diff --git "a/checkpoint-960/trainer_state.json" "b/checkpoint-960/trainer_state.json"
deleted file mode 100644--- "a/checkpoint-960/trainer_state.json"
+++ /dev/null
@@ -1,6810 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.6033940917661847,
-  "eval_steps": 160,
-  "global_step": 960,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0006285355122564425,
-      "grad_norm": 2.96633243560791,
-      "learning_rate": 0.0,
-      "loss": 7.5468,
-      "step": 1
-    },
-    {
-      "epoch": 0.0006285355122564425,
-      "eval_loss": 7.076071739196777,
-      "eval_runtime": 1556.6109,
-      "eval_samples_per_second": 1.656,
-      "eval_steps_per_second": 1.656,
-      "step": 1
-    },
-    {
-      "epoch": 0.001257071024512885,
-      "grad_norm": 2.7123501300811768,
-      "learning_rate": 4.0000000000000003e-07,
-      "loss": 6.3309,
-      "step": 2
-    },
-    {
-      "epoch": 0.0018856065367693275,
-      "grad_norm": 2.4243223667144775,
-      "learning_rate": 8.000000000000001e-07,
-      "loss": 6.7763,
-      "step": 3
-    },
-    {
-      "epoch": 0.00251414204902577,
-      "grad_norm": 2.319216728210449,
-      "learning_rate": 1.2000000000000002e-06,
-      "loss": 6.8187,
-      "step": 4
-    },
-    {
-      "epoch": 0.0031426775612822125,
-      "grad_norm": 2.4935989379882812,
-      "learning_rate": 1.6000000000000001e-06,
-      "loss": 7.0526,
-      "step": 5
-    },
-    {
-      "epoch": 0.003771213073538655,
-      "grad_norm": 2.1718926429748535,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 6.7646,
-      "step": 6
-    },
-    {
-      "epoch": 0.0043997485857950975,
-      "grad_norm": 2.177217960357666,
-      "learning_rate": 2.4000000000000003e-06,
-      "loss": 6.6131,
-      "step": 7
-    },
-    {
-      "epoch": 0.00502828409805154,
-      "grad_norm": 2.9915874004364014,
-      "learning_rate": 2.8000000000000003e-06,
-      "loss": 7.6544,
-      "step": 8
-    },
-    {
-      "epoch": 0.0056568196103079825,
-      "grad_norm": 2.6981074810028076,
-      "learning_rate": 3.2000000000000003e-06,
-      "loss": 6.799,
-      "step": 9
-    },
-    {
-      "epoch": 0.006285355122564425,
-      "grad_norm": 4.512426376342773,
-      "learning_rate": 3.6e-06,
-      "loss": 8.3895,
-      "step": 10
-    },
-    {
-      "epoch": 0.0069138906348208675,
-      "grad_norm": 2.3968913555145264,
-      "learning_rate": 4.000000000000001e-06,
-      "loss": 6.3478,
-      "step": 11
-    },
-    {
-      "epoch": 0.00754242614707731,
-      "grad_norm": 1.9744027853012085,
-      "learning_rate": 4.4e-06,
-      "loss": 5.5536,
-      "step": 12
-    },
-    {
-      "epoch": 0.008170961659333752,
-      "grad_norm": 3.050507068634033,
-      "learning_rate": 4.800000000000001e-06,
-      "loss": 6.5491,
-      "step": 13
-    },
-    {
-      "epoch": 0.008799497171590195,
-      "grad_norm": 3.0034799575805664,
-      "learning_rate": 5.2e-06,
-      "loss": 7.2764,
-      "step": 14
-    },
-    {
-      "epoch": 0.009428032683846637,
-      "grad_norm": 2.323613405227661,
-      "learning_rate": 5.600000000000001e-06,
-      "loss": 6.8805,
-      "step": 15
-    },
-    {
-      "epoch": 0.01005656819610308,
-      "grad_norm": 3.129593849182129,
-      "learning_rate": 6e-06,
-      "loss": 7.3171,
-      "step": 16
-    },
-    {
-      "epoch": 0.010685103708359522,
-      "grad_norm": 2.296137571334839,
-      "learning_rate": 6.4000000000000006e-06,
-      "loss": 6.4251,
-      "step": 17
-    },
-    {
-      "epoch": 0.011313639220615965,
-      "grad_norm": 2.637282133102417,
-      "learning_rate": 6.800000000000001e-06,
-      "loss": 6.6142,
-      "step": 18
-    },
-    {
-      "epoch": 0.011942174732872407,
-      "grad_norm": 2.1313271522521973,
-      "learning_rate": 7.2e-06,
-      "loss": 6.3841,
-      "step": 19
-    },
-    {
-      "epoch": 0.01257071024512885,
-      "grad_norm": 2.7492284774780273,
-      "learning_rate": 7.6e-06,
-      "loss": 6.8148,
-      "step": 20
-    },
-    {
-      "epoch": 0.013199245757385292,
-      "grad_norm": 2.945878267288208,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 6.9732,
-      "step": 21
-    },
-    {
-      "epoch": 0.013827781269641735,
-      "grad_norm": 3.709951162338257,
-      "learning_rate": 8.400000000000001e-06,
-      "loss": 7.7273,
-      "step": 22
-    },
-    {
-      "epoch": 0.014456316781898177,
-      "grad_norm": 3.023289203643799,
-      "learning_rate": 8.8e-06,
-      "loss": 7.0649,
-      "step": 23
-    },
-    {
-      "epoch": 0.01508485229415462,
-      "grad_norm": 3.163715124130249,
-      "learning_rate": 9.2e-06,
-      "loss": 6.9342,
-      "step": 24
-    },
-    {
-      "epoch": 0.01571338780641106,
-      "grad_norm": 4.114445686340332,
-      "learning_rate": 9.600000000000001e-06,
-      "loss": 8.119,
-      "step": 25
-    },
-    {
-      "epoch": 0.016341923318667503,
-      "grad_norm": 3.021068572998047,
-      "learning_rate": 1e-05,
-      "loss": 7.4067,
-      "step": 26
-    },
-    {
-      "epoch": 0.01697045883092395,
-      "grad_norm": 3.724407911300659,
-      "learning_rate": 1.04e-05,
-      "loss": 7.3869,
-      "step": 27
-    },
-    {
-      "epoch": 0.01759899434318039,
-      "grad_norm": 2.656257390975952,
-      "learning_rate": 1.08e-05,
-      "loss": 5.9961,
-      "step": 28
-    },
-    {
-      "epoch": 0.018227529855436832,
-      "grad_norm": 2.7785143852233887,
-      "learning_rate": 1.1200000000000001e-05,
-      "loss": 5.6596,
-      "step": 29
-    },
-    {
-      "epoch": 0.018856065367693273,
-      "grad_norm": 3.130934715270996,
-      "learning_rate": 1.16e-05,
-      "loss": 6.6092,
-      "step": 30
-    },
-    {
-      "epoch": 0.01948460087994972,
-      "grad_norm": 3.42301869392395,
-      "learning_rate": 1.2e-05,
-      "loss": 6.3373,
-      "step": 31
-    },
-    {
-      "epoch": 0.02011313639220616,
-      "grad_norm": 2.8691611289978027,
-      "learning_rate": 1.24e-05,
-      "loss": 6.5923,
-      "step": 32
-    },
-    {
-      "epoch": 0.020741671904462602,
-      "grad_norm": 2.917086601257324,
-      "learning_rate": 1.2800000000000001e-05,
-      "loss": 5.9773,
-      "step": 33
-    },
-    {
-      "epoch": 0.021370207416719043,
-      "grad_norm": 4.07196044921875,
-      "learning_rate": 1.32e-05,
-      "loss": 7.4423,
-      "step": 34
-    },
-    {
-      "epoch": 0.02199874292897549,
-      "grad_norm": 4.738312244415283,
-      "learning_rate": 1.3600000000000002e-05,
-      "loss": 7.5113,
-      "step": 35
-    },
-    {
-      "epoch": 0.02262727844123193,
-      "grad_norm": 3.898664712905884,
-      "learning_rate": 1.4000000000000001e-05,
-      "loss": 6.8738,
-      "step": 36
-    },
-    {
-      "epoch": 0.023255813953488372,
-      "grad_norm": 3.7448792457580566,
-      "learning_rate": 1.44e-05,
-      "loss": 6.9615,
-      "step": 37
-    },
-    {
-      "epoch": 0.023884349465744813,
-      "grad_norm": 3.5938379764556885,
-      "learning_rate": 1.48e-05,
-      "loss": 6.0651,
-      "step": 38
-    },
-    {
-      "epoch": 0.02451288497800126,
-      "grad_norm": 4.253636360168457,
-      "learning_rate": 1.52e-05,
-      "loss": 6.9986,
-      "step": 39
-    },
-    {
-      "epoch": 0.0251414204902577,
-      "grad_norm": 4.985451698303223,
-      "learning_rate": 1.56e-05,
-      "loss": 7.252,
-      "step": 40
-    },
-    {
-      "epoch": 0.025769956002514142,
-      "grad_norm": 4.376275062561035,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 6.8091,
-      "step": 41
-    },
-    {
-      "epoch": 0.026398491514770583,
-      "grad_norm": 4.697645664215088,
-      "learning_rate": 1.6400000000000002e-05,
-      "loss": 6.4319,
-      "step": 42
-    },
-    {
-      "epoch": 0.02702702702702703,
-      "grad_norm": 5.258227348327637,
-      "learning_rate": 1.6800000000000002e-05,
-      "loss": 6.7672,
-      "step": 43
-    },
-    {
-      "epoch": 0.02765556253928347,
-      "grad_norm": 5.063000679016113,
-      "learning_rate": 1.7199999999999998e-05,
-      "loss": 6.3354,
-      "step": 44
-    },
-    {
-      "epoch": 0.028284098051539912,
-      "grad_norm": 4.573636531829834,
-      "learning_rate": 1.76e-05,
-      "loss": 6.3374,
-      "step": 45
-    },
-    {
-      "epoch": 0.028912633563796353,
-      "grad_norm": 4.72340202331543,
-      "learning_rate": 1.8e-05,
-      "loss": 6.6553,
-      "step": 46
-    },
-    {
-      "epoch": 0.0295411690760528,
-      "grad_norm": 6.681248664855957,
-      "learning_rate": 1.84e-05,
-      "loss": 7.7157,
-      "step": 47
-    },
-    {
-      "epoch": 0.03016970458830924,
-      "grad_norm": 5.952408313751221,
-      "learning_rate": 1.88e-05,
-      "loss": 5.8215,
-      "step": 48
-    },
-    {
-      "epoch": 0.030798240100565682,
-      "grad_norm": 6.599308967590332,
-      "learning_rate": 1.9200000000000003e-05,
-      "loss": 6.921,
-      "step": 49
-    },
-    {
-      "epoch": 0.03142677561282212,
-      "grad_norm": 6.538867473602295,
-      "learning_rate": 1.9600000000000002e-05,
-      "loss": 7.1274,
-      "step": 50
-    },
-    {
-      "epoch": 0.03205531112507857,
-      "grad_norm": 5.91294527053833,
-      "learning_rate": 2e-05,
-      "loss": 6.7263,
-      "step": 51
-    },
-    {
-      "epoch": 0.03268384663733501,
-      "grad_norm": 7.943373203277588,
-      "learning_rate": 2.04e-05,
-      "loss": 7.4335,
-      "step": 52
-    },
-    {
-      "epoch": 0.03331238214959145,
-      "grad_norm": 7.023540496826172,
-      "learning_rate": 2.08e-05,
-      "loss": 6.3428,
-      "step": 53
-    },
-    {
-      "epoch": 0.0339409176618479,
-      "grad_norm": 7.031850814819336,
-      "learning_rate": 2.12e-05,
-      "loss": 6.2423,
-      "step": 54
-    },
-    {
-      "epoch": 0.034569453174104335,
-      "grad_norm": 6.891653537750244,
-      "learning_rate": 2.16e-05,
-      "loss": 6.4081,
-      "step": 55
-    },
-    {
-      "epoch": 0.03519798868636078,
-      "grad_norm": 8.165786743164062,
-      "learning_rate": 2.2000000000000003e-05,
-      "loss": 7.1081,
-      "step": 56
-    },
-    {
-      "epoch": 0.035826524198617225,
-      "grad_norm": 9.146330833435059,
-      "learning_rate": 2.2400000000000002e-05,
-      "loss": 7.4309,
-      "step": 57
-    },
-    {
-      "epoch": 0.036455059710873663,
-      "grad_norm": 8.637526512145996,
-      "learning_rate": 2.2800000000000002e-05,
-      "loss": 6.9889,
-      "step": 58
-    },
-    {
-      "epoch": 0.03708359522313011,
-      "grad_norm": 8.397353172302246,
-      "learning_rate": 2.32e-05,
-      "loss": 5.8222,
-      "step": 59
-    },
-    {
-      "epoch": 0.03771213073538655,
-      "grad_norm": 9.219857215881348,
-      "learning_rate": 2.36e-05,
-      "loss": 7.0839,
-      "step": 60
-    },
-    {
-      "epoch": 0.03834066624764299,
-      "grad_norm": 8.762686729431152,
-      "learning_rate": 2.4e-05,
-      "loss": 6.192,
-      "step": 61
-    },
-    {
-      "epoch": 0.03896920175989944,
-      "grad_norm": 9.55370044708252,
-      "learning_rate": 2.44e-05,
-      "loss": 6.2674,
-      "step": 62
-    },
-    {
-      "epoch": 0.039597737272155875,
-      "grad_norm": 10.248711585998535,
-      "learning_rate": 2.48e-05,
-      "loss": 7.4737,
-      "step": 63
-    },
-    {
-      "epoch": 0.04022627278441232,
-      "grad_norm": 9.455551147460938,
-      "learning_rate": 2.5200000000000003e-05,
-      "loss": 6.5796,
-      "step": 64
-    },
-    {
-      "epoch": 0.04085480829666876,
-      "grad_norm": 10.217570304870605,
-      "learning_rate": 2.5600000000000002e-05,
-      "loss": 6.8329,
-      "step": 65
-    },
-    {
-      "epoch": 0.041483343808925204,
-      "grad_norm": 12.418697357177734,
-      "learning_rate": 2.6000000000000002e-05,
-      "loss": 7.0127,
-      "step": 66
-    },
-    {
-      "epoch": 0.04211187932118165,
-      "grad_norm": 13.362143516540527,
-      "learning_rate": 2.64e-05,
-      "loss": 6.3027,
-      "step": 67
-    },
-    {
-      "epoch": 0.04274041483343809,
-      "grad_norm": 10.577826499938965,
-      "learning_rate": 2.6800000000000004e-05,
-      "loss": 6.2406,
-      "step": 68
-    },
-    {
-      "epoch": 0.04336895034569453,
-      "grad_norm": 13.15530776977539,
-      "learning_rate": 2.7200000000000004e-05,
-      "loss": 7.3093,
-      "step": 69
-    },
-    {
-      "epoch": 0.04399748585795098,
-      "grad_norm": 10.775976181030273,
-      "learning_rate": 2.7600000000000003e-05,
-      "loss": 5.9398,
-      "step": 70
-    },
-    {
-      "epoch": 0.044626021370207415,
-      "grad_norm": 12.925591468811035,
-      "learning_rate": 2.8000000000000003e-05,
-      "loss": 6.7144,
-      "step": 71
-    },
-    {
-      "epoch": 0.04525455688246386,
-      "grad_norm": 12.626113891601562,
-      "learning_rate": 2.84e-05,
-      "loss": 6.5783,
-      "step": 72
-    },
-    {
-      "epoch": 0.0458830923947203,
-      "grad_norm": 14.04005241394043,
-      "learning_rate": 2.88e-05,
-      "loss": 6.1111,
-      "step": 73
-    },
-    {
-      "epoch": 0.046511627906976744,
-      "grad_norm": 14.279847145080566,
-      "learning_rate": 2.9199999999999998e-05,
-      "loss": 5.7717,
-      "step": 74
-    },
-    {
-      "epoch": 0.04714016341923319,
-      "grad_norm": 13.597288131713867,
-      "learning_rate": 2.96e-05,
-      "loss": 6.7714,
-      "step": 75
-    },
-    {
-      "epoch": 0.04776869893148963,
-      "grad_norm": 12.93455696105957,
-      "learning_rate": 3e-05,
-      "loss": 6.5082,
-      "step": 76
-    },
-    {
-      "epoch": 0.04839723444374607,
-      "grad_norm": 12.823902130126953,
-      "learning_rate": 3.04e-05,
-      "loss": 6.7108,
-      "step": 77
-    },
-    {
-      "epoch": 0.04902576995600252,
-      "grad_norm": 16.93589973449707,
-      "learning_rate": 3.08e-05,
-      "loss": 6.2773,
-      "step": 78
-    },
-    {
-      "epoch": 0.049654305468258955,
-      "grad_norm": 14.550610542297363,
-      "learning_rate": 3.12e-05,
-      "loss": 6.4329,
-      "step": 79
-    },
-    {
-      "epoch": 0.0502828409805154,
-      "grad_norm": 11.992222785949707,
-      "learning_rate": 3.16e-05,
-      "loss": 5.3369,
-      "step": 80
-    },
-    {
-      "epoch": 0.05091137649277184,
-      "grad_norm": 12.921990394592285,
-      "learning_rate": 3.2000000000000005e-05,
-      "loss": 5.8783,
-      "step": 81
-    },
-    {
-      "epoch": 0.051539912005028284,
-      "grad_norm": 14.483002662658691,
-      "learning_rate": 3.24e-05,
-      "loss": 7.4091,
-      "step": 82
-    },
-    {
-      "epoch": 0.05216844751728473,
-      "grad_norm": 15.877086639404297,
-      "learning_rate": 3.2800000000000004e-05,
-      "loss": 6.9743,
-      "step": 83
-    },
-    {
-      "epoch": 0.05279698302954117,
-      "grad_norm": 15.85240650177002,
-      "learning_rate": 3.32e-05,
-      "loss": 7.0001,
-      "step": 84
-    },
-    {
-      "epoch": 0.05342551854179761,
-      "grad_norm": 17.0369815826416,
-      "learning_rate": 3.3600000000000004e-05,
-      "loss": 5.8022,
-      "step": 85
-    },
-    {
-      "epoch": 0.05405405405405406,
-      "grad_norm": 15.62733268737793,
-      "learning_rate": 3.4000000000000007e-05,
-      "loss": 6.8172,
-      "step": 86
-    },
-    {
-      "epoch": 0.054682589566310495,
-      "grad_norm": 18.79668426513672,
-      "learning_rate": 3.4399999999999996e-05,
-      "loss": 6.6659,
-      "step": 87
-    },
-    {
-      "epoch": 0.05531112507856694,
-      "grad_norm": 15.78856086730957,
-      "learning_rate": 3.48e-05,
-      "loss": 5.7255,
-      "step": 88
-    },
-    {
-      "epoch": 0.05593966059082338,
-      "grad_norm": 13.196313858032227,
-      "learning_rate": 3.52e-05,
-      "loss": 5.8423,
-      "step": 89
-    },
-    {
-      "epoch": 0.056568196103079824,
-      "grad_norm": 16.4498233795166,
-      "learning_rate": 3.56e-05,
-      "loss": 5.4969,
-      "step": 90
-    },
-    {
-      "epoch": 0.05719673161533627,
-      "grad_norm": 15.243169784545898,
-      "learning_rate": 3.6e-05,
-      "loss": 6.0186,
-      "step": 91
-    },
-    {
-      "epoch": 0.05782526712759271,
-      "grad_norm": 17.294044494628906,
-      "learning_rate": 3.6400000000000004e-05,
-      "loss": 6.8408,
-      "step": 92
-    },
-    {
-      "epoch": 0.05845380263984915,
-      "grad_norm": 19.32530975341797,
-      "learning_rate": 3.68e-05,
-      "loss": 6.5562,
-      "step": 93
-    },
-    {
-      "epoch": 0.0590823381521056,
-      "grad_norm": 20.01514434814453,
-      "learning_rate": 3.72e-05,
-      "loss": 6.4273,
-      "step": 94
-    },
-    {
-      "epoch": 0.059710873664362035,
-      "grad_norm": 19.90467643737793,
-      "learning_rate": 3.76e-05,
-      "loss": 7.2277,
-      "step": 95
-    },
-    {
-      "epoch": 0.06033940917661848,
-      "grad_norm": 17.582975387573242,
-      "learning_rate": 3.8e-05,
-      "loss": 7.0173,
-      "step": 96
-    },
-    {
-      "epoch": 0.06096794468887492,
-      "grad_norm": 17.471969604492188,
-      "learning_rate": 3.8400000000000005e-05,
-      "loss": 6.6919,
-      "step": 97
-    },
-    {
-      "epoch": 0.061596480201131364,
-      "grad_norm": 16.06781005859375,
-      "learning_rate": 3.88e-05,
-      "loss": 6.54,
-      "step": 98
-    },
-    {
-      "epoch": 0.06222501571338781,
-      "grad_norm": 17.99164390563965,
-      "learning_rate": 3.9200000000000004e-05,
-      "loss": 5.9168,
-      "step": 99
-    },
-    {
-      "epoch": 0.06285355122564425,
-      "grad_norm": 16.01885986328125,
-      "learning_rate": 3.960000000000001e-05,
-      "loss": 5.9236,
-      "step": 100
-    },
-    {
-      "epoch": 0.06348208673790069,
-      "grad_norm": 9.705466270446777,
-      "learning_rate": 4e-05,
-      "loss": 4.4168,
-      "step": 101
-    },
-    {
-      "epoch": 0.06411062225015714,
-      "grad_norm": 21.02065086364746,
-      "learning_rate": 4.0400000000000006e-05,
-      "loss": 6.7312,
-      "step": 102
-    },
-    {
-      "epoch": 0.06473915776241358,
-      "grad_norm": 16.56360626220703,
-      "learning_rate": 4.08e-05,
-      "loss": 6.5865,
-      "step": 103
-    },
-    {
-      "epoch": 0.06536769327467001,
-      "grad_norm": 17.319807052612305,
-      "learning_rate": 4.12e-05,
-      "loss": 6.4122,
-      "step": 104
-    },
-    {
-      "epoch": 0.06599622878692646,
-      "grad_norm": 21.3114070892334,
-      "learning_rate": 4.16e-05,
-      "loss": 6.9886,
-      "step": 105
-    },
-    {
-      "epoch": 0.0666247642991829,
-      "grad_norm": 21.147327423095703,
-      "learning_rate": 4.2e-05,
-      "loss": 6.7595,
-      "step": 106
-    },
-    {
-      "epoch": 0.06725329981143935,
-      "grad_norm": 16.264938354492188,
-      "learning_rate": 4.24e-05,
-      "loss": 6.114,
-      "step": 107
-    },
-    {
-      "epoch": 0.0678818353236958,
-      "grad_norm": 20.424713134765625,
-      "learning_rate": 4.2800000000000004e-05,
-      "loss": 6.9508,
-      "step": 108
-    },
-    {
-      "epoch": 0.06851037083595223,
-      "grad_norm": 19.48565673828125,
-      "learning_rate": 4.32e-05,
-      "loss": 6.7488,
-      "step": 109
-    },
-    {
-      "epoch": 0.06913890634820867,
-      "grad_norm": 17.111894607543945,
-      "learning_rate": 4.36e-05,
-      "loss": 6.5613,
-      "step": 110
-    },
-    {
-      "epoch": 0.06976744186046512,
-      "grad_norm": 14.604440689086914,
-      "learning_rate": 4.4000000000000006e-05,
-      "loss": 6.0278,
-      "step": 111
-    },
-    {
-      "epoch": 0.07039597737272156,
-      "grad_norm": 19.691083908081055,
-      "learning_rate": 4.44e-05,
-      "loss": 6.6524,
-      "step": 112
-    },
-    {
-      "epoch": 0.071024512884978,
-      "grad_norm": 20.216869354248047,
-      "learning_rate": 4.4800000000000005e-05,
-      "loss": 7.1919,
-      "step": 113
-    },
-    {
-      "epoch": 0.07165304839723445,
-      "grad_norm": 12.34801197052002,
-      "learning_rate": 4.52e-05,
-      "loss": 5.8613,
-      "step": 114
-    },
-    {
-      "epoch": 0.07228158390949088,
-      "grad_norm": 10.295191764831543,
-      "learning_rate": 4.5600000000000004e-05,
-      "loss": 5.2475,
-      "step": 115
-    },
-    {
-      "epoch": 0.07291011942174733,
-      "grad_norm": 15.049263954162598,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 6.1295,
-      "step": 116
-    },
-    {
-      "epoch": 0.07353865493400377,
-      "grad_norm": 12.287694931030273,
-      "learning_rate": 4.64e-05,
-      "loss": 5.7615,
-      "step": 117
-    },
-    {
-      "epoch": 0.07416719044626022,
-      "grad_norm": 12.11177921295166,
-      "learning_rate": 4.6800000000000006e-05,
-      "loss": 5.8763,
-      "step": 118
-    },
-    {
-      "epoch": 0.07479572595851666,
-      "grad_norm": 11.103803634643555,
-      "learning_rate": 4.72e-05,
-      "loss": 5.5072,
-      "step": 119
-    },
-    {
-      "epoch": 0.0754242614707731,
-      "grad_norm": 10.065237998962402,
-      "learning_rate": 4.76e-05,
-      "loss": 5.4734,
-      "step": 120
-    },
-    {
-      "epoch": 0.07605279698302954,
-      "grad_norm": 15.039546012878418,
-      "learning_rate": 4.8e-05,
-      "loss": 6.2005,
-      "step": 121
-    },
-    {
-      "epoch": 0.07668133249528598,
-      "grad_norm": 10.25068473815918,
-      "learning_rate": 4.8400000000000004e-05,
-      "loss": 5.4703,
-      "step": 122
-    },
-    {
-      "epoch": 0.07730986800754243,
-      "grad_norm": 13.106711387634277,
-      "learning_rate": 4.88e-05,
-      "loss": 6.6926,
-      "step": 123
-    },
-    {
-      "epoch": 0.07793840351979887,
-      "grad_norm": 7.927108287811279,
-      "learning_rate": 4.92e-05,
-      "loss": 5.3666,
-      "step": 124
-    },
-    {
-      "epoch": 0.0785669390320553,
-      "grad_norm": 10.937745094299316,
-      "learning_rate": 4.96e-05,
-      "loss": 6.1474,
-      "step": 125
-    },
-    {
-      "epoch": 0.07919547454431175,
-      "grad_norm": 10.88867473602295,
-      "learning_rate": 5e-05,
-      "loss": 6.1572,
-      "step": 126
-    },
-    {
-      "epoch": 0.0798240100565682,
-      "grad_norm": 11.629264831542969,
-      "learning_rate": 5.0400000000000005e-05,
-      "loss": 6.391,
-      "step": 127
-    },
-    {
-      "epoch": 0.08045254556882464,
-      "grad_norm": 10.296239852905273,
-      "learning_rate": 5.08e-05,
-      "loss": 5.9652,
-      "step": 128
-    },
-    {
-      "epoch": 0.08108108108108109,
-      "grad_norm": 11.038286209106445,
-      "learning_rate": 5.1200000000000004e-05,
-      "loss": 6.1295,
-      "step": 129
-    },
-    {
-      "epoch": 0.08170961659333752,
-      "grad_norm": 9.234803199768066,
-      "learning_rate": 5.16e-05,
-      "loss": 5.796,
-      "step": 130
-    },
-    {
-      "epoch": 0.08233815210559396,
-      "grad_norm": 8.689288139343262,
-      "learning_rate": 5.2000000000000004e-05,
-      "loss": 5.3704,
-      "step": 131
-    },
-    {
-      "epoch": 0.08296668761785041,
-      "grad_norm": 15.41921615600586,
-      "learning_rate": 5.2400000000000007e-05,
-      "loss": 6.0926,
-      "step": 132
-    },
-    {
-      "epoch": 0.08359522313010685,
-      "grad_norm": 8.419554710388184,
-      "learning_rate": 5.28e-05,
-      "loss": 5.8071,
-      "step": 133
-    },
-    {
-      "epoch": 0.0842237586423633,
-      "grad_norm": 8.644979476928711,
-      "learning_rate": 5.3200000000000006e-05,
-      "loss": 5.9138,
-      "step": 134
-    },
-    {
-      "epoch": 0.08485229415461974,
-      "grad_norm": 11.236026763916016,
-      "learning_rate": 5.360000000000001e-05,
-      "loss": 5.9092,
-      "step": 135
-    },
-    {
-      "epoch": 0.08548082966687617,
-      "grad_norm": 9.669437408447266,
-      "learning_rate": 5.4000000000000005e-05,
-      "loss": 5.3778,
-      "step": 136
-    },
-    {
-      "epoch": 0.08610936517913262,
-      "grad_norm": 10.624286651611328,
-      "learning_rate": 5.440000000000001e-05,
-      "loss": 5.4098,
-      "step": 137
-    },
-    {
-      "epoch": 0.08673790069138906,
-      "grad_norm": 8.831917762756348,
-      "learning_rate": 5.4800000000000004e-05,
-      "loss": 5.3806,
-      "step": 138
-    },
-    {
-      "epoch": 0.08736643620364551,
-      "grad_norm": 8.536581993103027,
-      "learning_rate": 5.520000000000001e-05,
-      "loss": 5.9237,
-      "step": 139
-    },
-    {
-      "epoch": 0.08799497171590195,
-      "grad_norm": 7.873721599578857,
-      "learning_rate": 5.560000000000001e-05,
-      "loss": 5.423,
-      "step": 140
-    },
-    {
-      "epoch": 0.08862350722815839,
-      "grad_norm": 8.635188102722168,
-      "learning_rate": 5.6000000000000006e-05,
-      "loss": 5.6118,
-      "step": 141
-    },
-    {
-      "epoch": 0.08925204274041483,
-      "grad_norm": 13.39542293548584,
-      "learning_rate": 5.6399999999999995e-05,
-      "loss": 5.2728,
-      "step": 142
-    },
-    {
-      "epoch": 0.08988057825267128,
-      "grad_norm": 12.998862266540527,
-      "learning_rate": 5.68e-05,
-      "loss": 6.9434,
-      "step": 143
-    },
-    {
-      "epoch": 0.09050911376492772,
-      "grad_norm": 8.149964332580566,
-      "learning_rate": 5.72e-05,
-      "loss": 5.3559,
-      "step": 144
-    },
-    {
-      "epoch": 0.09113764927718417,
-      "grad_norm": 7.66946268081665,
-      "learning_rate": 5.76e-05,
-      "loss": 5.5603,
-      "step": 145
-    },
-    {
-      "epoch": 0.0917661847894406,
-      "grad_norm": 9.277702331542969,
-      "learning_rate": 5.8e-05,
-      "loss": 4.9751,
-      "step": 146
-    },
-    {
-      "epoch": 0.09239472030169704,
-      "grad_norm": 7.442458152770996,
-      "learning_rate": 5.8399999999999997e-05,
-      "loss": 5.1653,
-      "step": 147
-    },
-    {
-      "epoch": 0.09302325581395349,
-      "grad_norm": 8.340120315551758,
-      "learning_rate": 5.88e-05,
-      "loss": 5.5422,
-      "step": 148
-    },
-    {
-      "epoch": 0.09365179132620993,
-      "grad_norm": 6.774919033050537,
-      "learning_rate": 5.92e-05,
-      "loss": 5.0187,
-      "step": 149
-    },
-    {
-      "epoch": 0.09428032683846638,
-      "grad_norm": 8.363201141357422,
-      "learning_rate": 5.96e-05,
-      "loss": 4.9803,
-      "step": 150
-    },
-    {
-      "epoch": 0.09490886235072282,
-      "grad_norm": 7.182234764099121,
-      "learning_rate": 6e-05,
-      "loss": 5.2913,
-      "step": 151
-    },
-    {
-      "epoch": 0.09553739786297925,
-      "grad_norm": 9.065616607666016,
-      "learning_rate": 6.04e-05,
-      "loss": 5.8604,
-      "step": 152
-    },
-    {
-      "epoch": 0.0961659333752357,
-      "grad_norm": 7.823053359985352,
-      "learning_rate": 6.08e-05,
-      "loss": 5.7326,
-      "step": 153
-    },
-    {
-      "epoch": 0.09679446888749214,
-      "grad_norm": 8.177785873413086,
-      "learning_rate": 6.12e-05,
-      "loss": 5.5663,
-      "step": 154
-    },
-    {
-      "epoch": 0.09742300439974859,
-      "grad_norm": 8.24718952178955,
-      "learning_rate": 6.16e-05,
-      "loss": 5.5606,
-      "step": 155
-    },
-    {
-      "epoch": 0.09805153991200503,
-      "grad_norm": 10.260727882385254,
-      "learning_rate": 6.2e-05,
-      "loss": 5.7043,
-      "step": 156
-    },
-    {
-      "epoch": 0.09868007542426147,
-      "grad_norm": 11.80507755279541,
-      "learning_rate": 6.24e-05,
-      "loss": 6.0268,
-      "step": 157
-    },
-    {
-      "epoch": 0.09930861093651791,
-      "grad_norm": 9.024588584899902,
-      "learning_rate": 6.280000000000001e-05,
-      "loss": 6.2249,
-      "step": 158
-    },
-    {
-      "epoch": 0.09993714644877436,
-      "grad_norm": 6.814016342163086,
-      "learning_rate": 6.32e-05,
-      "loss": 5.0123,
-      "step": 159
-    },
-    {
-      "epoch": 0.1005656819610308,
-      "grad_norm": 6.701868534088135,
-      "learning_rate": 6.36e-05,
-      "loss": 4.9993,
-      "step": 160
-    },
-    {
-      "epoch": 0.1005656819610308,
-      "eval_loss": 5.605074882507324,
-      "eval_runtime": 1565.1736,
-      "eval_samples_per_second": 1.647,
-      "eval_steps_per_second": 1.647,
-      "step": 160
-    },
-    {
-      "epoch": 0.10119421747328725,
-      "grad_norm": 14.352143287658691,
-      "learning_rate": 6.400000000000001e-05,
-      "loss": 5.8635,
-      "step": 161
-    },
-    {
-      "epoch": 0.10182275298554368,
-      "grad_norm": 7.681995868682861,
-      "learning_rate": 6.440000000000001e-05,
-      "loss": 5.2773,
-      "step": 162
-    },
-    {
-      "epoch": 0.10245128849780012,
-      "grad_norm": 10.032212257385254,
-      "learning_rate": 6.48e-05,
-      "loss": 5.4718,
-      "step": 163
-    },
-    {
-      "epoch": 0.10307982401005657,
-      "grad_norm": 6.617798805236816,
-      "learning_rate": 6.52e-05,
-      "loss": 4.7259,
-      "step": 164
-    },
-    {
-      "epoch": 0.10370835952231301,
-      "grad_norm": 7.318296432495117,
-      "learning_rate": 6.560000000000001e-05,
-      "loss": 4.9979,
-      "step": 165
-    },
-    {
-      "epoch": 0.10433689503456946,
-      "grad_norm": 9.494800567626953,
-      "learning_rate": 6.6e-05,
-      "loss": 5.4222,
-      "step": 166
-    },
-    {
-      "epoch": 0.1049654305468259,
-      "grad_norm": 6.2663798332214355,
-      "learning_rate": 6.64e-05,
-      "loss": 4.806,
-      "step": 167
-    },
-    {
-      "epoch": 0.10559396605908233,
-      "grad_norm": 7.666187286376953,
-      "learning_rate": 6.680000000000001e-05,
-      "loss": 5.583,
-      "step": 168
-    },
-    {
-      "epoch": 0.10622250157133878,
-      "grad_norm": 6.545588493347168,
-      "learning_rate": 6.720000000000001e-05,
-      "loss": 5.4927,
-      "step": 169
-    },
-    {
-      "epoch": 0.10685103708359522,
-      "grad_norm": 7.650016784667969,
-      "learning_rate": 6.76e-05,
-      "loss": 5.6347,
-      "step": 170
-    },
-    {
-      "epoch": 0.10747957259585167,
-      "grad_norm": 6.05757474899292,
-      "learning_rate": 6.800000000000001e-05,
-      "loss": 4.8323,
-      "step": 171
-    },
-    {
-      "epoch": 0.10810810810810811,
-      "grad_norm": 8.37306022644043,
-      "learning_rate": 6.840000000000001e-05,
-      "loss": 5.5312,
-      "step": 172
-    },
-    {
-      "epoch": 0.10873664362036455,
-      "grad_norm": 6.950132369995117,
-      "learning_rate": 6.879999999999999e-05,
-      "loss": 5.216,
-      "step": 173
-    },
-    {
-      "epoch": 0.10936517913262099,
-      "grad_norm": 7.643744945526123,
-      "learning_rate": 6.92e-05,
-      "loss": 5.374,
-      "step": 174
-    },
-    {
-      "epoch": 0.10999371464487744,
-      "grad_norm": 12.621402740478516,
-      "learning_rate": 6.96e-05,
-      "loss": 6.3553,
-      "step": 175
-    },
-    {
-      "epoch": 0.11062225015713388,
-      "grad_norm": 6.861866474151611,
-      "learning_rate": 7e-05,
-      "loss": 5.0186,
-      "step": 176
-    },
-    {
-      "epoch": 0.11125078566939033,
-      "grad_norm": 7.023342609405518,
-      "learning_rate": 7.04e-05,
-      "loss": 4.7693,
-      "step": 177
-    },
-    {
-      "epoch": 0.11187932118164676,
-      "grad_norm": 7.627071380615234,
-      "learning_rate": 7.08e-05,
-      "loss": 5.5354,
-      "step": 178
-    },
-    {
-      "epoch": 0.1125078566939032,
-      "grad_norm": 7.475245952606201,
-      "learning_rate": 7.12e-05,
-      "loss": 5.5916,
-      "step": 179
-    },
-    {
-      "epoch": 0.11313639220615965,
-      "grad_norm": 6.348559379577637,
-      "learning_rate": 7.16e-05,
-      "loss": 4.7914,
-      "step": 180
-    },
-    {
-      "epoch": 0.11376492771841609,
-      "grad_norm": 6.895409107208252,
-      "learning_rate": 7.2e-05,
-      "loss": 5.4136,
-      "step": 181
-    },
-    {
-      "epoch": 0.11439346323067254,
-      "grad_norm": 5.746918201446533,
-      "learning_rate": 7.24e-05,
-      "loss": 4.8071,
-      "step": 182
-    },
-    {
-      "epoch": 0.11502199874292897,
-      "grad_norm": 7.965058326721191,
-      "learning_rate": 7.280000000000001e-05,
-      "loss": 4.6486,
-      "step": 183
-    },
-    {
-      "epoch": 0.11565053425518541,
-      "grad_norm": 8.059706687927246,
-      "learning_rate": 7.32e-05,
-      "loss": 5.3917,
-      "step": 184
-    },
-    {
-      "epoch": 0.11627906976744186,
-      "grad_norm": 7.2255353927612305,
-      "learning_rate": 7.36e-05,
-      "loss": 5.0876,
-      "step": 185
-    },
-    {
-      "epoch": 0.1169076052796983,
-      "grad_norm": 6.53950834274292,
-      "learning_rate": 7.4e-05,
-      "loss": 4.7656,
-      "step": 186
-    },
-    {
-      "epoch": 0.11753614079195475,
-      "grad_norm": 6.379930019378662,
-      "learning_rate": 7.44e-05,
-      "loss": 4.6405,
-      "step": 187
-    },
-    {
-      "epoch": 0.1181646763042112,
-      "grad_norm": 7.332822322845459,
-      "learning_rate": 7.48e-05,
-      "loss": 4.6839,
-      "step": 188
-    },
-    {
-      "epoch": 0.11879321181646763,
-      "grad_norm": 7.975095272064209,
-      "learning_rate": 7.52e-05,
-      "loss": 4.8748,
-      "step": 189
-    },
-    {
-      "epoch": 0.11942174732872407,
-      "grad_norm": 7.8162360191345215,
-      "learning_rate": 7.560000000000001e-05,
-      "loss": 4.9994,
-      "step": 190
-    },
-    {
-      "epoch": 0.12005028284098052,
-      "grad_norm": 7.749350070953369,
-      "learning_rate": 7.6e-05,
-      "loss": 4.7996,
-      "step": 191
-    },
-    {
-      "epoch": 0.12067881835323696,
-      "grad_norm": 12.814620018005371,
-      "learning_rate": 7.64e-05,
-      "loss": 5.4858,
-      "step": 192
-    },
-    {
-      "epoch": 0.1213073538654934,
-      "grad_norm": 7.985275745391846,
-      "learning_rate": 7.680000000000001e-05,
-      "loss": 4.9178,
-      "step": 193
-    },
-    {
-      "epoch": 0.12193588937774984,
-      "grad_norm": 7.037015438079834,
-      "learning_rate": 7.72e-05,
-      "loss": 4.4436,
-      "step": 194
-    },
-    {
-      "epoch": 0.12256442489000628,
-      "grad_norm": 12.540748596191406,
-      "learning_rate": 7.76e-05,
-      "loss": 5.3947,
-      "step": 195
-    },
-    {
-      "epoch": 0.12319296040226273,
-      "grad_norm": 8.698318481445312,
-      "learning_rate": 7.800000000000001e-05,
-      "loss": 4.6521,
-      "step": 196
-    },
-    {
-      "epoch": 0.12382149591451917,
-      "grad_norm": 6.837226867675781,
-      "learning_rate": 7.840000000000001e-05,
-      "loss": 4.4502,
-      "step": 197
-    },
-    {
-      "epoch": 0.12445003142677562,
-      "grad_norm": 6.902530670166016,
-      "learning_rate": 7.88e-05,
-      "loss": 5.2111,
-      "step": 198
-    },
-    {
-      "epoch": 0.12507856693903205,
-      "grad_norm": 7.714503288269043,
-      "learning_rate": 7.920000000000001e-05,
-      "loss": 4.5983,
-      "step": 199
-    },
-    {
-      "epoch": 0.1257071024512885,
-      "grad_norm": 9.488588333129883,
-      "learning_rate": 7.960000000000001e-05,
-      "loss": 5.496,
-      "step": 200
-    },
-    {
-      "epoch": 0.12633563796354494,
-      "grad_norm": 9.41787052154541,
-      "learning_rate": 8e-05,
-      "loss": 4.8966,
-      "step": 201
-    },
-    {
-      "epoch": 0.12696417347580138,
-      "grad_norm": 7.63663911819458,
-      "learning_rate": 8.04e-05,
-      "loss": 4.6692,
-      "step": 202
-    },
-    {
-      "epoch": 0.12759270898805783,
-      "grad_norm": 8.535087585449219,
-      "learning_rate": 8.080000000000001e-05,
-      "loss": 5.0543,
-      "step": 203
-    },
-    {
-      "epoch": 0.12822124450031427,
-      "grad_norm": 8.822395324707031,
-      "learning_rate": 8.120000000000001e-05,
-      "loss": 4.7249,
-      "step": 204
-    },
-    {
-      "epoch": 0.12884978001257072,
-      "grad_norm": 7.7394561767578125,
-      "learning_rate": 8.16e-05,
-      "loss": 4.5474,
-      "step": 205
-    },
-    {
-      "epoch": 0.12947831552482716,
-      "grad_norm": 9.459196090698242,
-      "learning_rate": 8.2e-05,
-      "loss": 5.3748,
-      "step": 206
-    },
-    {
-      "epoch": 0.13010685103708358,
-      "grad_norm": 6.900613784790039,
-      "learning_rate": 8.24e-05,
-      "loss": 4.5716,
-      "step": 207
-    },
-    {
-      "epoch": 0.13073538654934003,
-      "grad_norm": 7.961105823516846,
-      "learning_rate": 8.28e-05,
-      "loss": 4.5067,
-      "step": 208
-    },
-    {
-      "epoch": 0.13136392206159647,
-      "grad_norm": 10.71306037902832,
-      "learning_rate": 8.32e-05,
-      "loss": 4.8309,
-      "step": 209
-    },
-    {
-      "epoch": 0.13199245757385292,
-      "grad_norm": 8.900117874145508,
-      "learning_rate": 8.36e-05,
-      "loss": 5.0913,
-      "step": 210
-    },
-    {
-      "epoch": 0.13262099308610936,
-      "grad_norm": 9.863144874572754,
-      "learning_rate": 8.4e-05,
-      "loss": 4.9469,
-      "step": 211
-    },
-    {
-      "epoch": 0.1332495285983658,
-      "grad_norm": 7.620909690856934,
-      "learning_rate": 8.44e-05,
-      "loss": 4.484,
-      "step": 212
-    },
-    {
-      "epoch": 0.13387806411062225,
-      "grad_norm": 10.667424201965332,
-      "learning_rate": 8.48e-05,
-      "loss": 5.1474,
-      "step": 213
-    },
-    {
-      "epoch": 0.1345065996228787,
-      "grad_norm": 11.249619483947754,
-      "learning_rate": 8.52e-05,
-      "loss": 4.6222,
-      "step": 214
-    },
-    {
-      "epoch": 0.13513513513513514,
-      "grad_norm": 8.625935554504395,
-      "learning_rate": 8.560000000000001e-05,
-      "loss": 4.4776,
-      "step": 215
-    },
-    {
-      "epoch": 0.1357636706473916,
-      "grad_norm": 8.138617515563965,
-      "learning_rate": 8.6e-05,
-      "loss": 4.7134,
-      "step": 216
-    },
-    {
-      "epoch": 0.13639220615964803,
-      "grad_norm": 7.485641956329346,
-      "learning_rate": 8.64e-05,
-      "loss": 4.8201,
-      "step": 217
-    },
-    {
-      "epoch": 0.13702074167190445,
-      "grad_norm": 11.87485408782959,
-      "learning_rate": 8.680000000000001e-05,
-      "loss": 4.7288,
-      "step": 218
-    },
-    {
-      "epoch": 0.1376492771841609,
-      "grad_norm": 8.551025390625,
-      "learning_rate": 8.72e-05,
-      "loss": 4.3091,
-      "step": 219
-    },
-    {
-      "epoch": 0.13827781269641734,
-      "grad_norm": 10.597816467285156,
-      "learning_rate": 8.76e-05,
-      "loss": 4.9491,
-      "step": 220
-    },
-    {
-      "epoch": 0.13890634820867379,
-      "grad_norm": 84.34934997558594,
-      "learning_rate": 8.800000000000001e-05,
-      "loss": 7.8641,
-      "step": 221
-    },
-    {
-      "epoch": 0.13953488372093023,
-      "grad_norm": 14.08538818359375,
-      "learning_rate": 8.840000000000001e-05,
-      "loss": 5.1718,
-      "step": 222
-    },
-    {
-      "epoch": 0.14016341923318668,
-      "grad_norm": 8.5634183883667,
-      "learning_rate": 8.88e-05,
-      "loss": 4.5042,
-      "step": 223
-    },
-    {
-      "epoch": 0.14079195474544312,
-      "grad_norm": 9.070499420166016,
-      "learning_rate": 8.92e-05,
-      "loss": 4.684,
-      "step": 224
-    },
-    {
-      "epoch": 0.14142049025769957,
-      "grad_norm": 13.369037628173828,
-      "learning_rate": 8.960000000000001e-05,
-      "loss": 4.2649,
-      "step": 225
-    },
-    {
-      "epoch": 0.142049025769956,
-      "grad_norm": 8.797863960266113,
-      "learning_rate": 9e-05,
-      "loss": 4.0673,
-      "step": 226
-    },
-    {
-      "epoch": 0.14267756128221246,
-      "grad_norm": 11.846273422241211,
-      "learning_rate": 9.04e-05,
-      "loss": 4.3157,
-      "step": 227
-    },
-    {
-      "epoch": 0.1433060967944689,
-      "grad_norm": 9.263139724731445,
-      "learning_rate": 9.080000000000001e-05,
-      "loss": 4.2926,
-      "step": 228
-    },
-    {
-      "epoch": 0.14393463230672532,
-      "grad_norm": 6.980598449707031,
-      "learning_rate": 9.120000000000001e-05,
-      "loss": 4.5284,
-      "step": 229
-    },
-    {
-      "epoch": 0.14456316781898176,
-      "grad_norm": 7.539294719696045,
-      "learning_rate": 9.16e-05,
-      "loss": 4.0574,
-      "step": 230
-    },
-    {
-      "epoch": 0.1451917033312382,
-      "grad_norm": 10.551584243774414,
-      "learning_rate": 9.200000000000001e-05,
-      "loss": 4.8214,
-      "step": 231
-    },
-    {
-      "epoch": 0.14582023884349465,
-      "grad_norm": 8.377208709716797,
-      "learning_rate": 9.240000000000001e-05,
-      "loss": 4.1492,
-      "step": 232
-    },
-    {
-      "epoch": 0.1464487743557511,
-      "grad_norm": 8.809621810913086,
-      "learning_rate": 9.28e-05,
-      "loss": 3.9481,
-      "step": 233
-    },
-    {
-      "epoch": 0.14707730986800754,
-      "grad_norm": 15.098812103271484,
-      "learning_rate": 9.320000000000002e-05,
-      "loss": 4.5192,
-      "step": 234
-    },
-    {
-      "epoch": 0.147705845380264,
-      "grad_norm": 16.269895553588867,
-      "learning_rate": 9.360000000000001e-05,
-      "loss": 4.5962,
-      "step": 235
-    },
-    {
-      "epoch": 0.14833438089252043,
-      "grad_norm": 9.021276473999023,
-      "learning_rate": 9.4e-05,
-      "loss": 4.6729,
-      "step": 236
-    },
-    {
-      "epoch": 0.14896291640477688,
-      "grad_norm": 10.110734939575195,
-      "learning_rate": 9.44e-05,
-      "loss": 4.5957,
-      "step": 237
-    },
-    {
-      "epoch": 0.14959145191703332,
-      "grad_norm": 10.254793167114258,
-      "learning_rate": 9.48e-05,
-      "loss": 4.1534,
-      "step": 238
-    },
-    {
-      "epoch": 0.15021998742928974,
-      "grad_norm": 10.400528907775879,
-      "learning_rate": 9.52e-05,
-      "loss": 4.5035,
-      "step": 239
-    },
-    {
-      "epoch": 0.1508485229415462,
-      "grad_norm": 13.529309272766113,
-      "learning_rate": 9.56e-05,
-      "loss": 4.7124,
-      "step": 240
-    },
-    {
-      "epoch": 0.15147705845380263,
-      "grad_norm": 9.187389373779297,
-      "learning_rate": 9.6e-05,
-      "loss": 4.2564,
-      "step": 241
-    },
-    {
-      "epoch": 0.15210559396605908,
-      "grad_norm": 9.760189056396484,
-      "learning_rate": 9.64e-05,
-      "loss": 4.5863,
-      "step": 242
-    },
-    {
-      "epoch": 0.15273412947831552,
-      "grad_norm": 11.033064842224121,
-      "learning_rate": 9.680000000000001e-05,
-      "loss": 4.4069,
-      "step": 243
-    },
-    {
-      "epoch": 0.15336266499057197,
-      "grad_norm": 8.79299259185791,
-      "learning_rate": 9.72e-05,
-      "loss": 4.2232,
-      "step": 244
-    },
-    {
-      "epoch": 0.1539912005028284,
-      "grad_norm": 10.526970863342285,
-      "learning_rate": 9.76e-05,
-      "loss": 4.6675,
-      "step": 245
-    },
-    {
-      "epoch": 0.15461973601508486,
-      "grad_norm": 14.993115425109863,
-      "learning_rate": 9.8e-05,
-      "loss": 4.3974,
-      "step": 246
-    },
-    {
-      "epoch": 0.1552482715273413,
-      "grad_norm": 8.852916717529297,
-      "learning_rate": 9.84e-05,
-      "loss": 4.1023,
-      "step": 247
-    },
-    {
-      "epoch": 0.15587680703959775,
-      "grad_norm": 17.305910110473633,
-      "learning_rate": 9.88e-05,
-      "loss": 4.2657,
-      "step": 248
-    },
-    {
-      "epoch": 0.1565053425518542,
-      "grad_norm": 12.877272605895996,
-      "learning_rate": 9.92e-05,
-      "loss": 4.318,
-      "step": 249
-    },
-    {
-      "epoch": 0.1571338780641106,
-      "grad_norm": 12.16046142578125,
-      "learning_rate": 9.960000000000001e-05,
-      "loss": 4.0387,
-      "step": 250
-    },
-    {
-      "epoch": 0.15776241357636706,
-      "grad_norm": 13.384797096252441,
-      "learning_rate": 0.0001,
-      "loss": 4.3935,
-      "step": 251
-    },
-    {
-      "epoch": 0.1583909490886235,
-      "grad_norm": 12.947620391845703,
-      "learning_rate": 0.0001004,
-      "loss": 4.2752,
-      "step": 252
-    },
-    {
-      "epoch": 0.15901948460087995,
-      "grad_norm": 13.004393577575684,
-      "learning_rate": 0.00010080000000000001,
-      "loss": 4.4285,
-      "step": 253
-    },
-    {
-      "epoch": 0.1596480201131364,
-      "grad_norm": 10.64500617980957,
-      "learning_rate": 0.00010120000000000001,
-      "loss": 4.3775,
-      "step": 254
-    },
-    {
-      "epoch": 0.16027655562539284,
-      "grad_norm": 10.208504676818848,
-      "learning_rate": 0.0001016,
-      "loss": 4.3942,
-      "step": 255
-    },
-    {
-      "epoch": 0.16090509113764928,
-      "grad_norm": 10.392770767211914,
-      "learning_rate": 0.00010200000000000001,
-      "loss": 3.964,
-      "step": 256
-    },
-    {
-      "epoch": 0.16153362664990573,
-      "grad_norm": 11.704667091369629,
-      "learning_rate": 0.00010240000000000001,
-      "loss": 3.2764,
-      "step": 257
-    },
-    {
-      "epoch": 0.16216216216216217,
-      "grad_norm": 11.466705322265625,
-      "learning_rate": 0.0001028,
-      "loss": 4.3286,
-      "step": 258
-    },
-    {
-      "epoch": 0.16279069767441862,
-      "grad_norm": 11.332155227661133,
-      "learning_rate": 0.0001032,
-      "loss": 4.4598,
-      "step": 259
-    },
-    {
-      "epoch": 0.16341923318667503,
-      "grad_norm": 10.597373962402344,
-      "learning_rate": 0.00010360000000000001,
-      "loss": 4.3576,
-      "step": 260
-    },
-    {
-      "epoch": 0.16404776869893148,
-      "grad_norm": 13.826549530029297,
-      "learning_rate": 0.00010400000000000001,
-      "loss": 4.1209,
-      "step": 261
-    },
-    {
-      "epoch": 0.16467630421118792,
-      "grad_norm": 12.812018394470215,
-      "learning_rate": 0.0001044,
-      "loss": 4.3951,
-      "step": 262
-    },
-    {
-      "epoch": 0.16530483972344437,
-      "grad_norm": 11.573945045471191,
-      "learning_rate": 0.00010480000000000001,
-      "loss": 4.6093,
-      "step": 263
-    },
-    {
-      "epoch": 0.16593337523570081,
-      "grad_norm": 9.195262908935547,
-      "learning_rate": 0.00010520000000000001,
-      "loss": 4.0342,
-      "step": 264
-    },
-    {
-      "epoch": 0.16656191074795726,
-      "grad_norm": 10.87674331665039,
-      "learning_rate": 0.0001056,
-      "loss": 3.9368,
-      "step": 265
-    },
-    {
-      "epoch": 0.1671904462602137,
-      "grad_norm": 11.914413452148438,
-      "learning_rate": 0.00010600000000000002,
-      "loss": 4.0043,
-      "step": 266
-    },
-    {
-      "epoch": 0.16781898177247015,
-      "grad_norm": 11.688831329345703,
-      "learning_rate": 0.00010640000000000001,
-      "loss": 3.6894,
-      "step": 267
-    },
-    {
-      "epoch": 0.1684475172847266,
-      "grad_norm": 17.798152923583984,
-      "learning_rate": 0.00010680000000000001,
-      "loss": 4.4073,
-      "step": 268
-    },
-    {
-      "epoch": 0.16907605279698304,
-      "grad_norm": 11.202817916870117,
-      "learning_rate": 0.00010720000000000002,
-      "loss": 3.9713,
-      "step": 269
-    },
-    {
-      "epoch": 0.16970458830923948,
-      "grad_norm": 11.484283447265625,
-      "learning_rate": 0.00010760000000000001,
-      "loss": 3.7401,
-      "step": 270
-    },
-    {
-      "epoch": 0.1703331238214959,
-      "grad_norm": 8.625189781188965,
-      "learning_rate": 0.00010800000000000001,
-      "loss": 3.6847,
-      "step": 271
-    },
-    {
-      "epoch": 0.17096165933375235,
-      "grad_norm": 14.114002227783203,
-      "learning_rate": 0.00010840000000000002,
-      "loss": 4.1115,
-      "step": 272
-    },
-    {
-      "epoch": 0.1715901948460088,
-      "grad_norm": 12.885270118713379,
-      "learning_rate": 0.00010880000000000002,
-      "loss": 3.5002,
-      "step": 273
-    },
-    {
-      "epoch": 0.17221873035826524,
-      "grad_norm": 13.46296501159668,
-      "learning_rate": 0.00010920000000000001,
-      "loss": 4.0249,
-      "step": 274
-    },
-    {
-      "epoch": 0.17284726587052168,
-      "grad_norm": 17.22674560546875,
-      "learning_rate": 0.00010960000000000001,
-      "loss": 4.4484,
-      "step": 275
-    },
-    {
-      "epoch": 0.17347580138277813,
-      "grad_norm": 13.292183876037598,
-      "learning_rate": 0.00011000000000000002,
-      "loss": 3.9718,
-      "step": 276
-    },
-    {
-      "epoch": 0.17410433689503457,
-      "grad_norm": 35.4398307800293,
-      "learning_rate": 0.00011040000000000001,
-      "loss": 4.0052,
-      "step": 277
-    },
-    {
-      "epoch": 0.17473287240729102,
-      "grad_norm": 19.460407257080078,
-      "learning_rate": 0.00011080000000000001,
-      "loss": 4.1892,
-      "step": 278
-    },
-    {
-      "epoch": 0.17536140791954746,
-      "grad_norm": 15.537309646606445,
-      "learning_rate": 0.00011120000000000002,
-      "loss": 3.9878,
-      "step": 279
-    },
-    {
-      "epoch": 0.1759899434318039,
-      "grad_norm": 16.156564712524414,
-      "learning_rate": 0.00011160000000000002,
-      "loss": 3.8753,
-      "step": 280
-    },
-    {
-      "epoch": 0.17661847894406035,
-      "grad_norm": 17.241336822509766,
-      "learning_rate": 0.00011200000000000001,
-      "loss": 3.9479,
-      "step": 281
-    },
-    {
-      "epoch": 0.17724701445631677,
-      "grad_norm": 20.027856826782227,
-      "learning_rate": 0.00011240000000000002,
-      "loss": 3.9856,
-      "step": 282
-    },
-    {
-      "epoch": 0.17787554996857322,
-      "grad_norm": 11.107442855834961,
-      "learning_rate": 0.00011279999999999999,
-      "loss": 3.5669,
-      "step": 283
-    },
-    {
-      "epoch": 0.17850408548082966,
-      "grad_norm": 14.415189743041992,
-      "learning_rate": 0.0001132,
-      "loss": 4.1763,
-      "step": 284
-    },
-    {
-      "epoch": 0.1791326209930861,
-      "grad_norm": 16.054901123046875,
-      "learning_rate": 0.0001136,
-      "loss": 4.1089,
-      "step": 285
-    },
-    {
-      "epoch": 0.17976115650534255,
-      "grad_norm": 17.718029022216797,
-      "learning_rate": 0.00011399999999999999,
-      "loss": 3.7917,
-      "step": 286
-    },
-    {
-      "epoch": 0.180389692017599,
-      "grad_norm": 15.520782470703125,
-      "learning_rate": 0.0001144,
-      "loss": 3.9876,
-      "step": 287
-    },
-    {
-      "epoch": 0.18101822752985544,
-      "grad_norm": 19.573312759399414,
-      "learning_rate": 0.0001148,
-      "loss": 3.9456,
-      "step": 288
-    },
-    {
-      "epoch": 0.1816467630421119,
-      "grad_norm": 11.45984935760498,
-      "learning_rate": 0.0001152,
-      "loss": 3.5074,
-      "step": 289
-    },
-    {
-      "epoch": 0.18227529855436833,
-      "grad_norm": 21.8663387298584,
-      "learning_rate": 0.00011559999999999999,
-      "loss": 4.0081,
-      "step": 290
-    },
-    {
-      "epoch": 0.18290383406662478,
-      "grad_norm": 16.874753952026367,
-      "learning_rate": 0.000116,
-      "loss": 3.9281,
-      "step": 291
-    },
-    {
-      "epoch": 0.1835323695788812,
-      "grad_norm": 16.98707389831543,
-      "learning_rate": 0.0001164,
-      "loss": 3.9644,
-      "step": 292
-    },
-    {
-      "epoch": 0.18416090509113764,
-      "grad_norm": 12.668580055236816,
-      "learning_rate": 0.00011679999999999999,
-      "loss": 3.3014,
-      "step": 293
-    },
-    {
-      "epoch": 0.18478944060339408,
-      "grad_norm": 11.530134201049805,
-      "learning_rate": 0.0001172,
-      "loss": 3.3005,
-      "step": 294
-    },
-    {
-      "epoch": 0.18541797611565053,
-      "grad_norm": 53.85222244262695,
-      "learning_rate": 0.0001176,
-      "loss": 4.4674,
-      "step": 295
-    },
-    {
-      "epoch": 0.18604651162790697,
-      "grad_norm": 12.703718185424805,
-      "learning_rate": 0.000118,
-      "loss": 3.629,
-      "step": 296
-    },
-    {
-      "epoch": 0.18667504714016342,
-      "grad_norm": 18.4884090423584,
-      "learning_rate": 0.0001184,
-      "loss": 3.7944,
-      "step": 297
-    },
-    {
-      "epoch": 0.18730358265241986,
-      "grad_norm": 18.730792999267578,
-      "learning_rate": 0.0001188,
-      "loss": 3.6521,
-      "step": 298
-    },
-    {
-      "epoch": 0.1879321181646763,
-      "grad_norm": 10.74968433380127,
-      "learning_rate": 0.0001192,
-      "loss": 3.6895,
-      "step": 299
-    },
-    {
-      "epoch": 0.18856065367693275,
-      "grad_norm": 13.541333198547363,
-      "learning_rate": 0.00011960000000000001,
-      "loss": 3.4517,
-      "step": 300
-    },
-    {
-      "epoch": 0.1891891891891892,
-      "grad_norm": 20.38814926147461,
-      "learning_rate": 0.00012,
-      "loss": 3.3987,
-      "step": 301
-    },
-    {
-      "epoch": 0.18981772470144564,
-      "grad_norm": 21.178226470947266,
-      "learning_rate": 0.0001204,
-      "loss": 3.6073,
-      "step": 302
-    },
-    {
-      "epoch": 0.19044626021370206,
-      "grad_norm": 11.370046615600586,
-      "learning_rate": 0.0001208,
-      "loss": 3.3391,
-      "step": 303
-    },
-    {
-      "epoch": 0.1910747957259585,
-      "grad_norm": 10.467302322387695,
-      "learning_rate": 0.0001212,
-      "loss": 3.7676,
-      "step": 304
-    },
-    {
-      "epoch": 0.19170333123821495,
-      "grad_norm": 11.307904243469238,
-      "learning_rate": 0.0001216,
-      "loss": 3.4048,
-      "step": 305
-    },
-    {
-      "epoch": 0.1923318667504714,
-      "grad_norm": 20.741159439086914,
-      "learning_rate": 0.000122,
-      "loss": 3.1971,
-      "step": 306
-    },
-    {
-      "epoch": 0.19296040226272784,
-      "grad_norm": 22.384532928466797,
-      "learning_rate": 0.0001224,
-      "loss": 3.2315,
-      "step": 307
-    },
-    {
-      "epoch": 0.1935889377749843,
-      "grad_norm": 19.073701858520508,
-      "learning_rate": 0.0001228,
-      "loss": 3.3426,
-      "step": 308
-    },
-    {
-      "epoch": 0.19421747328724073,
-      "grad_norm": 20.864418029785156,
-      "learning_rate": 0.0001232,
-      "loss": 3.4605,
-      "step": 309
-    },
-    {
-      "epoch": 0.19484600879949718,
-      "grad_norm": 15.888052940368652,
-      "learning_rate": 0.0001236,
-      "loss": 3.5554,
-      "step": 310
-    },
-    {
-      "epoch": 0.19547454431175362,
-      "grad_norm": 13.650964736938477,
-      "learning_rate": 0.000124,
-      "loss": 3.3372,
-      "step": 311
-    },
-    {
-      "epoch": 0.19610307982401007,
-      "grad_norm": 20.19765853881836,
-      "learning_rate": 0.00012440000000000002,
-      "loss": 3.4044,
-      "step": 312
-    },
-    {
-      "epoch": 0.19673161533626649,
-      "grad_norm": 18.977705001831055,
-      "learning_rate": 0.0001248,
-      "loss": 3.5597,
-      "step": 313
-    },
-    {
-      "epoch": 0.19736015084852293,
-      "grad_norm": 13.097780227661133,
-      "learning_rate": 0.0001252,
-      "loss": 3.2755,
-      "step": 314
-    },
-    {
-      "epoch": 0.19798868636077938,
-      "grad_norm": 17.84178924560547,
-      "learning_rate": 0.00012560000000000002,
-      "loss": 3.2663,
-      "step": 315
-    },
-    {
-      "epoch": 0.19861722187303582,
-      "grad_norm": 14.159675598144531,
-      "learning_rate": 0.000126,
-      "loss": 3.4946,
-      "step": 316
-    },
-    {
-      "epoch": 0.19924575738529227,
-      "grad_norm": 11.891308784484863,
-      "learning_rate": 0.0001264,
-      "loss": 2.8523,
-      "step": 317
-    },
-    {
-      "epoch": 0.1998742928975487,
-      "grad_norm": 15.97802734375,
-      "learning_rate": 0.00012680000000000002,
-      "loss": 3.2556,
-      "step": 318
-    },
-    {
-      "epoch": 0.20050282840980516,
-      "grad_norm": 13.670428276062012,
-      "learning_rate": 0.0001272,
-      "loss": 3.4079,
-      "step": 319
-    },
-    {
-      "epoch": 0.2011313639220616,
-      "grad_norm": 15.742596626281738,
-      "learning_rate": 0.0001276,
-      "loss": 3.358,
-      "step": 320
-    },
-    {
-      "epoch": 0.2011313639220616,
-      "eval_loss": 2.595961093902588,
-      "eval_runtime": 1561.7692,
-      "eval_samples_per_second": 1.651,
-      "eval_steps_per_second": 1.651,
-      "step": 320
-    },
-    {
-      "epoch": 0.20175989943431805,
-      "grad_norm": 18.516000747680664,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 3.4599,
-      "step": 321
-    },
-    {
-      "epoch": 0.2023884349465745,
-      "grad_norm": 12.767962455749512,
-      "learning_rate": 0.0001284,
-      "loss": 3.2328,
-      "step": 322
-    },
-    {
-      "epoch": 0.20301697045883094,
-      "grad_norm": 18.14620018005371,
-      "learning_rate": 0.00012880000000000001,
-      "loss": 3.5025,
-      "step": 323
-    },
-    {
-      "epoch": 0.20364550597108735,
-      "grad_norm": 16.109487533569336,
-      "learning_rate": 0.00012920000000000002,
-      "loss": 3.5465,
-      "step": 324
-    },
-    {
-      "epoch": 0.2042740414833438,
-      "grad_norm": 26.81826400756836,
-      "learning_rate": 0.0001296,
-      "loss": 3.7021,
-      "step": 325
-    },
-    {
-      "epoch": 0.20490257699560024,
-      "grad_norm": 18.376623153686523,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 3.3511,
-      "step": 326
-    },
-    {
-      "epoch": 0.2055311125078567,
-      "grad_norm": 16.065563201904297,
-      "learning_rate": 0.0001304,
-      "loss": 3.0496,
-      "step": 327
-    },
-    {
-      "epoch": 0.20615964802011313,
-      "grad_norm": 19.734437942504883,
-      "learning_rate": 0.0001308,
-      "loss": 3.3436,
-      "step": 328
-    },
-    {
-      "epoch": 0.20678818353236958,
-      "grad_norm": 15.109872817993164,
-      "learning_rate": 0.00013120000000000002,
-      "loss": 3.1295,
-      "step": 329
-    },
-    {
-      "epoch": 0.20741671904462602,
-      "grad_norm": 13.069215774536133,
-      "learning_rate": 0.0001316,
-      "loss": 3.018,
-      "step": 330
-    },
-    {
-      "epoch": 0.20804525455688247,
-      "grad_norm": 12.85176944732666,
-      "learning_rate": 0.000132,
-      "loss": 3.0171,
-      "step": 331
-    },
-    {
-      "epoch": 0.20867379006913891,
-      "grad_norm": 20.065465927124023,
-      "learning_rate": 0.00013240000000000002,
-      "loss": 3.1725,
-      "step": 332
-    },
-    {
-      "epoch": 0.20930232558139536,
-      "grad_norm": 17.447635650634766,
-      "learning_rate": 0.0001328,
-      "loss": 2.9863,
-      "step": 333
-    },
-    {
-      "epoch": 0.2099308610936518,
-      "grad_norm": 20.958803176879883,
-      "learning_rate": 0.0001332,
-      "loss": 3.236,
-      "step": 334
-    },
-    {
-      "epoch": 0.21055939660590822,
-      "grad_norm": 24.92554473876953,
-      "learning_rate": 0.00013360000000000002,
-      "loss": 2.9125,
-      "step": 335
-    },
-    {
-      "epoch": 0.21118793211816467,
-      "grad_norm": 12.4500150680542,
-      "learning_rate": 0.000134,
-      "loss": 2.4232,
-      "step": 336
-    },
-    {
-      "epoch": 0.2118164676304211,
-      "grad_norm": 19.983152389526367,
-      "learning_rate": 0.00013440000000000001,
-      "loss": 3.2391,
-      "step": 337
-    },
-    {
-      "epoch": 0.21244500314267756,
-      "grad_norm": 14.444880485534668,
-      "learning_rate": 0.00013480000000000002,
-      "loss": 2.8852,
-      "step": 338
-    },
-    {
-      "epoch": 0.213073538654934,
-      "grad_norm": 17.165590286254883,
-      "learning_rate": 0.0001352,
-      "loss": 3.2699,
-      "step": 339
-    },
-    {
-      "epoch": 0.21370207416719045,
-      "grad_norm": 16.150278091430664,
-      "learning_rate": 0.00013560000000000002,
-      "loss": 3.066,
-      "step": 340
-    },
-    {
-      "epoch": 0.2143306096794469,
-      "grad_norm": 27.125503540039062,
-      "learning_rate": 0.00013600000000000003,
-      "loss": 3.1006,
-      "step": 341
-    },
-    {
-      "epoch": 0.21495914519170334,
-      "grad_norm": 18.716642379760742,
-      "learning_rate": 0.0001364,
-      "loss": 2.9524,
-      "step": 342
-    },
-    {
-      "epoch": 0.21558768070395978,
-      "grad_norm": 14.65403938293457,
-      "learning_rate": 0.00013680000000000002,
-      "loss": 2.9555,
-      "step": 343
-    },
-    {
-      "epoch": 0.21621621621621623,
-      "grad_norm": 15.025317192077637,
-      "learning_rate": 0.00013720000000000003,
-      "loss": 2.7592,
-      "step": 344
-    },
-    {
-      "epoch": 0.21684475172847265,
-      "grad_norm": 23.24863052368164,
-      "learning_rate": 0.00013759999999999998,
-      "loss": 3.2544,
-      "step": 345
-    },
-    {
-      "epoch": 0.2174732872407291,
-      "grad_norm": 14.683283805847168,
-      "learning_rate": 0.000138,
-      "loss": 3.1798,
-      "step": 346
-    },
-    {
-      "epoch": 0.21810182275298554,
-      "grad_norm": 19.991384506225586,
-      "learning_rate": 0.0001384,
-      "loss": 3.0177,
-      "step": 347
-    },
-    {
-      "epoch": 0.21873035826524198,
-      "grad_norm": 20.53168296813965,
-      "learning_rate": 0.00013879999999999999,
-      "loss": 3.182,
-      "step": 348
-    },
-    {
-      "epoch": 0.21935889377749843,
-      "grad_norm": 23.478450775146484,
-      "learning_rate": 0.0001392,
-      "loss": 3.268,
-      "step": 349
-    },
-    {
-      "epoch": 0.21998742928975487,
-      "grad_norm": 15.088510513305664,
-      "learning_rate": 0.0001396,
-      "loss": 2.7058,
-      "step": 350
-    },
-    {
-      "epoch": 0.22061596480201132,
-      "grad_norm": 16.69074821472168,
-      "learning_rate": 0.00014,
-      "loss": 2.9989,
-      "step": 351
-    },
-    {
-      "epoch": 0.22124450031426776,
-      "grad_norm": 24.132953643798828,
-      "learning_rate": 0.0001404,
-      "loss": 2.8016,
-      "step": 352
-    },
-    {
-      "epoch": 0.2218730358265242,
-      "grad_norm": 13.829506874084473,
-      "learning_rate": 0.0001408,
-      "loss": 2.9762,
-      "step": 353
-    },
-    {
-      "epoch": 0.22250157133878065,
-      "grad_norm": 11.858349800109863,
-      "learning_rate": 0.0001412,
-      "loss": 3.0663,
-      "step": 354
-    },
-    {
-      "epoch": 0.2231301068510371,
-      "grad_norm": 17.9423885345459,
-      "learning_rate": 0.0001416,
-      "loss": 3.0817,
-      "step": 355
-    },
-    {
-      "epoch": 0.22375864236329351,
-      "grad_norm": 17.859312057495117,
-      "learning_rate": 0.000142,
-      "loss": 3.2717,
-      "step": 356
-    },
-    {
-      "epoch": 0.22438717787554996,
-      "grad_norm": 24.465381622314453,
-      "learning_rate": 0.0001424,
-      "loss": 3.0278,
-      "step": 357
-    },
-    {
-      "epoch": 0.2250157133878064,
-      "grad_norm": 31.655973434448242,
-      "learning_rate": 0.0001428,
-      "loss": 2.5686,
-      "step": 358
-    },
-    {
-      "epoch": 0.22564424890006285,
-      "grad_norm": 23.032289505004883,
-      "learning_rate": 0.0001432,
-      "loss": 2.8256,
-      "step": 359
-    },
-    {
-      "epoch": 0.2262727844123193,
-      "grad_norm": 9.913031578063965,
-      "learning_rate": 0.0001436,
-      "loss": 2.6509,
-      "step": 360
-    },
-    {
-      "epoch": 0.22690131992457574,
-      "grad_norm": 14.368906021118164,
-      "learning_rate": 0.000144,
-      "loss": 2.7751,
-      "step": 361
-    },
-    {
-      "epoch": 0.22752985543683218,
-      "grad_norm": 14.559577941894531,
-      "learning_rate": 0.0001444,
-      "loss": 2.7144,
-      "step": 362
-    },
-    {
-      "epoch": 0.22815839094908863,
-      "grad_norm": 11.854909896850586,
-      "learning_rate": 0.0001448,
-      "loss": 2.6202,
-      "step": 363
-    },
-    {
-      "epoch": 0.22878692646134507,
-      "grad_norm": 15.724352836608887,
-      "learning_rate": 0.0001452,
-      "loss": 2.9942,
-      "step": 364
-    },
-    {
-      "epoch": 0.22941546197360152,
-      "grad_norm": 18.073122024536133,
-      "learning_rate": 0.00014560000000000002,
-      "loss": 2.7307,
-      "step": 365
-    },
-    {
-      "epoch": 0.23004399748585794,
-      "grad_norm": 13.995152473449707,
-      "learning_rate": 0.000146,
-      "loss": 2.5305,
-      "step": 366
-    },
-    {
-      "epoch": 0.23067253299811438,
-      "grad_norm": 24.081336975097656,
-      "learning_rate": 0.0001464,
-      "loss": 2.9235,
-      "step": 367
-    },
-    {
-      "epoch": 0.23130106851037083,
-      "grad_norm": 15.185482025146484,
-      "learning_rate": 0.00014680000000000002,
-      "loss": 2.8097,
-      "step": 368
-    },
-    {
-      "epoch": 0.23192960402262727,
-      "grad_norm": 17.898988723754883,
-      "learning_rate": 0.0001472,
-      "loss": 2.7808,
-      "step": 369
-    },
-    {
-      "epoch": 0.23255813953488372,
-      "grad_norm": 11.116854667663574,
-      "learning_rate": 0.0001476,
-      "loss": 2.9811,
-      "step": 370
-    },
-    {
-      "epoch": 0.23318667504714016,
-      "grad_norm": 16.254613876342773,
-      "learning_rate": 0.000148,
-      "loss": 2.6689,
-      "step": 371
-    },
-    {
-      "epoch": 0.2338152105593966,
-      "grad_norm": 15.59523868560791,
-      "learning_rate": 0.0001484,
-      "loss": 2.6041,
-      "step": 372
-    },
-    {
-      "epoch": 0.23444374607165305,
-      "grad_norm": 12.621963500976562,
-      "learning_rate": 0.0001488,
-      "loss": 2.889,
-      "step": 373
-    },
-    {
-      "epoch": 0.2350722815839095,
-      "grad_norm": 21.332027435302734,
-      "learning_rate": 0.0001492,
-      "loss": 2.6854,
-      "step": 374
-    },
-    {
-      "epoch": 0.23570081709616594,
-      "grad_norm": 25.096506118774414,
-      "learning_rate": 0.0001496,
-      "loss": 3.0866,
-      "step": 375
-    },
-    {
-      "epoch": 0.2363293526084224,
-      "grad_norm": 21.07834815979004,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 2.8421,
-      "step": 376
-    },
-    {
-      "epoch": 0.2369578881206788,
-      "grad_norm": 56.05162048339844,
-      "learning_rate": 0.0001504,
-      "loss": 2.8167,
-      "step": 377
-    },
-    {
-      "epoch": 0.23758642363293525,
-      "grad_norm": 33.98356246948242,
-      "learning_rate": 0.0001508,
-      "loss": 2.9985,
-      "step": 378
-    },
-    {
-      "epoch": 0.2382149591451917,
-      "grad_norm": 31.202903747558594,
-      "learning_rate": 0.00015120000000000002,
-      "loss": 2.3907,
-      "step": 379
-    },
-    {
-      "epoch": 0.23884349465744814,
-      "grad_norm": 12.752126693725586,
-      "learning_rate": 0.0001516,
-      "loss": 2.4548,
-      "step": 380
-    },
-    {
-      "epoch": 0.23947203016970459,
-      "grad_norm": 18.89848518371582,
-      "learning_rate": 0.000152,
-      "loss": 2.5799,
-      "step": 381
-    },
-    {
-      "epoch": 0.24010056568196103,
-      "grad_norm": 12.335553169250488,
-      "learning_rate": 0.00015240000000000002,
-      "loss": 2.4312,
-      "step": 382
-    },
-    {
-      "epoch": 0.24072910119421748,
-      "grad_norm": 14.589320182800293,
-      "learning_rate": 0.0001528,
-      "loss": 2.7752,
-      "step": 383
-    },
-    {
-      "epoch": 0.24135763670647392,
-      "grad_norm": 19.386524200439453,
-      "learning_rate": 0.0001532,
-      "loss": 2.6769,
-      "step": 384
-    },
-    {
-      "epoch": 0.24198617221873037,
-      "grad_norm": 11.126659393310547,
-      "learning_rate": 0.00015360000000000002,
-      "loss": 2.6094,
-      "step": 385
-    },
-    {
-      "epoch": 0.2426147077309868,
-      "grad_norm": 12.37399673461914,
-      "learning_rate": 0.000154,
-      "loss": 2.4149,
-      "step": 386
-    },
-    {
-      "epoch": 0.24324324324324326,
-      "grad_norm": 9.323434829711914,
-      "learning_rate": 0.0001544,
-      "loss": 2.6124,
-      "step": 387
-    },
-    {
-      "epoch": 0.24387177875549967,
-      "grad_norm": 15.187394142150879,
-      "learning_rate": 0.00015480000000000002,
-      "loss": 2.2974,
-      "step": 388
-    },
-    {
-      "epoch": 0.24450031426775612,
-      "grad_norm": 14.098670959472656,
-      "learning_rate": 0.0001552,
-      "loss": 2.5228,
-      "step": 389
-    },
-    {
-      "epoch": 0.24512884978001256,
-      "grad_norm": 22.275894165039062,
-      "learning_rate": 0.00015560000000000001,
-      "loss": 2.5581,
-      "step": 390
-    },
-    {
-      "epoch": 0.245757385292269,
-      "grad_norm": 23.715696334838867,
-      "learning_rate": 0.00015600000000000002,
-      "loss": 2.5637,
-      "step": 391
-    },
-    {
-      "epoch": 0.24638592080452545,
-      "grad_norm": 12.024730682373047,
-      "learning_rate": 0.0001564,
-      "loss": 2.6799,
-      "step": 392
-    },
-    {
-      "epoch": 0.2470144563167819,
-      "grad_norm": 128.14434814453125,
-      "learning_rate": 0.00015680000000000002,
-      "loss": 4.7508,
-      "step": 393
-    },
-    {
-      "epoch": 0.24764299182903834,
-      "grad_norm": 9.767908096313477,
-      "learning_rate": 0.00015720000000000003,
-      "loss": 2.8455,
-      "step": 394
-    },
-    {
-      "epoch": 0.2482715273412948,
-      "grad_norm": 14.82866382598877,
-      "learning_rate": 0.0001576,
-      "loss": 2.7026,
-      "step": 395
-    },
-    {
-      "epoch": 0.24890006285355123,
-      "grad_norm": 17.91452407836914,
-      "learning_rate": 0.00015800000000000002,
-      "loss": 2.3927,
-      "step": 396
-    },
-    {
-      "epoch": 0.24952859836580768,
-      "grad_norm": 9.49526596069336,
-      "learning_rate": 0.00015840000000000003,
-      "loss": 2.3653,
-      "step": 397
-    },
-    {
-      "epoch": 0.2501571338780641,
-      "grad_norm": 11.44519329071045,
-      "learning_rate": 0.0001588,
-      "loss": 2.7203,
-      "step": 398
-    },
-    {
-      "epoch": 0.25078566939032054,
-      "grad_norm": 11.376216888427734,
-      "learning_rate": 0.00015920000000000002,
-      "loss": 2.5542,
-      "step": 399
-    },
-    {
-      "epoch": 0.251414204902577,
-      "grad_norm": 18.18035888671875,
-      "learning_rate": 0.0001596,
-      "loss": 2.6502,
-      "step": 400
-    },
-    {
-      "epoch": 0.25204274041483343,
-      "grad_norm": 12.473836898803711,
-      "learning_rate": 0.00016,
-      "loss": 2.1878,
-      "step": 401
-    },
-    {
-      "epoch": 0.2526712759270899,
-      "grad_norm": 13.397380828857422,
-      "learning_rate": 0.00016040000000000002,
-      "loss": 2.384,
-      "step": 402
-    },
-    {
-      "epoch": 0.2532998114393463,
-      "grad_norm": 14.128639221191406,
-      "learning_rate": 0.0001608,
-      "loss": 2.4143,
-      "step": 403
-    },
-    {
-      "epoch": 0.25392834695160277,
-      "grad_norm": 14.258450508117676,
-      "learning_rate": 0.00016120000000000002,
-      "loss": 2.4701,
-      "step": 404
-    },
-    {
-      "epoch": 0.2545568824638592,
-      "grad_norm": 13.462814331054688,
-      "learning_rate": 0.00016160000000000002,
-      "loss": 2.3382,
-      "step": 405
-    },
-    {
-      "epoch": 0.25518541797611566,
-      "grad_norm": 9.772506713867188,
-      "learning_rate": 0.000162,
-      "loss": 2.5515,
-      "step": 406
-    },
-    {
-      "epoch": 0.2558139534883721,
-      "grad_norm": 15.334366798400879,
-      "learning_rate": 0.00016240000000000002,
-      "loss": 2.4442,
-      "step": 407
-    },
-    {
-      "epoch": 0.25644248900062855,
-      "grad_norm": 8.635390281677246,
-      "learning_rate": 0.0001628,
-      "loss": 2.3196,
-      "step": 408
-    },
-    {
-      "epoch": 0.257071024512885,
-      "grad_norm": 10.05532455444336,
-      "learning_rate": 0.0001632,
-      "loss": 2.3188,
-      "step": 409
-    },
-    {
-      "epoch": 0.25769956002514144,
-      "grad_norm": 9.961398124694824,
-      "learning_rate": 0.0001636,
-      "loss": 2.6808,
-      "step": 410
-    },
-    {
-      "epoch": 0.2583280955373979,
-      "grad_norm": 12.767550468444824,
-      "learning_rate": 0.000164,
-      "loss": 2.3732,
-      "step": 411
-    },
-    {
-      "epoch": 0.25895663104965433,
-      "grad_norm": 9.951260566711426,
-      "learning_rate": 0.0001644,
-      "loss": 2.4287,
-      "step": 412
-    },
-    {
-      "epoch": 0.2595851665619108,
-      "grad_norm": 11.40839958190918,
-      "learning_rate": 0.0001648,
-      "loss": 2.1428,
-      "step": 413
-    },
-    {
-      "epoch": 0.26021370207416716,
-      "grad_norm": 13.8335542678833,
-      "learning_rate": 0.0001652,
-      "loss": 2.4355,
-      "step": 414
-    },
-    {
-      "epoch": 0.2608422375864236,
-      "grad_norm": 14.79465389251709,
-      "learning_rate": 0.0001656,
-      "loss": 2.6137,
-      "step": 415
-    },
-    {
-      "epoch": 0.26147077309868005,
-      "grad_norm": 12.087128639221191,
-      "learning_rate": 0.000166,
-      "loss": 2.5661,
-      "step": 416
-    },
-    {
-      "epoch": 0.2620993086109365,
-      "grad_norm": 66.9678726196289,
-      "learning_rate": 0.0001664,
-      "loss": 2.905,
-      "step": 417
-    },
-    {
-      "epoch": 0.26272784412319294,
-      "grad_norm": 36.95875549316406,
-      "learning_rate": 0.0001668,
-      "loss": 2.5886,
-      "step": 418
-    },
-    {
-      "epoch": 0.2633563796354494,
-      "grad_norm": 16.434181213378906,
-      "learning_rate": 0.0001672,
-      "loss": 2.4761,
-      "step": 419
-    },
-    {
-      "epoch": 0.26398491514770583,
-      "grad_norm": 17.993885040283203,
-      "learning_rate": 0.0001676,
-      "loss": 2.5257,
-      "step": 420
-    },
-    {
-      "epoch": 0.2646134506599623,
-      "grad_norm": 15.398675918579102,
-      "learning_rate": 0.000168,
-      "loss": 2.3469,
-      "step": 421
-    },
-    {
-      "epoch": 0.2652419861722187,
-      "grad_norm": 15.613100051879883,
-      "learning_rate": 0.0001684,
-      "loss": 2.614,
-      "step": 422
-    },
-    {
-      "epoch": 0.26587052168447517,
-      "grad_norm": 14.203115463256836,
-      "learning_rate": 0.0001688,
-      "loss": 2.5969,
-      "step": 423
-    },
-    {
-      "epoch": 0.2664990571967316,
-      "grad_norm": 18.7460880279541,
-      "learning_rate": 0.0001692,
-      "loss": 2.6752,
-      "step": 424
-    },
-    {
-      "epoch": 0.26712759270898806,
-      "grad_norm": 15.008576393127441,
-      "learning_rate": 0.0001696,
-      "loss": 2.3482,
-      "step": 425
-    },
-    {
-      "epoch": 0.2677561282212445,
-      "grad_norm": 12.07258415222168,
-      "learning_rate": 0.00017,
-      "loss": 2.0798,
-      "step": 426
-    },
-    {
-      "epoch": 0.26838466373350095,
-      "grad_norm": 25.918943405151367,
-      "learning_rate": 0.0001704,
-      "loss": 2.4682,
-      "step": 427
-    },
-    {
-      "epoch": 0.2690131992457574,
-      "grad_norm": 6.374201774597168,
-      "learning_rate": 0.0001708,
-      "loss": 2.3433,
-      "step": 428
-    },
-    {
-      "epoch": 0.26964173475801384,
-      "grad_norm": 13.480561256408691,
-      "learning_rate": 0.00017120000000000001,
-      "loss": 2.1633,
-      "step": 429
-    },
-    {
-      "epoch": 0.2702702702702703,
-      "grad_norm": 19.05206871032715,
-      "learning_rate": 0.0001716,
-      "loss": 2.5378,
-      "step": 430
-    },
-    {
-      "epoch": 0.27089880578252673,
-      "grad_norm": 28.43244743347168,
-      "learning_rate": 0.000172,
-      "loss": 2.4796,
-      "step": 431
-    },
-    {
-      "epoch": 0.2715273412947832,
-      "grad_norm": 19.896743774414062,
-      "learning_rate": 0.00017240000000000002,
-      "loss": 2.169,
-      "step": 432
-    },
-    {
-      "epoch": 0.2721558768070396,
-      "grad_norm": 31.176748275756836,
-      "learning_rate": 0.0001728,
-      "loss": 2.1738,
-      "step": 433
-    },
-    {
-      "epoch": 0.27278441231929607,
-      "grad_norm": 5.707266330718994,
-      "learning_rate": 0.0001732,
-      "loss": 2.1389,
-      "step": 434
-    },
-    {
-      "epoch": 0.27341294783155246,
-      "grad_norm": 19.774263381958008,
-      "learning_rate": 0.00017360000000000002,
-      "loss": 2.6666,
-      "step": 435
-    },
-    {
-      "epoch": 0.2740414833438089,
-      "grad_norm": 19.493816375732422,
-      "learning_rate": 0.000174,
-      "loss": 2.2989,
-      "step": 436
-    },
-    {
-      "epoch": 0.27467001885606535,
-      "grad_norm": 16.929563522338867,
-      "learning_rate": 0.0001744,
-      "loss": 2.3341,
-      "step": 437
-    },
-    {
-      "epoch": 0.2752985543683218,
-      "grad_norm": 9.590645790100098,
-      "learning_rate": 0.00017480000000000002,
-      "loss": 2.5236,
-      "step": 438
-    },
-    {
-      "epoch": 0.27592708988057824,
-      "grad_norm": 7.97600793838501,
-      "learning_rate": 0.0001752,
-      "loss": 2.2307,
-      "step": 439
-    },
-    {
-      "epoch": 0.2765556253928347,
-      "grad_norm": 7.129279613494873,
-      "learning_rate": 0.0001756,
-      "loss": 2.4411,
-      "step": 440
-    },
-    {
-      "epoch": 0.2771841609050911,
-      "grad_norm": 9.409801483154297,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 2.3803,
-      "step": 441
-    },
-    {
-      "epoch": 0.27781269641734757,
-      "grad_norm": 6.196171283721924,
-      "learning_rate": 0.0001764,
-      "loss": 2.5736,
-      "step": 442
-    },
-    {
-      "epoch": 0.278441231929604,
-      "grad_norm": 9.682530403137207,
-      "learning_rate": 0.00017680000000000001,
-      "loss": 2.1353,
-      "step": 443
-    },
-    {
-      "epoch": 0.27906976744186046,
-      "grad_norm": 20.320688247680664,
-      "learning_rate": 0.0001772,
-      "loss": 2.2107,
-      "step": 444
-    },
-    {
-      "epoch": 0.2796983029541169,
-      "grad_norm": 20.578222274780273,
-      "learning_rate": 0.0001776,
-      "loss": 2.0656,
-      "step": 445
-    },
-    {
-      "epoch": 0.28032683846637335,
-      "grad_norm": 33.76546859741211,
-      "learning_rate": 0.00017800000000000002,
-      "loss": 2.2221,
-      "step": 446
-    },
-    {
-      "epoch": 0.2809553739786298,
-      "grad_norm": 9.561470985412598,
-      "learning_rate": 0.0001784,
-      "loss": 2.5248,
-      "step": 447
-    },
-    {
-      "epoch": 0.28158390949088624,
-      "grad_norm": 15.284167289733887,
-      "learning_rate": 0.0001788,
-      "loss": 2.1954,
-      "step": 448
-    },
-    {
-      "epoch": 0.2822124450031427,
-      "grad_norm": 27.233264923095703,
-      "learning_rate": 0.00017920000000000002,
-      "loss": 2.1467,
-      "step": 449
-    },
-    {
-      "epoch": 0.28284098051539913,
-      "grad_norm": 8.692459106445312,
-      "learning_rate": 0.0001796,
-      "loss": 2.4224,
-      "step": 450
-    },
-    {
-      "epoch": 0.2834695160276556,
-      "grad_norm": 23.0391845703125,
-      "learning_rate": 0.00018,
-      "loss": 2.3062,
-      "step": 451
-    },
-    {
-      "epoch": 0.284098051539912,
-      "grad_norm": 33.97864532470703,
-      "learning_rate": 0.00018040000000000002,
-      "loss": 2.5164,
-      "step": 452
-    },
-    {
-      "epoch": 0.28472658705216847,
-      "grad_norm": 7.73515510559082,
-      "learning_rate": 0.0001808,
-      "loss": 2.3682,
-      "step": 453
-    },
-    {
-      "epoch": 0.2853551225644249,
-      "grad_norm": 10.368907928466797,
-      "learning_rate": 0.0001812,
-      "loss": 2.1135,
-      "step": 454
-    },
-    {
-      "epoch": 0.28598365807668136,
-      "grad_norm": 9.352826118469238,
-      "learning_rate": 0.00018160000000000002,
-      "loss": 2.1376,
-      "step": 455
-    },
-    {
-      "epoch": 0.2866121935889378,
-      "grad_norm": 226.2757110595703,
-      "learning_rate": 0.000182,
-      "loss": 4.9444,
-      "step": 456
-    },
-    {
-      "epoch": 0.2872407291011942,
-      "grad_norm": 14.291020393371582,
-      "learning_rate": 0.00018240000000000002,
-      "loss": 2.2792,
-      "step": 457
-    },
-    {
-      "epoch": 0.28786926461345064,
-      "grad_norm": 14.201563835144043,
-      "learning_rate": 0.00018280000000000003,
-      "loss": 1.9881,
-      "step": 458
-    },
-    {
-      "epoch": 0.2884978001257071,
-      "grad_norm": 6.268864154815674,
-      "learning_rate": 0.0001832,
-      "loss": 2.2419,
-      "step": 459
-    },
-    {
-      "epoch": 0.2891263356379635,
-      "grad_norm": 7.990386486053467,
-      "learning_rate": 0.00018360000000000002,
-      "loss": 2.1261,
-      "step": 460
-    },
-    {
-      "epoch": 0.28975487115022,
-      "grad_norm": 12.354260444641113,
-      "learning_rate": 0.00018400000000000003,
-      "loss": 1.8171,
-      "step": 461
-    },
-    {
-      "epoch": 0.2903834066624764,
-      "grad_norm": 8.037335395812988,
-      "learning_rate": 0.0001844,
-      "loss": 2.1203,
-      "step": 462
-    },
-    {
-      "epoch": 0.29101194217473286,
-      "grad_norm": 12.988319396972656,
-      "learning_rate": 0.00018480000000000002,
-      "loss": 2.0204,
-      "step": 463
-    },
-    {
-      "epoch": 0.2916404776869893,
-      "grad_norm": 21.61684799194336,
-      "learning_rate": 0.00018520000000000003,
-      "loss": 2.3283,
-      "step": 464
-    },
-    {
-      "epoch": 0.29226901319924575,
-      "grad_norm": 33.48648452758789,
-      "learning_rate": 0.0001856,
-      "loss": 2.4362,
-      "step": 465
-    },
-    {
-      "epoch": 0.2928975487115022,
-      "grad_norm": 24.978181838989258,
-      "learning_rate": 0.00018600000000000002,
-      "loss": 1.9866,
-      "step": 466
-    },
-    {
-      "epoch": 0.29352608422375864,
-      "grad_norm": 12.113028526306152,
-      "learning_rate": 0.00018640000000000003,
-      "loss": 2.1763,
-      "step": 467
-    },
-    {
-      "epoch": 0.2941546197360151,
-      "grad_norm": 15.348548889160156,
-      "learning_rate": 0.00018680000000000001,
-      "loss": 2.4879,
-      "step": 468
-    },
-    {
-      "epoch": 0.29478315524827153,
-      "grad_norm": 7.841541767120361,
-      "learning_rate": 0.00018720000000000002,
-      "loss": 2.469,
-      "step": 469
-    },
-    {
-      "epoch": 0.295411690760528,
-      "grad_norm": 9.705923080444336,
-      "learning_rate": 0.0001876,
-      "loss": 2.3946,
-      "step": 470
-    },
-    {
-      "epoch": 0.2960402262727844,
-      "grad_norm": 13.874395370483398,
-      "learning_rate": 0.000188,
-      "loss": 1.9966,
-      "step": 471
-    },
-    {
-      "epoch": 0.29666876178504087,
-      "grad_norm": 14.510929107666016,
-      "learning_rate": 0.0001884,
-      "loss": 1.9661,
-      "step": 472
-    },
-    {
-      "epoch": 0.2972972972972973,
-      "grad_norm": 9.351888656616211,
-      "learning_rate": 0.0001888,
-      "loss": 2.2073,
-      "step": 473
-    },
-    {
-      "epoch": 0.29792583280955376,
-      "grad_norm": 9.50893783569336,
-      "learning_rate": 0.0001892,
-      "loss": 2.2,
-      "step": 474
-    },
-    {
-      "epoch": 0.2985543683218102,
-      "grad_norm": 6.685521602630615,
-      "learning_rate": 0.0001896,
-      "loss": 2.3768,
-      "step": 475
-    },
-    {
-      "epoch": 0.29918290383406665,
-      "grad_norm": 43.20718002319336,
-      "learning_rate": 0.00019,
-      "loss": 2.1069,
-      "step": 476
-    },
-    {
-      "epoch": 0.2998114393463231,
-      "grad_norm": 13.695243835449219,
-      "learning_rate": 0.0001904,
-      "loss": 2.1093,
-      "step": 477
-    },
-    {
-      "epoch": 0.3004399748585795,
-      "grad_norm": 10.47667121887207,
-      "learning_rate": 0.0001908,
-      "loss": 2.0928,
-      "step": 478
-    },
-    {
-      "epoch": 0.30106851037083593,
-      "grad_norm": 28.000720977783203,
-      "learning_rate": 0.0001912,
-      "loss": 1.949,
-      "step": 479
-    },
-    {
-      "epoch": 0.3016970458830924,
-      "grad_norm": 6.865454196929932,
-      "learning_rate": 0.0001916,
-      "loss": 1.809,
-      "step": 480
-    },
-    {
-      "epoch": 0.3016970458830924,
-      "eval_loss": 1.3915096521377563,
-      "eval_runtime": 1572.1918,
-      "eval_samples_per_second": 1.64,
-      "eval_steps_per_second": 1.64,
-      "step": 480
-    },
-    {
-      "epoch": 0.3023255813953488,
-      "grad_norm": 5.930575847625732,
-      "learning_rate": 0.000192,
-      "loss": 2.1386,
-      "step": 481
-    },
-    {
-      "epoch": 0.30295411690760526,
-      "grad_norm": 7.512749671936035,
-      "learning_rate": 0.00019240000000000001,
-      "loss": 2.3738,
-      "step": 482
-    },
-    {
-      "epoch": 0.3035826524198617,
-      "grad_norm": 10.778457641601562,
-      "learning_rate": 0.0001928,
-      "loss": 1.9493,
-      "step": 483
-    },
-    {
-      "epoch": 0.30421118793211815,
-      "grad_norm": 12.165234565734863,
-      "learning_rate": 0.0001932,
-      "loss": 2.1425,
-      "step": 484
-    },
-    {
-      "epoch": 0.3048397234443746,
-      "grad_norm": 6.66940450668335,
-      "learning_rate": 0.00019360000000000002,
-      "loss": 2.2216,
-      "step": 485
-    },
-    {
-      "epoch": 0.30546825895663104,
-      "grad_norm": 10.975049018859863,
-      "learning_rate": 0.000194,
-      "loss": 2.3318,
-      "step": 486
-    },
-    {
-      "epoch": 0.3060967944688875,
-      "grad_norm": 7.881476402282715,
-      "learning_rate": 0.0001944,
-      "loss": 2.3984,
-      "step": 487
-    },
-    {
-      "epoch": 0.30672532998114393,
-      "grad_norm": 7.184864044189453,
-      "learning_rate": 0.0001948,
-      "loss": 1.9152,
-      "step": 488
-    },
-    {
-      "epoch": 0.3073538654934004,
-      "grad_norm": 8.655898094177246,
-      "learning_rate": 0.0001952,
-      "loss": 2.0512,
-      "step": 489
-    },
-    {
-      "epoch": 0.3079824010056568,
-      "grad_norm": 9.263758659362793,
-      "learning_rate": 0.0001956,
-      "loss": 2.0096,
-      "step": 490
-    },
-    {
-      "epoch": 0.30861093651791327,
-      "grad_norm": 5.204033374786377,
-      "learning_rate": 0.000196,
-      "loss": 2.3024,
-      "step": 491
-    },
-    {
-      "epoch": 0.3092394720301697,
-      "grad_norm": 10.690205574035645,
-      "learning_rate": 0.0001964,
-      "loss": 2.2217,
-      "step": 492
-    },
-    {
-      "epoch": 0.30986800754242616,
-      "grad_norm": 9.402382850646973,
-      "learning_rate": 0.0001968,
-      "loss": 2.0444,
-      "step": 493
-    },
-    {
-      "epoch": 0.3104965430546826,
-      "grad_norm": 28.077444076538086,
-      "learning_rate": 0.0001972,
-      "loss": 2.3741,
-      "step": 494
-    },
-    {
-      "epoch": 0.31112507856693905,
-      "grad_norm": 13.81711483001709,
-      "learning_rate": 0.0001976,
-      "loss": 1.6765,
-      "step": 495
-    },
-    {
-      "epoch": 0.3117536140791955,
-      "grad_norm": 10.126565933227539,
-      "learning_rate": 0.00019800000000000002,
-      "loss": 2.1858,
-      "step": 496
-    },
-    {
-      "epoch": 0.31238214959145194,
-      "grad_norm": 9.726242065429688,
-      "learning_rate": 0.0001984,
-      "loss": 1.9308,
-      "step": 497
-    },
-    {
-      "epoch": 0.3130106851037084,
-      "grad_norm": 5.540197372436523,
-      "learning_rate": 0.0001988,
-      "loss": 1.9632,
-      "step": 498
-    },
-    {
-      "epoch": 0.3136392206159648,
-      "grad_norm": 11.275084495544434,
-      "learning_rate": 0.00019920000000000002,
-      "loss": 1.8719,
-      "step": 499
-    },
-    {
-      "epoch": 0.3142677561282212,
-      "grad_norm": 8.379544258117676,
-      "learning_rate": 0.0001996,
-      "loss": 2.1343,
-      "step": 500
-    },
-    {
-      "epoch": 0.31489629164047767,
-      "grad_norm": 7.902101039886475,
-      "learning_rate": 0.0002,
-      "loss": 2.0374,
-      "step": 501
-    },
-    {
-      "epoch": 0.3155248271527341,
-      "grad_norm": 5.915253162384033,
-      "learning_rate": 0.00019999962686803274,
-      "loss": 1.9273,
-      "step": 502
-    },
-    {
-      "epoch": 0.31615336266499056,
-      "grad_norm": 4.51748514175415,
-      "learning_rate": 0.0001999985074752248,
-      "loss": 1.7414,
-      "step": 503
-    },
-    {
-      "epoch": 0.316781898177247,
-      "grad_norm": 82.88562774658203,
-      "learning_rate": 0.000199996641830858,
-      "loss": 2.4431,
-      "step": 504
-    },
-    {
-      "epoch": 0.31741043368950345,
-      "grad_norm": 16.860361099243164,
-      "learning_rate": 0.00019999402995040202,
-      "loss": 2.031,
-      "step": 505
-    },
-    {
-      "epoch": 0.3180389692017599,
-      "grad_norm": 10.03348159790039,
-      "learning_rate": 0.000199990671855514,
-      "loss": 2.1866,
-      "step": 506
-    },
-    {
-      "epoch": 0.31866750471401634,
-      "grad_norm": 7.5439629554748535,
-      "learning_rate": 0.00019998656757403872,
-      "loss": 1.9684,
-      "step": 507
-    },
-    {
-      "epoch": 0.3192960402262728,
-      "grad_norm": 8.82386302947998,
-      "learning_rate": 0.00019998171714000814,
-      "loss": 2.1364,
-      "step": 508
-    },
-    {
-      "epoch": 0.3199245757385292,
-      "grad_norm": 8.354187965393066,
-      "learning_rate": 0.00019997612059364118,
-      "loss": 1.6715,
-      "step": 509
-    },
-    {
-      "epoch": 0.32055311125078567,
-      "grad_norm": 6.262081146240234,
-      "learning_rate": 0.0001999697779813434,
-      "loss": 2.1308,
-      "step": 510
-    },
-    {
-      "epoch": 0.3211816467630421,
-      "grad_norm": 12.487313270568848,
-      "learning_rate": 0.0001999626893557066,
-      "loss": 1.8659,
-      "step": 511
-    },
-    {
-      "epoch": 0.32181018227529856,
-      "grad_norm": 13.1874418258667,
-      "learning_rate": 0.00019995485477550848,
-      "loss": 1.9808,
-      "step": 512
-    },
-    {
-      "epoch": 0.322438717787555,
-      "grad_norm": 6.41532039642334,
-      "learning_rate": 0.00019994627430571188,
-      "loss": 2.1896,
-      "step": 513
-    },
-    {
-      "epoch": 0.32306725329981145,
-      "grad_norm": 8.269707679748535,
-      "learning_rate": 0.00019993694801746456,
-      "loss": 1.9233,
-      "step": 514
-    },
-    {
-      "epoch": 0.3236957888120679,
-      "grad_norm": 7.2478556632995605,
-      "learning_rate": 0.00019992687598809847,
-      "loss": 2.0612,
-      "step": 515
-    },
-    {
-      "epoch": 0.32432432432432434,
-      "grad_norm": 3.833040952682495,
-      "learning_rate": 0.00019991605830112902,
-      "loss": 2.1114,
-      "step": 516
-    },
-    {
-      "epoch": 0.3249528598365808,
-      "grad_norm": 38.45088577270508,
-      "learning_rate": 0.00019990449504625458,
-      "loss": 2.0145,
-      "step": 517
-    },
-    {
-      "epoch": 0.32558139534883723,
-      "grad_norm": 6.172846794128418,
-      "learning_rate": 0.00019989218631935555,
-      "loss": 2.0293,
-      "step": 518
-    },
-    {
-      "epoch": 0.3262099308610937,
-      "grad_norm": 12.175736427307129,
-      "learning_rate": 0.00019987913222249378,
-      "loss": 1.8907,
-      "step": 519
-    },
-    {
-      "epoch": 0.32683846637335007,
-      "grad_norm": 17.118629455566406,
-      "learning_rate": 0.00019986533286391145,
-      "loss": 2.0689,
-      "step": 520
-    },
-    {
-      "epoch": 0.3274670018856065,
-      "grad_norm": 10.824390411376953,
-      "learning_rate": 0.0001998507883580304,
-      "loss": 1.8524,
-      "step": 521
-    },
-    {
-      "epoch": 0.32809553739786296,
-      "grad_norm": 11.699383735656738,
-      "learning_rate": 0.00019983549882545104,
-      "loss": 1.9415,
-      "step": 522
-    },
-    {
-      "epoch": 0.3287240729101194,
-      "grad_norm": 6.905187606811523,
-      "learning_rate": 0.00019981946439295148,
-      "loss": 1.9727,
-      "step": 523
-    },
-    {
-      "epoch": 0.32935260842237585,
-      "grad_norm": 6.928370952606201,
-      "learning_rate": 0.00019980268519348638,
-      "loss": 1.6597,
-      "step": 524
-    },
-    {
-      "epoch": 0.3299811439346323,
-      "grad_norm": 11.314483642578125,
-      "learning_rate": 0.00019978516136618586,
-      "loss": 1.8615,
-      "step": 525
-    },
-    {
-      "epoch": 0.33060967944688874,
-      "grad_norm": 7.91243839263916,
-      "learning_rate": 0.0001997668930563543,
-      "loss": 1.9287,
-      "step": 526
-    },
-    {
-      "epoch": 0.3312382149591452,
-      "grad_norm": 13.120015144348145,
-      "learning_rate": 0.00019974788041546938,
-      "loss": 1.8362,
-      "step": 527
-    },
-    {
-      "epoch": 0.33186675047140163,
-      "grad_norm": 5.466783046722412,
-      "learning_rate": 0.00019972812360118043,
-      "loss": 2.0244,
-      "step": 528
-    },
-    {
-      "epoch": 0.3324952859836581,
-      "grad_norm": 4.511836528778076,
-      "learning_rate": 0.0001997076227773075,
-      "loss": 1.9735,
-      "step": 529
-    },
-    {
-      "epoch": 0.3331238214959145,
-      "grad_norm": 54.1873779296875,
-      "learning_rate": 0.0001996863781138397,
-      "loss": 1.8809,
-      "step": 530
-    },
-    {
-      "epoch": 0.33375235700817096,
-      "grad_norm": 39.161216735839844,
-      "learning_rate": 0.00019966438978693402,
-      "loss": 2.0392,
-      "step": 531
-    },
-    {
-      "epoch": 0.3343808925204274,
-      "grad_norm": 64.01873016357422,
-      "learning_rate": 0.00019964165797891373,
-      "loss": 1.7525,
-      "step": 532
-    },
-    {
-      "epoch": 0.33500942803268385,
-      "grad_norm": 5.953110694885254,
-      "learning_rate": 0.00019961818287826693,
-      "loss": 1.9637,
-      "step": 533
-    },
-    {
-      "epoch": 0.3356379635449403,
-      "grad_norm": 5.852209091186523,
-      "learning_rate": 0.00019959396467964497,
-      "loss": 1.9106,
-      "step": 534
-    },
-    {
-      "epoch": 0.33626649905719674,
-      "grad_norm": 7.1264328956604,
-      "learning_rate": 0.00019956900358386083,
-      "loss": 2.0108,
-      "step": 535
-    },
-    {
-      "epoch": 0.3368950345694532,
-      "grad_norm": 12.140629768371582,
-      "learning_rate": 0.0001995432997978874,
-      "loss": 2.0983,
-      "step": 536
-    },
-    {
-      "epoch": 0.33752357008170963,
-      "grad_norm": 14.71324634552002,
-      "learning_rate": 0.00019951685353485603,
-      "loss": 2.0762,
-      "step": 537
-    },
-    {
-      "epoch": 0.3381521055939661,
-      "grad_norm": 14.816312789916992,
-      "learning_rate": 0.00019948966501405425,
-      "loss": 2.0775,
-      "step": 538
-    },
-    {
-      "epoch": 0.3387806411062225,
-      "grad_norm": 6.533554553985596,
-      "learning_rate": 0.0001994617344609245,
-      "loss": 2.2237,
-      "step": 539
-    },
-    {
-      "epoch": 0.33940917661847897,
-      "grad_norm": 9.91523265838623,
-      "learning_rate": 0.00019943306210706198,
-      "loss": 1.7658,
-      "step": 540
-    },
-    {
-      "epoch": 0.34003771213073536,
-      "grad_norm": 5.4957780838012695,
-      "learning_rate": 0.00019940364819021265,
-      "loss": 1.699,
-      "step": 541
-    },
-    {
-      "epoch": 0.3406662476429918,
-      "grad_norm": 4.798709869384766,
-      "learning_rate": 0.0001993734929542715,
-      "loss": 2.1305,
-      "step": 542
-    },
-    {
-      "epoch": 0.34129478315524825,
-      "grad_norm": 10.779973983764648,
-      "learning_rate": 0.00019934259664928036,
-      "loss": 1.697,
-      "step": 543
-    },
-    {
-      "epoch": 0.3419233186675047,
-      "grad_norm": 82.30536651611328,
-      "learning_rate": 0.00019931095953142585,
-      "loss": 3.1804,
-      "step": 544
-    },
-    {
-      "epoch": 0.34255185417976114,
-      "grad_norm": 6.669949531555176,
-      "learning_rate": 0.00019927858186303735,
-      "loss": 2.0105,
-      "step": 545
-    },
-    {
-      "epoch": 0.3431803896920176,
-      "grad_norm": 6.1852803230285645,
-      "learning_rate": 0.00019924546391258464,
-      "loss": 1.6387,
-      "step": 546
-    },
-    {
-      "epoch": 0.34380892520427403,
-      "grad_norm": 6.42205810546875,
-      "learning_rate": 0.00019921160595467595,
-      "loss": 2.0396,
-      "step": 547
-    },
-    {
-      "epoch": 0.3444374607165305,
-      "grad_norm": 4.6135406494140625,
-      "learning_rate": 0.00019917700827005536,
-      "loss": 2.1966,
-      "step": 548
-    },
-    {
-      "epoch": 0.3450659962287869,
-      "grad_norm": 3.7657713890075684,
-      "learning_rate": 0.00019914167114560064,
-      "loss": 1.7663,
-      "step": 549
-    },
-    {
-      "epoch": 0.34569453174104336,
-      "grad_norm": 4.691615104675293,
-      "learning_rate": 0.00019910559487432104,
-      "loss": 1.7651,
-      "step": 550
-    },
-    {
-      "epoch": 0.3463230672532998,
-      "grad_norm": 3.708641290664673,
-      "learning_rate": 0.00019906877975535447,
-      "loss": 1.9406,
-      "step": 551
-    },
-    {
-      "epoch": 0.34695160276555626,
-      "grad_norm": 30.91510772705078,
-      "learning_rate": 0.0001990312260939654,
-      "loss": 2.4156,
-      "step": 552
-    },
-    {
-      "epoch": 0.3475801382778127,
-      "grad_norm": 4.338770389556885,
-      "learning_rate": 0.00019899293420154202,
-      "loss": 1.726,
-      "step": 553
-    },
-    {
-      "epoch": 0.34820867379006915,
-      "grad_norm": 4.463732719421387,
-      "learning_rate": 0.00019895390439559387,
-      "loss": 2.1101,
-      "step": 554
-    },
-    {
-      "epoch": 0.3488372093023256,
-      "grad_norm": 3.511244297027588,
-      "learning_rate": 0.00019891413699974918,
-      "loss": 1.7408,
-      "step": 555
-    },
-    {
-      "epoch": 0.34946574481458204,
-      "grad_norm": 6.33323860168457,
-      "learning_rate": 0.00019887363234375206,
-      "loss": 2.2318,
-      "step": 556
-    },
-    {
-      "epoch": 0.3500942803268385,
-      "grad_norm": 7.024548053741455,
-      "learning_rate": 0.00019883239076345992,
-      "loss": 1.7199,
-      "step": 557
-    },
-    {
-      "epoch": 0.3507228158390949,
-      "grad_norm": 4.091303825378418,
-      "learning_rate": 0.00019879041260084055,
-      "loss": 2.2822,
-      "step": 558
-    },
-    {
-      "epoch": 0.35135135135135137,
-      "grad_norm": 4.067759037017822,
-      "learning_rate": 0.0001987476982039694,
-      "loss": 1.9152,
-      "step": 559
-    },
-    {
-      "epoch": 0.3519798868636078,
-      "grad_norm": 21.216266632080078,
-      "learning_rate": 0.0001987042479270266,
-      "loss": 1.631,
-      "step": 560
-    },
-    {
-      "epoch": 0.35260842237586426,
-      "grad_norm": 9.859007835388184,
-      "learning_rate": 0.00019866006213029413,
-      "loss": 2.1393,
-      "step": 561
-    },
-    {
-      "epoch": 0.3532369578881207,
-      "grad_norm": 6.041215896606445,
-      "learning_rate": 0.0001986151411801527,
-      "loss": 1.8395,
-      "step": 562
-    },
-    {
-      "epoch": 0.3538654934003771,
-      "grad_norm": 7.770387172698975,
-      "learning_rate": 0.0001985694854490788,
-      "loss": 2.0751,
-      "step": 563
-    },
-    {
-      "epoch": 0.35449402891263354,
-      "grad_norm": 3.955648422241211,
-      "learning_rate": 0.00019852309531564162,
-      "loss": 2.0338,
-      "step": 564
-    },
-    {
-      "epoch": 0.35512256442489,
-      "grad_norm": 64.14674377441406,
-      "learning_rate": 0.00019847597116449988,
-      "loss": 2.3877,
-      "step": 565
-    },
-    {
-      "epoch": 0.35575109993714643,
-      "grad_norm": 8.95103645324707,
-      "learning_rate": 0.0001984281133863986,
-      "loss": 1.9109,
-      "step": 566
-    },
-    {
-      "epoch": 0.3563796354494029,
-      "grad_norm": 17.331172943115234,
-      "learning_rate": 0.000198379522378166,
-      "loss": 1.9694,
-      "step": 567
-    },
-    {
-      "epoch": 0.3570081709616593,
-      "grad_norm": 10.267071723937988,
-      "learning_rate": 0.00019833019854270992,
-      "loss": 2.0442,
-      "step": 568
-    },
-    {
-      "epoch": 0.35763670647391577,
-      "grad_norm": 12.023430824279785,
-      "learning_rate": 0.0001982801422890149,
-      "loss": 1.697,
-      "step": 569
-    },
-    {
-      "epoch": 0.3582652419861722,
-      "grad_norm": 3.4745445251464844,
-      "learning_rate": 0.00019822935403213845,
-      "loss": 1.8609,
-      "step": 570
-    },
-    {
-      "epoch": 0.35889377749842866,
-      "grad_norm": 14.138343811035156,
-      "learning_rate": 0.00019817783419320768,
-      "loss": 1.8126,
-      "step": 571
-    },
-    {
-      "epoch": 0.3595223130106851,
-      "grad_norm": 4.1279449462890625,
-      "learning_rate": 0.00019812558319941596,
-      "loss": 1.7317,
-      "step": 572
-    },
-    {
-      "epoch": 0.36015084852294155,
-      "grad_norm": 3.9519424438476562,
-      "learning_rate": 0.00019807260148401915,
-      "loss": 1.8072,
-      "step": 573
-    },
-    {
-      "epoch": 0.360779384035198,
-      "grad_norm": 5.094558238983154,
-      "learning_rate": 0.00019801888948633225,
-      "loss": 1.9189,
-      "step": 574
-    },
-    {
-      "epoch": 0.36140791954745444,
-      "grad_norm": 5.643648624420166,
-      "learning_rate": 0.00019796444765172547,
-      "loss": 1.6462,
-      "step": 575
-    },
-    {
-      "epoch": 0.3620364550597109,
-      "grad_norm": 5.166630268096924,
-      "learning_rate": 0.0001979092764316208,
-      "loss": 1.9548,
-      "step": 576
-    },
-    {
-      "epoch": 0.3626649905719673,
-      "grad_norm": 5.57295036315918,
-      "learning_rate": 0.0001978533762834882,
-      "loss": 2.1468,
-      "step": 577
-    },
-    {
-      "epoch": 0.3632935260842238,
-      "grad_norm": 6.271886348724365,
-      "learning_rate": 0.00019779674767084172,
-      "loss": 2.1451,
-      "step": 578
-    },
-    {
-      "epoch": 0.3639220615964802,
-      "grad_norm": 6.9632887840271,
-      "learning_rate": 0.00019773939106323564,
-      "loss": 2.0131,
-      "step": 579
-    },
-    {
-      "epoch": 0.36455059710873666,
-      "grad_norm": 5.3868303298950195,
-      "learning_rate": 0.00019768130693626076,
-      "loss": 2.0985,
-      "step": 580
-    },
-    {
-      "epoch": 0.3651791326209931,
-      "grad_norm": 14.987902641296387,
-      "learning_rate": 0.00019762249577154028,
-      "loss": 1.8193,
-      "step": 581
-    },
-    {
-      "epoch": 0.36580766813324955,
-      "grad_norm": 3.5422184467315674,
-      "learning_rate": 0.0001975629580567259,
-      "loss": 1.8757,
-      "step": 582
-    },
-    {
-      "epoch": 0.366436203645506,
-      "grad_norm": 3.7627673149108887,
-      "learning_rate": 0.0001975026942854937,
-      "loss": 2.0999,
-      "step": 583
-    },
-    {
-      "epoch": 0.3670647391577624,
-      "grad_norm": 12.89395523071289,
-      "learning_rate": 0.0001974417049575401,
-      "loss": 1.6594,
-      "step": 584
-    },
-    {
-      "epoch": 0.36769327467001883,
-      "grad_norm": 4.728719711303711,
-      "learning_rate": 0.00019737999057857774,
-      "loss": 1.8786,
-      "step": 585
-    },
-    {
-      "epoch": 0.3683218101822753,
-      "grad_norm": 9.114471435546875,
-      "learning_rate": 0.00019731755166033126,
-      "loss": 1.9816,
-      "step": 586
-    },
-    {
-      "epoch": 0.3689503456945317,
-      "grad_norm": 16.096595764160156,
-      "learning_rate": 0.00019725438872053295,
-      "loss": 2.1673,
-      "step": 587
-    },
-    {
-      "epoch": 0.36957888120678817,
-      "grad_norm": 2.9777557849884033,
-      "learning_rate": 0.00019719050228291876,
-      "loss": 1.9243,
-      "step": 588
-    },
-    {
-      "epoch": 0.3702074167190446,
-      "grad_norm": 5.046726703643799,
-      "learning_rate": 0.0001971258928772235,
-      "loss": 1.9836,
-      "step": 589
-    },
-    {
-      "epoch": 0.37083595223130106,
-      "grad_norm": 4.913296222686768,
-      "learning_rate": 0.00019706056103917688,
-      "loss": 2.0576,
-      "step": 590
-    },
-    {
-      "epoch": 0.3714644877435575,
-      "grad_norm": 4.675854682922363,
-      "learning_rate": 0.00019699450731049882,
-      "loss": 2.1639,
-      "step": 591
-    },
-    {
-      "epoch": 0.37209302325581395,
-      "grad_norm": 5.70509672164917,
-      "learning_rate": 0.0001969277322388951,
-      "loss": 1.7714,
-      "step": 592
-    },
-    {
-      "epoch": 0.3727215587680704,
-      "grad_norm": 6.298268795013428,
-      "learning_rate": 0.00019686023637805264,
-      "loss": 2.0385,
-      "step": 593
-    },
-    {
-      "epoch": 0.37335009428032684,
-      "grad_norm": 3.511186361312866,
-      "learning_rate": 0.0001967920202876351,
-      "loss": 1.6813,
-      "step": 594
-    },
-    {
-      "epoch": 0.3739786297925833,
-      "grad_norm": 3.8464162349700928,
-      "learning_rate": 0.0001967230845332781,
-      "loss": 1.4338,
-      "step": 595
-    },
-    {
-      "epoch": 0.37460716530483973,
-      "grad_norm": 4.702010631561279,
-      "learning_rate": 0.00019665342968658463,
-      "loss": 1.9824,
-      "step": 596
-    },
-    {
-      "epoch": 0.3752357008170962,
-      "grad_norm": 24.309362411499023,
-      "learning_rate": 0.00019658305632512023,
-      "loss": 1.7995,
-      "step": 597
-    },
-    {
-      "epoch": 0.3758642363293526,
-      "grad_norm": 8.361018180847168,
-      "learning_rate": 0.00019651196503240822,
-      "loss": 1.8303,
-      "step": 598
-    },
-    {
-      "epoch": 0.37649277184160906,
-      "grad_norm": 13.187949180603027,
-      "learning_rate": 0.000196440156397925,
-      "loss": 1.5381,
-      "step": 599
-    },
-    {
-      "epoch": 0.3771213073538655,
-      "grad_norm": 3.4687323570251465,
-      "learning_rate": 0.00019636763101709488,
-      "loss": 1.6627,
-      "step": 600
-    },
-    {
-      "epoch": 0.37774984286612195,
-      "grad_norm": 3.7859907150268555,
-      "learning_rate": 0.00019629438949128538,
-      "loss": 1.7985,
-      "step": 601
-    },
-    {
-      "epoch": 0.3783783783783784,
-      "grad_norm": 4.294689655303955,
-      "learning_rate": 0.00019622043242780219,
-      "loss": 1.7507,
-      "step": 602
-    },
-    {
-      "epoch": 0.37900691389063484,
-      "grad_norm": 5.246135234832764,
-      "learning_rate": 0.00019614576043988405,
-      "loss": 1.9783,
-      "step": 603
-    },
-    {
-      "epoch": 0.3796354494028913,
-      "grad_norm": 6.5482258796691895,
-      "learning_rate": 0.00019607037414669774,
-      "loss": 1.6939,
-      "step": 604
-    },
-    {
-      "epoch": 0.3802639849151477,
-      "grad_norm": 7.9593963623046875,
-      "learning_rate": 0.00019599427417333297,
-      "loss": 1.7155,
-      "step": 605
-    },
-    {
-      "epoch": 0.3808925204274041,
-      "grad_norm": 4.534102916717529,
-      "learning_rate": 0.0001959174611507971,
-      "loss": 1.6135,
-      "step": 606
-    },
-    {
-      "epoch": 0.38152105593966057,
-      "grad_norm": 3.6695873737335205,
-      "learning_rate": 0.00019583993571601008,
-      "loss": 2.0391,
-      "step": 607
-    },
-    {
-      "epoch": 0.382149591451917,
-      "grad_norm": 26.93898582458496,
-      "learning_rate": 0.0001957616985117989,
-      "loss": 1.8184,
-      "step": 608
-    },
-    {
-      "epoch": 0.38277812696417346,
-      "grad_norm": 6.302891254425049,
-      "learning_rate": 0.00019568275018689256,
-      "loss": 2.2152,
-      "step": 609
-    },
-    {
-      "epoch": 0.3834066624764299,
-      "grad_norm": 4.594456195831299,
-      "learning_rate": 0.00019560309139591642,
-      "loss": 1.9796,
-      "step": 610
-    },
-    {
-      "epoch": 0.38403519798868635,
-      "grad_norm": 5.86282205581665,
-      "learning_rate": 0.00019552272279938694,
-      "loss": 1.8413,
-      "step": 611
-    },
-    {
-      "epoch": 0.3846637335009428,
-      "grad_norm": 4.744015216827393,
-      "learning_rate": 0.00019544164506370625,
-      "loss": 1.7081,
-      "step": 612
-    },
-    {
-      "epoch": 0.38529226901319924,
-      "grad_norm": 7.284010887145996,
-      "learning_rate": 0.00019535985886115639,
-      "loss": 1.825,
-      "step": 613
-    },
-    {
-      "epoch": 0.3859208045254557,
-      "grad_norm": 3.884884834289551,
-      "learning_rate": 0.00019527736486989398,
-      "loss": 1.6148,
-      "step": 614
-    },
-    {
-      "epoch": 0.38654934003771213,
-      "grad_norm": 5.0570068359375,
-      "learning_rate": 0.0001951941637739445,
-      "loss": 1.7481,
-      "step": 615
-    },
-    {
-      "epoch": 0.3871778755499686,
-      "grad_norm": 3.745852470397949,
-      "learning_rate": 0.00019511025626319656,
-      "loss": 2.0021,
-      "step": 616
-    },
-    {
-      "epoch": 0.387806411062225,
-      "grad_norm": 7.246944904327393,
-      "learning_rate": 0.00019502564303339624,
-      "loss": 1.9073,
-      "step": 617
-    },
-    {
-      "epoch": 0.38843494657448147,
-      "grad_norm": 4.088373184204102,
-      "learning_rate": 0.00019494032478614137,
-      "loss": 1.7618,
-      "step": 618
-    },
-    {
-      "epoch": 0.3890634820867379,
-      "grad_norm": 3.925509214401245,
-      "learning_rate": 0.0001948543022288756,
-      "loss": 1.9142,
-      "step": 619
-    },
-    {
-      "epoch": 0.38969201759899436,
-      "grad_norm": 5.785417079925537,
-      "learning_rate": 0.00019476757607488266,
-      "loss": 2.0534,
-      "step": 620
-    },
-    {
-      "epoch": 0.3903205531112508,
-      "grad_norm": 4.438549518585205,
-      "learning_rate": 0.00019468014704328027,
-      "loss": 2.0836,
-      "step": 621
-    },
-    {
-      "epoch": 0.39094908862350725,
-      "grad_norm": 3.809293508529663,
-      "learning_rate": 0.0001945920158590144,
-      "loss": 1.8568,
-      "step": 622
-    },
-    {
-      "epoch": 0.3915776241357637,
-      "grad_norm": 43.43647384643555,
-      "learning_rate": 0.00019450318325285314,
-      "loss": 1.8248,
-      "step": 623
-    },
-    {
-      "epoch": 0.39220615964802014,
-      "grad_norm": 4.826264381408691,
-      "learning_rate": 0.00019441364996138053,
-      "loss": 2.0728,
-      "step": 624
-    },
-    {
-      "epoch": 0.3928346951602766,
-      "grad_norm": 5.580936908721924,
-      "learning_rate": 0.00019432341672699066,
-      "loss": 1.5899,
-      "step": 625
-    },
-    {
-      "epoch": 0.39346323067253297,
-      "grad_norm": 30.76082420349121,
-      "learning_rate": 0.00019423248429788144,
-      "loss": 1.7365,
-      "step": 626
-    },
-    {
-      "epoch": 0.3940917661847894,
-      "grad_norm": 34.04156494140625,
-      "learning_rate": 0.00019414085342804826,
-      "loss": 1.8151,
-      "step": 627
-    },
-    {
-      "epoch": 0.39472030169704586,
-      "grad_norm": 7.619344711303711,
-      "learning_rate": 0.000194048524877278,
-      "loss": 2.1841,
-      "step": 628
-    },
-    {
-      "epoch": 0.3953488372093023,
-      "grad_norm": 6.076333999633789,
-      "learning_rate": 0.00019395549941114254,
-      "loss": 1.3382,
-      "step": 629
-    },
-    {
-      "epoch": 0.39597737272155875,
-      "grad_norm": 4.319580554962158,
-      "learning_rate": 0.00019386177780099237,
-      "loss": 2.0434,
-      "step": 630
-    },
-    {
-      "epoch": 0.3966059082338152,
-      "grad_norm": 5.401275634765625,
-      "learning_rate": 0.0001937673608239504,
-      "loss": 2.0768,
-      "step": 631
-    },
-    {
-      "epoch": 0.39723444374607164,
-      "grad_norm": 7.192997455596924,
-      "learning_rate": 0.00019367224926290536,
-      "loss": 2.2093,
-      "step": 632
-    },
-    {
-      "epoch": 0.3978629792583281,
-      "grad_norm": 5.700124740600586,
-      "learning_rate": 0.0001935764439065053,
-      "loss": 1.8486,
-      "step": 633
-    },
-    {
-      "epoch": 0.39849151477058453,
-      "grad_norm": 6.410958766937256,
-      "learning_rate": 0.00019347994554915114,
-      "loss": 1.7625,
-      "step": 634
-    },
-    {
-      "epoch": 0.399120050282841,
-      "grad_norm": 4.75112247467041,
-      "learning_rate": 0.00019338275499099005,
-      "loss": 1.9693,
-      "step": 635
-    },
-    {
-      "epoch": 0.3997485857950974,
-      "grad_norm": 4.653494834899902,
-      "learning_rate": 0.00019328487303790879,
-      "loss": 1.9736,
-      "step": 636
-    },
-    {
-      "epoch": 0.40037712130735387,
-      "grad_norm": 2.9836111068725586,
-      "learning_rate": 0.00019318630050152704,
-      "loss": 1.7472,
-      "step": 637
-    },
-    {
-      "epoch": 0.4010056568196103,
-      "grad_norm": 2.469727039337158,
-      "learning_rate": 0.00019308703819919065,
-      "loss": 2.2143,
-      "step": 638
-    },
-    {
-      "epoch": 0.40163419233186676,
-      "grad_norm": 25.313440322875977,
-      "learning_rate": 0.00019298708695396496,
-      "loss": 2.1339,
-      "step": 639
-    },
-    {
-      "epoch": 0.4022627278441232,
-      "grad_norm": 3.8813374042510986,
-      "learning_rate": 0.0001928864475946278,
-      "loss": 2.088,
-      "step": 640
-    },
-    {
-      "epoch": 0.4022627278441232,
-      "eval_loss": 1.1269772052764893,
-      "eval_runtime": 1568.8549,
-      "eval_samples_per_second": 1.643,
-      "eval_steps_per_second": 1.643,
-      "step": 640
-    },
-    {
-      "epoch": 0.40289126335637965,
-      "grad_norm": 9.410492897033691,
-      "learning_rate": 0.00019278512095566278,
-      "loss": 1.9134,
-      "step": 641
-    },
-    {
-      "epoch": 0.4035197988686361,
-      "grad_norm": 4.390370845794678,
-      "learning_rate": 0.00019268310787725238,
-      "loss": 1.5095,
-      "step": 642
-    },
-    {
-      "epoch": 0.40414833438089254,
-      "grad_norm": 3.2495274543762207,
-      "learning_rate": 0.00019258040920527075,
-      "loss": 1.5648,
-      "step": 643
-    },
-    {
-      "epoch": 0.404776869893149,
-      "grad_norm": 2.887073278427124,
-      "learning_rate": 0.00019247702579127694,
-      "loss": 1.9786,
-      "step": 644
-    },
-    {
-      "epoch": 0.40540540540540543,
-      "grad_norm": 3.6503512859344482,
-      "learning_rate": 0.00019237295849250786,
-      "loss": 1.7403,
-      "step": 645
-    },
-    {
-      "epoch": 0.4060339409176619,
-      "grad_norm": 3.6960840225219727,
-      "learning_rate": 0.0001922682081718709,
-      "loss": 1.8488,
-      "step": 646
-    },
-    {
-      "epoch": 0.4066624764299183,
-      "grad_norm": 47.15095520019531,
-      "learning_rate": 0.00019216277569793702,
-      "loss": 2.8805,
-      "step": 647
-    },
-    {
-      "epoch": 0.4072910119421747,
-      "grad_norm": 3.1784255504608154,
-      "learning_rate": 0.00019205666194493348,
-      "loss": 1.7315,
-      "step": 648
-    },
-    {
-      "epoch": 0.40791954745443115,
-      "grad_norm": 3.352231740951538,
-      "learning_rate": 0.0001919498677927366,
-      "loss": 1.7752,
-      "step": 649
-    },
-    {
-      "epoch": 0.4085480829666876,
-      "grad_norm": 3.8916022777557373,
-      "learning_rate": 0.00019184239412686443,
-      "loss": 1.6095,
-      "step": 650
-    },
-    {
-      "epoch": 0.40917661847894404,
-      "grad_norm": 4.626668453216553,
-      "learning_rate": 0.00019173424183846938,
-      "loss": 2.0136,
-      "step": 651
-    },
-    {
-      "epoch": 0.4098051539912005,
-      "grad_norm": 3.6814186573028564,
-      "learning_rate": 0.00019162541182433094,
-      "loss": 1.9785,
-      "step": 652
-    },
-    {
-      "epoch": 0.41043368950345693,
-      "grad_norm": 2.4360921382904053,
-      "learning_rate": 0.0001915159049868482,
-      "loss": 2.1039,
-      "step": 653
-    },
-    {
-      "epoch": 0.4110622250157134,
-      "grad_norm": 3.070681571960449,
-      "learning_rate": 0.00019140572223403222,
-      "loss": 1.8298,
-      "step": 654
-    },
-    {
-      "epoch": 0.4116907605279698,
-      "grad_norm": 3.048560619354248,
-      "learning_rate": 0.00019129486447949884,
-      "loss": 1.9087,
-      "step": 655
-    },
-    {
-      "epoch": 0.41231929604022627,
-      "grad_norm": 8.032454490661621,
-      "learning_rate": 0.00019118333264246066,
-      "loss": 1.8988,
-      "step": 656
-    },
-    {
-      "epoch": 0.4129478315524827,
-      "grad_norm": 5.433006763458252,
-      "learning_rate": 0.00019107112764771983,
-      "loss": 1.7312,
-      "step": 657
-    },
-    {
-      "epoch": 0.41357636706473916,
-      "grad_norm": 5.955564022064209,
-      "learning_rate": 0.00019095825042566008,
-      "loss": 2.0372,
-      "step": 658
-    },
-    {
-      "epoch": 0.4142049025769956,
-      "grad_norm": 16.444969177246094,
-      "learning_rate": 0.00019084470191223926,
-      "loss": 1.7105,
-      "step": 659
-    },
-    {
-      "epoch": 0.41483343808925205,
-      "grad_norm": 7.758225440979004,
-      "learning_rate": 0.00019073048304898133,
-      "loss": 1.8812,
-      "step": 660
-    },
-    {
-      "epoch": 0.4154619736015085,
-      "grad_norm": 4.389394283294678,
-      "learning_rate": 0.00019061559478296872,
-      "loss": 1.9399,
-      "step": 661
-    },
-    {
-      "epoch": 0.41609050911376494,
-      "grad_norm": 6.461364269256592,
-      "learning_rate": 0.00019050003806683443,
-      "loss": 1.557,
-      "step": 662
-    },
-    {
-      "epoch": 0.4167190446260214,
-      "grad_norm": 6.0508317947387695,
-      "learning_rate": 0.0001903838138587541,
-      "loss": 1.7769,
-      "step": 663
-    },
-    {
-      "epoch": 0.41734758013827783,
-      "grad_norm": 5.960983753204346,
-      "learning_rate": 0.00019026692312243816,
-      "loss": 1.7441,
-      "step": 664
-    },
-    {
-      "epoch": 0.4179761156505343,
-      "grad_norm": 5.332518577575684,
-      "learning_rate": 0.0001901493668271237,
-      "loss": 1.7507,
-      "step": 665
-    },
-    {
-      "epoch": 0.4186046511627907,
-      "grad_norm": 4.627866268157959,
-      "learning_rate": 0.00019003114594756654,
-      "loss": 1.588,
-      "step": 666
-    },
-    {
-      "epoch": 0.41923318667504716,
-      "grad_norm": 5.30118465423584,
-      "learning_rate": 0.0001899122614640331,
-      "loss": 2.1642,
-      "step": 667
-    },
-    {
-      "epoch": 0.4198617221873036,
-      "grad_norm": 3.94102144241333,
-      "learning_rate": 0.00018979271436229232,
-      "loss": 1.8787,
-      "step": 668
-    },
-    {
-      "epoch": 0.42049025769956,
-      "grad_norm": 3.952944040298462,
-      "learning_rate": 0.0001896725056336074,
-      "loss": 2.1777,
-      "step": 669
-    },
-    {
-      "epoch": 0.42111879321181644,
-      "grad_norm": 17.84577178955078,
-      "learning_rate": 0.00018955163627472772,
-      "loss": 1.5896,
-      "step": 670
-    },
-    {
-      "epoch": 0.4217473287240729,
-      "grad_norm": 3.3658595085144043,
-      "learning_rate": 0.00018943010728788036,
-      "loss": 1.7622,
-      "step": 671
-    },
-    {
-      "epoch": 0.42237586423632933,
-      "grad_norm": 3.9689407348632812,
-      "learning_rate": 0.00018930791968076202,
-      "loss": 1.8379,
-      "step": 672
-    },
-    {
-      "epoch": 0.4230043997485858,
-      "grad_norm": 2.2758445739746094,
-      "learning_rate": 0.0001891850744665305,
-      "loss": 1.6416,
-      "step": 673
-    },
-    {
-      "epoch": 0.4236329352608422,
-      "grad_norm": 25.5117130279541,
-      "learning_rate": 0.00018906157266379637,
-      "loss": 1.6938,
-      "step": 674
-    },
-    {
-      "epoch": 0.42426147077309867,
-      "grad_norm": 2.699244976043701,
-      "learning_rate": 0.00018893741529661464,
-      "loss": 1.9915,
-      "step": 675
-    },
-    {
-      "epoch": 0.4248900062853551,
-      "grad_norm": 34.14410400390625,
-      "learning_rate": 0.00018881260339447594,
-      "loss": 1.7325,
-      "step": 676
-    },
-    {
-      "epoch": 0.42551854179761156,
-      "grad_norm": 3.199965476989746,
-      "learning_rate": 0.0001886871379922983,
-      "loss": 1.9895,
-      "step": 677
-    },
-    {
-      "epoch": 0.426147077309868,
-      "grad_norm": 29.026304244995117,
-      "learning_rate": 0.00018856102013041842,
-      "loss": 1.5769,
-      "step": 678
-    },
-    {
-      "epoch": 0.42677561282212445,
-      "grad_norm": 2.1777989864349365,
-      "learning_rate": 0.00018843425085458316,
-      "loss": 1.8859,
-      "step": 679
-    },
-    {
-      "epoch": 0.4274041483343809,
-      "grad_norm": 4.491693019866943,
-      "learning_rate": 0.0001883068312159407,
-      "loss": 1.9437,
-      "step": 680
-    },
-    {
-      "epoch": 0.42803268384663734,
-      "grad_norm": 8.690496444702148,
-      "learning_rate": 0.00018817876227103189,
-      "loss": 1.7174,
-      "step": 681
-    },
-    {
-      "epoch": 0.4286612193588938,
-      "grad_norm": 3.7214949131011963,
-      "learning_rate": 0.00018805004508178161,
-      "loss": 2.0811,
-      "step": 682
-    },
-    {
-      "epoch": 0.42928975487115023,
-      "grad_norm": 6.077978610992432,
-      "learning_rate": 0.00018792068071548984,
-      "loss": 1.7471,
-      "step": 683
-    },
-    {
-      "epoch": 0.4299182903834067,
-      "grad_norm": 6.373495578765869,
-      "learning_rate": 0.00018779067024482274,
-      "loss": 2.0545,
-      "step": 684
-    },
-    {
-      "epoch": 0.4305468258956631,
-      "grad_norm": 5.059445381164551,
-      "learning_rate": 0.00018766001474780397,
-      "loss": 2.0324,
-      "step": 685
-    },
-    {
-      "epoch": 0.43117536140791957,
-      "grad_norm": 5.652797222137451,
-      "learning_rate": 0.0001875287153078056,
-      "loss": 1.6775,
-      "step": 686
-    },
-    {
-      "epoch": 0.431803896920176,
-      "grad_norm": 4.22088623046875,
-      "learning_rate": 0.0001873967730135391,
-      "loss": 1.8297,
-      "step": 687
-    },
-    {
-      "epoch": 0.43243243243243246,
-      "grad_norm": 2.631542921066284,
-      "learning_rate": 0.0001872641889590465,
-      "loss": 1.9138,
-      "step": 688
-    },
-    {
-      "epoch": 0.4330609679446889,
-      "grad_norm": 2.948751211166382,
-      "learning_rate": 0.00018713096424369103,
-      "loss": 1.6555,
-      "step": 689
-    },
-    {
-      "epoch": 0.4336895034569453,
-      "grad_norm": 2.5569674968719482,
-      "learning_rate": 0.00018699709997214832,
-      "loss": 1.5643,
-      "step": 690
-    },
-    {
-      "epoch": 0.43431803896920174,
-      "grad_norm": 4.394289493560791,
-      "learning_rate": 0.00018686259725439691,
-      "loss": 1.621,
-      "step": 691
-    },
-    {
-      "epoch": 0.4349465744814582,
-      "grad_norm": 2.499648332595825,
-      "learning_rate": 0.00018672745720570947,
-      "loss": 2.168,
-      "step": 692
-    },
-    {
-      "epoch": 0.4355751099937146,
-      "grad_norm": 2.7896997928619385,
-      "learning_rate": 0.00018659168094664304,
-      "loss": 2.0703,
-      "step": 693
-    },
-    {
-      "epoch": 0.43620364550597107,
-      "grad_norm": 6.9485650062561035,
-      "learning_rate": 0.00018645526960303022,
-      "loss": 1.6304,
-      "step": 694
-    },
-    {
-      "epoch": 0.4368321810182275,
-      "grad_norm": 59.711971282958984,
-      "learning_rate": 0.0001863182243059694,
-      "loss": 2.3173,
-      "step": 695
-    },
-    {
-      "epoch": 0.43746071653048396,
-      "grad_norm": 9.602359771728516,
-      "learning_rate": 0.00018618054619181585,
-      "loss": 1.7722,
-      "step": 696
-    },
-    {
-      "epoch": 0.4380892520427404,
-      "grad_norm": 3.540498971939087,
-      "learning_rate": 0.00018604223640217185,
-      "loss": 1.4779,
-      "step": 697
-    },
-    {
-      "epoch": 0.43871778755499685,
-      "grad_norm": 3.870150089263916,
-      "learning_rate": 0.00018590329608387748,
-      "loss": 1.4608,
-      "step": 698
-    },
-    {
-      "epoch": 0.4393463230672533,
-      "grad_norm": 2.603410005569458,
-      "learning_rate": 0.0001857637263890011,
-      "loss": 1.9159,
-      "step": 699
-    },
-    {
-      "epoch": 0.43997485857950974,
-      "grad_norm": 2.723639488220215,
-      "learning_rate": 0.00018562352847482965,
-      "loss": 1.4755,
-      "step": 700
-    },
-    {
-      "epoch": 0.4406033940917662,
-      "grad_norm": 5.783612251281738,
-      "learning_rate": 0.00018548270350385922,
-      "loss": 1.4706,
-      "step": 701
-    },
-    {
-      "epoch": 0.44123192960402263,
-      "grad_norm": 5.094363689422607,
-      "learning_rate": 0.00018534125264378537,
-      "loss": 1.7839,
-      "step": 702
-    },
-    {
-      "epoch": 0.4418604651162791,
-      "grad_norm": 8.562081336975098,
-      "learning_rate": 0.00018519917706749336,
-      "loss": 1.7617,
-      "step": 703
-    },
-    {
-      "epoch": 0.4424890006285355,
-      "grad_norm": 3.990987777709961,
-      "learning_rate": 0.0001850564779530485,
-      "loss": 1.6584,
-      "step": 704
-    },
-    {
-      "epoch": 0.44311753614079197,
-      "grad_norm": 4.689113616943359,
-      "learning_rate": 0.0001849131564836864,
-      "loss": 1.7704,
-      "step": 705
-    },
-    {
-      "epoch": 0.4437460716530484,
-      "grad_norm": 3.648507595062256,
-      "learning_rate": 0.00018476921384780306,
-      "loss": 1.999,
-      "step": 706
-    },
-    {
-      "epoch": 0.44437460716530486,
-      "grad_norm": 4.041159152984619,
-      "learning_rate": 0.00018462465123894514,
-      "loss": 1.8709,
-      "step": 707
-    },
-    {
-      "epoch": 0.4450031426775613,
-      "grad_norm": 5.241822719573975,
-      "learning_rate": 0.0001844794698558,
-      "loss": 2.04,
-      "step": 708
-    },
-    {
-      "epoch": 0.44563167818981775,
-      "grad_norm": 3.5962722301483154,
-      "learning_rate": 0.00018433367090218573,
-      "loss": 1.7618,
-      "step": 709
-    },
-    {
-      "epoch": 0.4462602137020742,
-      "grad_norm": 4.885190010070801,
-      "learning_rate": 0.0001841872555870413,
-      "loss": 1.7482,
-      "step": 710
-    },
-    {
-      "epoch": 0.4468887492143306,
-      "grad_norm": 11.033466339111328,
-      "learning_rate": 0.00018404022512441627,
-      "loss": 1.6004,
-      "step": 711
-    },
-    {
-      "epoch": 0.44751728472658703,
-      "grad_norm": 2.763528823852539,
-      "learning_rate": 0.000183892580733461,
-      "loss": 1.8139,
-      "step": 712
-    },
-    {
-      "epoch": 0.4481458202388435,
-      "grad_norm": 2.823786735534668,
-      "learning_rate": 0.0001837443236384165,
-      "loss": 1.932,
-      "step": 713
-    },
-    {
-      "epoch": 0.4487743557510999,
-      "grad_norm": 3.0920910835266113,
-      "learning_rate": 0.0001835954550686041,
-      "loss": 2.1842,
-      "step": 714
-    },
-    {
-      "epoch": 0.44940289126335636,
-      "grad_norm": 6.687446594238281,
-      "learning_rate": 0.00018344597625841538,
-      "loss": 1.4632,
-      "step": 715
-    },
-    {
-      "epoch": 0.4500314267756128,
-      "grad_norm": 3.8577492237091064,
-      "learning_rate": 0.00018329588844730196,
-      "loss": 1.5663,
-      "step": 716
-    },
-    {
-      "epoch": 0.45065996228786925,
-      "grad_norm": 4.575584411621094,
-      "learning_rate": 0.0001831451928797652,
-      "loss": 1.9887,
-      "step": 717
-    },
-    {
-      "epoch": 0.4512884978001257,
-      "grad_norm": 3.485588788986206,
-      "learning_rate": 0.00018299389080534586,
-      "loss": 1.7647,
-      "step": 718
-    },
-    {
-      "epoch": 0.45191703331238214,
-      "grad_norm": 2.9639642238616943,
-      "learning_rate": 0.0001828419834786137,
-      "loss": 1.6995,
-      "step": 719
-    },
-    {
-      "epoch": 0.4525455688246386,
-      "grad_norm": 4.451672554016113,
-      "learning_rate": 0.00018268947215915716,
-      "loss": 1.5361,
-      "step": 720
-    },
-    {
-      "epoch": 0.45317410433689503,
-      "grad_norm": 4.583763599395752,
-      "learning_rate": 0.00018253635811157285,
-      "loss": 1.1242,
-      "step": 721
-    },
-    {
-      "epoch": 0.4538026398491515,
-      "grad_norm": 4.331716537475586,
-      "learning_rate": 0.00018238264260545518,
-      "loss": 1.8472,
-      "step": 722
-    },
-    {
-      "epoch": 0.4544311753614079,
-      "grad_norm": 2.900270700454712,
-      "learning_rate": 0.00018222832691538568,
-      "loss": 1.9554,
-      "step": 723
-    },
-    {
-      "epoch": 0.45505971087366437,
-      "grad_norm": 3.316112756729126,
-      "learning_rate": 0.00018207341232092248,
-      "loss": 1.8085,
-      "step": 724
-    },
-    {
-      "epoch": 0.4556882463859208,
-      "grad_norm": 3.347519874572754,
-      "learning_rate": 0.00018191790010658974,
-      "loss": 1.7429,
-      "step": 725
-    },
-    {
-      "epoch": 0.45631678189817726,
-      "grad_norm": 3.0476086139678955,
-      "learning_rate": 0.00018176179156186698,
-      "loss": 1.7755,
-      "step": 726
-    },
-    {
-      "epoch": 0.4569453174104337,
-      "grad_norm": 4.309592247009277,
-      "learning_rate": 0.00018160508798117843,
-      "loss": 1.5496,
-      "step": 727
-    },
-    {
-      "epoch": 0.45757385292269015,
-      "grad_norm": 8.562623023986816,
-      "learning_rate": 0.00018144779066388218,
-      "loss": 1.789,
-      "step": 728
-    },
-    {
-      "epoch": 0.4582023884349466,
-      "grad_norm": 2.293079137802124,
-      "learning_rate": 0.00018128990091425949,
-      "loss": 2.1914,
-      "step": 729
-    },
-    {
-      "epoch": 0.45883092394720304,
-      "grad_norm": 8.049859046936035,
-      "learning_rate": 0.00018113142004150398,
-      "loss": 1.6645,
-      "step": 730
-    },
-    {
-      "epoch": 0.4594594594594595,
-      "grad_norm": 19.898277282714844,
-      "learning_rate": 0.0001809723493597108,
-      "loss": 1.2446,
-      "step": 731
-    },
-    {
-      "epoch": 0.4600879949717159,
-      "grad_norm": 29.26360321044922,
-      "learning_rate": 0.00018081269018786563,
-      "loss": 1.612,
-      "step": 732
-    },
-    {
-      "epoch": 0.4607165304839723,
-      "grad_norm": 3.1725094318389893,
-      "learning_rate": 0.0001806524438498338,
-      "loss": 1.9092,
-      "step": 733
-    },
-    {
-      "epoch": 0.46134506599622876,
-      "grad_norm": 2.3968775272369385,
-      "learning_rate": 0.00018049161167434937,
-      "loss": 2.1533,
-      "step": 734
-    },
-    {
-      "epoch": 0.4619736015084852,
-      "grad_norm": 3.0249500274658203,
-      "learning_rate": 0.00018033019499500398,
-      "loss": 1.7566,
-      "step": 735
-    },
-    {
-      "epoch": 0.46260213702074165,
-      "grad_norm": 3.576960325241089,
-      "learning_rate": 0.000180168195150236,
-      "loss": 1.444,
-      "step": 736
-    },
-    {
-      "epoch": 0.4632306725329981,
-      "grad_norm": 2.93385648727417,
-      "learning_rate": 0.00018000561348331914,
-      "loss": 1.8811,
-      "step": 737
-    },
-    {
-      "epoch": 0.46385920804525455,
-      "grad_norm": 2.894970178604126,
-      "learning_rate": 0.0001798424513423516,
-      "loss": 1.8163,
-      "step": 738
-    },
-    {
-      "epoch": 0.464487743557511,
-      "grad_norm": 3.2280712127685547,
-      "learning_rate": 0.00017967871008024478,
-      "loss": 1.7769,
-      "step": 739
-    },
-    {
-      "epoch": 0.46511627906976744,
-      "grad_norm": 3.0282838344573975,
-      "learning_rate": 0.00017951439105471192,
-      "loss": 2.0009,
-      "step": 740
-    },
-    {
-      "epoch": 0.4657448145820239,
-      "grad_norm": 3.0622615814208984,
-      "learning_rate": 0.00017934949562825706,
-      "loss": 1.978,
-      "step": 741
-    },
-    {
-      "epoch": 0.4663733500942803,
-      "grad_norm": 5.17506742477417,
-      "learning_rate": 0.00017918402516816368,
-      "loss": 1.7729,
-      "step": 742
-    },
-    {
-      "epoch": 0.46700188560653677,
-      "grad_norm": 2.4315149784088135,
-      "learning_rate": 0.00017901798104648324,
-      "loss": 1.6185,
-      "step": 743
-    },
-    {
-      "epoch": 0.4676304211187932,
-      "grad_norm": 6.906350612640381,
-      "learning_rate": 0.00017885136464002404,
-      "loss": 1.443,
-      "step": 744
-    },
-    {
-      "epoch": 0.46825895663104966,
-      "grad_norm": 8.11252212524414,
-      "learning_rate": 0.0001786841773303395,
-      "loss": 1.7909,
-      "step": 745
-    },
-    {
-      "epoch": 0.4688874921433061,
-      "grad_norm": 2.88930082321167,
-      "learning_rate": 0.000178516420503717,
-      "loss": 1.8463,
-      "step": 746
-    },
-    {
-      "epoch": 0.46951602765556255,
-      "grad_norm": 6.115964889526367,
-      "learning_rate": 0.00017834809555116615,
-      "loss": 2.1431,
-      "step": 747
-    },
-    {
-      "epoch": 0.470144563167819,
-      "grad_norm": 4.440715789794922,
-      "learning_rate": 0.00017817920386840744,
-      "loss": 2.0347,
-      "step": 748
-    },
-    {
-      "epoch": 0.47077309868007544,
-      "grad_norm": 3.351571559906006,
-      "learning_rate": 0.0001780097468558606,
-      "loss": 1.4647,
-      "step": 749
-    },
-    {
-      "epoch": 0.4714016341923319,
-      "grad_norm": 3.25675106048584,
-      "learning_rate": 0.00017783972591863288,
-      "loss": 1.4636,
-      "step": 750
-    },
-    {
-      "epoch": 0.47203016970458833,
-      "grad_norm": 4.558582305908203,
-      "learning_rate": 0.00017766914246650749,
-      "loss": 1.3471,
-      "step": 751
-    },
-    {
-      "epoch": 0.4726587052168448,
-      "grad_norm": 5.9593024253845215,
-      "learning_rate": 0.00017749799791393206,
-      "loss": 1.8219,
-      "step": 752
-    },
-    {
-      "epoch": 0.4732872407291012,
-      "grad_norm": 4.069904327392578,
-      "learning_rate": 0.00017732629368000667,
-      "loss": 1.9191,
-      "step": 753
-    },
-    {
-      "epoch": 0.4739157762413576,
-      "grad_norm": 4.142630577087402,
-      "learning_rate": 0.00017715403118847208,
-      "loss": 1.7309,
-      "step": 754
-    },
-    {
-      "epoch": 0.47454431175361406,
-      "grad_norm": 3.7842137813568115,
-      "learning_rate": 0.0001769812118676982,
-      "loss": 1.6221,
-      "step": 755
-    },
-    {
-      "epoch": 0.4751728472658705,
-      "grad_norm": 3.864184856414795,
-      "learning_rate": 0.000176807837150672,
-      "loss": 1.8064,
-      "step": 756
-    },
-    {
-      "epoch": 0.47580138277812695,
-      "grad_norm": 3.0092368125915527,
-      "learning_rate": 0.0001766339084749856,
-      "loss": 1.6365,
-      "step": 757
-    },
-    {
-      "epoch": 0.4764299182903834,
-      "grad_norm": 12.817537307739258,
-      "learning_rate": 0.00017645942728282464,
-      "loss": 1.8892,
-      "step": 758
-    },
-    {
-      "epoch": 0.47705845380263984,
-      "grad_norm": 11.806923866271973,
-      "learning_rate": 0.00017628439502095594,
-      "loss": 1.6168,
-      "step": 759
-    },
-    {
-      "epoch": 0.4776869893148963,
-      "grad_norm": 5.879858493804932,
-      "learning_rate": 0.0001761088131407158,
-      "loss": 1.8019,
-      "step": 760
-    },
-    {
-      "epoch": 0.4783155248271527,
-      "grad_norm": 3.0829169750213623,
-      "learning_rate": 0.00017593268309799783,
-      "loss": 1.5807,
-      "step": 761
-    },
-    {
-      "epoch": 0.47894406033940917,
-      "grad_norm": 2.097031831741333,
-      "learning_rate": 0.00017575600635324088,
-      "loss": 2.0684,
-      "step": 762
-    },
-    {
-      "epoch": 0.4795725958516656,
-      "grad_norm": 2.688417673110962,
-      "learning_rate": 0.00017557878437141698,
-      "loss": 1.8658,
-      "step": 763
-    },
-    {
-      "epoch": 0.48020113136392206,
-      "grad_norm": 3.2802345752716064,
-      "learning_rate": 0.00017540101862201926,
-      "loss": 1.9306,
-      "step": 764
-    },
-    {
-      "epoch": 0.4808296668761785,
-      "grad_norm": 3.1129918098449707,
-      "learning_rate": 0.00017522271057904946,
-      "loss": 1.6982,
-      "step": 765
-    },
-    {
-      "epoch": 0.48145820238843495,
-      "grad_norm": 2.2457778453826904,
-      "learning_rate": 0.0001750438617210061,
-      "loss": 1.9326,
-      "step": 766
-    },
-    {
-      "epoch": 0.4820867379006914,
-      "grad_norm": 2.9294021129608154,
-      "learning_rate": 0.000174864473530872,
-      "loss": 2.0253,
-      "step": 767
-    },
-    {
-      "epoch": 0.48271527341294784,
-      "grad_norm": 2.652953863143921,
-      "learning_rate": 0.00017468454749610196,
-      "loss": 1.3577,
-      "step": 768
-    },
-    {
-      "epoch": 0.4833438089252043,
-      "grad_norm": 3.715381622314453,
-      "learning_rate": 0.0001745040851086106,
-      "loss": 1.922,
-      "step": 769
-    },
-    {
-      "epoch": 0.48397234443746073,
-      "grad_norm": 3.603480100631714,
-      "learning_rate": 0.00017432308786475978,
-      "loss": 1.8925,
-      "step": 770
-    },
-    {
-      "epoch": 0.4846008799497172,
-      "grad_norm": 4.010918617248535,
-      "learning_rate": 0.0001741415572653464,
-      "loss": 1.6332,
-      "step": 771
-    },
-    {
-      "epoch": 0.4852294154619736,
-      "grad_norm": 3.399214029312134,
-      "learning_rate": 0.00017395949481558966,
-      "loss": 1.9582,
-      "step": 772
-    },
-    {
-      "epoch": 0.48585795097423007,
-      "grad_norm": 2.358330488204956,
-      "learning_rate": 0.00017377690202511904,
-      "loss": 1.8979,
-      "step": 773
-    },
-    {
-      "epoch": 0.4864864864864865,
-      "grad_norm": 2.503108263015747,
-      "learning_rate": 0.00017359378040796123,
-      "loss": 1.6271,
-      "step": 774
-    },
-    {
-      "epoch": 0.4871150219987429,
-      "grad_norm": 2.3593077659606934,
-      "learning_rate": 0.00017341013148252813,
-      "loss": 1.8728,
-      "step": 775
-    },
-    {
-      "epoch": 0.48774355751099935,
-      "grad_norm": 11.187983512878418,
-      "learning_rate": 0.00017322595677160375,
-      "loss": 1.768,
-      "step": 776
-    },
-    {
-      "epoch": 0.4883720930232558,
-      "grad_norm": 3.171013116836548,
-      "learning_rate": 0.00017304125780233194,
-      "loss": 1.7985,
-      "step": 777
-    },
-    {
-      "epoch": 0.48900062853551224,
-      "grad_norm": 3.1267857551574707,
-      "learning_rate": 0.00017285603610620363,
-      "loss": 1.5857,
-      "step": 778
-    },
-    {
-      "epoch": 0.4896291640477687,
-      "grad_norm": 7.174981594085693,
-      "learning_rate": 0.00017267029321904397,
-      "loss": 1.7335,
-      "step": 779
-    },
-    {
-      "epoch": 0.49025769956002513,
-      "grad_norm": 2.160280227661133,
-      "learning_rate": 0.0001724840306809999,
-      "loss": 2.0375,
-      "step": 780
-    },
-    {
-      "epoch": 0.4908862350722816,
-      "grad_norm": 6.354787349700928,
-      "learning_rate": 0.0001722972500365271,
-      "loss": 1.5088,
-      "step": 781
-    },
-    {
-      "epoch": 0.491514770584538,
-      "grad_norm": 31.453384399414062,
-      "learning_rate": 0.00017210995283437733,
-      "loss": 1.6668,
-      "step": 782
-    },
-    {
-      "epoch": 0.49214330609679446,
-      "grad_norm": 45.95703887939453,
-      "learning_rate": 0.0001719221406275856,
-      "loss": 1.4828,
-      "step": 783
-    },
-    {
-      "epoch": 0.4927718416090509,
-      "grad_norm": 3.3195204734802246,
-      "learning_rate": 0.00017173381497345719,
-      "loss": 1.8632,
-      "step": 784
-    },
-    {
-      "epoch": 0.49340037712130735,
-      "grad_norm": 2.7932851314544678,
-      "learning_rate": 0.00017154497743355479,
-      "loss": 1.8966,
-      "step": 785
-    },
-    {
-      "epoch": 0.4940289126335638,
-      "grad_norm": 4.167323112487793,
-      "learning_rate": 0.00017135562957368554,
-      "loss": 1.586,
-      "step": 786
-    },
-    {
-      "epoch": 0.49465744814582024,
-      "grad_norm": 2.7749907970428467,
-      "learning_rate": 0.00017116577296388813,
-      "loss": 1.8016,
-      "step": 787
-    },
-    {
-      "epoch": 0.4952859836580767,
-      "grad_norm": 3.2511887550354004,
-      "learning_rate": 0.0001709754091784197,
-      "loss": 2.0155,
-      "step": 788
-    },
-    {
-      "epoch": 0.49591451917033313,
-      "grad_norm": 3.043982744216919,
-      "learning_rate": 0.00017078453979574274,
-      "loss": 1.7555,
-      "step": 789
-    },
-    {
-      "epoch": 0.4965430546825896,
-      "grad_norm": 4.874665260314941,
-      "learning_rate": 0.00017059316639851207,
-      "loss": 1.8308,
-      "step": 790
-    },
-    {
-      "epoch": 0.497171590194846,
-      "grad_norm": 4.281073093414307,
-      "learning_rate": 0.00017040129057356186,
-      "loss": 1.6109,
-      "step": 791
-    },
-    {
-      "epoch": 0.49780012570710247,
-      "grad_norm": 4.453769207000732,
-      "learning_rate": 0.0001702089139118921,
-      "loss": 1.5652,
-      "step": 792
-    },
-    {
-      "epoch": 0.4984286612193589,
-      "grad_norm": 2.850391149520874,
-      "learning_rate": 0.00017001603800865576,
-      "loss": 1.9772,
-      "step": 793
-    },
-    {
-      "epoch": 0.49905719673161536,
-      "grad_norm": 2.58915114402771,
-      "learning_rate": 0.00016982266446314537,
-      "loss": 1.7888,
-      "step": 794
-    },
-    {
-      "epoch": 0.4996857322438718,
-      "grad_norm": 2.1942155361175537,
-      "learning_rate": 0.00016962879487877989,
-      "loss": 1.7295,
-      "step": 795
-    },
-    {
-      "epoch": 0.5003142677561282,
-      "grad_norm": 5.866901874542236,
-      "learning_rate": 0.0001694344308630913,
-      "loss": 1.6227,
-      "step": 796
-    },
-    {
-      "epoch": 0.5009428032683847,
-      "grad_norm": 4.190849304199219,
-      "learning_rate": 0.00016923957402771128,
-      "loss": 1.9444,
-      "step": 797
-    },
-    {
-      "epoch": 0.5015713387806411,
-      "grad_norm": 3.735076665878296,
-      "learning_rate": 0.000169044225988358,
-      "loss": 1.5726,
-      "step": 798
-    },
-    {
-      "epoch": 0.5021998742928976,
-      "grad_norm": 2.586787223815918,
-      "learning_rate": 0.00016884838836482243,
-      "loss": 1.7038,
-      "step": 799
-    },
-    {
-      "epoch": 0.502828409805154,
-      "grad_norm": 3.8179101943969727,
-      "learning_rate": 0.0001686520627809553,
-      "loss": 1.8377,
-      "step": 800
-    },
-    {
-      "epoch": 0.502828409805154,
-      "eval_loss": 1.0471904277801514,
-      "eval_runtime": 1566.6812,
-      "eval_samples_per_second": 1.646,
-      "eval_steps_per_second": 1.646,
-      "step": 800
-    },
-    {
-      "epoch": 0.5034569453174105,
-      "grad_norm": 3.700340986251831,
-      "learning_rate": 0.00016845525086465327,
-      "loss": 1.3971,
-      "step": 801
-    },
-    {
-      "epoch": 0.5040854808296669,
-      "grad_norm": 3.863966703414917,
-      "learning_rate": 0.00016825795424784554,
-      "loss": 1.3689,
-      "step": 802
-    },
-    {
-      "epoch": 0.5047140163419234,
-      "grad_norm": 5.150142192840576,
-      "learning_rate": 0.00016806017456648056,
-      "loss": 1.5778,
-      "step": 803
-    },
-    {
-      "epoch": 0.5053425518541798,
-      "grad_norm": 3.1379594802856445,
-      "learning_rate": 0.0001678619134605121,
-      "loss": 1.6475,
-      "step": 804
-    },
-    {
-      "epoch": 0.5059710873664363,
-      "grad_norm": 2.5254056453704834,
-      "learning_rate": 0.00016766317257388576,
-      "loss": 1.9058,
-      "step": 805
-    },
-    {
-      "epoch": 0.5065996228786926,
-      "grad_norm": 3.2213141918182373,
-      "learning_rate": 0.00016746395355452564,
-      "loss": 1.5966,
-      "step": 806
-    },
-    {
-      "epoch": 0.507228158390949,
-      "grad_norm": 2.67704701423645,
-      "learning_rate": 0.0001672642580543202,
-      "loss": 1.8397,
-      "step": 807
-    },
-    {
-      "epoch": 0.5078566939032055,
-      "grad_norm": 2.7627856731414795,
-      "learning_rate": 0.00016706408772910894,
-      "loss": 1.9829,
-      "step": 808
-    },
-    {
-      "epoch": 0.5084852294154619,
-      "grad_norm": 3.3486082553863525,
-      "learning_rate": 0.00016686344423866843,
-      "loss": 2.0275,
-      "step": 809
-    },
-    {
-      "epoch": 0.5091137649277184,
-      "grad_norm": 4.416764736175537,
-      "learning_rate": 0.00016666232924669866,
-      "loss": 1.7995,
-      "step": 810
-    },
-    {
-      "epoch": 0.5097423004399748,
-      "grad_norm": 3.926478862762451,
-      "learning_rate": 0.00016646074442080926,
-      "loss": 1.3349,
-      "step": 811
-    },
-    {
-      "epoch": 0.5103708359522313,
-      "grad_norm": 3.0945920944213867,
-      "learning_rate": 0.00016625869143250564,
-      "loss": 1.8098,
-      "step": 812
-    },
-    {
-      "epoch": 0.5109993714644877,
-      "grad_norm": 7.1972784996032715,
-      "learning_rate": 0.0001660561719571751,
-      "loss": 1.7203,
-      "step": 813
-    },
-    {
-      "epoch": 0.5116279069767442,
-      "grad_norm": 2.261600971221924,
-      "learning_rate": 0.00016585318767407296,
-      "loss": 1.8334,
-      "step": 814
-    },
-    {
-      "epoch": 0.5122564424890006,
-      "grad_norm": 23.770172119140625,
-      "learning_rate": 0.00016564974026630873,
-      "loss": 1.2436,
-      "step": 815
-    },
-    {
-      "epoch": 0.5128849780012571,
-      "grad_norm": 1.8770813941955566,
-      "learning_rate": 0.0001654458314208319,
-      "loss": 1.9914,
-      "step": 816
-    },
-    {
-      "epoch": 0.5135135135135135,
-      "grad_norm": 2.9977574348449707,
-      "learning_rate": 0.00016524146282841825,
-      "loss": 1.5698,
-      "step": 817
-    },
-    {
-      "epoch": 0.51414204902577,
-      "grad_norm": 4.5086565017700195,
-      "learning_rate": 0.00016503663618365572,
-      "loss": 1.8745,
-      "step": 818
-    },
-    {
-      "epoch": 0.5147705845380264,
-      "grad_norm": 2.250277280807495,
-      "learning_rate": 0.00016483135318493024,
-      "loss": 2.0471,
-      "step": 819
-    },
-    {
-      "epoch": 0.5153991200502829,
-      "grad_norm": 2.7155048847198486,
-      "learning_rate": 0.0001646256155344118,
-      "loss": 1.7132,
-      "step": 820
-    },
-    {
-      "epoch": 0.5160276555625393,
-      "grad_norm": 2.070505142211914,
-      "learning_rate": 0.00016441942493804028,
-      "loss": 1.5661,
-      "step": 821
-    },
-    {
-      "epoch": 0.5166561910747958,
-      "grad_norm": 2.1399850845336914,
-      "learning_rate": 0.0001642127831055113,
-      "loss": 2.2479,
-      "step": 822
-    },
-    {
-      "epoch": 0.5172847265870522,
-      "grad_norm": 10.017570495605469,
-      "learning_rate": 0.00016400569175026202,
-      "loss": 1.8744,
-      "step": 823
-    },
-    {
-      "epoch": 0.5179132620993087,
-      "grad_norm": 7.541717529296875,
-      "learning_rate": 0.00016379815258945704,
-      "loss": 1.787,
-      "step": 824
-    },
-    {
-      "epoch": 0.518541797611565,
-      "grad_norm": 5.188529968261719,
-      "learning_rate": 0.00016359016734397396,
-      "loss": 1.8559,
-      "step": 825
-    },
-    {
-      "epoch": 0.5191703331238215,
-      "grad_norm": 2.2011945247650146,
-      "learning_rate": 0.00016338173773838938,
-      "loss": 1.5309,
-      "step": 826
-    },
-    {
-      "epoch": 0.5197988686360779,
-      "grad_norm": 3.5199337005615234,
-      "learning_rate": 0.00016317286550096436,
-      "loss": 1.4987,
-      "step": 827
-    },
-    {
-      "epoch": 0.5204274041483343,
-      "grad_norm": 3.5257673263549805,
-      "learning_rate": 0.00016296355236363022,
-      "loss": 1.4651,
-      "step": 828
-    },
-    {
-      "epoch": 0.5210559396605908,
-      "grad_norm": 7.473969459533691,
-      "learning_rate": 0.00016275380006197413,
-      "loss": 1.3646,
-      "step": 829
-    },
-    {
-      "epoch": 0.5216844751728472,
-      "grad_norm": 3.5532689094543457,
-      "learning_rate": 0.0001625436103352247,
-      "loss": 1.6972,
-      "step": 830
-    },
-    {
-      "epoch": 0.5223130106851037,
-      "grad_norm": 3.332782745361328,
-      "learning_rate": 0.00016233298492623766,
-      "loss": 1.8272,
-      "step": 831
-    },
-    {
-      "epoch": 0.5229415461973601,
-      "grad_norm": 2.6560447216033936,
-      "learning_rate": 0.00016212192558148127,
-      "loss": 1.849,
-      "step": 832
-    },
-    {
-      "epoch": 0.5235700817096166,
-      "grad_norm": 2.767364978790283,
-      "learning_rate": 0.00016191043405102199,
-      "loss": 1.6504,
-      "step": 833
-    },
-    {
-      "epoch": 0.524198617221873,
-      "grad_norm": 2.5089499950408936,
-      "learning_rate": 0.0001616985120885098,
-      "loss": 1.5984,
-      "step": 834
-    },
-    {
-      "epoch": 0.5248271527341295,
-      "grad_norm": 2.243863582611084,
-      "learning_rate": 0.0001614861614511638,
-      "loss": 1.9573,
-      "step": 835
-    },
-    {
-      "epoch": 0.5254556882463859,
-      "grad_norm": 5.696925640106201,
-      "learning_rate": 0.00016127338389975758,
-      "loss": 1.5365,
-      "step": 836
-    },
-    {
-      "epoch": 0.5260842237586424,
-      "grad_norm": 15.416232109069824,
-      "learning_rate": 0.00016106018119860455,
-      "loss": 1.5344,
-      "step": 837
-    },
-    {
-      "epoch": 0.5267127592708988,
-      "grad_norm": 3.5068626403808594,
-      "learning_rate": 0.00016084655511554354,
-      "loss": 1.3403,
-      "step": 838
-    },
-    {
-      "epoch": 0.5273412947831553,
-      "grad_norm": 2.7104172706604004,
-      "learning_rate": 0.00016063250742192386,
-      "loss": 1.6286,
-      "step": 839
-    },
-    {
-      "epoch": 0.5279698302954117,
-      "grad_norm": 2.5087764263153076,
-      "learning_rate": 0.00016041803989259076,
-      "loss": 1.7183,
-      "step": 840
-    },
-    {
-      "epoch": 0.5285983658076682,
-      "grad_norm": 8.253801345825195,
-      "learning_rate": 0.00016020315430587072,
-      "loss": 1.944,
-      "step": 841
-    },
-    {
-      "epoch": 0.5292269013199246,
-      "grad_norm": 6.215940952301025,
-      "learning_rate": 0.00015998785244355669,
-      "loss": 1.2669,
-      "step": 842
-    },
-    {
-      "epoch": 0.5298554368321811,
-      "grad_norm": 2.5656116008758545,
-      "learning_rate": 0.00015977213609089322,
-      "loss": 2.0271,
-      "step": 843
-    },
-    {
-      "epoch": 0.5304839723444374,
-      "grad_norm": 5.3323493003845215,
-      "learning_rate": 0.00015955600703656186,
-      "loss": 1.4939,
-      "step": 844
-    },
-    {
-      "epoch": 0.531112507856694,
-      "grad_norm": 2.5133509635925293,
-      "learning_rate": 0.00015933946707266615,
-      "loss": 2.0631,
-      "step": 845
-    },
-    {
-      "epoch": 0.5317410433689503,
-      "grad_norm": 2.797114610671997,
-      "learning_rate": 0.0001591225179947168,
-      "loss": 1.8101,
-      "step": 846
-    },
-    {
-      "epoch": 0.5323695788812068,
-      "grad_norm": 3.838271141052246,
-      "learning_rate": 0.00015890516160161678,
-      "loss": 1.4939,
-      "step": 847
-    },
-    {
-      "epoch": 0.5329981143934632,
-      "grad_norm": 6.3040995597839355,
-      "learning_rate": 0.0001586873996956466,
-      "loss": 1.7562,
-      "step": 848
-    },
-    {
-      "epoch": 0.5336266499057196,
-      "grad_norm": 3.633244514465332,
-      "learning_rate": 0.0001584692340824491,
-      "loss": 1.9957,
-      "step": 849
-    },
-    {
-      "epoch": 0.5342551854179761,
-      "grad_norm": 3.348219156265259,
-      "learning_rate": 0.00015825066657101453,
-      "loss": 1.3537,
-      "step": 850
-    },
-    {
-      "epoch": 0.5348837209302325,
-      "grad_norm": 2.8102500438690186,
-      "learning_rate": 0.00015803169897366572,
-      "loss": 2.0199,
-      "step": 851
-    },
-    {
-      "epoch": 0.535512256442489,
-      "grad_norm": 2.8683907985687256,
-      "learning_rate": 0.00015781233310604287,
-      "loss": 1.8299,
-      "step": 852
-    },
-    {
-      "epoch": 0.5361407919547454,
-      "grad_norm": 2.856029510498047,
-      "learning_rate": 0.00015759257078708867,
-      "loss": 1.5422,
-      "step": 853
-    },
-    {
-      "epoch": 0.5367693274670019,
-      "grad_norm": 3.02531099319458,
-      "learning_rate": 0.000157372413839033,
-      "loss": 1.7447,
-      "step": 854
-    },
-    {
-      "epoch": 0.5373978629792583,
-      "grad_norm": 2.963717460632324,
-      "learning_rate": 0.000157151864087378,
-      "loss": 1.6809,
-      "step": 855
-    },
-    {
-      "epoch": 0.5380263984915148,
-      "grad_norm": 16.036455154418945,
-      "learning_rate": 0.00015693092336088274,
-      "loss": 1.5663,
-      "step": 856
-    },
-    {
-      "epoch": 0.5386549340037712,
-      "grad_norm": 14.2581148147583,
-      "learning_rate": 0.00015670959349154838,
-      "loss": 1.6203,
-      "step": 857
-    },
-    {
-      "epoch": 0.5392834695160277,
-      "grad_norm": 2.873945474624634,
-      "learning_rate": 0.00015648787631460272,
-      "loss": 1.6255,
-      "step": 858
-    },
-    {
-      "epoch": 0.5399120050282841,
-      "grad_norm": 2.8614494800567627,
-      "learning_rate": 0.0001562657736684849,
-      "loss": 1.7169,
-      "step": 859
-    },
-    {
-      "epoch": 0.5405405405405406,
-      "grad_norm": 2.071613311767578,
-      "learning_rate": 0.0001560432873948305,
-      "loss": 1.8202,
-      "step": 860
-    },
-    {
-      "epoch": 0.541169076052797,
-      "grad_norm": 3.9846320152282715,
-      "learning_rate": 0.00015582041933845598,
-      "loss": 1.4323,
-      "step": 861
-    },
-    {
-      "epoch": 0.5417976115650535,
-      "grad_norm": 2.527543544769287,
-      "learning_rate": 0.00015559717134734343,
-      "loss": 1.5789,
-      "step": 862
-    },
-    {
-      "epoch": 0.5424261470773099,
-      "grad_norm": 2.104928493499756,
-      "learning_rate": 0.00015537354527262538,
-      "loss": 1.8236,
-      "step": 863
-    },
-    {
-      "epoch": 0.5430546825895664,
-      "grad_norm": 2.0675976276397705,
-      "learning_rate": 0.00015514954296856932,
-      "loss": 1.7982,
-      "step": 864
-    },
-    {
-      "epoch": 0.5436832181018227,
-      "grad_norm": 4.772681713104248,
-      "learning_rate": 0.0001549251662925624,
-      "loss": 1.816,
-      "step": 865
-    },
-    {
-      "epoch": 0.5443117536140792,
-      "grad_norm": 3.118591785430908,
-      "learning_rate": 0.00015470041710509587,
-      "loss": 1.8371,
-      "step": 866
-    },
-    {
-      "epoch": 0.5449402891263356,
-      "grad_norm": 3.6090643405914307,
-      "learning_rate": 0.00015447529726975,
-      "loss": 1.6502,
-      "step": 867
-    },
-    {
-      "epoch": 0.5455688246385921,
-      "grad_norm": 4.579808235168457,
-      "learning_rate": 0.00015424980865317816,
-      "loss": 1.8025,
-      "step": 868
-    },
-    {
-      "epoch": 0.5461973601508485,
-      "grad_norm": 2.9439306259155273,
-      "learning_rate": 0.00015402395312509178,
-      "loss": 1.8314,
-      "step": 869
-    },
-    {
-      "epoch": 0.5468258956631049,
-      "grad_norm": 3.228983163833618,
-      "learning_rate": 0.00015379773255824454,
-      "loss": 1.6519,
-      "step": 870
-    },
-    {
-      "epoch": 0.5474544311753614,
-      "grad_norm": 3.073241949081421,
-      "learning_rate": 0.0001535711488284171,
-      "loss": 1.4897,
-      "step": 871
-    },
-    {
-      "epoch": 0.5480829666876178,
-      "grad_norm": 3.359070062637329,
-      "learning_rate": 0.00015334420381440115,
-      "loss": 1.9755,
-      "step": 872
-    },
-    {
-      "epoch": 0.5487115021998743,
-      "grad_norm": 2.6963229179382324,
-      "learning_rate": 0.00015311689939798435,
-      "loss": 1.5332,
-      "step": 873
-    },
-    {
-      "epoch": 0.5493400377121307,
-      "grad_norm": 4.286027431488037,
-      "learning_rate": 0.0001528892374639343,
-      "loss": 1.5066,
-      "step": 874
-    },
-    {
-      "epoch": 0.5499685732243872,
-      "grad_norm": 3.306358814239502,
-      "learning_rate": 0.00015266121989998313,
-      "loss": 1.2646,
-      "step": 875
-    },
-    {
-      "epoch": 0.5505971087366436,
-      "grad_norm": 4.356008529663086,
-      "learning_rate": 0.00015243284859681178,
-      "loss": 1.4592,
-      "step": 876
-    },
-    {
-      "epoch": 0.5512256442489001,
-      "grad_norm": 2.7557637691497803,
-      "learning_rate": 0.0001522041254480343,
-      "loss": 2.0077,
-      "step": 877
-    },
-    {
-      "epoch": 0.5518541797611565,
-      "grad_norm": 5.654608249664307,
-      "learning_rate": 0.0001519750523501823,
-      "loss": 1.5102,
-      "step": 878
-    },
-    {
-      "epoch": 0.552482715273413,
-      "grad_norm": 3.0355632305145264,
-      "learning_rate": 0.00015174563120268886,
-      "loss": 1.7046,
-      "step": 879
-    },
-    {
-      "epoch": 0.5531112507856694,
-      "grad_norm": 2.3773937225341797,
-      "learning_rate": 0.00015151586390787337,
-      "loss": 2.0118,
-      "step": 880
-    },
-    {
-      "epoch": 0.5537397862979259,
-      "grad_norm": 1.9712527990341187,
-      "learning_rate": 0.00015128575237092505,
-      "loss": 1.6286,
-      "step": 881
-    },
-    {
-      "epoch": 0.5543683218101823,
-      "grad_norm": 2.4755544662475586,
-      "learning_rate": 0.0001510552984998878,
-      "loss": 1.7739,
-      "step": 882
-    },
-    {
-      "epoch": 0.5549968573224388,
-      "grad_norm": 1.8995095491409302,
-      "learning_rate": 0.00015082450420564393,
-      "loss": 1.9459,
-      "step": 883
-    },
-    {
-      "epoch": 0.5556253928346951,
-      "grad_norm": 1.985937237739563,
-      "learning_rate": 0.0001505933714018986,
-      "loss": 1.579,
-      "step": 884
-    },
-    {
-      "epoch": 0.5562539283469516,
-      "grad_norm": 2.6388299465179443,
-      "learning_rate": 0.00015036190200516366,
-      "loss": 1.6257,
-      "step": 885
-    },
-    {
-      "epoch": 0.556882463859208,
-      "grad_norm": 1.895621418952942,
-      "learning_rate": 0.0001501300979347421,
-      "loss": 1.8962,
-      "step": 886
-    },
-    {
-      "epoch": 0.5575109993714645,
-      "grad_norm": 54.625526428222656,
-      "learning_rate": 0.00014989796111271187,
-      "loss": 1.7338,
-      "step": 887
-    },
-    {
-      "epoch": 0.5581395348837209,
-      "grad_norm": 2.2018158435821533,
-      "learning_rate": 0.00014966549346391009,
-      "loss": 1.8835,
-      "step": 888
-    },
-    {
-      "epoch": 0.5587680703959774,
-      "grad_norm": 5.001894474029541,
-      "learning_rate": 0.00014943269691591692,
-      "loss": 1.7645,
-      "step": 889
-    },
-    {
-      "epoch": 0.5593966059082338,
-      "grad_norm": 24.939252853393555,
-      "learning_rate": 0.0001491995733990399,
-      "loss": 1.7232,
-      "step": 890
-    },
-    {
-      "epoch": 0.5600251414204902,
-      "grad_norm": 4.670384883880615,
-      "learning_rate": 0.00014896612484629755,
-      "loss": 1.5004,
-      "step": 891
-    },
-    {
-      "epoch": 0.5606536769327467,
-      "grad_norm": 2.6586263179779053,
-      "learning_rate": 0.00014873235319340359,
-      "loss": 1.6975,
-      "step": 892
-    },
-    {
-      "epoch": 0.5612822124450031,
-      "grad_norm": 2.209890604019165,
-      "learning_rate": 0.00014849826037875084,
-      "loss": 1.5577,
-      "step": 893
-    },
-    {
-      "epoch": 0.5619107479572596,
-      "grad_norm": 3.994396686553955,
-      "learning_rate": 0.00014826384834339522,
-      "loss": 1.2563,
-      "step": 894
-    },
-    {
-      "epoch": 0.562539283469516,
-      "grad_norm": 2.467743158340454,
-      "learning_rate": 0.00014802911903103935,
-      "loss": 1.8903,
-      "step": 895
-    },
-    {
-      "epoch": 0.5631678189817725,
-      "grad_norm": 2.7943837642669678,
-      "learning_rate": 0.00014779407438801685,
-      "loss": 1.8327,
-      "step": 896
-    },
-    {
-      "epoch": 0.5637963544940289,
-      "grad_norm": 3.3911454677581787,
-      "learning_rate": 0.00014755871636327594,
-      "loss": 1.4657,
-      "step": 897
-    },
-    {
-      "epoch": 0.5644248900062854,
-      "grad_norm": 2.7245395183563232,
-      "learning_rate": 0.00014732304690836336,
-      "loss": 1.6989,
-      "step": 898
-    },
-    {
-      "epoch": 0.5650534255185418,
-      "grad_norm": 2.283728837966919,
-      "learning_rate": 0.00014708706797740814,
-      "loss": 1.6395,
-      "step": 899
-    },
-    {
-      "epoch": 0.5656819610307983,
-      "grad_norm": 6.15742826461792,
-      "learning_rate": 0.0001468507815271055,
-      "loss": 1.5643,
-      "step": 900
-    },
-    {
-      "epoch": 0.5663104965430547,
-      "grad_norm": 3.2166006565093994,
-      "learning_rate": 0.00014661418951670042,
-      "loss": 2.0207,
-      "step": 901
-    },
-    {
-      "epoch": 0.5669390320553112,
-      "grad_norm": 2.7222771644592285,
-      "learning_rate": 0.00014637729390797172,
-      "loss": 1.8429,
-      "step": 902
-    },
-    {
-      "epoch": 0.5675675675675675,
-      "grad_norm": 2.573390483856201,
-      "learning_rate": 0.00014614009666521542,
-      "loss": 1.5806,
-      "step": 903
-    },
-    {
-      "epoch": 0.568196103079824,
-      "grad_norm": 2.363739490509033,
-      "learning_rate": 0.00014590259975522877,
-      "loss": 1.6681,
-      "step": 904
-    },
-    {
-      "epoch": 0.5688246385920804,
-      "grad_norm": 2.040877342224121,
-      "learning_rate": 0.0001456648051472937,
-      "loss": 1.9898,
-      "step": 905
-    },
-    {
-      "epoch": 0.5694531741043369,
-      "grad_norm": 2.5492324829101562,
-      "learning_rate": 0.00014542671481316072,
-      "loss": 1.111,
-      "step": 906
-    },
-    {
-      "epoch": 0.5700817096165933,
-      "grad_norm": 9.515697479248047,
-      "learning_rate": 0.00014518833072703227,
-      "loss": 1.8542,
-      "step": 907
-    },
-    {
-      "epoch": 0.5707102451288498,
-      "grad_norm": 2.2363474369049072,
-      "learning_rate": 0.00014494965486554678,
-      "loss": 1.7958,
-      "step": 908
-    },
-    {
-      "epoch": 0.5713387806411062,
-      "grad_norm": 4.901029109954834,
-      "learning_rate": 0.0001447106892077618,
-      "loss": 1.9061,
-      "step": 909
-    },
-    {
-      "epoch": 0.5719673161533627,
-      "grad_norm": 7.2911882400512695,
-      "learning_rate": 0.00014447143573513796,
-      "loss": 1.3471,
-      "step": 910
-    },
-    {
-      "epoch": 0.5725958516656191,
-      "grad_norm": 2.8644142150878906,
-      "learning_rate": 0.00014423189643152226,
-      "loss": 1.6385,
-      "step": 911
-    },
-    {
-      "epoch": 0.5732243871778756,
-      "grad_norm": 2.798529624938965,
-      "learning_rate": 0.00014399207328313194,
-      "loss": 1.8201,
-      "step": 912
-    },
-    {
-      "epoch": 0.573852922690132,
-      "grad_norm": 2.2028634548187256,
-      "learning_rate": 0.00014375196827853766,
-      "loss": 1.6705,
-      "step": 913
-    },
-    {
-      "epoch": 0.5744814582023884,
-      "grad_norm": 2.8815603256225586,
-      "learning_rate": 0.00014351158340864732,
-      "loss": 1.7115,
-      "step": 914
-    },
-    {
-      "epoch": 0.5751099937146449,
-      "grad_norm": 3.91245436668396,
-      "learning_rate": 0.00014327092066668932,
-      "loss": 1.8134,
-      "step": 915
-    },
-    {
-      "epoch": 0.5757385292269013,
-      "grad_norm": 2.8592488765716553,
-      "learning_rate": 0.00014302998204819618,
-      "loss": 1.5497,
-      "step": 916
-    },
-    {
-      "epoch": 0.5763670647391578,
-      "grad_norm": 2.7535643577575684,
-      "learning_rate": 0.0001427887695509879,
-      "loss": 1.6112,
-      "step": 917
-    },
-    {
-      "epoch": 0.5769956002514142,
-      "grad_norm": 3.177537679672241,
-      "learning_rate": 0.00014254728517515547,
-      "loss": 1.7777,
-      "step": 918
-    },
-    {
-      "epoch": 0.5776241357636707,
-      "grad_norm": 2.271500825881958,
-      "learning_rate": 0.00014230553092304415,
-      "loss": 1.9161,
-      "step": 919
-    },
-    {
-      "epoch": 0.578252671275927,
-      "grad_norm": 2.780168056488037,
-      "learning_rate": 0.00014206350879923714,
-      "loss": 1.602,
-      "step": 920
-    },
-    {
-      "epoch": 0.5788812067881836,
-      "grad_norm": 1.8702342510223389,
-      "learning_rate": 0.00014182122081053865,
-      "loss": 1.6333,
-      "step": 921
-    },
-    {
-      "epoch": 0.57950974230044,
-      "grad_norm": 2.2033650875091553,
-      "learning_rate": 0.00014157866896595745,
-      "loss": 1.7852,
-      "step": 922
-    },
-    {
-      "epoch": 0.5801382778126964,
-      "grad_norm": 2.3561549186706543,
-      "learning_rate": 0.00014133585527669007,
-      "loss": 1.5509,
-      "step": 923
-    },
-    {
-      "epoch": 0.5807668133249528,
-      "grad_norm": 2.623044967651367,
-      "learning_rate": 0.00014109278175610435,
-      "loss": 1.9336,
-      "step": 924
-    },
-    {
-      "epoch": 0.5813953488372093,
-      "grad_norm": 2.6602065563201904,
-      "learning_rate": 0.00014084945041972256,
-      "loss": 2.0173,
-      "step": 925
-    },
-    {
-      "epoch": 0.5820238843494657,
-      "grad_norm": 7.116496562957764,
-      "learning_rate": 0.0001406058632852046,
-      "loss": 1.8753,
-      "step": 926
-    },
-    {
-      "epoch": 0.5826524198617222,
-      "grad_norm": 6.817981243133545,
-      "learning_rate": 0.0001403620223723316,
-      "loss": 1.6024,
-      "step": 927
-    },
-    {
-      "epoch": 0.5832809553739786,
-      "grad_norm": 1.9530831575393677,
-      "learning_rate": 0.00014011792970298887,
-      "loss": 1.5929,
-      "step": 928
-    },
-    {
-      "epoch": 0.5839094908862351,
-      "grad_norm": 3.191023826599121,
-      "learning_rate": 0.0001398735873011492,
-      "loss": 1.6694,
-      "step": 929
-    },
-    {
-      "epoch": 0.5845380263984915,
-      "grad_norm": 2.2665297985076904,
-      "learning_rate": 0.0001396289971928562,
-      "loss": 1.5795,
-      "step": 930
-    },
-    {
-      "epoch": 0.585166561910748,
-      "grad_norm": 3.497770071029663,
-      "learning_rate": 0.00013938416140620738,
-      "loss": 1.8285,
-      "step": 931
-    },
-    {
-      "epoch": 0.5857950974230044,
-      "grad_norm": 4.176694869995117,
-      "learning_rate": 0.00013913908197133742,
-      "loss": 1.2752,
-      "step": 932
-    },
-    {
-      "epoch": 0.5864236329352609,
-      "grad_norm": 2.205921173095703,
-      "learning_rate": 0.00013889376092040122,
-      "loss": 1.7818,
-      "step": 933
-    },
-    {
-      "epoch": 0.5870521684475173,
-      "grad_norm": 2.4708597660064697,
-      "learning_rate": 0.0001386482002875571,
-      "loss": 1.7249,
-      "step": 934
-    },
-    {
-      "epoch": 0.5876807039597737,
-      "grad_norm": 4.025508880615234,
-      "learning_rate": 0.00013840240210895007,
-      "loss": 1.2812,
-      "step": 935
-    },
-    {
-      "epoch": 0.5883092394720302,
-      "grad_norm": 2.7530086040496826,
-      "learning_rate": 0.00013815636842269468,
-      "loss": 1.746,
-      "step": 936
-    },
-    {
-      "epoch": 0.5889377749842866,
-      "grad_norm": 1.9235401153564453,
-      "learning_rate": 0.00013791010126885838,
-      "loss": 2.1382,
-      "step": 937
-    },
-    {
-      "epoch": 0.5895663104965431,
-      "grad_norm": 2.125422239303589,
-      "learning_rate": 0.00013766360268944444,
-      "loss": 1.6725,
-      "step": 938
-    },
-    {
-      "epoch": 0.5901948460087995,
-      "grad_norm": 2.940282106399536,
-      "learning_rate": 0.0001374168747283751,
-      "loss": 1.4106,
-      "step": 939
-    },
-    {
-      "epoch": 0.590823381521056,
-      "grad_norm": 3.4331438541412354,
-      "learning_rate": 0.00013716991943147453,
-      "loss": 1.2228,
-      "step": 940
-    },
-    {
-      "epoch": 0.5914519170333123,
-      "grad_norm": 2.6568222045898438,
-      "learning_rate": 0.000136922738846452,
-      "loss": 1.8888,
-      "step": 941
-    },
-    {
-      "epoch": 0.5920804525455688,
-      "grad_norm": 2.1608529090881348,
-      "learning_rate": 0.00013667533502288476,
-      "loss": 1.7013,
-      "step": 942
-    },
-    {
-      "epoch": 0.5927089880578252,
-      "grad_norm": 2.2908928394317627,
-      "learning_rate": 0.00013642771001220121,
-      "loss": 1.6208,
-      "step": 943
-    },
-    {
-      "epoch": 0.5933375235700817,
-      "grad_norm": 3.6159627437591553,
-      "learning_rate": 0.00013617986586766373,
-      "loss": 1.4259,
-      "step": 944
-    },
-    {
-      "epoch": 0.5939660590823381,
-      "grad_norm": 2.032099485397339,
-      "learning_rate": 0.00013593180464435166,
-      "loss": 1.8553,
-      "step": 945
-    },
-    {
-      "epoch": 0.5945945945945946,
-      "grad_norm": 7.025946140289307,
-      "learning_rate": 0.00013568352839914445,
-      "loss": 1.6668,
-      "step": 946
-    },
-    {
-      "epoch": 0.595223130106851,
-      "grad_norm": 2.595669746398926,
-      "learning_rate": 0.00013543503919070439,
-      "loss": 1.7053,
-      "step": 947
-    },
-    {
-      "epoch": 0.5958516656191075,
-      "grad_norm": 2.9132773876190186,
-      "learning_rate": 0.0001351863390794596,
-      "loss": 1.6292,
-      "step": 948
-    },
-    {
-      "epoch": 0.5964802011313639,
-      "grad_norm": 2.3960158824920654,
-      "learning_rate": 0.00013493743012758707,
-      "loss": 1.557,
-      "step": 949
-    },
-    {
-      "epoch": 0.5971087366436204,
-      "grad_norm": 1.575936198234558,
-      "learning_rate": 0.00013468831439899533,
-      "loss": 1.6991,
-      "step": 950
-    },
-    {
-      "epoch": 0.5977372721558768,
-      "grad_norm": 2.822359800338745,
-      "learning_rate": 0.00013443899395930762,
-      "loss": 1.391,
-      "step": 951
-    },
-    {
-      "epoch": 0.5983658076681333,
-      "grad_norm": 5.096828937530518,
-      "learning_rate": 0.00013418947087584445,
-      "loss": 1.9117,
-      "step": 952
-    },
-    {
-      "epoch": 0.5989943431803897,
-      "grad_norm": 4.0271315574646,
-      "learning_rate": 0.00013393974721760674,
-      "loss": 1.3417,
-      "step": 953
-    },
-    {
-      "epoch": 0.5996228786926462,
-      "grad_norm": 2.699956178665161,
-      "learning_rate": 0.0001336898250552584,
-      "loss": 1.7204,
-      "step": 954
-    },
-    {
-      "epoch": 0.6002514142049026,
-      "grad_norm": 3.784418821334839,
-      "learning_rate": 0.0001334397064611095,
-      "loss": 1.3982,
-      "step": 955
-    },
-    {
-      "epoch": 0.600879949717159,
-      "grad_norm": 2.163050413131714,
-      "learning_rate": 0.00013318939350909868,
-      "loss": 1.6849,
-      "step": 956
-    },
-    {
-      "epoch": 0.6015084852294155,
-      "grad_norm": 2.501710891723633,
-      "learning_rate": 0.00013293888827477633,
-      "loss": 1.6264,
-      "step": 957
-    },
-    {
-      "epoch": 0.6021370207416719,
-      "grad_norm": 2.0204994678497314,
-      "learning_rate": 0.00013268819283528707,
-      "loss": 1.6999,
-      "step": 958
-    },
-    {
-      "epoch": 0.6027655562539284,
-      "grad_norm": 2.1536333560943604,
-      "learning_rate": 0.00013243730926935278,
-      "loss": 1.6226,
-      "step": 959
-    },
-    {
-      "epoch": 0.6033940917661847,
-      "grad_norm": 2.409135103225708,
-      "learning_rate": 0.00013218623965725518,
-      "loss": 1.8002,
-      "step": 960
-    },
-    {
-      "epoch": 0.6033940917661847,
-      "eval_loss": 1.0100071430206299,
-      "eval_runtime": 1572.7567,
-      "eval_samples_per_second": 1.639,
-      "eval_steps_per_second": 1.639,
-      "step": 960
-    }
-  ],
-  "logging_steps": 1,
-  "max_steps": 1591,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 160,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.227629746301436e+19,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}