ryanmarten commited on
Commit
ed6ecf9
·
verified ·
1 Parent(s): 80c682e

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 sha256:0bfd47b8b42782908601ad5b4d521325ca520e5d0d1ab33f465595bbb24e441d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac6a9f67bc364c64cb66a6cd3a727fe12cc82cb59066fe479d5fc7201161693
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:b5ec0fc144fed3782694c80fea16bc8f89a816a5544c129df87babc835ffdd0a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8497eb0b590d5fdfcb0f033a525928b2ace76eb74c5dee0ff4efbc996fd86fc2
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:beb5487f2eeb1079199edff35e924b551e768903c1629e70b426910d31ac884c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a06d20faf7ff356d63a209eba4a717262ede9568db7107555f84de900ed8e6
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6499a254e9857103cb63976ea78a0914cf27885f57d100d5035480b5af2e4e47
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d745a153b6b5d5132805cfec4f35c82861b69743c79ce3e2970275b3784d75
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -622,3 +622,155 @@
622
  {"current_steps": 622, "total_steps": 775, "loss": 0.3295, "lr": 4.570216403561141e-06, "epoch": 4.0, "percentage": 80.26, "elapsed_time": "7:32:42", "remaining_time": "1:51:21"}
623
  {"current_steps": 623, "total_steps": 775, "loss": 0.2947, "lr": 4.513018537450897e-06, "epoch": 4.006430868167203, "percentage": 80.39, "elapsed_time": "7:34:10", "remaining_time": "1:50:48"}
624
  {"current_steps": 624, "total_steps": 775, "loss": 0.2952, "lr": 4.456135301414672e-06, "epoch": 4.012861736334405, "percentage": 80.52, "elapsed_time": "7:34:52", "remaining_time": "1:50:04"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
622
  {"current_steps": 622, "total_steps": 775, "loss": 0.3295, "lr": 4.570216403561141e-06, "epoch": 4.0, "percentage": 80.26, "elapsed_time": "7:32:42", "remaining_time": "1:51:21"}
623
  {"current_steps": 623, "total_steps": 775, "loss": 0.2947, "lr": 4.513018537450897e-06, "epoch": 4.006430868167203, "percentage": 80.39, "elapsed_time": "7:34:10", "remaining_time": "1:50:48"}
624
  {"current_steps": 624, "total_steps": 775, "loss": 0.2952, "lr": 4.456135301414672e-06, "epoch": 4.012861736334405, "percentage": 80.52, "elapsed_time": "7:34:52", "remaining_time": "1:50:04"}
625
+ {"current_steps": 625, "total_steps": 775, "loss": 0.3121, "lr": 4.3995678510796445e-06, "epoch": 4.019292604501608, "percentage": 80.65, "elapsed_time": "7:35:33", "remaining_time": "1:49:19"}
626
+ {"current_steps": 626, "total_steps": 775, "loss": 0.3027, "lr": 4.343317335657571e-06, "epoch": 4.02572347266881, "percentage": 80.77, "elapsed_time": "7:36:16", "remaining_time": "1:48:36"}
627
+ {"current_steps": 627, "total_steps": 775, "loss": 0.2738, "lr": 4.287384897921423e-06, "epoch": 4.032154340836013, "percentage": 80.9, "elapsed_time": "7:37:03", "remaining_time": "1:47:53"}
628
+ {"current_steps": 628, "total_steps": 775, "loss": 0.3134, "lr": 4.231771674182181e-06, "epoch": 4.038585209003215, "percentage": 81.03, "elapsed_time": "7:37:50", "remaining_time": "1:47:10"}
629
+ {"current_steps": 629, "total_steps": 775, "loss": 0.303, "lr": 4.176478794265737e-06, "epoch": 4.045016077170418, "percentage": 81.16, "elapsed_time": "7:38:33", "remaining_time": "1:46:26"}
630
+ {"current_steps": 630, "total_steps": 775, "loss": 0.2687, "lr": 4.1215073814899466e-06, "epoch": 4.051446945337621, "percentage": 81.29, "elapsed_time": "7:39:15", "remaining_time": "1:45:42"}
631
+ {"current_steps": 631, "total_steps": 775, "loss": 0.3086, "lr": 4.0668585526418235e-06, "epoch": 4.057877813504823, "percentage": 81.42, "elapsed_time": "7:40:03", "remaining_time": "1:44:59"}
632
+ {"current_steps": 632, "total_steps": 775, "loss": 0.2677, "lr": 4.012533417954834e-06, "epoch": 4.064308681672026, "percentage": 81.55, "elapsed_time": "7:40:44", "remaining_time": "1:44:15"}
633
+ {"current_steps": 633, "total_steps": 775, "loss": 0.2869, "lr": 3.958533081086331e-06, "epoch": 4.070739549839228, "percentage": 81.68, "elapsed_time": "7:41:24", "remaining_time": "1:43:30"}
634
+ {"current_steps": 634, "total_steps": 775, "loss": 0.2826, "lr": 3.904858639095174e-06, "epoch": 4.077170418006431, "percentage": 81.81, "elapsed_time": "7:42:09", "remaining_time": "1:42:46"}
635
+ {"current_steps": 635, "total_steps": 775, "loss": 0.2645, "lr": 3.851511182419385e-06, "epoch": 4.083601286173633, "percentage": 81.94, "elapsed_time": "7:42:49", "remaining_time": "1:42:02"}
636
+ {"current_steps": 636, "total_steps": 775, "loss": 0.2751, "lr": 3.7984917948540513e-06, "epoch": 4.090032154340836, "percentage": 82.06, "elapsed_time": "7:43:34", "remaining_time": "1:41:18"}
637
+ {"current_steps": 637, "total_steps": 775, "loss": 0.294, "lr": 3.7458015535292603e-06, "epoch": 4.096463022508039, "percentage": 82.19, "elapsed_time": "7:44:15", "remaining_time": "1:40:34"}
638
+ {"current_steps": 638, "total_steps": 775, "loss": 0.2776, "lr": 3.6934415288882487e-06, "epoch": 4.102893890675241, "percentage": 82.32, "elapsed_time": "7:44:56", "remaining_time": "1:39:50"}
639
+ {"current_steps": 639, "total_steps": 775, "loss": 0.3021, "lr": 3.641412784665648e-06, "epoch": 4.109324758842444, "percentage": 82.45, "elapsed_time": "7:45:40", "remaining_time": "1:39:06"}
640
+ {"current_steps": 640, "total_steps": 775, "loss": 0.2877, "lr": 3.5897163778658618e-06, "epoch": 4.115755627009646, "percentage": 82.58, "elapsed_time": "7:46:17", "remaining_time": "1:38:21"}
641
+ {"current_steps": 641, "total_steps": 775, "loss": 0.2804, "lr": 3.5383533587415954e-06, "epoch": 4.122186495176849, "percentage": 82.71, "elapsed_time": "7:47:03", "remaining_time": "1:37:38"}
642
+ {"current_steps": 642, "total_steps": 775, "loss": 0.2786, "lr": 3.4873247707725376e-06, "epoch": 4.128617363344051, "percentage": 82.84, "elapsed_time": "7:47:42", "remaining_time": "1:36:53"}
643
+ {"current_steps": 643, "total_steps": 775, "loss": 0.2471, "lr": 3.436631650644142e-06, "epoch": 4.135048231511254, "percentage": 82.97, "elapsed_time": "7:48:22", "remaining_time": "1:36:09"}
644
+ {"current_steps": 644, "total_steps": 775, "loss": 0.2981, "lr": 3.3862750282265798e-06, "epoch": 4.141479099678457, "percentage": 83.1, "elapsed_time": "7:49:08", "remaining_time": "1:35:25"}
645
+ {"current_steps": 645, "total_steps": 775, "loss": 0.2729, "lr": 3.3362559265537954e-06, "epoch": 4.147909967845659, "percentage": 83.23, "elapsed_time": "7:49:52", "remaining_time": "1:34:42"}
646
+ {"current_steps": 646, "total_steps": 775, "loss": 0.2702, "lr": 3.2865753618027398e-06, "epoch": 4.154340836012862, "percentage": 83.35, "elapsed_time": "7:50:33", "remaining_time": "1:33:57"}
647
+ {"current_steps": 647, "total_steps": 775, "loss": 0.2743, "lr": 3.2372343432727305e-06, "epoch": 4.160771704180064, "percentage": 83.48, "elapsed_time": "7:51:19", "remaining_time": "1:33:14"}
648
+ {"current_steps": 648, "total_steps": 775, "loss": 0.2582, "lr": 3.188233873364941e-06, "epoch": 4.167202572347267, "percentage": 83.61, "elapsed_time": "7:51:58", "remaining_time": "1:32:30"}
649
+ {"current_steps": 649, "total_steps": 775, "loss": 0.2875, "lr": 3.1395749475620185e-06, "epoch": 4.173633440514469, "percentage": 83.74, "elapsed_time": "7:52:42", "remaining_time": "1:31:46"}
650
+ {"current_steps": 650, "total_steps": 775, "loss": 0.2848, "lr": 3.091258554407901e-06, "epoch": 4.180064308681672, "percentage": 83.87, "elapsed_time": "7:53:27", "remaining_time": "1:31:02"}
651
+ {"current_steps": 651, "total_steps": 775, "loss": 0.3006, "lr": 3.0432856754876817e-06, "epoch": 4.186495176848875, "percentage": 84.0, "elapsed_time": "7:54:14", "remaining_time": "1:30:19"}
652
+ {"current_steps": 652, "total_steps": 775, "loss": 0.2901, "lr": 2.9956572854077205e-06, "epoch": 4.192926045016077, "percentage": 84.13, "elapsed_time": "7:54:51", "remaining_time": "1:29:34"}
653
+ {"current_steps": 653, "total_steps": 775, "loss": 0.3014, "lr": 2.9483743517757956e-06, "epoch": 4.19935691318328, "percentage": 84.26, "elapsed_time": "7:55:35", "remaining_time": "1:28:51"}
654
+ {"current_steps": 654, "total_steps": 775, "loss": 0.263, "lr": 2.9014378351814866e-06, "epoch": 4.205787781350482, "percentage": 84.39, "elapsed_time": "7:56:15", "remaining_time": "1:28:06"}
655
+ {"current_steps": 655, "total_steps": 775, "loss": 0.2769, "lr": 2.854848689176637e-06, "epoch": 4.212218649517685, "percentage": 84.52, "elapsed_time": "7:56:55", "remaining_time": "1:27:22"}
656
+ {"current_steps": 656, "total_steps": 775, "loss": 0.2734, "lr": 2.808607860255981e-06, "epoch": 4.218649517684887, "percentage": 84.65, "elapsed_time": "7:57:36", "remaining_time": "1:26:38"}
657
+ {"current_steps": 657, "total_steps": 775, "loss": 0.2866, "lr": 2.762716287837921e-06, "epoch": 4.22508038585209, "percentage": 84.77, "elapsed_time": "7:58:21", "remaining_time": "1:25:54"}
658
+ {"current_steps": 658, "total_steps": 775, "loss": 0.3012, "lr": 2.717174904245445e-06, "epoch": 4.231511254019293, "percentage": 84.9, "elapsed_time": "7:59:05", "remaining_time": "1:25:11"}
659
+ {"current_steps": 659, "total_steps": 775, "loss": 0.2775, "lr": 2.671984634687186e-06, "epoch": 4.237942122186495, "percentage": 85.03, "elapsed_time": "7:59:47", "remaining_time": "1:24:27"}
660
+ {"current_steps": 660, "total_steps": 775, "loss": 0.2894, "lr": 2.6271463972386226e-06, "epoch": 4.244372990353698, "percentage": 85.16, "elapsed_time": "8:00:39", "remaining_time": "1:23:45"}
661
+ {"current_steps": 661, "total_steps": 775, "loss": 0.2691, "lr": 2.582661102823416e-06, "epoch": 4.2508038585209, "percentage": 85.29, "elapsed_time": "8:01:21", "remaining_time": "1:23:01"}
662
+ {"current_steps": 662, "total_steps": 775, "loss": 0.2958, "lr": 2.5385296551949214e-06, "epoch": 4.257234726688103, "percentage": 85.42, "elapsed_time": "8:02:09", "remaining_time": "1:22:18"}
663
+ {"current_steps": 663, "total_steps": 775, "loss": 0.2557, "lr": 2.4947529509178246e-06, "epoch": 4.263665594855305, "percentage": 85.55, "elapsed_time": "8:02:47", "remaining_time": "1:21:33"}
664
+ {"current_steps": 664, "total_steps": 775, "loss": 0.2754, "lr": 2.4513318793499274e-06, "epoch": 4.270096463022508, "percentage": 85.68, "elapsed_time": "8:03:33", "remaining_time": "1:20:50"}
665
+ {"current_steps": 665, "total_steps": 775, "loss": 0.293, "lr": 2.4082673226240627e-06, "epoch": 4.276527331189711, "percentage": 85.81, "elapsed_time": "8:04:16", "remaining_time": "1:20:06"}
666
+ {"current_steps": 666, "total_steps": 775, "loss": 0.2677, "lr": 2.365560155630202e-06, "epoch": 4.282958199356913, "percentage": 85.94, "elapsed_time": "8:05:00", "remaining_time": "1:19:22"}
667
+ {"current_steps": 667, "total_steps": 775, "loss": 0.3004, "lr": 2.3232112459976562e-06, "epoch": 4.289389067524116, "percentage": 86.06, "elapsed_time": "8:05:41", "remaining_time": "1:18:38"}
668
+ {"current_steps": 668, "total_steps": 775, "loss": 0.3121, "lr": 2.2812214540774645e-06, "epoch": 4.295819935691318, "percentage": 86.19, "elapsed_time": "8:06:24", "remaining_time": "1:17:54"}
669
+ {"current_steps": 669, "total_steps": 775, "loss": 0.3024, "lr": 2.239591632924907e-06, "epoch": 4.302250803858521, "percentage": 86.32, "elapsed_time": "8:07:08", "remaining_time": "1:17:11"}
670
+ {"current_steps": 670, "total_steps": 775, "loss": 0.303, "lr": 2.198322628282181e-06, "epoch": 4.308681672025724, "percentage": 86.45, "elapsed_time": "8:07:56", "remaining_time": "1:16:28"}
671
+ {"current_steps": 671, "total_steps": 775, "loss": 0.2857, "lr": 2.157415278561219e-06, "epoch": 4.315112540192926, "percentage": 86.58, "elapsed_time": "8:08:44", "remaining_time": "1:15:45"}
672
+ {"current_steps": 672, "total_steps": 775, "loss": 0.2713, "lr": 2.1168704148266415e-06, "epoch": 4.321543408360129, "percentage": 86.71, "elapsed_time": "8:09:25", "remaining_time": "1:15:00"}
673
+ {"current_steps": 673, "total_steps": 775, "loss": 0.2981, "lr": 2.0766888607788906e-06, "epoch": 4.327974276527331, "percentage": 86.84, "elapsed_time": "8:10:13", "remaining_time": "1:14:17"}
674
+ {"current_steps": 674, "total_steps": 775, "loss": 0.2989, "lr": 2.0368714327374905e-06, "epoch": 4.334405144694534, "percentage": 86.97, "elapsed_time": "8:10:56", "remaining_time": "1:13:34"}
675
+ {"current_steps": 675, "total_steps": 775, "loss": 0.2577, "lr": 1.9974189396244627e-06, "epoch": 4.340836012861736, "percentage": 87.1, "elapsed_time": "8:11:34", "remaining_time": "1:12:49"}
676
+ {"current_steps": 676, "total_steps": 775, "loss": 0.301, "lr": 1.958332182947895e-06, "epoch": 4.347266881028939, "percentage": 87.23, "elapsed_time": "8:12:18", "remaining_time": "1:12:05"}
677
+ {"current_steps": 677, "total_steps": 775, "loss": 0.2595, "lr": 1.9196119567856455e-06, "epoch": 4.353697749196142, "percentage": 87.35, "elapsed_time": "8:12:58", "remaining_time": "1:11:21"}
678
+ {"current_steps": 678, "total_steps": 775, "loss": 0.2851, "lr": 1.8812590477692216e-06, "epoch": 4.360128617363344, "percentage": 87.48, "elapsed_time": "8:13:40", "remaining_time": "1:10:37"}
679
+ {"current_steps": 679, "total_steps": 775, "loss": 0.2762, "lr": 1.8432742350678023e-06, "epoch": 4.366559485530547, "percentage": 87.61, "elapsed_time": "8:14:25", "remaining_time": "1:09:54"}
680
+ {"current_steps": 680, "total_steps": 775, "loss": 0.3076, "lr": 1.8056582903724095e-06, "epoch": 4.372990353697749, "percentage": 87.74, "elapsed_time": "8:15:06", "remaining_time": "1:09:10"}
681
+ {"current_steps": 681, "total_steps": 775, "loss": 0.2627, "lr": 1.7684119778802066e-06, "epoch": 4.379421221864952, "percentage": 87.87, "elapsed_time": "8:15:49", "remaining_time": "1:08:26"}
682
+ {"current_steps": 682, "total_steps": 775, "loss": 0.2882, "lr": 1.7315360542790105e-06, "epoch": 4.385852090032154, "percentage": 88.0, "elapsed_time": "8:16:29", "remaining_time": "1:07:42"}
683
+ {"current_steps": 683, "total_steps": 775, "loss": 0.2752, "lr": 1.6950312687318816e-06, "epoch": 4.392282958199357, "percentage": 88.13, "elapsed_time": "8:17:10", "remaining_time": "1:06:58"}
684
+ {"current_steps": 684, "total_steps": 775, "loss": 0.3032, "lr": 1.6588983628619404e-06, "epoch": 4.39871382636656, "percentage": 88.26, "elapsed_time": "8:17:57", "remaining_time": "1:06:14"}
685
+ {"current_steps": 685, "total_steps": 775, "loss": 0.2749, "lr": 1.6231380707372668e-06, "epoch": 4.405144694533762, "percentage": 88.39, "elapsed_time": "8:18:44", "remaining_time": "1:05:31"}
686
+ {"current_steps": 686, "total_steps": 775, "loss": 0.3008, "lr": 1.5877511188560092e-06, "epoch": 4.411575562700965, "percentage": 88.52, "elapsed_time": "8:19:31", "remaining_time": "1:04:48"}
687
+ {"current_steps": 687, "total_steps": 775, "loss": 0.287, "lr": 1.5527382261316272e-06, "epoch": 4.418006430868167, "percentage": 88.65, "elapsed_time": "8:20:18", "remaining_time": "1:04:05"}
688
+ {"current_steps": 688, "total_steps": 775, "loss": 0.2704, "lr": 1.5181001038782618e-06, "epoch": 4.42443729903537, "percentage": 88.77, "elapsed_time": "8:21:03", "remaining_time": "1:03:21"}
689
+ {"current_steps": 689, "total_steps": 775, "loss": 0.2919, "lr": 1.4838374557963064e-06, "epoch": 4.430868167202572, "percentage": 88.9, "elapsed_time": "8:21:48", "remaining_time": "1:02:38"}
690
+ {"current_steps": 690, "total_steps": 775, "loss": 0.2752, "lr": 1.4499509779581078e-06, "epoch": 4.437299035369775, "percentage": 89.03, "elapsed_time": "8:22:34", "remaining_time": "1:01:54"}
691
+ {"current_steps": 691, "total_steps": 775, "loss": 0.2851, "lr": 1.4164413587938209e-06, "epoch": 4.443729903536978, "percentage": 89.16, "elapsed_time": "8:23:21", "remaining_time": "1:01:11"}
692
+ {"current_steps": 692, "total_steps": 775, "loss": 0.2623, "lr": 1.383309279077425e-06, "epoch": 4.45016077170418, "percentage": 89.29, "elapsed_time": "8:24:01", "remaining_time": "1:00:27"}
693
+ {"current_steps": 693, "total_steps": 775, "loss": 0.2671, "lr": 1.3505554119128861e-06, "epoch": 4.456591639871383, "percentage": 89.42, "elapsed_time": "8:24:44", "remaining_time": "0:59:43"}
694
+ {"current_steps": 694, "total_steps": 775, "loss": 0.2886, "lr": 1.3181804227204897e-06, "epoch": 4.463022508038585, "percentage": 89.55, "elapsed_time": "8:25:28", "remaining_time": "0:58:59"}
695
+ {"current_steps": 695, "total_steps": 775, "loss": 0.2817, "lr": 1.286184969223323e-06, "epoch": 4.469453376205788, "percentage": 89.68, "elapsed_time": "8:26:10", "remaining_time": "0:58:15"}
696
+ {"current_steps": 696, "total_steps": 775, "loss": 0.303, "lr": 1.2545697014339141e-06, "epoch": 4.47588424437299, "percentage": 89.81, "elapsed_time": "8:26:57", "remaining_time": "0:57:32"}
697
+ {"current_steps": 697, "total_steps": 775, "loss": 0.2779, "lr": 1.2233352616410122e-06, "epoch": 4.482315112540193, "percentage": 89.94, "elapsed_time": "8:27:40", "remaining_time": "0:56:48"}
698
+ {"current_steps": 698, "total_steps": 775, "loss": 0.2886, "lr": 1.192482284396561e-06, "epoch": 4.488745980707396, "percentage": 90.06, "elapsed_time": "8:28:22", "remaining_time": "0:56:04"}
699
+ {"current_steps": 699, "total_steps": 775, "loss": 0.2642, "lr": 1.1620113965027823e-06, "epoch": 4.495176848874598, "percentage": 90.19, "elapsed_time": "8:29:00", "remaining_time": "0:55:20"}
700
+ {"current_steps": 700, "total_steps": 775, "loss": 0.2848, "lr": 1.131923216999471e-06, "epoch": 4.501607717041801, "percentage": 90.32, "elapsed_time": "8:29:45", "remaining_time": "0:54:37"}
701
+ {"current_steps": 701, "total_steps": 775, "loss": 0.2791, "lr": 1.1022183571513944e-06, "epoch": 4.508038585209003, "percentage": 90.45, "elapsed_time": "8:30:27", "remaining_time": "0:53:53"}
702
+ {"current_steps": 702, "total_steps": 775, "loss": 0.2955, "lr": 1.0728974204358833e-06, "epoch": 4.514469453376206, "percentage": 90.58, "elapsed_time": "8:31:10", "remaining_time": "0:53:09"}
703
+ {"current_steps": 703, "total_steps": 775, "loss": 0.2924, "lr": 1.0439610025305735e-06, "epoch": 4.520900321543408, "percentage": 90.71, "elapsed_time": "8:31:55", "remaining_time": "0:52:25"}
704
+ {"current_steps": 704, "total_steps": 775, "loss": 0.2548, "lr": 1.0154096913012989e-06, "epoch": 4.527331189710611, "percentage": 90.84, "elapsed_time": "8:32:42", "remaining_time": "0:51:42"}
705
+ {"current_steps": 705, "total_steps": 775, "loss": 0.2757, "lr": 9.872440667901562e-07, "epoch": 4.533762057877814, "percentage": 90.97, "elapsed_time": "8:33:24", "remaining_time": "0:50:58"}
706
+ {"current_steps": 706, "total_steps": 775, "loss": 0.2705, "lr": 9.59464701203714e-07, "epoch": 4.540192926045016, "percentage": 91.1, "elapsed_time": "8:34:06", "remaining_time": "0:50:14"}
707
+ {"current_steps": 707, "total_steps": 775, "loss": 0.2566, "lr": 9.320721589013892e-07, "epoch": 4.546623794212219, "percentage": 91.23, "elapsed_time": "8:34:53", "remaining_time": "0:49:31"}
708
+ {"current_steps": 708, "total_steps": 775, "loss": 0.2794, "lr": 9.050669963839875e-07, "epoch": 4.553054662379421, "percentage": 91.35, "elapsed_time": "8:35:34", "remaining_time": "0:48:47"}
709
+ {"current_steps": 709, "total_steps": 775, "loss": 0.2603, "lr": 8.784497622823874e-07, "epoch": 4.559485530546624, "percentage": 91.48, "elapsed_time": "8:36:16", "remaining_time": "0:48:03"}
710
+ {"current_steps": 710, "total_steps": 775, "loss": 0.304, "lr": 8.522209973464024e-07, "epoch": 4.565916398713826, "percentage": 91.61, "elapsed_time": "8:37:04", "remaining_time": "0:47:20"}
711
+ {"current_steps": 711, "total_steps": 775, "loss": 0.3007, "lr": 8.263812344337907e-07, "epoch": 4.572347266881029, "percentage": 91.74, "elapsed_time": "8:37:46", "remaining_time": "0:46:36"}
712
+ {"current_steps": 712, "total_steps": 775, "loss": 0.273, "lr": 8.009309984994363e-07, "epoch": 4.578778135048232, "percentage": 91.87, "elapsed_time": "8:38:30", "remaining_time": "0:45:52"}
713
+ {"current_steps": 713, "total_steps": 775, "loss": 0.2772, "lr": 7.758708065846799e-07, "epoch": 4.585209003215434, "percentage": 92.0, "elapsed_time": "8:39:08", "remaining_time": "0:45:08"}
714
+ {"current_steps": 714, "total_steps": 775, "loss": 0.2907, "lr": 7.512011678068077e-07, "epoch": 4.591639871382637, "percentage": 92.13, "elapsed_time": "8:39:53", "remaining_time": "0:44:24"}
715
+ {"current_steps": 715, "total_steps": 775, "loss": 0.3144, "lr": 7.269225833487193e-07, "epoch": 4.598070739549839, "percentage": 92.26, "elapsed_time": "8:40:40", "remaining_time": "0:43:41"}
716
+ {"current_steps": 716, "total_steps": 775, "loss": 0.2798, "lr": 7.030355464487404e-07, "epoch": 4.604501607717042, "percentage": 92.39, "elapsed_time": "8:41:20", "remaining_time": "0:42:57"}
717
+ {"current_steps": 717, "total_steps": 775, "loss": 0.2866, "lr": 6.79540542390611e-07, "epoch": 4.610932475884244, "percentage": 92.52, "elapsed_time": "8:42:01", "remaining_time": "0:42:13"}
718
+ {"current_steps": 718, "total_steps": 775, "loss": 0.2663, "lr": 6.564380484936062e-07, "epoch": 4.617363344051447, "percentage": 92.65, "elapsed_time": "8:42:43", "remaining_time": "0:41:29"}
719
+ {"current_steps": 719, "total_steps": 775, "loss": 0.2954, "lr": 6.33728534102862e-07, "epoch": 4.62379421221865, "percentage": 92.77, "elapsed_time": "8:43:27", "remaining_time": "0:40:46"}
720
+ {"current_steps": 720, "total_steps": 775, "loss": 0.2727, "lr": 6.114124605798232e-07, "epoch": 4.630225080385852, "percentage": 92.9, "elapsed_time": "8:44:13", "remaining_time": "0:40:02"}
721
+ {"current_steps": 721, "total_steps": 775, "loss": 0.3034, "lr": 5.894902812928838e-07, "epoch": 4.636655948553055, "percentage": 93.03, "elapsed_time": "8:44:56", "remaining_time": "0:39:18"}
722
+ {"current_steps": 722, "total_steps": 775, "loss": 0.2449, "lr": 5.679624416081652e-07, "epoch": 4.643086816720257, "percentage": 93.16, "elapsed_time": "8:45:41", "remaining_time": "0:38:35"}
723
+ {"current_steps": 723, "total_steps": 775, "loss": 0.2826, "lr": 5.468293788804735e-07, "epoch": 4.64951768488746, "percentage": 93.29, "elapsed_time": "8:46:23", "remaining_time": "0:37:51"}
724
+ {"current_steps": 724, "total_steps": 775, "loss": 0.283, "lr": 5.260915224444207e-07, "epoch": 4.655948553054662, "percentage": 93.42, "elapsed_time": "8:47:06", "remaining_time": "0:37:07"}
725
+ {"current_steps": 725, "total_steps": 775, "loss": 0.3025, "lr": 5.05749293605684e-07, "epoch": 4.662379421221865, "percentage": 93.55, "elapsed_time": "8:47:51", "remaining_time": "0:36:24"}
726
+ {"current_steps": 726, "total_steps": 775, "loss": 0.2976, "lr": 4.858031056324652e-07, "epoch": 4.668810289389068, "percentage": 93.68, "elapsed_time": "8:48:38", "remaining_time": "0:35:40"}
727
+ {"current_steps": 727, "total_steps": 775, "loss": 0.2594, "lr": 4.6625336374708894e-07, "epoch": 4.67524115755627, "percentage": 93.81, "elapsed_time": "8:49:18", "remaining_time": "0:34:56"}
728
+ {"current_steps": 728, "total_steps": 775, "loss": 0.2675, "lr": 4.471004651177646e-07, "epoch": 4.681672025723473, "percentage": 93.94, "elapsed_time": "8:49:59", "remaining_time": "0:34:12"}
729
+ {"current_steps": 729, "total_steps": 775, "loss": 0.3021, "lr": 4.2834479885052846e-07, "epoch": 4.688102893890675, "percentage": 94.06, "elapsed_time": "8:50:41", "remaining_time": "0:33:29"}
730
+ {"current_steps": 730, "total_steps": 775, "loss": 0.2879, "lr": 4.099867459813256e-07, "epoch": 4.694533762057878, "percentage": 94.19, "elapsed_time": "8:51:26", "remaining_time": "0:32:45"}
731
+ {"current_steps": 731, "total_steps": 775, "loss": 0.2828, "lr": 3.9202667946828033e-07, "epoch": 4.70096463022508, "percentage": 94.32, "elapsed_time": "8:52:14", "remaining_time": "0:32:02"}
732
+ {"current_steps": 732, "total_steps": 775, "loss": 0.2818, "lr": 3.744649641841114e-07, "epoch": 4.707395498392283, "percentage": 94.45, "elapsed_time": "8:52:57", "remaining_time": "0:31:18"}
733
+ {"current_steps": 733, "total_steps": 775, "loss": 0.2888, "lr": 3.573019569087266e-07, "epoch": 4.713826366559486, "percentage": 94.58, "elapsed_time": "8:53:44", "remaining_time": "0:30:34"}
734
+ {"current_steps": 734, "total_steps": 775, "loss": 0.2677, "lr": 3.4053800632196434e-07, "epoch": 4.720257234726688, "percentage": 94.71, "elapsed_time": "8:54:30", "remaining_time": "0:29:51"}
735
+ {"current_steps": 735, "total_steps": 775, "loss": 0.2785, "lr": 3.2417345299652346e-07, "epoch": 4.726688102893891, "percentage": 94.84, "elapsed_time": "8:55:07", "remaining_time": "0:29:07"}
736
+ {"current_steps": 736, "total_steps": 775, "loss": 0.2882, "lr": 3.0820862939103137e-07, "epoch": 4.733118971061093, "percentage": 94.97, "elapsed_time": "8:55:51", "remaining_time": "0:28:23"}
737
+ {"current_steps": 737, "total_steps": 775, "loss": 0.2678, "lr": 2.926438598432957e-07, "epoch": 4.739549839228296, "percentage": 95.1, "elapsed_time": "8:56:36", "remaining_time": "0:27:40"}
738
+ {"current_steps": 738, "total_steps": 775, "loss": 0.2801, "lr": 2.7747946056371654e-07, "epoch": 4.745980707395498, "percentage": 95.23, "elapsed_time": "8:57:20", "remaining_time": "0:26:56"}
739
+ {"current_steps": 739, "total_steps": 775, "loss": 0.2977, "lr": 2.627157396288604e-07, "epoch": 4.752411575562701, "percentage": 95.35, "elapsed_time": "8:58:03", "remaining_time": "0:26:12"}
740
+ {"current_steps": 740, "total_steps": 775, "loss": 0.2569, "lr": 2.48352996975203e-07, "epoch": 4.758842443729904, "percentage": 95.48, "elapsed_time": "8:58:49", "remaining_time": "0:25:29"}
741
+ {"current_steps": 741, "total_steps": 775, "loss": 0.2999, "lr": 2.343915243930317e-07, "epoch": 4.765273311897106, "percentage": 95.61, "elapsed_time": "8:59:33", "remaining_time": "0:24:45"}
742
+ {"current_steps": 742, "total_steps": 775, "loss": 0.2772, "lr": 2.208316055205173e-07, "epoch": 4.771704180064309, "percentage": 95.74, "elapsed_time": "9:00:17", "remaining_time": "0:24:01"}
743
+ {"current_steps": 743, "total_steps": 775, "loss": 0.2711, "lr": 2.076735158379606e-07, "epoch": 4.778135048231511, "percentage": 95.87, "elapsed_time": "9:01:05", "remaining_time": "0:23:18"}
744
+ {"current_steps": 744, "total_steps": 775, "loss": 0.2913, "lr": 1.94917522662188e-07, "epoch": 4.784565916398714, "percentage": 96.0, "elapsed_time": "9:01:48", "remaining_time": "0:22:34"}
745
+ {"current_steps": 745, "total_steps": 775, "loss": 0.2511, "lr": 1.8256388514112487e-07, "epoch": 4.790996784565916, "percentage": 96.13, "elapsed_time": "9:02:29", "remaining_time": "0:21:50"}
746
+ {"current_steps": 746, "total_steps": 775, "loss": 0.2869, "lr": 1.7061285424852415e-07, "epoch": 4.797427652733119, "percentage": 96.26, "elapsed_time": "9:03:10", "remaining_time": "0:21:06"}
747
+ {"current_steps": 747, "total_steps": 775, "loss": 0.264, "lr": 1.590646727788725e-07, "epoch": 4.803858520900322, "percentage": 96.39, "elapsed_time": "9:03:50", "remaining_time": "0:20:23"}
748
+ {"current_steps": 748, "total_steps": 775, "loss": 0.2826, "lr": 1.4791957534245893e-07, "epoch": 4.810289389067524, "percentage": 96.52, "elapsed_time": "9:04:36", "remaining_time": "0:19:39"}
749
+ {"current_steps": 749, "total_steps": 775, "loss": 0.2583, "lr": 1.3717778836060735e-07, "epoch": 4.816720257234727, "percentage": 96.65, "elapsed_time": "9:05:17", "remaining_time": "0:18:55"}
750
+ {"current_steps": 750, "total_steps": 775, "loss": 0.3046, "lr": 1.2683953006107362e-07, "epoch": 4.823151125401929, "percentage": 96.77, "elapsed_time": "9:06:01", "remaining_time": "0:18:12"}
751
+ {"current_steps": 751, "total_steps": 775, "loss": 0.2915, "lr": 1.1690501047361802e-07, "epoch": 4.829581993569132, "percentage": 96.9, "elapsed_time": "9:06:45", "remaining_time": "0:17:28"}
752
+ {"current_steps": 752, "total_steps": 775, "loss": 0.2951, "lr": 1.0737443142573301e-07, "epoch": 4.836012861736334, "percentage": 97.03, "elapsed_time": "9:07:27", "remaining_time": "0:16:44"}
753
+ {"current_steps": 753, "total_steps": 775, "loss": 0.308, "lr": 9.824798653854217e-08, "epoch": 4.842443729903537, "percentage": 97.16, "elapsed_time": "9:08:14", "remaining_time": "0:16:01"}
754
+ {"current_steps": 754, "total_steps": 775, "loss": 0.2686, "lr": 8.952586122287443e-08, "epoch": 4.84887459807074, "percentage": 97.29, "elapsed_time": "9:08:54", "remaining_time": "0:15:17"}
755
+ {"current_steps": 755, "total_steps": 775, "loss": 0.2919, "lr": 8.120823267548705e-08, "epoch": 4.855305466237942, "percentage": 97.42, "elapsed_time": "9:09:38", "remaining_time": "0:14:33"}
756
+ {"current_steps": 756, "total_steps": 775, "loss": 0.2685, "lr": 7.329526987547742e-08, "epoch": 4.861736334405145, "percentage": 97.55, "elapsed_time": "9:10:21", "remaining_time": "0:13:49"}
757
+ {"current_steps": 757, "total_steps": 775, "loss": 0.3088, "lr": 6.578713358083466e-08, "epoch": 4.868167202572347, "percentage": 97.68, "elapsed_time": "9:11:05", "remaining_time": "0:13:06"}
758
+ {"current_steps": 758, "total_steps": 775, "loss": 0.2694, "lr": 5.8683976325191185e-08, "epoch": 4.87459807073955, "percentage": 97.81, "elapsed_time": "9:11:47", "remaining_time": "0:12:22"}
759
+ {"current_steps": 759, "total_steps": 775, "loss": 0.2744, "lr": 5.1985942414709556e-08, "epoch": 4.881028938906752, "percentage": 97.94, "elapsed_time": "9:12:29", "remaining_time": "0:11:38"}
760
+ {"current_steps": 760, "total_steps": 775, "loss": 0.2934, "lr": 4.569316792515599e-08, "epoch": 4.887459807073955, "percentage": 98.06, "elapsed_time": "9:13:12", "remaining_time": "0:10:55"}
761
+ {"current_steps": 761, "total_steps": 775, "loss": 0.2791, "lr": 3.9805780699144755e-08, "epoch": 4.893890675241158, "percentage": 98.19, "elapsed_time": "9:13:57", "remaining_time": "0:10:11"}
762
+ {"current_steps": 762, "total_steps": 775, "loss": 0.2813, "lr": 3.432390034352251e-08, "epoch": 4.90032154340836, "percentage": 98.32, "elapsed_time": "9:14:42", "remaining_time": "0:09:27"}
763
+ {"current_steps": 763, "total_steps": 775, "loss": 0.2731, "lr": 2.9247638226950205e-08, "epoch": 4.906752411575563, "percentage": 98.45, "elapsed_time": "9:15:20", "remaining_time": "0:08:44"}
764
+ {"current_steps": 764, "total_steps": 775, "loss": 0.2512, "lr": 2.4577097477647137e-08, "epoch": 4.913183279742765, "percentage": 98.58, "elapsed_time": "9:15:59", "remaining_time": "0:08:00"}
765
+ {"current_steps": 765, "total_steps": 775, "loss": 0.2872, "lr": 2.0312372981274864e-08, "epoch": 4.919614147909968, "percentage": 98.71, "elapsed_time": "9:16:43", "remaining_time": "0:07:16"}
766
+ {"current_steps": 766, "total_steps": 775, "loss": 0.2864, "lr": 1.645355137903426e-08, "epoch": 4.92604501607717, "percentage": 98.84, "elapsed_time": "9:17:29", "remaining_time": "0:06:33"}
767
+ {"current_steps": 767, "total_steps": 775, "loss": 0.2821, "lr": 1.3000711065882521e-08, "epoch": 4.932475884244373, "percentage": 98.97, "elapsed_time": "9:18:15", "remaining_time": "0:05:49"}
768
+ {"current_steps": 768, "total_steps": 775, "loss": 0.2878, "lr": 9.953922188958854e-09, "epoch": 4.938906752411576, "percentage": 99.1, "elapsed_time": "9:18:56", "remaining_time": "0:05:05"}
769
+ {"current_steps": 769, "total_steps": 775, "loss": 0.2652, "lr": 7.313246646150074e-09, "epoch": 4.945337620578778, "percentage": 99.23, "elapsed_time": "9:19:40", "remaining_time": "0:04:22"}
770
+ {"current_steps": 770, "total_steps": 775, "loss": 0.2943, "lr": 5.078738084831614e-09, "epoch": 4.951768488745981, "percentage": 99.35, "elapsed_time": "9:20:26", "remaining_time": "0:03:38"}
771
+ {"current_steps": 771, "total_steps": 775, "loss": 0.2773, "lr": 3.2504419007839406e-09, "epoch": 4.958199356913183, "percentage": 99.48, "elapsed_time": "9:21:10", "remaining_time": "0:02:54"}
772
+ {"current_steps": 772, "total_steps": 775, "loss": 0.2796, "lr": 1.8283952372666337e-09, "epoch": 4.964630225080386, "percentage": 99.61, "elapsed_time": "9:21:54", "remaining_time": "0:02:11"}
773
+ {"current_steps": 773, "total_steps": 775, "loss": 0.266, "lr": 8.126269842612111e-10, "epoch": 4.971061093247588, "percentage": 99.74, "elapsed_time": "9:22:33", "remaining_time": "0:01:27"}
774
+ {"current_steps": 774, "total_steps": 775, "loss": 0.2778, "lr": 2.0315777789159387e-10, "epoch": 4.977491961414791, "percentage": 99.87, "elapsed_time": "9:23:15", "remaining_time": "0:00:43"}
775
+ {"current_steps": 775, "total_steps": 775, "loss": 0.2972, "lr": 0.0, "epoch": 4.983922829581994, "percentage": 100.0, "elapsed_time": "9:24:00", "remaining_time": "0:00:00"}
776
+ {"current_steps": 775, "total_steps": 775, "epoch": 4.983922829581994, "percentage": 100.0, "elapsed_time": "9:25:06", "remaining_time": "0:00:00"}