gsmyrnis commited on
Commit
e7692ef
·
verified ·
1 Parent(s): 7b0adc6

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 sha256:7eed6030b5d7cd6b69380d90ae733e1f6d1cc301cce6766cce0309b9aaab7edf
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4cf2cd632afab63d0c502e65a18d7abb2474b514aaa50d2b10bc42ee26c4f2
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e91f0333485bb026ad269d2164745f3a2124956ce00e686d8d8c5c406d16391
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11286115d7aedd4e2670cf8b0ca1b323d07c1eb7299504b220eaffdd5f7fb34
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:230d11b0635b62c8d71ce7a18328b0f4f745b7e34e9af7bd4b28b9619a5c17d6
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554b63547346f01bcd1aea7e2347724254eff214a1a2bf0e6eb4b88bf90226fd
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83b66f7d3e3bb1d4802b35177d184e9354bbd64d7275b9c06b66120776856d73
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:857ca14ec61342be0a9a1cc4185e41187d79bc8085bfaf148904e8e4fe2af5b4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -369,3 +369,173 @@
369
  {"current_steps": 369, "total_steps": 540, "loss": 0.4316, "lr": 2.7560040989976894e-06, "epoch": 2.0424354243542435, "percentage": 68.33, "elapsed_time": "1:48:57", "remaining_time": "0:50:29"}
370
  {"current_steps": 370, "total_steps": 540, "loss": 0.4271, "lr": 2.7271681614074973e-06, "epoch": 2.047970479704797, "percentage": 68.52, "elapsed_time": "1:49:14", "remaining_time": "0:50:11"}
371
  {"current_steps": 371, "total_steps": 540, "loss": 0.4226, "lr": 2.6984271952520723e-06, "epoch": 2.0535055350553506, "percentage": 68.7, "elapsed_time": "1:49:32", "remaining_time": "0:49:54"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
369
  {"current_steps": 369, "total_steps": 540, "loss": 0.4316, "lr": 2.7560040989976894e-06, "epoch": 2.0424354243542435, "percentage": 68.33, "elapsed_time": "1:48:57", "remaining_time": "0:50:29"}
370
  {"current_steps": 370, "total_steps": 540, "loss": 0.4271, "lr": 2.7271681614074973e-06, "epoch": 2.047970479704797, "percentage": 68.52, "elapsed_time": "1:49:14", "remaining_time": "0:50:11"}
371
  {"current_steps": 371, "total_steps": 540, "loss": 0.4226, "lr": 2.6984271952520723e-06, "epoch": 2.0535055350553506, "percentage": 68.7, "elapsed_time": "1:49:32", "remaining_time": "0:49:54"}
372
+ {"current_steps": 372, "total_steps": 540, "loss": 0.4414, "lr": 2.6697824014873076e-06, "epoch": 2.059040590405904, "percentage": 68.89, "elapsed_time": "1:49:49", "remaining_time": "0:49:35"}
373
+ {"current_steps": 373, "total_steps": 540, "loss": 0.4318, "lr": 2.641234977050484e-06, "epoch": 2.0645756457564577, "percentage": 69.07, "elapsed_time": "1:50:06", "remaining_time": "0:49:17"}
374
+ {"current_steps": 374, "total_steps": 540, "loss": 0.3978, "lr": 2.6127861148102552e-06, "epoch": 2.0701107011070112, "percentage": 69.26, "elapsed_time": "1:50:23", "remaining_time": "0:48:59"}
375
+ {"current_steps": 375, "total_steps": 540, "loss": 0.4202, "lr": 2.5844370035168077e-06, "epoch": 2.0756457564575648, "percentage": 69.44, "elapsed_time": "1:50:40", "remaining_time": "0:48:41"}
376
+ {"current_steps": 376, "total_steps": 540, "loss": 0.4305, "lr": 2.5561888277521797e-06, "epoch": 2.081180811808118, "percentage": 69.63, "elapsed_time": "1:50:58", "remaining_time": "0:48:24"}
377
+ {"current_steps": 377, "total_steps": 540, "loss": 0.4279, "lr": 2.528042767880766e-06, "epoch": 2.0867158671586714, "percentage": 69.81, "elapsed_time": "1:51:16", "remaining_time": "0:48:06"}
378
+ {"current_steps": 378, "total_steps": 540, "loss": 0.4201, "lr": 2.5000000000000015e-06, "epoch": 2.092250922509225, "percentage": 70.0, "elapsed_time": "1:51:34", "remaining_time": "0:47:48"}
379
+ {"current_steps": 379, "total_steps": 540, "loss": 0.4082, "lr": 2.4720616958912054e-06, "epoch": 2.0977859778597785, "percentage": 70.19, "elapsed_time": "1:51:49", "remaining_time": "0:47:30"}
380
+ {"current_steps": 380, "total_steps": 540, "loss": 0.4888, "lr": 2.4442290229706344e-06, "epoch": 2.103321033210332, "percentage": 70.37, "elapsed_time": "1:52:07", "remaining_time": "0:47:12"}
381
+ {"current_steps": 381, "total_steps": 540, "loss": 0.4131, "lr": 2.4165031442406857e-06, "epoch": 2.1088560885608856, "percentage": 70.56, "elapsed_time": "1:52:22", "remaining_time": "0:46:53"}
382
+ {"current_steps": 382, "total_steps": 540, "loss": 0.4433, "lr": 2.3888852182413087e-06, "epoch": 2.114391143911439, "percentage": 70.74, "elapsed_time": "1:52:38", "remaining_time": "0:46:35"}
383
+ {"current_steps": 383, "total_steps": 540, "loss": 0.399, "lr": 2.361376399001592e-06, "epoch": 2.1199261992619927, "percentage": 70.93, "elapsed_time": "1:52:55", "remaining_time": "0:46:17"}
384
+ {"current_steps": 384, "total_steps": 540, "loss": 0.4398, "lr": 2.333977835991545e-06, "epoch": 2.125461254612546, "percentage": 71.11, "elapsed_time": "1:53:13", "remaining_time": "0:45:59"}
385
+ {"current_steps": 385, "total_steps": 540, "loss": 0.4554, "lr": 2.3066906740740626e-06, "epoch": 2.1309963099630997, "percentage": 71.3, "elapsed_time": "1:53:30", "remaining_time": "0:45:41"}
386
+ {"current_steps": 386, "total_steps": 540, "loss": 0.4428, "lr": 2.2795160534570866e-06, "epoch": 2.1365313653136533, "percentage": 71.48, "elapsed_time": "1:53:48", "remaining_time": "0:45:24"}
387
+ {"current_steps": 387, "total_steps": 540, "loss": 0.4057, "lr": 2.2524551096459703e-06, "epoch": 2.142066420664207, "percentage": 71.67, "elapsed_time": "1:54:04", "remaining_time": "0:45:05"}
388
+ {"current_steps": 388, "total_steps": 540, "loss": 0.44, "lr": 2.2255089733960162e-06, "epoch": 2.14760147601476, "percentage": 71.85, "elapsed_time": "1:54:22", "remaining_time": "0:44:48"}
389
+ {"current_steps": 389, "total_steps": 540, "loss": 0.41, "lr": 2.1986787706652377e-06, "epoch": 2.1531365313653135, "percentage": 72.04, "elapsed_time": "1:54:40", "remaining_time": "0:44:30"}
390
+ {"current_steps": 390, "total_steps": 540, "loss": 0.4057, "lr": 2.171965622567308e-06, "epoch": 2.158671586715867, "percentage": 72.22, "elapsed_time": "1:54:58", "remaining_time": "0:44:13"}
391
+ {"current_steps": 391, "total_steps": 540, "loss": 0.4516, "lr": 2.1453706453247088e-06, "epoch": 2.1642066420664205, "percentage": 72.41, "elapsed_time": "1:55:15", "remaining_time": "0:43:55"}
392
+ {"current_steps": 392, "total_steps": 540, "loss": 0.4073, "lr": 2.1188949502220987e-06, "epoch": 2.169741697416974, "percentage": 72.59, "elapsed_time": "1:55:33", "remaining_time": "0:43:37"}
393
+ {"current_steps": 393, "total_steps": 540, "loss": 0.4351, "lr": 2.0925396435598665e-06, "epoch": 2.1752767527675276, "percentage": 72.78, "elapsed_time": "1:55:50", "remaining_time": "0:43:19"}
394
+ {"current_steps": 394, "total_steps": 540, "loss": 0.4179, "lr": 2.066305826607911e-06, "epoch": 2.180811808118081, "percentage": 72.96, "elapsed_time": "1:56:07", "remaining_time": "0:43:01"}
395
+ {"current_steps": 395, "total_steps": 540, "loss": 0.4003, "lr": 2.0401945955596206e-06, "epoch": 2.1863468634686347, "percentage": 73.15, "elapsed_time": "1:56:26", "remaining_time": "0:42:44"}
396
+ {"current_steps": 396, "total_steps": 540, "loss": 0.4333, "lr": 2.0142070414860704e-06, "epoch": 2.1918819188191883, "percentage": 73.33, "elapsed_time": "1:56:43", "remaining_time": "0:42:26"}
397
+ {"current_steps": 397, "total_steps": 540, "loss": 0.426, "lr": 1.9883442502904284e-06, "epoch": 2.197416974169742, "percentage": 73.52, "elapsed_time": "1:56:59", "remaining_time": "0:42:08"}
398
+ {"current_steps": 398, "total_steps": 540, "loss": 0.4453, "lr": 1.962607302662582e-06, "epoch": 2.2029520295202953, "percentage": 73.7, "elapsed_time": "1:57:17", "remaining_time": "0:41:50"}
399
+ {"current_steps": 399, "total_steps": 540, "loss": 0.4192, "lr": 1.936997274033986e-06, "epoch": 2.208487084870849, "percentage": 73.89, "elapsed_time": "1:57:35", "remaining_time": "0:41:33"}
400
+ {"current_steps": 400, "total_steps": 540, "loss": 0.4256, "lr": 1.9115152345327154e-06, "epoch": 2.2140221402214024, "percentage": 74.07, "elapsed_time": "1:57:54", "remaining_time": "0:41:16"}
401
+ {"current_steps": 401, "total_steps": 540, "loss": 0.4151, "lr": 1.8861622489387555e-06, "epoch": 2.2195571955719555, "percentage": 74.26, "elapsed_time": "1:58:12", "remaining_time": "0:40:58"}
402
+ {"current_steps": 402, "total_steps": 540, "loss": 0.3997, "lr": 1.8609393766395083e-06, "epoch": 2.225092250922509, "percentage": 74.44, "elapsed_time": "1:58:29", "remaining_time": "0:40:40"}
403
+ {"current_steps": 403, "total_steps": 540, "loss": 0.4265, "lr": 1.8358476715855262e-06, "epoch": 2.2306273062730626, "percentage": 74.63, "elapsed_time": "1:58:48", "remaining_time": "0:40:23"}
404
+ {"current_steps": 404, "total_steps": 540, "loss": 0.4449, "lr": 1.8108881822464697e-06, "epoch": 2.236162361623616, "percentage": 74.81, "elapsed_time": "1:59:05", "remaining_time": "0:40:05"}
405
+ {"current_steps": 405, "total_steps": 540, "loss": 0.408, "lr": 1.7860619515673034e-06, "epoch": 2.2416974169741697, "percentage": 75.0, "elapsed_time": "1:59:23", "remaining_time": "0:39:47"}
406
+ {"current_steps": 406, "total_steps": 540, "loss": 0.452, "lr": 1.7613700169247055e-06, "epoch": 2.2472324723247232, "percentage": 75.19, "elapsed_time": "1:59:40", "remaining_time": "0:39:29"}
407
+ {"current_steps": 407, "total_steps": 540, "loss": 0.3949, "lr": 1.7368134100837286e-06, "epoch": 2.2527675276752768, "percentage": 75.37, "elapsed_time": "1:59:56", "remaining_time": "0:39:11"}
408
+ {"current_steps": 408, "total_steps": 540, "loss": 0.4278, "lr": 1.7123931571546826e-06, "epoch": 2.2583025830258303, "percentage": 75.56, "elapsed_time": "2:00:13", "remaining_time": "0:38:53"}
409
+ {"current_steps": 409, "total_steps": 540, "loss": 0.4416, "lr": 1.6881102785502618e-06, "epoch": 2.263837638376384, "percentage": 75.74, "elapsed_time": "2:00:29", "remaining_time": "0:38:35"}
410
+ {"current_steps": 410, "total_steps": 540, "loss": 0.4121, "lr": 1.6639657889429017e-06, "epoch": 2.2693726937269374, "percentage": 75.93, "elapsed_time": "2:00:47", "remaining_time": "0:38:17"}
411
+ {"current_steps": 411, "total_steps": 540, "loss": 0.4011, "lr": 1.639960697222388e-06, "epoch": 2.274907749077491, "percentage": 76.11, "elapsed_time": "2:01:03", "remaining_time": "0:37:59"}
412
+ {"current_steps": 412, "total_steps": 540, "loss": 0.437, "lr": 1.6160960064536907e-06, "epoch": 2.280442804428044, "percentage": 76.3, "elapsed_time": "2:01:21", "remaining_time": "0:37:42"}
413
+ {"current_steps": 413, "total_steps": 540, "loss": 0.4307, "lr": 1.5923727138350548e-06, "epoch": 2.2859778597785976, "percentage": 76.48, "elapsed_time": "2:01:39", "remaining_time": "0:37:24"}
414
+ {"current_steps": 414, "total_steps": 540, "loss": 0.4381, "lr": 1.5687918106563326e-06, "epoch": 2.291512915129151, "percentage": 76.67, "elapsed_time": "2:01:58", "remaining_time": "0:37:07"}
415
+ {"current_steps": 415, "total_steps": 540, "loss": 0.3904, "lr": 1.5453542822575624e-06, "epoch": 2.2970479704797047, "percentage": 76.85, "elapsed_time": "2:02:14", "remaining_time": "0:36:49"}
416
+ {"current_steps": 416, "total_steps": 540, "loss": 0.4423, "lr": 1.52206110798779e-06, "epoch": 2.302583025830258, "percentage": 77.04, "elapsed_time": "2:02:33", "remaining_time": "0:36:31"}
417
+ {"current_steps": 417, "total_steps": 540, "loss": 0.4685, "lr": 1.4989132611641576e-06, "epoch": 2.3081180811808117, "percentage": 77.22, "elapsed_time": "2:02:52", "remaining_time": "0:36:14"}
418
+ {"current_steps": 418, "total_steps": 540, "loss": 0.4268, "lr": 1.4759117090312197e-06, "epoch": 2.3136531365313653, "percentage": 77.41, "elapsed_time": "2:03:09", "remaining_time": "0:35:56"}
419
+ {"current_steps": 419, "total_steps": 540, "loss": 0.4169, "lr": 1.453057412720536e-06, "epoch": 2.319188191881919, "percentage": 77.59, "elapsed_time": "2:03:28", "remaining_time": "0:35:39"}
420
+ {"current_steps": 420, "total_steps": 540, "loss": 0.4785, "lr": 1.4303513272105057e-06, "epoch": 2.3247232472324724, "percentage": 77.78, "elapsed_time": "2:03:46", "remaining_time": "0:35:21"}
421
+ {"current_steps": 421, "total_steps": 540, "loss": 0.4251, "lr": 1.4077944012864636e-06, "epoch": 2.330258302583026, "percentage": 77.96, "elapsed_time": "2:04:04", "remaining_time": "0:35:04"}
422
+ {"current_steps": 422, "total_steps": 540, "loss": 0.4076, "lr": 1.3853875775010355e-06, "epoch": 2.3357933579335795, "percentage": 78.15, "elapsed_time": "2:04:22", "remaining_time": "0:34:46"}
423
+ {"current_steps": 423, "total_steps": 540, "loss": 0.4358, "lr": 1.3631317921347564e-06, "epoch": 2.341328413284133, "percentage": 78.33, "elapsed_time": "2:04:38", "remaining_time": "0:34:28"}
424
+ {"current_steps": 424, "total_steps": 540, "loss": 0.4008, "lr": 1.3410279751569399e-06, "epoch": 2.3468634686346865, "percentage": 78.52, "elapsed_time": "2:04:56", "remaining_time": "0:34:10"}
425
+ {"current_steps": 425, "total_steps": 540, "loss": 0.4216, "lr": 1.3190770501868243e-06, "epoch": 2.35239852398524, "percentage": 78.7, "elapsed_time": "2:05:14", "remaining_time": "0:33:53"}
426
+ {"current_steps": 426, "total_steps": 540, "loss": 0.4286, "lr": 1.297279934454978e-06, "epoch": 2.357933579335793, "percentage": 78.89, "elapsed_time": "2:05:32", "remaining_time": "0:33:35"}
427
+ {"current_steps": 427, "total_steps": 540, "loss": 0.4369, "lr": 1.2756375387649717e-06, "epoch": 2.3634686346863467, "percentage": 79.07, "elapsed_time": "2:05:49", "remaining_time": "0:33:17"}
428
+ {"current_steps": 428, "total_steps": 540, "loss": 0.4092, "lr": 1.25415076745532e-06, "epoch": 2.3690036900369003, "percentage": 79.26, "elapsed_time": "2:06:06", "remaining_time": "0:33:00"}
429
+ {"current_steps": 429, "total_steps": 540, "loss": 0.4342, "lr": 1.2328205183616964e-06, "epoch": 2.374538745387454, "percentage": 79.44, "elapsed_time": "2:06:24", "remaining_time": "0:32:42"}
430
+ {"current_steps": 430, "total_steps": 540, "loss": 0.436, "lr": 1.2116476827794104e-06, "epoch": 2.3800738007380073, "percentage": 79.63, "elapsed_time": "2:06:41", "remaining_time": "0:32:24"}
431
+ {"current_steps": 431, "total_steps": 540, "loss": 0.4116, "lr": 1.1906331454261704e-06, "epoch": 2.385608856088561, "percentage": 79.81, "elapsed_time": "2:06:59", "remaining_time": "0:32:06"}
432
+ {"current_steps": 432, "total_steps": 540, "loss": 0.4411, "lr": 1.1697777844051105e-06, "epoch": 2.3911439114391144, "percentage": 80.0, "elapsed_time": "2:07:16", "remaining_time": "0:31:49"}
433
+ {"current_steps": 433, "total_steps": 540, "loss": 0.4284, "lr": 1.1490824711681026e-06, "epoch": 2.396678966789668, "percentage": 80.19, "elapsed_time": "2:07:32", "remaining_time": "0:31:31"}
434
+ {"current_steps": 434, "total_steps": 540, "loss": 0.4374, "lr": 1.1285480704793378e-06, "epoch": 2.4022140221402215, "percentage": 80.37, "elapsed_time": "2:07:48", "remaining_time": "0:31:12"}
435
+ {"current_steps": 435, "total_steps": 540, "loss": 0.3972, "lr": 1.1081754403792e-06, "epoch": 2.407749077490775, "percentage": 80.56, "elapsed_time": "2:08:06", "remaining_time": "0:30:55"}
436
+ {"current_steps": 436, "total_steps": 540, "loss": 0.4238, "lr": 1.0879654321484012e-06, "epoch": 2.4132841328413286, "percentage": 80.74, "elapsed_time": "2:08:24", "remaining_time": "0:30:37"}
437
+ {"current_steps": 437, "total_steps": 540, "loss": 0.4352, "lr": 1.067918890272419e-06, "epoch": 2.4188191881918817, "percentage": 80.93, "elapsed_time": "2:08:41", "remaining_time": "0:30:20"}
438
+ {"current_steps": 438, "total_steps": 540, "loss": 0.411, "lr": 1.0480366524062041e-06, "epoch": 2.4243542435424352, "percentage": 81.11, "elapsed_time": "2:08:59", "remaining_time": "0:30:02"}
439
+ {"current_steps": 439, "total_steps": 540, "loss": 0.4228, "lr": 1.0283195493391823e-06, "epoch": 2.4298892988929888, "percentage": 81.3, "elapsed_time": "2:09:14", "remaining_time": "0:29:44"}
440
+ {"current_steps": 440, "total_steps": 540, "loss": 0.4391, "lr": 1.008768404960535e-06, "epoch": 2.4354243542435423, "percentage": 81.48, "elapsed_time": "2:09:31", "remaining_time": "0:29:26"}
441
+ {"current_steps": 441, "total_steps": 540, "loss": 0.4274, "lr": 9.893840362247809e-07, "epoch": 2.440959409594096, "percentage": 81.67, "elapsed_time": "2:09:46", "remaining_time": "0:29:08"}
442
+ {"current_steps": 442, "total_steps": 540, "loss": 0.4078, "lr": 9.701672531176287e-07, "epoch": 2.4464944649446494, "percentage": 81.85, "elapsed_time": "2:10:02", "remaining_time": "0:28:50"}
443
+ {"current_steps": 443, "total_steps": 540, "loss": 0.4328, "lr": 9.511188586221376e-07, "epoch": 2.452029520295203, "percentage": 82.04, "elapsed_time": "2:10:21", "remaining_time": "0:28:32"}
444
+ {"current_steps": 444, "total_steps": 540, "loss": 0.4133, "lr": 9.322396486851626e-07, "epoch": 2.4575645756457565, "percentage": 82.22, "elapsed_time": "2:10:39", "remaining_time": "0:28:14"}
445
+ {"current_steps": 445, "total_steps": 540, "loss": 0.4343, "lr": 9.135304121840976e-07, "epoch": 2.46309963099631, "percentage": 82.41, "elapsed_time": "2:10:57", "remaining_time": "0:27:57"}
446
+ {"current_steps": 446, "total_steps": 540, "loss": 0.4297, "lr": 8.949919308939081e-07, "epoch": 2.4686346863468636, "percentage": 82.59, "elapsed_time": "2:11:15", "remaining_time": "0:27:39"}
447
+ {"current_steps": 447, "total_steps": 540, "loss": 0.4287, "lr": 8.766249794544662e-07, "epoch": 2.474169741697417, "percentage": 82.78, "elapsed_time": "2:11:34", "remaining_time": "0:27:22"}
448
+ {"current_steps": 448, "total_steps": 540, "loss": 0.4312, "lr": 8.584303253381848e-07, "epoch": 2.4797047970479706, "percentage": 82.96, "elapsed_time": "2:11:52", "remaining_time": "0:27:04"}
449
+ {"current_steps": 449, "total_steps": 540, "loss": 0.4333, "lr": 8.404087288179425e-07, "epoch": 2.485239852398524, "percentage": 83.15, "elapsed_time": "2:12:07", "remaining_time": "0:26:46"}
450
+ {"current_steps": 450, "total_steps": 540, "loss": 0.4041, "lr": 8.225609429353187e-07, "epoch": 2.4907749077490777, "percentage": 83.33, "elapsed_time": "2:12:23", "remaining_time": "0:26:28"}
451
+ {"current_steps": 451, "total_steps": 540, "loss": 0.4291, "lr": 8.048877134691269e-07, "epoch": 2.496309963099631, "percentage": 83.52, "elapsed_time": "2:12:40", "remaining_time": "0:26:10"}
452
+ {"current_steps": 452, "total_steps": 540, "loss": 0.4364, "lr": 7.873897789042523e-07, "epoch": 2.5018450184501844, "percentage": 83.7, "elapsed_time": "2:12:56", "remaining_time": "0:25:52"}
453
+ {"current_steps": 453, "total_steps": 540, "loss": 0.4075, "lr": 7.700678704007947e-07, "epoch": 2.507380073800738, "percentage": 83.89, "elapsed_time": "2:13:14", "remaining_time": "0:25:35"}
454
+ {"current_steps": 454, "total_steps": 540, "loss": 0.469, "lr": 7.529227117635135e-07, "epoch": 2.5129151291512914, "percentage": 84.07, "elapsed_time": "2:13:31", "remaining_time": "0:25:17"}
455
+ {"current_steps": 455, "total_steps": 540, "loss": 0.4057, "lr": 7.35955019411585e-07, "epoch": 2.518450184501845, "percentage": 84.26, "elapsed_time": "2:13:49", "remaining_time": "0:25:00"}
456
+ {"current_steps": 456, "total_steps": 540, "loss": 0.4276, "lr": 7.191655023486682e-07, "epoch": 2.5239852398523985, "percentage": 84.44, "elapsed_time": "2:14:07", "remaining_time": "0:24:42"}
457
+ {"current_steps": 457, "total_steps": 540, "loss": 0.373, "lr": 7.02554862133275e-07, "epoch": 2.529520295202952, "percentage": 84.63, "elapsed_time": "2:14:24", "remaining_time": "0:24:24"}
458
+ {"current_steps": 458, "total_steps": 540, "loss": 0.4577, "lr": 6.86123792849458e-07, "epoch": 2.5350553505535056, "percentage": 84.81, "elapsed_time": "2:14:42", "remaining_time": "0:24:07"}
459
+ {"current_steps": 459, "total_steps": 540, "loss": 0.4319, "lr": 6.698729810778065e-07, "epoch": 2.540590405904059, "percentage": 85.0, "elapsed_time": "2:15:00", "remaining_time": "0:23:49"}
460
+ {"current_steps": 460, "total_steps": 540, "loss": 0.451, "lr": 6.53803105866761e-07, "epoch": 2.5461254612546127, "percentage": 85.19, "elapsed_time": "2:15:17", "remaining_time": "0:23:31"}
461
+ {"current_steps": 461, "total_steps": 540, "loss": 0.4268, "lr": 6.379148387042317e-07, "epoch": 2.551660516605166, "percentage": 85.37, "elapsed_time": "2:15:33", "remaining_time": "0:23:13"}
462
+ {"current_steps": 462, "total_steps": 540, "loss": 0.4334, "lr": 6.222088434895462e-07, "epoch": 2.5571955719557193, "percentage": 85.56, "elapsed_time": "2:15:51", "remaining_time": "0:22:56"}
463
+ {"current_steps": 463, "total_steps": 540, "loss": 0.4104, "lr": 6.066857765057055e-07, "epoch": 2.562730627306273, "percentage": 85.74, "elapsed_time": "2:16:08", "remaining_time": "0:22:38"}
464
+ {"current_steps": 464, "total_steps": 540, "loss": 0.4341, "lr": 5.9134628639196e-07, "epoch": 2.5682656826568264, "percentage": 85.93, "elapsed_time": "2:16:27", "remaining_time": "0:22:21"}
465
+ {"current_steps": 465, "total_steps": 540, "loss": 0.3998, "lr": 5.76191014116711e-07, "epoch": 2.57380073800738, "percentage": 86.11, "elapsed_time": "2:16:44", "remaining_time": "0:22:03"}
466
+ {"current_steps": 466, "total_steps": 540, "loss": 0.448, "lr": 5.612205929507209e-07, "epoch": 2.5793357933579335, "percentage": 86.3, "elapsed_time": "2:17:01", "remaining_time": "0:21:45"}
467
+ {"current_steps": 467, "total_steps": 540, "loss": 0.4164, "lr": 5.464356484406535e-07, "epoch": 2.584870848708487, "percentage": 86.48, "elapsed_time": "2:17:19", "remaining_time": "0:21:27"}
468
+ {"current_steps": 468, "total_steps": 540, "loss": 0.4037, "lr": 5.318367983829393e-07, "epoch": 2.5904059040590406, "percentage": 86.67, "elapsed_time": "2:17:36", "remaining_time": "0:21:10"}
469
+ {"current_steps": 469, "total_steps": 540, "loss": 0.433, "lr": 5.174246527979532e-07, "epoch": 2.595940959409594, "percentage": 86.85, "elapsed_time": "2:17:53", "remaining_time": "0:20:52"}
470
+ {"current_steps": 470, "total_steps": 540, "loss": 0.4153, "lr": 5.031998139045352e-07, "epoch": 2.6014760147601477, "percentage": 87.04, "elapsed_time": "2:18:10", "remaining_time": "0:20:34"}
471
+ {"current_steps": 471, "total_steps": 540, "loss": 0.3974, "lr": 4.891628760948114e-07, "epoch": 2.607011070110701, "percentage": 87.22, "elapsed_time": "2:18:28", "remaining_time": "0:20:17"}
472
+ {"current_steps": 472, "total_steps": 540, "loss": 0.4423, "lr": 4.753144259093734e-07, "epoch": 2.6125461254612548, "percentage": 87.41, "elapsed_time": "2:18:46", "remaining_time": "0:19:59"}
473
+ {"current_steps": 473, "total_steps": 540, "loss": 0.395, "lr": 4.6165504201275635e-07, "epoch": 2.6180811808118083, "percentage": 87.59, "elapsed_time": "2:19:03", "remaining_time": "0:19:41"}
474
+ {"current_steps": 474, "total_steps": 540, "loss": 0.4765, "lr": 4.481852951692672e-07, "epoch": 2.623616236162362, "percentage": 87.78, "elapsed_time": "2:19:22", "remaining_time": "0:19:24"}
475
+ {"current_steps": 475, "total_steps": 540, "loss": 0.4114, "lr": 4.349057482191299e-07, "epoch": 2.6291512915129154, "percentage": 87.96, "elapsed_time": "2:19:40", "remaining_time": "0:19:06"}
476
+ {"current_steps": 476, "total_steps": 540, "loss": 0.4303, "lr": 4.2181695605497066e-07, "epoch": 2.6346863468634685, "percentage": 88.15, "elapsed_time": "2:19:57", "remaining_time": "0:18:49"}
477
+ {"current_steps": 477, "total_steps": 540, "loss": 0.4139, "lr": 4.089194655986306e-07, "epoch": 2.640221402214022, "percentage": 88.33, "elapsed_time": "2:20:14", "remaining_time": "0:18:31"}
478
+ {"current_steps": 478, "total_steps": 540, "loss": 0.4477, "lr": 3.9621381577830855e-07, "epoch": 2.6457564575645756, "percentage": 88.52, "elapsed_time": "2:20:32", "remaining_time": "0:18:13"}
479
+ {"current_steps": 479, "total_steps": 540, "loss": 0.4206, "lr": 3.837005375060482e-07, "epoch": 2.651291512915129, "percentage": 88.7, "elapsed_time": "2:20:48", "remaining_time": "0:17:55"}
480
+ {"current_steps": 480, "total_steps": 540, "loss": 0.4182, "lr": 3.7138015365554834e-07, "epoch": 2.6568265682656826, "percentage": 88.89, "elapsed_time": "2:21:06", "remaining_time": "0:17:38"}
481
+ {"current_steps": 481, "total_steps": 540, "loss": 0.4215, "lr": 3.592531790403159e-07, "epoch": 2.662361623616236, "percentage": 89.07, "elapsed_time": "2:21:21", "remaining_time": "0:17:20"}
482
+ {"current_steps": 482, "total_steps": 540, "loss": 0.4129, "lr": 3.473201203921578e-07, "epoch": 2.6678966789667897, "percentage": 89.26, "elapsed_time": "2:21:39", "remaining_time": "0:17:02"}
483
+ {"current_steps": 483, "total_steps": 540, "loss": 0.4473, "lr": 3.355814763399973e-07, "epoch": 2.6734317343173433, "percentage": 89.44, "elapsed_time": "2:21:57", "remaining_time": "0:16:45"}
484
+ {"current_steps": 484, "total_steps": 540, "loss": 0.4295, "lr": 3.2403773738905185e-07, "epoch": 2.678966789667897, "percentage": 89.63, "elapsed_time": "2:22:15", "remaining_time": "0:16:27"}
485
+ {"current_steps": 485, "total_steps": 540, "loss": 0.4394, "lr": 3.1268938590032495e-07, "epoch": 2.6845018450184504, "percentage": 89.81, "elapsed_time": "2:22:32", "remaining_time": "0:16:09"}
486
+ {"current_steps": 486, "total_steps": 540, "loss": 0.4313, "lr": 3.015368960704584e-07, "epoch": 2.6900369003690034, "percentage": 90.0, "elapsed_time": "2:22:50", "remaining_time": "0:15:52"}
487
+ {"current_steps": 487, "total_steps": 540, "loss": 0.3799, "lr": 2.905807339119138e-07, "epoch": 2.695571955719557, "percentage": 90.19, "elapsed_time": "2:23:06", "remaining_time": "0:15:34"}
488
+ {"current_steps": 488, "total_steps": 540, "loss": 0.437, "lr": 2.798213572335001e-07, "epoch": 2.7011070110701105, "percentage": 90.37, "elapsed_time": "2:23:24", "remaining_time": "0:15:16"}
489
+ {"current_steps": 489, "total_steps": 540, "loss": 0.4299, "lr": 2.6925921562124867e-07, "epoch": 2.706642066420664, "percentage": 90.56, "elapsed_time": "2:23:42", "remaining_time": "0:14:59"}
490
+ {"current_steps": 490, "total_steps": 540, "loss": 0.4329, "lr": 2.5889475041961767e-07, "epoch": 2.7121771217712176, "percentage": 90.74, "elapsed_time": "2:24:00", "remaining_time": "0:14:41"}
491
+ {"current_steps": 491, "total_steps": 540, "loss": 0.4254, "lr": 2.487283947130609e-07, "epoch": 2.717712177121771, "percentage": 90.93, "elapsed_time": "2:24:15", "remaining_time": "0:14:23"}
492
+ {"current_steps": 492, "total_steps": 540, "loss": 0.4161, "lr": 2.3876057330792344e-07, "epoch": 2.7232472324723247, "percentage": 91.11, "elapsed_time": "2:24:32", "remaining_time": "0:14:06"}
493
+ {"current_steps": 493, "total_steps": 540, "loss": 0.437, "lr": 2.289917027146943e-07, "epoch": 2.7287822878228782, "percentage": 91.3, "elapsed_time": "2:24:50", "remaining_time": "0:13:48"}
494
+ {"current_steps": 494, "total_steps": 540, "loss": 0.4064, "lr": 2.1942219113060215e-07, "epoch": 2.734317343173432, "percentage": 91.48, "elapsed_time": "2:25:07", "remaining_time": "0:13:30"}
495
+ {"current_steps": 495, "total_steps": 540, "loss": 0.4227, "lr": 2.1005243842255552e-07, "epoch": 2.7398523985239853, "percentage": 91.67, "elapsed_time": "2:25:25", "remaining_time": "0:13:13"}
496
+ {"current_steps": 496, "total_steps": 540, "loss": 0.4386, "lr": 2.0088283611044034e-07, "epoch": 2.745387453874539, "percentage": 91.85, "elapsed_time": "2:25:43", "remaining_time": "0:12:55"}
497
+ {"current_steps": 497, "total_steps": 540, "loss": 0.416, "lr": 1.919137673507543e-07, "epoch": 2.7509225092250924, "percentage": 92.04, "elapsed_time": "2:26:01", "remaining_time": "0:12:38"}
498
+ {"current_steps": 498, "total_steps": 540, "loss": 0.3909, "lr": 1.8314560692059836e-07, "epoch": 2.756457564575646, "percentage": 92.22, "elapsed_time": "2:26:17", "remaining_time": "0:12:20"}
499
+ {"current_steps": 499, "total_steps": 540, "loss": 0.4662, "lr": 1.745787212020178e-07, "epoch": 2.7619926199261995, "percentage": 92.41, "elapsed_time": "2:26:34", "remaining_time": "0:12:02"}
500
+ {"current_steps": 500, "total_steps": 540, "loss": 0.3959, "lr": 1.6621346816668993e-07, "epoch": 2.767527675276753, "percentage": 92.59, "elapsed_time": "2:26:51", "remaining_time": "0:11:44"}
501
+ {"current_steps": 501, "total_steps": 540, "loss": 0.4872, "lr": 1.5805019736097105e-07, "epoch": 2.773062730627306, "percentage": 92.78, "elapsed_time": "2:27:09", "remaining_time": "0:11:27"}
502
+ {"current_steps": 502, "total_steps": 540, "loss": 0.4125, "lr": 1.500892498912826e-07, "epoch": 2.7785977859778597, "percentage": 92.96, "elapsed_time": "2:27:28", "remaining_time": "0:11:09"}
503
+ {"current_steps": 503, "total_steps": 540, "loss": 0.4345, "lr": 1.4233095840986756e-07, "epoch": 2.784132841328413, "percentage": 93.15, "elapsed_time": "2:27:46", "remaining_time": "0:10:52"}
504
+ {"current_steps": 504, "total_steps": 540, "loss": 0.4016, "lr": 1.3477564710088097e-07, "epoch": 2.7896678966789668, "percentage": 93.33, "elapsed_time": "2:28:03", "remaining_time": "0:10:34"}
505
+ {"current_steps": 505, "total_steps": 540, "loss": 0.4398, "lr": 1.2742363166685035e-07, "epoch": 2.7952029520295203, "percentage": 93.52, "elapsed_time": "2:28:21", "remaining_time": "0:10:16"}
506
+ {"current_steps": 506, "total_steps": 540, "loss": 0.427, "lr": 1.2027521931548214e-07, "epoch": 2.800738007380074, "percentage": 93.7, "elapsed_time": "2:28:39", "remaining_time": "0:09:59"}
507
+ {"current_steps": 507, "total_steps": 540, "loss": 0.4564, "lr": 1.1333070874682217e-07, "epoch": 2.8062730627306274, "percentage": 93.89, "elapsed_time": "2:28:58", "remaining_time": "0:09:41"}
508
+ {"current_steps": 508, "total_steps": 540, "loss": 0.4195, "lr": 1.0659039014077943e-07, "epoch": 2.811808118081181, "percentage": 94.07, "elapsed_time": "2:29:14", "remaining_time": "0:09:24"}
509
+ {"current_steps": 509, "total_steps": 540, "loss": 0.424, "lr": 1.0005454514499413e-07, "epoch": 2.8173431734317345, "percentage": 94.26, "elapsed_time": "2:29:31", "remaining_time": "0:09:06"}
510
+ {"current_steps": 510, "total_steps": 540, "loss": 0.432, "lr": 9.372344686307655e-08, "epoch": 2.8228782287822876, "percentage": 94.44, "elapsed_time": "2:29:48", "remaining_time": "0:08:48"}
511
+ {"current_steps": 511, "total_steps": 540, "loss": 0.4167, "lr": 8.759735984318896e-08, "epoch": 2.828413284132841, "percentage": 94.63, "elapsed_time": "2:30:03", "remaining_time": "0:08:30"}
512
+ {"current_steps": 512, "total_steps": 540, "loss": 0.424, "lr": 8.167654006699444e-08, "epoch": 2.8339483394833946, "percentage": 94.81, "elapsed_time": "2:30:19", "remaining_time": "0:08:13"}
513
+ {"current_steps": 513, "total_steps": 540, "loss": 0.441, "lr": 7.59612349389599e-08, "epoch": 2.839483394833948, "percentage": 95.0, "elapsed_time": "2:30:36", "remaining_time": "0:07:55"}
514
+ {"current_steps": 514, "total_steps": 540, "loss": 0.4347, "lr": 7.04516832760177e-08, "epoch": 2.8450184501845017, "percentage": 95.19, "elapsed_time": "2:30:54", "remaining_time": "0:07:38"}
515
+ {"current_steps": 515, "total_steps": 540, "loss": 0.4011, "lr": 6.514811529758747e-08, "epoch": 2.8505535055350553, "percentage": 95.37, "elapsed_time": "2:31:10", "remaining_time": "0:07:20"}
516
+ {"current_steps": 516, "total_steps": 540, "loss": 0.4564, "lr": 6.005075261595495e-08, "epoch": 2.856088560885609, "percentage": 95.56, "elapsed_time": "2:31:29", "remaining_time": "0:07:02"}
517
+ {"current_steps": 517, "total_steps": 540, "loss": 0.4166, "lr": 5.515980822701439e-08, "epoch": 2.8616236162361623, "percentage": 95.74, "elapsed_time": "2:31:47", "remaining_time": "0:06:45"}
518
+ {"current_steps": 518, "total_steps": 540, "loss": 0.4138, "lr": 5.047548650136513e-08, "epoch": 2.867158671586716, "percentage": 95.93, "elapsed_time": "2:32:04", "remaining_time": "0:06:27"}
519
+ {"current_steps": 519, "total_steps": 540, "loss": 0.4423, "lr": 4.599798317577342e-08, "epoch": 2.8726937269372694, "percentage": 96.11, "elapsed_time": "2:32:20", "remaining_time": "0:06:09"}
520
+ {"current_steps": 520, "total_steps": 540, "loss": 0.4414, "lr": 4.172748534499449e-08, "epoch": 2.878228782287823, "percentage": 96.3, "elapsed_time": "2:32:37", "remaining_time": "0:05:52"}
521
+ {"current_steps": 521, "total_steps": 540, "loss": 0.411, "lr": 3.766417145395218e-08, "epoch": 2.8837638376383765, "percentage": 96.48, "elapsed_time": "2:32:55", "remaining_time": "0:05:34"}
522
+ {"current_steps": 522, "total_steps": 540, "loss": 0.45, "lr": 3.3808211290284886e-08, "epoch": 2.88929889298893, "percentage": 96.67, "elapsed_time": "2:33:12", "remaining_time": "0:05:16"}
523
+ {"current_steps": 523, "total_steps": 540, "loss": 0.385, "lr": 3.015976597725068e-08, "epoch": 2.8948339483394836, "percentage": 96.85, "elapsed_time": "2:33:29", "remaining_time": "0:04:59"}
524
+ {"current_steps": 524, "total_steps": 540, "loss": 0.4098, "lr": 2.6718987966992683e-08, "epoch": 2.900369003690037, "percentage": 97.04, "elapsed_time": "2:33:46", "remaining_time": "0:04:41"}
525
+ {"current_steps": 525, "total_steps": 540, "loss": 0.4396, "lr": 2.3486021034170857e-08, "epoch": 2.9059040590405907, "percentage": 97.22, "elapsed_time": "2:34:03", "remaining_time": "0:04:24"}
526
+ {"current_steps": 526, "total_steps": 540, "loss": 0.4344, "lr": 2.0461000269953457e-08, "epoch": 2.911439114391144, "percentage": 97.41, "elapsed_time": "2:34:22", "remaining_time": "0:04:06"}
527
+ {"current_steps": 527, "total_steps": 540, "loss": 0.4035, "lr": 1.7644052076371544e-08, "epoch": 2.9169741697416973, "percentage": 97.59, "elapsed_time": "2:34:39", "remaining_time": "0:03:48"}
528
+ {"current_steps": 528, "total_steps": 540, "loss": 0.4298, "lr": 1.5035294161039882e-08, "epoch": 2.922509225092251, "percentage": 97.78, "elapsed_time": "2:34:56", "remaining_time": "0:03:31"}
529
+ {"current_steps": 529, "total_steps": 540, "loss": 0.3991, "lr": 1.2634835532233658e-08, "epoch": 2.9280442804428044, "percentage": 97.96, "elapsed_time": "2:35:12", "remaining_time": "0:03:13"}
530
+ {"current_steps": 530, "total_steps": 540, "loss": 0.4408, "lr": 1.044277649433989e-08, "epoch": 2.933579335793358, "percentage": 98.15, "elapsed_time": "2:35:30", "remaining_time": "0:02:56"}
531
+ {"current_steps": 531, "total_steps": 540, "loss": 0.4355, "lr": 8.459208643659122e-09, "epoch": 2.9391143911439115, "percentage": 98.33, "elapsed_time": "2:35:47", "remaining_time": "0:02:38"}
532
+ {"current_steps": 532, "total_steps": 540, "loss": 0.4172, "lr": 6.6842148645840374e-09, "epoch": 2.944649446494465, "percentage": 98.52, "elapsed_time": "2:36:06", "remaining_time": "0:02:20"}
533
+ {"current_steps": 533, "total_steps": 540, "loss": 0.4017, "lr": 5.11786932613223e-09, "epoch": 2.9501845018450186, "percentage": 98.7, "elapsed_time": "2:36:21", "remaining_time": "0:02:03"}
534
+ {"current_steps": 534, "total_steps": 540, "loss": 0.4419, "lr": 3.760237478849793e-09, "epoch": 2.955719557195572, "percentage": 98.89, "elapsed_time": "2:36:39", "remaining_time": "0:01:45"}
535
+ {"current_steps": 535, "total_steps": 540, "loss": 0.3918, "lr": 2.611376052073511e-09, "epoch": 2.961254612546125, "percentage": 99.07, "elapsed_time": "2:36:55", "remaining_time": "0:01:27"}
536
+ {"current_steps": 536, "total_steps": 540, "loss": 0.4201, "lr": 1.6713330515627512e-09, "epoch": 2.9667896678966788, "percentage": 99.26, "elapsed_time": "2:37:12", "remaining_time": "0:01:10"}
537
+ {"current_steps": 537, "total_steps": 540, "loss": 0.4355, "lr": 9.401477574932927e-10, "epoch": 2.9723247232472323, "percentage": 99.44, "elapsed_time": "2:37:28", "remaining_time": "0:00:52"}
538
+ {"current_steps": 538, "total_steps": 540, "loss": 0.4416, "lr": 4.178507228136397e-10, "epoch": 2.977859778597786, "percentage": 99.63, "elapsed_time": "2:37:47", "remaining_time": "0:00:35"}
539
+ {"current_steps": 539, "total_steps": 540, "loss": 0.4129, "lr": 1.0446377197104174e-10, "epoch": 2.9833948339483394, "percentage": 99.81, "elapsed_time": "2:38:03", "remaining_time": "0:00:17"}
540
+ {"current_steps": 540, "total_steps": 540, "loss": 0.4395, "lr": 0.0, "epoch": 2.988929889298893, "percentage": 100.0, "elapsed_time": "2:38:19", "remaining_time": "0:00:00"}
541
+ {"current_steps": 540, "total_steps": 540, "epoch": 2.988929889298893, "percentage": 100.0, "elapsed_time": "2:41:27", "remaining_time": "0:00:00"}