Jiayi-Pan commited on
Commit
e7d992d
1 Parent(s): fa0721a

Training in progress, step 7000

Browse files
Files changed (2) hide show
  1. model.safetensors +1 -1
  2. trainer_log.jsonl +100 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:103da47917458dd38105ced764a36a07bd56d71cc47421a44a81419881d9e935
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:982ba96e0766a1bd15a86b867e4ce949392a3a5fc4f825a808dc1a77314eae1e
3
  size 4400216536
trainer_log.jsonl CHANGED
@@ -600,3 +600,103 @@
600
  {"current_steps": 6000, "total_steps": 10000, "loss": 2.3815, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7274575140626318e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "8:38:39", "remaining_time": "5:45:46"}
601
  {"current_steps": 6010, "total_steps": 10000, "loss": 2.3354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7199917582789633e-05, "epoch": 0.6, "percentage": 60.1, "elapsed_time": "8:39:55", "remaining_time": "5:45:10"}
602
  {"current_steps": 6020, "total_steps": 10000, "loss": 2.3555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7125337008617386e-05, "epoch": 0.6, "percentage": 60.2, "elapsed_time": "8:40:42", "remaining_time": "5:44:15"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
600
  {"current_steps": 6000, "total_steps": 10000, "loss": 2.3815, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7274575140626318e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "8:38:39", "remaining_time": "5:45:46"}
601
  {"current_steps": 6010, "total_steps": 10000, "loss": 2.3354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7199917582789633e-05, "epoch": 0.6, "percentage": 60.1, "elapsed_time": "8:39:55", "remaining_time": "5:45:10"}
602
  {"current_steps": 6020, "total_steps": 10000, "loss": 2.3555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7125337008617386e-05, "epoch": 0.6, "percentage": 60.2, "elapsed_time": "8:40:42", "remaining_time": "5:44:15"}
603
+ {"current_steps": 6030, "total_steps": 10000, "loss": 2.3506, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7050834154189733e-05, "epoch": 0.6, "percentage": 60.3, "elapsed_time": "8:41:34", "remaining_time": "5:43:23"}
604
+ {"current_steps": 6040, "total_steps": 10000, "loss": 2.3261, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6976409754819767e-05, "epoch": 0.6, "percentage": 60.4, "elapsed_time": "8:42:22", "remaining_time": "5:42:29"}
605
+ {"current_steps": 6050, "total_steps": 10000, "loss": 2.3653, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.690206454504627e-05, "epoch": 0.6, "percentage": 60.5, "elapsed_time": "8:43:13", "remaining_time": "5:41:36"}
606
+ {"current_steps": 6060, "total_steps": 10000, "loss": 2.3438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6827799258626442e-05, "epoch": 0.61, "percentage": 60.6, "elapsed_time": "8:44:05", "remaining_time": "5:40:44"}
607
+ {"current_steps": 6070, "total_steps": 10000, "loss": 2.3372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.675361462852868e-05, "epoch": 0.61, "percentage": 60.7, "elapsed_time": "8:44:58", "remaining_time": "5:39:53"}
608
+ {"current_steps": 6080, "total_steps": 10000, "loss": 2.3492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6679511386925337e-05, "epoch": 0.61, "percentage": 60.8, "elapsed_time": "8:45:46", "remaining_time": "5:38:59"}
609
+ {"current_steps": 6090, "total_steps": 10000, "loss": 2.3284, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6605490265185485e-05, "epoch": 0.61, "percentage": 60.9, "elapsed_time": "8:46:38", "remaining_time": "5:38:07"}
610
+ {"current_steps": 6100, "total_steps": 10000, "loss": 2.3043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6531551993867717e-05, "epoch": 0.61, "percentage": 61.0, "elapsed_time": "8:47:25", "remaining_time": "5:37:12"}
611
+ {"current_steps": 6110, "total_steps": 10000, "loss": 2.3432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6457697302712918e-05, "epoch": 0.61, "percentage": 61.1, "elapsed_time": "8:48:18", "remaining_time": "5:36:21"}
612
+ {"current_steps": 6120, "total_steps": 10000, "loss": 2.3202, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6383926920637077e-05, "epoch": 0.61, "percentage": 61.2, "elapsed_time": "8:49:09", "remaining_time": "5:35:29"}
613
+ {"current_steps": 6130, "total_steps": 10000, "loss": 2.3262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6310241575724077e-05, "epoch": 0.61, "percentage": 61.3, "elapsed_time": "8:50:02", "remaining_time": "5:34:37"}
614
+ {"current_steps": 6140, "total_steps": 10000, "loss": 2.3058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.623664199521853e-05, "epoch": 0.61, "percentage": 61.4, "elapsed_time": "8:50:50", "remaining_time": "5:33:43"}
615
+ {"current_steps": 6150, "total_steps": 10000, "loss": 2.3583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6163128905518578e-05, "epoch": 0.61, "percentage": 61.5, "elapsed_time": "8:51:38", "remaining_time": "5:32:49"}
616
+ {"current_steps": 6160, "total_steps": 10000, "loss": 2.3359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6089703032168733e-05, "epoch": 0.62, "percentage": 61.6, "elapsed_time": "8:52:31", "remaining_time": "5:31:57"}
617
+ {"current_steps": 6170, "total_steps": 10000, "loss": 2.3372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6016365099852735e-05, "epoch": 0.62, "percentage": 61.7, "elapsed_time": "8:53:22", "remaining_time": "5:31:05"}
618
+ {"current_steps": 6180, "total_steps": 10000, "loss": 2.3413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.594311583238636e-05, "epoch": 0.62, "percentage": 61.8, "elapsed_time": "8:54:15", "remaining_time": "5:30:14"}
619
+ {"current_steps": 6190, "total_steps": 10000, "loss": 2.3574, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5869955952710308e-05, "epoch": 0.62, "percentage": 61.9, "elapsed_time": "8:55:03", "remaining_time": "5:29:19"}
620
+ {"current_steps": 6200, "total_steps": 10000, "loss": 2.3149, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5796886182883053e-05, "epoch": 0.62, "percentage": 62.0, "elapsed_time": "8:55:56", "remaining_time": "5:28:28"}
621
+ {"current_steps": 6210, "total_steps": 10000, "loss": 2.3169, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.572390724407373e-05, "epoch": 0.62, "percentage": 62.1, "elapsed_time": "8:56:45", "remaining_time": "5:27:35"}
622
+ {"current_steps": 6220, "total_steps": 10000, "loss": 2.3257, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5651019856554995e-05, "epoch": 0.62, "percentage": 62.2, "elapsed_time": "8:57:36", "remaining_time": "5:26:42"}
623
+ {"current_steps": 6230, "total_steps": 10000, "loss": 2.3352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5578224739695938e-05, "epoch": 0.62, "percentage": 62.3, "elapsed_time": "8:58:27", "remaining_time": "5:25:50"}
624
+ {"current_steps": 6240, "total_steps": 10000, "loss": 2.3251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5505522611954975e-05, "epoch": 0.62, "percentage": 62.4, "elapsed_time": "8:59:19", "remaining_time": "5:24:58"}
625
+ {"current_steps": 6250, "total_steps": 10000, "loss": 2.351, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5432914190872757e-05, "epoch": 0.62, "percentage": 62.5, "elapsed_time": "9:00:10", "remaining_time": "5:24:06"}
626
+ {"current_steps": 6260, "total_steps": 10000, "loss": 2.3517, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.536040019306509e-05, "epoch": 0.63, "percentage": 62.6, "elapsed_time": "9:00:59", "remaining_time": "5:23:12"}
627
+ {"current_steps": 6270, "total_steps": 10000, "loss": 2.3324, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.528798133421585e-05, "epoch": 0.63, "percentage": 62.7, "elapsed_time": "9:01:54", "remaining_time": "5:22:22"}
628
+ {"current_steps": 6280, "total_steps": 10000, "loss": 2.3288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.521565832906994e-05, "epoch": 0.63, "percentage": 62.8, "elapsed_time": "9:02:41", "remaining_time": "5:21:28"}
629
+ {"current_steps": 6290, "total_steps": 10000, "loss": 2.2975, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5143431891426225e-05, "epoch": 0.63, "percentage": 62.9, "elapsed_time": "9:03:32", "remaining_time": "5:20:35"}
630
+ {"current_steps": 6300, "total_steps": 10000, "loss": 2.3613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5071302734130489e-05, "epoch": 0.63, "percentage": 63.0, "elapsed_time": "9:04:24", "remaining_time": "5:19:43"}
631
+ {"current_steps": 6310, "total_steps": 10000, "loss": 2.3177, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4999271569068385e-05, "epoch": 0.63, "percentage": 63.1, "elapsed_time": "9:05:15", "remaining_time": "5:18:51"}
632
+ {"current_steps": 6320, "total_steps": 10000, "loss": 2.2812, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4927339107158437e-05, "epoch": 0.63, "percentage": 63.2, "elapsed_time": "9:06:08", "remaining_time": "5:18:00"}
633
+ {"current_steps": 6330, "total_steps": 10000, "loss": 2.3682, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4855506058345003e-05, "epoch": 0.63, "percentage": 63.3, "elapsed_time": "9:06:56", "remaining_time": "5:17:06"}
634
+ {"current_steps": 6340, "total_steps": 10000, "loss": 2.3228, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4783773131591278e-05, "epoch": 0.63, "percentage": 63.4, "elapsed_time": "9:07:48", "remaining_time": "5:16:14"}
635
+ {"current_steps": 6350, "total_steps": 10000, "loss": 2.3247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4712141034872282e-05, "epoch": 0.64, "percentage": 63.5, "elapsed_time": "9:08:36", "remaining_time": "5:15:20"}
636
+ {"current_steps": 6360, "total_steps": 10000, "loss": 2.3507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4640610475167898e-05, "epoch": 0.64, "percentage": 63.6, "elapsed_time": "9:09:27", "remaining_time": "5:14:28"}
637
+ {"current_steps": 6370, "total_steps": 10000, "loss": 2.2799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4569182158455875e-05, "epoch": 0.64, "percentage": 63.7, "elapsed_time": "9:10:19", "remaining_time": "5:13:36"}
638
+ {"current_steps": 6380, "total_steps": 10000, "loss": 2.3349, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4497856789704844e-05, "epoch": 0.64, "percentage": 63.8, "elapsed_time": "9:11:08", "remaining_time": "5:12:42"}
639
+ {"current_steps": 6390, "total_steps": 10000, "loss": 2.2896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4426635072867423e-05, "epoch": 0.64, "percentage": 63.9, "elapsed_time": "9:12:01", "remaining_time": "5:11:52"}
640
+ {"current_steps": 6400, "total_steps": 10000, "loss": 2.3035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4355517710873184e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "9:12:49", "remaining_time": "5:10:57"}
641
+ {"current_steps": 6410, "total_steps": 10000, "loss": 2.2374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4284505405621795e-05, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "9:13:42", "remaining_time": "5:10:06"}
642
+ {"current_steps": 6420, "total_steps": 10000, "loss": 2.2836, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4213598857976024e-05, "epoch": 0.64, "percentage": 64.2, "elapsed_time": "9:14:32", "remaining_time": "5:09:13"}
643
+ {"current_steps": 6430, "total_steps": 10000, "loss": 2.2513, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4142798767754886e-05, "epoch": 0.64, "percentage": 64.3, "elapsed_time": "9:15:23", "remaining_time": "5:08:21"}
644
+ {"current_steps": 6440, "total_steps": 10000, "loss": 2.2739, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4072105833726684e-05, "epoch": 0.64, "percentage": 64.4, "elapsed_time": "9:16:14", "remaining_time": "5:07:29"}
645
+ {"current_steps": 6450, "total_steps": 10000, "loss": 2.2687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4001520753602121e-05, "epoch": 0.65, "percentage": 64.5, "elapsed_time": "9:17:08", "remaining_time": "5:06:38"}
646
+ {"current_steps": 6460, "total_steps": 10000, "loss": 2.2863, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3931044224027468e-05, "epoch": 0.65, "percentage": 64.6, "elapsed_time": "9:17:56", "remaining_time": "5:05:44"}
647
+ {"current_steps": 6470, "total_steps": 10000, "loss": 2.3074, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3860676940577594e-05, "epoch": 0.65, "percentage": 64.7, "elapsed_time": "9:18:43", "remaining_time": "5:04:50"}
648
+ {"current_steps": 6480, "total_steps": 10000, "loss": 2.3066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3790419597749199e-05, "epoch": 0.65, "percentage": 64.8, "elapsed_time": "9:19:35", "remaining_time": "5:03:58"}
649
+ {"current_steps": 6490, "total_steps": 10000, "loss": 2.3127, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3720272888953873e-05, "epoch": 0.65, "percentage": 64.9, "elapsed_time": "9:20:26", "remaining_time": "5:03:06"}
650
+ {"current_steps": 6500, "total_steps": 10000, "loss": 2.2648, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3650237506511331e-05, "epoch": 0.65, "percentage": 65.0, "elapsed_time": "9:21:18", "remaining_time": "5:02:14"}
651
+ {"current_steps": 6510, "total_steps": 10000, "loss": 2.277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3580314141642509e-05, "epoch": 0.65, "percentage": 65.1, "elapsed_time": "9:22:05", "remaining_time": "5:01:20"}
652
+ {"current_steps": 6520, "total_steps": 10000, "loss": 2.2983, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3510503484462805e-05, "epoch": 0.65, "percentage": 65.2, "elapsed_time": "9:22:58", "remaining_time": "5:00:28"}
653
+ {"current_steps": 6530, "total_steps": 10000, "loss": 2.2895, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3440806223975211e-05, "epoch": 0.65, "percentage": 65.3, "elapsed_time": "9:23:47", "remaining_time": "4:59:35"}
654
+ {"current_steps": 6540, "total_steps": 10000, "loss": 2.2635, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.337122304806354e-05, "epoch": 0.65, "percentage": 65.4, "elapsed_time": "9:24:40", "remaining_time": "4:58:44"}
655
+ {"current_steps": 6550, "total_steps": 10000, "loss": 2.2758, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.330175464348567e-05, "epoch": 0.66, "percentage": 65.5, "elapsed_time": "9:25:31", "remaining_time": "4:57:52"}
656
+ {"current_steps": 6560, "total_steps": 10000, "loss": 2.2807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3232401695866687e-05, "epoch": 0.66, "percentage": 65.6, "elapsed_time": "9:26:18", "remaining_time": "4:56:58"}
657
+ {"current_steps": 6570, "total_steps": 10000, "loss": 2.2994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3163164889692197e-05, "epoch": 0.66, "percentage": 65.7, "elapsed_time": "9:27:11", "remaining_time": "4:56:06"}
658
+ {"current_steps": 6580, "total_steps": 10000, "loss": 2.21, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.309404490830152e-05, "epoch": 0.66, "percentage": 65.8, "elapsed_time": "9:28:03", "remaining_time": "4:55:14"}
659
+ {"current_steps": 6590, "total_steps": 10000, "loss": 2.269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3025042433880977e-05, "epoch": 0.66, "percentage": 65.9, "elapsed_time": "9:28:51", "remaining_time": "4:54:21"}
660
+ {"current_steps": 6600, "total_steps": 10000, "loss": 2.2933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2956158147457115e-05, "epoch": 0.66, "percentage": 66.0, "elapsed_time": "9:29:43", "remaining_time": "4:53:29"}
661
+ {"current_steps": 6610, "total_steps": 10000, "loss": 2.2638, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2887392728890052e-05, "epoch": 0.66, "percentage": 66.1, "elapsed_time": "9:30:34", "remaining_time": "4:52:37"}
662
+ {"current_steps": 6620, "total_steps": 10000, "loss": 2.2736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2818746856866687e-05, "epoch": 0.66, "percentage": 66.2, "elapsed_time": "9:31:22", "remaining_time": "4:51:43"}
663
+ {"current_steps": 6630, "total_steps": 10000, "loss": 2.262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2750221208894086e-05, "epoch": 0.66, "percentage": 66.3, "elapsed_time": "9:32:13", "remaining_time": "4:50:51"}
664
+ {"current_steps": 6640, "total_steps": 10000, "loss": 2.2822, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2681816461292715e-05, "epoch": 0.66, "percentage": 66.4, "elapsed_time": "9:33:05", "remaining_time": "4:50:00"}
665
+ {"current_steps": 6650, "total_steps": 10000, "loss": 2.2882, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.261353328918981e-05, "epoch": 0.67, "percentage": 66.5, "elapsed_time": "9:33:53", "remaining_time": "4:49:06"}
666
+ {"current_steps": 6660, "total_steps": 10000, "loss": 2.2787, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.254537236651273e-05, "epoch": 0.67, "percentage": 66.6, "elapsed_time": "9:34:45", "remaining_time": "4:48:14"}
667
+ {"current_steps": 6670, "total_steps": 10000, "loss": 2.265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2477334365982248e-05, "epoch": 0.67, "percentage": 66.7, "elapsed_time": "9:35:37", "remaining_time": "4:47:22"}
668
+ {"current_steps": 6680, "total_steps": 10000, "loss": 2.3073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2409419959105981e-05, "epoch": 0.67, "percentage": 66.8, "elapsed_time": "9:36:25", "remaining_time": "4:46:29"}
669
+ {"current_steps": 6690, "total_steps": 10000, "loss": 2.2866, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2341629816171681e-05, "epoch": 0.67, "percentage": 66.9, "elapsed_time": "9:37:16", "remaining_time": "4:45:37"}
670
+ {"current_steps": 6700, "total_steps": 10000, "loss": 2.2688, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2273964606240718e-05, "epoch": 0.67, "percentage": 67.0, "elapsed_time": "9:38:07", "remaining_time": "4:44:44"}
671
+ {"current_steps": 6710, "total_steps": 10000, "loss": 2.277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2206424997141371e-05, "epoch": 0.67, "percentage": 67.1, "elapsed_time": "9:38:59", "remaining_time": "4:43:53"}
672
+ {"current_steps": 6720, "total_steps": 10000, "loss": 2.3483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2139011655462337e-05, "epoch": 0.67, "percentage": 67.2, "elapsed_time": "9:39:50", "remaining_time": "4:43:01"}
673
+ {"current_steps": 6730, "total_steps": 10000, "loss": 2.2505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2071725246546073e-05, "epoch": 0.67, "percentage": 67.3, "elapsed_time": "9:40:39", "remaining_time": "4:42:07"}
674
+ {"current_steps": 6740, "total_steps": 10000, "loss": 2.29, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2004566434482261e-05, "epoch": 0.67, "percentage": 67.4, "elapsed_time": "9:41:31", "remaining_time": "4:41:16"}
675
+ {"current_steps": 6750, "total_steps": 10000, "loss": 2.2629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1937535882101281e-05, "epoch": 0.68, "percentage": 67.5, "elapsed_time": "9:42:22", "remaining_time": "4:40:24"}
676
+ {"current_steps": 6760, "total_steps": 10000, "loss": 2.3079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1870634250967605e-05, "epoch": 0.68, "percentage": 67.6, "elapsed_time": "9:43:10", "remaining_time": "4:39:30"}
677
+ {"current_steps": 6770, "total_steps": 10000, "loss": 2.3037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1803862201373342e-05, "epoch": 0.68, "percentage": 67.7, "elapsed_time": "9:44:01", "remaining_time": "4:38:38"}
678
+ {"current_steps": 6780, "total_steps": 10000, "loss": 2.3066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1737220392331644e-05, "epoch": 0.68, "percentage": 67.8, "elapsed_time": "9:44:54", "remaining_time": "4:37:47"}
679
+ {"current_steps": 6790, "total_steps": 10000, "loss": 2.3082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1670709481570285e-05, "epoch": 0.68, "percentage": 67.9, "elapsed_time": "9:45:42", "remaining_time": "4:36:53"}
680
+ {"current_steps": 6800, "total_steps": 10000, "loss": 2.2134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1604330125525079e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "9:46:36", "remaining_time": "4:36:02"}
681
+ {"current_steps": 6810, "total_steps": 10000, "loss": 2.2617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1538082979333495e-05, "epoch": 0.68, "percentage": 68.1, "elapsed_time": "9:47:23", "remaining_time": "4:35:09"}
682
+ {"current_steps": 6820, "total_steps": 10000, "loss": 2.2301, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1471968696828106e-05, "epoch": 0.68, "percentage": 68.2, "elapsed_time": "9:48:16", "remaining_time": "4:34:17"}
683
+ {"current_steps": 6830, "total_steps": 10000, "loss": 2.2853, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1405987930530184e-05, "epoch": 0.68, "percentage": 68.3, "elapsed_time": "9:49:08", "remaining_time": "4:33:26"}
684
+ {"current_steps": 6840, "total_steps": 10000, "loss": 2.2843, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1340141331643276e-05, "epoch": 0.68, "percentage": 68.4, "elapsed_time": "9:49:59", "remaining_time": "4:32:33"}
685
+ {"current_steps": 6850, "total_steps": 10000, "loss": 2.2672, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1274429550046704e-05, "epoch": 0.69, "percentage": 68.5, "elapsed_time": "9:50:46", "remaining_time": "4:31:40"}
686
+ {"current_steps": 6860, "total_steps": 10000, "loss": 2.2482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1208853234289246e-05, "epoch": 0.69, "percentage": 68.6, "elapsed_time": "9:51:39", "remaining_time": "4:30:49"}
687
+ {"current_steps": 6870, "total_steps": 10000, "loss": 2.2373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1143413031582645e-05, "epoch": 0.69, "percentage": 68.7, "elapsed_time": "9:52:30", "remaining_time": "4:29:56"}
688
+ {"current_steps": 6880, "total_steps": 10000, "loss": 2.2345, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.107810958779531e-05, "epoch": 0.69, "percentage": 68.8, "elapsed_time": "9:53:21", "remaining_time": "4:29:04"}
689
+ {"current_steps": 6890, "total_steps": 10000, "loss": 2.2712, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1012943547445829e-05, "epoch": 0.69, "percentage": 68.9, "elapsed_time": "9:54:09", "remaining_time": "4:28:11"}
690
+ {"current_steps": 6900, "total_steps": 10000, "loss": 2.2707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0947915553696742e-05, "epoch": 0.69, "percentage": 69.0, "elapsed_time": "9:55:01", "remaining_time": "4:27:20"}
691
+ {"current_steps": 6910, "total_steps": 10000, "loss": 2.277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0883026248348076e-05, "epoch": 0.69, "percentage": 69.1, "elapsed_time": "9:55:50", "remaining_time": "4:26:26"}
692
+ {"current_steps": 6920, "total_steps": 10000, "loss": 2.278, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0818276271831093e-05, "epoch": 0.69, "percentage": 69.2, "elapsed_time": "9:56:42", "remaining_time": "4:25:35"}
693
+ {"current_steps": 6930, "total_steps": 10000, "loss": 2.2621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0753666263201906e-05, "epoch": 0.69, "percentage": 69.3, "elapsed_time": "9:57:34", "remaining_time": "4:24:43"}
694
+ {"current_steps": 6940, "total_steps": 10000, "loss": 2.2955, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0689196860135234e-05, "epoch": 0.69, "percentage": 69.4, "elapsed_time": "9:58:22", "remaining_time": "4:23:50"}
695
+ {"current_steps": 6950, "total_steps": 10000, "loss": 2.2963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0624868698918045e-05, "epoch": 0.69, "percentage": 69.5, "elapsed_time": "9:59:14", "remaining_time": "4:22:58"}
696
+ {"current_steps": 6960, "total_steps": 10000, "loss": 2.2728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0560682414443315e-05, "epoch": 0.7, "percentage": 69.6, "elapsed_time": "10:00:12", "remaining_time": "4:22:09"}
697
+ {"current_steps": 6970, "total_steps": 10000, "loss": 2.2468, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0496638640203774e-05, "epoch": 0.7, "percentage": 69.7, "elapsed_time": "10:00:55", "remaining_time": "4:21:14"}
698
+ {"current_steps": 6980, "total_steps": 10000, "loss": 2.2571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0432738008285603e-05, "epoch": 0.7, "percentage": 69.8, "elapsed_time": "10:01:49", "remaining_time": "4:20:23"}
699
+ {"current_steps": 6990, "total_steps": 10000, "loss": 2.2374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0368981149362256e-05, "epoch": 0.7, "percentage": 69.9, "elapsed_time": "10:02:42", "remaining_time": "4:19:32"}
700
+ {"current_steps": 7000, "total_steps": 10000, "loss": 2.2666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0305368692688174e-05, "epoch": 0.7, "percentage": 70.0, "elapsed_time": "10:03:35", "remaining_time": "4:18:40"}
701
+ {"current_steps": 7010, "total_steps": 10000, "loss": 2.268, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0241901266092643e-05, "epoch": 0.7, "percentage": 70.1, "elapsed_time": "10:04:56", "remaining_time": "4:18:01"}
702
+ {"current_steps": 7020, "total_steps": 10000, "loss": 2.2977, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.017857949597352e-05, "epoch": 0.7, "percentage": 70.2, "elapsed_time": "10:05:39", "remaining_time": "4:17:06"}