neginr commited on
Commit
f613f52
·
verified ·
1 Parent(s): 9739b8b

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 sha256:2f1053fb3f93abbaf325f7dd2192a2d6d6c83ba5a9e01cb3f64e6be07e1b5c74
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2d69bcf83f2e10f219765d3adf7003bdbd881a7604e77032dd44eb199f368e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a98f7babe4260d39ac5ca7fb3d2371f75ac8580044ad0cd0d35a1ca8f07ca9a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c2d1feba198588458e95f59f56fb13dc8fd154c6e6e804a59c6b977b4aac5f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b9d946c66cb0c2ca95bf03f8717cb713f3d24bb751090a4ea3a87a94f9e5d9b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286d6f851139bb672a0669b0153bfe2014311bca2b93f1eb4477ed5996b2cf69
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b80d1717079dcbd1108a8ef711cb74a0eff92bee1ff262fe8aa2385ae51cf95
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b72aaec2a56dfb94b3ac5eab2fefe9f55a0b0fa4ab70abaff41e3af5cf35ec
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -742,3 +742,349 @@
742
  {"current_steps": 742, "total_steps": 1230, "loss": 0.4259, "lr": 1.6303679480270466e-05, "epoch": 3.0055696202531648, "percentage": 60.33, "elapsed_time": "9:21:41", "remaining_time": "6:09:24"}
743
  {"current_steps": 743, "total_steps": 1230, "loss": 0.4205, "lr": 1.624791353909428e-05, "epoch": 3.009620253164557, "percentage": 60.41, "elapsed_time": "9:22:27", "remaining_time": "6:08:39"}
744
  {"current_steps": 744, "total_steps": 1230, "loss": 0.4065, "lr": 1.619217781670663e-05, "epoch": 3.0136708860759494, "percentage": 60.49, "elapsed_time": "9:23:11", "remaining_time": "6:07:53"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
742
  {"current_steps": 742, "total_steps": 1230, "loss": 0.4259, "lr": 1.6303679480270466e-05, "epoch": 3.0055696202531648, "percentage": 60.33, "elapsed_time": "9:21:41", "remaining_time": "6:09:24"}
743
  {"current_steps": 743, "total_steps": 1230, "loss": 0.4205, "lr": 1.624791353909428e-05, "epoch": 3.009620253164557, "percentage": 60.41, "elapsed_time": "9:22:27", "remaining_time": "6:08:39"}
744
  {"current_steps": 744, "total_steps": 1230, "loss": 0.4065, "lr": 1.619217781670663e-05, "epoch": 3.0136708860759494, "percentage": 60.49, "elapsed_time": "9:23:11", "remaining_time": "6:07:53"}
745
+ {"current_steps": 745, "total_steps": 1230, "loss": 0.4178, "lr": 1.6136472761995373e-05, "epoch": 3.017721518987342, "percentage": 60.57, "elapsed_time": "9:23:56", "remaining_time": "6:07:08"}
746
+ {"current_steps": 746, "total_steps": 1230, "loss": 0.4376, "lr": 1.608079882360134e-05, "epoch": 3.0217721518987344, "percentage": 60.65, "elapsed_time": "9:24:41", "remaining_time": "6:06:21"}
747
+ {"current_steps": 747, "total_steps": 1230, "loss": 0.4172, "lr": 1.60251564499148e-05, "epoch": 3.0258227848101265, "percentage": 60.73, "elapsed_time": "9:25:26", "remaining_time": "6:05:36"}
748
+ {"current_steps": 748, "total_steps": 1230, "loss": 0.4193, "lr": 1.596954608907176e-05, "epoch": 3.029873417721519, "percentage": 60.81, "elapsed_time": "9:26:10", "remaining_time": "6:04:50"}
749
+ {"current_steps": 749, "total_steps": 1230, "loss": 0.431, "lr": 1.591396818895043e-05, "epoch": 3.0339240506329115, "percentage": 60.89, "elapsed_time": "9:26:56", "remaining_time": "6:04:04"}
750
+ {"current_steps": 750, "total_steps": 1230, "loss": 0.4179, "lr": 1.585842319716759e-05, "epoch": 3.037974683544304, "percentage": 60.98, "elapsed_time": "9:27:40", "remaining_time": "6:03:18"}
751
+ {"current_steps": 751, "total_steps": 1230, "loss": 0.4306, "lr": 1.5802911561074944e-05, "epoch": 3.042025316455696, "percentage": 61.06, "elapsed_time": "9:28:24", "remaining_time": "6:02:32"}
752
+ {"current_steps": 752, "total_steps": 1230, "loss": 0.4203, "lr": 1.5747433727755595e-05, "epoch": 3.0460759493670886, "percentage": 61.14, "elapsed_time": "9:29:09", "remaining_time": "6:01:46"}
753
+ {"current_steps": 753, "total_steps": 1230, "loss": 0.4306, "lr": 1.5691990144020376e-05, "epoch": 3.050126582278481, "percentage": 61.22, "elapsed_time": "9:29:52", "remaining_time": "6:00:59"}
754
+ {"current_steps": 754, "total_steps": 1230, "loss": 0.4207, "lr": 1.5636581256404297e-05, "epoch": 3.0541772151898736, "percentage": 61.3, "elapsed_time": "9:30:39", "remaining_time": "6:00:15"}
755
+ {"current_steps": 755, "total_steps": 1230, "loss": 0.4178, "lr": 1.558120751116291e-05, "epoch": 3.0582278481012657, "percentage": 61.38, "elapsed_time": "9:31:25", "remaining_time": "5:59:30"}
756
+ {"current_steps": 756, "total_steps": 1230, "loss": 0.4229, "lr": 1.552586935426876e-05, "epoch": 3.062278481012658, "percentage": 61.46, "elapsed_time": "9:32:10", "remaining_time": "5:58:44"}
757
+ {"current_steps": 757, "total_steps": 1230, "loss": 0.4215, "lr": 1.547056723140774e-05, "epoch": 3.0663291139240507, "percentage": 61.54, "elapsed_time": "9:32:54", "remaining_time": "5:57:58"}
758
+ {"current_steps": 758, "total_steps": 1230, "loss": 0.4224, "lr": 1.5415301587975565e-05, "epoch": 3.0703797468354432, "percentage": 61.63, "elapsed_time": "9:33:39", "remaining_time": "5:57:12"}
759
+ {"current_steps": 759, "total_steps": 1230, "loss": 0.4268, "lr": 1.536007286907411e-05, "epoch": 3.0744303797468353, "percentage": 61.71, "elapsed_time": "9:34:23", "remaining_time": "5:56:26"}
760
+ {"current_steps": 760, "total_steps": 1230, "loss": 0.4242, "lr": 1.5304881519507896e-05, "epoch": 3.078481012658228, "percentage": 61.79, "elapsed_time": "9:35:08", "remaining_time": "5:55:40"}
761
+ {"current_steps": 761, "total_steps": 1230, "loss": 0.4174, "lr": 1.5249727983780453e-05, "epoch": 3.0825316455696203, "percentage": 61.87, "elapsed_time": "9:35:54", "remaining_time": "5:54:55"}
762
+ {"current_steps": 762, "total_steps": 1230, "loss": 0.4188, "lr": 1.5194612706090786e-05, "epoch": 3.086582278481013, "percentage": 61.95, "elapsed_time": "9:36:38", "remaining_time": "5:54:09"}
763
+ {"current_steps": 763, "total_steps": 1230, "loss": 0.4169, "lr": 1.5139536130329771e-05, "epoch": 3.090632911392405, "percentage": 62.03, "elapsed_time": "9:37:22", "remaining_time": "5:53:23"}
764
+ {"current_steps": 764, "total_steps": 1230, "loss": 0.4181, "lr": 1.508449870007656e-05, "epoch": 3.0946835443037974, "percentage": 62.11, "elapsed_time": "9:38:05", "remaining_time": "5:52:36"}
765
+ {"current_steps": 765, "total_steps": 1230, "loss": 0.4311, "lr": 1.5029500858595056e-05, "epoch": 3.09873417721519, "percentage": 62.2, "elapsed_time": "9:38:50", "remaining_time": "5:51:50"}
766
+ {"current_steps": 766, "total_steps": 1230, "loss": 0.4338, "lr": 1.4974543048830328e-05, "epoch": 3.1027848101265825, "percentage": 62.28, "elapsed_time": "9:39:35", "remaining_time": "5:51:05"}
767
+ {"current_steps": 767, "total_steps": 1230, "loss": 0.4261, "lr": 1.4919625713405e-05, "epoch": 3.1068354430379745, "percentage": 62.36, "elapsed_time": "9:40:22", "remaining_time": "5:50:20"}
768
+ {"current_steps": 768, "total_steps": 1230, "loss": 0.4174, "lr": 1.4864749294615756e-05, "epoch": 3.110886075949367, "percentage": 62.44, "elapsed_time": "9:41:07", "remaining_time": "5:49:34"}
769
+ {"current_steps": 769, "total_steps": 1230, "loss": 0.4154, "lr": 1.4809914234429716e-05, "epoch": 3.1149367088607596, "percentage": 62.52, "elapsed_time": "9:41:52", "remaining_time": "5:48:49"}
770
+ {"current_steps": 770, "total_steps": 1230, "loss": 0.4143, "lr": 1.4755120974480923e-05, "epoch": 3.118987341772152, "percentage": 62.6, "elapsed_time": "9:42:35", "remaining_time": "5:48:02"}
771
+ {"current_steps": 771, "total_steps": 1230, "loss": 0.4224, "lr": 1.4700369956066771e-05, "epoch": 3.123037974683544, "percentage": 62.68, "elapsed_time": "9:43:20", "remaining_time": "5:47:16"}
772
+ {"current_steps": 772, "total_steps": 1230, "loss": 0.4333, "lr": 1.4645661620144413e-05, "epoch": 3.1270886075949367, "percentage": 62.76, "elapsed_time": "9:44:07", "remaining_time": "5:46:32"}
773
+ {"current_steps": 773, "total_steps": 1230, "loss": 0.4276, "lr": 1.4590996407327284e-05, "epoch": 3.131139240506329, "percentage": 62.85, "elapsed_time": "9:44:54", "remaining_time": "5:45:47"}
774
+ {"current_steps": 774, "total_steps": 1230, "loss": 0.4116, "lr": 1.4536374757881487e-05, "epoch": 3.1351898734177217, "percentage": 62.93, "elapsed_time": "9:45:40", "remaining_time": "5:45:02"}
775
+ {"current_steps": 775, "total_steps": 1230, "loss": 0.4204, "lr": 1.4481797111722271e-05, "epoch": 3.1392405063291138, "percentage": 63.01, "elapsed_time": "9:46:24", "remaining_time": "5:44:16"}
776
+ {"current_steps": 776, "total_steps": 1230, "loss": 0.4367, "lr": 1.4427263908410507e-05, "epoch": 3.1432911392405063, "percentage": 63.09, "elapsed_time": "9:47:06", "remaining_time": "5:43:29"}
777
+ {"current_steps": 777, "total_steps": 1230, "loss": 0.4213, "lr": 1.4372775587149108e-05, "epoch": 3.147341772151899, "percentage": 63.17, "elapsed_time": "9:47:55", "remaining_time": "5:42:45"}
778
+ {"current_steps": 778, "total_steps": 1230, "loss": 0.446, "lr": 1.4318332586779522e-05, "epoch": 3.1513924050632913, "percentage": 63.25, "elapsed_time": "9:48:41", "remaining_time": "5:42:01"}
779
+ {"current_steps": 779, "total_steps": 1230, "loss": 0.4353, "lr": 1.4263935345778202e-05, "epoch": 3.1554430379746834, "percentage": 63.33, "elapsed_time": "9:49:26", "remaining_time": "5:41:15"}
780
+ {"current_steps": 780, "total_steps": 1230, "loss": 0.4257, "lr": 1.420958430225303e-05, "epoch": 3.159493670886076, "percentage": 63.41, "elapsed_time": "9:50:10", "remaining_time": "5:40:29"}
781
+ {"current_steps": 781, "total_steps": 1230, "loss": 0.426, "lr": 1.415527989393985e-05, "epoch": 3.1635443037974684, "percentage": 63.5, "elapsed_time": "9:50:54", "remaining_time": "5:39:42"}
782
+ {"current_steps": 782, "total_steps": 1230, "loss": 0.4274, "lr": 1.410102255819891e-05, "epoch": 3.167594936708861, "percentage": 63.58, "elapsed_time": "9:51:41", "remaining_time": "5:38:58"}
783
+ {"current_steps": 783, "total_steps": 1230, "loss": 0.419, "lr": 1.404681273201131e-05, "epoch": 3.171645569620253, "percentage": 63.66, "elapsed_time": "9:52:25", "remaining_time": "5:38:12"}
784
+ {"current_steps": 784, "total_steps": 1230, "loss": 0.4117, "lr": 1.399265085197556e-05, "epoch": 3.1756962025316455, "percentage": 63.74, "elapsed_time": "9:53:10", "remaining_time": "5:37:26"}
785
+ {"current_steps": 785, "total_steps": 1230, "loss": 0.4289, "lr": 1.393853735430398e-05, "epoch": 3.179746835443038, "percentage": 63.82, "elapsed_time": "9:53:56", "remaining_time": "5:36:41"}
786
+ {"current_steps": 786, "total_steps": 1230, "loss": 0.424, "lr": 1.3884472674819246e-05, "epoch": 3.1837974683544306, "percentage": 63.9, "elapsed_time": "9:54:42", "remaining_time": "5:35:56"}
787
+ {"current_steps": 787, "total_steps": 1230, "loss": 0.4244, "lr": 1.3830457248950864e-05, "epoch": 3.1878481012658226, "percentage": 63.98, "elapsed_time": "9:55:26", "remaining_time": "5:35:10"}
788
+ {"current_steps": 788, "total_steps": 1230, "loss": 0.4215, "lr": 1.377649151173163e-05, "epoch": 3.191898734177215, "percentage": 64.07, "elapsed_time": "9:56:11", "remaining_time": "5:34:24"}
789
+ {"current_steps": 789, "total_steps": 1230, "loss": 0.4145, "lr": 1.3722575897794181e-05, "epoch": 3.1959493670886077, "percentage": 64.15, "elapsed_time": "9:56:54", "remaining_time": "5:33:38"}
790
+ {"current_steps": 790, "total_steps": 1230, "loss": 0.4256, "lr": 1.3668710841367472e-05, "epoch": 3.2, "percentage": 64.23, "elapsed_time": "9:57:40", "remaining_time": "5:32:52"}
791
+ {"current_steps": 791, "total_steps": 1230, "loss": 0.4211, "lr": 1.361489677627324e-05, "epoch": 3.2040506329113922, "percentage": 64.31, "elapsed_time": "9:58:24", "remaining_time": "5:32:06"}
792
+ {"current_steps": 792, "total_steps": 1230, "loss": 0.4344, "lr": 1.3561134135922585e-05, "epoch": 3.2081012658227848, "percentage": 64.39, "elapsed_time": "9:59:07", "remaining_time": "5:31:20"}
793
+ {"current_steps": 793, "total_steps": 1230, "loss": 0.4127, "lr": 1.350742335331241e-05, "epoch": 3.2121518987341773, "percentage": 64.47, "elapsed_time": "9:59:52", "remaining_time": "5:30:34"}
794
+ {"current_steps": 794, "total_steps": 1230, "loss": 0.4131, "lr": 1.345376486102198e-05, "epoch": 3.21620253164557, "percentage": 64.55, "elapsed_time": "10:00:36", "remaining_time": "5:29:48"}
795
+ {"current_steps": 795, "total_steps": 1230, "loss": 0.4098, "lr": 1.3400159091209414e-05, "epoch": 3.220253164556962, "percentage": 64.63, "elapsed_time": "10:01:21", "remaining_time": "5:29:02"}
796
+ {"current_steps": 796, "total_steps": 1230, "loss": 0.4245, "lr": 1.3346606475608216e-05, "epoch": 3.2243037974683544, "percentage": 64.72, "elapsed_time": "10:02:05", "remaining_time": "5:28:16"}
797
+ {"current_steps": 797, "total_steps": 1230, "loss": 0.4125, "lr": 1.3293107445523781e-05, "epoch": 3.228354430379747, "percentage": 64.8, "elapsed_time": "10:02:49", "remaining_time": "5:27:30"}
798
+ {"current_steps": 798, "total_steps": 1230, "loss": 0.4135, "lr": 1.3239662431829949e-05, "epoch": 3.2324050632911394, "percentage": 64.88, "elapsed_time": "10:03:30", "remaining_time": "5:26:42"}
799
+ {"current_steps": 799, "total_steps": 1230, "loss": 0.4259, "lr": 1.3186271864965509e-05, "epoch": 3.2364556962025315, "percentage": 64.96, "elapsed_time": "10:04:15", "remaining_time": "5:25:57"}
800
+ {"current_steps": 800, "total_steps": 1230, "loss": 0.419, "lr": 1.3132936174930756e-05, "epoch": 3.240506329113924, "percentage": 65.04, "elapsed_time": "10:05:00", "remaining_time": "5:25:11"}
801
+ {"current_steps": 801, "total_steps": 1230, "loss": 0.4091, "lr": 1.3079655791283995e-05, "epoch": 3.2445569620253165, "percentage": 65.12, "elapsed_time": "10:05:46", "remaining_time": "5:24:26"}
802
+ {"current_steps": 802, "total_steps": 1230, "loss": 0.4073, "lr": 1.3026431143138108e-05, "epoch": 3.248607594936709, "percentage": 65.2, "elapsed_time": "10:06:31", "remaining_time": "5:23:41"}
803
+ {"current_steps": 803, "total_steps": 1230, "loss": 0.4089, "lr": 1.2973262659157114e-05, "epoch": 3.252658227848101, "percentage": 65.28, "elapsed_time": "10:07:17", "remaining_time": "5:22:55"}
804
+ {"current_steps": 804, "total_steps": 1230, "loss": 0.4412, "lr": 1.2920150767552651e-05, "epoch": 3.2567088607594936, "percentage": 65.37, "elapsed_time": "10:08:00", "remaining_time": "5:22:09"}
805
+ {"current_steps": 805, "total_steps": 1230, "loss": 0.4149, "lr": 1.2867095896080607e-05, "epoch": 3.260759493670886, "percentage": 65.45, "elapsed_time": "10:08:46", "remaining_time": "5:21:24"}
806
+ {"current_steps": 806, "total_steps": 1230, "loss": 0.4178, "lr": 1.2814098472037612e-05, "epoch": 3.2648101265822786, "percentage": 65.53, "elapsed_time": "10:09:30", "remaining_time": "5:20:38"}
807
+ {"current_steps": 807, "total_steps": 1230, "loss": 0.4148, "lr": 1.276115892225764e-05, "epoch": 3.2688607594936707, "percentage": 65.61, "elapsed_time": "10:10:16", "remaining_time": "5:19:53"}
808
+ {"current_steps": 808, "total_steps": 1230, "loss": 0.4272, "lr": 1.2708277673108555e-05, "epoch": 3.2729113924050632, "percentage": 65.69, "elapsed_time": "10:11:01", "remaining_time": "5:19:07"}
809
+ {"current_steps": 809, "total_steps": 1230, "loss": 0.421, "lr": 1.2655455150488649e-05, "epoch": 3.2769620253164558, "percentage": 65.77, "elapsed_time": "10:11:45", "remaining_time": "5:18:21"}
810
+ {"current_steps": 810, "total_steps": 1230, "loss": 0.4159, "lr": 1.2602691779823272e-05, "epoch": 3.2810126582278483, "percentage": 65.85, "elapsed_time": "10:12:28", "remaining_time": "5:17:34"}
811
+ {"current_steps": 811, "total_steps": 1230, "loss": 0.4248, "lr": 1.2549987986061355e-05, "epoch": 3.2850632911392403, "percentage": 65.93, "elapsed_time": "10:13:11", "remaining_time": "5:16:48"}
812
+ {"current_steps": 812, "total_steps": 1230, "loss": 0.4175, "lr": 1.2497344193672005e-05, "epoch": 3.289113924050633, "percentage": 66.02, "elapsed_time": "10:13:57", "remaining_time": "5:16:02"}
813
+ {"current_steps": 813, "total_steps": 1230, "loss": 0.4169, "lr": 1.2444760826641092e-05, "epoch": 3.2931645569620254, "percentage": 66.1, "elapsed_time": "10:14:42", "remaining_time": "5:15:17"}
814
+ {"current_steps": 814, "total_steps": 1230, "loss": 0.4037, "lr": 1.2392238308467817e-05, "epoch": 3.297215189873418, "percentage": 66.18, "elapsed_time": "10:15:29", "remaining_time": "5:14:32"}
815
+ {"current_steps": 815, "total_steps": 1230, "loss": 0.4323, "lr": 1.2339777062161326e-05, "epoch": 3.30126582278481, "percentage": 66.26, "elapsed_time": "10:16:11", "remaining_time": "5:13:46"}
816
+ {"current_steps": 816, "total_steps": 1230, "loss": 0.4278, "lr": 1.2287377510237293e-05, "epoch": 3.3053164556962025, "percentage": 66.34, "elapsed_time": "10:16:56", "remaining_time": "5:13:00"}
817
+ {"current_steps": 817, "total_steps": 1230, "loss": 0.4279, "lr": 1.2235040074714488e-05, "epoch": 3.309367088607595, "percentage": 66.42, "elapsed_time": "10:17:39", "remaining_time": "5:12:13"}
818
+ {"current_steps": 818, "total_steps": 1230, "loss": 0.4186, "lr": 1.2182765177111434e-05, "epoch": 3.3134177215189875, "percentage": 66.5, "elapsed_time": "10:18:24", "remaining_time": "5:11:28"}
819
+ {"current_steps": 819, "total_steps": 1230, "loss": 0.4101, "lr": 1.213055323844297e-05, "epoch": 3.3174683544303796, "percentage": 66.59, "elapsed_time": "10:19:09", "remaining_time": "5:10:42"}
820
+ {"current_steps": 820, "total_steps": 1230, "loss": 0.4179, "lr": 1.2078404679216864e-05, "epoch": 3.321518987341772, "percentage": 66.67, "elapsed_time": "10:19:55", "remaining_time": "5:09:57"}
821
+ {"current_steps": 821, "total_steps": 1230, "loss": 0.4108, "lr": 1.2026319919430458e-05, "epoch": 3.3255696202531646, "percentage": 66.75, "elapsed_time": "10:20:41", "remaining_time": "5:09:12"}
822
+ {"current_steps": 822, "total_steps": 1230, "loss": 0.4135, "lr": 1.1974299378567227e-05, "epoch": 3.329620253164557, "percentage": 66.83, "elapsed_time": "10:21:26", "remaining_time": "5:08:27"}
823
+ {"current_steps": 823, "total_steps": 1230, "loss": 0.4216, "lr": 1.1922343475593462e-05, "epoch": 3.333670886075949, "percentage": 66.91, "elapsed_time": "10:22:12", "remaining_time": "5:07:42"}
824
+ {"current_steps": 824, "total_steps": 1230, "loss": 0.4204, "lr": 1.187045262895488e-05, "epoch": 3.3377215189873417, "percentage": 66.99, "elapsed_time": "10:22:56", "remaining_time": "5:06:55"}
825
+ {"current_steps": 825, "total_steps": 1230, "loss": 0.4235, "lr": 1.1818627256573203e-05, "epoch": 3.3417721518987342, "percentage": 67.07, "elapsed_time": "10:23:42", "remaining_time": "5:06:11"}
826
+ {"current_steps": 826, "total_steps": 1230, "loss": 0.4262, "lr": 1.1766867775842864e-05, "epoch": 3.3458227848101267, "percentage": 67.15, "elapsed_time": "10:24:27", "remaining_time": "5:05:25"}
827
+ {"current_steps": 827, "total_steps": 1230, "loss": 0.4396, "lr": 1.1715174603627615e-05, "epoch": 3.349873417721519, "percentage": 67.24, "elapsed_time": "10:25:13", "remaining_time": "5:04:40"}
828
+ {"current_steps": 828, "total_steps": 1230, "loss": 0.4203, "lr": 1.1663548156257147e-05, "epoch": 3.3539240506329113, "percentage": 67.32, "elapsed_time": "10:25:57", "remaining_time": "5:03:54"}
829
+ {"current_steps": 829, "total_steps": 1230, "loss": 0.4146, "lr": 1.161198884952377e-05, "epoch": 3.357974683544304, "percentage": 67.4, "elapsed_time": "10:26:43", "remaining_time": "5:03:09"}
830
+ {"current_steps": 830, "total_steps": 1230, "loss": 0.4249, "lr": 1.1560497098679056e-05, "epoch": 3.3620253164556964, "percentage": 67.48, "elapsed_time": "10:27:27", "remaining_time": "5:02:23"}
831
+ {"current_steps": 831, "total_steps": 1230, "loss": 0.4228, "lr": 1.1509073318430479e-05, "epoch": 3.3660759493670884, "percentage": 67.56, "elapsed_time": "10:28:10", "remaining_time": "5:01:36"}
832
+ {"current_steps": 832, "total_steps": 1230, "loss": 0.4241, "lr": 1.1457717922938116e-05, "epoch": 3.370126582278481, "percentage": 67.64, "elapsed_time": "10:28:56", "remaining_time": "5:00:51"}
833
+ {"current_steps": 833, "total_steps": 1230, "loss": 0.4255, "lr": 1.1406431325811233e-05, "epoch": 3.3741772151898735, "percentage": 67.72, "elapsed_time": "10:29:42", "remaining_time": "5:00:06"}
834
+ {"current_steps": 834, "total_steps": 1230, "loss": 0.4339, "lr": 1.135521394010506e-05, "epoch": 3.378227848101266, "percentage": 67.8, "elapsed_time": "10:30:26", "remaining_time": "4:59:20"}
835
+ {"current_steps": 835, "total_steps": 1230, "loss": 0.4236, "lr": 1.1304066178317367e-05, "epoch": 3.382278481012658, "percentage": 67.89, "elapsed_time": "10:31:11", "remaining_time": "4:58:35"}
836
+ {"current_steps": 836, "total_steps": 1230, "loss": 0.4311, "lr": 1.1252988452385199e-05, "epoch": 3.3863291139240506, "percentage": 67.97, "elapsed_time": "10:31:56", "remaining_time": "4:57:49"}
837
+ {"current_steps": 837, "total_steps": 1230, "loss": 0.4161, "lr": 1.1201981173681536e-05, "epoch": 3.390379746835443, "percentage": 68.05, "elapsed_time": "10:32:40", "remaining_time": "4:57:03"}
838
+ {"current_steps": 838, "total_steps": 1230, "loss": 0.4192, "lr": 1.1151044753011991e-05, "epoch": 3.3944303797468356, "percentage": 68.13, "elapsed_time": "10:33:23", "remaining_time": "4:56:17"}
839
+ {"current_steps": 839, "total_steps": 1230, "loss": 0.4098, "lr": 1.1100179600611491e-05, "epoch": 3.3984810126582277, "percentage": 68.21, "elapsed_time": "10:34:09", "remaining_time": "4:55:32"}
840
+ {"current_steps": 840, "total_steps": 1230, "loss": 0.4119, "lr": 1.1049386126140985e-05, "epoch": 3.40253164556962, "percentage": 68.29, "elapsed_time": "10:34:53", "remaining_time": "4:54:46"}
841
+ {"current_steps": 841, "total_steps": 1230, "loss": 0.4375, "lr": 1.0998664738684128e-05, "epoch": 3.4065822784810127, "percentage": 68.37, "elapsed_time": "10:35:38", "remaining_time": "4:54:00"}
842
+ {"current_steps": 842, "total_steps": 1230, "loss": 0.4233, "lr": 1.0948015846744e-05, "epoch": 3.410632911392405, "percentage": 68.46, "elapsed_time": "10:36:24", "remaining_time": "4:53:15"}
843
+ {"current_steps": 741, "total_steps": 1230, "loss": 0.411, "lr": 1.6359475191103958e-05, "epoch": 3.012151898734177, "percentage": 60.24, "elapsed_time": "0:00:53", "remaining_time": "0:00:35"}
844
+ {"current_steps": 742, "total_steps": 1230, "loss": 0.4151, "lr": 1.6303679480270466e-05, "epoch": 3.0162025316455696, "percentage": 60.33, "elapsed_time": "0:01:38", "remaining_time": "0:01:04"}
845
+ {"current_steps": 743, "total_steps": 1230, "loss": 0.439, "lr": 1.624791353909428e-05, "epoch": 3.020253164556962, "percentage": 60.41, "elapsed_time": "0:02:22", "remaining_time": "0:01:33"}
846
+ {"current_steps": 744, "total_steps": 1230, "loss": 0.4179, "lr": 1.619217781670663e-05, "epoch": 3.0243037974683546, "percentage": 60.49, "elapsed_time": "0:03:08", "remaining_time": "0:02:02"}
847
+ {"current_steps": 745, "total_steps": 1230, "loss": 0.4219, "lr": 1.6136472761995373e-05, "epoch": 3.0283544303797467, "percentage": 60.57, "elapsed_time": "0:03:53", "remaining_time": "0:02:32"}
848
+ {"current_steps": 746, "total_steps": 1230, "loss": 0.4193, "lr": 1.608079882360134e-05, "epoch": 3.0324050632911392, "percentage": 60.65, "elapsed_time": "0:04:39", "remaining_time": "0:03:01"}
849
+ {"current_steps": 747, "total_steps": 1230, "loss": 0.4359, "lr": 1.60251564499148e-05, "epoch": 3.0364556962025318, "percentage": 60.73, "elapsed_time": "0:05:24", "remaining_time": "0:03:29"}
850
+ {"current_steps": 748, "total_steps": 1230, "loss": 0.4229, "lr": 1.596954608907176e-05, "epoch": 3.0405063291139243, "percentage": 60.81, "elapsed_time": "0:06:08", "remaining_time": "0:03:57"}
851
+ {"current_steps": 749, "total_steps": 1230, "loss": 0.4281, "lr": 1.591396818895043e-05, "epoch": 3.0445569620253163, "percentage": 60.89, "elapsed_time": "0:06:54", "remaining_time": "0:04:25"}
852
+ {"current_steps": 750, "total_steps": 1230, "loss": 0.4318, "lr": 1.585842319716759e-05, "epoch": 3.048607594936709, "percentage": 60.98, "elapsed_time": "0:07:37", "remaining_time": "0:04:52"}
853
+ {"current_steps": 751, "total_steps": 1230, "loss": 0.4178, "lr": 1.5802911561074944e-05, "epoch": 3.0526582278481014, "percentage": 61.06, "elapsed_time": "0:08:23", "remaining_time": "0:05:21"}
854
+ {"current_steps": 752, "total_steps": 1230, "loss": 0.4276, "lr": 1.5747433727755595e-05, "epoch": 3.056708860759494, "percentage": 61.14, "elapsed_time": "0:09:09", "remaining_time": "0:05:49"}
855
+ {"current_steps": 753, "total_steps": 1230, "loss": 0.4122, "lr": 1.5691990144020376e-05, "epoch": 3.060759493670886, "percentage": 61.22, "elapsed_time": "0:09:54", "remaining_time": "0:06:16"}
856
+ {"current_steps": 754, "total_steps": 1230, "loss": 0.4314, "lr": 1.5636581256404297e-05, "epoch": 3.0648101265822785, "percentage": 61.3, "elapsed_time": "0:10:39", "remaining_time": "0:06:43"}
857
+ {"current_steps": 755, "total_steps": 1230, "loss": 0.4228, "lr": 1.558120751116291e-05, "epoch": 3.068860759493671, "percentage": 61.38, "elapsed_time": "0:11:24", "remaining_time": "0:07:10"}
858
+ {"current_steps": 756, "total_steps": 1230, "loss": 0.4238, "lr": 1.552586935426876e-05, "epoch": 3.0729113924050635, "percentage": 61.46, "elapsed_time": "0:12:08", "remaining_time": "0:07:36"}
859
+ {"current_steps": 757, "total_steps": 1230, "loss": 0.4204, "lr": 1.547056723140774e-05, "epoch": 3.0769620253164556, "percentage": 61.54, "elapsed_time": "0:12:54", "remaining_time": "0:08:03"}
860
+ {"current_steps": 758, "total_steps": 1230, "loss": 0.4308, "lr": 1.5415301587975565e-05, "epoch": 3.081012658227848, "percentage": 61.63, "elapsed_time": "0:13:40", "remaining_time": "0:08:30"}
861
+ {"current_steps": 759, "total_steps": 1230, "loss": 0.4153, "lr": 1.536007286907411e-05, "epoch": 3.0850632911392406, "percentage": 61.71, "elapsed_time": "0:14:24", "remaining_time": "0:08:56"}
862
+ {"current_steps": 760, "total_steps": 1230, "loss": 0.4082, "lr": 1.5304881519507896e-05, "epoch": 3.089113924050633, "percentage": 61.79, "elapsed_time": "0:15:09", "remaining_time": "0:09:22"}
863
+ {"current_steps": 761, "total_steps": 1230, "loss": 0.4339, "lr": 1.5249727983780453e-05, "epoch": 3.093164556962025, "percentage": 61.87, "elapsed_time": "0:15:52", "remaining_time": "0:09:46"}
864
+ {"current_steps": 762, "total_steps": 1230, "loss": 0.4219, "lr": 1.5194612706090786e-05, "epoch": 3.0972151898734177, "percentage": 61.95, "elapsed_time": "0:16:36", "remaining_time": "0:10:12"}
865
+ {"current_steps": 763, "total_steps": 1230, "loss": 0.4316, "lr": 1.5139536130329771e-05, "epoch": 3.1012658227848102, "percentage": 62.03, "elapsed_time": "0:17:23", "remaining_time": "0:10:38"}
866
+ {"current_steps": 764, "total_steps": 1230, "loss": 0.4323, "lr": 1.508449870007656e-05, "epoch": 3.1053164556962027, "percentage": 62.11, "elapsed_time": "0:18:09", "remaining_time": "0:11:04"}
867
+ {"current_steps": 765, "total_steps": 1230, "loss": 0.4155, "lr": 1.5029500858595056e-05, "epoch": 3.109367088607595, "percentage": 62.2, "elapsed_time": "0:18:56", "remaining_time": "0:11:30"}
868
+ {"current_steps": 766, "total_steps": 1230, "loss": 0.4136, "lr": 1.4974543048830328e-05, "epoch": 3.1134177215189873, "percentage": 62.28, "elapsed_time": "0:19:40", "remaining_time": "0:11:54"}
869
+ {"current_steps": 767, "total_steps": 1230, "loss": 0.4244, "lr": 1.4919625713405e-05, "epoch": 3.11746835443038, "percentage": 62.36, "elapsed_time": "0:20:26", "remaining_time": "0:12:20"}
870
+ {"current_steps": 768, "total_steps": 1230, "loss": 0.4185, "lr": 1.4864749294615756e-05, "epoch": 3.1215189873417724, "percentage": 62.44, "elapsed_time": "0:21:09", "remaining_time": "0:12:43"}
871
+ {"current_steps": 769, "total_steps": 1230, "loss": 0.4176, "lr": 1.4809914234429716e-05, "epoch": 3.1255696202531644, "percentage": 62.52, "elapsed_time": "0:21:55", "remaining_time": "0:13:08"}
872
+ {"current_steps": 770, "total_steps": 1230, "loss": 0.4438, "lr": 1.4755120974480923e-05, "epoch": 3.129620253164557, "percentage": 62.6, "elapsed_time": "0:22:42", "remaining_time": "0:13:33"}
873
+ {"current_steps": 771, "total_steps": 1230, "loss": 0.4119, "lr": 1.4700369956066771e-05, "epoch": 3.1336708860759495, "percentage": 62.68, "elapsed_time": "0:23:28", "remaining_time": "0:13:58"}
874
+ {"current_steps": 772, "total_steps": 1230, "loss": 0.4157, "lr": 1.4645661620144413e-05, "epoch": 3.137721518987342, "percentage": 62.76, "elapsed_time": "0:24:12", "remaining_time": "0:14:21"}
875
+ {"current_steps": 773, "total_steps": 1230, "loss": 0.4299, "lr": 1.4590996407327284e-05, "epoch": 3.141772151898734, "percentage": 62.85, "elapsed_time": "0:24:56", "remaining_time": "0:14:44"}
876
+ {"current_steps": 774, "total_steps": 1230, "loss": 0.4325, "lr": 1.4536374757881487e-05, "epoch": 3.1458227848101266, "percentage": 62.93, "elapsed_time": "0:25:41", "remaining_time": "0:15:08"}
877
+ {"current_steps": 775, "total_steps": 1230, "loss": 0.4318, "lr": 1.4481797111722271e-05, "epoch": 3.149873417721519, "percentage": 63.01, "elapsed_time": "0:26:28", "remaining_time": "0:15:32"}
878
+ {"current_steps": 776, "total_steps": 1230, "loss": 0.4404, "lr": 1.4427263908410507e-05, "epoch": 3.1539240506329116, "percentage": 63.09, "elapsed_time": "0:27:14", "remaining_time": "0:15:56"}
879
+ {"current_steps": 777, "total_steps": 1230, "loss": 0.4297, "lr": 1.4372775587149108e-05, "epoch": 3.1579746835443037, "percentage": 63.17, "elapsed_time": "0:27:56", "remaining_time": "0:16:17"}
880
+ {"current_steps": 778, "total_steps": 1230, "loss": 0.4309, "lr": 1.4318332586779522e-05, "epoch": 3.162025316455696, "percentage": 63.25, "elapsed_time": "0:28:41", "remaining_time": "0:16:40"}
881
+ {"current_steps": 779, "total_steps": 1230, "loss": 0.4232, "lr": 1.4263935345778202e-05, "epoch": 3.1660759493670887, "percentage": 63.33, "elapsed_time": "0:29:27", "remaining_time": "0:17:03"}
882
+ {"current_steps": 780, "total_steps": 1230, "loss": 0.4267, "lr": 1.420958430225303e-05, "epoch": 3.170126582278481, "percentage": 63.41, "elapsed_time": "0:30:11", "remaining_time": "0:17:25"}
883
+ {"current_steps": 781, "total_steps": 1230, "loss": 0.4181, "lr": 1.415527989393985e-05, "epoch": 3.1741772151898733, "percentage": 63.5, "elapsed_time": "0:30:57", "remaining_time": "0:17:47"}
884
+ {"current_steps": 782, "total_steps": 1230, "loss": 0.4105, "lr": 1.410102255819891e-05, "epoch": 3.178227848101266, "percentage": 63.58, "elapsed_time": "0:31:43", "remaining_time": "0:18:10"}
885
+ {"current_steps": 783, "total_steps": 1230, "loss": 0.4367, "lr": 1.404681273201131e-05, "epoch": 3.1822784810126583, "percentage": 63.66, "elapsed_time": "0:32:28", "remaining_time": "0:18:32"}
886
+ {"current_steps": 784, "total_steps": 1230, "loss": 0.4099, "lr": 1.399265085197556e-05, "epoch": 3.186329113924051, "percentage": 63.74, "elapsed_time": "0:33:13", "remaining_time": "0:18:54"}
887
+ {"current_steps": 785, "total_steps": 1230, "loss": 0.4299, "lr": 1.393853735430398e-05, "epoch": 3.190379746835443, "percentage": 63.82, "elapsed_time": "0:33:58", "remaining_time": "0:19:15"}
888
+ {"current_steps": 786, "total_steps": 1230, "loss": 0.4205, "lr": 1.3884472674819246e-05, "epoch": 3.1944303797468354, "percentage": 63.9, "elapsed_time": "0:34:42", "remaining_time": "0:19:36"}
889
+ {"current_steps": 787, "total_steps": 1230, "loss": 0.4222, "lr": 1.3830457248950864e-05, "epoch": 3.198481012658228, "percentage": 63.98, "elapsed_time": "0:35:27", "remaining_time": "0:19:57"}
890
+ {"current_steps": 788, "total_steps": 1230, "loss": 0.4273, "lr": 1.377649151173163e-05, "epoch": 3.2025316455696204, "percentage": 64.07, "elapsed_time": "0:36:11", "remaining_time": "0:20:17"}
891
+ {"current_steps": 789, "total_steps": 1230, "loss": 0.4271, "lr": 1.3722575897794181e-05, "epoch": 3.2065822784810125, "percentage": 64.15, "elapsed_time": "0:36:56", "remaining_time": "0:20:38"}
892
+ {"current_steps": 790, "total_steps": 1230, "loss": 0.4134, "lr": 1.3668710841367472e-05, "epoch": 3.210632911392405, "percentage": 64.23, "elapsed_time": "0:37:40", "remaining_time": "0:20:58"}
893
+ {"current_steps": 791, "total_steps": 1230, "loss": 0.4171, "lr": 1.361489677627324e-05, "epoch": 3.2146835443037975, "percentage": 64.31, "elapsed_time": "0:38:24", "remaining_time": "0:21:18"}
894
+ {"current_steps": 792, "total_steps": 1230, "loss": 0.4098, "lr": 1.3561134135922585e-05, "epoch": 3.21873417721519, "percentage": 64.39, "elapsed_time": "0:39:10", "remaining_time": "0:21:39"}
895
+ {"current_steps": 793, "total_steps": 1230, "loss": 0.4204, "lr": 1.350742335331241e-05, "epoch": 3.222784810126582, "percentage": 64.47, "elapsed_time": "0:39:54", "remaining_time": "0:21:59"}
896
+ {"current_steps": 794, "total_steps": 1230, "loss": 0.4184, "lr": 1.345376486102198e-05, "epoch": 3.2268354430379746, "percentage": 64.55, "elapsed_time": "0:40:39", "remaining_time": "0:22:19"}
897
+ {"current_steps": 795, "total_steps": 1230, "loss": 0.4041, "lr": 1.3400159091209414e-05, "epoch": 3.230886075949367, "percentage": 64.63, "elapsed_time": "0:41:19", "remaining_time": "0:22:36"}
898
+ {"current_steps": 796, "total_steps": 1230, "loss": 0.4282, "lr": 1.3346606475608216e-05, "epoch": 3.2349367088607597, "percentage": 64.72, "elapsed_time": "0:42:05", "remaining_time": "0:22:56"}
899
+ {"current_steps": 797, "total_steps": 1230, "loss": 0.4171, "lr": 1.3293107445523781e-05, "epoch": 3.2389873417721518, "percentage": 64.8, "elapsed_time": "0:42:50", "remaining_time": "0:23:16"}
900
+ {"current_steps": 798, "total_steps": 1230, "loss": 0.4175, "lr": 1.3239662431829949e-05, "epoch": 3.2430379746835443, "percentage": 64.88, "elapsed_time": "0:43:35", "remaining_time": "0:23:35"}
901
+ {"current_steps": 799, "total_steps": 1230, "loss": 0.41, "lr": 1.3186271864965509e-05, "epoch": 3.247088607594937, "percentage": 64.96, "elapsed_time": "0:44:21", "remaining_time": "0:23:55"}
902
+ {"current_steps": 800, "total_steps": 1230, "loss": 0.4071, "lr": 1.3132936174930756e-05, "epoch": 3.2511392405063293, "percentage": 65.04, "elapsed_time": "0:45:07", "remaining_time": "0:24:15"}
903
+ {"current_steps": 801, "total_steps": 1230, "loss": 0.4299, "lr": 1.3079655791283995e-05, "epoch": 3.2551898734177214, "percentage": 65.12, "elapsed_time": "0:45:52", "remaining_time": "0:24:34"}
904
+ {"current_steps": 802, "total_steps": 1230, "loss": 0.4191, "lr": 1.3026431143138108e-05, "epoch": 3.259240506329114, "percentage": 65.2, "elapsed_time": "0:46:36", "remaining_time": "0:24:52"}
905
+ {"current_steps": 803, "total_steps": 1230, "loss": 0.4277, "lr": 1.2973262659157114e-05, "epoch": 3.2632911392405064, "percentage": 65.28, "elapsed_time": "0:47:22", "remaining_time": "0:25:11"}
906
+ {"current_steps": 804, "total_steps": 1230, "loss": 0.4069, "lr": 1.2920150767552651e-05, "epoch": 3.267341772151899, "percentage": 65.37, "elapsed_time": "0:48:06", "remaining_time": "0:25:29"}
907
+ {"current_steps": 805, "total_steps": 1230, "loss": 0.4218, "lr": 1.2867095896080607e-05, "epoch": 3.271392405063291, "percentage": 65.45, "elapsed_time": "0:48:51", "remaining_time": "0:25:47"}
908
+ {"current_steps": 806, "total_steps": 1230, "loss": 0.4216, "lr": 1.2814098472037612e-05, "epoch": 3.2754430379746835, "percentage": 65.53, "elapsed_time": "0:49:35", "remaining_time": "0:26:05"}
909
+ {"current_steps": 807, "total_steps": 1230, "loss": 0.426, "lr": 1.276115892225764e-05, "epoch": 3.279493670886076, "percentage": 65.61, "elapsed_time": "0:50:19", "remaining_time": "0:26:22"}
910
+ {"current_steps": 808, "total_steps": 1230, "loss": 0.4162, "lr": 1.2708277673108555e-05, "epoch": 3.2835443037974685, "percentage": 65.69, "elapsed_time": "0:51:03", "remaining_time": "0:26:39"}
911
+ {"current_steps": 809, "total_steps": 1230, "loss": 0.411, "lr": 1.2655455150488649e-05, "epoch": 3.2875949367088606, "percentage": 65.77, "elapsed_time": "0:51:47", "remaining_time": "0:26:57"}
912
+ {"current_steps": 810, "total_steps": 1230, "loss": 0.4203, "lr": 1.2602691779823272e-05, "epoch": 3.291645569620253, "percentage": 65.85, "elapsed_time": "0:52:33", "remaining_time": "0:27:14"}
913
+ {"current_steps": 811, "total_steps": 1230, "loss": 0.4117, "lr": 1.2549987986061355e-05, "epoch": 3.2956962025316456, "percentage": 65.93, "elapsed_time": "0:53:19", "remaining_time": "0:27:32"}
914
+ {"current_steps": 812, "total_steps": 1230, "loss": 0.4215, "lr": 1.2497344193672005e-05, "epoch": 3.299746835443038, "percentage": 66.02, "elapsed_time": "0:54:02", "remaining_time": "0:27:49"}
915
+ {"current_steps": 813, "total_steps": 1230, "loss": 0.4321, "lr": 1.2444760826641092e-05, "epoch": 3.3037974683544302, "percentage": 66.1, "elapsed_time": "0:54:47", "remaining_time": "0:28:06"}
916
+ {"current_steps": 814, "total_steps": 1230, "loss": 0.4247, "lr": 1.2392238308467817e-05, "epoch": 3.3078481012658227, "percentage": 66.18, "elapsed_time": "0:55:33", "remaining_time": "0:28:23"}
917
+ {"current_steps": 815, "total_steps": 1230, "loss": 0.4229, "lr": 1.2339777062161326e-05, "epoch": 3.3118987341772153, "percentage": 66.26, "elapsed_time": "0:56:16", "remaining_time": "0:28:39"}
918
+ {"current_steps": 816, "total_steps": 1230, "loss": 0.4215, "lr": 1.2287377510237293e-05, "epoch": 3.3159493670886078, "percentage": 66.34, "elapsed_time": "0:57:02", "remaining_time": "0:28:56"}
919
+ {"current_steps": 817, "total_steps": 1230, "loss": 0.4053, "lr": 1.2235040074714488e-05, "epoch": 3.32, "percentage": 66.42, "elapsed_time": "0:57:47", "remaining_time": "0:29:12"}
920
+ {"current_steps": 818, "total_steps": 1230, "loss": 0.4176, "lr": 1.2182765177111434e-05, "epoch": 3.3240506329113924, "percentage": 66.5, "elapsed_time": "0:58:34", "remaining_time": "0:29:30"}
921
+ {"current_steps": 819, "total_steps": 1230, "loss": 0.4028, "lr": 1.213055323844297e-05, "epoch": 3.328101265822785, "percentage": 66.59, "elapsed_time": "0:59:20", "remaining_time": "0:29:46"}
922
+ {"current_steps": 820, "total_steps": 1230, "loss": 0.4309, "lr": 1.2078404679216864e-05, "epoch": 3.3321518987341774, "percentage": 66.67, "elapsed_time": "1:00:06", "remaining_time": "0:30:03"}
923
+ {"current_steps": 821, "total_steps": 1230, "loss": 0.4082, "lr": 1.2026319919430458e-05, "epoch": 3.3362025316455695, "percentage": 66.75, "elapsed_time": "1:00:49", "remaining_time": "0:30:18"}
924
+ {"current_steps": 822, "total_steps": 1230, "loss": 0.4325, "lr": 1.1974299378567227e-05, "epoch": 3.340253164556962, "percentage": 66.83, "elapsed_time": "1:01:36", "remaining_time": "0:30:34"}
925
+ {"current_steps": 823, "total_steps": 1230, "loss": 0.4313, "lr": 1.1922343475593462e-05, "epoch": 3.3443037974683545, "percentage": 66.91, "elapsed_time": "1:02:22", "remaining_time": "0:30:50"}
926
+ {"current_steps": 824, "total_steps": 1230, "loss": 0.426, "lr": 1.187045262895488e-05, "epoch": 3.348354430379747, "percentage": 66.99, "elapsed_time": "1:03:07", "remaining_time": "0:31:06"}
927
+ {"current_steps": 825, "total_steps": 1230, "loss": 0.4298, "lr": 1.1818627256573203e-05, "epoch": 3.352405063291139, "percentage": 67.07, "elapsed_time": "1:03:52", "remaining_time": "0:31:21"}
928
+ {"current_steps": 826, "total_steps": 1230, "loss": 0.4157, "lr": 1.1766867775842864e-05, "epoch": 3.3564556962025316, "percentage": 67.15, "elapsed_time": "1:04:38", "remaining_time": "0:31:37"}
929
+ {"current_steps": 827, "total_steps": 1230, "loss": 0.4228, "lr": 1.1715174603627615e-05, "epoch": 3.360506329113924, "percentage": 67.24, "elapsed_time": "1:05:23", "remaining_time": "0:31:52"}
930
+ {"current_steps": 828, "total_steps": 1230, "loss": 0.4241, "lr": 1.1663548156257147e-05, "epoch": 3.3645569620253166, "percentage": 67.32, "elapsed_time": "1:06:06", "remaining_time": "0:32:05"}
931
+ {"current_steps": 829, "total_steps": 1230, "loss": 0.414, "lr": 1.161198884952377e-05, "epoch": 3.3686075949367087, "percentage": 67.4, "elapsed_time": "1:06:51", "remaining_time": "0:32:20"}
932
+ {"current_steps": 830, "total_steps": 1230, "loss": 0.4362, "lr": 1.1560497098679056e-05, "epoch": 3.372658227848101, "percentage": 67.48, "elapsed_time": "1:07:38", "remaining_time": "0:32:35"}
933
+ {"current_steps": 831, "total_steps": 1230, "loss": 0.423, "lr": 1.1509073318430479e-05, "epoch": 3.3767088607594937, "percentage": 67.56, "elapsed_time": "1:08:23", "remaining_time": "0:32:50"}
934
+ {"current_steps": 832, "total_steps": 1230, "loss": 0.4238, "lr": 1.1457717922938116e-05, "epoch": 3.3807594936708862, "percentage": 67.64, "elapsed_time": "1:09:08", "remaining_time": "0:33:04"}
935
+ {"current_steps": 833, "total_steps": 1230, "loss": 0.436, "lr": 1.1406431325811233e-05, "epoch": 3.3848101265822783, "percentage": 67.72, "elapsed_time": "1:09:53", "remaining_time": "0:33:18"}
936
+ {"current_steps": 834, "total_steps": 1230, "loss": 0.4196, "lr": 1.135521394010506e-05, "epoch": 3.388860759493671, "percentage": 67.8, "elapsed_time": "1:10:38", "remaining_time": "0:33:32"}
937
+ {"current_steps": 835, "total_steps": 1230, "loss": 0.419, "lr": 1.1304066178317367e-05, "epoch": 3.3929113924050633, "percentage": 67.89, "elapsed_time": "1:11:22", "remaining_time": "0:33:45"}
938
+ {"current_steps": 836, "total_steps": 1230, "loss": 0.4072, "lr": 1.1252988452385199e-05, "epoch": 3.396962025316456, "percentage": 67.97, "elapsed_time": "1:12:07", "remaining_time": "0:33:59"}
939
+ {"current_steps": 837, "total_steps": 1230, "loss": 0.4201, "lr": 1.1201981173681536e-05, "epoch": 3.401012658227848, "percentage": 68.05, "elapsed_time": "1:12:51", "remaining_time": "0:34:12"}
940
+ {"current_steps": 838, "total_steps": 1230, "loss": 0.4176, "lr": 1.1151044753011991e-05, "epoch": 3.4050632911392404, "percentage": 68.13, "elapsed_time": "1:13:36", "remaining_time": "0:34:26"}
941
+ {"current_steps": 839, "total_steps": 1230, "loss": 0.4374, "lr": 1.1100179600611491e-05, "epoch": 3.409113924050633, "percentage": 68.21, "elapsed_time": "1:14:22", "remaining_time": "0:34:39"}
942
+ {"current_steps": 840, "total_steps": 1230, "loss": 0.4205, "lr": 1.1049386126140985e-05, "epoch": 3.4131645569620255, "percentage": 68.29, "elapsed_time": "1:15:08", "remaining_time": "0:34:53"}
943
+ {"current_steps": 841, "total_steps": 1230, "loss": 0.4113, "lr": 1.0998664738684128e-05, "epoch": 3.4172151898734175, "percentage": 68.37, "elapsed_time": "1:15:54", "remaining_time": "0:35:06"}
944
+ {"current_steps": 842, "total_steps": 1230, "loss": 0.4179, "lr": 1.0948015846744e-05, "epoch": 3.42126582278481, "percentage": 68.46, "elapsed_time": "1:16:38", "remaining_time": "0:35:18"}
945
+ {"current_steps": 843, "total_steps": 1230, "loss": 0.4348, "lr": 1.0897439858239832e-05, "epoch": 3.4253164556962026, "percentage": 68.54, "elapsed_time": "1:17:22", "remaining_time": "0:35:31"}
946
+ {"current_steps": 844, "total_steps": 1230, "loss": 0.4264, "lr": 1.0846937180503652e-05, "epoch": 3.429367088607595, "percentage": 68.62, "elapsed_time": "1:18:08", "remaining_time": "0:35:44"}
947
+ {"current_steps": 845, "total_steps": 1230, "loss": 0.4201, "lr": 1.0796508220277117e-05, "epoch": 3.433417721518987, "percentage": 68.7, "elapsed_time": "1:18:51", "remaining_time": "0:35:55"}
948
+ {"current_steps": 846, "total_steps": 1230, "loss": 0.4204, "lr": 1.0746153383708107e-05, "epoch": 3.4374683544303797, "percentage": 68.78, "elapsed_time": "1:19:38", "remaining_time": "0:36:08"}
949
+ {"current_steps": 847, "total_steps": 1230, "loss": 0.4302, "lr": 1.0695873076347579e-05, "epoch": 3.441518987341772, "percentage": 68.86, "elapsed_time": "1:20:22", "remaining_time": "0:36:20"}
950
+ {"current_steps": 848, "total_steps": 1230, "loss": 0.4058, "lr": 1.0645667703146205e-05, "epoch": 3.4455696202531647, "percentage": 68.94, "elapsed_time": "1:21:07", "remaining_time": "0:36:32"}
951
+ {"current_steps": 849, "total_steps": 1230, "loss": 0.4178, "lr": 1.0595537668451161e-05, "epoch": 3.449620253164557, "percentage": 69.02, "elapsed_time": "1:21:51", "remaining_time": "0:36:44"}
952
+ {"current_steps": 850, "total_steps": 1230, "loss": 0.4186, "lr": 1.0545483376002854e-05, "epoch": 3.4536708860759493, "percentage": 69.11, "elapsed_time": "1:22:34", "remaining_time": "0:36:55"}
953
+ {"current_steps": 851, "total_steps": 1230, "loss": 0.4117, "lr": 1.0495505228931676e-05, "epoch": 3.457721518987342, "percentage": 69.19, "elapsed_time": "1:23:20", "remaining_time": "0:37:06"}
954
+ {"current_steps": 852, "total_steps": 1230, "loss": 0.4163, "lr": 1.044560362975474e-05, "epoch": 3.4617721518987343, "percentage": 69.27, "elapsed_time": "1:24:01", "remaining_time": "0:37:16"}
955
+ {"current_steps": 853, "total_steps": 1230, "loss": 0.4229, "lr": 1.0395778980372695e-05, "epoch": 3.4658227848101264, "percentage": 69.35, "elapsed_time": "1:24:44", "remaining_time": "0:37:27"}
956
+ {"current_steps": 854, "total_steps": 1230, "loss": 0.4153, "lr": 1.0346031682066381e-05, "epoch": 3.469873417721519, "percentage": 69.43, "elapsed_time": "1:25:30", "remaining_time": "0:37:39"}
957
+ {"current_steps": 855, "total_steps": 1230, "loss": 0.419, "lr": 1.0296362135493724e-05, "epoch": 3.4739240506329114, "percentage": 69.51, "elapsed_time": "1:26:14", "remaining_time": "0:37:49"}
958
+ {"current_steps": 856, "total_steps": 1230, "loss": 0.4367, "lr": 1.0246770740686422e-05, "epoch": 3.477974683544304, "percentage": 69.59, "elapsed_time": "1:26:58", "remaining_time": "0:38:00"}
959
+ {"current_steps": 857, "total_steps": 1230, "loss": 0.4263, "lr": 1.0197257897046743e-05, "epoch": 3.482025316455696, "percentage": 69.67, "elapsed_time": "1:27:40", "remaining_time": "0:38:09"}
960
+ {"current_steps": 858, "total_steps": 1230, "loss": 0.4232, "lr": 1.014782400334433e-05, "epoch": 3.4860759493670885, "percentage": 69.76, "elapsed_time": "1:28:27", "remaining_time": "0:38:20"}
961
+ {"current_steps": 859, "total_steps": 1230, "loss": 0.4381, "lr": 1.009846945771296e-05, "epoch": 3.490126582278481, "percentage": 69.84, "elapsed_time": "1:29:14", "remaining_time": "0:38:32"}
962
+ {"current_steps": 860, "total_steps": 1230, "loss": 0.4173, "lr": 1.0049194657647363e-05, "epoch": 3.4941772151898736, "percentage": 69.92, "elapsed_time": "1:29:57", "remaining_time": "0:38:42"}
963
+ {"current_steps": 861, "total_steps": 1230, "loss": 0.419, "lr": 1.0000000000000006e-05, "epoch": 3.4982278481012656, "percentage": 70.0, "elapsed_time": "1:30:42", "remaining_time": "0:38:52"}
964
+ {"current_steps": 862, "total_steps": 1230, "loss": 0.4255, "lr": 9.950885880977891e-06, "epoch": 3.502278481012658, "percentage": 70.08, "elapsed_time": "1:31:28", "remaining_time": "0:39:03"}
965
+ {"current_steps": 863, "total_steps": 1230, "loss": 0.41, "lr": 9.901852696139382e-06, "epoch": 3.5063291139240507, "percentage": 70.16, "elapsed_time": "1:32:12", "remaining_time": "0:39:12"}
966
+ {"current_steps": 864, "total_steps": 1230, "loss": 0.427, "lr": 9.852900840391027e-06, "epoch": 3.510379746835443, "percentage": 70.24, "elapsed_time": "1:32:57", "remaining_time": "0:39:22"}
967
+ {"current_steps": 865, "total_steps": 1230, "loss": 0.4282, "lr": 9.804030707984313e-06, "epoch": 3.5144303797468357, "percentage": 70.33, "elapsed_time": "1:33:43", "remaining_time": "0:39:32"}
968
+ {"current_steps": 866, "total_steps": 1230, "loss": 0.4348, "lr": 9.755242692512599e-06, "epoch": 3.5184810126582278, "percentage": 70.41, "elapsed_time": "1:34:27", "remaining_time": "0:39:42"}
969
+ {"current_steps": 867, "total_steps": 1230, "loss": 0.4261, "lr": 9.70653718690782e-06, "epoch": 3.5225316455696203, "percentage": 70.49, "elapsed_time": "1:35:10", "remaining_time": "0:39:50"}
970
+ {"current_steps": 868, "total_steps": 1230, "loss": 0.4129, "lr": 9.657914583437454e-06, "epoch": 3.526582278481013, "percentage": 70.57, "elapsed_time": "1:35:52", "remaining_time": "0:39:59"}
971
+ {"current_steps": 869, "total_steps": 1230, "loss": 0.4217, "lr": 9.609375273701246e-06, "epoch": 3.530632911392405, "percentage": 70.65, "elapsed_time": "1:36:39", "remaining_time": "0:40:09"}
972
+ {"current_steps": 870, "total_steps": 1230, "loss": 0.4156, "lr": 9.560919648628133e-06, "epoch": 3.5346835443037974, "percentage": 70.73, "elapsed_time": "1:37:21", "remaining_time": "0:40:17"}
973
+ {"current_steps": 871, "total_steps": 1230, "loss": 0.433, "lr": 9.512548098473047e-06, "epoch": 3.53873417721519, "percentage": 70.81, "elapsed_time": "1:38:08", "remaining_time": "0:40:26"}
974
+ {"current_steps": 872, "total_steps": 1230, "loss": 0.4221, "lr": 9.464261012813825e-06, "epoch": 3.5427848101265824, "percentage": 70.89, "elapsed_time": "1:38:52", "remaining_time": "0:40:35"}
975
+ {"current_steps": 873, "total_steps": 1230, "loss": 0.4257, "lr": 9.416058780547987e-06, "epoch": 3.546835443037975, "percentage": 70.98, "elapsed_time": "1:39:38", "remaining_time": "0:40:44"}
976
+ {"current_steps": 874, "total_steps": 1230, "loss": 0.4184, "lr": 9.367941789889714e-06, "epoch": 3.550886075949367, "percentage": 71.06, "elapsed_time": "1:40:24", "remaining_time": "0:40:53"}
977
+ {"current_steps": 875, "total_steps": 1230, "loss": 0.4274, "lr": 9.319910428366607e-06, "epoch": 3.5549367088607595, "percentage": 71.14, "elapsed_time": "1:41:08", "remaining_time": "0:41:02"}
978
+ {"current_steps": 876, "total_steps": 1230, "loss": 0.4312, "lr": 9.271965082816667e-06, "epoch": 3.558987341772152, "percentage": 71.22, "elapsed_time": "1:41:51", "remaining_time": "0:41:09"}
979
+ {"current_steps": 877, "total_steps": 1230, "loss": 0.4136, "lr": 9.224106139385111e-06, "epoch": 3.563037974683544, "percentage": 71.3, "elapsed_time": "1:42:34", "remaining_time": "0:41:17"}
980
+ {"current_steps": 878, "total_steps": 1230, "loss": 0.429, "lr": 9.176333983521291e-06, "epoch": 3.5670886075949366, "percentage": 71.38, "elapsed_time": "1:43:19", "remaining_time": "0:41:25"}
981
+ {"current_steps": 879, "total_steps": 1230, "loss": 0.4178, "lr": 9.12864899997558e-06, "epoch": 3.571139240506329, "percentage": 71.46, "elapsed_time": "1:44:03", "remaining_time": "0:41:33"}
982
+ {"current_steps": 880, "total_steps": 1230, "loss": 0.4173, "lr": 9.08105157279628e-06, "epoch": 3.5751898734177217, "percentage": 71.54, "elapsed_time": "1:44:47", "remaining_time": "0:41:40"}
983
+ {"current_steps": 881, "total_steps": 1230, "loss": 0.413, "lr": 9.03354208532653e-06, "epoch": 3.579240506329114, "percentage": 71.63, "elapsed_time": "1:45:30", "remaining_time": "0:41:47"}
984
+ {"current_steps": 882, "total_steps": 1230, "loss": 0.4315, "lr": 8.986120920201205e-06, "epoch": 3.5832911392405062, "percentage": 71.71, "elapsed_time": "1:46:13", "remaining_time": "0:41:54"}
985
+ {"current_steps": 883, "total_steps": 1230, "loss": 0.4132, "lr": 8.938788459343852e-06, "epoch": 3.5873417721518988, "percentage": 71.79, "elapsed_time": "1:46:59", "remaining_time": "0:42:02"}
986
+ {"current_steps": 884, "total_steps": 1230, "loss": 0.4135, "lr": 8.8915450839636e-06, "epoch": 3.5913924050632913, "percentage": 71.87, "elapsed_time": "1:47:44", "remaining_time": "0:42:10"}
987
+ {"current_steps": 885, "total_steps": 1230, "loss": 0.4258, "lr": 8.844391174552116e-06, "epoch": 3.5954430379746833, "percentage": 71.95, "elapsed_time": "1:48:26", "remaining_time": "0:42:16"}
988
+ {"current_steps": 886, "total_steps": 1230, "loss": 0.4034, "lr": 8.797327110880479e-06, "epoch": 3.599493670886076, "percentage": 72.03, "elapsed_time": "1:49:10", "remaining_time": "0:42:23"}
989
+ {"current_steps": 887, "total_steps": 1230, "loss": 0.4289, "lr": 8.750353271996206e-06, "epoch": 3.6035443037974684, "percentage": 72.11, "elapsed_time": "1:49:56", "remaining_time": "0:42:30"}
990
+ {"current_steps": 888, "total_steps": 1230, "loss": 0.4232, "lr": 8.703470036220132e-06, "epoch": 3.607594936708861, "percentage": 72.2, "elapsed_time": "1:50:41", "remaining_time": "0:42:38"}
991
+ {"current_steps": 889, "total_steps": 1230, "loss": 0.4007, "lr": 8.656677781143394e-06, "epoch": 3.6116455696202534, "percentage": 72.28, "elapsed_time": "1:51:29", "remaining_time": "0:42:45"}
992
+ {"current_steps": 890, "total_steps": 1230, "loss": 0.4126, "lr": 8.609976883624377e-06, "epoch": 3.6156962025316455, "percentage": 72.36, "elapsed_time": "1:52:12", "remaining_time": "0:42:52"}
993
+ {"current_steps": 891, "total_steps": 1230, "loss": 0.4331, "lr": 8.563367719785698e-06, "epoch": 3.619746835443038, "percentage": 72.44, "elapsed_time": "1:52:57", "remaining_time": "0:42:58"}
994
+ {"current_steps": 892, "total_steps": 1230, "loss": 0.4145, "lr": 8.516850665011138e-06, "epoch": 3.6237974683544305, "percentage": 72.52, "elapsed_time": "1:53:43", "remaining_time": "0:43:05"}
995
+ {"current_steps": 893, "total_steps": 1230, "loss": 0.4179, "lr": 8.47042609394269e-06, "epoch": 3.6278481012658226, "percentage": 72.6, "elapsed_time": "1:54:28", "remaining_time": "0:43:12"}
996
+ {"current_steps": 894, "total_steps": 1230, "loss": 0.4235, "lr": 8.424094380477432e-06, "epoch": 3.631898734177215, "percentage": 72.68, "elapsed_time": "1:55:12", "remaining_time": "0:43:18"}
997
+ {"current_steps": 895, "total_steps": 1230, "loss": 0.426, "lr": 8.37785589776465e-06, "epoch": 3.6359493670886076, "percentage": 72.76, "elapsed_time": "1:55:58", "remaining_time": "0:43:24"}
998
+ {"current_steps": 896, "total_steps": 1230, "loss": 0.4192, "lr": 8.331711018202694e-06, "epoch": 3.64, "percentage": 72.85, "elapsed_time": "1:56:44", "remaining_time": "0:43:31"}
999
+ {"current_steps": 897, "total_steps": 1230, "loss": 0.4348, "lr": 8.285660113436104e-06, "epoch": 3.6440506329113926, "percentage": 72.93, "elapsed_time": "1:57:29", "remaining_time": "0:43:37"}
1000
+ {"current_steps": 898, "total_steps": 1230, "loss": 0.432, "lr": 8.239703554352527e-06, "epoch": 3.6481012658227847, "percentage": 73.01, "elapsed_time": "1:58:15", "remaining_time": "0:43:43"}
1001
+ {"current_steps": 899, "total_steps": 1230, "loss": 0.4188, "lr": 8.193841711079775e-06, "epoch": 3.6521518987341772, "percentage": 73.09, "elapsed_time": "1:59:01", "remaining_time": "0:43:49"}
1002
+ {"current_steps": 900, "total_steps": 1230, "loss": 0.4227, "lr": 8.148074952982828e-06, "epoch": 3.6562025316455697, "percentage": 73.17, "elapsed_time": "1:59:47", "remaining_time": "0:43:55"}
1003
+ {"current_steps": 901, "total_steps": 1230, "loss": 0.4232, "lr": 8.102403648660859e-06, "epoch": 3.660253164556962, "percentage": 73.25, "elapsed_time": "2:00:31", "remaining_time": "0:44:00"}
1004
+ {"current_steps": 902, "total_steps": 1230, "loss": 0.4201, "lr": 8.056828165944282e-06, "epoch": 3.6643037974683543, "percentage": 73.33, "elapsed_time": "2:01:16", "remaining_time": "0:44:05"}
1005
+ {"current_steps": 903, "total_steps": 1230, "loss": 0.4282, "lr": 8.011348871891762e-06, "epoch": 3.668354430379747, "percentage": 73.41, "elapsed_time": "2:02:02", "remaining_time": "0:44:11"}
1006
+ {"current_steps": 904, "total_steps": 1230, "loss": 0.4918, "lr": 7.965966132787287e-06, "epoch": 3.6724050632911394, "percentage": 73.5, "elapsed_time": "2:02:49", "remaining_time": "0:44:17"}
1007
+ {"current_steps": 905, "total_steps": 1230, "loss": 0.408, "lr": 7.920680314137189e-06, "epoch": 3.676455696202532, "percentage": 73.58, "elapsed_time": "2:03:36", "remaining_time": "0:44:23"}
1008
+ {"current_steps": 906, "total_steps": 1230, "loss": 0.4252, "lr": 7.875491780667246e-06, "epoch": 3.680506329113924, "percentage": 73.66, "elapsed_time": "2:04:22", "remaining_time": "0:44:28"}
1009
+ {"current_steps": 907, "total_steps": 1230, "loss": 0.4327, "lr": 7.830400896319667e-06, "epoch": 3.6845569620253165, "percentage": 73.74, "elapsed_time": "2:05:05", "remaining_time": "0:44:32"}
1010
+ {"current_steps": 908, "total_steps": 1230, "loss": 0.4182, "lr": 7.785408024250259e-06, "epoch": 3.688607594936709, "percentage": 73.82, "elapsed_time": "2:05:51", "remaining_time": "0:44:38"}
1011
+ {"current_steps": 909, "total_steps": 1230, "loss": 0.4189, "lr": 7.74051352682542e-06, "epoch": 3.692658227848101, "percentage": 73.9, "elapsed_time": "2:06:37", "remaining_time": "0:44:42"}
1012
+ {"current_steps": 910, "total_steps": 1230, "loss": 0.4137, "lr": 7.695717765619257e-06, "epoch": 3.6967088607594936, "percentage": 73.98, "elapsed_time": "2:07:19", "remaining_time": "0:44:46"}
1013
+ {"current_steps": 911, "total_steps": 1230, "loss": 0.4268, "lr": 7.651021101410673e-06, "epoch": 3.700759493670886, "percentage": 74.07, "elapsed_time": "2:08:04", "remaining_time": "0:44:50"}
1014
+ {"current_steps": 912, "total_steps": 1230, "loss": 0.4228, "lr": 7.606423894180464e-06, "epoch": 3.7048101265822786, "percentage": 74.15, "elapsed_time": "2:08:46", "remaining_time": "0:44:54"}
1015
+ {"current_steps": 913, "total_steps": 1230, "loss": 0.404, "lr": 7.56192650310839e-06, "epoch": 3.708860759493671, "percentage": 74.23, "elapsed_time": "2:09:30", "remaining_time": "0:44:57"}
1016
+ {"current_steps": 914, "total_steps": 1230, "loss": 0.4102, "lr": 7.517529286570349e-06, "epoch": 3.712911392405063, "percentage": 74.31, "elapsed_time": "2:10:15", "remaining_time": "0:45:01"}
1017
+ {"current_steps": 915, "total_steps": 1230, "loss": 0.4244, "lr": 7.473232602135387e-06, "epoch": 3.7169620253164557, "percentage": 74.39, "elapsed_time": "2:11:00", "remaining_time": "0:45:06"}
1018
+ {"current_steps": 916, "total_steps": 1230, "loss": 0.4176, "lr": 7.429036806562935e-06, "epoch": 3.721012658227848, "percentage": 74.47, "elapsed_time": "2:11:43", "remaining_time": "0:45:09"}
1019
+ {"current_steps": 917, "total_steps": 1230, "loss": 0.4049, "lr": 7.3849422557998455e-06, "epoch": 3.7250632911392403, "percentage": 74.55, "elapsed_time": "2:12:30", "remaining_time": "0:45:13"}
1020
+ {"current_steps": 918, "total_steps": 1230, "loss": 0.4288, "lr": 7.340949304977567e-06, "epoch": 3.729113924050633, "percentage": 74.63, "elapsed_time": "2:13:16", "remaining_time": "0:45:17"}
1021
+ {"current_steps": 919, "total_steps": 1230, "loss": 0.4296, "lr": 7.297058308409282e-06, "epoch": 3.7331645569620253, "percentage": 74.72, "elapsed_time": "2:14:02", "remaining_time": "0:45:21"}
1022
+ {"current_steps": 920, "total_steps": 1230, "loss": 0.4188, "lr": 7.25326961958704e-06, "epoch": 3.737215189873418, "percentage": 74.8, "elapsed_time": "2:14:48", "remaining_time": "0:45:25"}
1023
+ {"current_steps": 921, "total_steps": 1230, "loss": 0.4912, "lr": 7.209583591178921e-06, "epoch": 3.7412658227848103, "percentage": 74.88, "elapsed_time": "2:15:32", "remaining_time": "0:45:28"}
1024
+ {"current_steps": 922, "total_steps": 1230, "loss": 0.4266, "lr": 7.1660005750261925e-06, "epoch": 3.7453164556962024, "percentage": 74.96, "elapsed_time": "2:16:14", "remaining_time": "0:45:30"}
1025
+ {"current_steps": 923, "total_steps": 1230, "loss": 0.4233, "lr": 7.1225209221404765e-06, "epoch": 3.749367088607595, "percentage": 75.04, "elapsed_time": "2:17:02", "remaining_time": "0:45:34"}
1026
+ {"current_steps": 924, "total_steps": 1230, "loss": 0.4055, "lr": 7.079144982700909e-06, "epoch": 3.7534177215189874, "percentage": 75.12, "elapsed_time": "2:17:49", "remaining_time": "0:45:38"}
1027
+ {"current_steps": 925, "total_steps": 1230, "loss": 0.4258, "lr": 7.0358731060513695e-06, "epoch": 3.7574683544303795, "percentage": 75.2, "elapsed_time": "2:18:33", "remaining_time": "0:45:41"}
1028
+ {"current_steps": 926, "total_steps": 1230, "loss": 0.4286, "lr": 6.99270564069757e-06, "epoch": 3.761518987341772, "percentage": 75.28, "elapsed_time": "2:19:18", "remaining_time": "0:45:44"}
1029
+ {"current_steps": 927, "total_steps": 1230, "loss": 0.423, "lr": 6.949642934304375e-06, "epoch": 3.7655696202531646, "percentage": 75.37, "elapsed_time": "2:20:02", "remaining_time": "0:45:46"}
1030
+ {"current_steps": 928, "total_steps": 1230, "loss": 0.4173, "lr": 6.906685333692871e-06, "epoch": 3.769620253164557, "percentage": 75.45, "elapsed_time": "2:20:46", "remaining_time": "0:45:48"}
1031
+ {"current_steps": 929, "total_steps": 1230, "loss": 0.4073, "lr": 6.86383318483769e-06, "epoch": 3.7736708860759496, "percentage": 75.53, "elapsed_time": "2:21:31", "remaining_time": "0:45:51"}
1032
+ {"current_steps": 930, "total_steps": 1230, "loss": 0.3993, "lr": 6.821086832864139e-06, "epoch": 3.7777215189873417, "percentage": 75.61, "elapsed_time": "2:22:16", "remaining_time": "0:45:53"}
1033
+ {"current_steps": 931, "total_steps": 1230, "loss": 0.4345, "lr": 6.77844662204546e-06, "epoch": 3.781772151898734, "percentage": 75.69, "elapsed_time": "2:23:02", "remaining_time": "0:45:56"}
1034
+ {"current_steps": 932, "total_steps": 1230, "loss": 0.411, "lr": 6.7359128958000455e-06, "epoch": 3.7858227848101267, "percentage": 75.77, "elapsed_time": "2:23:44", "remaining_time": "0:45:57"}
1035
+ {"current_steps": 933, "total_steps": 1230, "loss": 0.4184, "lr": 6.693485996688695e-06, "epoch": 3.7898734177215188, "percentage": 75.85, "elapsed_time": "2:24:29", "remaining_time": "0:45:59"}
1036
+ {"current_steps": 934, "total_steps": 1230, "loss": 0.4115, "lr": 6.651166266411801e-06, "epoch": 3.7939240506329113, "percentage": 75.93, "elapsed_time": "2:25:15", "remaining_time": "0:46:01"}
1037
+ {"current_steps": 935, "total_steps": 1230, "loss": 0.4237, "lr": 6.6089540458066725e-06, "epoch": 3.797974683544304, "percentage": 76.02, "elapsed_time": "2:25:59", "remaining_time": "0:46:03"}
1038
+ {"current_steps": 936, "total_steps": 1230, "loss": 0.4199, "lr": 6.566849674844711e-06, "epoch": 3.8020253164556963, "percentage": 76.1, "elapsed_time": "2:26:45", "remaining_time": "0:46:05"}
1039
+ {"current_steps": 937, "total_steps": 1230, "loss": 0.4253, "lr": 6.524853492628747e-06, "epoch": 3.806075949367089, "percentage": 76.18, "elapsed_time": "2:27:31", "remaining_time": "0:46:07"}
1040
+ {"current_steps": 938, "total_steps": 1230, "loss": 0.4296, "lr": 6.4829658373902536e-06, "epoch": 3.810126582278481, "percentage": 76.26, "elapsed_time": "2:28:17", "remaining_time": "0:46:09"}
1041
+ {"current_steps": 939, "total_steps": 1230, "loss": 0.4166, "lr": 6.441187046486648e-06, "epoch": 3.8141772151898734, "percentage": 76.34, "elapsed_time": "2:29:00", "remaining_time": "0:46:10"}
1042
+ {"current_steps": 940, "total_steps": 1230, "loss": 0.4209, "lr": 6.399517456398567e-06, "epoch": 3.818227848101266, "percentage": 76.42, "elapsed_time": "2:29:44", "remaining_time": "0:46:11"}
1043
+ {"current_steps": 941, "total_steps": 1230, "loss": 0.4084, "lr": 6.357957402727164e-06, "epoch": 3.822278481012658, "percentage": 76.5, "elapsed_time": "2:30:28", "remaining_time": "0:46:12"}
1044
+ {"current_steps": 942, "total_steps": 1230, "loss": 0.425, "lr": 6.316507220191395e-06, "epoch": 3.8263291139240505, "percentage": 76.59, "elapsed_time": "2:31:13", "remaining_time": "0:46:13"}
1045
+ {"current_steps": 943, "total_steps": 1230, "loss": 0.4223, "lr": 6.275167242625331e-06, "epoch": 3.830379746835443, "percentage": 76.67, "elapsed_time": "2:31:59", "remaining_time": "0:46:15"}
1046
+ {"current_steps": 944, "total_steps": 1230, "loss": 0.4271, "lr": 6.233937802975471e-06, "epoch": 3.8344303797468355, "percentage": 76.75, "elapsed_time": "2:32:45", "remaining_time": "0:46:16"}
1047
+ {"current_steps": 945, "total_steps": 1230, "loss": 0.397, "lr": 6.192819233298046e-06, "epoch": 3.838481012658228, "percentage": 76.83, "elapsed_time": "2:33:29", "remaining_time": "0:46:17"}
1048
+ {"current_steps": 946, "total_steps": 1230, "loss": 0.445, "lr": 6.151811864756383e-06, "epoch": 3.84253164556962, "percentage": 76.91, "elapsed_time": "2:34:15", "remaining_time": "0:46:18"}
1049
+ {"current_steps": 947, "total_steps": 1230, "loss": 0.4221, "lr": 6.1109160276181655e-06, "epoch": 3.8465822784810126, "percentage": 76.99, "elapsed_time": "2:34:59", "remaining_time": "0:46:19"}
1050
+ {"current_steps": 948, "total_steps": 1230, "loss": 0.4262, "lr": 6.070132051252868e-06, "epoch": 3.850632911392405, "percentage": 77.07, "elapsed_time": "2:35:43", "remaining_time": "0:46:19"}
1051
+ {"current_steps": 949, "total_steps": 1230, "loss": 0.4236, "lr": 6.0294602641290034e-06, "epoch": 3.8546835443037972, "percentage": 77.15, "elapsed_time": "2:36:26", "remaining_time": "0:46:19"}
1052
+ {"current_steps": 950, "total_steps": 1230, "loss": 0.4352, "lr": 5.988900993811575e-06, "epoch": 3.8587341772151897, "percentage": 77.24, "elapsed_time": "2:37:10", "remaining_time": "0:46:19"}
1053
+ {"current_steps": 951, "total_steps": 1230, "loss": 0.4201, "lr": 5.948454566959363e-06, "epoch": 3.8627848101265823, "percentage": 77.32, "elapsed_time": "2:37:56", "remaining_time": "0:46:20"}
1054
+ {"current_steps": 952, "total_steps": 1230, "loss": 0.4113, "lr": 5.908121309322328e-06, "epoch": 3.8668354430379748, "percentage": 77.4, "elapsed_time": "2:38:41", "remaining_time": "0:46:20"}
1055
+ {"current_steps": 953, "total_steps": 1230, "loss": 0.4245, "lr": 5.867901545738976e-06, "epoch": 3.8708860759493673, "percentage": 77.48, "elapsed_time": "2:39:26", "remaining_time": "0:46:20"}
1056
+ {"current_steps": 954, "total_steps": 1230, "loss": 0.4279, "lr": 5.827795600133774e-06, "epoch": 3.8749367088607594, "percentage": 77.56, "elapsed_time": "2:40:12", "remaining_time": "0:46:20"}
1057
+ {"current_steps": 955, "total_steps": 1230, "loss": 0.4329, "lr": 5.787803795514466e-06, "epoch": 3.878987341772152, "percentage": 77.64, "elapsed_time": "2:40:56", "remaining_time": "0:46:20"}
1058
+ {"current_steps": 956, "total_steps": 1230, "loss": 0.4162, "lr": 5.747926453969576e-06, "epoch": 3.8830379746835444, "percentage": 77.72, "elapsed_time": "2:41:42", "remaining_time": "0:46:20"}
1059
+ {"current_steps": 957, "total_steps": 1230, "loss": 0.4417, "lr": 5.708163896665708e-06, "epoch": 3.8870886075949365, "percentage": 77.8, "elapsed_time": "2:42:27", "remaining_time": "0:46:20"}
1060
+ {"current_steps": 958, "total_steps": 1230, "loss": 0.4184, "lr": 5.668516443845047e-06, "epoch": 3.891139240506329, "percentage": 77.89, "elapsed_time": "2:43:11", "remaining_time": "0:46:20"}
1061
+ {"current_steps": 959, "total_steps": 1230, "loss": 0.4336, "lr": 5.6289844148227225e-06, "epoch": 3.8951898734177215, "percentage": 77.97, "elapsed_time": "2:43:56", "remaining_time": "0:46:19"}
1062
+ {"current_steps": 960, "total_steps": 1230, "loss": 0.4164, "lr": 5.5895681279842615e-06, "epoch": 3.899240506329114, "percentage": 78.05, "elapsed_time": "2:44:40", "remaining_time": "0:46:18"}
1063
+ {"current_steps": 961, "total_steps": 1230, "loss": 0.4314, "lr": 5.550267900783019e-06, "epoch": 3.9032911392405065, "percentage": 78.13, "elapsed_time": "2:45:25", "remaining_time": "0:46:18"}
1064
+ {"current_steps": 962, "total_steps": 1230, "loss": 0.4274, "lr": 5.511084049737623e-06, "epoch": 3.9073417721518986, "percentage": 78.21, "elapsed_time": "2:46:10", "remaining_time": "0:46:17"}
1065
+ {"current_steps": 963, "total_steps": 1230, "loss": 0.4157, "lr": 5.4720168904294215e-06, "epoch": 3.911392405063291, "percentage": 78.29, "elapsed_time": "2:46:54", "remaining_time": "0:46:16"}
1066
+ {"current_steps": 964, "total_steps": 1230, "loss": 0.4245, "lr": 5.433066737499948e-06, "epoch": 3.9154430379746836, "percentage": 78.37, "elapsed_time": "2:47:37", "remaining_time": "0:46:15"}
1067
+ {"current_steps": 965, "total_steps": 1230, "loss": 0.4212, "lr": 5.394233904648376e-06, "epoch": 3.9194936708860757, "percentage": 78.46, "elapsed_time": "2:48:22", "remaining_time": "0:46:14"}
1068
+ {"current_steps": 966, "total_steps": 1230, "loss": 0.4339, "lr": 5.355518704628997e-06, "epoch": 3.923544303797468, "percentage": 78.54, "elapsed_time": "2:49:05", "remaining_time": "0:46:12"}
1069
+ {"current_steps": 967, "total_steps": 1230, "loss": 0.4424, "lr": 5.316921449248731e-06, "epoch": 3.9275949367088607, "percentage": 78.62, "elapsed_time": "2:49:51", "remaining_time": "0:46:11"}
1070
+ {"current_steps": 968, "total_steps": 1230, "loss": 0.4107, "lr": 5.278442449364538e-06, "epoch": 3.9316455696202532, "percentage": 78.7, "elapsed_time": "2:50:34", "remaining_time": "0:46:10"}
1071
+ {"current_steps": 969, "total_steps": 1230, "loss": 0.4258, "lr": 5.240082014881016e-06, "epoch": 3.9356962025316458, "percentage": 78.78, "elapsed_time": "2:51:18", "remaining_time": "0:46:08"}
1072
+ {"current_steps": 970, "total_steps": 1230, "loss": 0.4344, "lr": 5.201840454747822e-06, "epoch": 3.939746835443038, "percentage": 78.86, "elapsed_time": "2:52:05", "remaining_time": "0:46:07"}
1073
+ {"current_steps": 971, "total_steps": 1230, "loss": 0.4228, "lr": 5.163718076957223e-06, "epoch": 3.9437974683544303, "percentage": 78.94, "elapsed_time": "2:52:49", "remaining_time": "0:46:05"}
1074
+ {"current_steps": 972, "total_steps": 1230, "loss": 0.4291, "lr": 5.125715188541609e-06, "epoch": 3.947848101265823, "percentage": 79.02, "elapsed_time": "2:53:32", "remaining_time": "0:46:03"}
1075
+ {"current_steps": 973, "total_steps": 1230, "loss": 0.4318, "lr": 5.087832095571021e-06, "epoch": 3.951898734177215, "percentage": 79.11, "elapsed_time": "2:54:16", "remaining_time": "0:46:01"}
1076
+ {"current_steps": 974, "total_steps": 1230, "loss": 0.423, "lr": 5.0500691031506766e-06, "epoch": 3.9559493670886074, "percentage": 79.19, "elapsed_time": "2:55:00", "remaining_time": "0:46:00"}
1077
+ {"current_steps": 975, "total_steps": 1230, "loss": 0.4247, "lr": 5.01242651541854e-06, "epoch": 3.96, "percentage": 79.27, "elapsed_time": "2:55:46", "remaining_time": "0:45:58"}
1078
+ {"current_steps": 976, "total_steps": 1230, "loss": 0.4225, "lr": 4.974904635542815e-06, "epoch": 3.9640506329113925, "percentage": 79.35, "elapsed_time": "2:56:31", "remaining_time": "0:45:56"}
1079
+ {"current_steps": 977, "total_steps": 1230, "loss": 0.4171, "lr": 4.937503765719582e-06, "epoch": 3.968101265822785, "percentage": 79.43, "elapsed_time": "2:57:17", "remaining_time": "0:45:54"}
1080
+ {"current_steps": 978, "total_steps": 1230, "loss": 0.4291, "lr": 4.900224207170299e-06, "epoch": 3.972151898734177, "percentage": 79.51, "elapsed_time": "2:58:02", "remaining_time": "0:45:52"}
1081
+ {"current_steps": 979, "total_steps": 1230, "loss": 0.4191, "lr": 4.8630662601394065e-06, "epoch": 3.9762025316455696, "percentage": 79.59, "elapsed_time": "2:58:47", "remaining_time": "0:45:50"}
1082
+ {"current_steps": 980, "total_steps": 1230, "loss": 0.4178, "lr": 4.8260302238918995e-06, "epoch": 3.980253164556962, "percentage": 79.67, "elapsed_time": "2:59:33", "remaining_time": "0:45:48"}
1083
+ {"current_steps": 981, "total_steps": 1230, "loss": 0.4156, "lr": 4.789116396710924e-06, "epoch": 3.984303797468354, "percentage": 79.76, "elapsed_time": "3:00:16", "remaining_time": "0:45:45"}
1084
+ {"current_steps": 982, "total_steps": 1230, "loss": 0.4322, "lr": 4.752325075895368e-06, "epoch": 3.9883544303797467, "percentage": 79.84, "elapsed_time": "3:01:01", "remaining_time": "0:45:43"}
1085
+ {"current_steps": 983, "total_steps": 1230, "loss": 0.4124, "lr": 4.715656557757473e-06, "epoch": 3.992405063291139, "percentage": 79.92, "elapsed_time": "3:01:48", "remaining_time": "0:45:40"}
1086
+ {"current_steps": 984, "total_steps": 1230, "loss": 0.4062, "lr": 4.679111137620442e-06, "epoch": 3.9964556962025317, "percentage": 80.0, "elapsed_time": "3:02:31", "remaining_time": "0:45:37"}
1087
+ {"current_steps": 985, "total_steps": 1230, "loss": 0.415, "lr": 4.6426891098160585e-06, "epoch": 4.000506329113924, "percentage": 80.08, "elapsed_time": "3:05:12", "remaining_time": "0:46:04"}
1088
+ {"current_steps": 986, "total_steps": 1230, "loss": 0.4058, "lr": 4.6063907676823474e-06, "epoch": 4.004556962025316, "percentage": 80.16, "elapsed_time": "3:05:56", "remaining_time": "0:46:00"}
1089
+ {"current_steps": 987, "total_steps": 1230, "loss": 0.3731, "lr": 4.570216403561141e-06, "epoch": 4.008607594936709, "percentage": 80.24, "elapsed_time": "3:06:42", "remaining_time": "0:45:57"}
1090
+ {"current_steps": 988, "total_steps": 1230, "loss": 0.3876, "lr": 4.534166308795815e-06, "epoch": 4.012658227848101, "percentage": 80.33, "elapsed_time": "3:07:27", "remaining_time": "0:45:54"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37acb202651e6ca89088d59c4b8e04df0781ba31ef65fbf00877b78b938509ec
3
- size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421db23b9368ae5dd5b5f6d1ad37f7125a13941dc2b254c6935cf34272fe85ee
3
+ size 7288