sedrickkeh commited on
Commit
cd74fcf
·
verified ·
1 Parent(s): 393940e

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97491f415bf9d7d38043b6f656ec2864399aa31cb8a2c49a4a78f199dfde2595
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798a584425350fdfe6e3af7a2df1b6de6ca5470091ca5d51e61576e25521eea2
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:ce128c8a5229032a71ffa954b73ba1a30098ff6804eb93392833b739f7200cfc
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd4166499b64637458ac222c65fa32f11761f05a3d7c7edf1960ecb76f2c593
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74905481bd6a66d4bdc6cb212ece3221c92be772161f739f27495f2f6872e8cf
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e570e6ce464ffe5dd73411c683f98180066e74995b74c151addb175917311b86
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:dd84624c51e07eed2f27e94ac2ae82517eeff5852cedb3f9a25ae29fb5219f5f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3e0a73f09fdc45271830df5fe4a19571b3937ed158c396bbe7cf1c60173bc8
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -351,3 +351,175 @@
351
  {"current_steps": 3492, "total_steps": 5238, "eval_loss": 0.4207070767879486, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:18:30", "remaining_time": "3:39:15"}
352
  {"current_steps": 3500, "total_steps": 5238, "loss": 0.3263, "lr": 5e-06, "epoch": 2.004581901489118, "percentage": 66.82, "elapsed_time": "7:20:49", "remaining_time": "3:38:54"}
353
  {"current_steps": 3510, "total_steps": 5238, "loss": 0.3121, "lr": 5e-06, "epoch": 2.0103092783505154, "percentage": 67.01, "elapsed_time": "7:22:02", "remaining_time": "3:37:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
351
  {"current_steps": 3492, "total_steps": 5238, "eval_loss": 0.4207070767879486, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:18:30", "remaining_time": "3:39:15"}
352
  {"current_steps": 3500, "total_steps": 5238, "loss": 0.3263, "lr": 5e-06, "epoch": 2.004581901489118, "percentage": 66.82, "elapsed_time": "7:20:49", "remaining_time": "3:38:54"}
353
  {"current_steps": 3510, "total_steps": 5238, "loss": 0.3121, "lr": 5e-06, "epoch": 2.0103092783505154, "percentage": 67.01, "elapsed_time": "7:22:02", "remaining_time": "3:37:37"}
354
+ {"current_steps": 3520, "total_steps": 5238, "loss": 0.3064, "lr": 5e-06, "epoch": 2.016036655211913, "percentage": 67.2, "elapsed_time": "7:23:15", "remaining_time": "3:36:20"}
355
+ {"current_steps": 3530, "total_steps": 5238, "loss": 0.3114, "lr": 5e-06, "epoch": 2.0217640320733103, "percentage": 67.39, "elapsed_time": "7:24:27", "remaining_time": "3:35:03"}
356
+ {"current_steps": 3540, "total_steps": 5238, "loss": 0.309, "lr": 5e-06, "epoch": 2.027491408934708, "percentage": 67.58, "elapsed_time": "7:25:41", "remaining_time": "3:33:46"}
357
+ {"current_steps": 3550, "total_steps": 5238, "loss": 0.3152, "lr": 5e-06, "epoch": 2.0332187857961053, "percentage": 67.77, "elapsed_time": "7:26:54", "remaining_time": "3:32:29"}
358
+ {"current_steps": 3560, "total_steps": 5238, "loss": 0.3137, "lr": 5e-06, "epoch": 2.0389461626575027, "percentage": 67.96, "elapsed_time": "7:28:07", "remaining_time": "3:31:13"}
359
+ {"current_steps": 3570, "total_steps": 5238, "loss": 0.3142, "lr": 5e-06, "epoch": 2.0446735395189, "percentage": 68.16, "elapsed_time": "7:29:20", "remaining_time": "3:29:56"}
360
+ {"current_steps": 3580, "total_steps": 5238, "loss": 0.3138, "lr": 5e-06, "epoch": 2.0504009163802976, "percentage": 68.35, "elapsed_time": "7:30:33", "remaining_time": "3:28:40"}
361
+ {"current_steps": 3590, "total_steps": 5238, "loss": 0.3272, "lr": 5e-06, "epoch": 2.056128293241695, "percentage": 68.54, "elapsed_time": "7:31:47", "remaining_time": "3:27:23"}
362
+ {"current_steps": 3600, "total_steps": 5238, "loss": 0.3217, "lr": 5e-06, "epoch": 2.0618556701030926, "percentage": 68.73, "elapsed_time": "7:33:00", "remaining_time": "3:26:07"}
363
+ {"current_steps": 3610, "total_steps": 5238, "loss": 0.3126, "lr": 5e-06, "epoch": 2.0675830469644905, "percentage": 68.92, "elapsed_time": "7:34:14", "remaining_time": "3:24:50"}
364
+ {"current_steps": 3620, "total_steps": 5238, "loss": 0.3128, "lr": 5e-06, "epoch": 2.073310423825888, "percentage": 69.11, "elapsed_time": "7:35:27", "remaining_time": "3:23:34"}
365
+ {"current_steps": 3630, "total_steps": 5238, "loss": 0.3103, "lr": 5e-06, "epoch": 2.0790378006872854, "percentage": 69.3, "elapsed_time": "7:36:41", "remaining_time": "3:22:18"}
366
+ {"current_steps": 3640, "total_steps": 5238, "loss": 0.3122, "lr": 5e-06, "epoch": 2.084765177548683, "percentage": 69.49, "elapsed_time": "7:37:54", "remaining_time": "3:21:01"}
367
+ {"current_steps": 3650, "total_steps": 5238, "loss": 0.3241, "lr": 5e-06, "epoch": 2.0904925544100803, "percentage": 69.68, "elapsed_time": "7:39:08", "remaining_time": "3:19:45"}
368
+ {"current_steps": 3660, "total_steps": 5238, "loss": 0.3183, "lr": 5e-06, "epoch": 2.0962199312714778, "percentage": 69.87, "elapsed_time": "7:40:21", "remaining_time": "3:18:29"}
369
+ {"current_steps": 3670, "total_steps": 5238, "loss": 0.3142, "lr": 5e-06, "epoch": 2.1019473081328752, "percentage": 70.06, "elapsed_time": "7:41:35", "remaining_time": "3:17:12"}
370
+ {"current_steps": 3680, "total_steps": 5238, "loss": 0.3164, "lr": 5e-06, "epoch": 2.1076746849942727, "percentage": 70.26, "elapsed_time": "7:42:48", "remaining_time": "3:15:56"}
371
+ {"current_steps": 3690, "total_steps": 5238, "loss": 0.3121, "lr": 5e-06, "epoch": 2.11340206185567, "percentage": 70.45, "elapsed_time": "7:44:01", "remaining_time": "3:14:39"}
372
+ {"current_steps": 3700, "total_steps": 5238, "loss": 0.3134, "lr": 5e-06, "epoch": 2.1191294387170676, "percentage": 70.64, "elapsed_time": "7:45:14", "remaining_time": "3:13:23"}
373
+ {"current_steps": 3710, "total_steps": 5238, "loss": 0.3101, "lr": 5e-06, "epoch": 2.124856815578465, "percentage": 70.83, "elapsed_time": "7:46:27", "remaining_time": "3:12:06"}
374
+ {"current_steps": 3720, "total_steps": 5238, "loss": 0.3188, "lr": 5e-06, "epoch": 2.1305841924398625, "percentage": 71.02, "elapsed_time": "7:47:40", "remaining_time": "3:10:50"}
375
+ {"current_steps": 3730, "total_steps": 5238, "loss": 0.3153, "lr": 5e-06, "epoch": 2.13631156930126, "percentage": 71.21, "elapsed_time": "7:48:53", "remaining_time": "3:09:34"}
376
+ {"current_steps": 3740, "total_steps": 5238, "loss": 0.3123, "lr": 5e-06, "epoch": 2.1420389461626574, "percentage": 71.4, "elapsed_time": "7:50:06", "remaining_time": "3:08:17"}
377
+ {"current_steps": 3750, "total_steps": 5238, "loss": 0.3205, "lr": 5e-06, "epoch": 2.147766323024055, "percentage": 71.59, "elapsed_time": "7:51:19", "remaining_time": "3:07:01"}
378
+ {"current_steps": 3760, "total_steps": 5238, "loss": 0.3139, "lr": 5e-06, "epoch": 2.1534936998854524, "percentage": 71.78, "elapsed_time": "7:52:33", "remaining_time": "3:05:45"}
379
+ {"current_steps": 3770, "total_steps": 5238, "loss": 0.3182, "lr": 5e-06, "epoch": 2.15922107674685, "percentage": 71.97, "elapsed_time": "7:53:46", "remaining_time": "3:04:28"}
380
+ {"current_steps": 3780, "total_steps": 5238, "loss": 0.317, "lr": 5e-06, "epoch": 2.1649484536082473, "percentage": 72.16, "elapsed_time": "7:54:59", "remaining_time": "3:03:12"}
381
+ {"current_steps": 3790, "total_steps": 5238, "loss": 0.3232, "lr": 5e-06, "epoch": 2.1706758304696447, "percentage": 72.36, "elapsed_time": "7:56:12", "remaining_time": "3:01:56"}
382
+ {"current_steps": 3800, "total_steps": 5238, "loss": 0.315, "lr": 5e-06, "epoch": 2.176403207331042, "percentage": 72.55, "elapsed_time": "7:57:25", "remaining_time": "3:00:40"}
383
+ {"current_steps": 3810, "total_steps": 5238, "loss": 0.3157, "lr": 5e-06, "epoch": 2.1821305841924397, "percentage": 72.74, "elapsed_time": "7:58:39", "remaining_time": "2:59:24"}
384
+ {"current_steps": 3820, "total_steps": 5238, "loss": 0.3126, "lr": 5e-06, "epoch": 2.1878579610538376, "percentage": 72.93, "elapsed_time": "7:59:51", "remaining_time": "2:58:07"}
385
+ {"current_steps": 3830, "total_steps": 5238, "loss": 0.3128, "lr": 5e-06, "epoch": 2.193585337915235, "percentage": 73.12, "elapsed_time": "8:01:04", "remaining_time": "2:56:51"}
386
+ {"current_steps": 3840, "total_steps": 5238, "loss": 0.3197, "lr": 5e-06, "epoch": 2.1993127147766325, "percentage": 73.31, "elapsed_time": "8:02:17", "remaining_time": "2:55:35"}
387
+ {"current_steps": 3850, "total_steps": 5238, "loss": 0.3167, "lr": 5e-06, "epoch": 2.20504009163803, "percentage": 73.5, "elapsed_time": "8:03:30", "remaining_time": "2:54:18"}
388
+ {"current_steps": 3860, "total_steps": 5238, "loss": 0.3221, "lr": 5e-06, "epoch": 2.2107674684994274, "percentage": 73.69, "elapsed_time": "8:04:43", "remaining_time": "2:53:02"}
389
+ {"current_steps": 3870, "total_steps": 5238, "loss": 0.3209, "lr": 5e-06, "epoch": 2.216494845360825, "percentage": 73.88, "elapsed_time": "8:05:57", "remaining_time": "2:51:46"}
390
+ {"current_steps": 3880, "total_steps": 5238, "loss": 0.3201, "lr": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "8:07:10", "remaining_time": "2:50:30"}
391
+ {"current_steps": 3890, "total_steps": 5238, "loss": 0.3239, "lr": 5e-06, "epoch": 2.22794959908362, "percentage": 74.26, "elapsed_time": "8:08:23", "remaining_time": "2:49:14"}
392
+ {"current_steps": 3900, "total_steps": 5238, "loss": 0.3137, "lr": 5e-06, "epoch": 2.2336769759450172, "percentage": 74.46, "elapsed_time": "8:09:37", "remaining_time": "2:47:58"}
393
+ {"current_steps": 3910, "total_steps": 5238, "loss": 0.3157, "lr": 5e-06, "epoch": 2.2394043528064147, "percentage": 74.65, "elapsed_time": "8:10:50", "remaining_time": "2:46:42"}
394
+ {"current_steps": 3920, "total_steps": 5238, "loss": 0.3228, "lr": 5e-06, "epoch": 2.245131729667812, "percentage": 74.84, "elapsed_time": "8:12:03", "remaining_time": "2:45:26"}
395
+ {"current_steps": 3930, "total_steps": 5238, "loss": 0.3123, "lr": 5e-06, "epoch": 2.2508591065292096, "percentage": 75.03, "elapsed_time": "8:13:16", "remaining_time": "2:44:10"}
396
+ {"current_steps": 3940, "total_steps": 5238, "loss": 0.3135, "lr": 5e-06, "epoch": 2.256586483390607, "percentage": 75.22, "elapsed_time": "8:14:29", "remaining_time": "2:42:54"}
397
+ {"current_steps": 3950, "total_steps": 5238, "loss": 0.3166, "lr": 5e-06, "epoch": 2.2623138602520045, "percentage": 75.41, "elapsed_time": "8:15:42", "remaining_time": "2:41:38"}
398
+ {"current_steps": 3960, "total_steps": 5238, "loss": 0.3202, "lr": 5e-06, "epoch": 2.268041237113402, "percentage": 75.6, "elapsed_time": "8:16:55", "remaining_time": "2:40:22"}
399
+ {"current_steps": 3970, "total_steps": 5238, "loss": 0.323, "lr": 5e-06, "epoch": 2.2737686139747995, "percentage": 75.79, "elapsed_time": "8:18:08", "remaining_time": "2:39:06"}
400
+ {"current_steps": 3980, "total_steps": 5238, "loss": 0.3156, "lr": 5e-06, "epoch": 2.279495990836197, "percentage": 75.98, "elapsed_time": "8:19:22", "remaining_time": "2:37:50"}
401
+ {"current_steps": 3990, "total_steps": 5238, "loss": 0.319, "lr": 5e-06, "epoch": 2.2852233676975944, "percentage": 76.17, "elapsed_time": "8:20:34", "remaining_time": "2:36:34"}
402
+ {"current_steps": 4000, "total_steps": 5238, "loss": 0.3208, "lr": 5e-06, "epoch": 2.290950744558992, "percentage": 76.37, "elapsed_time": "8:21:47", "remaining_time": "2:35:18"}
403
+ {"current_steps": 4010, "total_steps": 5238, "loss": 0.3151, "lr": 5e-06, "epoch": 2.2966781214203893, "percentage": 76.56, "elapsed_time": "8:23:00", "remaining_time": "2:34:02"}
404
+ {"current_steps": 4020, "total_steps": 5238, "loss": 0.3198, "lr": 5e-06, "epoch": 2.3024054982817868, "percentage": 76.75, "elapsed_time": "8:24:13", "remaining_time": "2:32:46"}
405
+ {"current_steps": 4030, "total_steps": 5238, "loss": 0.3104, "lr": 5e-06, "epoch": 2.308132875143184, "percentage": 76.94, "elapsed_time": "8:25:26", "remaining_time": "2:31:30"}
406
+ {"current_steps": 4040, "total_steps": 5238, "loss": 0.3223, "lr": 5e-06, "epoch": 2.3138602520045817, "percentage": 77.13, "elapsed_time": "8:26:39", "remaining_time": "2:30:14"}
407
+ {"current_steps": 4050, "total_steps": 5238, "loss": 0.3183, "lr": 5e-06, "epoch": 2.319587628865979, "percentage": 77.32, "elapsed_time": "8:27:52", "remaining_time": "2:28:58"}
408
+ {"current_steps": 4060, "total_steps": 5238, "loss": 0.3125, "lr": 5e-06, "epoch": 2.325315005727377, "percentage": 77.51, "elapsed_time": "8:29:05", "remaining_time": "2:27:42"}
409
+ {"current_steps": 4070, "total_steps": 5238, "loss": 0.3166, "lr": 5e-06, "epoch": 2.3310423825887745, "percentage": 77.7, "elapsed_time": "8:30:18", "remaining_time": "2:26:26"}
410
+ {"current_steps": 4080, "total_steps": 5238, "loss": 0.3241, "lr": 5e-06, "epoch": 2.336769759450172, "percentage": 77.89, "elapsed_time": "8:31:31", "remaining_time": "2:25:10"}
411
+ {"current_steps": 4090, "total_steps": 5238, "loss": 0.3267, "lr": 5e-06, "epoch": 2.3424971363115694, "percentage": 78.08, "elapsed_time": "8:32:43", "remaining_time": "2:23:54"}
412
+ {"current_steps": 4100, "total_steps": 5238, "loss": 0.3152, "lr": 5e-06, "epoch": 2.348224513172967, "percentage": 78.27, "elapsed_time": "8:33:55", "remaining_time": "2:22:38"}
413
+ {"current_steps": 4110, "total_steps": 5238, "loss": 0.3293, "lr": 5e-06, "epoch": 2.3539518900343643, "percentage": 78.47, "elapsed_time": "8:35:08", "remaining_time": "2:21:23"}
414
+ {"current_steps": 4120, "total_steps": 5238, "loss": 0.3134, "lr": 5e-06, "epoch": 2.359679266895762, "percentage": 78.66, "elapsed_time": "8:36:21", "remaining_time": "2:20:07"}
415
+ {"current_steps": 4130, "total_steps": 5238, "loss": 0.3217, "lr": 5e-06, "epoch": 2.3654066437571593, "percentage": 78.85, "elapsed_time": "8:37:34", "remaining_time": "2:18:51"}
416
+ {"current_steps": 4140, "total_steps": 5238, "loss": 0.3179, "lr": 5e-06, "epoch": 2.3711340206185567, "percentage": 79.04, "elapsed_time": "8:38:47", "remaining_time": "2:17:35"}
417
+ {"current_steps": 4150, "total_steps": 5238, "loss": 0.321, "lr": 5e-06, "epoch": 2.376861397479954, "percentage": 79.23, "elapsed_time": "8:40:00", "remaining_time": "2:16:19"}
418
+ {"current_steps": 4160, "total_steps": 5238, "loss": 0.3108, "lr": 5e-06, "epoch": 2.3825887743413516, "percentage": 79.42, "elapsed_time": "8:41:14", "remaining_time": "2:15:04"}
419
+ {"current_steps": 4170, "total_steps": 5238, "loss": 0.3217, "lr": 5e-06, "epoch": 2.388316151202749, "percentage": 79.61, "elapsed_time": "8:42:27", "remaining_time": "2:13:48"}
420
+ {"current_steps": 4180, "total_steps": 5238, "loss": 0.3162, "lr": 5e-06, "epoch": 2.3940435280641466, "percentage": 79.8, "elapsed_time": "8:43:40", "remaining_time": "2:12:32"}
421
+ {"current_steps": 4190, "total_steps": 5238, "loss": 0.3206, "lr": 5e-06, "epoch": 2.399770904925544, "percentage": 79.99, "elapsed_time": "8:44:53", "remaining_time": "2:11:17"}
422
+ {"current_steps": 4200, "total_steps": 5238, "loss": 0.3227, "lr": 5e-06, "epoch": 2.4054982817869415, "percentage": 80.18, "elapsed_time": "8:46:06", "remaining_time": "2:10:01"}
423
+ {"current_steps": 4210, "total_steps": 5238, "loss": 0.327, "lr": 5e-06, "epoch": 2.411225658648339, "percentage": 80.37, "elapsed_time": "8:47:18", "remaining_time": "2:08:45"}
424
+ {"current_steps": 4220, "total_steps": 5238, "loss": 0.3145, "lr": 5e-06, "epoch": 2.4169530355097364, "percentage": 80.57, "elapsed_time": "8:48:31", "remaining_time": "2:07:29"}
425
+ {"current_steps": 4230, "total_steps": 5238, "loss": 0.3192, "lr": 5e-06, "epoch": 2.422680412371134, "percentage": 80.76, "elapsed_time": "8:49:44", "remaining_time": "2:06:14"}
426
+ {"current_steps": 4240, "total_steps": 5238, "loss": 0.3187, "lr": 5e-06, "epoch": 2.4284077892325313, "percentage": 80.95, "elapsed_time": "8:50:57", "remaining_time": "2:04:58"}
427
+ {"current_steps": 4250, "total_steps": 5238, "loss": 0.3248, "lr": 5e-06, "epoch": 2.434135166093929, "percentage": 81.14, "elapsed_time": "8:52:10", "remaining_time": "2:03:42"}
428
+ {"current_steps": 4260, "total_steps": 5238, "loss": 0.3276, "lr": 5e-06, "epoch": 2.4398625429553267, "percentage": 81.33, "elapsed_time": "8:53:23", "remaining_time": "2:02:27"}
429
+ {"current_steps": 4270, "total_steps": 5238, "loss": 0.3076, "lr": 5e-06, "epoch": 2.445589919816724, "percentage": 81.52, "elapsed_time": "8:54:36", "remaining_time": "2:01:11"}
430
+ {"current_steps": 4280, "total_steps": 5238, "loss": 0.3183, "lr": 5e-06, "epoch": 2.4513172966781216, "percentage": 81.71, "elapsed_time": "8:55:49", "remaining_time": "1:59:56"}
431
+ {"current_steps": 4290, "total_steps": 5238, "loss": 0.3169, "lr": 5e-06, "epoch": 2.457044673539519, "percentage": 81.9, "elapsed_time": "8:57:03", "remaining_time": "1:58:40"}
432
+ {"current_steps": 4300, "total_steps": 5238, "loss": 0.3181, "lr": 5e-06, "epoch": 2.4627720504009165, "percentage": 82.09, "elapsed_time": "8:58:16", "remaining_time": "1:57:25"}
433
+ {"current_steps": 4310, "total_steps": 5238, "loss": 0.3214, "lr": 5e-06, "epoch": 2.468499427262314, "percentage": 82.28, "elapsed_time": "8:59:30", "remaining_time": "1:56:09"}
434
+ {"current_steps": 4320, "total_steps": 5238, "loss": 0.3232, "lr": 5e-06, "epoch": 2.4742268041237114, "percentage": 82.47, "elapsed_time": "9:00:43", "remaining_time": "1:54:54"}
435
+ {"current_steps": 4330, "total_steps": 5238, "loss": 0.3203, "lr": 5e-06, "epoch": 2.479954180985109, "percentage": 82.67, "elapsed_time": "9:01:56", "remaining_time": "1:53:38"}
436
+ {"current_steps": 4340, "total_steps": 5238, "loss": 0.3205, "lr": 5e-06, "epoch": 2.4856815578465064, "percentage": 82.86, "elapsed_time": "9:03:10", "remaining_time": "1:52:23"}
437
+ {"current_steps": 4350, "total_steps": 5238, "loss": 0.3258, "lr": 5e-06, "epoch": 2.491408934707904, "percentage": 83.05, "elapsed_time": "9:04:23", "remaining_time": "1:51:07"}
438
+ {"current_steps": 4360, "total_steps": 5238, "loss": 0.3194, "lr": 5e-06, "epoch": 2.4971363115693013, "percentage": 83.24, "elapsed_time": "9:05:36", "remaining_time": "1:49:52"}
439
+ {"current_steps": 4370, "total_steps": 5238, "loss": 0.3225, "lr": 5e-06, "epoch": 2.5028636884306987, "percentage": 83.43, "elapsed_time": "9:06:49", "remaining_time": "1:48:36"}
440
+ {"current_steps": 4380, "total_steps": 5238, "loss": 0.3205, "lr": 5e-06, "epoch": 2.508591065292096, "percentage": 83.62, "elapsed_time": "9:08:03", "remaining_time": "1:47:21"}
441
+ {"current_steps": 4390, "total_steps": 5238, "loss": 0.3175, "lr": 5e-06, "epoch": 2.5143184421534936, "percentage": 83.81, "elapsed_time": "9:09:15", "remaining_time": "1:46:05"}
442
+ {"current_steps": 4400, "total_steps": 5238, "loss": 0.3223, "lr": 5e-06, "epoch": 2.520045819014891, "percentage": 84.0, "elapsed_time": "9:10:28", "remaining_time": "1:44:50"}
443
+ {"current_steps": 4410, "total_steps": 5238, "loss": 0.323, "lr": 5e-06, "epoch": 2.5257731958762886, "percentage": 84.19, "elapsed_time": "9:11:42", "remaining_time": "1:43:35"}
444
+ {"current_steps": 4420, "total_steps": 5238, "loss": 0.3201, "lr": 5e-06, "epoch": 2.531500572737686, "percentage": 84.38, "elapsed_time": "9:12:55", "remaining_time": "1:42:19"}
445
+ {"current_steps": 4430, "total_steps": 5238, "loss": 0.3227, "lr": 5e-06, "epoch": 2.5372279495990835, "percentage": 84.57, "elapsed_time": "9:14:08", "remaining_time": "1:41:04"}
446
+ {"current_steps": 4440, "total_steps": 5238, "loss": 0.3201, "lr": 5e-06, "epoch": 2.542955326460481, "percentage": 84.77, "elapsed_time": "9:15:22", "remaining_time": "1:39:49"}
447
+ {"current_steps": 4450, "total_steps": 5238, "loss": 0.3196, "lr": 5e-06, "epoch": 2.5486827033218784, "percentage": 84.96, "elapsed_time": "9:16:35", "remaining_time": "1:38:33"}
448
+ {"current_steps": 4460, "total_steps": 5238, "loss": 0.3243, "lr": 5e-06, "epoch": 2.554410080183276, "percentage": 85.15, "elapsed_time": "9:17:48", "remaining_time": "1:37:18"}
449
+ {"current_steps": 4470, "total_steps": 5238, "loss": 0.3183, "lr": 5e-06, "epoch": 2.5601374570446733, "percentage": 85.34, "elapsed_time": "9:19:01", "remaining_time": "1:36:02"}
450
+ {"current_steps": 4480, "total_steps": 5238, "loss": 0.3172, "lr": 5e-06, "epoch": 2.565864833906071, "percentage": 85.53, "elapsed_time": "9:20:14", "remaining_time": "1:34:47"}
451
+ {"current_steps": 4490, "total_steps": 5238, "loss": 0.3276, "lr": 5e-06, "epoch": 2.5715922107674682, "percentage": 85.72, "elapsed_time": "9:21:28", "remaining_time": "1:33:32"}
452
+ {"current_steps": 4500, "total_steps": 5238, "loss": 0.3197, "lr": 5e-06, "epoch": 2.5773195876288657, "percentage": 85.91, "elapsed_time": "9:22:41", "remaining_time": "1:32:16"}
453
+ {"current_steps": 4510, "total_steps": 5238, "loss": 0.3303, "lr": 5e-06, "epoch": 2.5830469644902636, "percentage": 86.1, "elapsed_time": "9:23:55", "remaining_time": "1:31:01"}
454
+ {"current_steps": 4520, "total_steps": 5238, "loss": 0.3213, "lr": 5e-06, "epoch": 2.588774341351661, "percentage": 86.29, "elapsed_time": "9:25:08", "remaining_time": "1:29:46"}
455
+ {"current_steps": 4530, "total_steps": 5238, "loss": 0.3159, "lr": 5e-06, "epoch": 2.5945017182130585, "percentage": 86.48, "elapsed_time": "9:26:21", "remaining_time": "1:28:30"}
456
+ {"current_steps": 4540, "total_steps": 5238, "loss": 0.3198, "lr": 5e-06, "epoch": 2.600229095074456, "percentage": 86.67, "elapsed_time": "9:27:34", "remaining_time": "1:27:15"}
457
+ {"current_steps": 4550, "total_steps": 5238, "loss": 0.3239, "lr": 5e-06, "epoch": 2.6059564719358534, "percentage": 86.87, "elapsed_time": "9:28:47", "remaining_time": "1:26:00"}
458
+ {"current_steps": 4560, "total_steps": 5238, "loss": 0.3165, "lr": 5e-06, "epoch": 2.611683848797251, "percentage": 87.06, "elapsed_time": "9:30:00", "remaining_time": "1:24:45"}
459
+ {"current_steps": 4570, "total_steps": 5238, "loss": 0.3162, "lr": 5e-06, "epoch": 2.6174112256586484, "percentage": 87.25, "elapsed_time": "9:31:13", "remaining_time": "1:23:29"}
460
+ {"current_steps": 4580, "total_steps": 5238, "loss": 0.3162, "lr": 5e-06, "epoch": 2.623138602520046, "percentage": 87.44, "elapsed_time": "9:32:26", "remaining_time": "1:22:14"}
461
+ {"current_steps": 4590, "total_steps": 5238, "loss": 0.3173, "lr": 5e-06, "epoch": 2.6288659793814433, "percentage": 87.63, "elapsed_time": "9:33:39", "remaining_time": "1:20:59"}
462
+ {"current_steps": 4600, "total_steps": 5238, "loss": 0.327, "lr": 5e-06, "epoch": 2.6345933562428407, "percentage": 87.82, "elapsed_time": "9:34:51", "remaining_time": "1:19:43"}
463
+ {"current_steps": 4610, "total_steps": 5238, "loss": 0.3201, "lr": 5e-06, "epoch": 2.640320733104238, "percentage": 88.01, "elapsed_time": "9:36:04", "remaining_time": "1:18:28"}
464
+ {"current_steps": 4620, "total_steps": 5238, "loss": 0.3243, "lr": 5e-06, "epoch": 2.6460481099656357, "percentage": 88.2, "elapsed_time": "9:37:17", "remaining_time": "1:17:13"}
465
+ {"current_steps": 4630, "total_steps": 5238, "loss": 0.313, "lr": 5e-06, "epoch": 2.651775486827033, "percentage": 88.39, "elapsed_time": "9:38:30", "remaining_time": "1:15:58"}
466
+ {"current_steps": 4640, "total_steps": 5238, "loss": 0.3251, "lr": 5e-06, "epoch": 2.6575028636884306, "percentage": 88.58, "elapsed_time": "9:39:44", "remaining_time": "1:14:42"}
467
+ {"current_steps": 4650, "total_steps": 5238, "loss": 0.3171, "lr": 5e-06, "epoch": 2.663230240549828, "percentage": 88.77, "elapsed_time": "9:40:57", "remaining_time": "1:13:27"}
468
+ {"current_steps": 4660, "total_steps": 5238, "loss": 0.3196, "lr": 5e-06, "epoch": 2.6689576174112255, "percentage": 88.97, "elapsed_time": "9:42:10", "remaining_time": "1:12:12"}
469
+ {"current_steps": 4670, "total_steps": 5238, "loss": 0.33, "lr": 5e-06, "epoch": 2.6746849942726234, "percentage": 89.16, "elapsed_time": "9:43:23", "remaining_time": "1:10:57"}
470
+ {"current_steps": 4680, "total_steps": 5238, "loss": 0.3233, "lr": 5e-06, "epoch": 2.680412371134021, "percentage": 89.35, "elapsed_time": "9:44:36", "remaining_time": "1:09:42"}
471
+ {"current_steps": 4690, "total_steps": 5238, "loss": 0.3218, "lr": 5e-06, "epoch": 2.6861397479954183, "percentage": 89.54, "elapsed_time": "9:45:49", "remaining_time": "1:08:27"}
472
+ {"current_steps": 4700, "total_steps": 5238, "loss": 0.3115, "lr": 5e-06, "epoch": 2.691867124856816, "percentage": 89.73, "elapsed_time": "9:47:02", "remaining_time": "1:07:11"}
473
+ {"current_steps": 4710, "total_steps": 5238, "loss": 0.3229, "lr": 5e-06, "epoch": 2.6975945017182132, "percentage": 89.92, "elapsed_time": "9:48:16", "remaining_time": "1:05:56"}
474
+ {"current_steps": 4720, "total_steps": 5238, "loss": 0.3176, "lr": 5e-06, "epoch": 2.7033218785796107, "percentage": 90.11, "elapsed_time": "9:49:29", "remaining_time": "1:04:41"}
475
+ {"current_steps": 4730, "total_steps": 5238, "loss": 0.3216, "lr": 5e-06, "epoch": 2.709049255441008, "percentage": 90.3, "elapsed_time": "9:50:42", "remaining_time": "1:03:26"}
476
+ {"current_steps": 4740, "total_steps": 5238, "loss": 0.3255, "lr": 5e-06, "epoch": 2.7147766323024056, "percentage": 90.49, "elapsed_time": "9:51:55", "remaining_time": "1:02:11"}
477
+ {"current_steps": 4750, "total_steps": 5238, "loss": 0.3221, "lr": 5e-06, "epoch": 2.720504009163803, "percentage": 90.68, "elapsed_time": "9:53:09", "remaining_time": "1:00:56"}
478
+ {"current_steps": 4760, "total_steps": 5238, "loss": 0.3188, "lr": 5e-06, "epoch": 2.7262313860252005, "percentage": 90.87, "elapsed_time": "9:54:22", "remaining_time": "0:59:41"}
479
+ {"current_steps": 4770, "total_steps": 5238, "loss": 0.3268, "lr": 5e-06, "epoch": 2.731958762886598, "percentage": 91.07, "elapsed_time": "9:55:35", "remaining_time": "0:58:26"}
480
+ {"current_steps": 4780, "total_steps": 5238, "loss": 0.3146, "lr": 5e-06, "epoch": 2.7376861397479955, "percentage": 91.26, "elapsed_time": "9:56:49", "remaining_time": "0:57:11"}
481
+ {"current_steps": 4790, "total_steps": 5238, "loss": 0.3306, "lr": 5e-06, "epoch": 2.743413516609393, "percentage": 91.45, "elapsed_time": "9:58:02", "remaining_time": "0:55:56"}
482
+ {"current_steps": 4800, "total_steps": 5238, "loss": 0.3183, "lr": 5e-06, "epoch": 2.7491408934707904, "percentage": 91.64, "elapsed_time": "9:59:14", "remaining_time": "0:54:40"}
483
+ {"current_steps": 4810, "total_steps": 5238, "loss": 0.3102, "lr": 5e-06, "epoch": 2.754868270332188, "percentage": 91.83, "elapsed_time": "10:00:27", "remaining_time": "0:53:25"}
484
+ {"current_steps": 4820, "total_steps": 5238, "loss": 0.3296, "lr": 5e-06, "epoch": 2.7605956471935853, "percentage": 92.02, "elapsed_time": "10:01:39", "remaining_time": "0:52:10"}
485
+ {"current_steps": 4830, "total_steps": 5238, "loss": 0.3233, "lr": 5e-06, "epoch": 2.7663230240549828, "percentage": 92.21, "elapsed_time": "10:02:52", "remaining_time": "0:50:55"}
486
+ {"current_steps": 4840, "total_steps": 5238, "loss": 0.3273, "lr": 5e-06, "epoch": 2.77205040091638, "percentage": 92.4, "elapsed_time": "10:04:06", "remaining_time": "0:49:40"}
487
+ {"current_steps": 4850, "total_steps": 5238, "loss": 0.3169, "lr": 5e-06, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "10:05:19", "remaining_time": "0:48:25"}
488
+ {"current_steps": 4860, "total_steps": 5238, "loss": 0.3232, "lr": 5e-06, "epoch": 2.783505154639175, "percentage": 92.78, "elapsed_time": "10:06:32", "remaining_time": "0:47:10"}
489
+ {"current_steps": 4870, "total_steps": 5238, "loss": 0.3183, "lr": 5e-06, "epoch": 2.7892325315005726, "percentage": 92.97, "elapsed_time": "10:07:45", "remaining_time": "0:45:55"}
490
+ {"current_steps": 4880, "total_steps": 5238, "loss": 0.3251, "lr": 5e-06, "epoch": 2.79495990836197, "percentage": 93.17, "elapsed_time": "10:08:59", "remaining_time": "0:44:40"}
491
+ {"current_steps": 4890, "total_steps": 5238, "loss": 0.3231, "lr": 5e-06, "epoch": 2.8006872852233675, "percentage": 93.36, "elapsed_time": "10:10:12", "remaining_time": "0:43:25"}
492
+ {"current_steps": 4900, "total_steps": 5238, "loss": 0.3174, "lr": 5e-06, "epoch": 2.806414662084765, "percentage": 93.55, "elapsed_time": "10:11:25", "remaining_time": "0:42:10"}
493
+ {"current_steps": 4910, "total_steps": 5238, "loss": 0.3206, "lr": 5e-06, "epoch": 2.8121420389461624, "percentage": 93.74, "elapsed_time": "10:12:38", "remaining_time": "0:40:55"}
494
+ {"current_steps": 4920, "total_steps": 5238, "loss": 0.3271, "lr": 5e-06, "epoch": 2.81786941580756, "percentage": 93.93, "elapsed_time": "10:13:51", "remaining_time": "0:39:40"}
495
+ {"current_steps": 4930, "total_steps": 5238, "loss": 0.3255, "lr": 5e-06, "epoch": 2.8235967926689574, "percentage": 94.12, "elapsed_time": "10:15:04", "remaining_time": "0:38:25"}
496
+ {"current_steps": 4940, "total_steps": 5238, "loss": 0.3199, "lr": 5e-06, "epoch": 2.8293241695303553, "percentage": 94.31, "elapsed_time": "10:16:17", "remaining_time": "0:37:10"}
497
+ {"current_steps": 4950, "total_steps": 5238, "loss": 0.3287, "lr": 5e-06, "epoch": 2.8350515463917527, "percentage": 94.5, "elapsed_time": "10:17:31", "remaining_time": "0:35:55"}
498
+ {"current_steps": 4960, "total_steps": 5238, "loss": 0.3274, "lr": 5e-06, "epoch": 2.84077892325315, "percentage": 94.69, "elapsed_time": "10:18:44", "remaining_time": "0:34:40"}
499
+ {"current_steps": 4970, "total_steps": 5238, "loss": 0.3166, "lr": 5e-06, "epoch": 2.8465063001145476, "percentage": 94.88, "elapsed_time": "10:19:57", "remaining_time": "0:33:25"}
500
+ {"current_steps": 4980, "total_steps": 5238, "loss": 0.322, "lr": 5e-06, "epoch": 2.852233676975945, "percentage": 95.07, "elapsed_time": "10:21:10", "remaining_time": "0:32:10"}
501
+ {"current_steps": 4990, "total_steps": 5238, "loss": 0.3189, "lr": 5e-06, "epoch": 2.8579610538373426, "percentage": 95.27, "elapsed_time": "10:22:23", "remaining_time": "0:30:55"}
502
+ {"current_steps": 5000, "total_steps": 5238, "loss": 0.3215, "lr": 5e-06, "epoch": 2.86368843069874, "percentage": 95.46, "elapsed_time": "10:23:37", "remaining_time": "0:29:41"}
503
+ {"current_steps": 5010, "total_steps": 5238, "loss": 0.3293, "lr": 5e-06, "epoch": 2.8694158075601375, "percentage": 95.65, "elapsed_time": "10:24:50", "remaining_time": "0:28:26"}
504
+ {"current_steps": 5020, "total_steps": 5238, "loss": 0.3237, "lr": 5e-06, "epoch": 2.875143184421535, "percentage": 95.84, "elapsed_time": "10:26:03", "remaining_time": "0:27:11"}
505
+ {"current_steps": 5030, "total_steps": 5238, "loss": 0.3171, "lr": 5e-06, "epoch": 2.8808705612829324, "percentage": 96.03, "elapsed_time": "10:27:16", "remaining_time": "0:25:56"}
506
+ {"current_steps": 5040, "total_steps": 5238, "loss": 0.3153, "lr": 5e-06, "epoch": 2.88659793814433, "percentage": 96.22, "elapsed_time": "10:28:30", "remaining_time": "0:24:41"}
507
+ {"current_steps": 5050, "total_steps": 5238, "loss": 0.3263, "lr": 5e-06, "epoch": 2.8923253150057273, "percentage": 96.41, "elapsed_time": "10:29:43", "remaining_time": "0:23:26"}
508
+ {"current_steps": 5060, "total_steps": 5238, "loss": 0.3214, "lr": 5e-06, "epoch": 2.8980526918671248, "percentage": 96.6, "elapsed_time": "10:30:56", "remaining_time": "0:22:11"}
509
+ {"current_steps": 5070, "total_steps": 5238, "loss": 0.3192, "lr": 5e-06, "epoch": 2.9037800687285222, "percentage": 96.79, "elapsed_time": "10:32:09", "remaining_time": "0:20:56"}
510
+ {"current_steps": 5080, "total_steps": 5238, "loss": 0.3218, "lr": 5e-06, "epoch": 2.9095074455899197, "percentage": 96.98, "elapsed_time": "10:33:22", "remaining_time": "0:19:41"}
511
+ {"current_steps": 5090, "total_steps": 5238, "loss": 0.318, "lr": 5e-06, "epoch": 2.915234822451317, "percentage": 97.17, "elapsed_time": "10:34:35", "remaining_time": "0:18:27"}
512
+ {"current_steps": 5100, "total_steps": 5238, "loss": 0.3194, "lr": 5e-06, "epoch": 2.9209621993127146, "percentage": 97.37, "elapsed_time": "10:35:48", "remaining_time": "0:17:12"}
513
+ {"current_steps": 5110, "total_steps": 5238, "loss": 0.3297, "lr": 5e-06, "epoch": 2.9266895761741125, "percentage": 97.56, "elapsed_time": "10:37:01", "remaining_time": "0:15:57"}
514
+ {"current_steps": 5120, "total_steps": 5238, "loss": 0.3246, "lr": 5e-06, "epoch": 2.93241695303551, "percentage": 97.75, "elapsed_time": "10:38:15", "remaining_time": "0:14:42"}
515
+ {"current_steps": 5130, "total_steps": 5238, "loss": 0.318, "lr": 5e-06, "epoch": 2.9381443298969074, "percentage": 97.94, "elapsed_time": "10:39:28", "remaining_time": "0:13:27"}
516
+ {"current_steps": 5140, "total_steps": 5238, "loss": 0.3196, "lr": 5e-06, "epoch": 2.943871706758305, "percentage": 98.13, "elapsed_time": "10:40:42", "remaining_time": "0:12:12"}
517
+ {"current_steps": 5150, "total_steps": 5238, "loss": 0.3129, "lr": 5e-06, "epoch": 2.9495990836197024, "percentage": 98.32, "elapsed_time": "10:41:55", "remaining_time": "0:10:58"}
518
+ {"current_steps": 5160, "total_steps": 5238, "loss": 0.3247, "lr": 5e-06, "epoch": 2.9553264604811, "percentage": 98.51, "elapsed_time": "10:43:09", "remaining_time": "0:09:43"}
519
+ {"current_steps": 5170, "total_steps": 5238, "loss": 0.3198, "lr": 5e-06, "epoch": 2.9610538373424973, "percentage": 98.7, "elapsed_time": "10:44:22", "remaining_time": "0:08:28"}
520
+ {"current_steps": 5180, "total_steps": 5238, "loss": 0.3184, "lr": 5e-06, "epoch": 2.9667812142038947, "percentage": 98.89, "elapsed_time": "10:45:35", "remaining_time": "0:07:13"}
521
+ {"current_steps": 5190, "total_steps": 5238, "loss": 0.3167, "lr": 5e-06, "epoch": 2.972508591065292, "percentage": 99.08, "elapsed_time": "10:46:49", "remaining_time": "0:05:58"}
522
+ {"current_steps": 5200, "total_steps": 5238, "loss": 0.3263, "lr": 5e-06, "epoch": 2.9782359679266897, "percentage": 99.27, "elapsed_time": "10:48:02", "remaining_time": "0:04:44"}
523
+ {"current_steps": 5210, "total_steps": 5238, "loss": 0.3185, "lr": 5e-06, "epoch": 2.983963344788087, "percentage": 99.47, "elapsed_time": "10:49:16", "remaining_time": "0:03:29"}
524
+ {"current_steps": 5220, "total_steps": 5238, "loss": 0.3159, "lr": 5e-06, "epoch": 2.9896907216494846, "percentage": 99.66, "elapsed_time": "10:50:29", "remaining_time": "0:02:14"}
525
+ {"current_steps": 5230, "total_steps": 5238, "loss": 0.3266, "lr": 5e-06, "epoch": 2.995418098510882, "percentage": 99.85, "elapsed_time": "10:51:42", "remaining_time": "0:00:59"}