41, "elapsed_time": "1:42:47", "remaining_time": "0:39:09"}
379
+ {"current_steps": 379, "total_steps": 522, "loss": 0.3309, "lr": 4.247481574705744e-06, "epoch": 2.173996175908222, "percentage": 72.61, "elapsed_time": "1:42:57", "remaining_time": "0:38:50"}
380
+ {"current_steps": 380, "total_steps": 522, "loss": 0.3395, "lr": 4.192818962059112e-06, "epoch": 2.179732313575526, "percentage": 72.8, "elapsed_time": "1:43:13", "remaining_time": "0:38:34"}
381
+ {"current_steps": 381, "total_steps": 522, "loss": 0.3521, "lr": 4.138416915445656e-06, "epoch": 2.18546845124283, "percentage": 72.99, "elapsed_time": "1:43:27", "remaining_time": "0:38:17"}
382
+ {"current_steps": 382, "total_steps": 522, "loss": 0.379, "lr": 4.084277875864776e-06, "epoch": 2.191204588910134, "percentage": 73.18, "elapsed_time": "1:43:42", "remaining_time": "0:38:00"}
383
+ {"current_steps": 383, "total_steps": 522, "loss": 0.3803, "lr": 4.030404272514864e-06, "epoch": 2.196940726577438, "percentage": 73.37, "elapsed_time": "1:43:59", "remaining_time": "0:37:44"}
384
+ {"current_steps": 384, "total_steps": 522, "loss": 0.3622, "lr": 3.97679852268427e-06, "epoch": 2.202676864244742, "percentage": 73.56, "elapsed_time": "1:44:16", "remaining_time": "0:37:28"}
385
+ {"current_steps": 385, "total_steps": 522, "loss": 0.3673, "lr": 3.923463031642873e-06, "epoch": 2.208413001912046, "percentage": 73.75, "elapsed_time": "1:44:33", "remaining_time": "0:37:12"}
386
+ {"current_steps": 386, "total_steps": 522, "loss": 0.3647, "lr": 3.870400192534128e-06, "epoch": 2.21414913957935, "percentage": 73.95, "elapsed_time": "1:44:49", "remaining_time": "0:36:55"}
387
+ {"current_steps": 387, "total_steps": 522, "loss": 0.3822, "lr": 3.81761238626771e-06, "epoch": 2.2198852772466537, "percentage": 74.14, "elapsed_time": "1:45:08", "remaining_time": "0:36:40"}
388
+ {"current_steps": 388, "total_steps": 522, "loss": 0.4045, "lr": 3.7651019814126656e-06, "epoch": 2.2256214149139577, "percentage": 74.33, "elapsed_time": "1:45:23", "remaining_time": "0:36:23"}
389
+ {"current_steps": 389, "total_steps": 522, "loss": 0.3614, "lr": 3.712871334091154e-06, "epoch": 2.231357552581262, "percentage": 74.52, "elapsed_time": "1:45:40", "remaining_time": "0:36:07"}
390
+ {"current_steps": 390, "total_steps": 522, "loss": 0.3271, "lr": 3.6609227878727062e-06, "epoch": 2.237093690248566, "percentage": 74.71, "elapsed_time": "1:45:54", "remaining_time": "0:35:50"}
391
+ {"current_steps": 391, "total_steps": 522, "loss": 0.3428, "lr": 3.609258673669097e-06, "epoch": 2.24282982791587, "percentage": 74.9, "elapsed_time": "1:46:10", "remaining_time": "0:35:34"}
392
+ {"current_steps": 392, "total_steps": 522, "loss": 0.3861, "lr": 3.5578813096297293e-06, "epoch": 2.248565965583174, "percentage": 75.1, "elapsed_time": "1:46:29", "remaining_time": "0:35:19"}
393
+ {"current_steps": 393, "total_steps": 522, "loss": 0.42, "lr": 3.5067930010376484e-06, "epoch": 2.254302103250478, "percentage": 75.29, "elapsed_time": "1:46:46", "remaining_time": "0:35:02"}
394
+ {"current_steps": 394, "total_steps": 522, "loss": 0.3634, "lr": 3.4559960402060764e-06, "epoch": 2.260038240917782, "percentage": 75.48, "elapsed_time": "1:47:01", "remaining_time": "0:34:46"}
395
+ {"current_steps": 395, "total_steps": 522, "loss": 0.4019, "lr": 3.4054927063755793e-06, "epoch": 2.265774378585086, "percentage": 75.67, "elapsed_time": "1:47:15", "remaining_time": "0:34:29"}
396
+ {"current_steps": 396, "total_steps": 522, "loss": 0.3547, "lr": 3.355285265611784e-06, "epoch": 2.27151051625239, "percentage": 75.86, "elapsed_time": "1:47:32", "remaining_time": "0:34:12"}
397
+ {"current_steps": 397, "total_steps": 522, "loss": 0.3624, "lr": 3.3053759707037116e-06, "epoch": 2.2772466539196943, "percentage": 76.05, "elapsed_time": "1:47:43", "remaining_time": "0:33:54"}
398
+ {"current_steps": 398, "total_steps": 522, "loss": 0.3771, "lr": 3.2557670610626924e-06, "epoch": 2.2829827915869982, "percentage": 76.25, "elapsed_time": "1:47:56", "remaining_time": "0:33:37"}
399
+ {"current_steps": 399, "total_steps": 522, "loss": 0.3793, "lr": 3.2064607626218737e-06, "epoch": 2.288718929254302, "percentage": 76.44, "elapsed_time": "1:48:13", "remaining_time": "0:33:21"}
400
+ {"current_steps": 400, "total_steps": 522, "loss": 0.3784, "lr": 3.157459287736362e-06, "epoch": 2.294455066921606, "percentage": 76.63, "elapsed_time": "1:48:29", "remaining_time": "0:33:05"}
401
+ {"current_steps": 401, "total_steps": 522, "loss": 0.3892, "lr": 3.1087648350839382e-06, "epoch": 2.30019120458891, "percentage": 76.82, "elapsed_time": "1:48:44", "remaining_time": "0:32:48"}
402
+ {"current_steps": 402, "total_steps": 522, "loss": 0.3596, "lr": 3.0603795895664125e-06, "epoch": 2.305927342256214, "percentage": 77.01, "elapsed_time": "1:49:02", "remaining_time": "0:32:32"}
403
+ {"current_steps": 403, "total_steps": 522, "loss": 0.3933, "lr": 3.0123057222115835e-06, "epoch": 2.311663479923518, "percentage": 77.2, "elapsed_time": "1:49:17", "remaining_time": "0:32:16"}
404
+ {"current_steps": 404, "total_steps": 522, "loss": 0.3858, "lr": 2.9645453900758415e-06, "epoch": 2.317399617590822, "percentage": 77.39, "elapsed_time": "1:49:33", "remaining_time": "0:31:59"}
405
+ {"current_steps": 405, "total_steps": 522, "loss": 0.3503, "lr": 2.9171007361473512e-06, "epoch": 2.323135755258126, "percentage": 77.59, "elapsed_time": "1:49:49", "remaining_time": "0:31:43"}
406
+ {"current_steps": 406, "total_steps": 522, "loss": 0.3211, "lr": 2.869973889249933e-06, "epoch": 2.3288718929254304, "percentage": 77.78, "elapsed_time": "1:50:02", "remaining_time": "0:31:26"}
407
+ {"current_steps": 407, "total_steps": 522, "loss": 0.3283, "lr": 2.8231669639475068e-06, "epoch": 2.3346080305927344, "percentage": 77.97, "elapsed_time": "1:50:16", "remaining_time": "0:31:09"}
408
+ {"current_steps": 408, "total_steps": 522, "loss": 0.3694, "lr": 2.7766820604492474e-06, "epoch": 2.3403441682600383, "percentage": 78.16, "elapsed_time": "1:50:28", "remaining_time": "0:30:52"}
409
+ {"current_steps": 409, "total_steps": 522, "loss": 0.3277, "lr": 2.7305212645153213e-06, "epoch": 2.3460803059273423, "percentage": 78.35, "elapsed_time": "1:50:44", "remaining_time": "0:30:35"}
410
+ {"current_steps": 410, "total_steps": 522, "loss": 0.3648, "lr": 2.6846866473633126e-06, "epoch": 2.3518164435946463, "percentage": 78.54, "elapsed_time": "1:51:00", "remaining_time": "0:30:19"}
411
+ {"current_steps": 411, "total_steps": 522, "loss": 0.3553, "lr": 2.6391802655752853e-06, "epoch": 2.35755258126195, "percentage": 78.74, "elapsed_time": "1:51:13", "remaining_time": "0:30:02"}
412
+ {"current_steps": 412, "total_steps": 522, "loss": 0.3953, "lr": 2.594004161005511e-06, "epoch": 2.363288718929254, "percentage": 78.93, "elapsed_time": "1:51:31", "remaining_time": "0:29:46"}
413
+ {"current_steps": 413, "total_steps": 522, "loss": 0.3431, "lr": 2.5491603606888384e-06, "epoch": 2.369024856596558, "percentage": 79.12, "elapsed_time": "1:51:43", "remaining_time": "0:29:29"}
414
+ {"current_steps": 414, "total_steps": 522, "loss": 0.3587, "lr": 2.50465087674976e-06, "epoch": 2.3747609942638626, "percentage": 79.31, "elapsed_time": "1:52:00", "remaining_time": "0:29:13"}
415
+ {"current_steps": 415, "total_steps": 522, "loss": 0.3871, "lr": 2.460477706312103e-06, "epoch": 2.3804971319311665, "percentage": 79.5, "elapsed_time": "1:52:17", "remaining_time": "0:28:57"}
416
+ {"current_steps": 416, "total_steps": 522, "loss": 0.3796, "lr": 2.4166428314094514e-06, "epoch": 2.3862332695984705, "percentage": 79.69, "elapsed_time": "1:52:33", "remaining_time": "0:28:40"}
417
+ {"current_steps": 417, "total_steps": 522, "loss": 0.3723, "lr": 2.373148218896182e-06, "epoch": 2.3919694072657744, "percentage": 79.89, "elapsed_time": "1:52:50", "remaining_time": "0:28:24"}
418
+ {"current_steps": 418, "total_steps": 522, "loss": 0.375, "lr": 2.32999582035923e-06, "epoch": 2.3977055449330784, "percentage": 80.08, "elapsed_time": "1:53:05", "remaining_time": "0:28:08"}
419
+ {"current_steps": 419, "total_steps": 522, "loss": 0.359, "lr": 2.2871875720305158e-06, "epoch": 2.4034416826003824, "percentage": 80.27, "elapsed_time": "1:53:22", "remaining_time": "0:27:52"}
420
+ {"current_steps": 420, "total_steps": 522, "loss": 0.4019, "lr": 2.244725394700079e-06, "epoch": 2.4091778202676863, "percentage": 80.46, "elapsed_time": "1:53:39", "remaining_time": "0:27:36"}
421
+ {"current_steps": 421, "total_steps": 522, "loss": 0.339, "lr": 2.2026111936298687e-06, "epoch": 2.4149139579349903, "percentage": 80.65, "elapsed_time": "1:53:55", "remaining_time": "0:27:19"}
422
+ {"current_steps": 422, "total_steps": 522, "loss": 0.4068, "lr": 2.160846858468285e-06, "epoch": 2.4206500956022943, "percentage": 80.84, "elapsed_time": "1:54:12", "remaining_time": "0:27:03"}
423
+ {"current_steps": 423, "total_steps": 522, "loss": 0.3472, "lr": 2.119434263165361e-06, "epoch": 2.4263862332695982, "percentage": 81.03, "elapsed_time": "1:54:27", "remaining_time": "0:26:47"}
424
+ {"current_steps": 424, "total_steps": 522, "loss": 0.341, "lr": 2.078375265888707e-06, "epoch": 2.4321223709369026, "percentage": 81.23, "elapsed_time": "1:54:42", "remaining_time": "0:26:30"}
425
+ {"current_steps": 425, "total_steps": 522, "loss": 0.3826, "lr": 2.0376717089401166e-06, "epoch": 2.4378585086042066, "percentage": 81.42, "elapsed_time": "1:55:00", "remaining_time": "0:26:14"}
426
+ {"current_steps": 426, "total_steps": 522, "loss": 0.3562, "lr": 1.9973254186729084e-06, "epoch": 2.4435946462715106, "percentage": 81.61, "elapsed_time": "1:55:16", "remaining_time": "0:25:58"}
427
+ {"current_steps": 427, "total_steps": 522, "loss": 0.4103, "lr": 1.9573382054099786e-06, "epoch": 2.4493307839388145, "percentage": 81.8, "elapsed_time": "1:55:34", "remaining_time": "0:25:42"}
428
+ {"current_steps": 428, "total_steps": 522, "loss": 0.3632, "lr": 1.917711863362581e-06, "epoch": 2.4550669216061185, "percentage": 81.99, "elapsed_time": "1:55:47", "remaining_time": "0:25:25"}
429
+ {"current_steps": 429, "total_steps": 522, "loss": 0.4023, "lr": 1.8784481705498014e-06, "epoch": 2.4608030592734225, "percentage": 82.18, "elapsed_time": "1:56:01", "remaining_time": "0:25:09"}
430
+ {"current_steps": 430, "total_steps": 522, "loss": 0.3394, "lr": 1.8395488887188007e-06, "epoch": 2.4665391969407264, "percentage": 82.38, "elapsed_time": "1:56:17", "remaining_time": "0:24:52"}
431
+ {"current_steps": 431, "total_steps": 522, "loss": 0.3784, "lr": 1.8010157632657544e-06, "epoch": 2.472275334608031, "percentage": 82.57, "elapsed_time": "1:56:34", "remaining_time": "0:24:36"}
432
+ {"current_steps": 432, "total_steps": 522, "loss": 0.372, "lr": 1.7628505231575321e-06, "epoch": 2.478011472275335, "percentage": 82.76, "elapsed_time": "1:56:53", "remaining_time": "0:24:21"}
433
+ {"current_steps": 433, "total_steps": 522, "loss": 0.4246, "lr": 1.7250548808541324e-06, "epoch": 2.4837476099426388, "percentage": 82.95, "elapsed_time": "1:57:07", "remaining_time": "0:24:04"}
434
+ {"current_steps": 434, "total_steps": 522, "loss": 0.3674, "lr": 1.687630532231833e-06, "epoch": 2.4894837476099427, "percentage": 83.14, "elapsed_time": "1:57:23", "remaining_time": "0:23:48"}
435
+ {"current_steps": 435, "total_steps": 522, "loss": 0.3625, "lr": 1.6505791565071139e-06, "epoch": 2.4952198852772467, "percentage": 83.33, "elapsed_time": "1:57:39", "remaining_time": "0:23:31"}
436
+ {"current_steps": 436, "total_steps": 522, "loss": 0.3604, "lr": 1.6139024161612882e-06, "epoch": 2.5009560229445507, "percentage": 83.52, "elapsed_time": "1:57:59", "remaining_time": "0:23:16"}
437
+ {"current_steps": 437, "total_steps": 522, "loss": 0.3679, "lr": 1.577601956865934e-06, "epoch": 2.5066921606118546, "percentage": 83.72, "elapsed_time": "1:58:16", "remaining_time": "0:23:00"}
438
+ {"current_steps": 438, "total_steps": 522, "loss": 0.3741, "lr": 1.5416794074090258e-06, "epoch": 2.5124282982791586, "percentage": 83.91, "elapsed_time": "1:58:31", "remaining_time": "0:22:43"}
439
+ {"current_steps": 439, "total_steps": 522, "loss": 0.3667, "lr": 1.5061363796218787e-06, "epoch": 2.5181644359464626, "percentage": 84.1, "elapsed_time": "1:58:47", "remaining_time": "0:22:27"}
440
+ {"current_steps": 440, "total_steps": 522, "loss": 0.4242, "lr": 1.470974468306804e-06, "epoch": 2.5239005736137665, "percentage": 84.29, "elapsed_time": "1:59:05", "remaining_time": "0:22:11"}
441
+ {"current_steps": 441, "total_steps": 522, "loss": 0.3954, "lr": 1.4361952511655618e-06, "epoch": 2.5296367112810705, "percentage": 84.48, "elapsed_time": "1:59:22", "remaining_time": "0:21:55"}
442
+ {"current_steps": 442, "total_steps": 522, "loss": 0.3261, "lr": 1.4018002887285687e-06, "epoch": 2.535372848948375, "percentage": 84.67, "elapsed_time": "1:59:41", "remaining_time": "0:21:39"}
443
+ {"current_steps": 443, "total_steps": 522, "loss": 0.3538, "lr": 1.3677911242848807e-06, "epoch": 2.541108986615679, "percentage": 84.87, "elapsed_time": "1:59:57", "remaining_time": "0:21:23"}
444
+ {"current_steps": 444, "total_steps": 522, "loss": 0.3534, "lr": 1.334169283812936e-06, "epoch": 2.546845124282983, "percentage": 85.06, "elapsed_time": "2:00:14", "remaining_time": "0:21:07"}
445
+ {"current_steps": 445, "total_steps": 522, "loss": 0.3934, "lr": 1.300936275912098e-06, "epoch": 2.552581261950287, "percentage": 85.25, "elapsed_time": "2:00:32", "remaining_time": "0:20:51"}
446
+ {"current_steps": 446, "total_steps": 522, "loss": 0.3627, "lr": 1.2680935917349524e-06, "epoch": 2.5583173996175907, "percentage": 85.44, "elapsed_time": "2:00:47", "remaining_time": "0:20:34"}
447
+ {"current_steps": 447, "total_steps": 522, "loss": 0.3545, "lr": 1.2356427049204122e-06, "epoch": 2.5640535372848947, "percentage": 85.63, "elapsed_time": "2:01:00", "remaining_time": "0:20:18"}
448
+ {"current_steps": 448, "total_steps": 522, "loss": 0.3776, "lr": 1.2035850715275865e-06, "epoch": 2.569789674952199, "percentage": 85.82, "elapsed_time": "2:01:20", "remaining_time": "0:20:02"}
449
+ {"current_steps": 449, "total_steps": 522, "loss": 0.3266, "lr": 1.1719221299704497e-06, "epoch": 2.575525812619503, "percentage": 86.02, "elapsed_time": "2:01:32", "remaining_time": "0:19:45"}
450
+ {"current_steps": 450, "total_steps": 522, "loss": 0.3243, "lr": 1.1406553009533028e-06, "epoch": 2.581261950286807, "percentage": 86.21, "elapsed_time": "2:01:47", "remaining_time": "0:19:29"}
451
+ {"current_steps": 451, "total_steps": 522, "loss": 0.4062, "lr": 1.1097859874070294e-06, "epoch": 2.586998087954111, "percentage": 86.4, "elapsed_time": "2:02:01", "remaining_time": "0:19:12"}
452
+ {"current_steps": 452, "total_steps": 522, "loss": 0.3596, "lr": 1.0793155744261352e-06, "epoch": 2.592734225621415, "percentage": 86.59, "elapsed_time": "2:02:19", "remaining_time": "0:18:56"}
453
+ {"current_steps": 453, "total_steps": 522, "loss": 0.3834, "lr": 1.0492454292066178e-06, "epoch": 2.598470363288719, "percentage": 86.78, "elapsed_time": "2:02:37", "remaining_time": "0:18:40"}
454
+ {"current_steps": 454, "total_steps": 522, "loss": 0.3485, "lr": 1.0195769009845992e-06, "epoch": 2.604206500956023, "percentage": 86.97, "elapsed_time": "2:02:53", "remaining_time": "0:18:24"}
455
+ {"current_steps": 455, "total_steps": 522, "loss": 0.401, "lr": 9.903113209758098e-07, "epoch": 2.609942638623327, "percentage": 87.16, "elapsed_time": "2:03:07", "remaining_time": "0:18:07"}
456
+ {"current_steps": 456, "total_steps": 522, "loss": 0.3622, "lr": 9.614500023158335e-07, "epoch": 2.615678776290631, "percentage": 87.36, "elapsed_time": "2:03:24", "remaining_time": "0:17:51"}
457
+ {"current_steps": 457, "total_steps": 522, "loss": 0.3383, "lr": 9.329942400012059e-07, "epoch": 2.621414913957935, "percentage": 87.55, "elapsed_time": "2:03:42", "remaining_time": "0:17:35"}
458
+ {"current_steps": 458, "total_steps": 522, "loss": 0.3342, "lr": 9.049453108312967e-07, "epoch": 2.6271510516252388, "percentage": 87.74, "elapsed_time": "2:03:57", "remaining_time": "0:17:19"}
459
+ {"current_steps": 459, "total_steps": 522, "loss": 0.3916, "lr": 8.773044733510338e-07, "epoch": 2.632887189292543, "percentage": 87.93, "elapsed_time": "2:04:14", "remaining_time": "0:17:03"}
460
+ {"current_steps": 460, "total_steps": 522, "loss": 0.398, "lr": 8.50072967794413e-07, "epoch": 2.638623326959847, "percentage": 88.12, "elapsed_time": "2:04:32", "remaining_time": "0:16:47"}
461
+ {"current_steps": 461, "total_steps": 522, "loss": 0.3666, "lr": 8.232520160288704e-07, "epoch": 2.644359464627151, "percentage": 88.31, "elapsed_time": "2:04:44", "remaining_time": "0:16:30"}
462
+ {"current_steps": 462, "total_steps": 522, "loss": 0.3533, "lr": 7.96842821500442e-07, "epoch": 2.650095602294455, "percentage": 88.51, "elapsed_time": "2:05:01", "remaining_time": "0:16:14"}
463
+ {"current_steps": 463, "total_steps": 522, "loss": 0.3904, "lr": 7.708465691797718e-07, "epoch": 2.655831739961759, "percentage": 88.7, "elapsed_time": "2:05:13", "remaining_time": "0:15:57"}
464
+ {"current_steps": 464, "total_steps": 522, "loss": 0.366, "lr": 7.452644255089425e-07, "epoch": 2.661567877629063, "percentage": 88.89, "elapsed_time": "2:05:29", "remaining_time": "0:15:41"}
465
+ {"current_steps": 465, "total_steps": 522, "loss": 0.3518, "lr": 7.20097538349136e-07, "epoch": 2.667304015296367, "percentage": 89.08, "elapsed_time": "2:05:46", "remaining_time": "0:15:25"}
466
+ {"current_steps": 466, "total_steps": 522, "loss": 0.3531, "lr": 6.953470369291349e-07, "epoch": 2.6730401529636714, "percentage": 89.27, "elapsed_time": "2:06:03", "remaining_time": "0:15:08"}
467
+ {"current_steps": 467, "total_steps": 522, "loss": 0.3756, "lr": 6.710140317946424e-07, "epoch": 2.6787762906309753, "percentage": 89.46, "elapsed_time": "2:06:20", "remaining_time": "0:14:52"}
468
+ {"current_steps": 468, "total_steps": 522, "loss": 0.3952, "lr": 6.470996147584684e-07, "epoch": 2.6845124282982793, "percentage": 89.66, "elapsed_time": "2:06:35", "remaining_time": "0:14:36"}
469
+ {"current_steps": 469, "total_steps": 522, "loss": 0.3534, "lr": 6.236048588515242e-07, "epoch": 2.6902485659655833, "percentage": 89.85, "elapsed_time": "2:06:50", "remaining_time": "0:14:20"}
470
+ {"current_steps": 470, "total_steps": 522, "loss": 0.3591, "lr": 6.005308182746906e-07, "epoch": 2.6959847036328872, "percentage": 90.04, "elapsed_time": "2:07:05", "remaining_time": "0:14:03"}
471
+ {"current_steps": 471, "total_steps": 522, "loss": 0.3582, "lr": 5.778785283515054e-07, "epoch": 2.701720841300191, "percentage": 90.23, "elapsed_time": "2:07:22", "remaining_time": "0:13:47"}
472
+ {"current_steps": 472, "total_steps": 522, "loss": 0.3988, "lr": 5.556490054817132e-07, "epoch": 2.707456978967495, "percentage": 90.42, "elapsed_time": "2:07:38", "remaining_time": "0:13:31"}
473
+ {"current_steps": 473, "total_steps": 522, "loss": 0.3857, "lr": 5.33843247095659e-07, "epoch": 2.713193116634799, "percentage": 90.61, "elapsed_time": "2:07:55", "remaining_time": "0:13:15"}
474
+ {"current_steps": 474, "total_steps": 522, "loss": 0.398, "lr": 5.124622316095384e-07, "epoch": 2.718929254302103, "percentage": 90.8, "elapsed_time": "2:08:13", "remaining_time": "0:12:59"}
475
+ {"current_steps": 475, "total_steps": 522, "loss": 0.3443, "lr": 4.91506918381488e-07, "epoch": 2.724665391969407, "percentage": 91.0, "elapsed_time": "2:08:29", "remaining_time": "0:12:42"}
476
+ {"current_steps": 476, "total_steps": 522, "loss": 0.393, "lr": 4.709782476685476e-07, "epoch": 2.730401529636711, "percentage": 91.19, "elapsed_time": "2:08:46", "remaining_time": "0:12:26"}
477
+ {"current_steps": 477, "total_steps": 522, "loss": 0.363, "lr": 4.508771405844636e-07, "epoch": 2.7361376673040154, "percentage": 91.38, "elapsed_time": "2:09:00", "remaining_time": "0:12:10"}
478
+ {"current_steps": 478, "total_steps": 522, "loss": 0.2888, "lr": 4.3120449905836746e-07, "epoch": 2.7418738049713194, "percentage": 91.57, "elapsed_time": "2:09:12", "remaining_time": "0:11:53"}
479
+ {"current_steps": 479, "total_steps": 522, "loss": 0.369, "lr": 4.1196120579429786e-07, "epoch": 2.7476099426386233, "percentage": 91.76, "elapsed_time": "2:09:23", "remaining_time": "0:11:36"}
480
+ {"current_steps": 480, "total_steps": 522, "loss": 0.3687, "lr": 3.931481242315993e-07, "epoch": 2.7533460803059273, "percentage": 91.95, "elapsed_time": "2:09:37", "remaining_time": "0:11:20"}
481
+ {"current_steps": 481, "total_steps": 522, "loss": 0.3511, "lr": 3.747660985061785e-07, "epoch": 2.7590822179732313, "percentage": 92.15, "elapsed_time": "2:09:56", "remaining_time": "0:11:04"}
482
+ {"current_steps": 482, "total_steps": 522, "loss": 0.3887, "lr": 3.5681595341263144e-07, "epoch": 2.7648183556405352, "percentage": 92.34, "elapsed_time": "2:10:14", "remaining_time": "0:10:48"}
483
+ {"current_steps": 483, "total_steps": 522, "loss": 0.3865, "lr": 3.392984943672273e-07, "epoch": 2.7705544933078396, "percentage": 92.53, "elapsed_time": "2:10:31", "remaining_time": "0:10:32"}
484
+ {"current_steps": 484, "total_steps": 522, "loss": 0.3501, "lr": 3.2221450737178083e-07, "epoch": 2.7762906309751436, "percentage": 92.72, "elapsed_time": "2:10:47", "remaining_time": "0:10:16"}
485
+ {"current_steps": 485, "total_steps": 522, "loss": 0.3548, "lr": 3.055647589783717e-07, "epoch": 2.7820267686424476, "percentage": 92.91, "elapsed_time": "2:11:05", "remaining_time": "0:10:00"}
486
+ {"current_steps": 486, "total_steps": 522, "loss": 0.3662, "lr": 2.8934999625496287e-07, "epoch": 2.7877629063097515, "percentage": 93.1, "elapsed_time": "2:11:22", "remaining_time": "0:09:43"}
487
+ {"current_steps": 487, "total_steps": 522, "loss": 0.3535, "lr": 2.735709467518699e-07, "epoch": 2.7934990439770555, "percentage": 93.3, "elapsed_time": "2:11:40", "remaining_time": "0:09:27"}
488
+ {"current_steps": 488, "total_steps": 522, "loss": 0.3995, "lr": 2.5822831846912035e-07, "epoch": 2.7992351816443595, "percentage": 93.49, "elapsed_time": "2:11:55", "remaining_time": "0:09:11"}
489
+ {"current_steps": 489, "total_steps": 522, "loss": 0.35, "lr": 2.4332279982468454e-07, "epoch": 2.8049713193116634, "percentage": 93.68, "elapsed_time": "2:12:11", "remaining_time": "0:08:55"}
490
+ {"current_steps": 490, "total_steps": 522, "loss": 0.3727, "lr": 2.2885505962359055e-07, "epoch": 2.8107074569789674, "percentage": 93.87, "elapsed_time": "2:12:27", "remaining_time": "0:08:39"}
491
+ {"current_steps": 491, "total_steps": 522, "loss": 0.3947, "lr": 2.1482574702790804e-07, "epoch": 2.8164435946462714, "percentage": 94.06, "elapsed_time": "2:12:45", "remaining_time": "0:08:22"}
492
+ {"current_steps": 492, "total_steps": 522, "loss": 0.386, "lr": 2.0123549152762823e-07, "epoch": 2.8221797323135753, "percentage": 94.25, "elapsed_time": "2:12:59", "remaining_time": "0:08:06"}
493
+ {"current_steps": 493, "total_steps": 522, "loss": 0.4096, "lr": 1.8808490291241433e-07, "epoch": 2.8279158699808793, "percentage": 94.44, "elapsed_time": "2:13:16", "remaining_time": "0:07:50"}
494
+ {"current_steps": 494, "total_steps": 522, "loss": 0.3414, "lr": 1.7537457124423896e-07, "epoch": 2.8336520076481837, "percentage": 94.64, "elapsed_time": "2:13:32", "remaining_time": "0:07:34"}
495
+ {"current_steps": 495, "total_steps": 522, "loss": 0.3896, "lr": 1.631050668309131e-07, "epoch": 2.8393881453154877, "percentage": 94.83, "elapsed_time": "2:13:50", "remaining_time": "0:07:18"}
496
+ {"current_steps": 496, "total_steps": 522, "loss": 0.3823, "lr": 1.5127694020049432e-07, "epoch": 2.8451242829827916, "percentage": 95.02, "elapsed_time": "2:14:08", "remaining_time": "0:07:01"}
497
+ {"current_steps": 497, "total_steps": 522, "loss": 0.3725, "lr": 1.3989072207658328e-07, "epoch": 2.8508604206500956, "percentage": 95.21, "elapsed_time": "2:14:26", "remaining_time": "0:06:45"}
498
+ {"current_steps": 498, "total_steps": 522, "loss": 0.2904, "lr": 1.2894692335451376e-07, "epoch": 2.8565965583173996, "percentage": 95.4, "elapsed_time": "2:14:40", "remaining_time": "0:06:29"}
499
+ {"current_steps": 499, "total_steps": 522, "loss": 0.4438, "lr": 1.1844603507842667e-07, "epoch": 2.8623326959847035, "percentage": 95.59, "elapsed_time": "2:14:55", "remaining_time": "0:06:13"}
500
+ {"current_steps": 500, "total_steps": 522, "loss": 0.3444, "lr": 1.0838852841923541e-07, "epoch": 2.8680688336520075, "percentage": 95.79, "elapsed_time": "2:15:14", "remaining_time": "0:05:57"}
501
+ {"current_steps": 501, "total_steps": 522, "loss": 0.3635, "lr": 9.877485465349057e-08, "epoch": 2.873804971319312, "percentage": 95.98, "elapsed_time": "2:15:29", "remaining_time": "0:05:40"}
502
+ {"current_steps": 502, "total_steps": 522, "loss": 0.3544, "lr": 8.960544514312275e-08, "epoch": 2.879541108986616, "percentage": 96.17, "elapsed_time": "2:15:41", "remaining_time": "0:05:24"}
503
+ {"current_steps": 503, "total_steps": 522, "loss": 0.3823, "lr": 8.088071131609587e-08, "epoch": 2.88527724665392, "percentage": 96.36, "elapsed_time": "2:16:00", "remaining_time": "0:05:08"}
504
+ {"current_steps": 504, "total_steps": 522, "loss": 0.3123, "lr": 7.260104464793971e-08, "epoch": 2.891013384321224, "percentage": 96.55, "elapsed_time": "2:16:12", "remaining_time": "0:04:51"}
505
+ {"current_steps": 505, "total_steps": 522, "loss": 0.329, "lr": 6.476681664419171e-08, "epoch": 2.8967495219885278, "percentage": 96.74, "elapsed_time": "2:16:28", "remaining_time": "0:04:35"}
506
+ {"current_steps": 506, "total_steps": 522, "loss": 0.4483, "lr": 5.737837882371921e-08, "epoch": 2.9024856596558317, "percentage": 96.93, "elapsed_time": "2:16:45", "remaining_time": "0:04:19"}
507
+ {"current_steps": 507, "total_steps": 522, "loss": 0.4067, "lr": 5.0436062702956536e-08, "epoch": 2.9082217973231357, "percentage": 97.13, "elapsed_time": "2:17:03", "remaining_time": "0:04:03"}
508
+ {"current_steps": 508, "total_steps": 522, "loss": 0.3275, "lr": 4.394017978101905e-08, "epoch": 2.9139579349904396, "percentage": 97.32, "elapsed_time": "2:17:19", "remaining_time": "0:03:47"}
509
+ {"current_steps": 509, "total_steps": 522, "loss": 0.3467, "lr": 3.789102152573665e-08, "epoch": 2.9196940726577436, "percentage": 97.51, "elapsed_time": "2:17:39", "remaining_time": "0:03:30"}
510
+ {"current_steps": 510, "total_steps": 522, "loss": 0.3955, "lr": 3.228885936056858e-08, "epoch": 2.9254302103250476, "percentage": 97.7, "elapsed_time": "2:17:51", "remaining_time": "0:03:14"}
511
+ {"current_steps": 511, "total_steps": 522, "loss": 0.3531, "lr": 2.7133944652429912e-08, "epoch": 2.9311663479923515, "percentage": 97.89, "elapsed_time": "2:18:07", "remaining_time": "0:02:58"}
512
+ {"current_steps": 512, "total_steps": 522, "loss": 0.368, "lr": 2.242650870040497e-08, "epoch": 2.936902485659656, "percentage": 98.08, "elapsed_time": "2:18:26", "remaining_time": "0:02:42"}
513
+ {"current_steps": 513, "total_steps": 522, "loss": 0.3218, "lr": 1.8166762725381205e-08, "epoch": 2.94263862332696, "percentage": 98.28, "elapsed_time": "2:18:39", "remaining_time": "0:02:25"}
514
+ {"current_steps": 514, "total_steps": 522, "loss": 0.3885, "lr": 1.4354897860558992e-08, "epoch": 2.948374760994264, "percentage": 98.47, "elapsed_time": "2:18:53", "remaining_time": "0:02:09"}
515
+ {"current_steps": 515, "total_steps": 522, "loss": 0.3649, "lr": 1.099108514288627e-08, "epoch": 2.954110898661568, "percentage": 98.66, "elapsed_time": "2:19:07", "remaining_time": "0:01:53"}
516
+ {"current_steps": 516, "total_steps": 522, "loss": 0.3413, "lr": 8.075475505373576e-09, "epoch": 2.959847036328872, "percentage": 98.85, "elapsed_time": "2:19:23", "remaining_time": "0:01:37"}
517
+ {"current_steps": 517, "total_steps": 522, "loss": 0.337, "lr": 5.608199770334999e-09, "epoch": 2.9655831739961758, "percentage": 99.04, "elapsed_time": "2:19:37", "remaining_time": "0:01:21"}
518
+ {"current_steps": 518, "total_steps": 522, "loss": 0.4078, "lr": 3.5893686435028995e-09, "epoch": 2.97131931166348, "percentage": 99.23, "elapsed_time": "2:19:55", "remaining_time": "0:01:04"}
519
+ {"current_steps": 519, "total_steps": 522, "loss": 0.3268, "lr": 2.019072709074088e-09, "epoch": 2.977055449330784, "percentage": 99.43, "elapsed_time": "2:20:12", "remaining_time": "0:00:48"}
520
+ {"current_steps": 520, "total_steps": 522, "loss": 0.3836, "lr": 8.973824256364172e-10, "epoch": 2.982791586998088, "percentage": 99.62, "elapsed_time": "2:20:29", "remaining_time": "0:00:32"}
521
+ {"current_steps": 521, "total_steps": 522, "loss": 0.3802, "lr": 2.2434812301352915e-10, "epoch": 2.988527724665392, "percentage": 99.81, "elapsed_time": "2:20:44", "remaining_time": "0:00:16"}
522
+ {"current_steps": 522, "total_steps": 522, "loss": 0.3441, "lr": 0.0, "epoch": 2.994263862332696, "percentage": 100.0, "elapsed_time": "2:20:59", "remaining_time": "0:00:00"}
523
+ {"current_steps": 522, "total_steps": 522, "epoch": 2.994263862332696, "percentage": 100.0, "elapsed_time": "2:22:30", "remaining_time": "0:00:00"}