EtashGuha commited on
Commit
f1a868e
·
verified ·
1 Parent(s): 970a16f

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d574a4052c841507efe5c06b817aee006d20c633eeceac473912f5ea5760b0
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8253d00619d6ca130d8d71f53558c1b0a3c327c0d6f178ab2a172a5aebd57853
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c8471e2182f8c95f343db962bfd35153a2c39795ffd1c8cea490c647d87d3f2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ab610849605168cf551450166a8ba33fc8d9a86f010b7e7d7a3f6d7737d114
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e810a775431c430b268a2bf8a69c9937b8936ce82041d250e1384d9b06d1b7c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29074e9b5d5faf0dd52942fe9fadd557ceb81481aa9582a83c7088ee2daadea5
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20d8510f6702104da935c978c86f65a670a4738a5ed08291f3f0c0c410b6da9f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c731fdd24e70dfd890db9d8b2ae771f8a051d85084c2b22131c28a63e778e4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -387,3 +387,79 @@
387
  {"current_steps": 387, "total_steps": 465, "loss": 0.0325, "lr": 3.3393572992349156e-06, "epoch": 4.1225033288948065, "percentage": 83.23, "elapsed_time": "1:06:06", "remaining_time": "0:13:19"}
388
  {"current_steps": 388, "total_steps": 465, "loss": 0.0296, "lr": 3.2566704347494295e-06, "epoch": 4.133155792276964, "percentage": 83.44, "elapsed_time": "1:06:16", "remaining_time": "0:13:09"}
389
  {"current_steps": 389, "total_steps": 465, "loss": 0.0248, "lr": 3.174929343376374e-06, "epoch": 4.143808255659121, "percentage": 83.66, "elapsed_time": "1:06:25", "remaining_time": "0:12:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
387
  {"current_steps": 387, "total_steps": 465, "loss": 0.0325, "lr": 3.3393572992349156e-06, "epoch": 4.1225033288948065, "percentage": 83.23, "elapsed_time": "1:06:06", "remaining_time": "0:13:19"}
388
  {"current_steps": 388, "total_steps": 465, "loss": 0.0296, "lr": 3.2566704347494295e-06, "epoch": 4.133155792276964, "percentage": 83.44, "elapsed_time": "1:06:16", "remaining_time": "0:13:09"}
389
  {"current_steps": 389, "total_steps": 465, "loss": 0.0248, "lr": 3.174929343376374e-06, "epoch": 4.143808255659121, "percentage": 83.66, "elapsed_time": "1:06:25", "remaining_time": "0:12:58"}
390
+ {"current_steps": 390, "total_steps": 465, "loss": 0.0225, "lr": 3.0941386423889287e-06, "epoch": 4.154460719041278, "percentage": 83.87, "elapsed_time": "1:06:34", "remaining_time": "0:12:48"}
391
+ {"current_steps": 391, "total_steps": 465, "loss": 0.0234, "lr": 3.0143028953759756e-06, "epoch": 4.165113182423435, "percentage": 84.09, "elapsed_time": "1:06:43", "remaining_time": "0:12:37"}
392
+ {"current_steps": 392, "total_steps": 465, "loss": 0.0295, "lr": 2.9354266119843268e-06, "epoch": 4.175765645805592, "percentage": 84.3, "elapsed_time": "1:06:52", "remaining_time": "0:12:27"}
393
+ {"current_steps": 393, "total_steps": 465, "loss": 0.0266, "lr": 2.8575142476640106e-06, "epoch": 4.186418109187749, "percentage": 84.52, "elapsed_time": "1:07:01", "remaining_time": "0:12:16"}
394
+ {"current_steps": 394, "total_steps": 465, "loss": 0.0266, "lr": 2.7805702034165726e-06, "epoch": 4.197070572569907, "percentage": 84.73, "elapsed_time": "1:07:09", "remaining_time": "0:12:06"}
395
+ {"current_steps": 395, "total_steps": 465, "loss": 0.0187, "lr": 2.704598825546483e-06, "epoch": 4.207723035952064, "percentage": 84.95, "elapsed_time": "1:07:18", "remaining_time": "0:11:55"}
396
+ {"current_steps": 396, "total_steps": 465, "loss": 0.0324, "lr": 2.6296044054156446e-06, "epoch": 4.218375499334221, "percentage": 85.16, "elapsed_time": "1:07:27", "remaining_time": "0:11:45"}
397
+ {"current_steps": 397, "total_steps": 465, "loss": 0.0248, "lr": 2.5555911792009624e-06, "epoch": 4.229027962716378, "percentage": 85.38, "elapsed_time": "1:07:37", "remaining_time": "0:11:34"}
398
+ {"current_steps": 398, "total_steps": 465, "loss": 0.0315, "lr": 2.482563327655081e-06, "epoch": 4.239680426098535, "percentage": 85.59, "elapsed_time": "1:07:46", "remaining_time": "0:11:24"}
399
+ {"current_steps": 399, "total_steps": 465, "loss": 0.0299, "lr": 2.410524975870221e-06, "epoch": 4.250332889480692, "percentage": 85.81, "elapsed_time": "1:07:55", "remaining_time": "0:11:14"}
400
+ {"current_steps": 400, "total_steps": 465, "loss": 0.0372, "lr": 2.3394801930451492e-06, "epoch": 4.26098535286285, "percentage": 86.02, "elapsed_time": "1:08:04", "remaining_time": "0:11:03"}
401
+ {"current_steps": 401, "total_steps": 465, "loss": 0.0228, "lr": 2.269432992255358e-06, "epoch": 4.271637816245007, "percentage": 86.24, "elapsed_time": "1:08:13", "remaining_time": "0:10:53"}
402
+ {"current_steps": 402, "total_steps": 465, "loss": 0.0244, "lr": 2.2003873302263434e-06, "epoch": 4.282290279627164, "percentage": 86.45, "elapsed_time": "1:08:22", "remaining_time": "0:10:42"}
403
+ {"current_steps": 403, "total_steps": 465, "loss": 0.039, "lr": 2.132347107110133e-06, "epoch": 4.292942743009321, "percentage": 86.67, "elapsed_time": "1:08:31", "remaining_time": "0:10:32"}
404
+ {"current_steps": 404, "total_steps": 465, "loss": 0.0248, "lr": 2.0653161662649633e-06, "epoch": 4.303595206391478, "percentage": 86.88, "elapsed_time": "1:08:40", "remaining_time": "0:10:22"}
405
+ {"current_steps": 405, "total_steps": 465, "loss": 0.0302, "lr": 1.9992982940381834e-06, "epoch": 4.314247669773636, "percentage": 87.1, "elapsed_time": "1:08:49", "remaining_time": "0:10:11"}
406
+ {"current_steps": 406, "total_steps": 465, "loss": 0.0222, "lr": 1.9342972195523837e-06, "epoch": 4.324900133155793, "percentage": 87.31, "elapsed_time": "1:08:58", "remaining_time": "0:10:01"}
407
+ {"current_steps": 407, "total_steps": 465, "loss": 0.0219, "lr": 1.8703166144947427e-06, "epoch": 4.3355525965379496, "percentage": 87.53, "elapsed_time": "1:09:06", "remaining_time": "0:09:50"}
408
+ {"current_steps": 408, "total_steps": 465, "loss": 0.0278, "lr": 1.8073600929096314e-06, "epoch": 4.3462050599201065, "percentage": 87.74, "elapsed_time": "1:09:15", "remaining_time": "0:09:40"}
409
+ {"current_steps": 409, "total_steps": 465, "loss": 0.0233, "lr": 1.7454312109944749e-06, "epoch": 4.3568575233022635, "percentage": 87.96, "elapsed_time": "1:09:24", "remaining_time": "0:09:30"}
410
+ {"current_steps": 410, "total_steps": 465, "loss": 0.024, "lr": 1.68453346689885e-06, "epoch": 4.3675099866844205, "percentage": 88.17, "elapsed_time": "1:09:34", "remaining_time": "0:09:19"}
411
+ {"current_steps": 411, "total_steps": 465, "loss": 0.0241, "lr": 1.624670300526925e-06, "epoch": 4.3781624500665774, "percentage": 88.39, "elapsed_time": "1:09:43", "remaining_time": "0:09:09"}
412
+ {"current_steps": 412, "total_steps": 465, "loss": 0.0203, "lr": 1.5658450933431103e-06, "epoch": 4.388814913448735, "percentage": 88.6, "elapsed_time": "1:09:52", "remaining_time": "0:08:59"}
413
+ {"current_steps": 413, "total_steps": 465, "loss": 0.0267, "lr": 1.5080611681810742e-06, "epoch": 4.399467376830892, "percentage": 88.82, "elapsed_time": "1:10:01", "remaining_time": "0:08:48"}
414
+ {"current_steps": 414, "total_steps": 465, "loss": 0.025, "lr": 1.4513217890560638e-06, "epoch": 4.410119840213049, "percentage": 89.03, "elapsed_time": "1:10:09", "remaining_time": "0:08:38"}
415
+ {"current_steps": 415, "total_steps": 465, "loss": 0.0248, "lr": 1.3956301609804901e-06, "epoch": 4.420772303595206, "percentage": 89.25, "elapsed_time": "1:10:18", "remaining_time": "0:08:28"}
416
+ {"current_steps": 416, "total_steps": 465, "loss": 0.0213, "lr": 1.3409894297829217e-06, "epoch": 4.431424766977363, "percentage": 89.46, "elapsed_time": "1:10:27", "remaining_time": "0:08:17"}
417
+ {"current_steps": 417, "total_steps": 465, "loss": 0.0199, "lr": 1.2874026819303698e-06, "epoch": 4.442077230359521, "percentage": 89.68, "elapsed_time": "1:10:36", "remaining_time": "0:08:07"}
418
+ {"current_steps": 418, "total_steps": 465, "loss": 0.0267, "lr": 1.2348729443539487e-06, "epoch": 4.452729693741678, "percentage": 89.89, "elapsed_time": "1:10:45", "remaining_time": "0:07:57"}
419
+ {"current_steps": 419, "total_steps": 465, "loss": 0.0249, "lr": 1.1834031842779137e-06, "epoch": 4.463382157123835, "percentage": 90.11, "elapsed_time": "1:10:54", "remaining_time": "0:07:47"}
420
+ {"current_steps": 420, "total_steps": 465, "loss": 0.0232, "lr": 1.1329963090520147e-06, "epoch": 4.474034620505992, "percentage": 90.32, "elapsed_time": "1:11:03", "remaining_time": "0:07:36"}
421
+ {"current_steps": 421, "total_steps": 465, "loss": 0.0342, "lr": 1.0836551659873073e-06, "epoch": 4.484687083888149, "percentage": 90.54, "elapsed_time": "1:11:12", "remaining_time": "0:07:26"}
422
+ {"current_steps": 422, "total_steps": 465, "loss": 0.0225, "lr": 1.0353825421952935e-06, "epoch": 4.495339547270306, "percentage": 90.75, "elapsed_time": "1:11:21", "remaining_time": "0:07:16"}
423
+ {"current_steps": 423, "total_steps": 465, "loss": 0.0247, "lr": 9.881811644304907e-07, "epoch": 4.505992010652463, "percentage": 90.97, "elapsed_time": "1:11:30", "remaining_time": "0:07:06"}
424
+ {"current_steps": 424, "total_steps": 465, "loss": 0.0206, "lr": 9.420536989364292e-07, "epoch": 4.516644474034621, "percentage": 91.18, "elapsed_time": "1:11:39", "remaining_time": "0:06:55"}
425
+ {"current_steps": 425, "total_steps": 465, "loss": 0.0239, "lr": 8.970027512950152e-07, "epoch": 4.527296937416778, "percentage": 91.4, "elapsed_time": "1:11:48", "remaining_time": "0:06:45"}
426
+ {"current_steps": 426, "total_steps": 465, "loss": 0.0298, "lr": 8.53030866279363e-07, "epoch": 4.537949400798935, "percentage": 91.61, "elapsed_time": "1:11:58", "remaining_time": "0:06:35"}
427
+ {"current_steps": 427, "total_steps": 465, "loss": 0.0244, "lr": 8.101405277100549e-07, "epoch": 4.548601864181092, "percentage": 91.83, "elapsed_time": "1:12:07", "remaining_time": "0:06:25"}
428
+ {"current_steps": 428, "total_steps": 465, "loss": 0.0252, "lr": 7.683341583148274e-07, "epoch": 4.559254327563249, "percentage": 92.04, "elapsed_time": "1:12:16", "remaining_time": "0:06:14"}
429
+ {"current_steps": 429, "total_steps": 465, "loss": 0.0213, "lr": 7.27614119591733e-07, "epoch": 4.5699067909454065, "percentage": 92.26, "elapsed_time": "1:12:24", "remaining_time": "0:06:04"}
430
+ {"current_steps": 430, "total_steps": 465, "loss": 0.029, "lr": 6.87982711675741e-07, "epoch": 4.5805592543275635, "percentage": 92.47, "elapsed_time": "1:12:33", "remaining_time": "0:05:54"}
431
+ {"current_steps": 431, "total_steps": 465, "loss": 0.0184, "lr": 6.494421732087941e-07, "epoch": 4.5912117177097205, "percentage": 92.69, "elapsed_time": "1:12:42", "remaining_time": "0:05:44"}
432
+ {"current_steps": 432, "total_steps": 465, "loss": 0.0191, "lr": 6.119946812133926e-07, "epoch": 4.6018641810918774, "percentage": 92.9, "elapsed_time": "1:12:51", "remaining_time": "0:05:33"}
433
+ {"current_steps": 433, "total_steps": 465, "loss": 0.0279, "lr": 5.756423509695852e-07, "epoch": 4.612516644474034, "percentage": 93.12, "elapsed_time": "1:13:01", "remaining_time": "0:05:23"}
434
+ {"current_steps": 434, "total_steps": 465, "loss": 0.0255, "lr": 5.403872358955031e-07, "epoch": 4.623169107856191, "percentage": 93.33, "elapsed_time": "1:13:09", "remaining_time": "0:05:13"}
435
+ {"current_steps": 435, "total_steps": 465, "loss": 0.0264, "lr": 5.062313274313701e-07, "epoch": 4.633821571238348, "percentage": 93.55, "elapsed_time": "1:13:18", "remaining_time": "0:05:03"}
436
+ {"current_steps": 436, "total_steps": 465, "loss": 0.0277, "lr": 4.7317655492699953e-07, "epoch": 4.644474034620506, "percentage": 93.76, "elapsed_time": "1:13:27", "remaining_time": "0:04:53"}
437
+ {"current_steps": 437, "total_steps": 465, "loss": 0.0243, "lr": 4.412247855328322e-07, "epoch": 4.655126498002663, "percentage": 93.98, "elapsed_time": "1:13:36", "remaining_time": "0:04:42"}
438
+ {"current_steps": 438, "total_steps": 465, "loss": 0.0315, "lr": 4.1037782409444337e-07, "epoch": 4.66577896138482, "percentage": 94.19, "elapsed_time": "1:13:45", "remaining_time": "0:04:32"}
439
+ {"current_steps": 439, "total_steps": 465, "loss": 0.029, "lr": 3.806374130506152e-07, "epoch": 4.676431424766977, "percentage": 94.41, "elapsed_time": "1:13:54", "remaining_time": "0:04:22"}
440
+ {"current_steps": 440, "total_steps": 465, "loss": 0.0199, "lr": 3.520052323349021e-07, "epoch": 4.687083888149134, "percentage": 94.62, "elapsed_time": "1:14:03", "remaining_time": "0:04:12"}
441
+ {"current_steps": 441, "total_steps": 465, "loss": 0.0246, "lr": 3.244828992807336e-07, "epoch": 4.697736351531292, "percentage": 94.84, "elapsed_time": "1:14:12", "remaining_time": "0:04:02"}
442
+ {"current_steps": 442, "total_steps": 465, "loss": 0.0223, "lr": 2.980719685300648e-07, "epoch": 4.708388814913449, "percentage": 95.05, "elapsed_time": "1:14:21", "remaining_time": "0:03:52"}
443
+ {"current_steps": 443, "total_steps": 465, "loss": 0.0244, "lr": 2.7277393194555357e-07, "epoch": 4.719041278295606, "percentage": 95.27, "elapsed_time": "1:14:30", "remaining_time": "0:03:42"}
444
+ {"current_steps": 444, "total_steps": 465, "loss": 0.0312, "lr": 2.485902185262967e-07, "epoch": 4.729693741677763, "percentage": 95.48, "elapsed_time": "1:14:39", "remaining_time": "0:03:31"}
445
+ {"current_steps": 445, "total_steps": 465, "loss": 0.0217, "lr": 2.2552219432710577e-07, "epoch": 4.74034620505992, "percentage": 95.7, "elapsed_time": "1:14:48", "remaining_time": "0:03:21"}
446
+ {"current_steps": 446, "total_steps": 465, "loss": 0.0287, "lr": 2.0357116238134633e-07, "epoch": 4.750998668442077, "percentage": 95.91, "elapsed_time": "1:14:57", "remaining_time": "0:03:11"}
447
+ {"current_steps": 447, "total_steps": 465, "loss": 0.0202, "lr": 1.8273836262732824e-07, "epoch": 4.761651131824235, "percentage": 96.13, "elapsed_time": "1:15:05", "remaining_time": "0:03:01"}
448
+ {"current_steps": 448, "total_steps": 465, "loss": 0.0298, "lr": 1.6302497183827038e-07, "epoch": 4.772303595206392, "percentage": 96.34, "elapsed_time": "1:15:14", "remaining_time": "0:02:51"}
449
+ {"current_steps": 449, "total_steps": 465, "loss": 0.0304, "lr": 1.444321035558338e-07, "epoch": 4.782956058588549, "percentage": 96.56, "elapsed_time": "1:15:24", "remaining_time": "0:02:41"}
450
+ {"current_steps": 450, "total_steps": 465, "loss": 0.0254, "lr": 1.2696080802721666e-07, "epoch": 4.793608521970706, "percentage": 96.77, "elapsed_time": "1:15:33", "remaining_time": "0:02:31"}
451
+ {"current_steps": 451, "total_steps": 465, "loss": 0.0236, "lr": 1.1061207214581703e-07, "epoch": 4.804260985352863, "percentage": 96.99, "elapsed_time": "1:15:42", "remaining_time": "0:02:21"}
452
+ {"current_steps": 452, "total_steps": 465, "loss": 0.0401, "lr": 9.538681939551319e-08, "epoch": 4.81491344873502, "percentage": 97.2, "elapsed_time": "1:15:51", "remaining_time": "0:02:10"}
453
+ {"current_steps": 453, "total_steps": 465, "loss": 0.0285, "lr": 8.128590979847639e-08, "epoch": 4.8255659121171774, "percentage": 97.42, "elapsed_time": "1:16:00", "remaining_time": "0:02:00"}
454
+ {"current_steps": 454, "total_steps": 465, "loss": 0.0212, "lr": 6.831013986660307e-08, "epoch": 4.836218375499334, "percentage": 97.63, "elapsed_time": "1:16:09", "remaining_time": "0:01:50"}
455
+ {"current_steps": 455, "total_steps": 465, "loss": 0.0226, "lr": 5.646024255651528e-08, "epoch": 4.846870838881491, "percentage": 97.85, "elapsed_time": "1:16:18", "remaining_time": "0:01:40"}
456
+ {"current_steps": 456, "total_steps": 465, "loss": 0.0303, "lr": 4.5736887228164936e-08, "epoch": 4.857523302263648, "percentage": 98.06, "elapsed_time": "1:16:27", "remaining_time": "0:01:30"}
457
+ {"current_steps": 457, "total_steps": 465, "loss": 0.0345, "lr": 3.614067960701961e-08, "epoch": 4.868175765645805, "percentage": 98.28, "elapsed_time": "1:16:37", "remaining_time": "0:01:20"}
458
+ {"current_steps": 458, "total_steps": 465, "loss": 0.0252, "lr": 2.76721617498521e-08, "epoch": 4.878828229027963, "percentage": 98.49, "elapsed_time": "1:16:46", "remaining_time": "0:01:10"}
459
+ {"current_steps": 459, "total_steps": 465, "loss": 0.0278, "lr": 2.0331812014113828e-08, "epoch": 4.88948069241012, "percentage": 98.71, "elapsed_time": "1:16:54", "remaining_time": "0:01:00"}
460
+ {"current_steps": 460, "total_steps": 465, "loss": 0.0317, "lr": 1.4120045030920904e-08, "epoch": 4.900133155792277, "percentage": 98.92, "elapsed_time": "1:17:04", "remaining_time": "0:00:50"}
461
+ {"current_steps": 461, "total_steps": 465, "loss": 0.0237, "lr": 9.037211681630631e-09, "epoch": 4.910785619174434, "percentage": 99.14, "elapsed_time": "1:17:13", "remaining_time": "0:00:40"}
462
+ {"current_steps": 462, "total_steps": 465, "loss": 0.0235, "lr": 5.083599078017365e-09, "epoch": 4.921438082556591, "percentage": 99.35, "elapsed_time": "1:17:22", "remaining_time": "0:00:30"}
463
+ {"current_steps": 463, "total_steps": 465, "loss": 0.021, "lr": 2.259430546067698e-09, "epoch": 4.932090545938748, "percentage": 99.57, "elapsed_time": "1:17:31", "remaining_time": "0:00:20"}
464
+ {"current_steps": 464, "total_steps": 465, "loss": 0.0212, "lr": 5.648656133461217e-10, "epoch": 4.942743009320905, "percentage": 99.78, "elapsed_time": "1:17:40", "remaining_time": "0:00:10"}
465
+ {"current_steps": 465, "total_steps": 465, "loss": 0.0345, "lr": 0.0, "epoch": 4.953395472703063, "percentage": 100.0, "elapsed_time": "1:17:49", "remaining_time": "0:00:00"}