EtashGuha commited on
Commit
1ff0e76
·
verified ·
1 Parent(s): dcbdc61

Training in progress, epoch 6

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30545f50674caa083b2149ab25a4084051608722c4bd7e02fe8e1dcaee544cb5
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52909e864d17cca4105dce9a17e2672771dd303d9e393414e0cfafb7877ff720
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80d35ddefecd1455c641c86e938c7576a7e7129cbeefa76a0b65d82415c22d9d
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d209fe8fa27d6b5016b667566459694c1529a2b10bbb9633496d5c3eecc7b1dc
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:e12fcea60006b74344880e5debea69de9b5c52661144c9669ba69595cb208d3e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:180f9b3cd7c86aa92b055fd8fb235d83ddbdf6f78e8ca31ac30d9593ac350004
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:058b16763dcd4a4726c423a75784a7732c0bcf0da3f1d925f6b72c135fc4b03c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8600937c392d70e310646348883c18eeb077bf2f3f460123777ff954a6c7464
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -408,3 +408,84 @@
408
  {"current_steps": 408, "total_steps": 567, "loss": 0.0035, "lr": 4.425105606571145e-06, "epoch": 5.037037037037037, "percentage": 71.96, "elapsed_time": "3:09:01", "remaining_time": "1:13:39"}
409
  {"current_steps": 409, "total_steps": 567, "loss": 0.0026, "lr": 4.374072483801769e-06, "epoch": 5.049382716049383, "percentage": 72.13, "elapsed_time": "3:09:25", "remaining_time": "1:13:10"}
410
  {"current_steps": 410, "total_steps": 567, "loss": 0.0024, "lr": 4.323252838554099e-06, "epoch": 5.061728395061729, "percentage": 72.31, "elapsed_time": "3:09:51", "remaining_time": "1:12:42"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  {"current_steps": 408, "total_steps": 567, "loss": 0.0035, "lr": 4.425105606571145e-06, "epoch": 5.037037037037037, "percentage": 71.96, "elapsed_time": "3:09:01", "remaining_time": "1:13:39"}
409
  {"current_steps": 409, "total_steps": 567, "loss": 0.0026, "lr": 4.374072483801769e-06, "epoch": 5.049382716049383, "percentage": 72.13, "elapsed_time": "3:09:25", "remaining_time": "1:13:10"}
410
  {"current_steps": 410, "total_steps": 567, "loss": 0.0024, "lr": 4.323252838554099e-06, "epoch": 5.061728395061729, "percentage": 72.31, "elapsed_time": "3:09:51", "remaining_time": "1:12:42"}
411
+ {"current_steps": 411, "total_steps": 567, "loss": 0.0016, "lr": 4.272648599194948e-06, "epoch": 5.074074074074074, "percentage": 72.49, "elapsed_time": "3:10:16", "remaining_time": "1:12:13"}
412
+ {"current_steps": 412, "total_steps": 567, "loss": 0.0061, "lr": 4.222261685917489e-06, "epoch": 5.08641975308642, "percentage": 72.66, "elapsed_time": "3:10:42", "remaining_time": "1:11:44"}
413
+ {"current_steps": 413, "total_steps": 567, "loss": 0.0017, "lr": 4.1720940106683915e-06, "epoch": 5.098765432098766, "percentage": 72.84, "elapsed_time": "3:11:12", "remaining_time": "1:11:17"}
414
+ {"current_steps": 414, "total_steps": 567, "loss": 0.0029, "lr": 4.12214747707527e-06, "epoch": 5.111111111111111, "percentage": 73.02, "elapsed_time": "3:11:37", "remaining_time": "1:10:49"}
415
+ {"current_steps": 415, "total_steps": 567, "loss": 0.0058, "lr": 4.0724239803744524e-06, "epoch": 5.1234567901234565, "percentage": 73.19, "elapsed_time": "3:12:07", "remaining_time": "1:10:21"}
416
+ {"current_steps": 416, "total_steps": 567, "loss": 0.0046, "lr": 4.022925407339064e-06, "epoch": 5.135802469135802, "percentage": 73.37, "elapsed_time": "3:12:37", "remaining_time": "1:09:55"}
417
+ {"current_steps": 417, "total_steps": 567, "loss": 0.0028, "lr": 3.973653636207437e-06, "epoch": 5.148148148148148, "percentage": 73.54, "elapsed_time": "3:13:02", "remaining_time": "1:09:26"}
418
+ {"current_steps": 418, "total_steps": 567, "loss": 0.0035, "lr": 3.924610536611833e-06, "epoch": 5.160493827160494, "percentage": 73.72, "elapsed_time": "3:13:33", "remaining_time": "1:08:59"}
419
+ {"current_steps": 419, "total_steps": 567, "loss": 0.0029, "lr": 3.875797969507502e-06, "epoch": 5.172839506172839, "percentage": 73.9, "elapsed_time": "3:13:59", "remaining_time": "1:08:31"}
420
+ {"current_steps": 420, "total_steps": 567, "loss": 0.0021, "lr": 3.827217787102072e-06, "epoch": 5.185185185185185, "percentage": 74.07, "elapsed_time": "3:14:28", "remaining_time": "1:08:03"}
421
+ {"current_steps": 421, "total_steps": 567, "loss": 0.0021, "lr": 3.7788718327852625e-06, "epoch": 5.197530864197531, "percentage": 74.25, "elapsed_time": "3:14:58", "remaining_time": "1:07:37"}
422
+ {"current_steps": 422, "total_steps": 567, "loss": 0.0048, "lr": 3.730761941058938e-06, "epoch": 5.209876543209877, "percentage": 74.43, "elapsed_time": "3:15:29", "remaining_time": "1:07:10"}
423
+ {"current_steps": 423, "total_steps": 567, "loss": 0.003, "lr": 3.6828899374674933e-06, "epoch": 5.222222222222222, "percentage": 74.6, "elapsed_time": "3:15:55", "remaining_time": "1:06:41"}
424
+ {"current_steps": 424, "total_steps": 567, "loss": 0.0028, "lr": 3.635257638528589e-06, "epoch": 5.234567901234568, "percentage": 74.78, "elapsed_time": "3:16:17", "remaining_time": "1:06:12"}
425
+ {"current_steps": 425, "total_steps": 567, "loss": 0.0021, "lr": 3.587866851664219e-06, "epoch": 5.246913580246914, "percentage": 74.96, "elapsed_time": "3:16:43", "remaining_time": "1:05:43"}
426
+ {"current_steps": 426, "total_steps": 567, "loss": 0.0016, "lr": 3.540719375132129e-06, "epoch": 5.2592592592592595, "percentage": 75.13, "elapsed_time": "3:17:09", "remaining_time": "1:05:15"}
427
+ {"current_steps": 427, "total_steps": 567, "loss": 0.0047, "lr": 3.493816997957582e-06, "epoch": 5.271604938271605, "percentage": 75.31, "elapsed_time": "3:17:29", "remaining_time": "1:04:45"}
428
+ {"current_steps": 428, "total_steps": 567, "loss": 0.0018, "lr": 3.447161499865467e-06, "epoch": 5.283950617283951, "percentage": 75.49, "elapsed_time": "3:17:56", "remaining_time": "1:04:17"}
429
+ {"current_steps": 429, "total_steps": 567, "loss": 0.0019, "lr": 3.4007546512127764e-06, "epoch": 5.296296296296296, "percentage": 75.66, "elapsed_time": "3:18:21", "remaining_time": "1:03:48"}
430
+ {"current_steps": 430, "total_steps": 567, "loss": 0.0015, "lr": 3.3545982129214227e-06, "epoch": 5.308641975308642, "percentage": 75.84, "elapsed_time": "3:18:49", "remaining_time": "1:03:20"}
431
+ {"current_steps": 431, "total_steps": 567, "loss": 0.0043, "lr": 3.308693936411421e-06, "epoch": 5.320987654320987, "percentage": 76.01, "elapsed_time": "3:19:18", "remaining_time": "1:02:53"}
432
+ {"current_steps": 432, "total_steps": 567, "loss": 0.0035, "lr": 3.2630435635344283e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "3:19:44", "remaining_time": "1:02:25"}
433
+ {"current_steps": 433, "total_steps": 567, "loss": 0.004, "lr": 3.21764882650766e-06, "epoch": 5.345679012345679, "percentage": 76.37, "elapsed_time": "3:20:10", "remaining_time": "1:01:56"}
434
+ {"current_steps": 434, "total_steps": 567, "loss": 0.0026, "lr": 3.1725114478481458e-06, "epoch": 5.3580246913580245, "percentage": 76.54, "elapsed_time": "3:20:37", "remaining_time": "1:01:28"}
435
+ {"current_steps": 435, "total_steps": 567, "loss": 0.0113, "lr": 3.1276331403073733e-06, "epoch": 5.37037037037037, "percentage": 76.72, "elapsed_time": "3:21:01", "remaining_time": "1:00:59"}
436
+ {"current_steps": 436, "total_steps": 567, "loss": 0.0016, "lr": 3.0830156068063e-06, "epoch": 5.382716049382716, "percentage": 76.9, "elapsed_time": "3:21:24", "remaining_time": "1:00:31"}
437
+ {"current_steps": 437, "total_steps": 567, "loss": 0.0029, "lr": 3.0386605403707347e-06, "epoch": 5.395061728395062, "percentage": 77.07, "elapsed_time": "3:21:52", "remaining_time": "1:00:03"}
438
+ {"current_steps": 438, "total_steps": 567, "loss": 0.007, "lr": 2.9945696240670905e-06, "epoch": 5.407407407407407, "percentage": 77.25, "elapsed_time": "3:22:20", "remaining_time": "0:59:35"}
439
+ {"current_steps": 439, "total_steps": 567, "loss": 0.0037, "lr": 2.95074453093853e-06, "epoch": 5.419753086419753, "percentage": 77.43, "elapsed_time": "3:22:45", "remaining_time": "0:59:07"}
440
+ {"current_steps": 440, "total_steps": 567, "loss": 0.0029, "lr": 2.907186923941466e-06, "epoch": 5.432098765432099, "percentage": 77.6, "elapsed_time": "3:23:14", "remaining_time": "0:58:39"}
441
+ {"current_steps": 441, "total_steps": 567, "loss": 0.0056, "lr": 2.8638984558824777e-06, "epoch": 5.444444444444445, "percentage": 77.78, "elapsed_time": "3:23:39", "remaining_time": "0:58:11"}
442
+ {"current_steps": 442, "total_steps": 567, "loss": 0.0023, "lr": 2.820880769355582e-06, "epoch": 5.45679012345679, "percentage": 77.95, "elapsed_time": "3:24:02", "remaining_time": "0:57:42"}
443
+ {"current_steps": 443, "total_steps": 567, "loss": 0.0043, "lr": 2.778135496679908e-06, "epoch": 5.469135802469136, "percentage": 78.13, "elapsed_time": "3:24:24", "remaining_time": "0:57:12"}
444
+ {"current_steps": 444, "total_steps": 567, "loss": 0.005, "lr": 2.7356642598377604e-06, "epoch": 5.481481481481482, "percentage": 78.31, "elapsed_time": "3:24:48", "remaining_time": "0:56:44"}
445
+ {"current_steps": 445, "total_steps": 567, "loss": 0.0021, "lr": 2.6934686704130698e-06, "epoch": 5.493827160493828, "percentage": 78.48, "elapsed_time": "3:25:20", "remaining_time": "0:56:17"}
446
+ {"current_steps": 446, "total_steps": 567, "loss": 0.0014, "lr": 2.6515503295302446e-06, "epoch": 5.506172839506172, "percentage": 78.66, "elapsed_time": "3:25:48", "remaining_time": "0:55:50"}
447
+ {"current_steps": 447, "total_steps": 567, "loss": 0.0038, "lr": 2.6099108277934105e-06, "epoch": 5.518518518518518, "percentage": 78.84, "elapsed_time": "3:26:15", "remaining_time": "0:55:22"}
448
+ {"current_steps": 448, "total_steps": 567, "loss": 0.0043, "lr": 2.5685517452260566e-06, "epoch": 5.530864197530864, "percentage": 79.01, "elapsed_time": "3:26:39", "remaining_time": "0:54:53"}
449
+ {"current_steps": 449, "total_steps": 567, "loss": 0.0016, "lr": 2.527474651211089e-06, "epoch": 5.54320987654321, "percentage": 79.19, "elapsed_time": "3:27:00", "remaining_time": "0:54:24"}
450
+ {"current_steps": 450, "total_steps": 567, "loss": 0.0095, "lr": 2.4866811044312667e-06, "epoch": 5.555555555555555, "percentage": 79.37, "elapsed_time": "3:27:26", "remaining_time": "0:53:56"}
451
+ {"current_steps": 451, "total_steps": 567, "loss": 0.0062, "lr": 2.4461726528100615e-06, "epoch": 5.567901234567901, "percentage": 79.54, "elapsed_time": "3:27:52", "remaining_time": "0:53:27"}
452
+ {"current_steps": 452, "total_steps": 567, "loss": 0.0043, "lr": 2.405950833452928e-06, "epoch": 5.580246913580247, "percentage": 79.72, "elapsed_time": "3:28:17", "remaining_time": "0:52:59"}
453
+ {"current_steps": 453, "total_steps": 567, "loss": 0.005, "lr": 2.3660171725889703e-06, "epoch": 5.592592592592593, "percentage": 79.89, "elapsed_time": "3:28:48", "remaining_time": "0:52:32"}
454
+ {"current_steps": 454, "total_steps": 567, "loss": 0.003, "lr": 2.32637318551303e-06, "epoch": 5.604938271604938, "percentage": 80.07, "elapsed_time": "3:29:16", "remaining_time": "0:52:05"}
455
+ {"current_steps": 455, "total_steps": 567, "loss": 0.0023, "lr": 2.287020376528193e-06, "epoch": 5.617283950617284, "percentage": 80.25, "elapsed_time": "3:29:46", "remaining_time": "0:51:38"}
456
+ {"current_steps": 456, "total_steps": 567, "loss": 0.0024, "lr": 2.2479602388887013e-06, "epoch": 5.62962962962963, "percentage": 80.42, "elapsed_time": "3:30:13", "remaining_time": "0:51:10"}
457
+ {"current_steps": 457, "total_steps": 567, "loss": 0.0041, "lr": 2.209194254743295e-06, "epoch": 5.6419753086419755, "percentage": 80.6, "elapsed_time": "3:30:38", "remaining_time": "0:50:42"}
458
+ {"current_steps": 458, "total_steps": 567, "loss": 0.0013, "lr": 2.170723895078972e-06, "epoch": 5.654320987654321, "percentage": 80.78, "elapsed_time": "3:31:02", "remaining_time": "0:50:13"}
459
+ {"current_steps": 459, "total_steps": 567, "loss": 0.0015, "lr": 2.132550619665168e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "3:31:29", "remaining_time": "0:49:45"}
460
+ {"current_steps": 460, "total_steps": 567, "loss": 0.0015, "lr": 2.0946758769983666e-06, "epoch": 5.679012345679013, "percentage": 81.13, "elapsed_time": "3:31:57", "remaining_time": "0:49:18"}
461
+ {"current_steps": 461, "total_steps": 567, "loss": 0.0022, "lr": 2.05710110424714e-06, "epoch": 5.6913580246913575, "percentage": 81.31, "elapsed_time": "3:32:20", "remaining_time": "0:48:49"}
462
+ {"current_steps": 462, "total_steps": 567, "loss": 0.0031, "lr": 2.019827727197605e-06, "epoch": 5.703703703703704, "percentage": 81.48, "elapsed_time": "3:32:46", "remaining_time": "0:48:21"}
463
+ {"current_steps": 463, "total_steps": 567, "loss": 0.0025, "lr": 1.982857160199334e-06, "epoch": 5.716049382716049, "percentage": 81.66, "elapsed_time": "3:33:12", "remaining_time": "0:47:53"}
464
+ {"current_steps": 464, "total_steps": 567, "loss": 0.0022, "lr": 1.946190806111674e-06, "epoch": 5.728395061728395, "percentage": 81.83, "elapsed_time": "3:33:39", "remaining_time": "0:47:25"}
465
+ {"current_steps": 465, "total_steps": 567, "loss": 0.0026, "lr": 1.9098300562505266e-06, "epoch": 5.7407407407407405, "percentage": 82.01, "elapsed_time": "3:34:10", "remaining_time": "0:46:58"}
466
+ {"current_steps": 466, "total_steps": 567, "loss": 0.0024, "lr": 1.873776290335545e-06, "epoch": 5.753086419753086, "percentage": 82.19, "elapsed_time": "3:34:32", "remaining_time": "0:46:29"}
467
+ {"current_steps": 467, "total_steps": 567, "loss": 0.0023, "lr": 1.8380308764377841e-06, "epoch": 5.765432098765432, "percentage": 82.36, "elapsed_time": "3:34:58", "remaining_time": "0:46:01"}
468
+ {"current_steps": 468, "total_steps": 567, "loss": 0.0026, "lr": 1.80259517092779e-06, "epoch": 5.777777777777778, "percentage": 82.54, "elapsed_time": "3:35:19", "remaining_time": "0:45:32"}
469
+ {"current_steps": 469, "total_steps": 567, "loss": 0.0023, "lr": 1.767470518424129e-06, "epoch": 5.790123456790123, "percentage": 82.72, "elapsed_time": "3:35:49", "remaining_time": "0:45:05"}
470
+ {"current_steps": 470, "total_steps": 567, "loss": 0.0014, "lr": 1.7326582517423662e-06, "epoch": 5.802469135802469, "percentage": 82.89, "elapsed_time": "3:36:18", "remaining_time": "0:44:38"}
471
+ {"current_steps": 471, "total_steps": 567, "loss": 0.0019, "lr": 1.6981596918444953e-06, "epoch": 5.814814814814815, "percentage": 83.07, "elapsed_time": "3:36:43", "remaining_time": "0:44:10"}
472
+ {"current_steps": 472, "total_steps": 567, "loss": 0.0013, "lr": 1.663976147788806e-06, "epoch": 5.827160493827161, "percentage": 83.25, "elapsed_time": "3:37:11", "remaining_time": "0:43:42"}
473
+ {"current_steps": 473, "total_steps": 567, "loss": 0.0017, "lr": 1.6301089166802232e-06, "epoch": 5.839506172839506, "percentage": 83.42, "elapsed_time": "3:37:35", "remaining_time": "0:43:14"}
474
+ {"current_steps": 474, "total_steps": 567, "loss": 0.0023, "lr": 1.596559283621074e-06, "epoch": 5.851851851851852, "percentage": 83.6, "elapsed_time": "3:38:04", "remaining_time": "0:42:47"}
475
+ {"current_steps": 475, "total_steps": 567, "loss": 0.0016, "lr": 1.5633285216623384e-06, "epoch": 5.864197530864198, "percentage": 83.77, "elapsed_time": "3:38:27", "remaining_time": "0:42:18"}
476
+ {"current_steps": 476, "total_steps": 567, "loss": 0.0012, "lr": 1.5304178917553302e-06, "epoch": 5.8765432098765435, "percentage": 83.95, "elapsed_time": "3:38:55", "remaining_time": "0:41:51"}
477
+ {"current_steps": 477, "total_steps": 567, "loss": 0.003, "lr": 1.4978286427038602e-06, "epoch": 5.888888888888889, "percentage": 84.13, "elapsed_time": "3:39:21", "remaining_time": "0:41:23"}
478
+ {"current_steps": 478, "total_steps": 567, "loss": 0.002, "lr": 1.4655620111168422e-06, "epoch": 5.901234567901234, "percentage": 84.3, "elapsed_time": "3:39:43", "remaining_time": "0:40:54"}
479
+ {"current_steps": 479, "total_steps": 567, "loss": 0.0059, "lr": 1.4336192213613742e-06, "epoch": 5.91358024691358, "percentage": 84.48, "elapsed_time": "3:40:06", "remaining_time": "0:40:26"}
480
+ {"current_steps": 480, "total_steps": 567, "loss": 0.0053, "lr": 1.4020014855162755e-06, "epoch": 5.925925925925926, "percentage": 84.66, "elapsed_time": "3:40:28", "remaining_time": "0:39:57"}
481
+ {"current_steps": 481, "total_steps": 567, "loss": 0.0031, "lr": 1.3707100033261035e-06, "epoch": 5.938271604938271, "percentage": 84.83, "elapsed_time": "3:40:51", "remaining_time": "0:39:29"}
482
+ {"current_steps": 482, "total_steps": 567, "loss": 0.0022, "lr": 1.339745962155613e-06, "epoch": 5.950617283950617, "percentage": 85.01, "elapsed_time": "3:41:16", "remaining_time": "0:39:01"}
483
+ {"current_steps": 483, "total_steps": 567, "loss": 0.0017, "lr": 1.3091105369447166e-06, "epoch": 5.962962962962963, "percentage": 85.19, "elapsed_time": "3:41:45", "remaining_time": "0:38:34"}
484
+ {"current_steps": 484, "total_steps": 567, "loss": 0.0017, "lr": 1.2788048901638917e-06, "epoch": 5.9753086419753085, "percentage": 85.36, "elapsed_time": "3:42:15", "remaining_time": "0:38:06"}
485
+ {"current_steps": 485, "total_steps": 567, "loss": 0.0016, "lr": 1.2488301717700735e-06, "epoch": 5.987654320987654, "percentage": 85.54, "elapsed_time": "3:42:43", "remaining_time": "0:37:39"}
486
+ {"current_steps": 486, "total_steps": 567, "loss": 0.0017, "lr": 1.2191875191630209e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "3:43:12", "remaining_time": "0:37:12"}
487
+ {"current_steps": 487, "total_steps": 567, "loss": 0.0013, "lr": 1.1898780571421554e-06, "epoch": 6.012345679012346, "percentage": 85.89, "elapsed_time": "3:44:40", "remaining_time": "0:36:54"}
488
+ {"current_steps": 488, "total_steps": 567, "loss": 0.0015, "lr": 1.1609028978638804e-06, "epoch": 6.0246913580246915, "percentage": 86.07, "elapsed_time": "3:45:04", "remaining_time": "0:36:26"}
489
+ {"current_steps": 489, "total_steps": 567, "loss": 0.0016, "lr": 1.132263140799381e-06, "epoch": 6.037037037037037, "percentage": 86.24, "elapsed_time": "3:45:35", "remaining_time": "0:35:59"}
490
+ {"current_steps": 490, "total_steps": 567, "loss": 0.0019, "lr": 1.1039598726929046e-06, "epoch": 6.049382716049383, "percentage": 86.42, "elapsed_time": "3:45:59", "remaining_time": "0:35:30"}
491
+ {"current_steps": 491, "total_steps": 567, "loss": 0.0019, "lr": 1.0759941675205221e-06, "epoch": 6.061728395061729, "percentage": 86.6, "elapsed_time": "3:46:24", "remaining_time": "0:35:02"}