diff --git "a/checkpoint-1737/trainer_state.json" "b/checkpoint-1737/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-1737/trainer_state.json"
@@ -0,0 +1,12209 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 869,
+  "global_step": 1737,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005757052389176742,
+      "grad_norm": 2.557003974914551,
+      "learning_rate": 0.0,
+      "loss": 5.4277,
+      "step": 1
+    },
+    {
+      "epoch": 0.0005757052389176742,
+      "eval_loss": 5.319709300994873,
+      "eval_runtime": 1026.7022,
+      "eval_samples_per_second": 2.496,
+      "eval_steps_per_second": 2.496,
+      "step": 1
+    },
+    {
+      "epoch": 0.0011514104778353484,
+      "grad_norm": 2.985229969024658,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 5.7019,
+      "step": 2
+    },
+    {
+      "epoch": 0.0017271157167530224,
+      "grad_norm": 3.0353081226348877,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1934,
+      "step": 3
+    },
+    {
+      "epoch": 0.002302820955670697,
+      "grad_norm": 3.724905490875244,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 5.4617,
+      "step": 4
+    },
+    {
+      "epoch": 0.0028785261945883708,
+      "grad_norm": 2.6505627632141113,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 5.4285,
+      "step": 5
+    },
+    {
+      "epoch": 0.0034542314335060447,
+      "grad_norm": 2.7363409996032715,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 5.8634,
+      "step": 6
+    },
+    {
+      "epoch": 0.004029936672423719,
+      "grad_norm": 3.082538366317749,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 4.7461,
+      "step": 7
+    },
+    {
+      "epoch": 0.004605641911341394,
+      "grad_norm": 9.095250129699707,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 7.5703,
+      "step": 8
+    },
+    {
+      "epoch": 0.0051813471502590676,
+      "grad_norm": 2.2597923278808594,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 5.3631,
+      "step": 9
+    },
+    {
+      "epoch": 0.0057570523891767415,
+      "grad_norm": 5.053525924682617,
+      "learning_rate": 3.6e-06,
+      "loss": 6.0132,
+      "step": 10
+    },
+    {
+      "epoch": 0.0063327576280944155,
+      "grad_norm": 2.7407820224761963,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 5.9776,
+      "step": 11
+    },
+    {
+      "epoch": 0.0069084628670120895,
+      "grad_norm": 2.4892263412475586,
+      "learning_rate": 4.4e-06,
+      "loss": 5.524,
+      "step": 12
+    },
+    {
+      "epoch": 0.007484168105929764,
+      "grad_norm": 2.5302274227142334,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 5.8044,
+      "step": 13
+    },
+    {
+      "epoch": 0.008059873344847437,
+      "grad_norm": 2.992504358291626,
+      "learning_rate": 5.2e-06,
+      "loss": 6.0307,
+      "step": 14
+    },
+    {
+      "epoch": 0.008635578583765112,
+      "grad_norm": 4.081608295440674,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 4.6732,
+      "step": 15
+    },
+    {
+      "epoch": 0.009211283822682787,
+      "grad_norm": 2.33296799659729,
+      "learning_rate": 6e-06,
+      "loss": 4.6356,
+      "step": 16
+    },
+    {
+      "epoch": 0.00978698906160046,
+      "grad_norm": 2.798452854156494,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 5.2941,
+      "step": 17
+    },
+    {
+      "epoch": 0.010362694300518135,
+      "grad_norm": 2.290029525756836,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 4.9405,
+      "step": 18
+    },
+    {
+      "epoch": 0.010938399539435808,
+      "grad_norm": 3.2164740562438965,
+      "learning_rate": 7.2e-06,
+      "loss": 5.6711,
+      "step": 19
+    },
+    {
+      "epoch": 0.011514104778353483,
+      "grad_norm": 2.4481987953186035,
+      "learning_rate": 7.6e-06,
+      "loss": 5.0366,
+      "step": 20
+    },
+    {
+      "epoch": 0.012089810017271158,
+      "grad_norm": 3.398063898086548,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 5.9377,
+      "step": 21
+    },
+    {
+      "epoch": 0.012665515256188831,
+      "grad_norm": 2.3936686515808105,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 5.4237,
+      "step": 22
+    },
+    {
+      "epoch": 0.013241220495106506,
+      "grad_norm": 2.7233810424804688,
+      "learning_rate": 8.8e-06,
+      "loss": 5.6551,
+      "step": 23
+    },
+    {
+      "epoch": 0.013816925734024179,
+      "grad_norm": 2.9957566261291504,
+      "learning_rate": 9.2e-06,
+      "loss": 4.7701,
+      "step": 24
+    },
+    {
+      "epoch": 0.014392630972941854,
+      "grad_norm": 6.397132396697998,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 6.4459,
+      "step": 25
+    },
+    {
+      "epoch": 0.014968336211859529,
+      "grad_norm": 3.0593409538269043,
+      "learning_rate": 1e-05,
+      "loss": 5.2758,
+      "step": 26
+    },
+    {
+      "epoch": 0.015544041450777202,
+      "grad_norm": 2.9723803997039795,
+      "learning_rate": 1.04e-05,
+      "loss": 5.6136,
+      "step": 27
+    },
+    {
+      "epoch": 0.016119746689694875,
+      "grad_norm": 2.03314471244812,
+      "learning_rate": 1.08e-05,
+      "loss": 5.3556,
+      "step": 28
+    },
+    {
+      "epoch": 0.01669545192861255,
+      "grad_norm": 1.777107834815979,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 5.1061,
+      "step": 29
+    },
+    {
+      "epoch": 0.017271157167530225,
+      "grad_norm": 3.2192044258117676,
+      "learning_rate": 1.16e-05,
+      "loss": 5.2414,
+      "step": 30
+    },
+    {
+      "epoch": 0.017846862406447898,
+      "grad_norm": 3.924452066421509,
+      "learning_rate": 1.2e-05,
+      "loss": 5.2754,
+      "step": 31
+    },
+    {
+      "epoch": 0.018422567645365574,
+      "grad_norm": 3.5611093044281006,
+      "learning_rate": 1.24e-05,
+      "loss": 5.2817,
+      "step": 32
+    },
+    {
+      "epoch": 0.018998272884283247,
+      "grad_norm": 2.5194263458251953,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 5.9063,
+      "step": 33
+    },
+    {
+      "epoch": 0.01957397812320092,
+      "grad_norm": 2.403895854949951,
+      "learning_rate": 1.32e-05,
+      "loss": 5.1161,
+      "step": 34
+    },
+    {
+      "epoch": 0.020149683362118594,
+      "grad_norm": 2.496400833129883,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 5.3049,
+      "step": 35
+    },
+    {
+      "epoch": 0.02072538860103627,
+      "grad_norm": 3.0970828533172607,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 5.5807,
+      "step": 36
+    },
+    {
+      "epoch": 0.021301093839953943,
+      "grad_norm": 3.941403388977051,
+      "learning_rate": 1.44e-05,
+      "loss": 6.0418,
+      "step": 37
+    },
+    {
+      "epoch": 0.021876799078871616,
+      "grad_norm": 2.291431188583374,
+      "learning_rate": 1.48e-05,
+      "loss": 4.3686,
+      "step": 38
+    },
+    {
+      "epoch": 0.022452504317789293,
+      "grad_norm": 2.783054828643799,
+      "learning_rate": 1.52e-05,
+      "loss": 5.15,
+      "step": 39
+    },
+    {
+      "epoch": 0.023028209556706966,
+      "grad_norm": 3.579267978668213,
+      "learning_rate": 1.56e-05,
+      "loss": 5.7507,
+      "step": 40
+    },
+    {
+      "epoch": 0.02360391479562464,
+      "grad_norm": 3.5277323722839355,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 6.112,
+      "step": 41
+    },
+    {
+      "epoch": 0.024179620034542316,
+      "grad_norm": 2.5100817680358887,
+      "learning_rate": 1.6400000000000002e-05,
+      "loss": 5.2133,
+      "step": 42
+    },
+    {
+      "epoch": 0.02475532527345999,
+      "grad_norm": 2.3821561336517334,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 6.0345,
+      "step": 43
+    },
+    {
+      "epoch": 0.025331030512377662,
+      "grad_norm": 3.0675108432769775,
+      "learning_rate": 1.7199999999999998e-05,
+      "loss": 5.2294,
+      "step": 44
+    },
+    {
+      "epoch": 0.025906735751295335,
+      "grad_norm": 2.8790383338928223,
+      "learning_rate": 1.76e-05,
+      "loss": 5.6393,
+      "step": 45
+    },
+    {
+      "epoch": 0.02648244099021301,
+      "grad_norm": 3.3649141788482666,
+      "learning_rate": 1.8e-05,
+      "loss": 6.014,
+      "step": 46
+    },
+    {
+      "epoch": 0.027058146229130685,
+      "grad_norm": 3.4695286750793457,
+      "learning_rate": 1.84e-05,
+      "loss": 5.3457,
+      "step": 47
+    },
+    {
+      "epoch": 0.027633851468048358,
+      "grad_norm": 3.303622245788574,
+      "learning_rate": 1.88e-05,
+      "loss": 5.593,
+      "step": 48
+    },
+    {
+      "epoch": 0.028209556706966035,
+      "grad_norm": 2.481895923614502,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 5.1439,
+      "step": 49
+    },
+    {
+      "epoch": 0.028785261945883708,
+      "grad_norm": 2.888579845428467,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 4.6318,
+      "step": 50
+    },
+    {
+      "epoch": 0.02936096718480138,
+      "grad_norm": 3.4528300762176514,
+      "learning_rate": 2e-05,
+      "loss": 5.0376,
+      "step": 51
+    },
+    {
+      "epoch": 0.029936672423719057,
+      "grad_norm": 3.6751370429992676,
+      "learning_rate": 2.04e-05,
+      "loss": 4.9183,
+      "step": 52
+    },
+    {
+      "epoch": 0.03051237766263673,
+      "grad_norm": 3.382035970687866,
+      "learning_rate": 2.08e-05,
+      "loss": 5.499,
+      "step": 53
+    },
+    {
+      "epoch": 0.031088082901554404,
+      "grad_norm": 2.8802406787872314,
+      "learning_rate": 2.12e-05,
+      "loss": 5.3177,
+      "step": 54
+    },
+    {
+      "epoch": 0.03166378814047208,
+      "grad_norm": 6.158539772033691,
+      "learning_rate": 2.16e-05,
+      "loss": 6.2133,
+      "step": 55
+    },
+    {
+      "epoch": 0.03223949337938975,
+      "grad_norm": 2.599864959716797,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 5.3691,
+      "step": 56
+    },
+    {
+      "epoch": 0.03281519861830743,
+      "grad_norm": 3.4526188373565674,
+      "learning_rate": 2.2400000000000002e-05,
+      "loss": 5.3801,
+      "step": 57
+    },
+    {
+      "epoch": 0.0333909038572251,
+      "grad_norm": 9.494807243347168,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 7.3116,
+      "step": 58
+    },
+    {
+      "epoch": 0.033966609096142776,
+      "grad_norm": 4.3456130027771,
+      "learning_rate": 2.32e-05,
+      "loss": 4.7467,
+      "step": 59
+    },
+    {
+      "epoch": 0.03454231433506045,
+      "grad_norm": 3.8471431732177734,
+      "learning_rate": 2.36e-05,
+      "loss": 5.2742,
+      "step": 60
+    },
+    {
+      "epoch": 0.03511801957397812,
+      "grad_norm": 3.985994815826416,
+      "learning_rate": 2.4e-05,
+      "loss": 5.4615,
+      "step": 61
+    },
+    {
+      "epoch": 0.035693724812895795,
+      "grad_norm": 9.588626861572266,
+      "learning_rate": 2.44e-05,
+      "loss": 6.8261,
+      "step": 62
+    },
+    {
+      "epoch": 0.03626943005181347,
+      "grad_norm": 5.3343915939331055,
+      "learning_rate": 2.48e-05,
+      "loss": 6.0899,
+      "step": 63
+    },
+    {
+      "epoch": 0.03684513529073115,
+      "grad_norm": 5.611617088317871,
+      "learning_rate": 2.5200000000000003e-05,
+      "loss": 6.4523,
+      "step": 64
+    },
+    {
+      "epoch": 0.03742084052964882,
+      "grad_norm": 4.497012615203857,
+      "learning_rate": 2.5600000000000002e-05,
+      "loss": 4.787,
+      "step": 65
+    },
+    {
+      "epoch": 0.037996545768566495,
+      "grad_norm": 5.032821178436279,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 5.6337,
+      "step": 66
+    },
+    {
+      "epoch": 0.03857225100748417,
+      "grad_norm": 3.732733726501465,
+      "learning_rate": 2.64e-05,
+      "loss": 5.5212,
+      "step": 67
+    },
+    {
+      "epoch": 0.03914795624640184,
+      "grad_norm": 4.3597517013549805,
+      "learning_rate": 2.6800000000000004e-05,
+      "loss": 4.647,
+      "step": 68
+    },
+    {
+      "epoch": 0.039723661485319514,
+      "grad_norm": 5.359225273132324,
+      "learning_rate": 2.7200000000000004e-05,
+      "loss": 5.7052,
+      "step": 69
+    },
+    {
+      "epoch": 0.04029936672423719,
+      "grad_norm": 4.9161601066589355,
+      "learning_rate": 2.7600000000000003e-05,
+      "loss": 5.3191,
+      "step": 70
+    },
+    {
+      "epoch": 0.04087507196315487,
+      "grad_norm": 4.137385368347168,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 5.1797,
+      "step": 71
+    },
+    {
+      "epoch": 0.04145077720207254,
+      "grad_norm": 4.728359699249268,
+      "learning_rate": 2.84e-05,
+      "loss": 5.1125,
+      "step": 72
+    },
+    {
+      "epoch": 0.042026482440990214,
+      "grad_norm": 4.568793773651123,
+      "learning_rate": 2.88e-05,
+      "loss": 5.7705,
+      "step": 73
+    },
+    {
+      "epoch": 0.04260218767990789,
+      "grad_norm": 4.931026935577393,
+      "learning_rate": 2.9199999999999998e-05,
+      "loss": 5.1052,
+      "step": 74
+    },
+    {
+      "epoch": 0.04317789291882556,
+      "grad_norm": 4.697461128234863,
+      "learning_rate": 2.96e-05,
+      "loss": 5.1404,
+      "step": 75
+    },
+    {
+      "epoch": 0.04375359815774323,
+      "grad_norm": 6.393320083618164,
+      "learning_rate": 3e-05,
+      "loss": 6.2212,
+      "step": 76
+    },
+    {
+      "epoch": 0.04432930339666091,
+      "grad_norm": 5.876922607421875,
+      "learning_rate": 3.04e-05,
+      "loss": 5.7775,
+      "step": 77
+    },
+    {
+      "epoch": 0.044905008635578586,
+      "grad_norm": 4.749701499938965,
+      "learning_rate": 3.08e-05,
+      "loss": 4.7321,
+      "step": 78
+    },
+    {
+      "epoch": 0.04548071387449626,
+      "grad_norm": 4.894115447998047,
+      "learning_rate": 3.12e-05,
+      "loss": 5.2017,
+      "step": 79
+    },
+    {
+      "epoch": 0.04605641911341393,
+      "grad_norm": 5.125804424285889,
+      "learning_rate": 3.16e-05,
+      "loss": 5.1661,
+      "step": 80
+    },
+    {
+      "epoch": 0.046632124352331605,
+      "grad_norm": 7.571075439453125,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 6.1439,
+      "step": 81
+    },
+    {
+      "epoch": 0.04720782959124928,
+      "grad_norm": 4.469061374664307,
+      "learning_rate": 3.24e-05,
+      "loss": 5.1732,
+      "step": 82
+    },
+    {
+      "epoch": 0.04778353483016695,
+      "grad_norm": 4.565371513366699,
+      "learning_rate": 3.2800000000000004e-05,
+      "loss": 5.4892,
+      "step": 83
+    },
+    {
+      "epoch": 0.04835924006908463,
+      "grad_norm": 5.844489097595215,
+      "learning_rate": 3.32e-05,
+      "loss": 5.875,
+      "step": 84
+    },
+    {
+      "epoch": 0.048934945308002305,
+      "grad_norm": 10.564720153808594,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 5.9008,
+      "step": 85
+    },
+    {
+      "epoch": 0.04951065054691998,
+      "grad_norm": 6.923472881317139,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 5.4949,
+      "step": 86
+    },
+    {
+      "epoch": 0.05008635578583765,
+      "grad_norm": 6.902386665344238,
+      "learning_rate": 3.4399999999999996e-05,
+      "loss": 4.9801,
+      "step": 87
+    },
+    {
+      "epoch": 0.050662061024755324,
+      "grad_norm": 8.239148139953613,
+      "learning_rate": 3.48e-05,
+      "loss": 5.6578,
+      "step": 88
+    },
+    {
+      "epoch": 0.051237766263673,
+      "grad_norm": 6.162630081176758,
+      "learning_rate": 3.52e-05,
+      "loss": 4.9911,
+      "step": 89
+    },
+    {
+      "epoch": 0.05181347150259067,
+      "grad_norm": 7.2612433433532715,
+      "learning_rate": 3.56e-05,
+      "loss": 5.7976,
+      "step": 90
+    },
+    {
+      "epoch": 0.05238917674150835,
+      "grad_norm": 6.149419784545898,
+      "learning_rate": 3.6e-05,
+      "loss": 4.9756,
+      "step": 91
+    },
+    {
+      "epoch": 0.05296488198042602,
+      "grad_norm": 7.4116106033325195,
+      "learning_rate": 3.6400000000000004e-05,
+      "loss": 5.5805,
+      "step": 92
+    },
+    {
+      "epoch": 0.0535405872193437,
+      "grad_norm": 5.512300491333008,
+      "learning_rate": 3.68e-05,
+      "loss": 4.5575,
+      "step": 93
+    },
+    {
+      "epoch": 0.05411629245826137,
+      "grad_norm": 14.799551963806152,
+      "learning_rate": 3.72e-05,
+      "loss": 5.2244,
+      "step": 94
+    },
+    {
+      "epoch": 0.05469199769717904,
+      "grad_norm": 9.756938934326172,
+      "learning_rate": 3.76e-05,
+      "loss": 4.8444,
+      "step": 95
+    },
+    {
+      "epoch": 0.055267702936096716,
+      "grad_norm": 6.400147914886475,
+      "learning_rate": 3.8e-05,
+      "loss": 5.5091,
+      "step": 96
+    },
+    {
+      "epoch": 0.055843408175014396,
+      "grad_norm": 8.406181335449219,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 5.2641,
+      "step": 97
+    },
+    {
+      "epoch": 0.05641911341393207,
+      "grad_norm": 6.860042572021484,
+      "learning_rate": 3.88e-05,
+      "loss": 5.2917,
+      "step": 98
+    },
+    {
+      "epoch": 0.05699481865284974,
+      "grad_norm": 7.542653560638428,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 5.1584,
+      "step": 99
+    },
+    {
+      "epoch": 0.057570523891767415,
+      "grad_norm": 8.149137496948242,
+      "learning_rate": 3.960000000000001e-05,
+      "loss": 5.5326,
+      "step": 100
+    },
+    {
+      "epoch": 0.05814622913068509,
+      "grad_norm": 5.590121269226074,
+      "learning_rate": 4e-05,
+      "loss": 5.2789,
+      "step": 101
+    },
+    {
+      "epoch": 0.05872193436960276,
+      "grad_norm": 7.877676010131836,
+      "learning_rate": 4.0400000000000006e-05,
+      "loss": 4.8526,
+      "step": 102
+    },
+    {
+      "epoch": 0.059297639608520435,
+      "grad_norm": 5.773808479309082,
+      "learning_rate": 4.08e-05,
+      "loss": 5.033,
+      "step": 103
+    },
+    {
+      "epoch": 0.059873344847438115,
+      "grad_norm": 6.092824935913086,
+      "learning_rate": 4.12e-05,
+      "loss": 4.8936,
+      "step": 104
+    },
+    {
+      "epoch": 0.06044905008635579,
+      "grad_norm": 5.934675693511963,
+      "learning_rate": 4.16e-05,
+      "loss": 4.4764,
+      "step": 105
+    },
+    {
+      "epoch": 0.06102475532527346,
+      "grad_norm": 5.622652530670166,
+      "learning_rate": 4.2e-05,
+      "loss": 5.1344,
+      "step": 106
+    },
+    {
+      "epoch": 0.061600460564191134,
+      "grad_norm": 7.697418212890625,
+      "learning_rate": 4.24e-05,
+      "loss": 5.2087,
+      "step": 107
+    },
+    {
+      "epoch": 0.06217616580310881,
+      "grad_norm": 5.204082489013672,
+      "learning_rate": 4.2800000000000004e-05,
+      "loss": 4.6294,
+      "step": 108
+    },
+    {
+      "epoch": 0.06275187104202648,
+      "grad_norm": 6.288537979125977,
+      "learning_rate": 4.32e-05,
+      "loss": 5.3009,
+      "step": 109
+    },
+    {
+      "epoch": 0.06332757628094415,
+      "grad_norm": 6.717288017272949,
+      "learning_rate": 4.36e-05,
+      "loss": 5.5392,
+      "step": 110
+    },
+    {
+      "epoch": 0.06390328151986183,
+      "grad_norm": 5.432399272918701,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 4.3602,
+      "step": 111
+    },
+    {
+      "epoch": 0.0644789867587795,
+      "grad_norm": 6.823062896728516,
+      "learning_rate": 4.44e-05,
+      "loss": 5.7343,
+      "step": 112
+    },
+    {
+      "epoch": 0.06505469199769717,
+      "grad_norm": 6.532074928283691,
+      "learning_rate": 4.4800000000000005e-05,
+      "loss": 5.0605,
+      "step": 113
+    },
+    {
+      "epoch": 0.06563039723661486,
+      "grad_norm": 5.982126712799072,
+      "learning_rate": 4.52e-05,
+      "loss": 5.2182,
+      "step": 114
+    },
+    {
+      "epoch": 0.06620610247553253,
+      "grad_norm": 5.759943962097168,
+      "learning_rate": 4.5600000000000004e-05,
+      "loss": 4.9098,
+      "step": 115
+    },
+    {
+      "epoch": 0.0667818077144502,
+      "grad_norm": 5.147834300994873,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 4.8671,
+      "step": 116
+    },
+    {
+      "epoch": 0.06735751295336788,
+      "grad_norm": 8.015042304992676,
+      "learning_rate": 4.64e-05,
+      "loss": 5.7445,
+      "step": 117
+    },
+    {
+      "epoch": 0.06793321819228555,
+      "grad_norm": 7.161843299865723,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 5.9092,
+      "step": 118
+    },
+    {
+      "epoch": 0.06850892343120323,
+      "grad_norm": 9.394163131713867,
+      "learning_rate": 4.72e-05,
+      "loss": 4.7243,
+      "step": 119
+    },
+    {
+      "epoch": 0.0690846286701209,
+      "grad_norm": 4.96219539642334,
+      "learning_rate": 4.76e-05,
+      "loss": 4.7233,
+      "step": 120
+    },
+    {
+      "epoch": 0.06966033390903857,
+      "grad_norm": 6.473387241363525,
+      "learning_rate": 4.8e-05,
+      "loss": 5.1295,
+      "step": 121
+    },
+    {
+      "epoch": 0.07023603914795624,
+      "grad_norm": 6.797422885894775,
+      "learning_rate": 4.8400000000000004e-05,
+      "loss": 4.7697,
+      "step": 122
+    },
+    {
+      "epoch": 0.07081174438687392,
+      "grad_norm": 6.656020641326904,
+      "learning_rate": 4.88e-05,
+      "loss": 5.2377,
+      "step": 123
+    },
+    {
+      "epoch": 0.07138744962579159,
+      "grad_norm": 5.552718639373779,
+      "learning_rate": 4.92e-05,
+      "loss": 4.4741,
+      "step": 124
+    },
+    {
+      "epoch": 0.07196315486470926,
+      "grad_norm": 6.101820468902588,
+      "learning_rate": 4.96e-05,
+      "loss": 4.4192,
+      "step": 125
+    },
+    {
+      "epoch": 0.07253886010362694,
+      "grad_norm": 7.695935249328613,
+      "learning_rate": 5e-05,
+      "loss": 5.4128,
+      "step": 126
+    },
+    {
+      "epoch": 0.07311456534254462,
+      "grad_norm": 6.9946208000183105,
+      "learning_rate": 5.0400000000000005e-05,
+      "loss": 5.4829,
+      "step": 127
+    },
+    {
+      "epoch": 0.0736902705814623,
+      "grad_norm": 16.10480308532715,
+      "learning_rate": 5.08e-05,
+      "loss": 4.6945,
+      "step": 128
+    },
+    {
+      "epoch": 0.07426597582037997,
+      "grad_norm": 5.313148021697998,
+      "learning_rate": 5.1200000000000004e-05,
+      "loss": 4.2429,
+      "step": 129
+    },
+    {
+      "epoch": 0.07484168105929764,
+      "grad_norm": 5.506260871887207,
+      "learning_rate": 5.16e-05,
+      "loss": 4.7241,
+      "step": 130
+    },
+    {
+      "epoch": 0.07541738629821532,
+      "grad_norm": 5.655925273895264,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 5.4156,
+      "step": 131
+    },
+    {
+      "epoch": 0.07599309153713299,
+      "grad_norm": 6.528857231140137,
+      "learning_rate": 5.2400000000000007e-05,
+      "loss": 5.3606,
+      "step": 132
+    },
+    {
+      "epoch": 0.07656879677605066,
+      "grad_norm": 5.360299110412598,
+      "learning_rate": 5.28e-05,
+      "loss": 5.0686,
+      "step": 133
+    },
+    {
+      "epoch": 0.07714450201496834,
+      "grad_norm": 5.301785945892334,
+      "learning_rate": 5.3200000000000006e-05,
+      "loss": 4.845,
+      "step": 134
+    },
+    {
+      "epoch": 0.07772020725388601,
+      "grad_norm": 4.986385345458984,
+      "learning_rate": 5.360000000000001e-05,
+      "loss": 5.1493,
+      "step": 135
+    },
+    {
+      "epoch": 0.07829591249280368,
+      "grad_norm": 5.200460433959961,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 4.781,
+      "step": 136
+    },
+    {
+      "epoch": 0.07887161773172136,
+      "grad_norm": 7.154032230377197,
+      "learning_rate": 5.440000000000001e-05,
+      "loss": 5.8801,
+      "step": 137
+    },
+    {
+      "epoch": 0.07944732297063903,
+      "grad_norm": 4.641168117523193,
+      "learning_rate": 5.4800000000000004e-05,
+      "loss": 5.1929,
+      "step": 138
+    },
+    {
+      "epoch": 0.0800230282095567,
+      "grad_norm": 4.8809123039245605,
+      "learning_rate": 5.520000000000001e-05,
+      "loss": 5.0221,
+      "step": 139
+    },
+    {
+      "epoch": 0.08059873344847437,
+      "grad_norm": 5.0507402420043945,
+      "learning_rate": 5.560000000000001e-05,
+      "loss": 4.8543,
+      "step": 140
+    },
+    {
+      "epoch": 0.08117443868739206,
+      "grad_norm": 6.459733963012695,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 5.051,
+      "step": 141
+    },
+    {
+      "epoch": 0.08175014392630973,
+      "grad_norm": 6.107847690582275,
+      "learning_rate": 5.6399999999999995e-05,
+      "loss": 4.8338,
+      "step": 142
+    },
+    {
+      "epoch": 0.08232584916522741,
+      "grad_norm": 6.28361701965332,
+      "learning_rate": 5.68e-05,
+      "loss": 5.1373,
+      "step": 143
+    },
+    {
+      "epoch": 0.08290155440414508,
+      "grad_norm": 4.957414627075195,
+      "learning_rate": 5.72e-05,
+      "loss": 4.8154,
+      "step": 144
+    },
+    {
+      "epoch": 0.08347725964306275,
+      "grad_norm": 4.774332046508789,
+      "learning_rate": 5.76e-05,
+      "loss": 4.7262,
+      "step": 145
+    },
+    {
+      "epoch": 0.08405296488198043,
+      "grad_norm": 7.41762113571167,
+      "learning_rate": 5.8e-05,
+      "loss": 5.5137,
+      "step": 146
+    },
+    {
+      "epoch": 0.0846286701208981,
+      "grad_norm": 7.484424591064453,
+      "learning_rate": 5.8399999999999997e-05,
+      "loss": 5.766,
+      "step": 147
+    },
+    {
+      "epoch": 0.08520437535981577,
+      "grad_norm": 4.917182922363281,
+      "learning_rate": 5.88e-05,
+      "loss": 5.0193,
+      "step": 148
+    },
+    {
+      "epoch": 0.08578008059873345,
+      "grad_norm": 4.608645915985107,
+      "learning_rate": 5.92e-05,
+      "loss": 5.0873,
+      "step": 149
+    },
+    {
+      "epoch": 0.08635578583765112,
+      "grad_norm": 6.5947794914245605,
+      "learning_rate": 5.96e-05,
+      "loss": 4.9855,
+      "step": 150
+    },
+    {
+      "epoch": 0.08693149107656879,
+      "grad_norm": 3.8302507400512695,
+      "learning_rate": 6e-05,
+      "loss": 3.7953,
+      "step": 151
+    },
+    {
+      "epoch": 0.08750719631548647,
+      "grad_norm": 3.6352171897888184,
+      "learning_rate": 6.04e-05,
+      "loss": 4.1647,
+      "step": 152
+    },
+    {
+      "epoch": 0.08808290155440414,
+      "grad_norm": 4.818563461303711,
+      "learning_rate": 6.08e-05,
+      "loss": 4.2128,
+      "step": 153
+    },
+    {
+      "epoch": 0.08865860679332183,
+      "grad_norm": 7.7323503494262695,
+      "learning_rate": 6.12e-05,
+      "loss": 5.4562,
+      "step": 154
+    },
+    {
+      "epoch": 0.0892343120322395,
+      "grad_norm": 5.785284996032715,
+      "learning_rate": 6.16e-05,
+      "loss": 4.8956,
+      "step": 155
+    },
+    {
+      "epoch": 0.08981001727115717,
+      "grad_norm": 6.181385040283203,
+      "learning_rate": 6.2e-05,
+      "loss": 5.2373,
+      "step": 156
+    },
+    {
+      "epoch": 0.09038572251007485,
+      "grad_norm": 6.015028476715088,
+      "learning_rate": 6.24e-05,
+      "loss": 4.3663,
+      "step": 157
+    },
+    {
+      "epoch": 0.09096142774899252,
+      "grad_norm": 4.41657829284668,
+      "learning_rate": 6.280000000000001e-05,
+      "loss": 4.5991,
+      "step": 158
+    },
+    {
+      "epoch": 0.09153713298791019,
+      "grad_norm": 6.5107622146606445,
+      "learning_rate": 6.32e-05,
+      "loss": 4.8784,
+      "step": 159
+    },
+    {
+      "epoch": 0.09211283822682786,
+      "grad_norm": 4.11070442199707,
+      "learning_rate": 6.36e-05,
+      "loss": 4.6766,
+      "step": 160
+    },
+    {
+      "epoch": 0.09268854346574554,
+      "grad_norm": 8.204343795776367,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 5.5088,
+      "step": 161
+    },
+    {
+      "epoch": 0.09326424870466321,
+      "grad_norm": 3.9389288425445557,
+      "learning_rate": 6.440000000000001e-05,
+      "loss": 4.3476,
+      "step": 162
+    },
+    {
+      "epoch": 0.09383995394358088,
+      "grad_norm": 5.597643852233887,
+      "learning_rate": 6.48e-05,
+      "loss": 4.9976,
+      "step": 163
+    },
+    {
+      "epoch": 0.09441565918249856,
+      "grad_norm": 8.994287490844727,
+      "learning_rate": 6.52e-05,
+      "loss": 5.5959,
+      "step": 164
+    },
+    {
+      "epoch": 0.09499136442141623,
+      "grad_norm": 5.60779333114624,
+      "learning_rate": 6.560000000000001e-05,
+      "loss": 4.6283,
+      "step": 165
+    },
+    {
+      "epoch": 0.0955670696603339,
+      "grad_norm": 4.319982528686523,
+      "learning_rate": 6.6e-05,
+      "loss": 4.041,
+      "step": 166
+    },
+    {
+      "epoch": 0.09614277489925158,
+      "grad_norm": 5.684337615966797,
+      "learning_rate": 6.64e-05,
+      "loss": 4.8941,
+      "step": 167
+    },
+    {
+      "epoch": 0.09671848013816926,
+      "grad_norm": 3.872518539428711,
+      "learning_rate": 6.680000000000001e-05,
+      "loss": 4.2242,
+      "step": 168
+    },
+    {
+      "epoch": 0.09729418537708694,
+      "grad_norm": 4.826557636260986,
+      "learning_rate": 6.720000000000001e-05,
+      "loss": 4.8546,
+      "step": 169
+    },
+    {
+      "epoch": 0.09786989061600461,
+      "grad_norm": 4.660156726837158,
+      "learning_rate": 6.76e-05,
+      "loss": 4.3797,
+      "step": 170
+    },
+    {
+      "epoch": 0.09844559585492228,
+      "grad_norm": 4.616059303283691,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 4.7293,
+      "step": 171
+    },
+    {
+      "epoch": 0.09902130109383996,
+      "grad_norm": 7.685507774353027,
+      "learning_rate": 6.840000000000001e-05,
+      "loss": 5.6251,
+      "step": 172
+    },
+    {
+      "epoch": 0.09959700633275763,
+      "grad_norm": 7.424576282501221,
+      "learning_rate": 6.879999999999999e-05,
+      "loss": 4.8253,
+      "step": 173
+    },
+    {
+      "epoch": 0.1001727115716753,
+      "grad_norm": 4.379521369934082,
+      "learning_rate": 6.92e-05,
+      "loss": 4.5287,
+      "step": 174
+    },
+    {
+      "epoch": 0.10074841681059298,
+      "grad_norm": 4.753964424133301,
+      "learning_rate": 6.96e-05,
+      "loss": 4.5554,
+      "step": 175
+    },
+    {
+      "epoch": 0.10132412204951065,
+      "grad_norm": 4.559609413146973,
+      "learning_rate": 7e-05,
+      "loss": 4.5615,
+      "step": 176
+    },
+    {
+      "epoch": 0.10189982728842832,
+      "grad_norm": 5.178406238555908,
+      "learning_rate": 7.04e-05,
+      "loss": 4.6344,
+      "step": 177
+    },
+    {
+      "epoch": 0.102475532527346,
+      "grad_norm": 7.4183526039123535,
+      "learning_rate": 7.08e-05,
+      "loss": 4.5451,
+      "step": 178
+    },
+    {
+      "epoch": 0.10305123776626367,
+      "grad_norm": 5.832037448883057,
+      "learning_rate": 7.12e-05,
+      "loss": 4.7097,
+      "step": 179
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 4.9681925773620605,
+      "learning_rate": 7.16e-05,
+      "loss": 4.6288,
+      "step": 180
+    },
+    {
+      "epoch": 0.10420264824409903,
+      "grad_norm": 4.886664867401123,
+      "learning_rate": 7.2e-05,
+      "loss": 4.7019,
+      "step": 181
+    },
+    {
+      "epoch": 0.1047783534830167,
+      "grad_norm": 4.668741226196289,
+      "learning_rate": 7.24e-05,
+      "loss": 4.4534,
+      "step": 182
+    },
+    {
+      "epoch": 0.10535405872193437,
+      "grad_norm": 7.459389686584473,
+      "learning_rate": 7.280000000000001e-05,
+      "loss": 5.4758,
+      "step": 183
+    },
+    {
+      "epoch": 0.10592976396085205,
+      "grad_norm": 31.545869827270508,
+      "learning_rate": 7.32e-05,
+      "loss": 6.179,
+      "step": 184
+    },
+    {
+      "epoch": 0.10650546919976972,
+      "grad_norm": 9.739182472229004,
+      "learning_rate": 7.36e-05,
+      "loss": 4.9662,
+      "step": 185
+    },
+    {
+      "epoch": 0.1070811744386874,
+      "grad_norm": 4.12076997756958,
+      "learning_rate": 7.4e-05,
+      "loss": 3.88,
+      "step": 186
+    },
+    {
+      "epoch": 0.10765687967760507,
+      "grad_norm": 5.808717727661133,
+      "learning_rate": 7.44e-05,
+      "loss": 4.6157,
+      "step": 187
+    },
+    {
+      "epoch": 0.10823258491652274,
+      "grad_norm": 3.6208741664886475,
+      "learning_rate": 7.48e-05,
+      "loss": 3.9156,
+      "step": 188
+    },
+    {
+      "epoch": 0.10880829015544041,
+      "grad_norm": 4.674955368041992,
+      "learning_rate": 7.52e-05,
+      "loss": 4.4751,
+      "step": 189
+    },
+    {
+      "epoch": 0.10938399539435809,
+      "grad_norm": 5.331599235534668,
+      "learning_rate": 7.560000000000001e-05,
+      "loss": 4.3887,
+      "step": 190
+    },
+    {
+      "epoch": 0.10995970063327576,
+      "grad_norm": 5.1405534744262695,
+      "learning_rate": 7.6e-05,
+      "loss": 4.9114,
+      "step": 191
+    },
+    {
+      "epoch": 0.11053540587219343,
+      "grad_norm": 3.7066593170166016,
+      "learning_rate": 7.64e-05,
+      "loss": 3.8948,
+      "step": 192
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 5.185431003570557,
+      "learning_rate": 7.680000000000001e-05,
+      "loss": 4.232,
+      "step": 193
+    },
+    {
+      "epoch": 0.11168681635002879,
+      "grad_norm": 4.900607585906982,
+      "learning_rate": 7.72e-05,
+      "loss": 4.667,
+      "step": 194
+    },
+    {
+      "epoch": 0.11226252158894647,
+      "grad_norm": 5.091091632843018,
+      "learning_rate": 7.76e-05,
+      "loss": 4.3946,
+      "step": 195
+    },
+    {
+      "epoch": 0.11283822682786414,
+      "grad_norm": 4.859619617462158,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 4.6306,
+      "step": 196
+    },
+    {
+      "epoch": 0.11341393206678181,
+      "grad_norm": 3.544200897216797,
+      "learning_rate": 7.840000000000001e-05,
+      "loss": 4.2118,
+      "step": 197
+    },
+    {
+      "epoch": 0.11398963730569948,
+      "grad_norm": 8.28862190246582,
+      "learning_rate": 7.88e-05,
+      "loss": 4.4431,
+      "step": 198
+    },
+    {
+      "epoch": 0.11456534254461716,
+      "grad_norm": 6.373688220977783,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 4.7554,
+      "step": 199
+    },
+    {
+      "epoch": 0.11514104778353483,
+      "grad_norm": 6.8544392585754395,
+      "learning_rate": 7.960000000000001e-05,
+      "loss": 4.8723,
+      "step": 200
+    },
+    {
+      "epoch": 0.1157167530224525,
+      "grad_norm": 7.207869052886963,
+      "learning_rate": 8e-05,
+      "loss": 4.1096,
+      "step": 201
+    },
+    {
+      "epoch": 0.11629245826137018,
+      "grad_norm": 4.9073333740234375,
+      "learning_rate": 8.04e-05,
+      "loss": 3.6834,
+      "step": 202
+    },
+    {
+      "epoch": 0.11686816350028785,
+      "grad_norm": 6.523554801940918,
+      "learning_rate": 8.080000000000001e-05,
+      "loss": 4.4934,
+      "step": 203
+    },
+    {
+      "epoch": 0.11744386873920552,
+      "grad_norm": 9.581537246704102,
+      "learning_rate": 8.120000000000001e-05,
+      "loss": 4.8199,
+      "step": 204
+    },
+    {
+      "epoch": 0.1180195739781232,
+      "grad_norm": 5.319664001464844,
+      "learning_rate": 8.16e-05,
+      "loss": 4.0881,
+      "step": 205
+    },
+    {
+      "epoch": 0.11859527921704087,
+      "grad_norm": 7.609442710876465,
+      "learning_rate": 8.2e-05,
+      "loss": 5.1011,
+      "step": 206
+    },
+    {
+      "epoch": 0.11917098445595854,
+      "grad_norm": 5.437283515930176,
+      "learning_rate": 8.24e-05,
+      "loss": 4.7683,
+      "step": 207
+    },
+    {
+      "epoch": 0.11974668969487623,
+      "grad_norm": 9.015962600708008,
+      "learning_rate": 8.28e-05,
+      "loss": 5.1197,
+      "step": 208
+    },
+    {
+      "epoch": 0.1203223949337939,
+      "grad_norm": 5.41486120223999,
+      "learning_rate": 8.32e-05,
+      "loss": 4.2228,
+      "step": 209
+    },
+    {
+      "epoch": 0.12089810017271158,
+      "grad_norm": 4.068630218505859,
+      "learning_rate": 8.36e-05,
+      "loss": 3.9683,
+      "step": 210
+    },
+    {
+      "epoch": 0.12147380541162925,
+      "grad_norm": 4.818974494934082,
+      "learning_rate": 8.4e-05,
+      "loss": 4.3969,
+      "step": 211
+    },
+    {
+      "epoch": 0.12204951065054692,
+      "grad_norm": 8.309637069702148,
+      "learning_rate": 8.44e-05,
+      "loss": 4.8983,
+      "step": 212
+    },
+    {
+      "epoch": 0.1226252158894646,
+      "grad_norm": 5.997379302978516,
+      "learning_rate": 8.48e-05,
+      "loss": 4.6983,
+      "step": 213
+    },
+    {
+      "epoch": 0.12320092112838227,
+      "grad_norm": 6.416568279266357,
+      "learning_rate": 8.52e-05,
+      "loss": 4.6,
+      "step": 214
+    },
+    {
+      "epoch": 0.12377662636729994,
+      "grad_norm": 5.038214206695557,
+      "learning_rate": 8.560000000000001e-05,
+      "loss": 4.1803,
+      "step": 215
+    },
+    {
+      "epoch": 0.12435233160621761,
+      "grad_norm": 5.035988807678223,
+      "learning_rate": 8.6e-05,
+      "loss": 4.1585,
+      "step": 216
+    },
+    {
+      "epoch": 0.12492803684513529,
+      "grad_norm": 6.7663726806640625,
+      "learning_rate": 8.64e-05,
+      "loss": 4.4256,
+      "step": 217
+    },
+    {
+      "epoch": 0.12550374208405296,
+      "grad_norm": 5.394269943237305,
+      "learning_rate": 8.680000000000001e-05,
+      "loss": 3.9008,
+      "step": 218
+    },
+    {
+      "epoch": 0.12607944732297063,
+      "grad_norm": 5.4501800537109375,
+      "learning_rate": 8.72e-05,
+      "loss": 3.9869,
+      "step": 219
+    },
+    {
+      "epoch": 0.1266551525618883,
+      "grad_norm": 4.7380170822143555,
+      "learning_rate": 8.76e-05,
+      "loss": 4.0876,
+      "step": 220
+    },
+    {
+      "epoch": 0.12723085780080598,
+      "grad_norm": 6.059116840362549,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 4.147,
+      "step": 221
+    },
+    {
+      "epoch": 0.12780656303972365,
+      "grad_norm": 5.5021586418151855,
+      "learning_rate": 8.840000000000001e-05,
+      "loss": 4.4547,
+      "step": 222
+    },
+    {
+      "epoch": 0.12838226827864133,
+      "grad_norm": 4.760106563568115,
+      "learning_rate": 8.88e-05,
+      "loss": 4.075,
+      "step": 223
+    },
+    {
+      "epoch": 0.128957973517559,
+      "grad_norm": 7.5847649574279785,
+      "learning_rate": 8.92e-05,
+      "loss": 4.6163,
+      "step": 224
+    },
+    {
+      "epoch": 0.12953367875647667,
+      "grad_norm": 6.257955074310303,
+      "learning_rate": 8.960000000000001e-05,
+      "loss": 4.6043,
+      "step": 225
+    },
+    {
+      "epoch": 0.13010938399539435,
+      "grad_norm": 7.368046283721924,
+      "learning_rate": 9e-05,
+      "loss": 4.7961,
+      "step": 226
+    },
+    {
+      "epoch": 0.13068508923431202,
+      "grad_norm": 4.385096549987793,
+      "learning_rate": 9.04e-05,
+      "loss": 4.1968,
+      "step": 227
+    },
+    {
+      "epoch": 0.13126079447322972,
+      "grad_norm": 6.34293794631958,
+      "learning_rate": 9.080000000000001e-05,
+      "loss": 4.3076,
+      "step": 228
+    },
+    {
+      "epoch": 0.1318364997121474,
+      "grad_norm": 6.403743267059326,
+      "learning_rate": 9.120000000000001e-05,
+      "loss": 3.8917,
+      "step": 229
+    },
+    {
+      "epoch": 0.13241220495106507,
+      "grad_norm": 6.792156219482422,
+      "learning_rate": 9.16e-05,
+      "loss": 3.9843,
+      "step": 230
+    },
+    {
+      "epoch": 0.13298791018998274,
+      "grad_norm": 8.062408447265625,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 4.2562,
+      "step": 231
+    },
+    {
+      "epoch": 0.1335636154289004,
+      "grad_norm": 8.513936042785645,
+      "learning_rate": 9.240000000000001e-05,
+      "loss": 4.6536,
+      "step": 232
+    },
+    {
+      "epoch": 0.13413932066781808,
+      "grad_norm": 5.92789363861084,
+      "learning_rate": 9.28e-05,
+      "loss": 4.104,
+      "step": 233
+    },
+    {
+      "epoch": 0.13471502590673576,
+      "grad_norm": 44.009300231933594,
+      "learning_rate": 9.320000000000002e-05,
+      "loss": 4.8297,
+      "step": 234
+    },
+    {
+      "epoch": 0.13529073114565343,
+      "grad_norm": 5.342921257019043,
+      "learning_rate": 9.360000000000001e-05,
+      "loss": 4.0662,
+      "step": 235
+    },
+    {
+      "epoch": 0.1358664363845711,
+      "grad_norm": 5.618771076202393,
+      "learning_rate": 9.4e-05,
+      "loss": 4.1692,
+      "step": 236
+    },
+    {
+      "epoch": 0.13644214162348878,
+      "grad_norm": 6.6655473709106445,
+      "learning_rate": 9.44e-05,
+      "loss": 4.2759,
+      "step": 237
+    },
+    {
+      "epoch": 0.13701784686240645,
+      "grad_norm": 6.415508270263672,
+      "learning_rate": 9.48e-05,
+      "loss": 4.025,
+      "step": 238
+    },
+    {
+      "epoch": 0.13759355210132412,
+      "grad_norm": 62.65280532836914,
+      "learning_rate": 9.52e-05,
+      "loss": 5.3187,
+      "step": 239
+    },
+    {
+      "epoch": 0.1381692573402418,
+      "grad_norm": 5.9870147705078125,
+      "learning_rate": 9.56e-05,
+      "loss": 4.3549,
+      "step": 240
+    },
+    {
+      "epoch": 0.13874496257915947,
+      "grad_norm": 6.323814868927002,
+      "learning_rate": 9.6e-05,
+      "loss": 4.0618,
+      "step": 241
+    },
+    {
+      "epoch": 0.13932066781807714,
+      "grad_norm": 7.25873327255249,
+      "learning_rate": 9.64e-05,
+      "loss": 4.6113,
+      "step": 242
+    },
+    {
+      "epoch": 0.13989637305699482,
+      "grad_norm": 6.708962440490723,
+      "learning_rate": 9.680000000000001e-05,
+      "loss": 4.2734,
+      "step": 243
+    },
+    {
+      "epoch": 0.1404720782959125,
+      "grad_norm": 6.766256332397461,
+      "learning_rate": 9.72e-05,
+      "loss": 3.8169,
+      "step": 244
+    },
+    {
+      "epoch": 0.14104778353483016,
+      "grad_norm": 9.25779914855957,
+      "learning_rate": 9.76e-05,
+      "loss": 4.0823,
+      "step": 245
+    },
+    {
+      "epoch": 0.14162348877374784,
+      "grad_norm": 6.24402379989624,
+      "learning_rate": 9.8e-05,
+      "loss": 3.9761,
+      "step": 246
+    },
+    {
+      "epoch": 0.1421991940126655,
+      "grad_norm": 4.627258777618408,
+      "learning_rate": 9.84e-05,
+      "loss": 3.3376,
+      "step": 247
+    },
+    {
+      "epoch": 0.14277489925158318,
+      "grad_norm": 6.5364766120910645,
+      "learning_rate": 9.88e-05,
+      "loss": 3.9101,
+      "step": 248
+    },
+    {
+      "epoch": 0.14335060449050085,
+      "grad_norm": 6.722381591796875,
+      "learning_rate": 9.92e-05,
+      "loss": 4.2916,
+      "step": 249
+    },
+    {
+      "epoch": 0.14392630972941853,
+      "grad_norm": 7.2800493240356445,
+      "learning_rate": 9.960000000000001e-05,
+      "loss": 4.1714,
+      "step": 250
+    },
+    {
+      "epoch": 0.1445020149683362,
+      "grad_norm": 9.137832641601562,
+      "learning_rate": 0.0001,
+      "loss": 3.9733,
+      "step": 251
+    },
+    {
+      "epoch": 0.14507772020725387,
+      "grad_norm": 5.290084362030029,
+      "learning_rate": 0.0001004,
+      "loss": 3.8465,
+      "step": 252
+    },
+    {
+      "epoch": 0.14565342544617155,
+      "grad_norm": 7.146475791931152,
+      "learning_rate": 0.00010080000000000001,
+      "loss": 4.154,
+      "step": 253
+    },
+    {
+      "epoch": 0.14622913068508925,
+      "grad_norm": 5.462000370025635,
+      "learning_rate": 0.00010120000000000001,
+      "loss": 3.8403,
+      "step": 254
+    },
+    {
+      "epoch": 0.14680483592400692,
+      "grad_norm": 8.053996086120605,
+      "learning_rate": 0.0001016,
+      "loss": 4.224,
+      "step": 255
+    },
+    {
+      "epoch": 0.1473805411629246,
+      "grad_norm": 56.904518127441406,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 5.3512,
+      "step": 256
+    },
+    {
+      "epoch": 0.14795624640184227,
+      "grad_norm": 67.7396469116211,
+      "learning_rate": 0.00010240000000000001,
+      "loss": 4.136,
+      "step": 257
+    },
+    {
+      "epoch": 0.14853195164075994,
+      "grad_norm": 5.19423770904541,
+      "learning_rate": 0.0001028,
+      "loss": 3.6272,
+      "step": 258
+    },
+    {
+      "epoch": 0.1491076568796776,
+      "grad_norm": 6.946446418762207,
+      "learning_rate": 0.0001032,
+      "loss": 3.7617,
+      "step": 259
+    },
+    {
+      "epoch": 0.1496833621185953,
+      "grad_norm": 6.839754104614258,
+      "learning_rate": 0.00010360000000000001,
+      "loss": 4.2895,
+      "step": 260
+    },
+    {
+      "epoch": 0.15025906735751296,
+      "grad_norm": 7.3253254890441895,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 4.0997,
+      "step": 261
+    },
+    {
+      "epoch": 0.15083477259643063,
+      "grad_norm": 6.981521129608154,
+      "learning_rate": 0.0001044,
+      "loss": 3.4663,
+      "step": 262
+    },
+    {
+      "epoch": 0.1514104778353483,
+      "grad_norm": 6.424066543579102,
+      "learning_rate": 0.00010480000000000001,
+      "loss": 4.0914,
+      "step": 263
+    },
+    {
+      "epoch": 0.15198618307426598,
+      "grad_norm": 6.7790398597717285,
+      "learning_rate": 0.00010520000000000001,
+      "loss": 4.0818,
+      "step": 264
+    },
+    {
+      "epoch": 0.15256188831318365,
+      "grad_norm": 7.887113094329834,
+      "learning_rate": 0.0001056,
+      "loss": 4.3784,
+      "step": 265
+    },
+    {
+      "epoch": 0.15313759355210133,
+      "grad_norm": 8.3016939163208,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 3.7843,
+      "step": 266
+    },
+    {
+      "epoch": 0.153713298791019,
+      "grad_norm": 10.073237419128418,
+      "learning_rate": 0.00010640000000000001,
+      "loss": 4.0118,
+      "step": 267
+    },
+    {
+      "epoch": 0.15428900402993667,
+      "grad_norm": 6.9664106369018555,
+      "learning_rate": 0.00010680000000000001,
+      "loss": 3.8644,
+      "step": 268
+    },
+    {
+      "epoch": 0.15486470926885434,
+      "grad_norm": 8.479534149169922,
+      "learning_rate": 0.00010720000000000002,
+      "loss": 3.7009,
+      "step": 269
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": 8.317602157592773,
+      "learning_rate": 0.00010760000000000001,
+      "loss": 3.7018,
+      "step": 270
+    },
+    {
+      "epoch": 0.1560161197466897,
+      "grad_norm": 6.020889759063721,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 3.656,
+      "step": 271
+    },
+    {
+      "epoch": 0.15659182498560736,
+      "grad_norm": 7.147673606872559,
+      "learning_rate": 0.00010840000000000002,
+      "loss": 3.9216,
+      "step": 272
+    },
+    {
+      "epoch": 0.15716753022452504,
+      "grad_norm": 5.485556125640869,
+      "learning_rate": 0.00010880000000000002,
+      "loss": 3.4732,
+      "step": 273
+    },
+    {
+      "epoch": 0.1577432354634427,
+      "grad_norm": 7.432086944580078,
+      "learning_rate": 0.00010920000000000001,
+      "loss": 3.423,
+      "step": 274
+    },
+    {
+      "epoch": 0.15831894070236038,
+      "grad_norm": 6.897833824157715,
+      "learning_rate": 0.00010960000000000001,
+      "loss": 3.6169,
+      "step": 275
+    },
+    {
+      "epoch": 0.15889464594127806,
+      "grad_norm": 7.707437992095947,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 3.6883,
+      "step": 276
+    },
+    {
+      "epoch": 0.15947035118019573,
+      "grad_norm": 5.546234607696533,
+      "learning_rate": 0.00011040000000000001,
+      "loss": 3.8388,
+      "step": 277
+    },
+    {
+      "epoch": 0.1600460564191134,
+      "grad_norm": 10.001431465148926,
+      "learning_rate": 0.00011080000000000001,
+      "loss": 3.372,
+      "step": 278
+    },
+    {
+      "epoch": 0.16062176165803108,
+      "grad_norm": 8.793180465698242,
+      "learning_rate": 0.00011120000000000002,
+      "loss": 3.7929,
+      "step": 279
+    },
+    {
+      "epoch": 0.16119746689694875,
+      "grad_norm": 8.189177513122559,
+      "learning_rate": 0.00011160000000000002,
+      "loss": 4.0091,
+      "step": 280
+    },
+    {
+      "epoch": 0.16177317213586645,
+      "grad_norm": 6.998697280883789,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 3.648,
+      "step": 281
+    },
+    {
+      "epoch": 0.16234887737478412,
+      "grad_norm": 8.115317344665527,
+      "learning_rate": 0.00011240000000000002,
+      "loss": 4.0327,
+      "step": 282
+    },
+    {
+      "epoch": 0.1629245826137018,
+      "grad_norm": 7.597106456756592,
+      "learning_rate": 0.00011279999999999999,
+      "loss": 3.7811,
+      "step": 283
+    },
+    {
+      "epoch": 0.16350028785261947,
+      "grad_norm": 6.518374443054199,
+      "learning_rate": 0.0001132,
+      "loss": 3.3359,
+      "step": 284
+    },
+    {
+      "epoch": 0.16407599309153714,
+      "grad_norm": 6.962795257568359,
+      "learning_rate": 0.0001136,
+      "loss": 3.3726,
+      "step": 285
+    },
+    {
+      "epoch": 0.16465169833045482,
+      "grad_norm": 8.1845703125,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 4.0042,
+      "step": 286
+    },
+    {
+      "epoch": 0.1652274035693725,
+      "grad_norm": 6.869271755218506,
+      "learning_rate": 0.0001144,
+      "loss": 3.4989,
+      "step": 287
+    },
+    {
+      "epoch": 0.16580310880829016,
+      "grad_norm": 12.261098861694336,
+      "learning_rate": 0.0001148,
+      "loss": 4.1045,
+      "step": 288
+    },
+    {
+      "epoch": 0.16637881404720783,
+      "grad_norm": 6.912962913513184,
+      "learning_rate": 0.0001152,
+      "loss": 3.6853,
+      "step": 289
+    },
+    {
+      "epoch": 0.1669545192861255,
+      "grad_norm": 8.545379638671875,
+      "learning_rate": 0.00011559999999999999,
+      "loss": 3.8903,
+      "step": 290
+    },
+    {
+      "epoch": 0.16753022452504318,
+      "grad_norm": 15.040228843688965,
+      "learning_rate": 0.000116,
+      "loss": 3.4079,
+      "step": 291
+    },
+    {
+      "epoch": 0.16810592976396085,
+      "grad_norm": 7.038132667541504,
+      "learning_rate": 0.0001164,
+      "loss": 3.7119,
+      "step": 292
+    },
+    {
+      "epoch": 0.16868163500287853,
+      "grad_norm": 6.259817123413086,
+      "learning_rate": 0.00011679999999999999,
+      "loss": 3.4931,
+      "step": 293
+    },
+    {
+      "epoch": 0.1692573402417962,
+      "grad_norm": 6.947351455688477,
+      "learning_rate": 0.0001172,
+      "loss": 3.677,
+      "step": 294
+    },
+    {
+      "epoch": 0.16983304548071387,
+      "grad_norm": 14.260014533996582,
+      "learning_rate": 0.0001176,
+      "loss": 3.9591,
+      "step": 295
+    },
+    {
+      "epoch": 0.17040875071963155,
+      "grad_norm": 6.70070743560791,
+      "learning_rate": 0.000118,
+      "loss": 3.2433,
+      "step": 296
+    },
+    {
+      "epoch": 0.17098445595854922,
+      "grad_norm": 11.697699546813965,
+      "learning_rate": 0.0001184,
+      "loss": 4.0909,
+      "step": 297
+    },
+    {
+      "epoch": 0.1715601611974669,
+      "grad_norm": 10.029029846191406,
+      "learning_rate": 0.0001188,
+      "loss": 3.5743,
+      "step": 298
+    },
+    {
+      "epoch": 0.17213586643638457,
+      "grad_norm": 6.6930365562438965,
+      "learning_rate": 0.0001192,
+      "loss": 3.2007,
+      "step": 299
+    },
+    {
+      "epoch": 0.17271157167530224,
+      "grad_norm": 21.772619247436523,
+      "learning_rate": 0.00011960000000000001,
+      "loss": 3.8505,
+      "step": 300
+    },
+    {
+      "epoch": 0.1732872769142199,
+      "grad_norm": 9.126256942749023,
+      "learning_rate": 0.00012,
+      "loss": 3.5777,
+      "step": 301
+    },
+    {
+      "epoch": 0.17386298215313759,
+      "grad_norm": 7.574469566345215,
+      "learning_rate": 0.0001204,
+      "loss": 3.5329,
+      "step": 302
+    },
+    {
+      "epoch": 0.17443868739205526,
+      "grad_norm": 6.436075687408447,
+      "learning_rate": 0.0001208,
+      "loss": 3.279,
+      "step": 303
+    },
+    {
+      "epoch": 0.17501439263097293,
+      "grad_norm": 5.945929527282715,
+      "learning_rate": 0.0001212,
+      "loss": 3.4338,
+      "step": 304
+    },
+    {
+      "epoch": 0.1755900978698906,
+      "grad_norm": 5.7057785987854,
+      "learning_rate": 0.0001216,
+      "loss": 3.2369,
+      "step": 305
+    },
+    {
+      "epoch": 0.17616580310880828,
+      "grad_norm": 9.411810874938965,
+      "learning_rate": 0.000122,
+      "loss": 3.5364,
+      "step": 306
+    },
+    {
+      "epoch": 0.17674150834772595,
+      "grad_norm": 8.872260093688965,
+      "learning_rate": 0.0001224,
+      "loss": 3.7803,
+      "step": 307
+    },
+    {
+      "epoch": 0.17731721358664365,
+      "grad_norm": 46.1115837097168,
+      "learning_rate": 0.0001228,
+      "loss": 3.7188,
+      "step": 308
+    },
+    {
+      "epoch": 0.17789291882556132,
+      "grad_norm": 48.33805465698242,
+      "learning_rate": 0.0001232,
+      "loss": 3.7491,
+      "step": 309
+    },
+    {
+      "epoch": 0.178468624064479,
+      "grad_norm": 7.272097587585449,
+      "learning_rate": 0.0001236,
+      "loss": 3.559,
+      "step": 310
+    },
+    {
+      "epoch": 0.17904432930339667,
+      "grad_norm": 7.471408367156982,
+      "learning_rate": 0.000124,
+      "loss": 3.6014,
+      "step": 311
+    },
+    {
+      "epoch": 0.17962003454231434,
+      "grad_norm": 11.095893859863281,
+      "learning_rate": 0.00012440000000000002,
+      "loss": 3.5741,
+      "step": 312
+    },
+    {
+      "epoch": 0.18019573978123202,
+      "grad_norm": 8.782601356506348,
+      "learning_rate": 0.0001248,
+      "loss": 3.2475,
+      "step": 313
+    },
+    {
+      "epoch": 0.1807714450201497,
+      "grad_norm": 7.485610485076904,
+      "learning_rate": 0.0001252,
+      "loss": 3.0304,
+      "step": 314
+    },
+    {
+      "epoch": 0.18134715025906736,
+      "grad_norm": 7.794425964355469,
+      "learning_rate": 0.00012560000000000002,
+      "loss": 2.9428,
+      "step": 315
+    },
+    {
+      "epoch": 0.18192285549798504,
+      "grad_norm": 6.470662593841553,
+      "learning_rate": 0.000126,
+      "loss": 3.4341,
+      "step": 316
+    },
+    {
+      "epoch": 0.1824985607369027,
+      "grad_norm": 10.054426193237305,
+      "learning_rate": 0.0001264,
+      "loss": 2.941,
+      "step": 317
+    },
+    {
+      "epoch": 0.18307426597582038,
+      "grad_norm": 93.38629150390625,
+      "learning_rate": 0.00012680000000000002,
+      "loss": 4.2291,
+      "step": 318
+    },
+    {
+      "epoch": 0.18364997121473806,
+      "grad_norm": 9.805968284606934,
+      "learning_rate": 0.0001272,
+      "loss": 3.0641,
+      "step": 319
+    },
+    {
+      "epoch": 0.18422567645365573,
+      "grad_norm": 6.104334831237793,
+      "learning_rate": 0.0001276,
+      "loss": 3.0856,
+      "step": 320
+    },
+    {
+      "epoch": 0.1848013816925734,
+      "grad_norm": 8.24195384979248,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 3.0774,
+      "step": 321
+    },
+    {
+      "epoch": 0.18537708693149108,
+      "grad_norm": 6.327628135681152,
+      "learning_rate": 0.0001284,
+      "loss": 3.0826,
+      "step": 322
+    },
+    {
+      "epoch": 0.18595279217040875,
+      "grad_norm": 11.529990196228027,
+      "learning_rate": 0.00012880000000000001,
+      "loss": 3.7882,
+      "step": 323
+    },
+    {
+      "epoch": 0.18652849740932642,
+      "grad_norm": 9.700762748718262,
+      "learning_rate": 0.00012920000000000002,
+      "loss": 3.4958,
+      "step": 324
+    },
+    {
+      "epoch": 0.1871042026482441,
+      "grad_norm": 10.289152145385742,
+      "learning_rate": 0.0001296,
+      "loss": 3.3652,
+      "step": 325
+    },
+    {
+      "epoch": 0.18767990788716177,
+      "grad_norm": 6.888269901275635,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 3.1086,
+      "step": 326
+    },
+    {
+      "epoch": 0.18825561312607944,
+      "grad_norm": 9.220719337463379,
+      "learning_rate": 0.0001304,
+      "loss": 3.5314,
+      "step": 327
+    },
+    {
+      "epoch": 0.1888313183649971,
+      "grad_norm": 9.044048309326172,
+      "learning_rate": 0.0001308,
+      "loss": 2.943,
+      "step": 328
+    },
+    {
+      "epoch": 0.1894070236039148,
+      "grad_norm": 11.338268280029297,
+      "learning_rate": 0.00013120000000000002,
+      "loss": 3.4617,
+      "step": 329
+    },
+    {
+      "epoch": 0.18998272884283246,
+      "grad_norm": 5.949525833129883,
+      "learning_rate": 0.0001316,
+      "loss": 2.8324,
+      "step": 330
+    },
+    {
+      "epoch": 0.19055843408175013,
+      "grad_norm": 9.158703804016113,
+      "learning_rate": 0.000132,
+      "loss": 3.1961,
+      "step": 331
+    },
+    {
+      "epoch": 0.1911341393206678,
+      "grad_norm": 8.708706855773926,
+      "learning_rate": 0.00013240000000000002,
+      "loss": 3.1941,
+      "step": 332
+    },
+    {
+      "epoch": 0.19170984455958548,
+      "grad_norm": 10.610583305358887,
+      "learning_rate": 0.0001328,
+      "loss": 3.3617,
+      "step": 333
+    },
+    {
+      "epoch": 0.19228554979850315,
+      "grad_norm": 8.023892402648926,
+      "learning_rate": 0.0001332,
+      "loss": 3.1775,
+      "step": 334
+    },
+    {
+      "epoch": 0.19286125503742085,
+      "grad_norm": 7.895623683929443,
+      "learning_rate": 0.00013360000000000002,
+      "loss": 3.1033,
+      "step": 335
+    },
+    {
+      "epoch": 0.19343696027633853,
+      "grad_norm": 6.376975059509277,
+      "learning_rate": 0.000134,
+      "loss": 2.808,
+      "step": 336
+    },
+    {
+      "epoch": 0.1940126655152562,
+      "grad_norm": 5.185142993927002,
+      "learning_rate": 0.00013440000000000001,
+      "loss": 2.8337,
+      "step": 337
+    },
+    {
+      "epoch": 0.19458837075417387,
+      "grad_norm": 6.408693790435791,
+      "learning_rate": 0.00013480000000000002,
+      "loss": 3.0604,
+      "step": 338
+    },
+    {
+      "epoch": 0.19516407599309155,
+      "grad_norm": 21.610239028930664,
+      "learning_rate": 0.0001352,
+      "loss": 3.431,
+      "step": 339
+    },
+    {
+      "epoch": 0.19573978123200922,
+      "grad_norm": 9.485398292541504,
+      "learning_rate": 0.00013560000000000002,
+      "loss": 3.2208,
+      "step": 340
+    },
+    {
+      "epoch": 0.1963154864709269,
+      "grad_norm": 6.460340976715088,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 2.793,
+      "step": 341
+    },
+    {
+      "epoch": 0.19689119170984457,
+      "grad_norm": 5.64215612411499,
+      "learning_rate": 0.0001364,
+      "loss": 2.8589,
+      "step": 342
+    },
+    {
+      "epoch": 0.19746689694876224,
+      "grad_norm": 6.9033427238464355,
+      "learning_rate": 0.00013680000000000002,
+      "loss": 3.1031,
+      "step": 343
+    },
+    {
+      "epoch": 0.1980426021876799,
+      "grad_norm": 5.724493980407715,
+      "learning_rate": 0.00013720000000000003,
+      "loss": 2.8605,
+      "step": 344
+    },
+    {
+      "epoch": 0.19861830742659758,
+      "grad_norm": 15.779448509216309,
+      "learning_rate": 0.00013759999999999998,
+      "loss": 3.2151,
+      "step": 345
+    },
+    {
+      "epoch": 0.19919401266551526,
+      "grad_norm": 6.960752964019775,
+      "learning_rate": 0.000138,
+      "loss": 2.8537,
+      "step": 346
+    },
+    {
+      "epoch": 0.19976971790443293,
+      "grad_norm": 8.871850967407227,
+      "learning_rate": 0.0001384,
+      "loss": 2.7536,
+      "step": 347
+    },
+    {
+      "epoch": 0.2003454231433506,
+      "grad_norm": 6.670348644256592,
+      "learning_rate": 0.00013879999999999999,
+      "loss": 2.9525,
+      "step": 348
+    },
+    {
+      "epoch": 0.20092112838226828,
+      "grad_norm": 9.574007034301758,
+      "learning_rate": 0.0001392,
+      "loss": 2.7996,
+      "step": 349
+    },
+    {
+      "epoch": 0.20149683362118595,
+      "grad_norm": 5.3862223625183105,
+      "learning_rate": 0.0001396,
+      "loss": 2.662,
+      "step": 350
+    },
+    {
+      "epoch": 0.20207253886010362,
+      "grad_norm": 11.832735061645508,
+      "learning_rate": 0.00014,
+      "loss": 3.1706,
+      "step": 351
+    },
+    {
+      "epoch": 0.2026482440990213,
+      "grad_norm": 8.553043365478516,
+      "learning_rate": 0.0001404,
+      "loss": 2.8034,
+      "step": 352
+    },
+    {
+      "epoch": 0.20322394933793897,
+      "grad_norm": 17.231216430664062,
+      "learning_rate": 0.0001408,
+      "loss": 2.8267,
+      "step": 353
+    },
+    {
+      "epoch": 0.20379965457685664,
+      "grad_norm": 10.80978012084961,
+      "learning_rate": 0.0001412,
+      "loss": 2.7008,
+      "step": 354
+    },
+    {
+      "epoch": 0.20437535981577432,
+      "grad_norm": 7.117002010345459,
+      "learning_rate": 0.0001416,
+      "loss": 2.5399,
+      "step": 355
+    },
+    {
+      "epoch": 0.204951065054692,
+      "grad_norm": 5.009802341461182,
+      "learning_rate": 0.000142,
+      "loss": 2.7215,
+      "step": 356
+    },
+    {
+      "epoch": 0.20552677029360966,
+      "grad_norm": 16.786869049072266,
+      "learning_rate": 0.0001424,
+      "loss": 2.9873,
+      "step": 357
+    },
+    {
+      "epoch": 0.20610247553252733,
+      "grad_norm": 7.779325008392334,
+      "learning_rate": 0.0001428,
+      "loss": 2.892,
+      "step": 358
+    },
+    {
+      "epoch": 0.206678180771445,
+      "grad_norm": 9.354433059692383,
+      "learning_rate": 0.0001432,
+      "loss": 2.7065,
+      "step": 359
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 13.15522575378418,
+      "learning_rate": 0.0001436,
+      "loss": 2.8061,
+      "step": 360
+    },
+    {
+      "epoch": 0.20782959124928038,
+      "grad_norm": 6.927896976470947,
+      "learning_rate": 0.000144,
+      "loss": 2.8687,
+      "step": 361
+    },
+    {
+      "epoch": 0.20840529648819806,
+      "grad_norm": 8.532772064208984,
+      "learning_rate": 0.0001444,
+      "loss": 2.9418,
+      "step": 362
+    },
+    {
+      "epoch": 0.20898100172711573,
+      "grad_norm": 8.618231773376465,
+      "learning_rate": 0.0001448,
+      "loss": 2.588,
+      "step": 363
+    },
+    {
+      "epoch": 0.2095567069660334,
+      "grad_norm": 4.94150447845459,
+      "learning_rate": 0.0001452,
+      "loss": 2.5464,
+      "step": 364
+    },
+    {
+      "epoch": 0.21013241220495107,
+      "grad_norm": 5.547298431396484,
+      "learning_rate": 0.00014560000000000002,
+      "loss": 2.755,
+      "step": 365
+    },
+    {
+      "epoch": 0.21070811744386875,
+      "grad_norm": 8.270822525024414,
+      "learning_rate": 0.000146,
+      "loss": 2.8345,
+      "step": 366
+    },
+    {
+      "epoch": 0.21128382268278642,
+      "grad_norm": 6.572064399719238,
+      "learning_rate": 0.0001464,
+      "loss": 2.6624,
+      "step": 367
+    },
+    {
+      "epoch": 0.2118595279217041,
+      "grad_norm": 8.243054389953613,
+      "learning_rate": 0.00014680000000000002,
+      "loss": 2.7102,
+      "step": 368
+    },
+    {
+      "epoch": 0.21243523316062177,
+      "grad_norm": 6.671678066253662,
+      "learning_rate": 0.0001472,
+      "loss": 2.4775,
+      "step": 369
+    },
+    {
+      "epoch": 0.21301093839953944,
+      "grad_norm": 5.922910690307617,
+      "learning_rate": 0.0001476,
+      "loss": 2.919,
+      "step": 370
+    },
+    {
+      "epoch": 0.2135866436384571,
+      "grad_norm": 12.84566593170166,
+      "learning_rate": 0.000148,
+      "loss": 2.5189,
+      "step": 371
+    },
+    {
+      "epoch": 0.2141623488773748,
+      "grad_norm": 7.342642307281494,
+      "learning_rate": 0.0001484,
+      "loss": 2.8968,
+      "step": 372
+    },
+    {
+      "epoch": 0.21473805411629246,
+      "grad_norm": 14.625147819519043,
+      "learning_rate": 0.0001488,
+      "loss": 2.6793,
+      "step": 373
+    },
+    {
+      "epoch": 0.21531375935521013,
+      "grad_norm": 6.683467388153076,
+      "learning_rate": 0.0001492,
+      "loss": 2.3975,
+      "step": 374
+    },
+    {
+      "epoch": 0.2158894645941278,
+      "grad_norm": 12.186212539672852,
+      "learning_rate": 0.0001496,
+      "loss": 2.856,
+      "step": 375
+    },
+    {
+      "epoch": 0.21646516983304548,
+      "grad_norm": 8.417567253112793,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.6326,
+      "step": 376
+    },
+    {
+      "epoch": 0.21704087507196315,
+      "grad_norm": 5.414144992828369,
+      "learning_rate": 0.0001504,
+      "loss": 2.7417,
+      "step": 377
+    },
+    {
+      "epoch": 0.21761658031088082,
+      "grad_norm": 13.388712882995605,
+      "learning_rate": 0.0001508,
+      "loss": 2.8813,
+      "step": 378
+    },
+    {
+      "epoch": 0.2181922855497985,
+      "grad_norm": 6.375700950622559,
+      "learning_rate": 0.00015120000000000002,
+      "loss": 2.7187,
+      "step": 379
+    },
+    {
+      "epoch": 0.21876799078871617,
+      "grad_norm": 9.897554397583008,
+      "learning_rate": 0.0001516,
+      "loss": 2.6278,
+      "step": 380
+    },
+    {
+      "epoch": 0.21934369602763384,
+      "grad_norm": 10.079334259033203,
+      "learning_rate": 0.000152,
+      "loss": 2.4861,
+      "step": 381
+    },
+    {
+      "epoch": 0.21991940126655152,
+      "grad_norm": 10.082268714904785,
+      "learning_rate": 0.00015240000000000002,
+      "loss": 2.6516,
+      "step": 382
+    },
+    {
+      "epoch": 0.2204951065054692,
+      "grad_norm": 9.192161560058594,
+      "learning_rate": 0.0001528,
+      "loss": 2.3307,
+      "step": 383
+    },
+    {
+      "epoch": 0.22107081174438686,
+      "grad_norm": 8.085034370422363,
+      "learning_rate": 0.0001532,
+      "loss": 2.3445,
+      "step": 384
+    },
+    {
+      "epoch": 0.22164651698330454,
+      "grad_norm": 5.418321132659912,
+      "learning_rate": 0.00015360000000000002,
+      "loss": 2.7119,
+      "step": 385
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 16.515369415283203,
+      "learning_rate": 0.000154,
+      "loss": 2.6647,
+      "step": 386
+    },
+    {
+      "epoch": 0.22279792746113988,
+      "grad_norm": 11.138907432556152,
+      "learning_rate": 0.0001544,
+      "loss": 2.6742,
+      "step": 387
+    },
+    {
+      "epoch": 0.22337363270005758,
+      "grad_norm": 20.75733184814453,
+      "learning_rate": 0.00015480000000000002,
+      "loss": 2.8834,
+      "step": 388
+    },
+    {
+      "epoch": 0.22394933793897526,
+      "grad_norm": 8.349270820617676,
+      "learning_rate": 0.0001552,
+      "loss": 2.6376,
+      "step": 389
+    },
+    {
+      "epoch": 0.22452504317789293,
+      "grad_norm": 6.902172088623047,
+      "learning_rate": 0.00015560000000000001,
+      "loss": 2.6186,
+      "step": 390
+    },
+    {
+      "epoch": 0.2251007484168106,
+      "grad_norm": 14.718120574951172,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 2.7649,
+      "step": 391
+    },
+    {
+      "epoch": 0.22567645365572828,
+      "grad_norm": 5.805610656738281,
+      "learning_rate": 0.0001564,
+      "loss": 2.6221,
+      "step": 392
+    },
+    {
+      "epoch": 0.22625215889464595,
+      "grad_norm": 6.138345718383789,
+      "learning_rate": 0.00015680000000000002,
+      "loss": 2.5751,
+      "step": 393
+    },
+    {
+      "epoch": 0.22682786413356362,
+      "grad_norm": 29.98923683166504,
+      "learning_rate": 0.00015720000000000003,
+      "loss": 2.824,
+      "step": 394
+    },
+    {
+      "epoch": 0.2274035693724813,
+      "grad_norm": 31.91318702697754,
+      "learning_rate": 0.0001576,
+      "loss": 2.6134,
+      "step": 395
+    },
+    {
+      "epoch": 0.22797927461139897,
+      "grad_norm": 10.812357902526855,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 2.4594,
+      "step": 396
+    },
+    {
+      "epoch": 0.22855497985031664,
+      "grad_norm": 7.6294755935668945,
+      "learning_rate": 0.00015840000000000003,
+      "loss": 2.5259,
+      "step": 397
+    },
+    {
+      "epoch": 0.22913068508923431,
+      "grad_norm": 5.666753768920898,
+      "learning_rate": 0.0001588,
+      "loss": 2.6108,
+      "step": 398
+    },
+    {
+      "epoch": 0.229706390328152,
+      "grad_norm": 6.732410907745361,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 2.5352,
+      "step": 399
+    },
+    {
+      "epoch": 0.23028209556706966,
+      "grad_norm": 6.749885082244873,
+      "learning_rate": 0.0001596,
+      "loss": 2.5103,
+      "step": 400
+    },
+    {
+      "epoch": 0.23085780080598733,
+      "grad_norm": 5.389144420623779,
+      "learning_rate": 0.00016,
+      "loss": 2.5803,
+      "step": 401
+    },
+    {
+      "epoch": 0.231433506044905,
+      "grad_norm": 6.996800422668457,
+      "learning_rate": 0.00016040000000000002,
+      "loss": 2.7746,
+      "step": 402
+    },
+    {
+      "epoch": 0.23200921128382268,
+      "grad_norm": 22.8950138092041,
+      "learning_rate": 0.0001608,
+      "loss": 2.5619,
+      "step": 403
+    },
+    {
+      "epoch": 0.23258491652274035,
+      "grad_norm": 11.477226257324219,
+      "learning_rate": 0.00016120000000000002,
+      "loss": 2.4898,
+      "step": 404
+    },
+    {
+      "epoch": 0.23316062176165803,
+      "grad_norm": 8.584878921508789,
+      "learning_rate": 0.00016160000000000002,
+      "loss": 2.4191,
+      "step": 405
+    },
+    {
+      "epoch": 0.2337363270005757,
+      "grad_norm": 6.987226963043213,
+      "learning_rate": 0.000162,
+      "loss": 2.4045,
+      "step": 406
+    },
+    {
+      "epoch": 0.23431203223949337,
+      "grad_norm": 12.917460441589355,
+      "learning_rate": 0.00016240000000000002,
+      "loss": 2.656,
+      "step": 407
+    },
+    {
+      "epoch": 0.23488773747841105,
+      "grad_norm": 13.053242683410645,
+      "learning_rate": 0.0001628,
+      "loss": 2.5026,
+      "step": 408
+    },
+    {
+      "epoch": 0.23546344271732872,
+      "grad_norm": 6.013350486755371,
+      "learning_rate": 0.0001632,
+      "loss": 2.4027,
+      "step": 409
+    },
+    {
+      "epoch": 0.2360391479562464,
+      "grad_norm": 21.95798110961914,
+      "learning_rate": 0.0001636,
+      "loss": 2.4155,
+      "step": 410
+    },
+    {
+      "epoch": 0.23661485319516407,
+      "grad_norm": 6.197417259216309,
+      "learning_rate": 0.000164,
+      "loss": 2.2512,
+      "step": 411
+    },
+    {
+      "epoch": 0.23719055843408174,
+      "grad_norm": 5.798823356628418,
+      "learning_rate": 0.0001644,
+      "loss": 2.5775,
+      "step": 412
+    },
+    {
+      "epoch": 0.2377662636729994,
+      "grad_norm": 12.58922290802002,
+      "learning_rate": 0.0001648,
+      "loss": 2.2999,
+      "step": 413
+    },
+    {
+      "epoch": 0.23834196891191708,
+      "grad_norm": 6.5375213623046875,
+      "learning_rate": 0.0001652,
+      "loss": 2.5818,
+      "step": 414
+    },
+    {
+      "epoch": 0.23891767415083479,
+      "grad_norm": 8.916410446166992,
+      "learning_rate": 0.0001656,
+      "loss": 2.3589,
+      "step": 415
+    },
+    {
+      "epoch": 0.23949337938975246,
+      "grad_norm": 7.457561492919922,
+      "learning_rate": 0.000166,
+      "loss": 2.5489,
+      "step": 416
+    },
+    {
+      "epoch": 0.24006908462867013,
+      "grad_norm": 18.522987365722656,
+      "learning_rate": 0.0001664,
+      "loss": 2.6065,
+      "step": 417
+    },
+    {
+      "epoch": 0.2406447898675878,
+      "grad_norm": 64.20520782470703,
+      "learning_rate": 0.0001668,
+      "loss": 2.7258,
+      "step": 418
+    },
+    {
+      "epoch": 0.24122049510650548,
+      "grad_norm": 40.07137680053711,
+      "learning_rate": 0.0001672,
+      "loss": 2.6834,
+      "step": 419
+    },
+    {
+      "epoch": 0.24179620034542315,
+      "grad_norm": 6.103574752807617,
+      "learning_rate": 0.0001676,
+      "loss": 2.4909,
+      "step": 420
+    },
+    {
+      "epoch": 0.24237190558434082,
+      "grad_norm": 6.48091983795166,
+      "learning_rate": 0.000168,
+      "loss": 2.5598,
+      "step": 421
+    },
+    {
+      "epoch": 0.2429476108232585,
+      "grad_norm": 6.65122127532959,
+      "learning_rate": 0.0001684,
+      "loss": 2.0797,
+      "step": 422
+    },
+    {
+      "epoch": 0.24352331606217617,
+      "grad_norm": 7.160250663757324,
+      "learning_rate": 0.0001688,
+      "loss": 2.4701,
+      "step": 423
+    },
+    {
+      "epoch": 0.24409902130109384,
+      "grad_norm": 5.73784875869751,
+      "learning_rate": 0.0001692,
+      "loss": 2.333,
+      "step": 424
+    },
+    {
+      "epoch": 0.24467472654001152,
+      "grad_norm": 21.651309967041016,
+      "learning_rate": 0.0001696,
+      "loss": 2.5034,
+      "step": 425
+    },
+    {
+      "epoch": 0.2452504317789292,
+      "grad_norm": 17.80324935913086,
+      "learning_rate": 0.00017,
+      "loss": 2.4943,
+      "step": 426
+    },
+    {
+      "epoch": 0.24582613701784686,
+      "grad_norm": 6.137923240661621,
+      "learning_rate": 0.0001704,
+      "loss": 2.4143,
+      "step": 427
+    },
+    {
+      "epoch": 0.24640184225676454,
+      "grad_norm": 5.833311080932617,
+      "learning_rate": 0.0001708,
+      "loss": 2.4598,
+      "step": 428
+    },
+    {
+      "epoch": 0.2469775474956822,
+      "grad_norm": 20.596446990966797,
+      "learning_rate": 0.00017120000000000001,
+      "loss": 2.4136,
+      "step": 429
+    },
+    {
+      "epoch": 0.24755325273459988,
+      "grad_norm": 5.577768802642822,
+      "learning_rate": 0.0001716,
+      "loss": 2.4349,
+      "step": 430
+    },
+    {
+      "epoch": 0.24812895797351756,
+      "grad_norm": 6.16340446472168,
+      "learning_rate": 0.000172,
+      "loss": 2.5712,
+      "step": 431
+    },
+    {
+      "epoch": 0.24870466321243523,
+      "grad_norm": 5.587292671203613,
+      "learning_rate": 0.00017240000000000002,
+      "loss": 2.522,
+      "step": 432
+    },
+    {
+      "epoch": 0.2492803684513529,
+      "grad_norm": 7.1100945472717285,
+      "learning_rate": 0.0001728,
+      "loss": 2.2343,
+      "step": 433
+    },
+    {
+      "epoch": 0.24985607369027057,
+      "grad_norm": 6.089508056640625,
+      "learning_rate": 0.0001732,
+      "loss": 2.5291,
+      "step": 434
+    },
+    {
+      "epoch": 0.2504317789291883,
+      "grad_norm": 12.8109769821167,
+      "learning_rate": 0.00017360000000000002,
+      "loss": 2.4944,
+      "step": 435
+    },
+    {
+      "epoch": 0.2510074841681059,
+      "grad_norm": 9.722925186157227,
+      "learning_rate": 0.000174,
+      "loss": 2.2176,
+      "step": 436
+    },
+    {
+      "epoch": 0.2515831894070236,
+      "grad_norm": 13.540785789489746,
+      "learning_rate": 0.0001744,
+      "loss": 2.3636,
+      "step": 437
+    },
+    {
+      "epoch": 0.25215889464594127,
+      "grad_norm": 22.12358856201172,
+      "learning_rate": 0.00017480000000000002,
+      "loss": 2.4757,
+      "step": 438
+    },
+    {
+      "epoch": 0.25273459988485897,
+      "grad_norm": 8.760823249816895,
+      "learning_rate": 0.0001752,
+      "loss": 2.256,
+      "step": 439
+    },
+    {
+      "epoch": 0.2533103051237766,
+      "grad_norm": 7.311398506164551,
+      "learning_rate": 0.0001756,
+      "loss": 2.3274,
+      "step": 440
+    },
+    {
+      "epoch": 0.2538860103626943,
+      "grad_norm": 9.8610200881958,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 2.4749,
+      "step": 441
+    },
+    {
+      "epoch": 0.25446171560161196,
+      "grad_norm": 7.475802898406982,
+      "learning_rate": 0.0001764,
+      "loss": 2.4547,
+      "step": 442
+    },
+    {
+      "epoch": 0.25503742084052966,
+      "grad_norm": 13.036137580871582,
+      "learning_rate": 0.00017680000000000001,
+      "loss": 2.1679,
+      "step": 443
+    },
+    {
+      "epoch": 0.2556131260794473,
+      "grad_norm": 11.247735977172852,
+      "learning_rate": 0.0001772,
+      "loss": 2.5446,
+      "step": 444
+    },
+    {
+      "epoch": 0.256188831318365,
+      "grad_norm": 7.0622124671936035,
+      "learning_rate": 0.0001776,
+      "loss": 2.3196,
+      "step": 445
+    },
+    {
+      "epoch": 0.25676453655728265,
+      "grad_norm": 5.404714107513428,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 2.2713,
+      "step": 446
+    },
+    {
+      "epoch": 0.25734024179620035,
+      "grad_norm": 44.592891693115234,
+      "learning_rate": 0.0001784,
+      "loss": 2.2287,
+      "step": 447
+    },
+    {
+      "epoch": 0.257915947035118,
+      "grad_norm": 30.109132766723633,
+      "learning_rate": 0.0001788,
+      "loss": 2.3153,
+      "step": 448
+    },
+    {
+      "epoch": 0.2584916522740357,
+      "grad_norm": 15.7490873336792,
+      "learning_rate": 0.00017920000000000002,
+      "loss": 2.3081,
+      "step": 449
+    },
+    {
+      "epoch": 0.25906735751295334,
+      "grad_norm": 13.772661209106445,
+      "learning_rate": 0.0001796,
+      "loss": 2.2548,
+      "step": 450
+    },
+    {
+      "epoch": 0.25964306275187105,
+      "grad_norm": 6.858334064483643,
+      "learning_rate": 0.00018,
+      "loss": 2.4804,
+      "step": 451
+    },
+    {
+      "epoch": 0.2602187679907887,
+      "grad_norm": 6.23155403137207,
+      "learning_rate": 0.00018040000000000002,
+      "loss": 2.4281,
+      "step": 452
+    },
+    {
+      "epoch": 0.2607944732297064,
+      "grad_norm": 5.4447150230407715,
+      "learning_rate": 0.0001808,
+      "loss": 2.342,
+      "step": 453
+    },
+    {
+      "epoch": 0.26137017846862404,
+      "grad_norm": 11.79716682434082,
+      "learning_rate": 0.0001812,
+      "loss": 2.2528,
+      "step": 454
+    },
+    {
+      "epoch": 0.26194588370754174,
+      "grad_norm": 10.708625793457031,
+      "learning_rate": 0.00018160000000000002,
+      "loss": 2.0204,
+      "step": 455
+    },
+    {
+      "epoch": 0.26252158894645944,
+      "grad_norm": 21.41659164428711,
+      "learning_rate": 0.000182,
+      "loss": 2.2593,
+      "step": 456
+    },
+    {
+      "epoch": 0.2630972941853771,
+      "grad_norm": 5.636983394622803,
+      "learning_rate": 0.00018240000000000002,
+      "loss": 2.1412,
+      "step": 457
+    },
+    {
+      "epoch": 0.2636729994242948,
+      "grad_norm": 9.639352798461914,
+      "learning_rate": 0.00018280000000000003,
+      "loss": 2.1103,
+      "step": 458
+    },
+    {
+      "epoch": 0.26424870466321243,
+      "grad_norm": 4.263064384460449,
+      "learning_rate": 0.0001832,
+      "loss": 2.2493,
+      "step": 459
+    },
+    {
+      "epoch": 0.26482440990213013,
+      "grad_norm": 8.983839988708496,
+      "learning_rate": 0.00018360000000000002,
+      "loss": 2.3782,
+      "step": 460
+    },
+    {
+      "epoch": 0.2654001151410478,
+      "grad_norm": 9.911988258361816,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 2.2117,
+      "step": 461
+    },
+    {
+      "epoch": 0.2659758203799655,
+      "grad_norm": 8.42939567565918,
+      "learning_rate": 0.0001844,
+      "loss": 2.0942,
+      "step": 462
+    },
+    {
+      "epoch": 0.2665515256188831,
+      "grad_norm": 9.866201400756836,
+      "learning_rate": 0.00018480000000000002,
+      "loss": 2.2761,
+      "step": 463
+    },
+    {
+      "epoch": 0.2671272308578008,
+      "grad_norm": 4.9825758934021,
+      "learning_rate": 0.00018520000000000003,
+      "loss": 2.1351,
+      "step": 464
+    },
+    {
+      "epoch": 0.26770293609671847,
+      "grad_norm": 3.4520153999328613,
+      "learning_rate": 0.0001856,
+      "loss": 2.234,
+      "step": 465
+    },
+    {
+      "epoch": 0.26827864133563617,
+      "grad_norm": 6.94691276550293,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 2.1368,
+      "step": 466
+    },
+    {
+      "epoch": 0.2688543465745538,
+      "grad_norm": 19.923587799072266,
+      "learning_rate": 0.00018640000000000003,
+      "loss": 2.4301,
+      "step": 467
+    },
+    {
+      "epoch": 0.2694300518134715,
+      "grad_norm": 24.741535186767578,
+      "learning_rate": 0.00018680000000000001,
+      "loss": 2.256,
+      "step": 468
+    },
+    {
+      "epoch": 0.27000575705238916,
+      "grad_norm": 9.313246726989746,
+      "learning_rate": 0.00018720000000000002,
+      "loss": 2.6483,
+      "step": 469
+    },
+    {
+      "epoch": 0.27058146229130686,
+      "grad_norm": 10.217698097229004,
+      "learning_rate": 0.0001876,
+      "loss": 1.8293,
+      "step": 470
+    },
+    {
+      "epoch": 0.2711571675302245,
+      "grad_norm": 28.85066032409668,
+      "learning_rate": 0.000188,
+      "loss": 2.3165,
+      "step": 471
+    },
+    {
+      "epoch": 0.2717328727691422,
+      "grad_norm": 5.764794826507568,
+      "learning_rate": 0.0001884,
+      "loss": 2.6914,
+      "step": 472
+    },
+    {
+      "epoch": 0.27230857800805985,
+      "grad_norm": 8.115283966064453,
+      "learning_rate": 0.0001888,
+      "loss": 2.5605,
+      "step": 473
+    },
+    {
+      "epoch": 0.27288428324697755,
+      "grad_norm": 11.941910743713379,
+      "learning_rate": 0.0001892,
+      "loss": 1.9626,
+      "step": 474
+    },
+    {
+      "epoch": 0.2734599884858952,
+      "grad_norm": 11.117420196533203,
+      "learning_rate": 0.0001896,
+      "loss": 2.4614,
+      "step": 475
+    },
+    {
+      "epoch": 0.2740356937248129,
+      "grad_norm": 6.908642292022705,
+      "learning_rate": 0.00019,
+      "loss": 2.3911,
+      "step": 476
+    },
+    {
+      "epoch": 0.27461139896373055,
+      "grad_norm": 10.433818817138672,
+      "learning_rate": 0.0001904,
+      "loss": 2.3747,
+      "step": 477
+    },
+    {
+      "epoch": 0.27518710420264825,
+      "grad_norm": 8.546224594116211,
+      "learning_rate": 0.0001908,
+      "loss": 2.2947,
+      "step": 478
+    },
+    {
+      "epoch": 0.2757628094415659,
+      "grad_norm": 5.434266090393066,
+      "learning_rate": 0.0001912,
+      "loss": 2.2115,
+      "step": 479
+    },
+    {
+      "epoch": 0.2763385146804836,
+      "grad_norm": 9.27397346496582,
+      "learning_rate": 0.0001916,
+      "loss": 2.2165,
+      "step": 480
+    },
+    {
+      "epoch": 0.27691421991940124,
+      "grad_norm": 4.052639484405518,
+      "learning_rate": 0.000192,
+      "loss": 2.1148,
+      "step": 481
+    },
+    {
+      "epoch": 0.27748992515831894,
+      "grad_norm": 7.541112422943115,
+      "learning_rate": 0.00019240000000000001,
+      "loss": 2.2489,
+      "step": 482
+    },
+    {
+      "epoch": 0.27806563039723664,
+      "grad_norm": 20.005165100097656,
+      "learning_rate": 0.0001928,
+      "loss": 2.3552,
+      "step": 483
+    },
+    {
+      "epoch": 0.2786413356361543,
+      "grad_norm": 6.74354362487793,
+      "learning_rate": 0.0001932,
+      "loss": 2.0027,
+      "step": 484
+    },
+    {
+      "epoch": 0.279217040875072,
+      "grad_norm": 4.244668960571289,
+      "learning_rate": 0.00019360000000000002,
+      "loss": 2.466,
+      "step": 485
+    },
+    {
+      "epoch": 0.27979274611398963,
+      "grad_norm": 32.92999267578125,
+      "learning_rate": 0.000194,
+      "loss": 2.0058,
+      "step": 486
+    },
+    {
+      "epoch": 0.28036845135290733,
+      "grad_norm": 5.099974155426025,
+      "learning_rate": 0.0001944,
+      "loss": 2.1534,
+      "step": 487
+    },
+    {
+      "epoch": 0.280944156591825,
+      "grad_norm": 8.950968742370605,
+      "learning_rate": 0.0001948,
+      "loss": 2.3272,
+      "step": 488
+    },
+    {
+      "epoch": 0.2815198618307427,
+      "grad_norm": 29.126623153686523,
+      "learning_rate": 0.0001952,
+      "loss": 2.0942,
+      "step": 489
+    },
+    {
+      "epoch": 0.2820955670696603,
+      "grad_norm": 26.04970932006836,
+      "learning_rate": 0.0001956,
+      "loss": 2.3703,
+      "step": 490
+    },
+    {
+      "epoch": 0.282671272308578,
+      "grad_norm": 7.4286370277404785,
+      "learning_rate": 0.000196,
+      "loss": 1.8691,
+      "step": 491
+    },
+    {
+      "epoch": 0.28324697754749567,
+      "grad_norm": 6.331235408782959,
+      "learning_rate": 0.0001964,
+      "loss": 2.2338,
+      "step": 492
+    },
+    {
+      "epoch": 0.28382268278641337,
+      "grad_norm": 4.98259162902832,
+      "learning_rate": 0.0001968,
+      "loss": 1.9059,
+      "step": 493
+    },
+    {
+      "epoch": 0.284398388025331,
+      "grad_norm": 12.111970901489258,
+      "learning_rate": 0.0001972,
+      "loss": 2.0567,
+      "step": 494
+    },
+    {
+      "epoch": 0.2849740932642487,
+      "grad_norm": 4.433606147766113,
+      "learning_rate": 0.0001976,
+      "loss": 2.061,
+      "step": 495
+    },
+    {
+      "epoch": 0.28554979850316636,
+      "grad_norm": 9.483826637268066,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.1855,
+      "step": 496
+    },
+    {
+      "epoch": 0.28612550374208406,
+      "grad_norm": 8.829517364501953,
+      "learning_rate": 0.0001984,
+      "loss": 2.0813,
+      "step": 497
+    },
+    {
+      "epoch": 0.2867012089810017,
+      "grad_norm": 5.547176361083984,
+      "learning_rate": 0.0001988,
+      "loss": 2.1782,
+      "step": 498
+    },
+    {
+      "epoch": 0.2872769142199194,
+      "grad_norm": 13.865377426147461,
+      "learning_rate": 0.00019920000000000002,
+      "loss": 1.9131,
+      "step": 499
+    },
+    {
+      "epoch": 0.28785261945883706,
+      "grad_norm": 13.441047668457031,
+      "learning_rate": 0.0001996,
+      "loss": 2.1865,
+      "step": 500
+    },
+    {
+      "epoch": 0.28842832469775476,
+      "grad_norm": 4.224601745605469,
+      "learning_rate": 0.0002,
+      "loss": 2.4949,
+      "step": 501
+    },
+    {
+      "epoch": 0.2890040299366724,
+      "grad_norm": 4.024444580078125,
+      "learning_rate": 0.000199999709749734,
+      "loss": 2.2281,
+      "step": 502
+    },
+    {
+      "epoch": 0.2895797351755901,
+      "grad_norm": 6.911625862121582,
+      "learning_rate": 0.000199998839000808,
+      "loss": 2.0534,
+      "step": 503
+    },
+    {
+      "epoch": 0.29015544041450775,
+      "grad_norm": 15.578252792358398,
+      "learning_rate": 0.00019999738775883837,
+      "loss": 2.1315,
+      "step": 504
+    },
+    {
+      "epoch": 0.29073114565342545,
+      "grad_norm": 14.918317794799805,
+      "learning_rate": 0.00019999535603318567,
+      "loss": 2.1605,
+      "step": 505
+    },
+    {
+      "epoch": 0.2913068508923431,
+      "grad_norm": 3.6653409004211426,
+      "learning_rate": 0.0001999927438369545,
+      "loss": 2.3675,
+      "step": 506
+    },
+    {
+      "epoch": 0.2918825561312608,
+      "grad_norm": 9.457073211669922,
+      "learning_rate": 0.0001999895511869936,
+      "loss": 2.2067,
+      "step": 507
+    },
+    {
+      "epoch": 0.2924582613701785,
+      "grad_norm": 16.254053115844727,
+      "learning_rate": 0.00019998577810389551,
+      "loss": 1.8262,
+      "step": 508
+    },
+    {
+      "epoch": 0.29303396660909614,
+      "grad_norm": 12.8787260055542,
+      "learning_rate": 0.00019998142461199664,
+      "loss": 2.1758,
+      "step": 509
+    },
+    {
+      "epoch": 0.29360967184801384,
+      "grad_norm": 7.122046947479248,
+      "learning_rate": 0.00019997649073937707,
+      "loss": 2.1842,
+      "step": 510
+    },
+    {
+      "epoch": 0.2941853770869315,
+      "grad_norm": 7.713693618774414,
+      "learning_rate": 0.00019997097651786033,
+      "loss": 2.1556,
+      "step": 511
+    },
+    {
+      "epoch": 0.2947610823258492,
+      "grad_norm": 5.447865962982178,
+      "learning_rate": 0.00019996488198301314,
+      "loss": 2.2058,
+      "step": 512
+    },
+    {
+      "epoch": 0.29533678756476683,
+      "grad_norm": 10.775145530700684,
+      "learning_rate": 0.0001999582071741453,
+      "loss": 2.365,
+      "step": 513
+    },
+    {
+      "epoch": 0.29591249280368453,
+      "grad_norm": 15.842108726501465,
+      "learning_rate": 0.00019995095213430937,
+      "loss": 2.1598,
+      "step": 514
+    },
+    {
+      "epoch": 0.2964881980426022,
+      "grad_norm": 27.204334259033203,
+      "learning_rate": 0.00019994311691030038,
+      "loss": 2.3135,
+      "step": 515
+    },
+    {
+      "epoch": 0.2970639032815199,
+      "grad_norm": 17.095380783081055,
+      "learning_rate": 0.0001999347015526556,
+      "loss": 2.1369,
+      "step": 516
+    },
+    {
+      "epoch": 0.2976396085204375,
+      "grad_norm": 5.58231258392334,
+      "learning_rate": 0.0001999257061156541,
+      "loss": 2.1524,
+      "step": 517
+    },
+    {
+      "epoch": 0.2982153137593552,
+      "grad_norm": 16.57658576965332,
+      "learning_rate": 0.00019991613065731652,
+      "loss": 2.2354,
+      "step": 518
+    },
+    {
+      "epoch": 0.2987910189982729,
+      "grad_norm": 10.48273754119873,
+      "learning_rate": 0.00019990597523940467,
+      "loss": 1.9177,
+      "step": 519
+    },
+    {
+      "epoch": 0.2993667242371906,
+      "grad_norm": 11.657440185546875,
+      "learning_rate": 0.00019989523992742096,
+      "loss": 2.1773,
+      "step": 520
+    },
+    {
+      "epoch": 0.2999424294761082,
+      "grad_norm": 8.428756713867188,
+      "learning_rate": 0.00019988392479060828,
+      "loss": 2.0253,
+      "step": 521
+    },
+    {
+      "epoch": 0.3005181347150259,
+      "grad_norm": 23.292964935302734,
+      "learning_rate": 0.00019987202990194938,
+      "loss": 2.1664,
+      "step": 522
+    },
+    {
+      "epoch": 0.30109383995394357,
+      "grad_norm": 11.076370239257812,
+      "learning_rate": 0.00019985955533816623,
+      "loss": 2.1639,
+      "step": 523
+    },
+    {
+      "epoch": 0.30166954519286127,
+      "grad_norm": 5.960238933563232,
+      "learning_rate": 0.00019984650117971993,
+      "loss": 2.28,
+      "step": 524
+    },
+    {
+      "epoch": 0.3022452504317789,
+      "grad_norm": 5.293085098266602,
+      "learning_rate": 0.00019983286751080984,
+      "loss": 2.0797,
+      "step": 525
+    },
+    {
+      "epoch": 0.3028209556706966,
+      "grad_norm": 6.787145614624023,
+      "learning_rate": 0.00019981865441937326,
+      "loss": 2.1623,
+      "step": 526
+    },
+    {
+      "epoch": 0.30339666090961426,
+      "grad_norm": 4.942052841186523,
+      "learning_rate": 0.00019980386199708468,
+      "loss": 1.9676,
+      "step": 527
+    },
+    {
+      "epoch": 0.30397236614853196,
+      "grad_norm": 3.7597603797912598,
+      "learning_rate": 0.0001997884903393553,
+      "loss": 2.0058,
+      "step": 528
+    },
+    {
+      "epoch": 0.3045480713874496,
+      "grad_norm": 4.015875339508057,
+      "learning_rate": 0.00019977253954533243,
+      "loss": 2.4905,
+      "step": 529
+    },
+    {
+      "epoch": 0.3051237766263673,
+      "grad_norm": 71.47596740722656,
+      "learning_rate": 0.00019975600971789873,
+      "loss": 2.2579,
+      "step": 530
+    },
+    {
+      "epoch": 0.30569948186528495,
+      "grad_norm": 5.182095050811768,
+      "learning_rate": 0.00019973890096367173,
+      "loss": 2.0343,
+      "step": 531
+    },
+    {
+      "epoch": 0.30627518710420265,
+      "grad_norm": 11.30048656463623,
+      "learning_rate": 0.000199721213393003,
+      "loss": 1.709,
+      "step": 532
+    },
+    {
+      "epoch": 0.3068508923431203,
+      "grad_norm": 7.1390700340271,
+      "learning_rate": 0.00019970294711997745,
+      "loss": 1.9582,
+      "step": 533
+    },
+    {
+      "epoch": 0.307426597582038,
+      "grad_norm": 4.473127841949463,
+      "learning_rate": 0.0001996841022624127,
+      "loss": 2.0572,
+      "step": 534
+    },
+    {
+      "epoch": 0.3080023028209557,
+      "grad_norm": 15.681950569152832,
+      "learning_rate": 0.00019966467894185812,
+      "loss": 2.0069,
+      "step": 535
+    },
+    {
+      "epoch": 0.30857800805987334,
+      "grad_norm": 3.4989001750946045,
+      "learning_rate": 0.0001996446772835943,
+      "loss": 2.3378,
+      "step": 536
+    },
+    {
+      "epoch": 0.30915371329879104,
+      "grad_norm": 6.156066417694092,
+      "learning_rate": 0.00019962409741663202,
+      "loss": 2.1491,
+      "step": 537
+    },
+    {
+      "epoch": 0.3097294185377087,
+      "grad_norm": 3.5091023445129395,
+      "learning_rate": 0.00019960293947371153,
+      "loss": 2.2707,
+      "step": 538
+    },
+    {
+      "epoch": 0.3103051237766264,
+      "grad_norm": 11.965502738952637,
+      "learning_rate": 0.00019958120359130178,
+      "loss": 1.9268,
+      "step": 539
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 23.450349807739258,
+      "learning_rate": 0.0001995588899095992,
+      "loss": 1.7938,
+      "step": 540
+    },
+    {
+      "epoch": 0.31145653425446174,
+      "grad_norm": 38.560482025146484,
+      "learning_rate": 0.00019953599857252733,
+      "loss": 2.2267,
+      "step": 541
+    },
+    {
+      "epoch": 0.3120322394933794,
+      "grad_norm": 15.327620506286621,
+      "learning_rate": 0.00019951252972773525,
+      "loss": 2.3168,
+      "step": 542
+    },
+    {
+      "epoch": 0.3126079447322971,
+      "grad_norm": 4.420673370361328,
+      "learning_rate": 0.0001994884835265973,
+      "loss": 2.0744,
+      "step": 543
+    },
+    {
+      "epoch": 0.31318364997121473,
+      "grad_norm": 19.81424903869629,
+      "learning_rate": 0.00019946386012421153,
+      "loss": 1.9736,
+      "step": 544
+    },
+    {
+      "epoch": 0.31375935521013243,
+      "grad_norm": 4.647876739501953,
+      "learning_rate": 0.00019943865967939908,
+      "loss": 2.1716,
+      "step": 545
+    },
+    {
+      "epoch": 0.3143350604490501,
+      "grad_norm": 5.088565349578857,
+      "learning_rate": 0.00019941288235470291,
+      "loss": 1.9915,
+      "step": 546
+    },
+    {
+      "epoch": 0.3149107656879678,
+      "grad_norm": 6.194237232208252,
+      "learning_rate": 0.00019938652831638697,
+      "loss": 1.9701,
+      "step": 547
+    },
+    {
+      "epoch": 0.3154864709268854,
+      "grad_norm": 5.4519429206848145,
+      "learning_rate": 0.00019935959773443497,
+      "loss": 2.2597,
+      "step": 548
+    },
+    {
+      "epoch": 0.3160621761658031,
+      "grad_norm": 7.437872409820557,
+      "learning_rate": 0.0001993320907825493,
+      "loss": 2.3016,
+      "step": 549
+    },
+    {
+      "epoch": 0.31663788140472077,
+      "grad_norm": 4.233456134796143,
+      "learning_rate": 0.00019930400763814993,
+      "loss": 1.8935,
+      "step": 550
+    },
+    {
+      "epoch": 0.31721358664363847,
+      "grad_norm": 5.772792339324951,
+      "learning_rate": 0.00019927534848237336,
+      "loss": 1.6373,
+      "step": 551
+    },
+    {
+      "epoch": 0.3177892918825561,
+      "grad_norm": 7.545225143432617,
+      "learning_rate": 0.0001992461135000713,
+      "loss": 1.9868,
+      "step": 552
+    },
+    {
+      "epoch": 0.3183649971214738,
+      "grad_norm": 5.72635555267334,
+      "learning_rate": 0.00019921630287980956,
+      "loss": 1.7728,
+      "step": 553
+    },
+    {
+      "epoch": 0.31894070236039146,
+      "grad_norm": 5.739555358886719,
+      "learning_rate": 0.0001991859168138668,
+      "loss": 1.8478,
+      "step": 554
+    },
+    {
+      "epoch": 0.31951640759930916,
+      "grad_norm": 3.295530319213867,
+      "learning_rate": 0.0001991549554982333,
+      "loss": 2.1454,
+      "step": 555
+    },
+    {
+      "epoch": 0.3200921128382268,
+      "grad_norm": 10.391168594360352,
+      "learning_rate": 0.0001991234191326098,
+      "loss": 2.2763,
+      "step": 556
+    },
+    {
+      "epoch": 0.3206678180771445,
+      "grad_norm": 14.846756935119629,
+      "learning_rate": 0.00019909130792040598,
+      "loss": 1.9783,
+      "step": 557
+    },
+    {
+      "epoch": 0.32124352331606215,
+      "grad_norm": 4.79947566986084,
+      "learning_rate": 0.0001990586220687394,
+      "loss": 2.1489,
+      "step": 558
+    },
+    {
+      "epoch": 0.32181922855497985,
+      "grad_norm": 4.786315441131592,
+      "learning_rate": 0.00019902536178843395,
+      "loss": 2.0194,
+      "step": 559
+    },
+    {
+      "epoch": 0.3223949337938975,
+      "grad_norm": 11.64875602722168,
+      "learning_rate": 0.00019899152729401868,
+      "loss": 1.8983,
+      "step": 560
+    },
+    {
+      "epoch": 0.3229706390328152,
+      "grad_norm": 9.477057456970215,
+      "learning_rate": 0.00019895711880372628,
+      "loss": 1.9139,
+      "step": 561
+    },
+    {
+      "epoch": 0.3235463442717329,
+      "grad_norm": 7.5819993019104,
+      "learning_rate": 0.00019892213653949166,
+      "loss": 1.843,
+      "step": 562
+    },
+    {
+      "epoch": 0.32412204951065055,
+      "grad_norm": 4.9545207023620605,
+      "learning_rate": 0.00019888658072695066,
+      "loss": 2.1052,
+      "step": 563
+    },
+    {
+      "epoch": 0.32469775474956825,
+      "grad_norm": 4.684484958648682,
+      "learning_rate": 0.0001988504515954385,
+      "loss": 1.7933,
+      "step": 564
+    },
+    {
+      "epoch": 0.3252734599884859,
+      "grad_norm": 8.41274356842041,
+      "learning_rate": 0.00019881374937798826,
+      "loss": 2.0737,
+      "step": 565
+    },
+    {
+      "epoch": 0.3258491652274036,
+      "grad_norm": 20.587425231933594,
+      "learning_rate": 0.00019877647431132948,
+      "loss": 1.6823,
+      "step": 566
+    },
+    {
+      "epoch": 0.32642487046632124,
+      "grad_norm": 12.793438911437988,
+      "learning_rate": 0.00019873862663588658,
+      "loss": 2.1764,
+      "step": 567
+    },
+    {
+      "epoch": 0.32700057570523894,
+      "grad_norm": 3.9023592472076416,
+      "learning_rate": 0.00019870020659577725,
+      "loss": 2.3804,
+      "step": 568
+    },
+    {
+      "epoch": 0.3275762809441566,
+      "grad_norm": 5.434683799743652,
+      "learning_rate": 0.000198661214438811,
+      "loss": 2.162,
+      "step": 569
+    },
+    {
+      "epoch": 0.3281519861830743,
+      "grad_norm": 5.3589019775390625,
+      "learning_rate": 0.00019862165041648744,
+      "loss": 2.2068,
+      "step": 570
+    },
+    {
+      "epoch": 0.32872769142199193,
+      "grad_norm": 5.979888439178467,
+      "learning_rate": 0.00019858151478399478,
+      "loss": 1.9811,
+      "step": 571
+    },
+    {
+      "epoch": 0.32930339666090963,
+      "grad_norm": 10.225967407226562,
+      "learning_rate": 0.0001985408078002081,
+      "loss": 1.7766,
+      "step": 572
+    },
+    {
+      "epoch": 0.3298791018998273,
+      "grad_norm": 7.599292278289795,
+      "learning_rate": 0.00019849952972768767,
+      "loss": 1.851,
+      "step": 573
+    },
+    {
+      "epoch": 0.330454807138745,
+      "grad_norm": 3.455409049987793,
+      "learning_rate": 0.0001984576808326773,
+      "loss": 1.9795,
+      "step": 574
+    },
+    {
+      "epoch": 0.3310305123776626,
+      "grad_norm": 4.577173709869385,
+      "learning_rate": 0.00019841526138510257,
+      "loss": 2.1139,
+      "step": 575
+    },
+    {
+      "epoch": 0.3316062176165803,
+      "grad_norm": 3.0964651107788086,
+      "learning_rate": 0.00019837227165856922,
+      "loss": 2.2629,
+      "step": 576
+    },
+    {
+      "epoch": 0.33218192285549797,
+      "grad_norm": 5.796529293060303,
+      "learning_rate": 0.0001983287119303612,
+      "loss": 2.1801,
+      "step": 577
+    },
+    {
+      "epoch": 0.33275762809441567,
+      "grad_norm": 13.77210521697998,
+      "learning_rate": 0.00019828458248143913,
+      "loss": 1.9382,
+      "step": 578
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 67.12165832519531,
+      "learning_rate": 0.00019823988359643805,
+      "loss": 2.0376,
+      "step": 579
+    },
+    {
+      "epoch": 0.333909038572251,
+      "grad_norm": 18.68467140197754,
+      "learning_rate": 0.00019819461556366615,
+      "loss": 2.1364,
+      "step": 580
+    },
+    {
+      "epoch": 0.33448474381116866,
+      "grad_norm": 3.4618403911590576,
+      "learning_rate": 0.00019814877867510244,
+      "loss": 2.4019,
+      "step": 581
+    },
+    {
+      "epoch": 0.33506044905008636,
+      "grad_norm": 2.982158899307251,
+      "learning_rate": 0.00019810237322639518,
+      "loss": 2.2236,
+      "step": 582
+    },
+    {
+      "epoch": 0.335636154289004,
+      "grad_norm": 18.654964447021484,
+      "learning_rate": 0.00019805539951685974,
+      "loss": 2.1278,
+      "step": 583
+    },
+    {
+      "epoch": 0.3362118595279217,
+      "grad_norm": 16.564912796020508,
+      "learning_rate": 0.00019800785784947683,
+      "loss": 1.8014,
+      "step": 584
+    },
+    {
+      "epoch": 0.33678756476683935,
+      "grad_norm": 31.10694122314453,
+      "learning_rate": 0.00019795974853089053,
+      "loss": 1.9206,
+      "step": 585
+    },
+    {
+      "epoch": 0.33736327000575705,
+      "grad_norm": 22.873422622680664,
+      "learning_rate": 0.00019791107187140618,
+      "loss": 2.0762,
+      "step": 586
+    },
+    {
+      "epoch": 0.3379389752446747,
+      "grad_norm": 4.631661415100098,
+      "learning_rate": 0.00019786182818498852,
+      "loss": 1.9247,
+      "step": 587
+    },
+    {
+      "epoch": 0.3385146804835924,
+      "grad_norm": 8.853531837463379,
+      "learning_rate": 0.00019781201778925969,
+      "loss": 1.7691,
+      "step": 588
+    },
+    {
+      "epoch": 0.3390903857225101,
+      "grad_norm": 10.22801685333252,
+      "learning_rate": 0.00019776164100549694,
+      "loss": 2.1087,
+      "step": 589
+    },
+    {
+      "epoch": 0.33966609096142775,
+      "grad_norm": 11.78855037689209,
+      "learning_rate": 0.0001977106981586309,
+      "loss": 2.2109,
+      "step": 590
+    },
+    {
+      "epoch": 0.34024179620034545,
+      "grad_norm": 9.323369026184082,
+      "learning_rate": 0.00019765918957724319,
+      "loss": 2.104,
+      "step": 591
+    },
+    {
+      "epoch": 0.3408175014392631,
+      "grad_norm": 10.116569519042969,
+      "learning_rate": 0.00019760711559356449,
+      "loss": 2.0949,
+      "step": 592
+    },
+    {
+      "epoch": 0.3413932066781808,
+      "grad_norm": 9.48695182800293,
+      "learning_rate": 0.00019755447654347226,
+      "loss": 2.1322,
+      "step": 593
+    },
+    {
+      "epoch": 0.34196891191709844,
+      "grad_norm": 11.74067497253418,
+      "learning_rate": 0.00019750127276648872,
+      "loss": 2.0404,
+      "step": 594
+    },
+    {
+      "epoch": 0.34254461715601614,
+      "grad_norm": 11.347387313842773,
+      "learning_rate": 0.00019744750460577856,
+      "loss": 1.6953,
+      "step": 595
+    },
+    {
+      "epoch": 0.3431203223949338,
+      "grad_norm": 3.8460686206817627,
+      "learning_rate": 0.00019739317240814668,
+      "loss": 2.1369,
+      "step": 596
+    },
+    {
+      "epoch": 0.3436960276338515,
+      "grad_norm": 3.9272382259368896,
+      "learning_rate": 0.00019733827652403615,
+      "loss": 2.1408,
+      "step": 597
+    },
+    {
+      "epoch": 0.34427173287276913,
+      "grad_norm": 6.900027751922607,
+      "learning_rate": 0.00019728281730752568,
+      "loss": 2.1793,
+      "step": 598
+    },
+    {
+      "epoch": 0.34484743811168683,
+      "grad_norm": 14.802238464355469,
+      "learning_rate": 0.00019722679511632757,
+      "loss": 2.0497,
+      "step": 599
+    },
+    {
+      "epoch": 0.3454231433506045,
+      "grad_norm": 12.431273460388184,
+      "learning_rate": 0.00019717021031178528,
+      "loss": 2.1025,
+      "step": 600
+    },
+    {
+      "epoch": 0.3459988485895222,
+      "grad_norm": 26.413490295410156,
+      "learning_rate": 0.00019711306325887116,
+      "loss": 2.0722,
+      "step": 601
+    },
+    {
+      "epoch": 0.3465745538284398,
+      "grad_norm": 15.21047592163086,
+      "learning_rate": 0.000197055354326184,
+      "loss": 1.8285,
+      "step": 602
+    },
+    {
+      "epoch": 0.3471502590673575,
+      "grad_norm": 4.017702579498291,
+      "learning_rate": 0.0001969970838859468,
+      "loss": 2.3358,
+      "step": 603
+    },
+    {
+      "epoch": 0.34772596430627517,
+      "grad_norm": 4.556800842285156,
+      "learning_rate": 0.00019693825231400423,
+      "loss": 2.1526,
+      "step": 604
+    },
+    {
+      "epoch": 0.34830166954519287,
+      "grad_norm": 8.760571479797363,
+      "learning_rate": 0.0001968788599898202,
+      "loss": 2.3013,
+      "step": 605
+    },
+    {
+      "epoch": 0.3488773747841105,
+      "grad_norm": 4.910373210906982,
+      "learning_rate": 0.0001968189072964757,
+      "loss": 2.038,
+      "step": 606
+    },
+    {
+      "epoch": 0.3494530800230282,
+      "grad_norm": 14.5215425491333,
+      "learning_rate": 0.00019675839462066582,
+      "loss": 2.2494,
+      "step": 607
+    },
+    {
+      "epoch": 0.35002878526194586,
+      "grad_norm": 7.343470573425293,
+      "learning_rate": 0.00019669732235269775,
+      "loss": 1.8103,
+      "step": 608
+    },
+    {
+      "epoch": 0.35060449050086356,
+      "grad_norm": 6.75926399230957,
+      "learning_rate": 0.00019663569088648796,
+      "loss": 2.0837,
+      "step": 609
+    },
+    {
+      "epoch": 0.3511801957397812,
+      "grad_norm": 4.556105136871338,
+      "learning_rate": 0.0001965735006195598,
+      "loss": 2.111,
+      "step": 610
+    },
+    {
+      "epoch": 0.3517559009786989,
+      "grad_norm": 7.004334449768066,
+      "learning_rate": 0.0001965107519530408,
+      "loss": 2.1351,
+      "step": 611
+    },
+    {
+      "epoch": 0.35233160621761656,
+      "grad_norm": 3.7574639320373535,
+      "learning_rate": 0.00019644744529166025,
+      "loss": 1.9899,
+      "step": 612
+    },
+    {
+      "epoch": 0.35290731145653426,
+      "grad_norm": 7.275668144226074,
+      "learning_rate": 0.0001963835810437465,
+      "loss": 1.7074,
+      "step": 613
+    },
+    {
+      "epoch": 0.3534830166954519,
+      "grad_norm": 4.05908727645874,
+      "learning_rate": 0.00019631915962122436,
+      "loss": 1.7602,
+      "step": 614
+    },
+    {
+      "epoch": 0.3540587219343696,
+      "grad_norm": 3.8614981174468994,
+      "learning_rate": 0.00019625418143961234,
+      "loss": 1.878,
+      "step": 615
+    },
+    {
+      "epoch": 0.3546344271732873,
+      "grad_norm": 3.8152644634246826,
+      "learning_rate": 0.00019618864691802013,
+      "loss": 2.1187,
+      "step": 616
+    },
+    {
+      "epoch": 0.35521013241220495,
+      "grad_norm": 7.1591668128967285,
+      "learning_rate": 0.00019612255647914574,
+      "loss": 1.889,
+      "step": 617
+    },
+    {
+      "epoch": 0.35578583765112265,
+      "grad_norm": 13.686311721801758,
+      "learning_rate": 0.00019605591054927294,
+      "loss": 1.8415,
+      "step": 618
+    },
+    {
+      "epoch": 0.3563615428900403,
+      "grad_norm": 4.854591369628906,
+      "learning_rate": 0.00019598870955826828,
+      "loss": 2.2113,
+      "step": 619
+    },
+    {
+      "epoch": 0.356937248128958,
+      "grad_norm": 8.912299156188965,
+      "learning_rate": 0.00019592095393957868,
+      "loss": 1.7633,
+      "step": 620
+    },
+    {
+      "epoch": 0.35751295336787564,
+      "grad_norm": 3.053098678588867,
+      "learning_rate": 0.00019585264413022818,
+      "loss": 1.9866,
+      "step": 621
+    },
+    {
+      "epoch": 0.35808865860679334,
+      "grad_norm": 22.903722763061523,
+      "learning_rate": 0.0001957837805708155,
+      "loss": 2.0566,
+      "step": 622
+    },
+    {
+      "epoch": 0.358664363845711,
+      "grad_norm": 2.5533032417297363,
+      "learning_rate": 0.000195714363705511,
+      "loss": 2.0484,
+      "step": 623
+    },
+    {
+      "epoch": 0.3592400690846287,
+      "grad_norm": 4.685166358947754,
+      "learning_rate": 0.00019564439398205388,
+      "loss": 1.9809,
+      "step": 624
+    },
+    {
+      "epoch": 0.35981577432354633,
+      "grad_norm": 6.896650314331055,
+      "learning_rate": 0.00019557387185174924,
+      "loss": 1.9147,
+      "step": 625
+    },
+    {
+      "epoch": 0.36039147956246403,
+      "grad_norm": 3.927499532699585,
+      "learning_rate": 0.00019550279776946525,
+      "loss": 1.8356,
+      "step": 626
+    },
+    {
+      "epoch": 0.3609671848013817,
+      "grad_norm": 2.7331018447875977,
+      "learning_rate": 0.00019543117219363016,
+      "loss": 1.9191,
+      "step": 627
+    },
+    {
+      "epoch": 0.3615428900402994,
+      "grad_norm": 6.016903400421143,
+      "learning_rate": 0.0001953589955862294,
+      "loss": 2.0919,
+      "step": 628
+    },
+    {
+      "epoch": 0.362118595279217,
+      "grad_norm": 5.431999683380127,
+      "learning_rate": 0.00019528626841280246,
+      "loss": 1.5794,
+      "step": 629
+    },
+    {
+      "epoch": 0.3626943005181347,
+      "grad_norm": 4.026440620422363,
+      "learning_rate": 0.00019521299114244004,
+      "loss": 2.2844,
+      "step": 630
+    },
+    {
+      "epoch": 0.36327000575705237,
+      "grad_norm": 7.0267863273620605,
+      "learning_rate": 0.00019513916424778097,
+      "loss": 1.8249,
+      "step": 631
+    },
+    {
+      "epoch": 0.3638457109959701,
+      "grad_norm": 4.048052787780762,
+      "learning_rate": 0.00019506478820500918,
+      "loss": 2.1139,
+      "step": 632
+    },
+    {
+      "epoch": 0.3644214162348877,
+      "grad_norm": 3.6997714042663574,
+      "learning_rate": 0.0001949898634938506,
+      "loss": 1.6588,
+      "step": 633
+    },
+    {
+      "epoch": 0.3649971214738054,
+      "grad_norm": 2.560260772705078,
+      "learning_rate": 0.00019491439059757002,
+      "loss": 1.9762,
+      "step": 634
+    },
+    {
+      "epoch": 0.36557282671272306,
+      "grad_norm": 17.04377555847168,
+      "learning_rate": 0.00019483837000296806,
+      "loss": 1.7949,
+      "step": 635
+    },
+    {
+      "epoch": 0.36614853195164077,
+      "grad_norm": 2.873385190963745,
+      "learning_rate": 0.00019476180220037807,
+      "loss": 1.9637,
+      "step": 636
+    },
+    {
+      "epoch": 0.3667242371905584,
+      "grad_norm": 7.77009391784668,
+      "learning_rate": 0.00019468468768366276,
+      "loss": 1.8636,
+      "step": 637
+    },
+    {
+      "epoch": 0.3672999424294761,
+      "grad_norm": 6.612690448760986,
+      "learning_rate": 0.00019460702695021123,
+      "loss": 1.734,
+      "step": 638
+    },
+    {
+      "epoch": 0.36787564766839376,
+      "grad_norm": 4.485565185546875,
+      "learning_rate": 0.0001945288205009357,
+      "loss": 1.6968,
+      "step": 639
+    },
+    {
+      "epoch": 0.36845135290731146,
+      "grad_norm": 2.9968698024749756,
+      "learning_rate": 0.0001944500688402682,
+      "loss": 1.8785,
+      "step": 640
+    },
+    {
+      "epoch": 0.3690270581462291,
+      "grad_norm": 4.952812194824219,
+      "learning_rate": 0.00019437077247615747,
+      "loss": 1.7285,
+      "step": 641
+    },
+    {
+      "epoch": 0.3696027633851468,
+      "grad_norm": 5.491662502288818,
+      "learning_rate": 0.00019429093192006543,
+      "loss": 1.6328,
+      "step": 642
+    },
+    {
+      "epoch": 0.3701784686240645,
+      "grad_norm": 3.8749518394470215,
+      "learning_rate": 0.00019421054768696422,
+      "loss": 2.2014,
+      "step": 643
+    },
+    {
+      "epoch": 0.37075417386298215,
+      "grad_norm": 6.7762627601623535,
+      "learning_rate": 0.0001941296202953326,
+      "loss": 2.0592,
+      "step": 644
+    },
+    {
+      "epoch": 0.37132987910189985,
+      "grad_norm": 3.307373046875,
+      "learning_rate": 0.00019404815026715267,
+      "loss": 2.3178,
+      "step": 645
+    },
+    {
+      "epoch": 0.3719055843408175,
+      "grad_norm": 3.4404947757720947,
+      "learning_rate": 0.00019396613812790666,
+      "loss": 2.3772,
+      "step": 646
+    },
+    {
+      "epoch": 0.3724812895797352,
+      "grad_norm": 4.453017711639404,
+      "learning_rate": 0.00019388358440657332,
+      "loss": 1.8855,
+      "step": 647
+    },
+    {
+      "epoch": 0.37305699481865284,
+      "grad_norm": 3.175896406173706,
+      "learning_rate": 0.00019380048963562466,
+      "loss": 1.8799,
+      "step": 648
+    },
+    {
+      "epoch": 0.37363270005757054,
+      "grad_norm": 22.680187225341797,
+      "learning_rate": 0.0001937168543510224,
+      "loss": 1.4755,
+      "step": 649
+    },
+    {
+      "epoch": 0.3742084052964882,
+      "grad_norm": 14.353453636169434,
+      "learning_rate": 0.00019363267909221468,
+      "loss": 1.9199,
+      "step": 650
+    },
+    {
+      "epoch": 0.3747841105354059,
+      "grad_norm": 3.4111273288726807,
+      "learning_rate": 0.00019354796440213237,
+      "loss": 2.0271,
+      "step": 651
+    },
+    {
+      "epoch": 0.37535981577432354,
+      "grad_norm": 2.5413737297058105,
+      "learning_rate": 0.00019346271082718575,
+      "loss": 2.0859,
+      "step": 652
+    },
+    {
+      "epoch": 0.37593552101324124,
+      "grad_norm": 2.3607568740844727,
+      "learning_rate": 0.00019337691891726087,
+      "loss": 2.1843,
+      "step": 653
+    },
+    {
+      "epoch": 0.3765112262521589,
+      "grad_norm": 6.652899265289307,
+      "learning_rate": 0.00019329058922571608,
+      "loss": 2.2823,
+      "step": 654
+    },
+    {
+      "epoch": 0.3770869314910766,
+      "grad_norm": 6.970069885253906,
+      "learning_rate": 0.00019320372230937835,
+      "loss": 2.0684,
+      "step": 655
+    },
+    {
+      "epoch": 0.3776626367299942,
+      "grad_norm": 6.668658256530762,
+      "learning_rate": 0.00019311631872853983,
+      "loss": 1.4474,
+      "step": 656
+    },
+    {
+      "epoch": 0.37823834196891193,
+      "grad_norm": 16.344221115112305,
+      "learning_rate": 0.00019302837904695418,
+      "loss": 1.958,
+      "step": 657
+    },
+    {
+      "epoch": 0.3788140472078296,
+      "grad_norm": 11.7747163772583,
+      "learning_rate": 0.00019293990383183277,
+      "loss": 1.9691,
+      "step": 658
+    },
+    {
+      "epoch": 0.3793897524467473,
+      "grad_norm": 3.1886119842529297,
+      "learning_rate": 0.00019285089365384138,
+      "loss": 2.0175,
+      "step": 659
+    },
+    {
+      "epoch": 0.3799654576856649,
+      "grad_norm": 7.979596138000488,
+      "learning_rate": 0.00019276134908709607,
+      "loss": 1.8705,
+      "step": 660
+    },
+    {
+      "epoch": 0.3805411629245826,
+      "grad_norm": 3.5675251483917236,
+      "learning_rate": 0.0001926712707091599,
+      "loss": 1.754,
+      "step": 661
+    },
+    {
+      "epoch": 0.38111686816350027,
+      "grad_norm": 2.696560859680176,
+      "learning_rate": 0.00019258065910103886,
+      "loss": 2.0815,
+      "step": 662
+    },
+    {
+      "epoch": 0.38169257340241797,
+      "grad_norm": 3.2219901084899902,
+      "learning_rate": 0.0001924895148471785,
+      "loss": 1.9866,
+      "step": 663
+    },
+    {
+      "epoch": 0.3822682786413356,
+      "grad_norm": 4.226520538330078,
+      "learning_rate": 0.00019239783853545962,
+      "loss": 1.848,
+      "step": 664
+    },
+    {
+      "epoch": 0.3828439838802533,
+      "grad_norm": 3.089921474456787,
+      "learning_rate": 0.00019230563075719513,
+      "loss": 2.3039,
+      "step": 665
+    },
+    {
+      "epoch": 0.38341968911917096,
+      "grad_norm": 3.959472179412842,
+      "learning_rate": 0.00019221289210712562,
+      "loss": 1.902,
+      "step": 666
+    },
+    {
+      "epoch": 0.38399539435808866,
+      "grad_norm": 9.597257614135742,
+      "learning_rate": 0.000192119623183416,
+      "loss": 1.9769,
+      "step": 667
+    },
+    {
+      "epoch": 0.3845710995970063,
+      "grad_norm": 15.12406063079834,
+      "learning_rate": 0.00019202582458765138,
+      "loss": 1.985,
+      "step": 668
+    },
+    {
+      "epoch": 0.385146804835924,
+      "grad_norm": 3.456636428833008,
+      "learning_rate": 0.00019193149692483326,
+      "loss": 1.6099,
+      "step": 669
+    },
+    {
+      "epoch": 0.3857225100748417,
+      "grad_norm": 2.650001287460327,
+      "learning_rate": 0.00019183664080337556,
+      "loss": 2.4192,
+      "step": 670
+    },
+    {
+      "epoch": 0.38629821531375935,
+      "grad_norm": 2.6241097450256348,
+      "learning_rate": 0.00019174125683510092,
+      "loss": 2.3614,
+      "step": 671
+    },
+    {
+      "epoch": 0.38687392055267705,
+      "grad_norm": 5.434971332550049,
+      "learning_rate": 0.00019164534563523641,
+      "loss": 1.782,
+      "step": 672
+    },
+    {
+      "epoch": 0.3874496257915947,
+      "grad_norm": 2.1434805393218994,
+      "learning_rate": 0.0001915489078224099,
+      "loss": 2.0285,
+      "step": 673
+    },
+    {
+      "epoch": 0.3880253310305124,
+      "grad_norm": 3.9473743438720703,
+      "learning_rate": 0.00019145194401864581,
+      "loss": 2.137,
+      "step": 674
+    },
+    {
+      "epoch": 0.38860103626943004,
+      "grad_norm": 3.913604259490967,
+      "learning_rate": 0.00019135445484936127,
+      "loss": 1.7514,
+      "step": 675
+    },
+    {
+      "epoch": 0.38917674150834775,
+      "grad_norm": 4.43229341506958,
+      "learning_rate": 0.000191256440943362,
+      "loss": 1.6698,
+      "step": 676
+    },
+    {
+      "epoch": 0.3897524467472654,
+      "grad_norm": 3.1151657104492188,
+      "learning_rate": 0.00019115790293283827,
+      "loss": 2.2421,
+      "step": 677
+    },
+    {
+      "epoch": 0.3903281519861831,
+      "grad_norm": 3.7743000984191895,
+      "learning_rate": 0.00019105884145336085,
+      "loss": 1.8634,
+      "step": 678
+    },
+    {
+      "epoch": 0.39090385722510074,
+      "grad_norm": 2.8315064907073975,
+      "learning_rate": 0.00019095925714387682,
+      "loss": 1.6003,
+      "step": 679
+    },
+    {
+      "epoch": 0.39147956246401844,
+      "grad_norm": 13.85084342956543,
+      "learning_rate": 0.00019085915064670557,
+      "loss": 1.9885,
+      "step": 680
+    },
+    {
+      "epoch": 0.3920552677029361,
+      "grad_norm": 8.601191520690918,
+      "learning_rate": 0.00019075852260753463,
+      "loss": 1.8575,
+      "step": 681
+    },
+    {
+      "epoch": 0.3926309729418538,
+      "grad_norm": 2.420215606689453,
+      "learning_rate": 0.00019065737367541545,
+      "loss": 2.0188,
+      "step": 682
+    },
+    {
+      "epoch": 0.39320667818077143,
+      "grad_norm": 9.427199363708496,
+      "learning_rate": 0.0001905557045027592,
+      "loss": 1.8087,
+      "step": 683
+    },
+    {
+      "epoch": 0.39378238341968913,
+      "grad_norm": 2.8770227432250977,
+      "learning_rate": 0.00019045351574533274,
+      "loss": 1.9231,
+      "step": 684
+    },
+    {
+      "epoch": 0.3943580886586068,
+      "grad_norm": 5.514732837677002,
+      "learning_rate": 0.00019035080806225404,
+      "loss": 1.8629,
+      "step": 685
+    },
+    {
+      "epoch": 0.3949337938975245,
+      "grad_norm": 5.505938529968262,
+      "learning_rate": 0.00019024758211598833,
+      "loss": 2.0178,
+      "step": 686
+    },
+    {
+      "epoch": 0.3955094991364421,
+      "grad_norm": 4.23834753036499,
+      "learning_rate": 0.00019014383857234355,
+      "loss": 1.5748,
+      "step": 687
+    },
+    {
+      "epoch": 0.3960852043753598,
+      "grad_norm": 4.225786209106445,
+      "learning_rate": 0.00019003957810046615,
+      "loss": 1.8404,
+      "step": 688
+    },
+    {
+      "epoch": 0.39666090961427747,
+      "grad_norm": 10.373225212097168,
+      "learning_rate": 0.00018993480137283685,
+      "loss": 1.9054,
+      "step": 689
+    },
+    {
+      "epoch": 0.39723661485319517,
+      "grad_norm": 5.083978652954102,
+      "learning_rate": 0.00018982950906526615,
+      "loss": 1.8938,
+      "step": 690
+    },
+    {
+      "epoch": 0.3978123200921128,
+      "grad_norm": 4.478074073791504,
+      "learning_rate": 0.00018972370185689,
+      "loss": 1.9073,
+      "step": 691
+    },
+    {
+      "epoch": 0.3983880253310305,
+      "grad_norm": 3.557939052581787,
+      "learning_rate": 0.00018961738043016556,
+      "loss": 1.847,
+      "step": 692
+    },
+    {
+      "epoch": 0.39896373056994816,
+      "grad_norm": 4.705951690673828,
+      "learning_rate": 0.00018951054547086666,
+      "loss": 1.7451,
+      "step": 693
+    },
+    {
+      "epoch": 0.39953943580886586,
+      "grad_norm": 2.8145923614501953,
+      "learning_rate": 0.00018940319766807943,
+      "loss": 2.054,
+      "step": 694
+    },
+    {
+      "epoch": 0.40011514104778356,
+      "grad_norm": 10.403020858764648,
+      "learning_rate": 0.00018929533771419783,
+      "loss": 1.8062,
+      "step": 695
+    },
+    {
+      "epoch": 0.4006908462867012,
+      "grad_norm": 5.947159290313721,
+      "learning_rate": 0.00018918696630491915,
+      "loss": 1.8459,
+      "step": 696
+    },
+    {
+      "epoch": 0.4012665515256189,
+      "grad_norm": 3.2348601818084717,
+      "learning_rate": 0.00018907808413923968,
+      "loss": 1.815,
+      "step": 697
+    },
+    {
+      "epoch": 0.40184225676453655,
+      "grad_norm": 8.500833511352539,
+      "learning_rate": 0.00018896869191945,
+      "loss": 1.535,
+      "step": 698
+    },
+    {
+      "epoch": 0.40241796200345425,
+      "grad_norm": 5.008488178253174,
+      "learning_rate": 0.0001888587903511306,
+      "loss": 2.3482,
+      "step": 699
+    },
+    {
+      "epoch": 0.4029936672423719,
+      "grad_norm": 2.739643096923828,
+      "learning_rate": 0.00018874838014314724,
+      "loss": 2.284,
+      "step": 700
+    },
+    {
+      "epoch": 0.4035693724812896,
+      "grad_norm": 10.596121788024902,
+      "learning_rate": 0.0001886374620076464,
+      "loss": 1.6078,
+      "step": 701
+    },
+    {
+      "epoch": 0.40414507772020725,
+      "grad_norm": 2.6627824306488037,
+      "learning_rate": 0.00018852603666005073,
+      "loss": 1.7632,
+      "step": 702
+    },
+    {
+      "epoch": 0.40472078295912495,
+      "grad_norm": 4.91156530380249,
+      "learning_rate": 0.00018841410481905434,
+      "loss": 1.8726,
+      "step": 703
+    },
+    {
+      "epoch": 0.4052964881980426,
+      "grad_norm": 3.1350510120391846,
+      "learning_rate": 0.0001883016672066183,
+      "loss": 2.0387,
+      "step": 704
+    },
+    {
+      "epoch": 0.4058721934369603,
+      "grad_norm": 16.92197036743164,
+      "learning_rate": 0.0001881887245479659,
+      "loss": 2.1191,
+      "step": 705
+    },
+    {
+      "epoch": 0.40644789867587794,
+      "grad_norm": 3.093526840209961,
+      "learning_rate": 0.00018807527757157787,
+      "loss": 2.0547,
+      "step": 706
+    },
+    {
+      "epoch": 0.40702360391479564,
+      "grad_norm": 4.2745680809021,
+      "learning_rate": 0.00018796132700918793,
+      "loss": 1.8785,
+      "step": 707
+    },
+    {
+      "epoch": 0.4075993091537133,
+      "grad_norm": 3.898991107940674,
+      "learning_rate": 0.00018784687359577791,
+      "loss": 1.6114,
+      "step": 708
+    },
+    {
+      "epoch": 0.408175014392631,
+      "grad_norm": 2.8433330059051514,
+      "learning_rate": 0.00018773191806957298,
+      "loss": 2.0685,
+      "step": 709
+    },
+    {
+      "epoch": 0.40875071963154863,
+      "grad_norm": 16.428258895874023,
+      "learning_rate": 0.00018761646117203696,
+      "loss": 1.8752,
+      "step": 710
+    },
+    {
+      "epoch": 0.40932642487046633,
+      "grad_norm": 4.984866142272949,
+      "learning_rate": 0.0001875005036478675,
+      "loss": 2.0355,
+      "step": 711
+    },
+    {
+      "epoch": 0.409902130109384,
+      "grad_norm": 3.2980496883392334,
+      "learning_rate": 0.00018738404624499136,
+      "loss": 1.8788,
+      "step": 712
+    },
+    {
+      "epoch": 0.4104778353483017,
+      "grad_norm": 2.58404541015625,
+      "learning_rate": 0.00018726708971455945,
+      "loss": 2.0856,
+      "step": 713
+    },
+    {
+      "epoch": 0.4110535405872193,
+      "grad_norm": 22.611204147338867,
+      "learning_rate": 0.00018714963481094207,
+      "loss": 1.7451,
+      "step": 714
+    },
+    {
+      "epoch": 0.411629245826137,
+      "grad_norm": 3.256192445755005,
+      "learning_rate": 0.0001870316822917241,
+      "loss": 1.7017,
+      "step": 715
+    },
+    {
+      "epoch": 0.41220495106505467,
+      "grad_norm": 3.7287187576293945,
+      "learning_rate": 0.00018691323291769992,
+      "loss": 1.5585,
+      "step": 716
+    },
+    {
+      "epoch": 0.41278065630397237,
+      "grad_norm": 4.698144912719727,
+      "learning_rate": 0.00018679428745286872,
+      "loss": 1.8391,
+      "step": 717
+    },
+    {
+      "epoch": 0.41335636154289,
+      "grad_norm": 8.514996528625488,
+      "learning_rate": 0.00018667484666442944,
+      "loss": 1.7789,
+      "step": 718
+    },
+    {
+      "epoch": 0.4139320667818077,
+      "grad_norm": 7.140060901641846,
+      "learning_rate": 0.00018655491132277589,
+      "loss": 1.894,
+      "step": 719
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 3.8144354820251465,
+      "learning_rate": 0.00018643448220149173,
+      "loss": 1.7206,
+      "step": 720
+    },
+    {
+      "epoch": 0.41508347725964306,
+      "grad_norm": 18.383852005004883,
+      "learning_rate": 0.0001863135600773455,
+      "loss": 1.9508,
+      "step": 721
+    },
+    {
+      "epoch": 0.41565918249856076,
+      "grad_norm": 4.58454704284668,
+      "learning_rate": 0.00018619214573028562,
+      "loss": 1.9023,
+      "step": 722
+    },
+    {
+      "epoch": 0.4162348877374784,
+      "grad_norm": 2.33950138092041,
+      "learning_rate": 0.00018607023994343533,
+      "loss": 1.9343,
+      "step": 723
+    },
+    {
+      "epoch": 0.4168105929763961,
+      "grad_norm": 3.2266829013824463,
+      "learning_rate": 0.0001859478435030877,
+      "loss": 2.0175,
+      "step": 724
+    },
+    {
+      "epoch": 0.41738629821531376,
+      "grad_norm": 2.7907965183258057,
+      "learning_rate": 0.00018582495719870047,
+      "loss": 1.9857,
+      "step": 725
+    },
+    {
+      "epoch": 0.41796200345423146,
+      "grad_norm": 9.727225303649902,
+      "learning_rate": 0.00018570158182289103,
+      "loss": 1.7811,
+      "step": 726
+    },
+    {
+      "epoch": 0.4185377086931491,
+      "grad_norm": 8.029142379760742,
+      "learning_rate": 0.00018557771817143132,
+      "loss": 2.1232,
+      "step": 727
+    },
+    {
+      "epoch": 0.4191134139320668,
+      "grad_norm": 17.49789810180664,
+      "learning_rate": 0.0001854533670432426,
+      "loss": 1.8807,
+      "step": 728
+    },
+    {
+      "epoch": 0.41968911917098445,
+      "grad_norm": 2.434882402420044,
+      "learning_rate": 0.00018532852924039035,
+      "loss": 1.839,
+      "step": 729
+    },
+    {
+      "epoch": 0.42026482440990215,
+      "grad_norm": 4.167110919952393,
+      "learning_rate": 0.0001852032055680792,
+      "loss": 1.803,
+      "step": 730
+    },
+    {
+      "epoch": 0.4208405296488198,
+      "grad_norm": 2.675874948501587,
+      "learning_rate": 0.00018507739683464752,
+      "loss": 2.3544,
+      "step": 731
+    },
+    {
+      "epoch": 0.4214162348877375,
+      "grad_norm": 3.3444297313690186,
+      "learning_rate": 0.00018495110385156237,
+      "loss": 2.0448,
+      "step": 732
+    },
+    {
+      "epoch": 0.42199194012665514,
+      "grad_norm": 4.82088041305542,
+      "learning_rate": 0.00018482432743341433,
+      "loss": 2.0651,
+      "step": 733
+    },
+    {
+      "epoch": 0.42256764536557284,
+      "grad_norm": 2.519653081893921,
+      "learning_rate": 0.000184697068397912,
+      "loss": 2.0949,
+      "step": 734
+    },
+    {
+      "epoch": 0.4231433506044905,
+      "grad_norm": 5.350189685821533,
+      "learning_rate": 0.0001845693275658769,
+      "loss": 1.7065,
+      "step": 735
+    },
+    {
+      "epoch": 0.4237190558434082,
+      "grad_norm": 3.690128803253174,
+      "learning_rate": 0.00018444110576123812,
+      "loss": 1.6012,
+      "step": 736
+    },
+    {
+      "epoch": 0.42429476108232583,
+      "grad_norm": 3.2592711448669434,
+      "learning_rate": 0.00018431240381102713,
+      "loss": 1.956,
+      "step": 737
+    },
+    {
+      "epoch": 0.42487046632124353,
+      "grad_norm": 8.19218921661377,
+      "learning_rate": 0.0001841832225453722,
+      "loss": 1.6416,
+      "step": 738
+    },
+    {
+      "epoch": 0.4254461715601612,
+      "grad_norm": 2.3770790100097656,
+      "learning_rate": 0.0001840535627974933,
+      "loss": 2.1405,
+      "step": 739
+    },
+    {
+      "epoch": 0.4260218767990789,
+      "grad_norm": 4.077558994293213,
+      "learning_rate": 0.00018392342540369657,
+      "loss": 1.5653,
+      "step": 740
+    },
+    {
+      "epoch": 0.4265975820379965,
+      "grad_norm": 2.6370084285736084,
+      "learning_rate": 0.00018379281120336897,
+      "loss": 1.768,
+      "step": 741
+    },
+    {
+      "epoch": 0.4271732872769142,
+      "grad_norm": 2.450295925140381,
+      "learning_rate": 0.00018366172103897283,
+      "loss": 1.7358,
+      "step": 742
+    },
+    {
+      "epoch": 0.42774899251583187,
+      "grad_norm": 5.39324951171875,
+      "learning_rate": 0.00018353015575604052,
+      "loss": 2.0319,
+      "step": 743
+    },
+    {
+      "epoch": 0.4283246977547496,
+      "grad_norm": 2.238994836807251,
+      "learning_rate": 0.0001833981162031689,
+      "loss": 2.1476,
+      "step": 744
+    },
+    {
+      "epoch": 0.4289004029936672,
+      "grad_norm": 2.7961604595184326,
+      "learning_rate": 0.00018326560323201382,
+      "loss": 1.937,
+      "step": 745
+    },
+    {
+      "epoch": 0.4294761082325849,
+      "grad_norm": 3.0251359939575195,
+      "learning_rate": 0.00018313261769728478,
+      "loss": 1.387,
+      "step": 746
+    },
+    {
+      "epoch": 0.43005181347150256,
+      "grad_norm": 12.313629150390625,
+      "learning_rate": 0.00018299916045673922,
+      "loss": 1.858,
+      "step": 747
+    },
+    {
+      "epoch": 0.43062751871042027,
+      "grad_norm": 2.7766458988189697,
+      "learning_rate": 0.00018286523237117717,
+      "loss": 1.7907,
+      "step": 748
+    },
+    {
+      "epoch": 0.43120322394933797,
+      "grad_norm": 4.888232707977295,
+      "learning_rate": 0.00018273083430443555,
+      "loss": 2.0781,
+      "step": 749
+    },
+    {
+      "epoch": 0.4317789291882556,
+      "grad_norm": 3.5016186237335205,
+      "learning_rate": 0.00018259596712338268,
+      "loss": 1.9422,
+      "step": 750
+    },
+    {
+      "epoch": 0.4323546344271733,
+      "grad_norm": 2.471903085708618,
+      "learning_rate": 0.00018246063169791269,
+      "loss": 1.4743,
+      "step": 751
+    },
+    {
+      "epoch": 0.43293033966609096,
+      "grad_norm": 5.355947494506836,
+      "learning_rate": 0.0001823248289009399,
+      "loss": 1.7892,
+      "step": 752
+    },
+    {
+      "epoch": 0.43350604490500866,
+      "grad_norm": 30.411474227905273,
+      "learning_rate": 0.00018218855960839308,
+      "loss": 2.1997,
+      "step": 753
+    },
+    {
+      "epoch": 0.4340817501439263,
+      "grad_norm": 22.769906997680664,
+      "learning_rate": 0.00018205182469921001,
+      "loss": 2.2114,
+      "step": 754
+    },
+    {
+      "epoch": 0.434657455382844,
+      "grad_norm": 2.85595703125,
+      "learning_rate": 0.00018191462505533172,
+      "loss": 1.6781,
+      "step": 755
+    },
+    {
+      "epoch": 0.43523316062176165,
+      "grad_norm": 13.515556335449219,
+      "learning_rate": 0.00018177696156169664,
+      "loss": 1.8627,
+      "step": 756
+    },
+    {
+      "epoch": 0.43580886586067935,
+      "grad_norm": 2.449556589126587,
+      "learning_rate": 0.00018163883510623514,
+      "loss": 1.9787,
+      "step": 757
+    },
+    {
+      "epoch": 0.436384571099597,
+      "grad_norm": 3.347914457321167,
+      "learning_rate": 0.00018150024657986373,
+      "loss": 1.6179,
+      "step": 758
+    },
+    {
+      "epoch": 0.4369602763385147,
+      "grad_norm": 2.167959451675415,
+      "learning_rate": 0.00018136119687647912,
+      "loss": 2.2641,
+      "step": 759
+    },
+    {
+      "epoch": 0.43753598157743234,
+      "grad_norm": 1.9680399894714355,
+      "learning_rate": 0.00018122168689295283,
+      "loss": 2.1557,
+      "step": 760
+    },
+    {
+      "epoch": 0.43811168681635004,
+      "grad_norm": 1.9507166147232056,
+      "learning_rate": 0.000181081717529125,
+      "loss": 1.9336,
+      "step": 761
+    },
+    {
+      "epoch": 0.4386873920552677,
+      "grad_norm": 10.30239200592041,
+      "learning_rate": 0.0001809412896877989,
+      "loss": 1.716,
+      "step": 762
+    },
+    {
+      "epoch": 0.4392630972941854,
+      "grad_norm": 17.331459045410156,
+      "learning_rate": 0.0001808004042747349,
+      "loss": 1.7709,
+      "step": 763
+    },
+    {
+      "epoch": 0.43983880253310303,
+      "grad_norm": 8.791406631469727,
+      "learning_rate": 0.00018065906219864476,
+      "loss": 1.8645,
+      "step": 764
+    },
+    {
+      "epoch": 0.44041450777202074,
+      "grad_norm": 14.691398620605469,
+      "learning_rate": 0.0001805172643711857,
+      "loss": 1.732,
+      "step": 765
+    },
+    {
+      "epoch": 0.4409902130109384,
+      "grad_norm": 8.738691329956055,
+      "learning_rate": 0.00018037501170695459,
+      "loss": 1.8119,
+      "step": 766
+    },
+    {
+      "epoch": 0.4415659182498561,
+      "grad_norm": 3.6133551597595215,
+      "learning_rate": 0.00018023230512348193,
+      "loss": 2.2517,
+      "step": 767
+    },
+    {
+      "epoch": 0.4421416234887737,
+      "grad_norm": 4.219852447509766,
+      "learning_rate": 0.00018008914554122597,
+      "loss": 1.9683,
+      "step": 768
+    },
+    {
+      "epoch": 0.44271732872769143,
+      "grad_norm": 6.014896869659424,
+      "learning_rate": 0.00017994553388356695,
+      "loss": 1.6415,
+      "step": 769
+    },
+    {
+      "epoch": 0.4432930339666091,
+      "grad_norm": 5.801370620727539,
+      "learning_rate": 0.00017980147107680083,
+      "loss": 1.8638,
+      "step": 770
+    },
+    {
+      "epoch": 0.4438687392055268,
+      "grad_norm": 3.9522225856781006,
+      "learning_rate": 0.00017965695805013365,
+      "loss": 2.1045,
+      "step": 771
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.9866466522216797,
+      "learning_rate": 0.00017951199573567524,
+      "loss": 1.9505,
+      "step": 772
+    },
+    {
+      "epoch": 0.4450201496833621,
+      "grad_norm": 3.0734667778015137,
+      "learning_rate": 0.00017936658506843335,
+      "loss": 2.2168,
+      "step": 773
+    },
+    {
+      "epoch": 0.44559585492227977,
+      "grad_norm": 3.1300957202911377,
+      "learning_rate": 0.00017922072698630772,
+      "loss": 1.8417,
+      "step": 774
+    },
+    {
+      "epoch": 0.44617156016119747,
+      "grad_norm": 2.1265501976013184,
+      "learning_rate": 0.00017907442243008382,
+      "loss": 2.0039,
+      "step": 775
+    },
+    {
+      "epoch": 0.44674726540011517,
+      "grad_norm": 2.7996795177459717,
+      "learning_rate": 0.00017892767234342684,
+      "loss": 1.8003,
+      "step": 776
+    },
+    {
+      "epoch": 0.4473229706390328,
+      "grad_norm": 6.149320602416992,
+      "learning_rate": 0.00017878047767287577,
+      "loss": 1.7551,
+      "step": 777
+    },
+    {
+      "epoch": 0.4478986758779505,
+      "grad_norm": 2.3379878997802734,
+      "learning_rate": 0.00017863283936783708,
+      "loss": 1.9938,
+      "step": 778
+    },
+    {
+      "epoch": 0.44847438111686816,
+      "grad_norm": 3.4820477962493896,
+      "learning_rate": 0.00017848475838057873,
+      "loss": 1.5153,
+      "step": 779
+    },
+    {
+      "epoch": 0.44905008635578586,
+      "grad_norm": 3.582059860229492,
+      "learning_rate": 0.00017833623566622397,
+      "loss": 1.9166,
+      "step": 780
+    },
+    {
+      "epoch": 0.4496257915947035,
+      "grad_norm": 3.9701995849609375,
+      "learning_rate": 0.00017818727218274513,
+      "loss": 1.4762,
+      "step": 781
+    },
+    {
+      "epoch": 0.4502014968336212,
+      "grad_norm": 2.0633654594421387,
+      "learning_rate": 0.00017803786889095764,
+      "loss": 2.1013,
+      "step": 782
+    },
+    {
+      "epoch": 0.45077720207253885,
+      "grad_norm": 2.459294080734253,
+      "learning_rate": 0.00017788802675451352,
+      "loss": 1.8575,
+      "step": 783
+    },
+    {
+      "epoch": 0.45135290731145655,
+      "grad_norm": 5.101840496063232,
+      "learning_rate": 0.00017773774673989553,
+      "loss": 1.4693,
+      "step": 784
+    },
+    {
+      "epoch": 0.4519286125503742,
+      "grad_norm": 2.827829360961914,
+      "learning_rate": 0.0001775870298164106,
+      "loss": 2.1377,
+      "step": 785
+    },
+    {
+      "epoch": 0.4525043177892919,
+      "grad_norm": 2.8199522495269775,
+      "learning_rate": 0.0001774358769561838,
+      "loss": 1.9839,
+      "step": 786
+    },
+    {
+      "epoch": 0.45308002302820954,
+      "grad_norm": 3.852107286453247,
+      "learning_rate": 0.00017728428913415192,
+      "loss": 1.7629,
+      "step": 787
+    },
+    {
+      "epoch": 0.45365572826712725,
+      "grad_norm": 5.424905776977539,
+      "learning_rate": 0.00017713226732805738,
+      "loss": 1.8626,
+      "step": 788
+    },
+    {
+      "epoch": 0.4542314335060449,
+      "grad_norm": 8.507397651672363,
+      "learning_rate": 0.0001769798125184417,
+      "loss": 2.0023,
+      "step": 789
+    },
+    {
+      "epoch": 0.4548071387449626,
+      "grad_norm": 2.348231792449951,
+      "learning_rate": 0.00017682692568863926,
+      "loss": 1.8687,
+      "step": 790
+    },
+    {
+      "epoch": 0.45538284398388024,
+      "grad_norm": 16.692827224731445,
+      "learning_rate": 0.00017667360782477106,
+      "loss": 2.0102,
+      "step": 791
+    },
+    {
+      "epoch": 0.45595854922279794,
+      "grad_norm": 3.0447139739990234,
+      "learning_rate": 0.00017651985991573826,
+      "loss": 1.867,
+      "step": 792
+    },
+    {
+      "epoch": 0.4565342544617156,
+      "grad_norm": 2.9347379207611084,
+      "learning_rate": 0.00017636568295321573,
+      "loss": 1.6961,
+      "step": 793
+    },
+    {
+      "epoch": 0.4571099597006333,
+      "grad_norm": 6.137345790863037,
+      "learning_rate": 0.00017621107793164582,
+      "loss": 1.5024,
+      "step": 794
+    },
+    {
+      "epoch": 0.45768566493955093,
+      "grad_norm": 1.9799631834030151,
+      "learning_rate": 0.0001760560458482318,
+      "loss": 1.9756,
+      "step": 795
+    },
+    {
+      "epoch": 0.45826137017846863,
+      "grad_norm": 10.146332740783691,
+      "learning_rate": 0.00017590058770293156,
+      "loss": 1.8236,
+      "step": 796
+    },
+    {
+      "epoch": 0.4588370754173863,
+      "grad_norm": 2.7647223472595215,
+      "learning_rate": 0.00017574470449845103,
+      "loss": 1.9874,
+      "step": 797
+    },
+    {
+      "epoch": 0.459412780656304,
+      "grad_norm": 2.6900711059570312,
+      "learning_rate": 0.00017558839724023781,
+      "loss": 1.9816,
+      "step": 798
+    },
+    {
+      "epoch": 0.4599884858952216,
+      "grad_norm": 2.0507872104644775,
+      "learning_rate": 0.00017543166693647467,
+      "loss": 2.1267,
+      "step": 799
+    },
+    {
+      "epoch": 0.4605641911341393,
+      "grad_norm": 5.527276515960693,
+      "learning_rate": 0.00017527451459807292,
+      "loss": 1.9468,
+      "step": 800
+    },
+    {
+      "epoch": 0.46113989637305697,
+      "grad_norm": 8.115386009216309,
+      "learning_rate": 0.00017511694123866615,
+      "loss": 1.6804,
+      "step": 801
+    },
+    {
+      "epoch": 0.46171560161197467,
+      "grad_norm": 2.108691692352295,
+      "learning_rate": 0.0001749589478746034,
+      "loss": 1.5739,
+      "step": 802
+    },
+    {
+      "epoch": 0.46229130685089237,
+      "grad_norm": 15.620509147644043,
+      "learning_rate": 0.00017480053552494288,
+      "loss": 1.7336,
+      "step": 803
+    },
+    {
+      "epoch": 0.46286701208981,
+      "grad_norm": 3.442645788192749,
+      "learning_rate": 0.00017464170521144508,
+      "loss": 1.7112,
+      "step": 804
+    },
+    {
+      "epoch": 0.4634427173287277,
+      "grad_norm": 7.99544095993042,
+      "learning_rate": 0.0001744824579585665,
+      "loss": 1.447,
+      "step": 805
+    },
+    {
+      "epoch": 0.46401842256764536,
+      "grad_norm": 7.0831217765808105,
+      "learning_rate": 0.0001743227947934529,
+      "loss": 1.8631,
+      "step": 806
+    },
+    {
+      "epoch": 0.46459412780656306,
+      "grad_norm": 6.996182441711426,
+      "learning_rate": 0.0001741627167459326,
+      "loss": 1.6913,
+      "step": 807
+    },
+    {
+      "epoch": 0.4651698330454807,
+      "grad_norm": 2.5042760372161865,
+      "learning_rate": 0.00017400222484851001,
+      "loss": 1.8691,
+      "step": 808
+    },
+    {
+      "epoch": 0.4657455382843984,
+      "grad_norm": 3.7604565620422363,
+      "learning_rate": 0.00017384132013635874,
+      "loss": 2.0776,
+      "step": 809
+    },
+    {
+      "epoch": 0.46632124352331605,
+      "grad_norm": 4.427332878112793,
+      "learning_rate": 0.00017368000364731517,
+      "loss": 1.879,
+      "step": 810
+    },
+    {
+      "epoch": 0.46689694876223375,
+      "grad_norm": 3.7155957221984863,
+      "learning_rate": 0.0001735182764218716,
+      "loss": 1.9187,
+      "step": 811
+    },
+    {
+      "epoch": 0.4674726540011514,
+      "grad_norm": 3.7291319370269775,
+      "learning_rate": 0.00017335613950316962,
+      "loss": 1.5446,
+      "step": 812
+    },
+    {
+      "epoch": 0.4680483592400691,
+      "grad_norm": 5.578220367431641,
+      "learning_rate": 0.0001731935939369933,
+      "loss": 1.9119,
+      "step": 813
+    },
+    {
+      "epoch": 0.46862406447898675,
+      "grad_norm": 3.377821207046509,
+      "learning_rate": 0.00017303064077176246,
+      "loss": 2.0695,
+      "step": 814
+    },
+    {
+      "epoch": 0.46919976971790445,
+      "grad_norm": 2.6164028644561768,
+      "learning_rate": 0.000172867281058526,
+      "loss": 1.8049,
+      "step": 815
+    },
+    {
+      "epoch": 0.4697754749568221,
+      "grad_norm": 13.39267635345459,
+      "learning_rate": 0.00017270351585095507,
+      "loss": 1.45,
+      "step": 816
+    },
+    {
+      "epoch": 0.4703511801957398,
+      "grad_norm": 2.8776485919952393,
+      "learning_rate": 0.00017253934620533625,
+      "loss": 1.9204,
+      "step": 817
+    },
+    {
+      "epoch": 0.47092688543465744,
+      "grad_norm": 3.7855734825134277,
+      "learning_rate": 0.00017237477318056462,
+      "loss": 1.2213,
+      "step": 818
+    },
+    {
+      "epoch": 0.47150259067357514,
+      "grad_norm": 2.4604861736297607,
+      "learning_rate": 0.00017220979783813724,
+      "loss": 1.6834,
+      "step": 819
+    },
+    {
+      "epoch": 0.4720782959124928,
+      "grad_norm": 3.9738218784332275,
+      "learning_rate": 0.00017204442124214603,
+      "loss": 2.0102,
+      "step": 820
+    },
+    {
+      "epoch": 0.4726540011514105,
+      "grad_norm": 53.47602462768555,
+      "learning_rate": 0.00017187864445927103,
+      "loss": 1.9759,
+      "step": 821
+    },
+    {
+      "epoch": 0.47322970639032813,
+      "grad_norm": 9.791850090026855,
+      "learning_rate": 0.0001717124685587734,
+      "loss": 1.5549,
+      "step": 822
+    },
+    {
+      "epoch": 0.47380541162924583,
+      "grad_norm": 3.8684937953948975,
+      "learning_rate": 0.00017154589461248877,
+      "loss": 1.5908,
+      "step": 823
+    },
+    {
+      "epoch": 0.4743811168681635,
+      "grad_norm": 24.494279861450195,
+      "learning_rate": 0.00017137892369482004,
+      "loss": 1.6402,
+      "step": 824
+    },
+    {
+      "epoch": 0.4749568221070812,
+      "grad_norm": 3.5959551334381104,
+      "learning_rate": 0.00017121155688273057,
+      "loss": 1.6951,
+      "step": 825
+    },
+    {
+      "epoch": 0.4755325273459988,
+      "grad_norm": 5.078423976898193,
+      "learning_rate": 0.00017104379525573738,
+      "loss": 1.6469,
+      "step": 826
+    },
+    {
+      "epoch": 0.4761082325849165,
+      "grad_norm": 2.160147190093994,
+      "learning_rate": 0.00017087563989590386,
+      "loss": 1.756,
+      "step": 827
+    },
+    {
+      "epoch": 0.47668393782383417,
+      "grad_norm": 3.555968999862671,
+      "learning_rate": 0.00017070709188783318,
+      "loss": 1.9666,
+      "step": 828
+    },
+    {
+      "epoch": 0.47725964306275187,
+      "grad_norm": 2.406215190887451,
+      "learning_rate": 0.00017053815231866088,
+      "loss": 2.0264,
+      "step": 829
+    },
+    {
+      "epoch": 0.47783534830166957,
+      "grad_norm": 3.1693837642669678,
+      "learning_rate": 0.00017036882227804826,
+      "loss": 1.6301,
+      "step": 830
+    },
+    {
+      "epoch": 0.4784110535405872,
+      "grad_norm": 2.4648032188415527,
+      "learning_rate": 0.00017019910285817505,
+      "loss": 2.1071,
+      "step": 831
+    },
+    {
+      "epoch": 0.4789867587795049,
+      "grad_norm": 2.020519733428955,
+      "learning_rate": 0.00017002899515373252,
+      "loss": 2.0168,
+      "step": 832
+    },
+    {
+      "epoch": 0.47956246401842256,
+      "grad_norm": 8.258744239807129,
+      "learning_rate": 0.00016985850026191634,
+      "loss": 1.738,
+      "step": 833
+    },
+    {
+      "epoch": 0.48013816925734026,
+      "grad_norm": 2.6535940170288086,
+      "learning_rate": 0.0001696876192824196,
+      "loss": 2.0153,
+      "step": 834
+    },
+    {
+      "epoch": 0.4807138744962579,
+      "grad_norm": 2.494950294494629,
+      "learning_rate": 0.00016951635331742564,
+      "loss": 1.8319,
+      "step": 835
+    },
+    {
+      "epoch": 0.4812895797351756,
+      "grad_norm": 13.977831840515137,
+      "learning_rate": 0.0001693447034716009,
+      "loss": 1.6622,
+      "step": 836
+    },
+    {
+      "epoch": 0.48186528497409326,
+      "grad_norm": 5.264831066131592,
+      "learning_rate": 0.00016917267085208798,
+      "loss": 1.7066,
+      "step": 837
+    },
+    {
+      "epoch": 0.48244099021301096,
+      "grad_norm": 3.8573200702667236,
+      "learning_rate": 0.0001690002565684982,
+      "loss": 1.7634,
+      "step": 838
+    },
+    {
+      "epoch": 0.4830166954519286,
+      "grad_norm": 4.011209487915039,
+      "learning_rate": 0.0001688274617329048,
+      "loss": 1.6426,
+      "step": 839
+    },
+    {
+      "epoch": 0.4835924006908463,
+      "grad_norm": 4.699135780334473,
+      "learning_rate": 0.00016865428745983538,
+      "loss": 1.9267,
+      "step": 840
+    },
+    {
+      "epoch": 0.48416810592976395,
+      "grad_norm": 4.957156181335449,
+      "learning_rate": 0.0001684807348662651,
+      "loss": 1.8474,
+      "step": 841
+    },
+    {
+      "epoch": 0.48474381116868165,
+      "grad_norm": 2.934382677078247,
+      "learning_rate": 0.00016830680507160924,
+      "loss": 1.7862,
+      "step": 842
+    },
+    {
+      "epoch": 0.4853195164075993,
+      "grad_norm": 2.630108594894409,
+      "learning_rate": 0.00016813249919771592,
+      "loss": 1.8025,
+      "step": 843
+    },
+    {
+      "epoch": 0.485895221646517,
+      "grad_norm": 3.7840278148651123,
+      "learning_rate": 0.00016795781836885913,
+      "loss": 1.5822,
+      "step": 844
+    },
+    {
+      "epoch": 0.48647092688543464,
+      "grad_norm": 4.31719446182251,
+      "learning_rate": 0.00016778276371173123,
+      "loss": 1.4343,
+      "step": 845
+    },
+    {
+      "epoch": 0.48704663212435234,
+      "grad_norm": 11.9985933303833,
+      "learning_rate": 0.00016760733635543578,
+      "loss": 1.8163,
+      "step": 846
+    },
+    {
+      "epoch": 0.48762233736327,
+      "grad_norm": 3.754255533218384,
+      "learning_rate": 0.00016743153743148024,
+      "loss": 1.9249,
+      "step": 847
+    },
+    {
+      "epoch": 0.4881980426021877,
+      "grad_norm": 2.8391778469085693,
+      "learning_rate": 0.00016725536807376873,
+      "loss": 1.6164,
+      "step": 848
+    },
+    {
+      "epoch": 0.48877374784110533,
+      "grad_norm": 2.3037109375,
+      "learning_rate": 0.0001670788294185947,
+      "loss": 1.7085,
+      "step": 849
+    },
+    {
+      "epoch": 0.48934945308002303,
+      "grad_norm": 30.62044334411621,
+      "learning_rate": 0.00016690192260463346,
+      "loss": 1.8193,
+      "step": 850
+    },
+    {
+      "epoch": 0.4899251583189407,
+      "grad_norm": 9.023576736450195,
+      "learning_rate": 0.00016672464877293504,
+      "loss": 1.7972,
+      "step": 851
+    },
+    {
+      "epoch": 0.4905008635578584,
+      "grad_norm": 4.591246128082275,
+      "learning_rate": 0.00016654700906691664,
+      "loss": 1.5173,
+      "step": 852
+    },
+    {
+      "epoch": 0.491076568796776,
+      "grad_norm": 4.623873710632324,
+      "learning_rate": 0.00016636900463235549,
+      "loss": 1.6689,
+      "step": 853
+    },
+    {
+      "epoch": 0.4916522740356937,
+      "grad_norm": 2.144906759262085,
+      "learning_rate": 0.00016619063661738124,
+      "loss": 2.0085,
+      "step": 854
+    },
+    {
+      "epoch": 0.49222797927461137,
+      "grad_norm": 2.73002290725708,
+      "learning_rate": 0.00016601190617246858,
+      "loss": 1.5989,
+      "step": 855
+    },
+    {
+      "epoch": 0.49280368451352907,
+      "grad_norm": 9.77154541015625,
+      "learning_rate": 0.00016583281445042998,
+      "loss": 1.9491,
+      "step": 856
+    },
+    {
+      "epoch": 0.4933793897524468,
+      "grad_norm": 5.815699577331543,
+      "learning_rate": 0.00016565336260640812,
+      "loss": 2.0127,
+      "step": 857
+    },
+    {
+      "epoch": 0.4939550949913644,
+      "grad_norm": 3.791182041168213,
+      "learning_rate": 0.00016547355179786838,
+      "loss": 1.865,
+      "step": 858
+    },
+    {
+      "epoch": 0.4945308002302821,
+      "grad_norm": 3.301182508468628,
+      "learning_rate": 0.00016529338318459165,
+      "loss": 1.7362,
+      "step": 859
+    },
+    {
+      "epoch": 0.49510650546919976,
+      "grad_norm": 3.233245849609375,
+      "learning_rate": 0.00016511285792866648,
+      "loss": 1.5621,
+      "step": 860
+    },
+    {
+      "epoch": 0.49568221070811747,
+      "grad_norm": 4.960054397583008,
+      "learning_rate": 0.00016493197719448182,
+      "loss": 1.739,
+      "step": 861
+    },
+    {
+      "epoch": 0.4962579159470351,
+      "grad_norm": 1.8711457252502441,
+      "learning_rate": 0.00016475074214871953,
+      "loss": 1.8269,
+      "step": 862
+    },
+    {
+      "epoch": 0.4968336211859528,
+      "grad_norm": 2.714691638946533,
+      "learning_rate": 0.00016456915396034666,
+      "loss": 2.1049,
+      "step": 863
+    },
+    {
+      "epoch": 0.49740932642487046,
+      "grad_norm": 4.092164993286133,
+      "learning_rate": 0.0001643872138006082,
+      "loss": 1.8893,
+      "step": 864
+    },
+    {
+      "epoch": 0.49798503166378816,
+      "grad_norm": 3.0131890773773193,
+      "learning_rate": 0.00016420492284301917,
+      "loss": 1.9821,
+      "step": 865
+    },
+    {
+      "epoch": 0.4985607369027058,
+      "grad_norm": 10.343781471252441,
+      "learning_rate": 0.00016402228226335735,
+      "loss": 2.1446,
+      "step": 866
+    },
+    {
+      "epoch": 0.4991364421416235,
+      "grad_norm": 4.245277404785156,
+      "learning_rate": 0.00016383929323965555,
+      "loss": 2.072,
+      "step": 867
+    },
+    {
+      "epoch": 0.49971214738054115,
+      "grad_norm": 11.761308670043945,
+      "learning_rate": 0.0001636559569521941,
+      "loss": 1.3602,
+      "step": 868
+    },
+    {
+      "epoch": 0.5002878526194589,
+      "grad_norm": 9.922039985656738,
+      "learning_rate": 0.00016347227458349302,
+      "loss": 1.7432,
+      "step": 869
+    },
+    {
+      "epoch": 0.5002878526194589,
+      "eval_loss": 1.1380085945129395,
+      "eval_runtime": 1021.271,
+      "eval_samples_per_second": 2.51,
+      "eval_steps_per_second": 2.51,
+      "step": 869
+    },
+    {
+      "epoch": 0.5008635578583766,
+      "grad_norm": 16.10755157470703,
+      "learning_rate": 0.00016328824731830482,
+      "loss": 1.9049,
+      "step": 870
+    },
+    {
+      "epoch": 0.5014392630972941,
+      "grad_norm": 4.447638511657715,
+      "learning_rate": 0.00016310387634360638,
+      "loss": 1.7126,
+      "step": 871
+    },
+    {
+      "epoch": 0.5020149683362118,
+      "grad_norm": 17.62114715576172,
+      "learning_rate": 0.00016291916284859155,
+      "loss": 1.5879,
+      "step": 872
+    },
+    {
+      "epoch": 0.5025906735751295,
+      "grad_norm": 3.3077991008758545,
+      "learning_rate": 0.00016273410802466353,
+      "loss": 1.5913,
+      "step": 873
+    },
+    {
+      "epoch": 0.5031663788140472,
+      "grad_norm": 3.9533162117004395,
+      "learning_rate": 0.00016254871306542695,
+      "loss": 1.5365,
+      "step": 874
+    },
+    {
+      "epoch": 0.5037420840529648,
+      "grad_norm": 5.701480865478516,
+      "learning_rate": 0.00016236297916668045,
+      "loss": 1.5129,
+      "step": 875
+    },
+    {
+      "epoch": 0.5043177892918825,
+      "grad_norm": 12.35987377166748,
+      "learning_rate": 0.0001621769075264088,
+      "loss": 1.9525,
+      "step": 876
+    },
+    {
+      "epoch": 0.5048934945308002,
+      "grad_norm": 2.3410115242004395,
+      "learning_rate": 0.0001619904993447751,
+      "loss": 1.9946,
+      "step": 877
+    },
+    {
+      "epoch": 0.5054691997697179,
+      "grad_norm": 3.4730076789855957,
+      "learning_rate": 0.00016180375582411328,
+      "loss": 1.2603,
+      "step": 878
+    },
+    {
+      "epoch": 0.5060449050086355,
+      "grad_norm": 10.503929138183594,
+      "learning_rate": 0.00016161667816892012,
+      "loss": 1.7077,
+      "step": 879
+    },
+    {
+      "epoch": 0.5066206102475532,
+      "grad_norm": 7.053747177124023,
+      "learning_rate": 0.00016142926758584767,
+      "loss": 1.5856,
+      "step": 880
+    },
+    {
+      "epoch": 0.5071963154864709,
+      "grad_norm": 4.179106712341309,
+      "learning_rate": 0.00016124152528369519,
+      "loss": 1.6933,
+      "step": 881
+    },
+    {
+      "epoch": 0.5077720207253886,
+      "grad_norm": 2.949862241744995,
+      "learning_rate": 0.00016105345247340171,
+      "loss": 2.1307,
+      "step": 882
+    },
+    {
+      "epoch": 0.5083477259643063,
+      "grad_norm": 2.3588945865631104,
+      "learning_rate": 0.000160865050368038,
+      "loss": 2.2399,
+      "step": 883
+    },
+    {
+      "epoch": 0.5089234312032239,
+      "grad_norm": 3.3859925270080566,
+      "learning_rate": 0.00016067632018279865,
+      "loss": 1.9435,
+      "step": 884
+    },
+    {
+      "epoch": 0.5094991364421416,
+      "grad_norm": 3.3930764198303223,
+      "learning_rate": 0.00016048726313499457,
+      "loss": 1.9658,
+      "step": 885
+    },
+    {
+      "epoch": 0.5100748416810593,
+      "grad_norm": 3.163694381713867,
+      "learning_rate": 0.00016029788044404477,
+      "loss": 2.0123,
+      "step": 886
+    },
+    {
+      "epoch": 0.510650546919977,
+      "grad_norm": 2.4561283588409424,
+      "learning_rate": 0.00016010817333146876,
+      "loss": 1.8384,
+      "step": 887
+    },
+    {
+      "epoch": 0.5112262521588946,
+      "grad_norm": 3.2786359786987305,
+      "learning_rate": 0.00015991814302087853,
+      "loss": 1.54,
+      "step": 888
+    },
+    {
+      "epoch": 0.5118019573978123,
+      "grad_norm": 9.279755592346191,
+      "learning_rate": 0.0001597277907379707,
+      "loss": 1.3626,
+      "step": 889
+    },
+    {
+      "epoch": 0.51237766263673,
+      "grad_norm": 1.9229642152786255,
+      "learning_rate": 0.0001595371177105186,
+      "loss": 2.2197,
+      "step": 890
+    },
+    {
+      "epoch": 0.5129533678756477,
+      "grad_norm": 2.7186543941497803,
+      "learning_rate": 0.00015934612516836446,
+      "loss": 1.9476,
+      "step": 891
+    },
+    {
+      "epoch": 0.5135290731145653,
+      "grad_norm": 2.1631014347076416,
+      "learning_rate": 0.00015915481434341123,
+      "loss": 1.7848,
+      "step": 892
+    },
+    {
+      "epoch": 0.514104778353483,
+      "grad_norm": 11.677098274230957,
+      "learning_rate": 0.0001589631864696149,
+      "loss": 1.8612,
+      "step": 893
+    },
+    {
+      "epoch": 0.5146804835924007,
+      "grad_norm": 3.0613834857940674,
+      "learning_rate": 0.00015877124278297636,
+      "loss": 1.6289,
+      "step": 894
+    },
+    {
+      "epoch": 0.5152561888313184,
+      "grad_norm": 2.7426950931549072,
+      "learning_rate": 0.00015857898452153354,
+      "loss": 2.2257,
+      "step": 895
+    },
+    {
+      "epoch": 0.515831894070236,
+      "grad_norm": 3.3551688194274902,
+      "learning_rate": 0.00015838641292535339,
+      "loss": 1.9517,
+      "step": 896
+    },
+    {
+      "epoch": 0.5164075993091537,
+      "grad_norm": 9.800053596496582,
+      "learning_rate": 0.0001581935292365238,
+      "loss": 1.6841,
+      "step": 897
+    },
+    {
+      "epoch": 0.5169833045480714,
+      "grad_norm": 2.620741844177246,
+      "learning_rate": 0.00015800033469914572,
+      "loss": 1.9933,
+      "step": 898
+    },
+    {
+      "epoch": 0.5175590097869891,
+      "grad_norm": 8.128425598144531,
+      "learning_rate": 0.00015780683055932504,
+      "loss": 1.9019,
+      "step": 899
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 2.946974754333496,
+      "learning_rate": 0.00015761301806516468,
+      "loss": 1.7235,
+      "step": 900
+    },
+    {
+      "epoch": 0.5187104202648244,
+      "grad_norm": 10.84506607055664,
+      "learning_rate": 0.00015741889846675625,
+      "loss": 1.6609,
+      "step": 901
+    },
+    {
+      "epoch": 0.5192861255037421,
+      "grad_norm": 4.477931499481201,
+      "learning_rate": 0.00015722447301617237,
+      "loss": 2.0412,
+      "step": 902
+    },
+    {
+      "epoch": 0.5198618307426598,
+      "grad_norm": 13.774998664855957,
+      "learning_rate": 0.00015702974296745843,
+      "loss": 1.5644,
+      "step": 903
+    },
+    {
+      "epoch": 0.5204375359815774,
+      "grad_norm": 4.497225284576416,
+      "learning_rate": 0.00015683470957662425,
+      "loss": 1.7644,
+      "step": 904
+    },
+    {
+      "epoch": 0.5210132412204951,
+      "grad_norm": 3.543210983276367,
+      "learning_rate": 0.00015663937410163644,
+      "loss": 1.6813,
+      "step": 905
+    },
+    {
+      "epoch": 0.5215889464594128,
+      "grad_norm": 4.446226119995117,
+      "learning_rate": 0.00015644373780240994,
+      "loss": 1.5355,
+      "step": 906
+    },
+    {
+      "epoch": 0.5221646516983305,
+      "grad_norm": 2.871023416519165,
+      "learning_rate": 0.00015624780194080004,
+      "loss": 1.8574,
+      "step": 907
+    },
+    {
+      "epoch": 0.5227403569372481,
+      "grad_norm": 3.543043851852417,
+      "learning_rate": 0.00015605156778059426,
+      "loss": 1.6743,
+      "step": 908
+    },
+    {
+      "epoch": 0.5233160621761658,
+      "grad_norm": 3.302360773086548,
+      "learning_rate": 0.00015585503658750399,
+      "loss": 2.004,
+      "step": 909
+    },
+    {
+      "epoch": 0.5238917674150835,
+      "grad_norm": 3.226323127746582,
+      "learning_rate": 0.00015565820962915668,
+      "loss": 1.8727,
+      "step": 910
+    },
+    {
+      "epoch": 0.5244674726540012,
+      "grad_norm": 2.56103777885437,
+      "learning_rate": 0.0001554610881750873,
+      "loss": 1.5572,
+      "step": 911
+    },
+    {
+      "epoch": 0.5250431778929189,
+      "grad_norm": 2.682222366333008,
+      "learning_rate": 0.00015526367349673044,
+      "loss": 1.8991,
+      "step": 912
+    },
+    {
+      "epoch": 0.5256188831318365,
+      "grad_norm": 2.8308794498443604,
+      "learning_rate": 0.00015506596686741192,
+      "loss": 1.895,
+      "step": 913
+    },
+    {
+      "epoch": 0.5261945883707542,
+      "grad_norm": 2.992013931274414,
+      "learning_rate": 0.0001548679695623407,
+      "loss": 1.7397,
+      "step": 914
+    },
+    {
+      "epoch": 0.5267702936096719,
+      "grad_norm": 3.145866870880127,
+      "learning_rate": 0.00015466968285860055,
+      "loss": 1.7754,
+      "step": 915
+    },
+    {
+      "epoch": 0.5273459988485896,
+      "grad_norm": 3.8366172313690186,
+      "learning_rate": 0.00015447110803514186,
+      "loss": 1.4537,
+      "step": 916
+    },
+    {
+      "epoch": 0.5279217040875072,
+      "grad_norm": 3.056429624557495,
+      "learning_rate": 0.00015427224637277348,
+      "loss": 1.9531,
+      "step": 917
+    },
+    {
+      "epoch": 0.5284974093264249,
+      "grad_norm": 23.298696517944336,
+      "learning_rate": 0.00015407309915415425,
+      "loss": 1.6287,
+      "step": 918
+    },
+    {
+      "epoch": 0.5290731145653426,
+      "grad_norm": 2.360717535018921,
+      "learning_rate": 0.0001538736676637849,
+      "loss": 2.492,
+      "step": 919
+    },
+    {
+      "epoch": 0.5296488198042603,
+      "grad_norm": 3.8945038318634033,
+      "learning_rate": 0.00015367395318799973,
+      "loss": 1.8311,
+      "step": 920
+    },
+    {
+      "epoch": 0.5302245250431779,
+      "grad_norm": 2.1640625,
+      "learning_rate": 0.00015347395701495833,
+      "loss": 1.9314,
+      "step": 921
+    },
+    {
+      "epoch": 0.5308002302820956,
+      "grad_norm": 2.0766513347625732,
+      "learning_rate": 0.00015327368043463718,
+      "loss": 2.1496,
+      "step": 922
+    },
+    {
+      "epoch": 0.5313759355210133,
+      "grad_norm": 2.49560809135437,
+      "learning_rate": 0.00015307312473882137,
+      "loss": 1.6021,
+      "step": 923
+    },
+    {
+      "epoch": 0.531951640759931,
+      "grad_norm": 3.279759645462036,
+      "learning_rate": 0.00015287229122109633,
+      "loss": 1.7603,
+      "step": 924
+    },
+    {
+      "epoch": 0.5325273459988485,
+      "grad_norm": 2.0442922115325928,
+      "learning_rate": 0.0001526711811768395,
+      "loss": 2.0437,
+      "step": 925
+    },
+    {
+      "epoch": 0.5331030512377662,
+      "grad_norm": 2.3960659503936768,
+      "learning_rate": 0.0001524697959032118,
+      "loss": 1.4901,
+      "step": 926
+    },
+    {
+      "epoch": 0.533678756476684,
+      "grad_norm": 2.597766160964966,
+      "learning_rate": 0.00015226813669914948,
+      "loss": 1.6113,
+      "step": 927
+    },
+    {
+      "epoch": 0.5342544617156016,
+      "grad_norm": 12.007303237915039,
+      "learning_rate": 0.00015206620486535552,
+      "loss": 1.6338,
+      "step": 928
+    },
+    {
+      "epoch": 0.5348301669545192,
+      "grad_norm": 2.297700881958008,
+      "learning_rate": 0.0001518640017042915,
+      "loss": 1.5866,
+      "step": 929
+    },
+    {
+      "epoch": 0.5354058721934369,
+      "grad_norm": 4.744719505310059,
+      "learning_rate": 0.00015166152852016902,
+      "loss": 2.1694,
+      "step": 930
+    },
+    {
+      "epoch": 0.5359815774323546,
+      "grad_norm": 2.273824453353882,
+      "learning_rate": 0.00015145878661894125,
+      "loss": 1.9095,
+      "step": 931
+    },
+    {
+      "epoch": 0.5365572826712723,
+      "grad_norm": 3.70763897895813,
+      "learning_rate": 0.00015125577730829473,
+      "loss": 1.7984,
+      "step": 932
+    },
+    {
+      "epoch": 0.5371329879101899,
+      "grad_norm": 4.088851451873779,
+      "learning_rate": 0.00015105250189764063,
+      "loss": 1.8663,
+      "step": 933
+    },
+    {
+      "epoch": 0.5377086931491076,
+      "grad_norm": 1.9229241609573364,
+      "learning_rate": 0.0001508489616981066,
+      "loss": 2.0268,
+      "step": 934
+    },
+    {
+      "epoch": 0.5382843983880253,
+      "grad_norm": 6.149089336395264,
+      "learning_rate": 0.00015064515802252817,
+      "loss": 1.5163,
+      "step": 935
+    },
+    {
+      "epoch": 0.538860103626943,
+      "grad_norm": 3.5841498374938965,
+      "learning_rate": 0.00015044109218544015,
+      "loss": 1.6879,
+      "step": 936
+    },
+    {
+      "epoch": 0.5394358088658607,
+      "grad_norm": 5.613948345184326,
+      "learning_rate": 0.00015023676550306848,
+      "loss": 1.4269,
+      "step": 937
+    },
+    {
+      "epoch": 0.5400115141047783,
+      "grad_norm": 5.511398792266846,
+      "learning_rate": 0.00015003217929332143,
+      "loss": 1.5413,
+      "step": 938
+    },
+    {
+      "epoch": 0.540587219343696,
+      "grad_norm": 5.14990758895874,
+      "learning_rate": 0.00014982733487578127,
+      "loss": 1.6226,
+      "step": 939
+    },
+    {
+      "epoch": 0.5411629245826137,
+      "grad_norm": 2.902458667755127,
+      "learning_rate": 0.0001496222335716957,
+      "loss": 1.6545,
+      "step": 940
+    },
+    {
+      "epoch": 0.5417386298215314,
+      "grad_norm": 4.643445014953613,
+      "learning_rate": 0.00014941687670396938,
+      "loss": 2.0121,
+      "step": 941
+    },
+    {
+      "epoch": 0.542314335060449,
+      "grad_norm": 3.1277265548706055,
+      "learning_rate": 0.00014921126559715528,
+      "loss": 1.6763,
+      "step": 942
+    },
+    {
+      "epoch": 0.5428900402993667,
+      "grad_norm": 1.9732697010040283,
+      "learning_rate": 0.00014900540157744625,
+      "loss": 1.8311,
+      "step": 943
+    },
+    {
+      "epoch": 0.5434657455382844,
+      "grad_norm": 7.364120006561279,
+      "learning_rate": 0.00014879928597266644,
+      "loss": 1.3101,
+      "step": 944
+    },
+    {
+      "epoch": 0.5440414507772021,
+      "grad_norm": 4.716955661773682,
+      "learning_rate": 0.0001485929201122628,
+      "loss": 1.8418,
+      "step": 945
+    },
+    {
+      "epoch": 0.5446171560161197,
+      "grad_norm": 2.276949167251587,
+      "learning_rate": 0.0001483863053272962,
+      "loss": 1.8196,
+      "step": 946
+    },
+    {
+      "epoch": 0.5451928612550374,
+      "grad_norm": 2.367461681365967,
+      "learning_rate": 0.00014817944295043332,
+      "loss": 1.952,
+      "step": 947
+    },
+    {
+      "epoch": 0.5457685664939551,
+      "grad_norm": 8.040431022644043,
+      "learning_rate": 0.0001479723343159377,
+      "loss": 1.9765,
+      "step": 948
+    },
+    {
+      "epoch": 0.5463442717328728,
+      "grad_norm": 1.7760546207427979,
+      "learning_rate": 0.0001477649807596613,
+      "loss": 1.8163,
+      "step": 949
+    },
+    {
+      "epoch": 0.5469199769717904,
+      "grad_norm": 6.472499370574951,
+      "learning_rate": 0.00014755738361903566,
+      "loss": 1.9802,
+      "step": 950
+    },
+    {
+      "epoch": 0.5474956822107081,
+      "grad_norm": 16.233253479003906,
+      "learning_rate": 0.00014734954423306371,
+      "loss": 1.8819,
+      "step": 951
+    },
+    {
+      "epoch": 0.5480713874496258,
+      "grad_norm": 2.759955644607544,
+      "learning_rate": 0.00014714146394231061,
+      "loss": 1.849,
+      "step": 952
+    },
+    {
+      "epoch": 0.5486470926885435,
+      "grad_norm": 2.3619799613952637,
+      "learning_rate": 0.00014693314408889554,
+      "loss": 1.9287,
+      "step": 953
+    },
+    {
+      "epoch": 0.5492227979274611,
+      "grad_norm": 7.854180335998535,
+      "learning_rate": 0.00014672458601648272,
+      "loss": 1.6121,
+      "step": 954
+    },
+    {
+      "epoch": 0.5497985031663788,
+      "grad_norm": 3.9259274005889893,
+      "learning_rate": 0.000146515791070273,
+      "loss": 1.4874,
+      "step": 955
+    },
+    {
+      "epoch": 0.5503742084052965,
+      "grad_norm": 3.472259521484375,
+      "learning_rate": 0.000146306760596995,
+      "loss": 1.7002,
+      "step": 956
+    },
+    {
+      "epoch": 0.5509499136442142,
+      "grad_norm": 9.12783145904541,
+      "learning_rate": 0.0001460974959448965,
+      "loss": 1.668,
+      "step": 957
+    },
+    {
+      "epoch": 0.5515256188831318,
+      "grad_norm": 3.1406407356262207,
+      "learning_rate": 0.00014588799846373574,
+      "loss": 1.6456,
+      "step": 958
+    },
+    {
+      "epoch": 0.5521013241220495,
+      "grad_norm": 2.9766335487365723,
+      "learning_rate": 0.00014567826950477277,
+      "loss": 1.5559,
+      "step": 959
+    },
+    {
+      "epoch": 0.5526770293609672,
+      "grad_norm": 3.6111319065093994,
+      "learning_rate": 0.00014546831042076052,
+      "loss": 1.7752,
+      "step": 960
+    },
+    {
+      "epoch": 0.5532527345998849,
+      "grad_norm": 4.001034259796143,
+      "learning_rate": 0.00014525812256593637,
+      "loss": 1.9761,
+      "step": 961
+    },
+    {
+      "epoch": 0.5538284398388025,
+      "grad_norm": 3.3448774814605713,
+      "learning_rate": 0.00014504770729601327,
+      "loss": 1.7559,
+      "step": 962
+    },
+    {
+      "epoch": 0.5544041450777202,
+      "grad_norm": 4.9256157875061035,
+      "learning_rate": 0.0001448370659681709,
+      "loss": 1.3841,
+      "step": 963
+    },
+    {
+      "epoch": 0.5549798503166379,
+      "grad_norm": 2.9494550228118896,
+      "learning_rate": 0.00014462619994104706,
+      "loss": 2.1265,
+      "step": 964
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 4.05312967300415,
+      "learning_rate": 0.00014441511057472893,
+      "loss": 1.3376,
+      "step": 965
+    },
+    {
+      "epoch": 0.5561312607944733,
+      "grad_norm": 4.632201194763184,
+      "learning_rate": 0.0001442037992307441,
+      "loss": 1.7425,
+      "step": 966
+    },
+    {
+      "epoch": 0.5567069660333909,
+      "grad_norm": 2.694762706756592,
+      "learning_rate": 0.00014399226727205205,
+      "loss": 2.0141,
+      "step": 967
+    },
+    {
+      "epoch": 0.5572826712723086,
+      "grad_norm": 2.672029495239258,
+      "learning_rate": 0.00014378051606303512,
+      "loss": 1.7991,
+      "step": 968
+    },
+    {
+      "epoch": 0.5578583765112263,
+      "grad_norm": 4.377752304077148,
+      "learning_rate": 0.00014356854696948986,
+      "loss": 1.5728,
+      "step": 969
+    },
+    {
+      "epoch": 0.558434081750144,
+      "grad_norm": 2.543248414993286,
+      "learning_rate": 0.00014335636135861824,
+      "loss": 2.063,
+      "step": 970
+    },
+    {
+      "epoch": 0.5590097869890616,
+      "grad_norm": 2.466642141342163,
+      "learning_rate": 0.00014314396059901863,
+      "loss": 1.7082,
+      "step": 971
+    },
+    {
+      "epoch": 0.5595854922279793,
+      "grad_norm": 4.953126430511475,
+      "learning_rate": 0.00014293134606067722,
+      "loss": 1.5022,
+      "step": 972
+    },
+    {
+      "epoch": 0.560161197466897,
+      "grad_norm": 5.41407585144043,
+      "learning_rate": 0.000142718519114959,
+      "loss": 1.7407,
+      "step": 973
+    },
+    {
+      "epoch": 0.5607369027058147,
+      "grad_norm": 2.768073797225952,
+      "learning_rate": 0.00014250548113459909,
+      "loss": 1.8574,
+      "step": 974
+    },
+    {
+      "epoch": 0.5613126079447323,
+      "grad_norm": 2.6404266357421875,
+      "learning_rate": 0.00014229223349369373,
+      "loss": 1.5253,
+      "step": 975
+    },
+    {
+      "epoch": 0.56188831318365,
+      "grad_norm": 2.4457454681396484,
+      "learning_rate": 0.00014207877756769138,
+      "loss": 1.9335,
+      "step": 976
+    },
+    {
+      "epoch": 0.5624640184225677,
+      "grad_norm": 12.25162410736084,
+      "learning_rate": 0.0001418651147333841,
+      "loss": 1.5656,
+      "step": 977
+    },
+    {
+      "epoch": 0.5630397236614854,
+      "grad_norm": 2.4453790187835693,
+      "learning_rate": 0.00014165124636889836,
+      "loss": 1.6927,
+      "step": 978
+    },
+    {
+      "epoch": 0.563615428900403,
+      "grad_norm": 2.6654469966888428,
+      "learning_rate": 0.0001414371738536865,
+      "loss": 1.5248,
+      "step": 979
+    },
+    {
+      "epoch": 0.5641911341393206,
+      "grad_norm": 2.3234498500823975,
+      "learning_rate": 0.00014122289856851735,
+      "loss": 1.7526,
+      "step": 980
+    },
+    {
+      "epoch": 0.5647668393782384,
+      "grad_norm": 2.1236610412597656,
+      "learning_rate": 0.0001410084218954679,
+      "loss": 1.81,
+      "step": 981
+    },
+    {
+      "epoch": 0.565342544617156,
+      "grad_norm": 2.213833808898926,
+      "learning_rate": 0.00014079374521791389,
+      "loss": 1.825,
+      "step": 982
+    },
+    {
+      "epoch": 0.5659182498560736,
+      "grad_norm": 5.118985176086426,
+      "learning_rate": 0.00014057886992052115,
+      "loss": 1.7381,
+      "step": 983
+    },
+    {
+      "epoch": 0.5664939550949913,
+      "grad_norm": 26.596086502075195,
+      "learning_rate": 0.00014036379738923668,
+      "loss": 1.4509,
+      "step": 984
+    },
+    {
+      "epoch": 0.567069660333909,
+      "grad_norm": 2.0581257343292236,
+      "learning_rate": 0.00014014852901127954,
+      "loss": 1.8644,
+      "step": 985
+    },
+    {
+      "epoch": 0.5676453655728267,
+      "grad_norm": 2.2645015716552734,
+      "learning_rate": 0.00013993306617513204,
+      "loss": 1.7144,
+      "step": 986
+    },
+    {
+      "epoch": 0.5682210708117443,
+      "grad_norm": 2.477935791015625,
+      "learning_rate": 0.00013971741027053071,
+      "loss": 1.6473,
+      "step": 987
+    },
+    {
+      "epoch": 0.568796776050662,
+      "grad_norm": 3.0278351306915283,
+      "learning_rate": 0.00013950156268845748,
+      "loss": 1.9054,
+      "step": 988
+    },
+    {
+      "epoch": 0.5693724812895797,
+      "grad_norm": 3.1719486713409424,
+      "learning_rate": 0.00013928552482113054,
+      "loss": 1.8626,
+      "step": 989
+    },
+    {
+      "epoch": 0.5699481865284974,
+      "grad_norm": 2.6236214637756348,
+      "learning_rate": 0.0001390692980619953,
+      "loss": 1.7584,
+      "step": 990
+    },
+    {
+      "epoch": 0.5705238917674151,
+      "grad_norm": 2.0949866771698,
+      "learning_rate": 0.00013885288380571575,
+      "loss": 1.8523,
+      "step": 991
+    },
+    {
+      "epoch": 0.5710995970063327,
+      "grad_norm": 3.192641496658325,
+      "learning_rate": 0.00013863628344816506,
+      "loss": 1.8358,
+      "step": 992
+    },
+    {
+      "epoch": 0.5716753022452504,
+      "grad_norm": 2.1230075359344482,
+      "learning_rate": 0.00013841949838641683,
+      "loss": 1.6974,
+      "step": 993
+    },
+    {
+      "epoch": 0.5722510074841681,
+      "grad_norm": 2.634091854095459,
+      "learning_rate": 0.00013820253001873602,
+      "loss": 1.8269,
+      "step": 994
+    },
+    {
+      "epoch": 0.5728267127230858,
+      "grad_norm": 2.884781837463379,
+      "learning_rate": 0.00013798537974456983,
+      "loss": 1.3469,
+      "step": 995
+    },
+    {
+      "epoch": 0.5734024179620034,
+      "grad_norm": 2.4384100437164307,
+      "learning_rate": 0.0001377680489645389,
+      "loss": 1.5845,
+      "step": 996
+    },
+    {
+      "epoch": 0.5739781232009211,
+      "grad_norm": 2.9231410026550293,
+      "learning_rate": 0.00013755053908042793,
+      "loss": 1.7073,
+      "step": 997
+    },
+    {
+      "epoch": 0.5745538284398388,
+      "grad_norm": 3.0704684257507324,
+      "learning_rate": 0.000137332851495177,
+      "loss": 1.4623,
+      "step": 998
+    },
+    {
+      "epoch": 0.5751295336787565,
+      "grad_norm": 2.402618885040283,
+      "learning_rate": 0.0001371149876128724,
+      "loss": 2.1455,
+      "step": 999
+    },
+    {
+      "epoch": 0.5757052389176741,
+      "grad_norm": 2.723708152770996,
+      "learning_rate": 0.00013689694883873733,
+      "loss": 1.5748,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5762809441565918,
+      "grad_norm": 1.9962085485458374,
+      "learning_rate": 0.00013667873657912332,
+      "loss": 1.9438,
+      "step": 1001
+    },
+    {
+      "epoch": 0.5768566493955095,
+      "grad_norm": 5.691616058349609,
+      "learning_rate": 0.0001364603522415006,
+      "loss": 2.3176,
+      "step": 1002
+    },
+    {
+      "epoch": 0.5774323546344272,
+      "grad_norm": 2.1746699810028076,
+      "learning_rate": 0.00013624179723444952,
+      "loss": 1.8675,
+      "step": 1003
+    },
+    {
+      "epoch": 0.5780080598733448,
+      "grad_norm": 4.523983478546143,
+      "learning_rate": 0.00013602307296765108,
+      "loss": 1.5397,
+      "step": 1004
+    },
+    {
+      "epoch": 0.5785837651122625,
+      "grad_norm": 29.249481201171875,
+      "learning_rate": 0.0001358041808518782,
+      "loss": 1.7436,
+      "step": 1005
+    },
+    {
+      "epoch": 0.5791594703511802,
+      "grad_norm": 2.0091192722320557,
+      "learning_rate": 0.00013558512229898628,
+      "loss": 1.9335,
+      "step": 1006
+    },
+    {
+      "epoch": 0.5797351755900979,
+      "grad_norm": 2.7708356380462646,
+      "learning_rate": 0.00013536589872190425,
+      "loss": 1.7912,
+      "step": 1007
+    },
+    {
+      "epoch": 0.5803108808290155,
+      "grad_norm": 2.417196273803711,
+      "learning_rate": 0.00013514651153462555,
+      "loss": 1.8221,
+      "step": 1008
+    },
+    {
+      "epoch": 0.5808865860679332,
+      "grad_norm": 2.3912861347198486,
+      "learning_rate": 0.00013492696215219874,
+      "loss": 1.526,
+      "step": 1009
+    },
+    {
+      "epoch": 0.5814622913068509,
+      "grad_norm": 1.8041644096374512,
+      "learning_rate": 0.00013470725199071868,
+      "loss": 1.5973,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5820379965457686,
+      "grad_norm": 3.6920905113220215,
+      "learning_rate": 0.00013448738246731723,
+      "loss": 1.8089,
+      "step": 1011
+    },
+    {
+      "epoch": 0.5826137017846862,
+      "grad_norm": 1.7696315050125122,
+      "learning_rate": 0.00013426735500015412,
+      "loss": 1.8036,
+      "step": 1012
+    },
+    {
+      "epoch": 0.5831894070236039,
+      "grad_norm": 2.644516706466675,
+      "learning_rate": 0.00013404717100840775,
+      "loss": 1.7614,
+      "step": 1013
+    },
+    {
+      "epoch": 0.5837651122625216,
+      "grad_norm": 6.610838413238525,
+      "learning_rate": 0.00013382683191226626,
+      "loss": 1.8272,
+      "step": 1014
+    },
+    {
+      "epoch": 0.5843408175014393,
+      "grad_norm": 25.5416202545166,
+      "learning_rate": 0.00013360633913291805,
+      "loss": 1.5991,
+      "step": 1015
+    },
+    {
+      "epoch": 0.584916522740357,
+      "grad_norm": 6.063877105712891,
+      "learning_rate": 0.00013338569409254285,
+      "loss": 1.9859,
+      "step": 1016
+    },
+    {
+      "epoch": 0.5854922279792746,
+      "grad_norm": 10.058717727661133,
+      "learning_rate": 0.00013316489821430257,
+      "loss": 1.5081,
+      "step": 1017
+    },
+    {
+      "epoch": 0.5860679332181923,
+      "grad_norm": 3.7417914867401123,
+      "learning_rate": 0.00013294395292233179,
+      "loss": 1.4591,
+      "step": 1018
+    },
+    {
+      "epoch": 0.58664363845711,
+      "grad_norm": 2.1001293659210205,
+      "learning_rate": 0.00013272285964172905,
+      "loss": 1.4471,
+      "step": 1019
+    },
+    {
+      "epoch": 0.5872193436960277,
+      "grad_norm": 4.2659454345703125,
+      "learning_rate": 0.00013250161979854727,
+      "loss": 1.6232,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5877950489349453,
+      "grad_norm": 3.3600850105285645,
+      "learning_rate": 0.00013228023481978477,
+      "loss": 2.0188,
+      "step": 1021
+    },
+    {
+      "epoch": 0.588370754173863,
+      "grad_norm": 4.816986560821533,
+      "learning_rate": 0.00013205870613337598,
+      "loss": 1.883,
+      "step": 1022
+    },
+    {
+      "epoch": 0.5889464594127807,
+      "grad_norm": 7.538907527923584,
+      "learning_rate": 0.00013183703516818221,
+      "loss": 1.6426,
+      "step": 1023
+    },
+    {
+      "epoch": 0.5895221646516984,
+      "grad_norm": 3.869892120361328,
+      "learning_rate": 0.00013161522335398252,
+      "loss": 1.5805,
+      "step": 1024
+    },
+    {
+      "epoch": 0.590097869890616,
+      "grad_norm": 2.9215962886810303,
+      "learning_rate": 0.00013139327212146438,
+      "loss": 2.0736,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5906735751295337,
+      "grad_norm": 3.044528007507324,
+      "learning_rate": 0.0001311711829022146,
+      "loss": 1.773,
+      "step": 1026
+    },
+    {
+      "epoch": 0.5912492803684514,
+      "grad_norm": 2.4565680027008057,
+      "learning_rate": 0.00013094895712870993,
+      "loss": 1.8526,
+      "step": 1027
+    },
+    {
+      "epoch": 0.5918249856073691,
+      "grad_norm": 2.8523366451263428,
+      "learning_rate": 0.00013072659623430797,
+      "loss": 1.6659,
+      "step": 1028
+    },
+    {
+      "epoch": 0.5924006908462867,
+      "grad_norm": 3.7679712772369385,
+      "learning_rate": 0.0001305041016532377,
+      "loss": 1.6689,
+      "step": 1029
+    },
+    {
+      "epoch": 0.5929763960852044,
+      "grad_norm": 2.0870449542999268,
+      "learning_rate": 0.0001302814748205906,
+      "loss": 1.955,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5935521013241221,
+      "grad_norm": 4.419449329376221,
+      "learning_rate": 0.000130058717172311,
+      "loss": 2.0321,
+      "step": 1031
+    },
+    {
+      "epoch": 0.5941278065630398,
+      "grad_norm": 3.5084879398345947,
+      "learning_rate": 0.00012983583014518704,
+      "loss": 1.8397,
+      "step": 1032
+    },
+    {
+      "epoch": 0.5947035118019574,
+      "grad_norm": 5.1162943840026855,
+      "learning_rate": 0.00012961281517684137,
+      "loss": 1.3311,
+      "step": 1033
+    },
+    {
+      "epoch": 0.595279217040875,
+      "grad_norm": 3.4573514461517334,
+      "learning_rate": 0.00012938967370572187,
+      "loss": 1.7966,
+      "step": 1034
+    },
+    {
+      "epoch": 0.5958549222797928,
+      "grad_norm": 3.372185468673706,
+      "learning_rate": 0.00012916640717109234,
+      "loss": 1.8347,
+      "step": 1035
+    },
+    {
+      "epoch": 0.5964306275187105,
+      "grad_norm": 5.885191440582275,
+      "learning_rate": 0.00012894301701302325,
+      "loss": 1.5451,
+      "step": 1036
+    },
+    {
+      "epoch": 0.597006332757628,
+      "grad_norm": 3.0024893283843994,
+      "learning_rate": 0.00012871950467238243,
+      "loss": 1.614,
+      "step": 1037
+    },
+    {
+      "epoch": 0.5975820379965457,
+      "grad_norm": 3.6248486042022705,
+      "learning_rate": 0.0001284958715908258,
+      "loss": 1.9764,
+      "step": 1038
+    },
+    {
+      "epoch": 0.5981577432354634,
+      "grad_norm": 2.173245668411255,
+      "learning_rate": 0.00012827211921078807,
+      "loss": 2.005,
+      "step": 1039
+    },
+    {
+      "epoch": 0.5987334484743811,
+      "grad_norm": 3.430807590484619,
+      "learning_rate": 0.00012804824897547342,
+      "loss": 1.4051,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5993091537132987,
+      "grad_norm": 2.929710865020752,
+      "learning_rate": 0.00012782426232884616,
+      "loss": 1.6919,
+      "step": 1041
+    },
+    {
+      "epoch": 0.5998848589522164,
+      "grad_norm": 10.41037654876709,
+      "learning_rate": 0.00012760016071562154,
+      "loss": 1.6745,
+      "step": 1042
+    },
+    {
+      "epoch": 0.6004605641911341,
+      "grad_norm": 2.4413540363311768,
+      "learning_rate": 0.00012737594558125622,
+      "loss": 1.7962,
+      "step": 1043
+    },
+    {
+      "epoch": 0.6010362694300518,
+      "grad_norm": 1.9357279539108276,
+      "learning_rate": 0.00012715161837193917,
+      "loss": 1.7911,
+      "step": 1044
+    },
+    {
+      "epoch": 0.6016119746689695,
+      "grad_norm": 1.77413010597229,
+      "learning_rate": 0.00012692718053458228,
+      "loss": 2.0216,
+      "step": 1045
+    },
+    {
+      "epoch": 0.6021876799078871,
+      "grad_norm": 2.166997194290161,
+      "learning_rate": 0.0001267026335168108,
+      "loss": 1.512,
+      "step": 1046
+    },
+    {
+      "epoch": 0.6027633851468048,
+      "grad_norm": 2.3894009590148926,
+      "learning_rate": 0.00012647797876695442,
+      "loss": 1.6451,
+      "step": 1047
+    },
+    {
+      "epoch": 0.6033390903857225,
+      "grad_norm": 1.9920623302459717,
+      "learning_rate": 0.00012625321773403759,
+      "loss": 1.8585,
+      "step": 1048
+    },
+    {
+      "epoch": 0.6039147956246402,
+      "grad_norm": 7.759680271148682,
+      "learning_rate": 0.00012602835186777028,
+      "loss": 1.4727,
+      "step": 1049
+    },
+    {
+      "epoch": 0.6044905008635578,
+      "grad_norm": 2.342421531677246,
+      "learning_rate": 0.00012580338261853867,
+      "loss": 1.8267,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6050662061024755,
+      "grad_norm": 3.670834541320801,
+      "learning_rate": 0.00012557831143739573,
+      "loss": 1.5525,
+      "step": 1051
+    },
+    {
+      "epoch": 0.6056419113413932,
+      "grad_norm": 2.409895181655884,
+      "learning_rate": 0.00012535313977605193,
+      "loss": 1.7907,
+      "step": 1052
+    },
+    {
+      "epoch": 0.6062176165803109,
+      "grad_norm": 46.487396240234375,
+      "learning_rate": 0.0001251278690868658,
+      "loss": 1.6402,
+      "step": 1053
+    },
+    {
+      "epoch": 0.6067933218192285,
+      "grad_norm": 2.1283092498779297,
+      "learning_rate": 0.00012490250082283462,
+      "loss": 1.8462,
+      "step": 1054
+    },
+    {
+      "epoch": 0.6073690270581462,
+      "grad_norm": 2.77925705909729,
+      "learning_rate": 0.00012467703643758506,
+      "loss": 1.7877,
+      "step": 1055
+    },
+    {
+      "epoch": 0.6079447322970639,
+      "grad_norm": 2.246321439743042,
+      "learning_rate": 0.00012445147738536367,
+      "loss": 2.0602,
+      "step": 1056
+    },
+    {
+      "epoch": 0.6085204375359816,
+      "grad_norm": 10.697153091430664,
+      "learning_rate": 0.00012422582512102776,
+      "loss": 1.5962,
+      "step": 1057
+    },
+    {
+      "epoch": 0.6090961427748992,
+      "grad_norm": 2.082714557647705,
+      "learning_rate": 0.00012400008110003568,
+      "loss": 1.1343,
+      "step": 1058
+    },
+    {
+      "epoch": 0.6096718480138169,
+      "grad_norm": 3.4832651615142822,
+      "learning_rate": 0.00012377424677843777,
+      "loss": 1.7796,
+      "step": 1059
+    },
+    {
+      "epoch": 0.6102475532527346,
+      "grad_norm": 2.243643045425415,
+      "learning_rate": 0.0001235483236128667,
+      "loss": 1.6396,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6108232584916523,
+      "grad_norm": 5.907801151275635,
+      "learning_rate": 0.0001233223130605282,
+      "loss": 1.7067,
+      "step": 1061
+    },
+    {
+      "epoch": 0.6113989637305699,
+      "grad_norm": 1.8457263708114624,
+      "learning_rate": 0.0001230962165791917,
+      "loss": 1.8954,
+      "step": 1062
+    },
+    {
+      "epoch": 0.6119746689694876,
+      "grad_norm": 2.2211413383483887,
+      "learning_rate": 0.00012287003562718083,
+      "loss": 1.6708,
+      "step": 1063
+    },
+    {
+      "epoch": 0.6125503742084053,
+      "grad_norm": 2.75714373588562,
+      "learning_rate": 0.00012264377166336412,
+      "loss": 1.8238,
+      "step": 1064
+    },
+    {
+      "epoch": 0.613126079447323,
+      "grad_norm": 2.9811720848083496,
+      "learning_rate": 0.00012241742614714542,
+      "loss": 1.7964,
+      "step": 1065
+    },
+    {
+      "epoch": 0.6137017846862406,
+      "grad_norm": 1.753533959388733,
+      "learning_rate": 0.00012219100053845465,
+      "loss": 2.1655,
+      "step": 1066
+    },
+    {
+      "epoch": 0.6142774899251583,
+      "grad_norm": 3.2706820964813232,
+      "learning_rate": 0.00012196449629773837,
+      "loss": 1.9122,
+      "step": 1067
+    },
+    {
+      "epoch": 0.614853195164076,
+      "grad_norm": 3.0341358184814453,
+      "learning_rate": 0.00012173791488595019,
+      "loss": 1.3391,
+      "step": 1068
+    },
+    {
+      "epoch": 0.6154289004029937,
+      "grad_norm": 6.340384006500244,
+      "learning_rate": 0.00012151125776454161,
+      "loss": 1.898,
+      "step": 1069
+    },
+    {
+      "epoch": 0.6160046056419114,
+      "grad_norm": 2.7424800395965576,
+      "learning_rate": 0.00012128452639545243,
+      "loss": 1.7949,
+      "step": 1070
+    },
+    {
+      "epoch": 0.616580310880829,
+      "grad_norm": 4.640672206878662,
+      "learning_rate": 0.00012105772224110125,
+      "loss": 1.7932,
+      "step": 1071
+    },
+    {
+      "epoch": 0.6171560161197467,
+      "grad_norm": 15.990649223327637,
+      "learning_rate": 0.00012083084676437626,
+      "loss": 1.7652,
+      "step": 1072
+    },
+    {
+      "epoch": 0.6177317213586644,
+      "grad_norm": 2.783991575241089,
+      "learning_rate": 0.00012060390142862562,
+      "loss": 1.6402,
+      "step": 1073
+    },
+    {
+      "epoch": 0.6183074265975821,
+      "grad_norm": 2.2968053817749023,
+      "learning_rate": 0.00012037688769764803,
+      "loss": 1.9988,
+      "step": 1074
+    },
+    {
+      "epoch": 0.6188831318364997,
+      "grad_norm": 2.0364556312561035,
+      "learning_rate": 0.0001201498070356835,
+      "loss": 2.2376,
+      "step": 1075
+    },
+    {
+      "epoch": 0.6194588370754174,
+      "grad_norm": 2.1875343322753906,
+      "learning_rate": 0.00011992266090740356,
+      "loss": 2.0095,
+      "step": 1076
+    },
+    {
+      "epoch": 0.6200345423143351,
+      "grad_norm": 2.150895118713379,
+      "learning_rate": 0.00011969545077790212,
+      "loss": 1.84,
+      "step": 1077
+    },
+    {
+      "epoch": 0.6206102475532528,
+      "grad_norm": 1.9572124481201172,
+      "learning_rate": 0.00011946817811268583,
+      "loss": 1.8961,
+      "step": 1078
+    },
+    {
+      "epoch": 0.6211859527921704,
+      "grad_norm": 2.214392900466919,
+      "learning_rate": 0.00011924084437766474,
+      "loss": 2.1148,
+      "step": 1079
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 3.1197032928466797,
+      "learning_rate": 0.00011901345103914278,
+      "loss": 1.8522,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6223373632700058,
+      "grad_norm": 2.3327748775482178,
+      "learning_rate": 0.00011878599956380833,
+      "loss": 1.3488,
+      "step": 1081
+    },
+    {
+      "epoch": 0.6229130685089235,
+      "grad_norm": 4.232432842254639,
+      "learning_rate": 0.00011855849141872478,
+      "loss": 1.3803,
+      "step": 1082
+    },
+    {
+      "epoch": 0.6234887737478411,
+      "grad_norm": 2.6493353843688965,
+      "learning_rate": 0.00011833092807132094,
+      "loss": 1.6068,
+      "step": 1083
+    },
+    {
+      "epoch": 0.6240644789867588,
+      "grad_norm": 4.1762495040893555,
+      "learning_rate": 0.00011810331098938183,
+      "loss": 1.8435,
+      "step": 1084
+    },
+    {
+      "epoch": 0.6246401842256765,
+      "grad_norm": 1.8596819639205933,
+      "learning_rate": 0.0001178756416410389,
+      "loss": 1.6533,
+      "step": 1085
+    },
+    {
+      "epoch": 0.6252158894645942,
+      "grad_norm": 3.031169891357422,
+      "learning_rate": 0.00011764792149476082,
+      "loss": 2.0339,
+      "step": 1086
+    },
+    {
+      "epoch": 0.6257915947035118,
+      "grad_norm": 2.637482166290283,
+      "learning_rate": 0.00011742015201934391,
+      "loss": 1.6899,
+      "step": 1087
+    },
+    {
+      "epoch": 0.6263672999424295,
+      "grad_norm": 2.928927421569824,
+      "learning_rate": 0.0001171923346839026,
+      "loss": 1.5966,
+      "step": 1088
+    },
+    {
+      "epoch": 0.6269430051813472,
+      "grad_norm": 1.9385987520217896,
+      "learning_rate": 0.00011696447095786005,
+      "loss": 1.7942,
+      "step": 1089
+    },
+    {
+      "epoch": 0.6275187104202649,
+      "grad_norm": 2.5360302925109863,
+      "learning_rate": 0.00011673656231093866,
+      "loss": 1.8061,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6280944156591824,
+      "grad_norm": 3.7727694511413574,
+      "learning_rate": 0.00011650861021315053,
+      "loss": 1.6725,
+      "step": 1091
+    },
+    {
+      "epoch": 0.6286701208981001,
+      "grad_norm": 2.319878101348877,
+      "learning_rate": 0.00011628061613478805,
+      "loss": 1.8349,
+      "step": 1092
+    },
+    {
+      "epoch": 0.6292458261370178,
+      "grad_norm": 2.03865385055542,
+      "learning_rate": 0.00011605258154641436,
+      "loss": 2.0155,
+      "step": 1093
+    },
+    {
+      "epoch": 0.6298215313759356,
+      "grad_norm": 8.286460876464844,
+      "learning_rate": 0.00011582450791885396,
+      "loss": 1.4949,
+      "step": 1094
+    },
+    {
+      "epoch": 0.6303972366148531,
+      "grad_norm": 3.0670244693756104,
+      "learning_rate": 0.00011559639672318301,
+      "loss": 1.5505,
+      "step": 1095
+    },
+    {
+      "epoch": 0.6309729418537708,
+      "grad_norm": 3.125257730484009,
+      "learning_rate": 0.00011536824943072013,
+      "loss": 1.8383,
+      "step": 1096
+    },
+    {
+      "epoch": 0.6315486470926885,
+      "grad_norm": 12.684760093688965,
+      "learning_rate": 0.00011514006751301665,
+      "loss": 1.6088,
+      "step": 1097
+    },
+    {
+      "epoch": 0.6321243523316062,
+      "grad_norm": 2.321836471557617,
+      "learning_rate": 0.00011491185244184737,
+      "loss": 1.3411,
+      "step": 1098
+    },
+    {
+      "epoch": 0.6327000575705239,
+      "grad_norm": 2.899108409881592,
+      "learning_rate": 0.00011468360568920075,
+      "loss": 1.6938,
+      "step": 1099
+    },
+    {
+      "epoch": 0.6332757628094415,
+      "grad_norm": 2.300163745880127,
+      "learning_rate": 0.00011445532872726978,
+      "loss": 1.9663,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6338514680483592,
+      "grad_norm": 2.8410146236419678,
+      "learning_rate": 0.00011422702302844217,
+      "loss": 1.411,
+      "step": 1101
+    },
+    {
+      "epoch": 0.6344271732872769,
+      "grad_norm": 2.567687749862671,
+      "learning_rate": 0.00011399869006529104,
+      "loss": 1.4076,
+      "step": 1102
+    },
+    {
+      "epoch": 0.6350028785261946,
+      "grad_norm": 2.7900848388671875,
+      "learning_rate": 0.00011377033131056536,
+      "loss": 1.927,
+      "step": 1103
+    },
+    {
+      "epoch": 0.6355785837651122,
+      "grad_norm": 4.51284646987915,
+      "learning_rate": 0.00011354194823718046,
+      "loss": 1.9738,
+      "step": 1104
+    },
+    {
+      "epoch": 0.6361542890040299,
+      "grad_norm": 2.4686641693115234,
+      "learning_rate": 0.00011331354231820844,
+      "loss": 1.8788,
+      "step": 1105
+    },
+    {
+      "epoch": 0.6367299942429476,
+      "grad_norm": 4.021846294403076,
+      "learning_rate": 0.00011308511502686887,
+      "loss": 1.6456,
+      "step": 1106
+    },
+    {
+      "epoch": 0.6373056994818653,
+      "grad_norm": 2.271044969558716,
+      "learning_rate": 0.00011285666783651918,
+      "loss": 1.8461,
+      "step": 1107
+    },
+    {
+      "epoch": 0.6378814047207829,
+      "grad_norm": 2.7978787422180176,
+      "learning_rate": 0.00011262820222064503,
+      "loss": 1.6951,
+      "step": 1108
+    },
+    {
+      "epoch": 0.6384571099597006,
+      "grad_norm": 2.1274783611297607,
+      "learning_rate": 0.00011239971965285103,
+      "loss": 1.579,
+      "step": 1109
+    },
+    {
+      "epoch": 0.6390328151986183,
+      "grad_norm": 2.2610461711883545,
+      "learning_rate": 0.00011217122160685107,
+      "loss": 1.7816,
+      "step": 1110
+    },
+    {
+      "epoch": 0.639608520437536,
+      "grad_norm": 3.3982491493225098,
+      "learning_rate": 0.00011194270955645894,
+      "loss": 1.645,
+      "step": 1111
+    },
+    {
+      "epoch": 0.6401842256764536,
+      "grad_norm": 2.5890631675720215,
+      "learning_rate": 0.00011171418497557866,
+      "loss": 1.8953,
+      "step": 1112
+    },
+    {
+      "epoch": 0.6407599309153713,
+      "grad_norm": 2.629909038543701,
+      "learning_rate": 0.00011148564933819515,
+      "loss": 1.3796,
+      "step": 1113
+    },
+    {
+      "epoch": 0.641335636154289,
+      "grad_norm": 8.610105514526367,
+      "learning_rate": 0.00011125710411836463,
+      "loss": 1.6267,
+      "step": 1114
+    },
+    {
+      "epoch": 0.6419113413932067,
+      "grad_norm": 1.8409522771835327,
+      "learning_rate": 0.0001110285507902051,
+      "loss": 1.5968,
+      "step": 1115
+    },
+    {
+      "epoch": 0.6424870466321243,
+      "grad_norm": 9.315035820007324,
+      "learning_rate": 0.00011079999082788695,
+      "loss": 1.6575,
+      "step": 1116
+    },
+    {
+      "epoch": 0.643062751871042,
+      "grad_norm": 1.8414576053619385,
+      "learning_rate": 0.00011057142570562317,
+      "loss": 1.9512,
+      "step": 1117
+    },
+    {
+      "epoch": 0.6436384571099597,
+      "grad_norm": 3.665769577026367,
+      "learning_rate": 0.00011034285689766025,
+      "loss": 1.6937,
+      "step": 1118
+    },
+    {
+      "epoch": 0.6442141623488774,
+      "grad_norm": 4.7261738777160645,
+      "learning_rate": 0.00011011428587826829,
+      "loss": 1.1675,
+      "step": 1119
+    },
+    {
+      "epoch": 0.644789867587795,
+      "grad_norm": 1.9036201238632202,
+      "learning_rate": 0.00010988571412173174,
+      "loss": 1.7549,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6453655728267127,
+      "grad_norm": 3.041926145553589,
+      "learning_rate": 0.00010965714310233979,
+      "loss": 1.6196,
+      "step": 1121
+    },
+    {
+      "epoch": 0.6459412780656304,
+      "grad_norm": 2.1135053634643555,
+      "learning_rate": 0.00010942857429437688,
+      "loss": 2.0311,
+      "step": 1122
+    },
+    {
+      "epoch": 0.6465169833045481,
+      "grad_norm": 2.664389133453369,
+      "learning_rate": 0.0001092000091721131,
+      "loss": 1.3273,
+      "step": 1123
+    },
+    {
+      "epoch": 0.6470926885434658,
+      "grad_norm": 1.9533644914627075,
+      "learning_rate": 0.00010897144920979492,
+      "loss": 2.0707,
+      "step": 1124
+    },
+    {
+      "epoch": 0.6476683937823834,
+      "grad_norm": 3.114617109298706,
+      "learning_rate": 0.00010874289588163538,
+      "loss": 1.9657,
+      "step": 1125
+    },
+    {
+      "epoch": 0.6482440990213011,
+      "grad_norm": 2.789735794067383,
+      "learning_rate": 0.00010851435066180486,
+      "loss": 1.7617,
+      "step": 1126
+    },
+    {
+      "epoch": 0.6488198042602188,
+      "grad_norm": 3.554517984390259,
+      "learning_rate": 0.00010828581502442139,
+      "loss": 1.7084,
+      "step": 1127
+    },
+    {
+      "epoch": 0.6493955094991365,
+      "grad_norm": 2.6153769493103027,
+      "learning_rate": 0.00010805729044354111,
+      "loss": 1.9482,
+      "step": 1128
+    },
+    {
+      "epoch": 0.6499712147380541,
+      "grad_norm": 3.099222183227539,
+      "learning_rate": 0.00010782877839314895,
+      "loss": 2.0045,
+      "step": 1129
+    },
+    {
+      "epoch": 0.6505469199769718,
+      "grad_norm": 3.3257076740264893,
+      "learning_rate": 0.00010760028034714899,
+      "loss": 1.7569,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6511226252158895,
+      "grad_norm": 11.2058744430542,
+      "learning_rate": 0.000107371797779355,
+      "loss": 1.4291,
+      "step": 1131
+    },
+    {
+      "epoch": 0.6516983304548072,
+      "grad_norm": 1.9433313608169556,
+      "learning_rate": 0.00010714333216348087,
+      "loss": 1.7501,
+      "step": 1132
+    },
+    {
+      "epoch": 0.6522740356937248,
+      "grad_norm": 6.8387651443481445,
+      "learning_rate": 0.00010691488497313115,
+      "loss": 1.8655,
+      "step": 1133
+    },
+    {
+      "epoch": 0.6528497409326425,
+      "grad_norm": 14.710614204406738,
+      "learning_rate": 0.0001066864576817916,
+      "loss": 1.6142,
+      "step": 1134
+    },
+    {
+      "epoch": 0.6534254461715602,
+      "grad_norm": 2.8211591243743896,
+      "learning_rate": 0.0001064580517628196,
+      "loss": 1.9977,
+      "step": 1135
+    },
+    {
+      "epoch": 0.6540011514104779,
+      "grad_norm": 10.522199630737305,
+      "learning_rate": 0.00010622966868943466,
+      "loss": 1.4866,
+      "step": 1136
+    },
+    {
+      "epoch": 0.6545768566493955,
+      "grad_norm": 18.36501121520996,
+      "learning_rate": 0.000106001309934709,
+      "loss": 1.9982,
+      "step": 1137
+    },
+    {
+      "epoch": 0.6551525618883132,
+      "grad_norm": 7.4732866287231445,
+      "learning_rate": 0.00010577297697155786,
+      "loss": 1.6959,
+      "step": 1138
+    },
+    {
+      "epoch": 0.6557282671272309,
+      "grad_norm": 4.5649094581604,
+      "learning_rate": 0.00010554467127273025,
+      "loss": 1.4753,
+      "step": 1139
+    },
+    {
+      "epoch": 0.6563039723661486,
+      "grad_norm": 2.2757229804992676,
+      "learning_rate": 0.00010531639431079927,
+      "loss": 1.8967,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6568796776050662,
+      "grad_norm": 3.5460915565490723,
+      "learning_rate": 0.00010508814755815266,
+      "loss": 1.445,
+      "step": 1141
+    },
+    {
+      "epoch": 0.6574553828439839,
+      "grad_norm": 5.268508434295654,
+      "learning_rate": 0.00010485993248698337,
+      "loss": 1.6088,
+      "step": 1142
+    },
+    {
+      "epoch": 0.6580310880829016,
+      "grad_norm": 4.5665388107299805,
+      "learning_rate": 0.00010463175056927991,
+      "loss": 1.5503,
+      "step": 1143
+    },
+    {
+      "epoch": 0.6586067933218193,
+      "grad_norm": 4.9753546714782715,
+      "learning_rate": 0.00010440360327681702,
+      "loss": 2.015,
+      "step": 1144
+    },
+    {
+      "epoch": 0.6591824985607369,
+      "grad_norm": 4.048013210296631,
+      "learning_rate": 0.00010417549208114608,
+      "loss": 1.8249,
+      "step": 1145
+    },
+    {
+      "epoch": 0.6597582037996546,
+      "grad_norm": 1.9025744199752808,
+      "learning_rate": 0.00010394741845358564,
+      "loss": 1.9516,
+      "step": 1146
+    },
+    {
+      "epoch": 0.6603339090385723,
+      "grad_norm": 3.0757157802581787,
+      "learning_rate": 0.00010371938386521196,
+      "loss": 1.8365,
+      "step": 1147
+    },
+    {
+      "epoch": 0.66090961427749,
+      "grad_norm": 4.190611362457275,
+      "learning_rate": 0.00010349138978684949,
+      "loss": 1.725,
+      "step": 1148
+    },
+    {
+      "epoch": 0.6614853195164075,
+      "grad_norm": 3.264749765396118,
+      "learning_rate": 0.00010326343768906138,
+      "loss": 1.4593,
+      "step": 1149
+    },
+    {
+      "epoch": 0.6620610247553252,
+      "grad_norm": 2.502470016479492,
+      "learning_rate": 0.00010303552904213998,
+      "loss": 1.6255,
+      "step": 1150
+    },
+    {
+      "epoch": 0.662636729994243,
+      "grad_norm": 2.5127601623535156,
+      "learning_rate": 0.0001028076653160974,
+      "loss": 1.8302,
+      "step": 1151
+    },
+    {
+      "epoch": 0.6632124352331606,
+      "grad_norm": 1.9711816310882568,
+      "learning_rate": 0.00010257984798065615,
+      "loss": 1.6349,
+      "step": 1152
+    },
+    {
+      "epoch": 0.6637881404720783,
+      "grad_norm": 2.5800209045410156,
+      "learning_rate": 0.00010235207850523923,
+      "loss": 1.8541,
+      "step": 1153
+    },
+    {
+      "epoch": 0.6643638457109959,
+      "grad_norm": 2.15277361869812,
+      "learning_rate": 0.00010212435835896113,
+      "loss": 2.0093,
+      "step": 1154
+    },
+    {
+      "epoch": 0.6649395509499136,
+      "grad_norm": 2.074312925338745,
+      "learning_rate": 0.0001018966890106182,
+      "loss": 1.5909,
+      "step": 1155
+    },
+    {
+      "epoch": 0.6655152561888313,
+      "grad_norm": 1.9219588041305542,
+      "learning_rate": 0.00010166907192867907,
+      "loss": 1.816,
+      "step": 1156
+    },
+    {
+      "epoch": 0.666090961427749,
+      "grad_norm": 11.162732124328613,
+      "learning_rate": 0.00010144150858127529,
+      "loss": 1.359,
+      "step": 1157
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.046509265899658,
+      "learning_rate": 0.00010121400043619169,
+      "loss": 1.8493,
+      "step": 1158
+    },
+    {
+      "epoch": 0.6672423719055843,
+      "grad_norm": 2.8525936603546143,
+      "learning_rate": 0.00010098654896085724,
+      "loss": 1.7511,
+      "step": 1159
+    },
+    {
+      "epoch": 0.667818077144502,
+      "grad_norm": 2.0714986324310303,
+      "learning_rate": 0.00010075915562233529,
+      "loss": 2.1803,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6683937823834197,
+      "grad_norm": 2.4236810207366943,
+      "learning_rate": 0.00010053182188731418,
+      "loss": 1.9524,
+      "step": 1161
+    },
+    {
+      "epoch": 0.6689694876223373,
+      "grad_norm": 2.0779378414154053,
+      "learning_rate": 0.00010030454922209792,
+      "loss": 1.4239,
+      "step": 1162
+    },
+    {
+      "epoch": 0.669545192861255,
+      "grad_norm": 2.2357749938964844,
+      "learning_rate": 0.00010007733909259646,
+      "loss": 1.946,
+      "step": 1163
+    },
+    {
+      "epoch": 0.6701208981001727,
+      "grad_norm": 3.204003095626831,
+      "learning_rate": 9.985019296431652e-05,
+      "loss": 1.5353,
+      "step": 1164
+    },
+    {
+      "epoch": 0.6706966033390904,
+      "grad_norm": 6.192695140838623,
+      "learning_rate": 9.962311230235195e-05,
+      "loss": 1.7483,
+      "step": 1165
+    },
+    {
+      "epoch": 0.671272308578008,
+      "grad_norm": 1.6048142910003662,
+      "learning_rate": 9.939609857137439e-05,
+      "loss": 1.919,
+      "step": 1166
+    },
+    {
+      "epoch": 0.6718480138169257,
+      "grad_norm": 1.7395859956741333,
+      "learning_rate": 9.916915323562377e-05,
+      "loss": 1.8967,
+      "step": 1167
+    },
+    {
+      "epoch": 0.6724237190558434,
+      "grad_norm": 9.254240989685059,
+      "learning_rate": 9.894227775889877e-05,
+      "loss": 1.468,
+      "step": 1168
+    },
+    {
+      "epoch": 0.6729994242947611,
+      "grad_norm": 2.008310079574585,
+      "learning_rate": 9.871547360454761e-05,
+      "loss": 2.1097,
+      "step": 1169
+    },
+    {
+      "epoch": 0.6735751295336787,
+      "grad_norm": 5.330569267272949,
+      "learning_rate": 9.848874223545838e-05,
+      "loss": 1.5188,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6741508347725964,
+      "grad_norm": 2.926645040512085,
+      "learning_rate": 9.826208511404979e-05,
+      "loss": 1.8197,
+      "step": 1171
+    },
+    {
+      "epoch": 0.6747265400115141,
+      "grad_norm": 2.621838331222534,
+      "learning_rate": 9.803550370226168e-05,
+      "loss": 1.8151,
+      "step": 1172
+    },
+    {
+      "epoch": 0.6753022452504318,
+      "grad_norm": 3.4823410511016846,
+      "learning_rate": 9.780899946154535e-05,
+      "loss": 1.5427,
+      "step": 1173
+    },
+    {
+      "epoch": 0.6758779504893494,
+      "grad_norm": 4.249687671661377,
+      "learning_rate": 9.758257385285459e-05,
+      "loss": 1.6277,
+      "step": 1174
+    },
+    {
+      "epoch": 0.6764536557282671,
+      "grad_norm": 3.4192488193511963,
+      "learning_rate": 9.735622833663589e-05,
+      "loss": 1.958,
+      "step": 1175
+    },
+    {
+      "epoch": 0.6770293609671848,
+      "grad_norm": 2.2742438316345215,
+      "learning_rate": 9.712996437281919e-05,
+      "loss": 1.9273,
+      "step": 1176
+    },
+    {
+      "epoch": 0.6776050662061025,
+      "grad_norm": 2.9063401222229004,
+      "learning_rate": 9.690378342080832e-05,
+      "loss": 1.3239,
+      "step": 1177
+    },
+    {
+      "epoch": 0.6781807714450202,
+      "grad_norm": 7.125305652618408,
+      "learning_rate": 9.667768693947184e-05,
+      "loss": 1.3987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.6787564766839378,
+      "grad_norm": 2.73252010345459,
+      "learning_rate": 9.645167638713334e-05,
+      "loss": 1.7407,
+      "step": 1179
+    },
+    {
+      "epoch": 0.6793321819228555,
+      "grad_norm": 2.822937250137329,
+      "learning_rate": 9.622575322156226e-05,
+      "loss": 2.0836,
+      "step": 1180
+    },
+    {
+      "epoch": 0.6799078871617732,
+      "grad_norm": 1.957633376121521,
+      "learning_rate": 9.599991889996435e-05,
+      "loss": 1.8197,
+      "step": 1181
+    },
+    {
+      "epoch": 0.6804835924006909,
+      "grad_norm": 3.0812935829162598,
+      "learning_rate": 9.577417487897227e-05,
+      "loss": 1.8606,
+      "step": 1182
+    },
+    {
+      "epoch": 0.6810592976396085,
+      "grad_norm": 2.941861152648926,
+      "learning_rate": 9.554852261463634e-05,
+      "loss": 2.1113,
+      "step": 1183
+    },
+    {
+      "epoch": 0.6816350028785262,
+      "grad_norm": 2.8906712532043457,
+      "learning_rate": 9.532296356241496e-05,
+      "loss": 1.6709,
+      "step": 1184
+    },
+    {
+      "epoch": 0.6822107081174439,
+      "grad_norm": 9.170804977416992,
+      "learning_rate": 9.509749917716537e-05,
+      "loss": 1.6481,
+      "step": 1185
+    },
+    {
+      "epoch": 0.6827864133563616,
+      "grad_norm": 6.398213863372803,
+      "learning_rate": 9.487213091313422e-05,
+      "loss": 1.6377,
+      "step": 1186
+    },
+    {
+      "epoch": 0.6833621185952792,
+      "grad_norm": 2.3572301864624023,
+      "learning_rate": 9.46468602239481e-05,
+      "loss": 1.4058,
+      "step": 1187
+    },
+    {
+      "epoch": 0.6839378238341969,
+      "grad_norm": 2.4743688106536865,
+      "learning_rate": 9.44216885626043e-05,
+      "loss": 1.6128,
+      "step": 1188
+    },
+    {
+      "epoch": 0.6845135290731146,
+      "grad_norm": 2.0609121322631836,
+      "learning_rate": 9.419661738146137e-05,
+      "loss": 2.064,
+      "step": 1189
+    },
+    {
+      "epoch": 0.6850892343120323,
+      "grad_norm": 2.409160614013672,
+      "learning_rate": 9.397164813222974e-05,
+      "loss": 1.4584,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6856649395509499,
+      "grad_norm": 18.25377655029297,
+      "learning_rate": 9.374678226596245e-05,
+      "loss": 1.8134,
+      "step": 1191
+    },
+    {
+      "epoch": 0.6862406447898676,
+      "grad_norm": 2.806365489959717,
+      "learning_rate": 9.352202123304561e-05,
+      "loss": 1.5046,
+      "step": 1192
+    },
+    {
+      "epoch": 0.6868163500287853,
+      "grad_norm": 1.8805674314498901,
+      "learning_rate": 9.329736648318921e-05,
+      "loss": 1.8979,
+      "step": 1193
+    },
+    {
+      "epoch": 0.687392055267703,
+      "grad_norm": 3.183284282684326,
+      "learning_rate": 9.307281946541774e-05,
+      "loss": 2.0024,
+      "step": 1194
+    },
+    {
+      "epoch": 0.6879677605066206,
+      "grad_norm": 4.2624006271362305,
+      "learning_rate": 9.284838162806082e-05,
+      "loss": 1.5019,
+      "step": 1195
+    },
+    {
+      "epoch": 0.6885434657455383,
+      "grad_norm": 3.5346248149871826,
+      "learning_rate": 9.262405441874382e-05,
+      "loss": 1.3593,
+      "step": 1196
+    },
+    {
+      "epoch": 0.689119170984456,
+      "grad_norm": 1.8233470916748047,
+      "learning_rate": 9.23998392843785e-05,
+      "loss": 2.3358,
+      "step": 1197
+    },
+    {
+      "epoch": 0.6896948762233737,
+      "grad_norm": 3.124511480331421,
+      "learning_rate": 9.217573767115383e-05,
+      "loss": 1.4681,
+      "step": 1198
+    },
+    {
+      "epoch": 0.6902705814622913,
+      "grad_norm": 2.2693393230438232,
+      "learning_rate": 9.195175102452657e-05,
+      "loss": 1.6685,
+      "step": 1199
+    },
+    {
+      "epoch": 0.690846286701209,
+      "grad_norm": 2.4168596267700195,
+      "learning_rate": 9.172788078921191e-05,
+      "loss": 2.1741,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6914219919401267,
+      "grad_norm": 2.8741111755371094,
+      "learning_rate": 9.150412840917421e-05,
+      "loss": 1.8631,
+      "step": 1201
+    },
+    {
+      "epoch": 0.6919976971790444,
+      "grad_norm": 2.5383141040802,
+      "learning_rate": 9.128049532761759e-05,
+      "loss": 1.5728,
+      "step": 1202
+    },
+    {
+      "epoch": 0.6925734024179621,
+      "grad_norm": 2.7610490322113037,
+      "learning_rate": 9.105698298697676e-05,
+      "loss": 1.7652,
+      "step": 1203
+    },
+    {
+      "epoch": 0.6931491076568796,
+      "grad_norm": 7.25991678237915,
+      "learning_rate": 9.083359282890767e-05,
+      "loss": 1.4954,
+      "step": 1204
+    },
+    {
+      "epoch": 0.6937248128957973,
+      "grad_norm": 3.7028870582580566,
+      "learning_rate": 9.061032629427812e-05,
+      "loss": 1.5809,
+      "step": 1205
+    },
+    {
+      "epoch": 0.694300518134715,
+      "grad_norm": 2.123594284057617,
+      "learning_rate": 9.038718482315866e-05,
+      "loss": 1.9145,
+      "step": 1206
+    },
+    {
+      "epoch": 0.6948762233736328,
+      "grad_norm": 5.9489827156066895,
+      "learning_rate": 9.0164169854813e-05,
+      "loss": 1.6488,
+      "step": 1207
+    },
+    {
+      "epoch": 0.6954519286125503,
+      "grad_norm": 2.7276246547698975,
+      "learning_rate": 8.994128282768903e-05,
+      "loss": 1.3695,
+      "step": 1208
+    },
+    {
+      "epoch": 0.696027633851468,
+      "grad_norm": 4.6926116943359375,
+      "learning_rate": 8.971852517940941e-05,
+      "loss": 1.751,
+      "step": 1209
+    },
+    {
+      "epoch": 0.6966033390903857,
+      "grad_norm": 8.851062774658203,
+      "learning_rate": 8.949589834676229e-05,
+      "loss": 1.8289,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6971790443293034,
+      "grad_norm": 2.5200765132904053,
+      "learning_rate": 8.927340376569209e-05,
+      "loss": 1.6664,
+      "step": 1211
+    },
+    {
+      "epoch": 0.697754749568221,
+      "grad_norm": 2.227609157562256,
+      "learning_rate": 8.90510428712901e-05,
+      "loss": 1.7865,
+      "step": 1212
+    },
+    {
+      "epoch": 0.6983304548071387,
+      "grad_norm": 2.7458364963531494,
+      "learning_rate": 8.882881709778541e-05,
+      "loss": 1.8385,
+      "step": 1213
+    },
+    {
+      "epoch": 0.6989061600460564,
+      "grad_norm": 3.33707594871521,
+      "learning_rate": 8.860672787853563e-05,
+      "loss": 1.2672,
+      "step": 1214
+    },
+    {
+      "epoch": 0.6994818652849741,
+      "grad_norm": 1.9355860948562622,
+      "learning_rate": 8.838477664601752e-05,
+      "loss": 1.7449,
+      "step": 1215
+    },
+    {
+      "epoch": 0.7000575705238917,
+      "grad_norm": 2.399412155151367,
+      "learning_rate": 8.816296483181783e-05,
+      "loss": 1.8579,
+      "step": 1216
+    },
+    {
+      "epoch": 0.7006332757628094,
+      "grad_norm": 2.3706471920013428,
+      "learning_rate": 8.794129386662405e-05,
+      "loss": 1.9366,
+      "step": 1217
+    },
+    {
+      "epoch": 0.7012089810017271,
+      "grad_norm": 7.656529903411865,
+      "learning_rate": 8.771976518021523e-05,
+      "loss": 1.7295,
+      "step": 1218
+    },
+    {
+      "epoch": 0.7017846862406448,
+      "grad_norm": 1.9502934217453003,
+      "learning_rate": 8.749838020145275e-05,
+      "loss": 1.8921,
+      "step": 1219
+    },
+    {
+      "epoch": 0.7023603914795624,
+      "grad_norm": 2.2740495204925537,
+      "learning_rate": 8.727714035827097e-05,
+      "loss": 1.5383,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7029360967184801,
+      "grad_norm": 1.800449252128601,
+      "learning_rate": 8.705604707766824e-05,
+      "loss": 1.7226,
+      "step": 1221
+    },
+    {
+      "epoch": 0.7035118019573978,
+      "grad_norm": 3.378472089767456,
+      "learning_rate": 8.683510178569747e-05,
+      "loss": 1.774,
+      "step": 1222
+    },
+    {
+      "epoch": 0.7040875071963155,
+      "grad_norm": 9.736815452575684,
+      "learning_rate": 8.661430590745716e-05,
+      "loss": 1.5152,
+      "step": 1223
+    },
+    {
+      "epoch": 0.7046632124352331,
+      "grad_norm": 2.5010931491851807,
+      "learning_rate": 8.639366086708198e-05,
+      "loss": 2.0701,
+      "step": 1224
+    },
+    {
+      "epoch": 0.7052389176741508,
+      "grad_norm": 4.483166694641113,
+      "learning_rate": 8.617316808773377e-05,
+      "loss": 1.7541,
+      "step": 1225
+    },
+    {
+      "epoch": 0.7058146229130685,
+      "grad_norm": 2.1824142932891846,
+      "learning_rate": 8.595282899159224e-05,
+      "loss": 1.9888,
+      "step": 1226
+    },
+    {
+      "epoch": 0.7063903281519862,
+      "grad_norm": 2.690760612487793,
+      "learning_rate": 8.573264499984592e-05,
+      "loss": 1.4562,
+      "step": 1227
+    },
+    {
+      "epoch": 0.7069660333909038,
+      "grad_norm": 2.433600425720215,
+      "learning_rate": 8.551261753268278e-05,
+      "loss": 1.7995,
+      "step": 1228
+    },
+    {
+      "epoch": 0.7075417386298215,
+      "grad_norm": 2.5094082355499268,
+      "learning_rate": 8.529274800928133e-05,
+      "loss": 1.9741,
+      "step": 1229
+    },
+    {
+      "epoch": 0.7081174438687392,
+      "grad_norm": 3.7042555809020996,
+      "learning_rate": 8.507303784780131e-05,
+      "loss": 1.9219,
+      "step": 1230
+    },
+    {
+      "epoch": 0.7086931491076569,
+      "grad_norm": 9.36429214477539,
+      "learning_rate": 8.485348846537454e-05,
+      "loss": 1.4939,
+      "step": 1231
+    },
+    {
+      "epoch": 0.7092688543465746,
+      "grad_norm": 15.673849105834961,
+      "learning_rate": 8.463410127809576e-05,
+      "loss": 1.6711,
+      "step": 1232
+    },
+    {
+      "epoch": 0.7098445595854922,
+      "grad_norm": 4.705075740814209,
+      "learning_rate": 8.441487770101375e-05,
+      "loss": 1.7079,
+      "step": 1233
+    },
+    {
+      "epoch": 0.7104202648244099,
+      "grad_norm": 3.9517462253570557,
+      "learning_rate": 8.41958191481218e-05,
+      "loss": 1.7706,
+      "step": 1234
+    },
+    {
+      "epoch": 0.7109959700633276,
+      "grad_norm": 2.705690622329712,
+      "learning_rate": 8.397692703234894e-05,
+      "loss": 1.7043,
+      "step": 1235
+    },
+    {
+      "epoch": 0.7115716753022453,
+      "grad_norm": 3.2132418155670166,
+      "learning_rate": 8.375820276555056e-05,
+      "loss": 1.6642,
+      "step": 1236
+    },
+    {
+      "epoch": 0.7121473805411629,
+      "grad_norm": 5.179574489593506,
+      "learning_rate": 8.353964775849943e-05,
+      "loss": 1.2606,
+      "step": 1237
+    },
+    {
+      "epoch": 0.7127230857800806,
+      "grad_norm": 2.834803581237793,
+      "learning_rate": 8.332126342087672e-05,
+      "loss": 1.9747,
+      "step": 1238
+    },
+    {
+      "epoch": 0.7132987910189983,
+      "grad_norm": 4.0652995109558105,
+      "learning_rate": 8.310305116126265e-05,
+      "loss": 1.6335,
+      "step": 1239
+    },
+    {
+      "epoch": 0.713874496257916,
+      "grad_norm": 3.4388492107391357,
+      "learning_rate": 8.288501238712765e-05,
+      "loss": 1.7383,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7144502014968336,
+      "grad_norm": 2.006385326385498,
+      "learning_rate": 8.2667148504823e-05,
+      "loss": 1.6261,
+      "step": 1241
+    },
+    {
+      "epoch": 0.7150259067357513,
+      "grad_norm": 3.83569598197937,
+      "learning_rate": 8.24494609195721e-05,
+      "loss": 1.4952,
+      "step": 1242
+    },
+    {
+      "epoch": 0.715601611974669,
+      "grad_norm": 3.785851240158081,
+      "learning_rate": 8.223195103546115e-05,
+      "loss": 1.9108,
+      "step": 1243
+    },
+    {
+      "epoch": 0.7161773172135867,
+      "grad_norm": 2.0811095237731934,
+      "learning_rate": 8.201462025543017e-05,
+      "loss": 1.5987,
+      "step": 1244
+    },
+    {
+      "epoch": 0.7167530224525043,
+      "grad_norm": 3.619274139404297,
+      "learning_rate": 8.179746998126403e-05,
+      "loss": 1.9112,
+      "step": 1245
+    },
+    {
+      "epoch": 0.717328727691422,
+      "grad_norm": 2.366683006286621,
+      "learning_rate": 8.158050161358319e-05,
+      "loss": 1.8774,
+      "step": 1246
+    },
+    {
+      "epoch": 0.7179044329303397,
+      "grad_norm": 3.2668917179107666,
+      "learning_rate": 8.136371655183497e-05,
+      "loss": 1.5932,
+      "step": 1247
+    },
+    {
+      "epoch": 0.7184801381692574,
+      "grad_norm": 5.13369607925415,
+      "learning_rate": 8.114711619428428e-05,
+      "loss": 1.5434,
+      "step": 1248
+    },
+    {
+      "epoch": 0.719055843408175,
+      "grad_norm": 5.853895664215088,
+      "learning_rate": 8.09307019380047e-05,
+      "loss": 1.5837,
+      "step": 1249
+    },
+    {
+      "epoch": 0.7196315486470927,
+      "grad_norm": 2.1570184230804443,
+      "learning_rate": 8.071447517886952e-05,
+      "loss": 2.0624,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7202072538860104,
+      "grad_norm": 1.9529211521148682,
+      "learning_rate": 8.049843731154254e-05,
+      "loss": 1.7785,
+      "step": 1251
+    },
+    {
+      "epoch": 0.7207829591249281,
+      "grad_norm": 5.114016532897949,
+      "learning_rate": 8.02825897294693e-05,
+      "loss": 1.7406,
+      "step": 1252
+    },
+    {
+      "epoch": 0.7213586643638457,
+      "grad_norm": 2.745934009552002,
+      "learning_rate": 8.006693382486801e-05,
+      "loss": 1.737,
+      "step": 1253
+    },
+    {
+      "epoch": 0.7219343696027634,
+      "grad_norm": 10.330817222595215,
+      "learning_rate": 7.985147098872048e-05,
+      "loss": 1.5649,
+      "step": 1254
+    },
+    {
+      "epoch": 0.7225100748416811,
+      "grad_norm": 1.7928460836410522,
+      "learning_rate": 7.963620261076334e-05,
+      "loss": 1.8267,
+      "step": 1255
+    },
+    {
+      "epoch": 0.7230857800805988,
+      "grad_norm": 1.9616749286651611,
+      "learning_rate": 7.942113007947887e-05,
+      "loss": 1.9707,
+      "step": 1256
+    },
+    {
+      "epoch": 0.7236614853195165,
+      "grad_norm": 2.0727272033691406,
+      "learning_rate": 7.920625478208615e-05,
+      "loss": 1.8589,
+      "step": 1257
+    },
+    {
+      "epoch": 0.724237190558434,
+      "grad_norm": 3.0034399032592773,
+      "learning_rate": 7.899157810453213e-05,
+      "loss": 1.9103,
+      "step": 1258
+    },
+    {
+      "epoch": 0.7248128957973518,
+      "grad_norm": 2.041135787963867,
+      "learning_rate": 7.877710143148267e-05,
+      "loss": 1.8537,
+      "step": 1259
+    },
+    {
+      "epoch": 0.7253886010362695,
+      "grad_norm": 8.20665454864502,
+      "learning_rate": 7.856282614631356e-05,
+      "loss": 1.2161,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7259643062751872,
+      "grad_norm": 2.1425111293792725,
+      "learning_rate": 7.834875363110166e-05,
+      "loss": 1.9613,
+      "step": 1261
+    },
+    {
+      "epoch": 0.7265400115141047,
+      "grad_norm": 2.895951509475708,
+      "learning_rate": 7.813488526661595e-05,
+      "loss": 1.6368,
+      "step": 1262
+    },
+    {
+      "epoch": 0.7271157167530224,
+      "grad_norm": 1.6481860876083374,
+      "learning_rate": 7.792122243230864e-05,
+      "loss": 2.0891,
+      "step": 1263
+    },
+    {
+      "epoch": 0.7276914219919401,
+      "grad_norm": 1.5633034706115723,
+      "learning_rate": 7.770776650630631e-05,
+      "loss": 1.4721,
+      "step": 1264
+    },
+    {
+      "epoch": 0.7282671272308578,
+      "grad_norm": 2.921679735183716,
+      "learning_rate": 7.749451886540091e-05,
+      "loss": 1.2774,
+      "step": 1265
+    },
+    {
+      "epoch": 0.7288428324697754,
+      "grad_norm": 2.167282819747925,
+      "learning_rate": 7.7281480885041e-05,
+      "loss": 1.7595,
+      "step": 1266
+    },
+    {
+      "epoch": 0.7294185377086931,
+      "grad_norm": 2.5153279304504395,
+      "learning_rate": 7.706865393932283e-05,
+      "loss": 2.0746,
+      "step": 1267
+    },
+    {
+      "epoch": 0.7299942429476108,
+      "grad_norm": 1.6189182996749878,
+      "learning_rate": 7.68560394009814e-05,
+      "loss": 1.7528,
+      "step": 1268
+    },
+    {
+      "epoch": 0.7305699481865285,
+      "grad_norm": 3.0685760974884033,
+      "learning_rate": 7.664363864138178e-05,
+      "loss": 1.3272,
+      "step": 1269
+    },
+    {
+      "epoch": 0.7311456534254461,
+      "grad_norm": 1.9861022233963013,
+      "learning_rate": 7.643145303051016e-05,
+      "loss": 1.8826,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7317213586643638,
+      "grad_norm": 2.7280659675598145,
+      "learning_rate": 7.621948393696492e-05,
+      "loss": 1.9363,
+      "step": 1271
+    },
+    {
+      "epoch": 0.7322970639032815,
+      "grad_norm": 4.763440132141113,
+      "learning_rate": 7.600773272794798e-05,
+      "loss": 1.8717,
+      "step": 1272
+    },
+    {
+      "epoch": 0.7328727691421992,
+      "grad_norm": 3.8978776931762695,
+      "learning_rate": 7.57962007692559e-05,
+      "loss": 1.692,
+      "step": 1273
+    },
+    {
+      "epoch": 0.7334484743811168,
+      "grad_norm": 4.123043060302734,
+      "learning_rate": 7.558488942527109e-05,
+      "loss": 1.8497,
+      "step": 1274
+    },
+    {
+      "epoch": 0.7340241796200345,
+      "grad_norm": 2.32194185256958,
+      "learning_rate": 7.537380005895296e-05,
+      "loss": 1.7812,
+      "step": 1275
+    },
+    {
+      "epoch": 0.7345998848589522,
+      "grad_norm": 2.7786030769348145,
+      "learning_rate": 7.516293403182912e-05,
+      "loss": 1.4425,
+      "step": 1276
+    },
+    {
+      "epoch": 0.7351755900978699,
+      "grad_norm": 1.8613038063049316,
+      "learning_rate": 7.495229270398674e-05,
+      "loss": 1.9893,
+      "step": 1277
+    },
+    {
+      "epoch": 0.7357512953367875,
+      "grad_norm": 2.449399709701538,
+      "learning_rate": 7.474187743406362e-05,
+      "loss": 1.5826,
+      "step": 1278
+    },
+    {
+      "epoch": 0.7363270005757052,
+      "grad_norm": 2.0494472980499268,
+      "learning_rate": 7.453168957923949e-05,
+      "loss": 1.9416,
+      "step": 1279
+    },
+    {
+      "epoch": 0.7369027058146229,
+      "grad_norm": 1.910123348236084,
+      "learning_rate": 7.432173049522728e-05,
+      "loss": 1.5807,
+      "step": 1280
+    },
+    {
+      "epoch": 0.7374784110535406,
+      "grad_norm": 2.3191299438476562,
+      "learning_rate": 7.411200153626428e-05,
+      "loss": 2.169,
+      "step": 1281
+    },
+    {
+      "epoch": 0.7380541162924582,
+      "grad_norm": 2.6251776218414307,
+      "learning_rate": 7.390250405510352e-05,
+      "loss": 1.3672,
+      "step": 1282
+    },
+    {
+      "epoch": 0.7386298215313759,
+      "grad_norm": 3.652298927307129,
+      "learning_rate": 7.369323940300503e-05,
+      "loss": 1.7192,
+      "step": 1283
+    },
+    {
+      "epoch": 0.7392055267702936,
+      "grad_norm": 2.2988710403442383,
+      "learning_rate": 7.348420892972705e-05,
+      "loss": 2.2075,
+      "step": 1284
+    },
+    {
+      "epoch": 0.7397812320092113,
+      "grad_norm": 2.720458984375,
+      "learning_rate": 7.327541398351731e-05,
+      "loss": 1.53,
+      "step": 1285
+    },
+    {
+      "epoch": 0.740356937248129,
+      "grad_norm": 22.601173400878906,
+      "learning_rate": 7.306685591110449e-05,
+      "loss": 1.6638,
+      "step": 1286
+    },
+    {
+      "epoch": 0.7409326424870466,
+      "grad_norm": 3.0639970302581787,
+      "learning_rate": 7.28585360576894e-05,
+      "loss": 2.0271,
+      "step": 1287
+    },
+    {
+      "epoch": 0.7415083477259643,
+      "grad_norm": 3.046778678894043,
+      "learning_rate": 7.265045576693632e-05,
+      "loss": 1.6931,
+      "step": 1288
+    },
+    {
+      "epoch": 0.742084052964882,
+      "grad_norm": 4.0570969581604,
+      "learning_rate": 7.244261638096434e-05,
+      "loss": 1.5182,
+      "step": 1289
+    },
+    {
+      "epoch": 0.7426597582037997,
+      "grad_norm": 2.360447645187378,
+      "learning_rate": 7.223501924033878e-05,
+      "loss": 1.7788,
+      "step": 1290
+    },
+    {
+      "epoch": 0.7432354634427173,
+      "grad_norm": 2.19985294342041,
+      "learning_rate": 7.202766568406234e-05,
+      "loss": 1.826,
+      "step": 1291
+    },
+    {
+      "epoch": 0.743811168681635,
+      "grad_norm": 6.608851432800293,
+      "learning_rate": 7.182055704956671e-05,
+      "loss": 1.2474,
+      "step": 1292
+    },
+    {
+      "epoch": 0.7443868739205527,
+      "grad_norm": 2.359436511993408,
+      "learning_rate": 7.161369467270385e-05,
+      "loss": 1.6463,
+      "step": 1293
+    },
+    {
+      "epoch": 0.7449625791594704,
+      "grad_norm": 2.1586437225341797,
+      "learning_rate": 7.14070798877373e-05,
+      "loss": 1.8218,
+      "step": 1294
+    },
+    {
+      "epoch": 0.745538284398388,
+      "grad_norm": 3.0305073261260986,
+      "learning_rate": 7.120071402733359e-05,
+      "loss": 1.5873,
+      "step": 1295
+    },
+    {
+      "epoch": 0.7461139896373057,
+      "grad_norm": 1.7526609897613525,
+      "learning_rate": 7.09945984225538e-05,
+      "loss": 1.9706,
+      "step": 1296
+    },
+    {
+      "epoch": 0.7466896948762234,
+      "grad_norm": 3.412294387817383,
+      "learning_rate": 7.078873440284477e-05,
+      "loss": 1.8407,
+      "step": 1297
+    },
+    {
+      "epoch": 0.7472654001151411,
+      "grad_norm": 2.3854801654815674,
+      "learning_rate": 7.058312329603065e-05,
+      "loss": 1.4573,
+      "step": 1298
+    },
+    {
+      "epoch": 0.7478411053540587,
+      "grad_norm": 3.6485955715179443,
+      "learning_rate": 7.037776642830433e-05,
+      "loss": 1.6198,
+      "step": 1299
+    },
+    {
+      "epoch": 0.7484168105929764,
+      "grad_norm": 1.9419339895248413,
+      "learning_rate": 7.017266512421878e-05,
+      "loss": 1.8447,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7489925158318941,
+      "grad_norm": 2.8531014919281006,
+      "learning_rate": 6.99678207066786e-05,
+      "loss": 1.5635,
+      "step": 1301
+    },
+    {
+      "epoch": 0.7495682210708118,
+      "grad_norm": 2.279210090637207,
+      "learning_rate": 6.976323449693156e-05,
+      "loss": 1.7548,
+      "step": 1302
+    },
+    {
+      "epoch": 0.7501439263097294,
+      "grad_norm": 1.8601477146148682,
+      "learning_rate": 6.955890781455987e-05,
+      "loss": 2.1579,
+      "step": 1303
+    },
+    {
+      "epoch": 0.7507196315486471,
+      "grad_norm": 2.6298389434814453,
+      "learning_rate": 6.93548419774719e-05,
+      "loss": 1.5116,
+      "step": 1304
+    },
+    {
+      "epoch": 0.7512953367875648,
+      "grad_norm": 3.179581880569458,
+      "learning_rate": 6.915103830189342e-05,
+      "loss": 1.3385,
+      "step": 1305
+    },
+    {
+      "epoch": 0.7518710420264825,
+      "grad_norm": 51.62275695800781,
+      "learning_rate": 6.894749810235938e-05,
+      "loss": 1.4703,
+      "step": 1306
+    },
+    {
+      "epoch": 0.7524467472654001,
+      "grad_norm": 5.406750679016113,
+      "learning_rate": 6.87442226917053e-05,
+      "loss": 1.4089,
+      "step": 1307
+    },
+    {
+      "epoch": 0.7530224525043178,
+      "grad_norm": 3.1115217208862305,
+      "learning_rate": 6.854121338105875e-05,
+      "loss": 1.8881,
+      "step": 1308
+    },
+    {
+      "epoch": 0.7535981577432355,
+      "grad_norm": 11.897812843322754,
+      "learning_rate": 6.833847147983103e-05,
+      "loss": 1.3264,
+      "step": 1309
+    },
+    {
+      "epoch": 0.7541738629821532,
+      "grad_norm": 2.3330416679382324,
+      "learning_rate": 6.813599829570852e-05,
+      "loss": 1.2674,
+      "step": 1310
+    },
+    {
+      "epoch": 0.7547495682210709,
+      "grad_norm": 2.1948859691619873,
+      "learning_rate": 6.793379513464449e-05,
+      "loss": 1.7049,
+      "step": 1311
+    },
+    {
+      "epoch": 0.7553252734599885,
+      "grad_norm": 4.7169413566589355,
+      "learning_rate": 6.773186330085054e-05,
+      "loss": 1.6359,
+      "step": 1312
+    },
+    {
+      "epoch": 0.7559009786989062,
+      "grad_norm": 2.132951498031616,
+      "learning_rate": 6.753020409678819e-05,
+      "loss": 1.3256,
+      "step": 1313
+    },
+    {
+      "epoch": 0.7564766839378239,
+      "grad_norm": 2.582689046859741,
+      "learning_rate": 6.732881882316052e-05,
+      "loss": 2.0414,
+      "step": 1314
+    },
+    {
+      "epoch": 0.7570523891767416,
+      "grad_norm": 3.74625301361084,
+      "learning_rate": 6.712770877890369e-05,
+      "loss": 1.6727,
+      "step": 1315
+    },
+    {
+      "epoch": 0.7576280944156591,
+      "grad_norm": 11.082663536071777,
+      "learning_rate": 6.692687526117865e-05,
+      "loss": 1.7192,
+      "step": 1316
+    },
+    {
+      "epoch": 0.7582037996545768,
+      "grad_norm": 7.31722354888916,
+      "learning_rate": 6.672631956536286e-05,
+      "loss": 1.9284,
+      "step": 1317
+    },
+    {
+      "epoch": 0.7587795048934945,
+      "grad_norm": 2.2905490398406982,
+      "learning_rate": 6.652604298504168e-05,
+      "loss": 1.6203,
+      "step": 1318
+    },
+    {
+      "epoch": 0.7593552101324123,
+      "grad_norm": 1.9625123739242554,
+      "learning_rate": 6.63260468120003e-05,
+      "loss": 1.7967,
+      "step": 1319
+    },
+    {
+      "epoch": 0.7599309153713298,
+      "grad_norm": 4.101654529571533,
+      "learning_rate": 6.612633233621513e-05,
+      "loss": 1.6865,
+      "step": 1320
+    },
+    {
+      "epoch": 0.7605066206102475,
+      "grad_norm": 1.899525761604309,
+      "learning_rate": 6.59269008458458e-05,
+      "loss": 1.9603,
+      "step": 1321
+    },
+    {
+      "epoch": 0.7610823258491652,
+      "grad_norm": 2.649081230163574,
+      "learning_rate": 6.572775362722654e-05,
+      "loss": 1.8846,
+      "step": 1322
+    },
+    {
+      "epoch": 0.7616580310880829,
+      "grad_norm": 2.6892385482788086,
+      "learning_rate": 6.552889196485812e-05,
+      "loss": 1.7135,
+      "step": 1323
+    },
+    {
+      "epoch": 0.7622337363270005,
+      "grad_norm": 2.641362190246582,
+      "learning_rate": 6.533031714139947e-05,
+      "loss": 1.6431,
+      "step": 1324
+    },
+    {
+      "epoch": 0.7628094415659182,
+      "grad_norm": 2.4511632919311523,
+      "learning_rate": 6.513203043765932e-05,
+      "loss": 1.6093,
+      "step": 1325
+    },
+    {
+      "epoch": 0.7633851468048359,
+      "grad_norm": 2.739757537841797,
+      "learning_rate": 6.49340331325881e-05,
+      "loss": 1.576,
+      "step": 1326
+    },
+    {
+      "epoch": 0.7639608520437536,
+      "grad_norm": 3.0558271408081055,
+      "learning_rate": 6.473632650326958e-05,
+      "loss": 1.2116,
+      "step": 1327
+    },
+    {
+      "epoch": 0.7645365572826712,
+      "grad_norm": 2.0293328762054443,
+      "learning_rate": 6.453891182491272e-05,
+      "loss": 2.0026,
+      "step": 1328
+    },
+    {
+      "epoch": 0.7651122625215889,
+      "grad_norm": 2.7013015747070312,
+      "learning_rate": 6.434179037084338e-05,
+      "loss": 1.5642,
+      "step": 1329
+    },
+    {
+      "epoch": 0.7656879677605066,
+      "grad_norm": 2.754798412322998,
+      "learning_rate": 6.414496341249605e-05,
+      "loss": 1.959,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7662636729994243,
+      "grad_norm": 10.559093475341797,
+      "learning_rate": 6.394843221940578e-05,
+      "loss": 1.5451,
+      "step": 1331
+    },
+    {
+      "epoch": 0.7668393782383419,
+      "grad_norm": 2.1670234203338623,
+      "learning_rate": 6.375219805919995e-05,
+      "loss": 1.8978,
+      "step": 1332
+    },
+    {
+      "epoch": 0.7674150834772596,
+      "grad_norm": 2.215994358062744,
+      "learning_rate": 6.355626219759005e-05,
+      "loss": 1.7036,
+      "step": 1333
+    },
+    {
+      "epoch": 0.7679907887161773,
+      "grad_norm": 10.172525405883789,
+      "learning_rate": 6.336062589836359e-05,
+      "loss": 1.7827,
+      "step": 1334
+    },
+    {
+      "epoch": 0.768566493955095,
+      "grad_norm": 4.433283805847168,
+      "learning_rate": 6.316529042337577e-05,
+      "loss": 1.4581,
+      "step": 1335
+    },
+    {
+      "epoch": 0.7691421991940126,
+      "grad_norm": 2.3281450271606445,
+      "learning_rate": 6.29702570325416e-05,
+      "loss": 1.7009,
+      "step": 1336
+    },
+    {
+      "epoch": 0.7697179044329303,
+      "grad_norm": 2.0074803829193115,
+      "learning_rate": 6.277552698382761e-05,
+      "loss": 2.1468,
+      "step": 1337
+    },
+    {
+      "epoch": 0.770293609671848,
+      "grad_norm": 1.4934829473495483,
+      "learning_rate": 6.25811015332438e-05,
+      "loss": 1.456,
+      "step": 1338
+    },
+    {
+      "epoch": 0.7708693149107657,
+      "grad_norm": 5.488325595855713,
+      "learning_rate": 6.238698193483539e-05,
+      "loss": 1.2045,
+      "step": 1339
+    },
+    {
+      "epoch": 0.7714450201496834,
+      "grad_norm": 2.7806265354156494,
+      "learning_rate": 6.219316944067497e-05,
+      "loss": 1.7917,
+      "step": 1340
+    },
+    {
+      "epoch": 0.772020725388601,
+      "grad_norm": 8.058002471923828,
+      "learning_rate": 6.19996653008543e-05,
+      "loss": 1.7587,
+      "step": 1341
+    },
+    {
+      "epoch": 0.7725964306275187,
+      "grad_norm": 4.710812568664551,
+      "learning_rate": 6.180647076347621e-05,
+      "loss": 1.4779,
+      "step": 1342
+    },
+    {
+      "epoch": 0.7731721358664364,
+      "grad_norm": 13.711342811584473,
+      "learning_rate": 6.161358707464666e-05,
+      "loss": 1.5732,
+      "step": 1343
+    },
+    {
+      "epoch": 0.7737478411053541,
+      "grad_norm": 2.5771145820617676,
+      "learning_rate": 6.142101547846648e-05,
+      "loss": 1.6616,
+      "step": 1344
+    },
+    {
+      "epoch": 0.7743235463442717,
+      "grad_norm": 3.267062187194824,
+      "learning_rate": 6.122875721702365e-05,
+      "loss": 1.541,
+      "step": 1345
+    },
+    {
+      "epoch": 0.7748992515831894,
+      "grad_norm": 2.233874559402466,
+      "learning_rate": 6.103681353038511e-05,
+      "loss": 1.5368,
+      "step": 1346
+    },
+    {
+      "epoch": 0.7754749568221071,
+      "grad_norm": 2.080592632293701,
+      "learning_rate": 6.084518565658877e-05,
+      "loss": 1.8878,
+      "step": 1347
+    },
+    {
+      "epoch": 0.7760506620610248,
+      "grad_norm": 2.5689923763275146,
+      "learning_rate": 6.065387483163556e-05,
+      "loss": 1.5645,
+      "step": 1348
+    },
+    {
+      "epoch": 0.7766263672999424,
+      "grad_norm": 2.084365129470825,
+      "learning_rate": 6.04628822894814e-05,
+      "loss": 1.4915,
+      "step": 1349
+    },
+    {
+      "epoch": 0.7772020725388601,
+      "grad_norm": 4.5587382316589355,
+      "learning_rate": 6.0272209262029324e-05,
+      "loss": 1.7316,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 2.5827181339263916,
+      "learning_rate": 6.008185697912148e-05,
+      "loss": 1.8245,
+      "step": 1351
+    },
+    {
+      "epoch": 0.7783534830166955,
+      "grad_norm": 1.711262822151184,
+      "learning_rate": 5.989182666853125e-05,
+      "loss": 1.879,
+      "step": 1352
+    },
+    {
+      "epoch": 0.7789291882556131,
+      "grad_norm": 3.053706407546997,
+      "learning_rate": 5.970211955595526e-05,
+      "loss": 1.73,
+      "step": 1353
+    },
+    {
+      "epoch": 0.7795048934945308,
+      "grad_norm": 4.040714263916016,
+      "learning_rate": 5.951273686500546e-05,
+      "loss": 1.9029,
+      "step": 1354
+    },
+    {
+      "epoch": 0.7800805987334485,
+      "grad_norm": 3.6155359745025635,
+      "learning_rate": 5.9323679817201347e-05,
+      "loss": 1.8518,
+      "step": 1355
+    },
+    {
+      "epoch": 0.7806563039723662,
+      "grad_norm": 2.805917739868164,
+      "learning_rate": 5.913494963196202e-05,
+      "loss": 1.3817,
+      "step": 1356
+    },
+    {
+      "epoch": 0.7812320092112838,
+      "grad_norm": 2.4106318950653076,
+      "learning_rate": 5.894654752659826e-05,
+      "loss": 1.779,
+      "step": 1357
+    },
+    {
+      "epoch": 0.7818077144502015,
+      "grad_norm": 2.7342028617858887,
+      "learning_rate": 5.875847471630482e-05,
+      "loss": 1.539,
+      "step": 1358
+    },
+    {
+      "epoch": 0.7823834196891192,
+      "grad_norm": 4.626698970794678,
+      "learning_rate": 5.8570732414152354e-05,
+      "loss": 1.9292,
+      "step": 1359
+    },
+    {
+      "epoch": 0.7829591249280369,
+      "grad_norm": 2.9248266220092773,
+      "learning_rate": 5.8383321831079866e-05,
+      "loss": 2.1375,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7835348301669545,
+      "grad_norm": 4.143459796905518,
+      "learning_rate": 5.8196244175886714e-05,
+      "loss": 1.4635,
+      "step": 1361
+    },
+    {
+      "epoch": 0.7841105354058722,
+      "grad_norm": 2.493175983428955,
+      "learning_rate": 5.8009500655224926e-05,
+      "loss": 2.0653,
+      "step": 1362
+    },
+    {
+      "epoch": 0.7846862406447899,
+      "grad_norm": 2.802454710006714,
+      "learning_rate": 5.782309247359122e-05,
+      "loss": 1.4671,
+      "step": 1363
+    },
+    {
+      "epoch": 0.7852619458837076,
+      "grad_norm": 2.482621192932129,
+      "learning_rate": 5.7637020833319543e-05,
+      "loss": 1.7631,
+      "step": 1364
+    },
+    {
+      "epoch": 0.7858376511226253,
+      "grad_norm": 1.9779695272445679,
+      "learning_rate": 5.745128693457305e-05,
+      "loss": 2.0734,
+      "step": 1365
+    },
+    {
+      "epoch": 0.7864133563615429,
+      "grad_norm": 11.706380844116211,
+      "learning_rate": 5.7265891975336516e-05,
+      "loss": 1.4198,
+      "step": 1366
+    },
+    {
+      "epoch": 0.7869890616004606,
+      "grad_norm": 2.605114459991455,
+      "learning_rate": 5.708083715140847e-05,
+      "loss": 1.6385,
+      "step": 1367
+    },
+    {
+      "epoch": 0.7875647668393783,
+      "grad_norm": 3.059677839279175,
+      "learning_rate": 5.689612365639365e-05,
+      "loss": 1.6017,
+      "step": 1368
+    },
+    {
+      "epoch": 0.788140472078296,
+      "grad_norm": 1.8578213453292847,
+      "learning_rate": 5.6711752681695196e-05,
+      "loss": 2.0283,
+      "step": 1369
+    },
+    {
+      "epoch": 0.7887161773172136,
+      "grad_norm": 3.1265645027160645,
+      "learning_rate": 5.6527725416507004e-05,
+      "loss": 1.4247,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7892918825561313,
+      "grad_norm": 1.9533611536026,
+      "learning_rate": 5.634404304780596e-05,
+      "loss": 2.2994,
+      "step": 1371
+    },
+    {
+      "epoch": 0.789867587795049,
+      "grad_norm": 2.1204652786254883,
+      "learning_rate": 5.6160706760344474e-05,
+      "loss": 1.5297,
+      "step": 1372
+    },
+    {
+      "epoch": 0.7904432930339667,
+      "grad_norm": 1.745361089706421,
+      "learning_rate": 5.597771773664268e-05,
+      "loss": 1.8504,
+      "step": 1373
+    },
+    {
+      "epoch": 0.7910189982728842,
+      "grad_norm": 7.502842903137207,
+      "learning_rate": 5.579507715698088e-05,
+      "loss": 1.6416,
+      "step": 1374
+    },
+    {
+      "epoch": 0.791594703511802,
+      "grad_norm": 2.107741117477417,
+      "learning_rate": 5.561278619939183e-05,
+      "loss": 1.5842,
+      "step": 1375
+    },
+    {
+      "epoch": 0.7921704087507196,
+      "grad_norm": 2.415151357650757,
+      "learning_rate": 5.5430846039653336e-05,
+      "loss": 1.8056,
+      "step": 1376
+    },
+    {
+      "epoch": 0.7927461139896373,
+      "grad_norm": 2.2191529273986816,
+      "learning_rate": 5.52492578512805e-05,
+      "loss": 1.9055,
+      "step": 1377
+    },
+    {
+      "epoch": 0.7933218192285549,
+      "grad_norm": 2.3005576133728027,
+      "learning_rate": 5.506802280551822e-05,
+      "loss": 1.8145,
+      "step": 1378
+    },
+    {
+      "epoch": 0.7938975244674726,
+      "grad_norm": 4.749843597412109,
+      "learning_rate": 5.4887142071333564e-05,
+      "loss": 1.4035,
+      "step": 1379
+    },
+    {
+      "epoch": 0.7944732297063903,
+      "grad_norm": 2.0399606227874756,
+      "learning_rate": 5.470661681540838e-05,
+      "loss": 2.1479,
+      "step": 1380
+    },
+    {
+      "epoch": 0.795048934945308,
+      "grad_norm": 7.833768844604492,
+      "learning_rate": 5.452644820213162e-05,
+      "loss": 1.5584,
+      "step": 1381
+    },
+    {
+      "epoch": 0.7956246401842256,
+      "grad_norm": 3.434250593185425,
+      "learning_rate": 5.434663739359189e-05,
+      "loss": 1.7674,
+      "step": 1382
+    },
+    {
+      "epoch": 0.7962003454231433,
+      "grad_norm": 2.5569870471954346,
+      "learning_rate": 5.416718554957005e-05,
+      "loss": 1.5466,
+      "step": 1383
+    },
+    {
+      "epoch": 0.796776050662061,
+      "grad_norm": 2.374488115310669,
+      "learning_rate": 5.398809382753145e-05,
+      "loss": 1.65,
+      "step": 1384
+    },
+    {
+      "epoch": 0.7973517559009787,
+      "grad_norm": 13.02526569366455,
+      "learning_rate": 5.3809363382618795e-05,
+      "loss": 1.5528,
+      "step": 1385
+    },
+    {
+      "epoch": 0.7979274611398963,
+      "grad_norm": 1.7816729545593262,
+      "learning_rate": 5.363099536764451e-05,
+      "loss": 1.5285,
+      "step": 1386
+    },
+    {
+      "epoch": 0.798503166378814,
+      "grad_norm": 1.901544451713562,
+      "learning_rate": 5.345299093308336e-05,
+      "loss": 2.0212,
+      "step": 1387
+    },
+    {
+      "epoch": 0.7990788716177317,
+      "grad_norm": 2.702831506729126,
+      "learning_rate": 5.3275351227065e-05,
+      "loss": 1.6804,
+      "step": 1388
+    },
+    {
+      "epoch": 0.7996545768566494,
+      "grad_norm": 2.1472456455230713,
+      "learning_rate": 5.309807739536656e-05,
+      "loss": 1.8676,
+      "step": 1389
+    },
+    {
+      "epoch": 0.8002302820955671,
+      "grad_norm": 3.610424518585205,
+      "learning_rate": 5.292117058140532e-05,
+      "loss": 1.6772,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8008059873344847,
+      "grad_norm": 2.5551178455352783,
+      "learning_rate": 5.274463192623127e-05,
+      "loss": 1.9616,
+      "step": 1391
+    },
+    {
+      "epoch": 0.8013816925734024,
+      "grad_norm": 1.9815688133239746,
+      "learning_rate": 5.256846256851982e-05,
+      "loss": 1.9971,
+      "step": 1392
+    },
+    {
+      "epoch": 0.8019573978123201,
+      "grad_norm": 2.0742135047912598,
+      "learning_rate": 5.239266364456428e-05,
+      "loss": 1.9663,
+      "step": 1393
+    },
+    {
+      "epoch": 0.8025331030512378,
+      "grad_norm": 9.950126647949219,
+      "learning_rate": 5.221723628826882e-05,
+      "loss": 1.7592,
+      "step": 1394
+    },
+    {
+      "epoch": 0.8031088082901554,
+      "grad_norm": 4.535610675811768,
+      "learning_rate": 5.2042181631140894e-05,
+      "loss": 1.5708,
+      "step": 1395
+    },
+    {
+      "epoch": 0.8036845135290731,
+      "grad_norm": 1.889936089515686,
+      "learning_rate": 5.1867500802284086e-05,
+      "loss": 1.5133,
+      "step": 1396
+    },
+    {
+      "epoch": 0.8042602187679908,
+      "grad_norm": 8.857065200805664,
+      "learning_rate": 5.169319492839082e-05,
+      "loss": 1.7476,
+      "step": 1397
+    },
+    {
+      "epoch": 0.8048359240069085,
+      "grad_norm": 2.364290952682495,
+      "learning_rate": 5.1519265133734926e-05,
+      "loss": 1.6828,
+      "step": 1398
+    },
+    {
+      "epoch": 0.8054116292458261,
+      "grad_norm": 2.6671769618988037,
+      "learning_rate": 5.1345712540164645e-05,
+      "loss": 1.7961,
+      "step": 1399
+    },
+    {
+      "epoch": 0.8059873344847438,
+      "grad_norm": 2.6673574447631836,
+      "learning_rate": 5.117253826709525e-05,
+      "loss": 1.6032,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8065630397236615,
+      "grad_norm": 2.591360092163086,
+      "learning_rate": 5.09997434315018e-05,
+      "loss": 1.7569,
+      "step": 1401
+    },
+    {
+      "epoch": 0.8071387449625792,
+      "grad_norm": 3.1606340408325195,
+      "learning_rate": 5.0827329147912064e-05,
+      "loss": 1.781,
+      "step": 1402
+    },
+    {
+      "epoch": 0.8077144502014968,
+      "grad_norm": 2.5817081928253174,
+      "learning_rate": 5.065529652839911e-05,
+      "loss": 1.4997,
+      "step": 1403
+    },
+    {
+      "epoch": 0.8082901554404145,
+      "grad_norm": 2.332239866256714,
+      "learning_rate": 5.048364668257437e-05,
+      "loss": 1.5715,
+      "step": 1404
+    },
+    {
+      "epoch": 0.8088658606793322,
+      "grad_norm": 2.802133560180664,
+      "learning_rate": 5.0312380717580395e-05,
+      "loss": 1.6691,
+      "step": 1405
+    },
+    {
+      "epoch": 0.8094415659182499,
+      "grad_norm": 2.61683988571167,
+      "learning_rate": 5.0141499738083665e-05,
+      "loss": 1.6009,
+      "step": 1406
+    },
+    {
+      "epoch": 0.8100172711571675,
+      "grad_norm": 3.1548593044281006,
+      "learning_rate": 4.9971004846267525e-05,
+      "loss": 1.7691,
+      "step": 1407
+    },
+    {
+      "epoch": 0.8105929763960852,
+      "grad_norm": 1.757272720336914,
+      "learning_rate": 4.980089714182498e-05,
+      "loss": 1.7078,
+      "step": 1408
+    },
+    {
+      "epoch": 0.8111686816350029,
+      "grad_norm": 1.6123958826065063,
+      "learning_rate": 4.963117772195175e-05,
+      "loss": 1.6996,
+      "step": 1409
+    },
+    {
+      "epoch": 0.8117443868739206,
+      "grad_norm": 1.9068481922149658,
+      "learning_rate": 4.9461847681339117e-05,
+      "loss": 1.9354,
+      "step": 1410
+    },
+    {
+      "epoch": 0.8123200921128382,
+      "grad_norm": 9.043222427368164,
+      "learning_rate": 4.929290811216684e-05,
+      "loss": 1.8378,
+      "step": 1411
+    },
+    {
+      "epoch": 0.8128957973517559,
+      "grad_norm": 2.600364923477173,
+      "learning_rate": 4.9124360104096145e-05,
+      "loss": 1.6121,
+      "step": 1412
+    },
+    {
+      "epoch": 0.8134715025906736,
+      "grad_norm": 10.776697158813477,
+      "learning_rate": 4.8956204744262645e-05,
+      "loss": 1.5468,
+      "step": 1413
+    },
+    {
+      "epoch": 0.8140472078295913,
+      "grad_norm": 33.18220138549805,
+      "learning_rate": 4.878844311726944e-05,
+      "loss": 1.9193,
+      "step": 1414
+    },
+    {
+      "epoch": 0.8146229130685089,
+      "grad_norm": 3.4159226417541504,
+      "learning_rate": 4.862107630517999e-05,
+      "loss": 1.8736,
+      "step": 1415
+    },
+    {
+      "epoch": 0.8151986183074266,
+      "grad_norm": 1.6860475540161133,
+      "learning_rate": 4.845410538751124e-05,
+      "loss": 1.8344,
+      "step": 1416
+    },
+    {
+      "epoch": 0.8157743235463443,
+      "grad_norm": 2.0587282180786133,
+      "learning_rate": 4.8287531441226624e-05,
+      "loss": 1.3845,
+      "step": 1417
+    },
+    {
+      "epoch": 0.816350028785262,
+      "grad_norm": 2.421825885772705,
+      "learning_rate": 4.812135554072902e-05,
+      "loss": 1.5756,
+      "step": 1418
+    },
+    {
+      "epoch": 0.8169257340241797,
+      "grad_norm": 3.1374471187591553,
+      "learning_rate": 4.795557875785398e-05,
+      "loss": 1.7904,
+      "step": 1419
+    },
+    {
+      "epoch": 0.8175014392630973,
+      "grad_norm": 2.8920180797576904,
+      "learning_rate": 4.7790202161862766e-05,
+      "loss": 1.7138,
+      "step": 1420
+    },
+    {
+      "epoch": 0.818077144502015,
+      "grad_norm": 1.6835691928863525,
+      "learning_rate": 4.762522681943539e-05,
+      "loss": 1.9889,
+      "step": 1421
+    },
+    {
+      "epoch": 0.8186528497409327,
+      "grad_norm": 23.137161254882812,
+      "learning_rate": 4.74606537946638e-05,
+      "loss": 1.3748,
+      "step": 1422
+    },
+    {
+      "epoch": 0.8192285549798504,
+      "grad_norm": 2.444957733154297,
+      "learning_rate": 4.7296484149044934e-05,
+      "loss": 1.5844,
+      "step": 1423
+    },
+    {
+      "epoch": 0.819804260218768,
+      "grad_norm": 2.6292054653167725,
+      "learning_rate": 4.7132718941473996e-05,
+      "loss": 1.9214,
+      "step": 1424
+    },
+    {
+      "epoch": 0.8203799654576857,
+      "grad_norm": 3.0672450065612793,
+      "learning_rate": 4.696935922823757e-05,
+      "loss": 1.5782,
+      "step": 1425
+    },
+    {
+      "epoch": 0.8209556706966034,
+      "grad_norm": 3.0023117065429688,
+      "learning_rate": 4.6806406063006725e-05,
+      "loss": 1.5314,
+      "step": 1426
+    },
+    {
+      "epoch": 0.8215313759355211,
+      "grad_norm": 1.7481844425201416,
+      "learning_rate": 4.664386049683041e-05,
+      "loss": 1.698,
+      "step": 1427
+    },
+    {
+      "epoch": 0.8221070811744386,
+      "grad_norm": 2.199160575866699,
+      "learning_rate": 4.648172357812841e-05,
+      "loss": 1.9814,
+      "step": 1428
+    },
+    {
+      "epoch": 0.8226827864133563,
+      "grad_norm": 2.4570064544677734,
+      "learning_rate": 4.631999635268484e-05,
+      "loss": 1.8599,
+      "step": 1429
+    },
+    {
+      "epoch": 0.823258491652274,
+      "grad_norm": 1.9632291793823242,
+      "learning_rate": 4.6158679863641276e-05,
+      "loss": 1.4043,
+      "step": 1430
+    },
+    {
+      "epoch": 0.8238341968911918,
+      "grad_norm": 1.8881250619888306,
+      "learning_rate": 4.599777515149e-05,
+      "loss": 1.2514,
+      "step": 1431
+    },
+    {
+      "epoch": 0.8244099021301093,
+      "grad_norm": 2.0757150650024414,
+      "learning_rate": 4.5837283254067406e-05,
+      "loss": 1.6057,
+      "step": 1432
+    },
+    {
+      "epoch": 0.824985607369027,
+      "grad_norm": 2.9833948612213135,
+      "learning_rate": 4.567720520654711e-05,
+      "loss": 1.7238,
+      "step": 1433
+    },
+    {
+      "epoch": 0.8255613126079447,
+      "grad_norm": 2.425083637237549,
+      "learning_rate": 4.5517542041433505e-05,
+      "loss": 1.4574,
+      "step": 1434
+    },
+    {
+      "epoch": 0.8261370178468624,
+      "grad_norm": 2.698265552520752,
+      "learning_rate": 4.535829478855495e-05,
+      "loss": 2.1176,
+      "step": 1435
+    },
+    {
+      "epoch": 0.82671272308578,
+      "grad_norm": 4.3886895179748535,
+      "learning_rate": 4.5199464475057156e-05,
+      "loss": 1.3737,
+      "step": 1436
+    },
+    {
+      "epoch": 0.8272884283246977,
+      "grad_norm": 1.7580487728118896,
+      "learning_rate": 4.504105212539662e-05,
+      "loss": 1.9613,
+      "step": 1437
+    },
+    {
+      "epoch": 0.8278641335636154,
+      "grad_norm": 7.8885884284973145,
+      "learning_rate": 4.4883058761333876e-05,
+      "loss": 2.0528,
+      "step": 1438
+    },
+    {
+      "epoch": 0.8284398388025331,
+      "grad_norm": 2.186002492904663,
+      "learning_rate": 4.4725485401927084e-05,
+      "loss": 1.2608,
+      "step": 1439
+    },
+    {
+      "epoch": 0.8290155440414507,
+      "grad_norm": 3.021320343017578,
+      "learning_rate": 4.456833306352535e-05,
+      "loss": 1.8178,
+      "step": 1440
+    },
+    {
+      "epoch": 0.8295912492803684,
+      "grad_norm": 2.60939359664917,
+      "learning_rate": 4.4411602759762206e-05,
+      "loss": 1.4904,
+      "step": 1441
+    },
+    {
+      "epoch": 0.8301669545192861,
+      "grad_norm": 4.945908069610596,
+      "learning_rate": 4.425529550154898e-05,
+      "loss": 1.5249,
+      "step": 1442
+    },
+    {
+      "epoch": 0.8307426597582038,
+      "grad_norm": 14.266429901123047,
+      "learning_rate": 4.409941229706844e-05,
+      "loss": 1.5869,
+      "step": 1443
+    },
+    {
+      "epoch": 0.8313183649971215,
+      "grad_norm": 9.433239936828613,
+      "learning_rate": 4.394395415176819e-05,
+      "loss": 1.6449,
+      "step": 1444
+    },
+    {
+      "epoch": 0.8318940702360391,
+      "grad_norm": 5.42481803894043,
+      "learning_rate": 4.37889220683542e-05,
+      "loss": 1.2183,
+      "step": 1445
+    },
+    {
+      "epoch": 0.8324697754749568,
+      "grad_norm": 2.151113748550415,
+      "learning_rate": 4.3634317046784276e-05,
+      "loss": 1.781,
+      "step": 1446
+    },
+    {
+      "epoch": 0.8330454807138745,
+      "grad_norm": 2.0852885246276855,
+      "learning_rate": 4.348014008426174e-05,
+      "loss": 1.5667,
+      "step": 1447
+    },
+    {
+      "epoch": 0.8336211859527922,
+      "grad_norm": 3.500631332397461,
+      "learning_rate": 4.332639217522892e-05,
+      "loss": 1.7769,
+      "step": 1448
+    },
+    {
+      "epoch": 0.8341968911917098,
+      "grad_norm": 1.7998766899108887,
+      "learning_rate": 4.317307431136077e-05,
+      "loss": 1.7307,
+      "step": 1449
+    },
+    {
+      "epoch": 0.8347725964306275,
+      "grad_norm": 2.19659423828125,
+      "learning_rate": 4.302018748155835e-05,
+      "loss": 1.3793,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8353483016695452,
+      "grad_norm": 2.0075533390045166,
+      "learning_rate": 4.2867732671942655e-05,
+      "loss": 1.73,
+      "step": 1451
+    },
+    {
+      "epoch": 0.8359240069084629,
+      "grad_norm": 2.092893123626709,
+      "learning_rate": 4.27157108658481e-05,
+      "loss": 1.5776,
+      "step": 1452
+    },
+    {
+      "epoch": 0.8364997121473805,
+      "grad_norm": 2.9703755378723145,
+      "learning_rate": 4.256412304381626e-05,
+      "loss": 1.8263,
+      "step": 1453
+    },
+    {
+      "epoch": 0.8370754173862982,
+      "grad_norm": 2.695039749145508,
+      "learning_rate": 4.241297018358944e-05,
+      "loss": 1.7818,
+      "step": 1454
+    },
+    {
+      "epoch": 0.8376511226252159,
+      "grad_norm": 1.862975835800171,
+      "learning_rate": 4.22622532601045e-05,
+      "loss": 1.9428,
+      "step": 1455
+    },
+    {
+      "epoch": 0.8382268278641336,
+      "grad_norm": 1.650801181793213,
+      "learning_rate": 4.2111973245486484e-05,
+      "loss": 1.9121,
+      "step": 1456
+    },
+    {
+      "epoch": 0.8388025331030512,
+      "grad_norm": 5.668527126312256,
+      "learning_rate": 4.1962131109042415e-05,
+      "loss": 1.6202,
+      "step": 1457
+    },
+    {
+      "epoch": 0.8393782383419689,
+      "grad_norm": 2.183865785598755,
+      "learning_rate": 4.1812727817254895e-05,
+      "loss": 1.5201,
+      "step": 1458
+    },
+    {
+      "epoch": 0.8399539435808866,
+      "grad_norm": 2.1227545738220215,
+      "learning_rate": 4.1663764333776064e-05,
+      "loss": 1.7222,
+      "step": 1459
+    },
+    {
+      "epoch": 0.8405296488198043,
+      "grad_norm": 9.781892776489258,
+      "learning_rate": 4.151524161942127e-05,
+      "loss": 1.4787,
+      "step": 1460
+    },
+    {
+      "epoch": 0.8411053540587219,
+      "grad_norm": 2.429591178894043,
+      "learning_rate": 4.136716063216295e-05,
+      "loss": 1.6744,
+      "step": 1461
+    },
+    {
+      "epoch": 0.8416810592976396,
+      "grad_norm": 6.654470920562744,
+      "learning_rate": 4.1219522327124274e-05,
+      "loss": 1.3484,
+      "step": 1462
+    },
+    {
+      "epoch": 0.8422567645365573,
+      "grad_norm": 1.9197490215301514,
+      "learning_rate": 4.1072327656573195e-05,
+      "loss": 2.0138,
+      "step": 1463
+    },
+    {
+      "epoch": 0.842832469775475,
+      "grad_norm": 2.8286044597625732,
+      "learning_rate": 4.0925577569916215e-05,
+      "loss": 1.7853,
+      "step": 1464
+    },
+    {
+      "epoch": 0.8434081750143926,
+      "grad_norm": 2.5149343013763428,
+      "learning_rate": 4.077927301369229e-05,
+      "loss": 1.8245,
+      "step": 1465
+    },
+    {
+      "epoch": 0.8439838802533103,
+      "grad_norm": 2.691681146621704,
+      "learning_rate": 4.0633414931566674e-05,
+      "loss": 1.6478,
+      "step": 1466
+    },
+    {
+      "epoch": 0.844559585492228,
+      "grad_norm": 2.1990113258361816,
+      "learning_rate": 4.048800426432481e-05,
+      "loss": 2.1302,
+      "step": 1467
+    },
+    {
+      "epoch": 0.8451352907311457,
+      "grad_norm": 2.3419196605682373,
+      "learning_rate": 4.0343041949866374e-05,
+      "loss": 1.4665,
+      "step": 1468
+    },
+    {
+      "epoch": 0.8457109959700633,
+      "grad_norm": 7.4243621826171875,
+      "learning_rate": 4.019852892319918e-05,
+      "loss": 1.7909,
+      "step": 1469
+    },
+    {
+      "epoch": 0.846286701208981,
+      "grad_norm": 2.0324108600616455,
+      "learning_rate": 4.0054466116433076e-05,
+      "loss": 1.5596,
+      "step": 1470
+    },
+    {
+      "epoch": 0.8468624064478987,
+      "grad_norm": 2.6202523708343506,
+      "learning_rate": 3.991085445877407e-05,
+      "loss": 1.6099,
+      "step": 1471
+    },
+    {
+      "epoch": 0.8474381116868164,
+      "grad_norm": 2.4301211833953857,
+      "learning_rate": 3.976769487651812e-05,
+      "loss": 1.5236,
+      "step": 1472
+    },
+    {
+      "epoch": 0.8480138169257341,
+      "grad_norm": 2.1029152870178223,
+      "learning_rate": 3.962498829304544e-05,
+      "loss": 1.633,
+      "step": 1473
+    },
+    {
+      "epoch": 0.8485895221646517,
+      "grad_norm": 1.8765809535980225,
+      "learning_rate": 3.948273562881431e-05,
+      "loss": 2.2869,
+      "step": 1474
+    },
+    {
+      "epoch": 0.8491652274035694,
+      "grad_norm": 4.706104755401611,
+      "learning_rate": 3.934093780135526e-05,
+      "loss": 1.5334,
+      "step": 1475
+    },
+    {
+      "epoch": 0.8497409326424871,
+      "grad_norm": 2.9571614265441895,
+      "learning_rate": 3.919959572526515e-05,
+      "loss": 1.601,
+      "step": 1476
+    },
+    {
+      "epoch": 0.8503166378814048,
+      "grad_norm": 2.8153023719787598,
+      "learning_rate": 3.905871031220114e-05,
+      "loss": 1.714,
+      "step": 1477
+    },
+    {
+      "epoch": 0.8508923431203224,
+      "grad_norm": 3.300020694732666,
+      "learning_rate": 3.891828247087503e-05,
+      "loss": 1.5648,
+      "step": 1478
+    },
+    {
+      "epoch": 0.8514680483592401,
+      "grad_norm": 1.9410463571548462,
+      "learning_rate": 3.8778313107047194e-05,
+      "loss": 1.5899,
+      "step": 1479
+    },
+    {
+      "epoch": 0.8520437535981578,
+      "grad_norm": 2.5568149089813232,
+      "learning_rate": 3.8638803123520885e-05,
+      "loss": 1.445,
+      "step": 1480
+    },
+    {
+      "epoch": 0.8526194588370755,
+      "grad_norm": 2.5880024433135986,
+      "learning_rate": 3.849975342013632e-05,
+      "loss": 1.5832,
+      "step": 1481
+    },
+    {
+      "epoch": 0.853195164075993,
+      "grad_norm": 2.6164777278900146,
+      "learning_rate": 3.836116489376487e-05,
+      "loss": 1.8137,
+      "step": 1482
+    },
+    {
+      "epoch": 0.8537708693149108,
+      "grad_norm": 2.442946195602417,
+      "learning_rate": 3.8223038438303386e-05,
+      "loss": 1.8325,
+      "step": 1483
+    },
+    {
+      "epoch": 0.8543465745538285,
+      "grad_norm": 2.978116750717163,
+      "learning_rate": 3.80853749446683e-05,
+      "loss": 1.6184,
+      "step": 1484
+    },
+    {
+      "epoch": 0.8549222797927462,
+      "grad_norm": 2.5034267902374268,
+      "learning_rate": 3.794817530078998e-05,
+      "loss": 1.7953,
+      "step": 1485
+    },
+    {
+      "epoch": 0.8554979850316637,
+      "grad_norm": 1.9510966539382935,
+      "learning_rate": 3.781144039160696e-05,
+      "loss": 2.0733,
+      "step": 1486
+    },
+    {
+      "epoch": 0.8560736902705814,
+      "grad_norm": 3.1095547676086426,
+      "learning_rate": 3.7675171099060146e-05,
+      "loss": 1.6943,
+      "step": 1487
+    },
+    {
+      "epoch": 0.8566493955094991,
+      "grad_norm": 4.343941688537598,
+      "learning_rate": 3.753936830208732e-05,
+      "loss": 1.8097,
+      "step": 1488
+    },
+    {
+      "epoch": 0.8572251007484168,
+      "grad_norm": 4.57112455368042,
+      "learning_rate": 3.740403287661733e-05,
+      "loss": 1.5298,
+      "step": 1489
+    },
+    {
+      "epoch": 0.8578008059873344,
+      "grad_norm": 2.700908660888672,
+      "learning_rate": 3.7269165695564466e-05,
+      "loss": 1.6386,
+      "step": 1490
+    },
+    {
+      "epoch": 0.8583765112262521,
+      "grad_norm": 5.609554767608643,
+      "learning_rate": 3.7134767628822866e-05,
+      "loss": 1.6708,
+      "step": 1491
+    },
+    {
+      "epoch": 0.8589522164651698,
+      "grad_norm": 1.9039596319198608,
+      "learning_rate": 3.70008395432608e-05,
+      "loss": 1.7443,
+      "step": 1492
+    },
+    {
+      "epoch": 0.8595279217040875,
+      "grad_norm": 1.7202305793762207,
+      "learning_rate": 3.6867382302715246e-05,
+      "loss": 1.6488,
+      "step": 1493
+    },
+    {
+      "epoch": 0.8601036269430051,
+      "grad_norm": 4.734544277191162,
+      "learning_rate": 3.673439676798619e-05,
+      "loss": 1.5792,
+      "step": 1494
+    },
+    {
+      "epoch": 0.8606793321819228,
+      "grad_norm": 2.9303762912750244,
+      "learning_rate": 3.660188379683111e-05,
+      "loss": 1.9368,
+      "step": 1495
+    },
+    {
+      "epoch": 0.8612550374208405,
+      "grad_norm": 2.010754346847534,
+      "learning_rate": 3.6469844243959504e-05,
+      "loss": 1.4729,
+      "step": 1496
+    },
+    {
+      "epoch": 0.8618307426597582,
+      "grad_norm": 5.018930435180664,
+      "learning_rate": 3.633827896102718e-05,
+      "loss": 1.5923,
+      "step": 1497
+    },
+    {
+      "epoch": 0.8624064478986759,
+      "grad_norm": 3.2413840293884277,
+      "learning_rate": 3.620718879663105e-05,
+      "loss": 1.5517,
+      "step": 1498
+    },
+    {
+      "epoch": 0.8629821531375935,
+      "grad_norm": 5.733468055725098,
+      "learning_rate": 3.607657459630344e-05,
+      "loss": 1.826,
+      "step": 1499
+    },
+    {
+      "epoch": 0.8635578583765112,
+      "grad_norm": 2.5515568256378174,
+      "learning_rate": 3.594643720250672e-05,
+      "loss": 1.7602,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8641335636154289,
+      "grad_norm": 2.406984329223633,
+      "learning_rate": 3.581677745462783e-05,
+      "loss": 1.5286,
+      "step": 1501
+    },
+    {
+      "epoch": 0.8647092688543466,
+      "grad_norm": 5.683862686157227,
+      "learning_rate": 3.5687596188972904e-05,
+      "loss": 1.4922,
+      "step": 1502
+    },
+    {
+      "epoch": 0.8652849740932642,
+      "grad_norm": 1.9116665124893188,
+      "learning_rate": 3.5558894238761884e-05,
+      "loss": 1.7833,
+      "step": 1503
+    },
+    {
+      "epoch": 0.8658606793321819,
+      "grad_norm": 3.2668724060058594,
+      "learning_rate": 3.5430672434123125e-05,
+      "loss": 1.5224,
+      "step": 1504
+    },
+    {
+      "epoch": 0.8664363845710996,
+      "grad_norm": 1.9823722839355469,
+      "learning_rate": 3.530293160208803e-05,
+      "loss": 1.8138,
+      "step": 1505
+    },
+    {
+      "epoch": 0.8670120898100173,
+      "grad_norm": 2.5123682022094727,
+      "learning_rate": 3.517567256658567e-05,
+      "loss": 1.5935,
+      "step": 1506
+    },
+    {
+      "epoch": 0.8675877950489349,
+      "grad_norm": 2.4445598125457764,
+      "learning_rate": 3.504889614843762e-05,
+      "loss": 1.5742,
+      "step": 1507
+    },
+    {
+      "epoch": 0.8681635002878526,
+      "grad_norm": 1.7008769512176514,
+      "learning_rate": 3.4922603165352505e-05,
+      "loss": 1.8661,
+      "step": 1508
+    },
+    {
+      "epoch": 0.8687392055267703,
+      "grad_norm": 4.077759265899658,
+      "learning_rate": 3.479679443192083e-05,
+      "loss": 1.5453,
+      "step": 1509
+    },
+    {
+      "epoch": 0.869314910765688,
+      "grad_norm": 2.2880473136901855,
+      "learning_rate": 3.467147075960968e-05,
+      "loss": 1.7597,
+      "step": 1510
+    },
+    {
+      "epoch": 0.8698906160046056,
+      "grad_norm": 2.8297314643859863,
+      "learning_rate": 3.454663295675743e-05,
+      "loss": 2.0131,
+      "step": 1511
+    },
+    {
+      "epoch": 0.8704663212435233,
+      "grad_norm": 1.678479552268982,
+      "learning_rate": 3.442228182856869e-05,
+      "loss": 1.8904,
+      "step": 1512
+    },
+    {
+      "epoch": 0.871042026482441,
+      "grad_norm": 2.128466844558716,
+      "learning_rate": 3.429841817710897e-05,
+      "loss": 1.7562,
+      "step": 1513
+    },
+    {
+      "epoch": 0.8716177317213587,
+      "grad_norm": 1.8092970848083496,
+      "learning_rate": 3.4175042801299537e-05,
+      "loss": 1.764,
+      "step": 1514
+    },
+    {
+      "epoch": 0.8721934369602763,
+      "grad_norm": 2.2660231590270996,
+      "learning_rate": 3.4052156496912324e-05,
+      "loss": 1.7881,
+      "step": 1515
+    },
+    {
+      "epoch": 0.872769142199194,
+      "grad_norm": 1.9774857759475708,
+      "learning_rate": 3.3929760056564676e-05,
+      "loss": 1.6372,
+      "step": 1516
+    },
+    {
+      "epoch": 0.8733448474381117,
+      "grad_norm": 2.9389281272888184,
+      "learning_rate": 3.380785426971439e-05,
+      "loss": 1.6053,
+      "step": 1517
+    },
+    {
+      "epoch": 0.8739205526770294,
+      "grad_norm": 3.5324361324310303,
+      "learning_rate": 3.36864399226545e-05,
+      "loss": 1.2821,
+      "step": 1518
+    },
+    {
+      "epoch": 0.874496257915947,
+      "grad_norm": 3.9741134643554688,
+      "learning_rate": 3.356551779850826e-05,
+      "loss": 1.4092,
+      "step": 1519
+    },
+    {
+      "epoch": 0.8750719631548647,
+      "grad_norm": 2.823326826095581,
+      "learning_rate": 3.3445088677224115e-05,
+      "loss": 1.4555,
+      "step": 1520
+    },
+    {
+      "epoch": 0.8756476683937824,
+      "grad_norm": 2.093947410583496,
+      "learning_rate": 3.332515333557057e-05,
+      "loss": 1.8958,
+      "step": 1521
+    },
+    {
+      "epoch": 0.8762233736327001,
+      "grad_norm": 1.6862866878509521,
+      "learning_rate": 3.320571254713129e-05,
+      "loss": 1.7541,
+      "step": 1522
+    },
+    {
+      "epoch": 0.8767990788716177,
+      "grad_norm": 2.490295171737671,
+      "learning_rate": 3.308676708230009e-05,
+      "loss": 1.8613,
+      "step": 1523
+    },
+    {
+      "epoch": 0.8773747841105354,
+      "grad_norm": 2.3449649810791016,
+      "learning_rate": 3.296831770827591e-05,
+      "loss": 1.7296,
+      "step": 1524
+    },
+    {
+      "epoch": 0.8779504893494531,
+      "grad_norm": 1.8488191366195679,
+      "learning_rate": 3.285036518905793e-05,
+      "loss": 1.923,
+      "step": 1525
+    },
+    {
+      "epoch": 0.8785261945883708,
+      "grad_norm": 1.8789899349212646,
+      "learning_rate": 3.2732910285440556e-05,
+      "loss": 1.6328,
+      "step": 1526
+    },
+    {
+      "epoch": 0.8791018998272885,
+      "grad_norm": 3.361023426055908,
+      "learning_rate": 3.2615953755008644e-05,
+      "loss": 1.7281,
+      "step": 1527
+    },
+    {
+      "epoch": 0.8796776050662061,
+      "grad_norm": 42.89087677001953,
+      "learning_rate": 3.2499496352132506e-05,
+      "loss": 1.774,
+      "step": 1528
+    },
+    {
+      "epoch": 0.8802533103051238,
+      "grad_norm": 5.994923114776611,
+      "learning_rate": 3.238353882796306e-05,
+      "loss": 1.9721,
+      "step": 1529
+    },
+    {
+      "epoch": 0.8808290155440415,
+      "grad_norm": 13.579315185546875,
+      "learning_rate": 3.226808193042703e-05,
+      "loss": 1.2176,
+      "step": 1530
+    },
+    {
+      "epoch": 0.8814047207829592,
+      "grad_norm": 2.5451056957244873,
+      "learning_rate": 3.215312640422209e-05,
+      "loss": 1.528,
+      "step": 1531
+    },
+    {
+      "epoch": 0.8819804260218768,
+      "grad_norm": 2.525620698928833,
+      "learning_rate": 3.203867299081208e-05,
+      "loss": 1.9587,
+      "step": 1532
+    },
+    {
+      "epoch": 0.8825561312607945,
+      "grad_norm": 3.4536986351013184,
+      "learning_rate": 3.1924722428422166e-05,
+      "loss": 1.6012,
+      "step": 1533
+    },
+    {
+      "epoch": 0.8831318364997122,
+      "grad_norm": 12.571866989135742,
+      "learning_rate": 3.181127545203415e-05,
+      "loss": 1.6318,
+      "step": 1534
+    },
+    {
+      "epoch": 0.8837075417386299,
+      "grad_norm": 1.5467040538787842,
+      "learning_rate": 3.169833279338171e-05,
+      "loss": 1.6015,
+      "step": 1535
+    },
+    {
+      "epoch": 0.8842832469775475,
+      "grad_norm": 2.1955318450927734,
+      "learning_rate": 3.158589518094569e-05,
+      "loss": 1.7985,
+      "step": 1536
+    },
+    {
+      "epoch": 0.8848589522164652,
+      "grad_norm": 2.313436985015869,
+      "learning_rate": 3.147396333994931e-05,
+      "loss": 1.7134,
+      "step": 1537
+    },
+    {
+      "epoch": 0.8854346574553829,
+      "grad_norm": 2.0974152088165283,
+      "learning_rate": 3.136253799235361e-05,
+      "loss": 1.5563,
+      "step": 1538
+    },
+    {
+      "epoch": 0.8860103626943006,
+      "grad_norm": 18.715166091918945,
+      "learning_rate": 3.1251619856852766e-05,
+      "loss": 1.5542,
+      "step": 1539
+    },
+    {
+      "epoch": 0.8865860679332181,
+      "grad_norm": 2.192904472351074,
+      "learning_rate": 3.114120964886941e-05,
+      "loss": 1.6669,
+      "step": 1540
+    },
+    {
+      "epoch": 0.8871617731721358,
+      "grad_norm": 2.376451253890991,
+      "learning_rate": 3.103130808055001e-05,
+      "loss": 1.7179,
+      "step": 1541
+    },
+    {
+      "epoch": 0.8877374784110535,
+      "grad_norm": 1.8845385313034058,
+      "learning_rate": 3.0921915860760336e-05,
+      "loss": 1.6391,
+      "step": 1542
+    },
+    {
+      "epoch": 0.8883131836499712,
+      "grad_norm": 8.009706497192383,
+      "learning_rate": 3.081303369508086e-05,
+      "loss": 1.5454,
+      "step": 1543
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.6856307983398438,
+      "learning_rate": 3.0704662285802205e-05,
+      "loss": 1.4787,
+      "step": 1544
+    },
+    {
+      "epoch": 0.8894645941278065,
+      "grad_norm": 3.4085445404052734,
+      "learning_rate": 3.05968023319206e-05,
+      "loss": 1.5018,
+      "step": 1545
+    },
+    {
+      "epoch": 0.8900402993667242,
+      "grad_norm": 2.609632968902588,
+      "learning_rate": 3.0489454529133355e-05,
+      "loss": 1.6954,
+      "step": 1546
+    },
+    {
+      "epoch": 0.8906160046056419,
+      "grad_norm": 3.0396652221679688,
+      "learning_rate": 3.0382619569834457e-05,
+      "loss": 1.3057,
+      "step": 1547
+    },
+    {
+      "epoch": 0.8911917098445595,
+      "grad_norm": 2.7313220500946045,
+      "learning_rate": 3.0276298143110026e-05,
+      "loss": 1.5419,
+      "step": 1548
+    },
+    {
+      "epoch": 0.8917674150834772,
+      "grad_norm": 2.755401849746704,
+      "learning_rate": 3.0170490934733876e-05,
+      "loss": 1.6691,
+      "step": 1549
+    },
+    {
+      "epoch": 0.8923431203223949,
+      "grad_norm": 1.716202974319458,
+      "learning_rate": 3.006519862716317e-05,
+      "loss": 1.7587,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8929188255613126,
+      "grad_norm": 1.8662277460098267,
+      "learning_rate": 2.9960421899533865e-05,
+      "loss": 1.9159,
+      "step": 1551
+    },
+    {
+      "epoch": 0.8934945308002303,
+      "grad_norm": 4.879543781280518,
+      "learning_rate": 2.9856161427656487e-05,
+      "loss": 1.3678,
+      "step": 1552
+    },
+    {
+      "epoch": 0.8940702360391479,
+      "grad_norm": 2.583407402038574,
+      "learning_rate": 2.975241788401171e-05,
+      "loss": 1.7672,
+      "step": 1553
+    },
+    {
+      "epoch": 0.8946459412780656,
+      "grad_norm": 3.620436906814575,
+      "learning_rate": 2.9649191937746e-05,
+      "loss": 1.661,
+      "step": 1554
+    },
+    {
+      "epoch": 0.8952216465169833,
+      "grad_norm": 3.122196912765503,
+      "learning_rate": 2.9546484254667305e-05,
+      "loss": 1.6674,
+      "step": 1555
+    },
+    {
+      "epoch": 0.895797351755901,
+      "grad_norm": 3.580239772796631,
+      "learning_rate": 2.9444295497240786e-05,
+      "loss": 1.5959,
+      "step": 1556
+    },
+    {
+      "epoch": 0.8963730569948186,
+      "grad_norm": 3.08005690574646,
+      "learning_rate": 2.934262632458456e-05,
+      "loss": 1.7921,
+      "step": 1557
+    },
+    {
+      "epoch": 0.8969487622337363,
+      "grad_norm": 3.1388845443725586,
+      "learning_rate": 2.924147739246538e-05,
+      "loss": 1.4324,
+      "step": 1558
+    },
+    {
+      "epoch": 0.897524467472654,
+      "grad_norm": 1.6643763780593872,
+      "learning_rate": 2.9140849353294465e-05,
+      "loss": 2.0322,
+      "step": 1559
+    },
+    {
+      "epoch": 0.8981001727115717,
+      "grad_norm": 10.998340606689453,
+      "learning_rate": 2.9040742856123226e-05,
+      "loss": 1.3504,
+      "step": 1560
+    },
+    {
+      "epoch": 0.8986758779504893,
+      "grad_norm": 1.995599389076233,
+      "learning_rate": 2.8941158546639192e-05,
+      "loss": 1.7513,
+      "step": 1561
+    },
+    {
+      "epoch": 0.899251583189407,
+      "grad_norm": 3.020902156829834,
+      "learning_rate": 2.8842097067161745e-05,
+      "loss": 1.4212,
+      "step": 1562
+    },
+    {
+      "epoch": 0.8998272884283247,
+      "grad_norm": 12.61132526397705,
+      "learning_rate": 2.8743559056638008e-05,
+      "loss": 1.5555,
+      "step": 1563
+    },
+    {
+      "epoch": 0.9004029936672424,
+      "grad_norm": 2.2911295890808105,
+      "learning_rate": 2.8645545150638743e-05,
+      "loss": 2.0018,
+      "step": 1564
+    },
+    {
+      "epoch": 0.90097869890616,
+      "grad_norm": 2.1019484996795654,
+      "learning_rate": 2.854805598135421e-05,
+      "loss": 1.7656,
+      "step": 1565
+    },
+    {
+      "epoch": 0.9015544041450777,
+      "grad_norm": 3.490584373474121,
+      "learning_rate": 2.845109217759012e-05,
+      "loss": 1.8212,
+      "step": 1566
+    },
+    {
+      "epoch": 0.9021301093839954,
+      "grad_norm": 2.4750654697418213,
+      "learning_rate": 2.83546543647636e-05,
+      "loss": 1.901,
+      "step": 1567
+    },
+    {
+      "epoch": 0.9027058146229131,
+      "grad_norm": 2.432142972946167,
+      "learning_rate": 2.8258743164899106e-05,
+      "loss": 1.5119,
+      "step": 1568
+    },
+    {
+      "epoch": 0.9032815198618307,
+      "grad_norm": 2.253786325454712,
+      "learning_rate": 2.816335919662445e-05,
+      "loss": 1.6083,
+      "step": 1569
+    },
+    {
+      "epoch": 0.9038572251007484,
+      "grad_norm": 3.009180784225464,
+      "learning_rate": 2.8068503075166773e-05,
+      "loss": 1.5534,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9044329303396661,
+      "grad_norm": 2.081758499145508,
+      "learning_rate": 2.797417541234863e-05,
+      "loss": 1.6858,
+      "step": 1571
+    },
+    {
+      "epoch": 0.9050086355785838,
+      "grad_norm": 1.856590986251831,
+      "learning_rate": 2.7880376816584003e-05,
+      "loss": 1.8481,
+      "step": 1572
+    },
+    {
+      "epoch": 0.9055843408175014,
+      "grad_norm": 2.4933712482452393,
+      "learning_rate": 2.7787107892874394e-05,
+      "loss": 1.4156,
+      "step": 1573
+    },
+    {
+      "epoch": 0.9061600460564191,
+      "grad_norm": 1.8182414770126343,
+      "learning_rate": 2.7694369242804907e-05,
+      "loss": 1.628,
+      "step": 1574
+    },
+    {
+      "epoch": 0.9067357512953368,
+      "grad_norm": 13.650918960571289,
+      "learning_rate": 2.7602161464540395e-05,
+      "loss": 1.4532,
+      "step": 1575
+    },
+    {
+      "epoch": 0.9073114565342545,
+      "grad_norm": 3.2630724906921387,
+      "learning_rate": 2.7510485152821548e-05,
+      "loss": 1.376,
+      "step": 1576
+    },
+    {
+      "epoch": 0.9078871617731722,
+      "grad_norm": 4.373472690582275,
+      "learning_rate": 2.7419340898961132e-05,
+      "loss": 1.5321,
+      "step": 1577
+    },
+    {
+      "epoch": 0.9084628670120898,
+      "grad_norm": 2.0004711151123047,
+      "learning_rate": 2.7328729290840127e-05,
+      "loss": 1.747,
+      "step": 1578
+    },
+    {
+      "epoch": 0.9090385722510075,
+      "grad_norm": 2.9218342304229736,
+      "learning_rate": 2.7238650912903956e-05,
+      "loss": 2.0486,
+      "step": 1579
+    },
+    {
+      "epoch": 0.9096142774899252,
+      "grad_norm": 2.9490227699279785,
+      "learning_rate": 2.7149106346158652e-05,
+      "loss": 1.6398,
+      "step": 1580
+    },
+    {
+      "epoch": 0.9101899827288429,
+      "grad_norm": 11.921220779418945,
+      "learning_rate": 2.7060096168167222e-05,
+      "loss": 1.7228,
+      "step": 1581
+    },
+    {
+      "epoch": 0.9107656879677605,
+      "grad_norm": 2.0314650535583496,
+      "learning_rate": 2.697162095304584e-05,
+      "loss": 1.7209,
+      "step": 1582
+    },
+    {
+      "epoch": 0.9113413932066782,
+      "grad_norm": 1.8610918521881104,
+      "learning_rate": 2.688368127146016e-05,
+      "loss": 1.886,
+      "step": 1583
+    },
+    {
+      "epoch": 0.9119170984455959,
+      "grad_norm": 2.199465274810791,
+      "learning_rate": 2.679627769062167e-05,
+      "loss": 1.4507,
+      "step": 1584
+    },
+    {
+      "epoch": 0.9124928036845136,
+      "grad_norm": 2.219393253326416,
+      "learning_rate": 2.670941077428395e-05,
+      "loss": 1.6459,
+      "step": 1585
+    },
+    {
+      "epoch": 0.9130685089234312,
+      "grad_norm": 2.5611228942871094,
+      "learning_rate": 2.6623081082739138e-05,
+      "loss": 1.5528,
+      "step": 1586
+    },
+    {
+      "epoch": 0.9136442141623489,
+      "grad_norm": 2.2698912620544434,
+      "learning_rate": 2.6537289172814268e-05,
+      "loss": 1.8762,
+      "step": 1587
+    },
+    {
+      "epoch": 0.9142199194012666,
+      "grad_norm": 1.809807300567627,
+      "learning_rate": 2.645203559786764e-05,
+      "loss": 1.8672,
+      "step": 1588
+    },
+    {
+      "epoch": 0.9147956246401843,
+      "grad_norm": 2.394334077835083,
+      "learning_rate": 2.6367320907785354e-05,
+      "loss": 1.8658,
+      "step": 1589
+    },
+    {
+      "epoch": 0.9153713298791019,
+      "grad_norm": 2.3083090782165527,
+      "learning_rate": 2.6283145648977615e-05,
+      "loss": 1.6307,
+      "step": 1590
+    },
+    {
+      "epoch": 0.9159470351180196,
+      "grad_norm": 2.8742313385009766,
+      "learning_rate": 2.619951036437537e-05,
+      "loss": 1.4434,
+      "step": 1591
+    },
+    {
+      "epoch": 0.9165227403569373,
+      "grad_norm": 5.4378814697265625,
+      "learning_rate": 2.6116415593426696e-05,
+      "loss": 1.819,
+      "step": 1592
+    },
+    {
+      "epoch": 0.917098445595855,
+      "grad_norm": 3.034571886062622,
+      "learning_rate": 2.603386187209335e-05,
+      "loss": 1.6265,
+      "step": 1593
+    },
+    {
+      "epoch": 0.9176741508347726,
+      "grad_norm": 2.155155658721924,
+      "learning_rate": 2.5951849732847334e-05,
+      "loss": 1.9646,
+      "step": 1594
+    },
+    {
+      "epoch": 0.9182498560736903,
+      "grad_norm": 1.7606446743011475,
+      "learning_rate": 2.5870379704667425e-05,
+      "loss": 2.1482,
+      "step": 1595
+    },
+    {
+      "epoch": 0.918825561312608,
+      "grad_norm": 4.015327453613281,
+      "learning_rate": 2.5789452313035774e-05,
+      "loss": 1.625,
+      "step": 1596
+    },
+    {
+      "epoch": 0.9194012665515257,
+      "grad_norm": 1.6838213205337524,
+      "learning_rate": 2.570906807993455e-05,
+      "loss": 2.0371,
+      "step": 1597
+    },
+    {
+      "epoch": 0.9199769717904432,
+      "grad_norm": 6.240045547485352,
+      "learning_rate": 2.5629227523842524e-05,
+      "loss": 1.4062,
+      "step": 1598
+    },
+    {
+      "epoch": 0.9205526770293609,
+      "grad_norm": 2.6227452754974365,
+      "learning_rate": 2.5549931159731778e-05,
+      "loss": 1.7335,
+      "step": 1599
+    },
+    {
+      "epoch": 0.9211283822682786,
+      "grad_norm": 3.019052505493164,
+      "learning_rate": 2.5471179499064294e-05,
+      "loss": 1.8169,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9217040875071963,
+      "grad_norm": 1.5943353176116943,
+      "learning_rate": 2.539297304978876e-05,
+      "loss": 1.896,
+      "step": 1601
+    },
+    {
+      "epoch": 0.9222797927461139,
+      "grad_norm": 2.934171438217163,
+      "learning_rate": 2.5315312316337252e-05,
+      "loss": 1.379,
+      "step": 1602
+    },
+    {
+      "epoch": 0.9228554979850316,
+      "grad_norm": 3.901970624923706,
+      "learning_rate": 2.523819779962194e-05,
+      "loss": 1.8632,
+      "step": 1603
+    },
+    {
+      "epoch": 0.9234312032239493,
+      "grad_norm": 2.195929765701294,
+      "learning_rate": 2.5161629997031944e-05,
+      "loss": 1.7058,
+      "step": 1604
+    },
+    {
+      "epoch": 0.924006908462867,
+      "grad_norm": 2.3955047130584717,
+      "learning_rate": 2.508560940243e-05,
+      "loss": 1.4185,
+      "step": 1605
+    },
+    {
+      "epoch": 0.9245826137017847,
+      "grad_norm": 2.9388465881347656,
+      "learning_rate": 2.501013650614941e-05,
+      "loss": 1.7711,
+      "step": 1606
+    },
+    {
+      "epoch": 0.9251583189407023,
+      "grad_norm": 2.6130528450012207,
+      "learning_rate": 2.4935211794990814e-05,
+      "loss": 1.9241,
+      "step": 1607
+    },
+    {
+      "epoch": 0.92573402417962,
+      "grad_norm": 2.5149128437042236,
+      "learning_rate": 2.4860835752219037e-05,
+      "loss": 1.6489,
+      "step": 1608
+    },
+    {
+      "epoch": 0.9263097294185377,
+      "grad_norm": 1.8280526399612427,
+      "learning_rate": 2.4787008857559985e-05,
+      "loss": 1.868,
+      "step": 1609
+    },
+    {
+      "epoch": 0.9268854346574554,
+      "grad_norm": 2.8214285373687744,
+      "learning_rate": 2.4713731587197576e-05,
+      "loss": 1.6348,
+      "step": 1610
+    },
+    {
+      "epoch": 0.927461139896373,
+      "grad_norm": 2.166651487350464,
+      "learning_rate": 2.464100441377062e-05,
+      "loss": 1.564,
+      "step": 1611
+    },
+    {
+      "epoch": 0.9280368451352907,
+      "grad_norm": 3.42960786819458,
+      "learning_rate": 2.456882780636984e-05,
+      "loss": 1.6368,
+      "step": 1612
+    },
+    {
+      "epoch": 0.9286125503742084,
+      "grad_norm": 3.0816545486450195,
+      "learning_rate": 2.4497202230534767e-05,
+      "loss": 1.584,
+      "step": 1613
+    },
+    {
+      "epoch": 0.9291882556131261,
+      "grad_norm": 3.077716588973999,
+      "learning_rate": 2.4426128148250772e-05,
+      "loss": 1.4579,
+      "step": 1614
+    },
+    {
+      "epoch": 0.9297639608520437,
+      "grad_norm": 2.8600645065307617,
+      "learning_rate": 2.4355606017946132e-05,
+      "loss": 1.7954,
+      "step": 1615
+    },
+    {
+      "epoch": 0.9303396660909614,
+      "grad_norm": 8.195825576782227,
+      "learning_rate": 2.4285636294489007e-05,
+      "loss": 1.9368,
+      "step": 1616
+    },
+    {
+      "epoch": 0.9309153713298791,
+      "grad_norm": 2.4190659523010254,
+      "learning_rate": 2.4216219429184505e-05,
+      "loss": 1.7215,
+      "step": 1617
+    },
+    {
+      "epoch": 0.9314910765687968,
+      "grad_norm": 2.667177200317383,
+      "learning_rate": 2.4147355869771823e-05,
+      "loss": 1.7393,
+      "step": 1618
+    },
+    {
+      "epoch": 0.9320667818077144,
+      "grad_norm": 2.0316147804260254,
+      "learning_rate": 2.4079046060421354e-05,
+      "loss": 1.4818,
+      "step": 1619
+    },
+    {
+      "epoch": 0.9326424870466321,
+      "grad_norm": 2.696448802947998,
+      "learning_rate": 2.4011290441731725e-05,
+      "loss": 1.5608,
+      "step": 1620
+    },
+    {
+      "epoch": 0.9332181922855498,
+      "grad_norm": 3.0991251468658447,
+      "learning_rate": 2.3944089450727105e-05,
+      "loss": 1.3969,
+      "step": 1621
+    },
+    {
+      "epoch": 0.9337938975244675,
+      "grad_norm": 4.551261901855469,
+      "learning_rate": 2.3877443520854285e-05,
+      "loss": 2.0114,
+      "step": 1622
+    },
+    {
+      "epoch": 0.9343696027633851,
+      "grad_norm": 2.6424806118011475,
+      "learning_rate": 2.3811353081979903e-05,
+      "loss": 1.7309,
+      "step": 1623
+    },
+    {
+      "epoch": 0.9349453080023028,
+      "grad_norm": 2.344975709915161,
+      "learning_rate": 2.374581856038768e-05,
+      "loss": 1.9615,
+      "step": 1624
+    },
+    {
+      "epoch": 0.9355210132412205,
+      "grad_norm": 2.182274103164673,
+      "learning_rate": 2.368084037877566e-05,
+      "loss": 1.5409,
+      "step": 1625
+    },
+    {
+      "epoch": 0.9360967184801382,
+      "grad_norm": 1.5671800374984741,
+      "learning_rate": 2.36164189562535e-05,
+      "loss": 1.5329,
+      "step": 1626
+    },
+    {
+      "epoch": 0.9366724237190558,
+      "grad_norm": 2.3709981441497803,
+      "learning_rate": 2.3552554708339762e-05,
+      "loss": 1.6425,
+      "step": 1627
+    },
+    {
+      "epoch": 0.9372481289579735,
+      "grad_norm": 1.7221273183822632,
+      "learning_rate": 2.348924804695924e-05,
+      "loss": 2.1214,
+      "step": 1628
+    },
+    {
+      "epoch": 0.9378238341968912,
+      "grad_norm": 7.530386447906494,
+      "learning_rate": 2.3426499380440244e-05,
+      "loss": 1.7609,
+      "step": 1629
+    },
+    {
+      "epoch": 0.9383995394358089,
+      "grad_norm": 3.001779794692993,
+      "learning_rate": 2.3364309113512055e-05,
+      "loss": 1.7659,
+      "step": 1630
+    },
+    {
+      "epoch": 0.9389752446747266,
+      "grad_norm": 18.927640914916992,
+      "learning_rate": 2.3302677647302263e-05,
+      "loss": 1.8659,
+      "step": 1631
+    },
+    {
+      "epoch": 0.9395509499136442,
+      "grad_norm": 1.6772960424423218,
+      "learning_rate": 2.3241605379334193e-05,
+      "loss": 2.0614,
+      "step": 1632
+    },
+    {
+      "epoch": 0.9401266551525619,
+      "grad_norm": 1.9646209478378296,
+      "learning_rate": 2.3181092703524335e-05,
+      "loss": 1.7435,
+      "step": 1633
+    },
+    {
+      "epoch": 0.9407023603914796,
+      "grad_norm": 2.128422498703003,
+      "learning_rate": 2.3121140010179795e-05,
+      "loss": 2.0111,
+      "step": 1634
+    },
+    {
+      "epoch": 0.9412780656303973,
+      "grad_norm": 2.581804037094116,
+      "learning_rate": 2.3061747685995807e-05,
+      "loss": 1.8062,
+      "step": 1635
+    },
+    {
+      "epoch": 0.9418537708693149,
+      "grad_norm": 7.562809467315674,
+      "learning_rate": 2.3002916114053213e-05,
+      "loss": 1.3657,
+      "step": 1636
+    },
+    {
+      "epoch": 0.9424294761082326,
+      "grad_norm": 1.8379217386245728,
+      "learning_rate": 2.2944645673815997e-05,
+      "loss": 1.6477,
+      "step": 1637
+    },
+    {
+      "epoch": 0.9430051813471503,
+      "grad_norm": 3.521094560623169,
+      "learning_rate": 2.288693674112885e-05,
+      "loss": 1.8025,
+      "step": 1638
+    },
+    {
+      "epoch": 0.943580886586068,
+      "grad_norm": 2.9809885025024414,
+      "learning_rate": 2.282978968821472e-05,
+      "loss": 1.7513,
+      "step": 1639
+    },
+    {
+      "epoch": 0.9441565918249856,
+      "grad_norm": 2.543513298034668,
+      "learning_rate": 2.277320488367245e-05,
+      "loss": 1.716,
+      "step": 1640
+    },
+    {
+      "epoch": 0.9447322970639033,
+      "grad_norm": 2.3292295932769775,
+      "learning_rate": 2.2717182692474345e-05,
+      "loss": 1.9099,
+      "step": 1641
+    },
+    {
+      "epoch": 0.945308002302821,
+      "grad_norm": 1.9723621606826782,
+      "learning_rate": 2.2661723475963876e-05,
+      "loss": 2.1615,
+      "step": 1642
+    },
+    {
+      "epoch": 0.9458837075417387,
+      "grad_norm": 2.1482696533203125,
+      "learning_rate": 2.2606827591853334e-05,
+      "loss": 1.8962,
+      "step": 1643
+    },
+    {
+      "epoch": 0.9464594127806563,
+      "grad_norm": 1.9180927276611328,
+      "learning_rate": 2.2552495394221467e-05,
+      "loss": 1.9678,
+      "step": 1644
+    },
+    {
+      "epoch": 0.947035118019574,
+      "grad_norm": 1.9327963590621948,
+      "learning_rate": 2.2498727233511302e-05,
+      "loss": 1.7332,
+      "step": 1645
+    },
+    {
+      "epoch": 0.9476108232584917,
+      "grad_norm": 3.8075265884399414,
+      "learning_rate": 2.2445523456527767e-05,
+      "loss": 1.6557,
+      "step": 1646
+    },
+    {
+      "epoch": 0.9481865284974094,
+      "grad_norm": 1.7101929187774658,
+      "learning_rate": 2.2392884406435543e-05,
+      "loss": 2.1128,
+      "step": 1647
+    },
+    {
+      "epoch": 0.948762233736327,
+      "grad_norm": 1.7822319269180298,
+      "learning_rate": 2.2340810422756836e-05,
+      "loss": 1.816,
+      "step": 1648
+    },
+    {
+      "epoch": 0.9493379389752447,
+      "grad_norm": 5.779254913330078,
+      "learning_rate": 2.228930184136912e-05,
+      "loss": 1.9192,
+      "step": 1649
+    },
+    {
+      "epoch": 0.9499136442141624,
+      "grad_norm": 2.4106295108795166,
+      "learning_rate": 2.2238358994503063e-05,
+      "loss": 1.7973,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9504893494530801,
+      "grad_norm": 2.4829814434051514,
+      "learning_rate": 2.2187982210740333e-05,
+      "loss": 1.6453,
+      "step": 1651
+    },
+    {
+      "epoch": 0.9510650546919976,
+      "grad_norm": 2.071115493774414,
+      "learning_rate": 2.2138171815011468e-05,
+      "loss": 1.488,
+      "step": 1652
+    },
+    {
+      "epoch": 0.9516407599309153,
+      "grad_norm": 26.930036544799805,
+      "learning_rate": 2.2088928128593843e-05,
+      "loss": 1.6709,
+      "step": 1653
+    },
+    {
+      "epoch": 0.952216465169833,
+      "grad_norm": 2.1612465381622314,
+      "learning_rate": 2.2040251469109495e-05,
+      "loss": 1.6311,
+      "step": 1654
+    },
+    {
+      "epoch": 0.9527921704087507,
+      "grad_norm": 3.163404941558838,
+      "learning_rate": 2.1992142150523176e-05,
+      "loss": 1.4744,
+      "step": 1655
+    },
+    {
+      "epoch": 0.9533678756476683,
+      "grad_norm": 2.483236312866211,
+      "learning_rate": 2.1944600483140278e-05,
+      "loss": 1.6517,
+      "step": 1656
+    },
+    {
+      "epoch": 0.953943580886586,
+      "grad_norm": 5.248150825500488,
+      "learning_rate": 2.1897626773604836e-05,
+      "loss": 1.6209,
+      "step": 1657
+    },
+    {
+      "epoch": 0.9545192861255037,
+      "grad_norm": 2.1589105129241943,
+      "learning_rate": 2.1851221324897565e-05,
+      "loss": 1.5809,
+      "step": 1658
+    },
+    {
+      "epoch": 0.9550949913644214,
+      "grad_norm": 1.8094933032989502,
+      "learning_rate": 2.1805384436333874e-05,
+      "loss": 1.9728,
+      "step": 1659
+    },
+    {
+      "epoch": 0.9556706966033391,
+      "grad_norm": 2.7613184452056885,
+      "learning_rate": 2.1760116403561952e-05,
+      "loss": 1.1957,
+      "step": 1660
+    },
+    {
+      "epoch": 0.9562464018422567,
+      "grad_norm": 2.1082611083984375,
+      "learning_rate": 2.171541751856089e-05,
+      "loss": 1.744,
+      "step": 1661
+    },
+    {
+      "epoch": 0.9568221070811744,
+      "grad_norm": 1.894872784614563,
+      "learning_rate": 2.167128806963877e-05,
+      "loss": 1.9222,
+      "step": 1662
+    },
+    {
+      "epoch": 0.9573978123200921,
+      "grad_norm": 2.93796706199646,
+      "learning_rate": 2.1627728341430785e-05,
+      "loss": 1.3205,
+      "step": 1663
+    },
+    {
+      "epoch": 0.9579735175590098,
+      "grad_norm": 10.441288948059082,
+      "learning_rate": 2.1584738614897443e-05,
+      "loss": 1.8898,
+      "step": 1664
+    },
+    {
+      "epoch": 0.9585492227979274,
+      "grad_norm": 2.859072208404541,
+      "learning_rate": 2.1542319167322733e-05,
+      "loss": 1.9356,
+      "step": 1665
+    },
+    {
+      "epoch": 0.9591249280368451,
+      "grad_norm": 2.527703046798706,
+      "learning_rate": 2.1500470272312348e-05,
+      "loss": 1.4273,
+      "step": 1666
+    },
+    {
+      "epoch": 0.9597006332757628,
+      "grad_norm": 2.4457950592041016,
+      "learning_rate": 2.1459192199791912e-05,
+      "loss": 1.7344,
+      "step": 1667
+    },
+    {
+      "epoch": 0.9602763385146805,
+      "grad_norm": 2.34979248046875,
+      "learning_rate": 2.1418485216005223e-05,
+      "loss": 1.7195,
+      "step": 1668
+    },
+    {
+      "epoch": 0.9608520437535981,
+      "grad_norm": 2.34717059135437,
+      "learning_rate": 2.1378349583512573e-05,
+      "loss": 1.58,
+      "step": 1669
+    },
+    {
+      "epoch": 0.9614277489925158,
+      "grad_norm": 2.3701369762420654,
+      "learning_rate": 2.1338785561189023e-05,
+      "loss": 2.1231,
+      "step": 1670
+    },
+    {
+      "epoch": 0.9620034542314335,
+      "grad_norm": 2.568822145462036,
+      "learning_rate": 2.129979340422277e-05,
+      "loss": 1.7789,
+      "step": 1671
+    },
+    {
+      "epoch": 0.9625791594703512,
+      "grad_norm": 1.8855364322662354,
+      "learning_rate": 2.1261373364113445e-05,
+      "loss": 1.8349,
+      "step": 1672
+    },
+    {
+      "epoch": 0.9631548647092688,
+      "grad_norm": 2.4160568714141846,
+      "learning_rate": 2.1223525688670525e-05,
+      "loss": 1.5641,
+      "step": 1673
+    },
+    {
+      "epoch": 0.9637305699481865,
+      "grad_norm": 2.138890266418457,
+      "learning_rate": 2.118625062201174e-05,
+      "loss": 2.0292,
+      "step": 1674
+    },
+    {
+      "epoch": 0.9643062751871042,
+      "grad_norm": 5.407046794891357,
+      "learning_rate": 2.114954840456152e-05,
+      "loss": 1.8162,
+      "step": 1675
+    },
+    {
+      "epoch": 0.9648819804260219,
+      "grad_norm": 8.997716903686523,
+      "learning_rate": 2.1113419273049347e-05,
+      "loss": 1.7905,
+      "step": 1676
+    },
+    {
+      "epoch": 0.9654576856649395,
+      "grad_norm": 6.042900085449219,
+      "learning_rate": 2.1077863460508356e-05,
+      "loss": 1.6091,
+      "step": 1677
+    },
+    {
+      "epoch": 0.9660333909038572,
+      "grad_norm": 2.089484214782715,
+      "learning_rate": 2.1042881196273746e-05,
+      "loss": 1.7954,
+      "step": 1678
+    },
+    {
+      "epoch": 0.9666090961427749,
+      "grad_norm": 8.689520835876465,
+      "learning_rate": 2.1008472705981318e-05,
+      "loss": 1.4159,
+      "step": 1679
+    },
+    {
+      "epoch": 0.9671848013816926,
+      "grad_norm": 2.4581947326660156,
+      "learning_rate": 2.0974638211566043e-05,
+      "loss": 1.8515,
+      "step": 1680
+    },
+    {
+      "epoch": 0.9677605066206102,
+      "grad_norm": 3.0923051834106445,
+      "learning_rate": 2.094137793126061e-05,
+      "loss": 1.8517,
+      "step": 1681
+    },
+    {
+      "epoch": 0.9683362118595279,
+      "grad_norm": 4.534923553466797,
+      "learning_rate": 2.090869207959403e-05,
+      "loss": 1.8189,
+      "step": 1682
+    },
+    {
+      "epoch": 0.9689119170984456,
+      "grad_norm": 17.9989013671875,
+      "learning_rate": 2.0876580867390223e-05,
+      "loss": 1.7087,
+      "step": 1683
+    },
+    {
+      "epoch": 0.9694876223373633,
+      "grad_norm": 13.498319625854492,
+      "learning_rate": 2.0845044501766714e-05,
+      "loss": 1.5246,
+      "step": 1684
+    },
+    {
+      "epoch": 0.970063327576281,
+      "grad_norm": 1.770861029624939,
+      "learning_rate": 2.0814083186133242e-05,
+      "loss": 1.9975,
+      "step": 1685
+    },
+    {
+      "epoch": 0.9706390328151986,
+      "grad_norm": 9.35171890258789,
+      "learning_rate": 2.078369712019047e-05,
+      "loss": 1.9534,
+      "step": 1686
+    },
+    {
+      "epoch": 0.9712147380541163,
+      "grad_norm": 4.246802806854248,
+      "learning_rate": 2.0753886499928725e-05,
+      "loss": 1.8388,
+      "step": 1687
+    },
+    {
+      "epoch": 0.971790443293034,
+      "grad_norm": 2.292266368865967,
+      "learning_rate": 2.0724651517626646e-05,
+      "loss": 2.018,
+      "step": 1688
+    },
+    {
+      "epoch": 0.9723661485319517,
+      "grad_norm": 2.2317075729370117,
+      "learning_rate": 2.069599236185007e-05,
+      "loss": 1.557,
+      "step": 1689
+    },
+    {
+      "epoch": 0.9729418537708693,
+      "grad_norm": 1.822417974472046,
+      "learning_rate": 2.0667909217450722e-05,
+      "loss": 2.0152,
+      "step": 1690
+    },
+    {
+      "epoch": 0.973517559009787,
+      "grad_norm": 2.128849506378174,
+      "learning_rate": 2.0640402265565045e-05,
+      "loss": 1.641,
+      "step": 1691
+    },
+    {
+      "epoch": 0.9740932642487047,
+      "grad_norm": 2.9787139892578125,
+      "learning_rate": 2.0613471683613027e-05,
+      "loss": 1.7885,
+      "step": 1692
+    },
+    {
+      "epoch": 0.9746689694876224,
+      "grad_norm": 2.338369131088257,
+      "learning_rate": 2.0587117645297094e-05,
+      "loss": 1.5801,
+      "step": 1693
+    },
+    {
+      "epoch": 0.97524467472654,
+      "grad_norm": 3.2537646293640137,
+      "learning_rate": 2.056134032060095e-05,
+      "loss": 1.592,
+      "step": 1694
+    },
+    {
+      "epoch": 0.9758203799654577,
+      "grad_norm": 2.961337089538574,
+      "learning_rate": 2.0536139875788487e-05,
+      "loss": 1.8043,
+      "step": 1695
+    },
+    {
+      "epoch": 0.9763960852043754,
+      "grad_norm": 2.1817891597747803,
+      "learning_rate": 2.051151647340272e-05,
+      "loss": 1.9847,
+      "step": 1696
+    },
+    {
+      "epoch": 0.9769717904432931,
+      "grad_norm": 1.955907940864563,
+      "learning_rate": 2.0487470272264746e-05,
+      "loss": 1.7351,
+      "step": 1697
+    },
+    {
+      "epoch": 0.9775474956822107,
+      "grad_norm": 2.760674476623535,
+      "learning_rate": 2.0464001427472702e-05,
+      "loss": 1.4975,
+      "step": 1698
+    },
+    {
+      "epoch": 0.9781232009211284,
+      "grad_norm": 4.867976188659668,
+      "learning_rate": 2.0441110090400788e-05,
+      "loss": 1.3526,
+      "step": 1699
+    },
+    {
+      "epoch": 0.9786989061600461,
+      "grad_norm": 1.6726274490356445,
+      "learning_rate": 2.0418796408698243e-05,
+      "loss": 1.9551,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9792746113989638,
+      "grad_norm": 2.014341354370117,
+      "learning_rate": 2.0397060526288457e-05,
+      "loss": 1.7735,
+      "step": 1701
+    },
+    {
+      "epoch": 0.9798503166378814,
+      "grad_norm": 4.674740314483643,
+      "learning_rate": 2.0375902583367994e-05,
+      "loss": 1.5233,
+      "step": 1702
+    },
+    {
+      "epoch": 0.9804260218767991,
+      "grad_norm": 4.285624980926514,
+      "learning_rate": 2.0355322716405716e-05,
+      "loss": 1.6072,
+      "step": 1703
+    },
+    {
+      "epoch": 0.9810017271157168,
+      "grad_norm": 3.051121234893799,
+      "learning_rate": 2.033532105814189e-05,
+      "loss": 1.8901,
+      "step": 1704
+    },
+    {
+      "epoch": 0.9815774323546345,
+      "grad_norm": 5.40238094329834,
+      "learning_rate": 2.0315897737587324e-05,
+      "loss": 1.5611,
+      "step": 1705
+    },
+    {
+      "epoch": 0.982153137593552,
+      "grad_norm": 2.2683660984039307,
+      "learning_rate": 2.0297052880022547e-05,
+      "loss": 1.7574,
+      "step": 1706
+    },
+    {
+      "epoch": 0.9827288428324698,
+      "grad_norm": 2.483015537261963,
+      "learning_rate": 2.0278786606997015e-05,
+      "loss": 1.6142,
+      "step": 1707
+    },
+    {
+      "epoch": 0.9833045480713875,
+      "grad_norm": 7.593777656555176,
+      "learning_rate": 2.0261099036328283e-05,
+      "loss": 1.404,
+      "step": 1708
+    },
+    {
+      "epoch": 0.9838802533103052,
+      "grad_norm": 2.8865814208984375,
+      "learning_rate": 2.0243990282101285e-05,
+      "loss": 1.6438,
+      "step": 1709
+    },
+    {
+      "epoch": 0.9844559585492227,
+      "grad_norm": 2.0971438884735107,
+      "learning_rate": 2.0227460454667604e-05,
+      "loss": 1.9595,
+      "step": 1710
+    },
+    {
+      "epoch": 0.9850316637881404,
+      "grad_norm": 3.2938170433044434,
+      "learning_rate": 2.0211509660644712e-05,
+      "loss": 1.9466,
+      "step": 1711
+    },
+    {
+      "epoch": 0.9856073690270581,
+      "grad_norm": 4.085682392120361,
+      "learning_rate": 2.0196138002915334e-05,
+      "loss": 1.3636,
+      "step": 1712
+    },
+    {
+      "epoch": 0.9861830742659758,
+      "grad_norm": 1.9215073585510254,
+      "learning_rate": 2.0181345580626736e-05,
+      "loss": 2.0688,
+      "step": 1713
+    },
+    {
+      "epoch": 0.9867587795048935,
+      "grad_norm": 1.8667635917663574,
+      "learning_rate": 2.0167132489190146e-05,
+      "loss": 1.8577,
+      "step": 1714
+    },
+    {
+      "epoch": 0.9873344847438111,
+      "grad_norm": 2.045741081237793,
+      "learning_rate": 2.0153498820280076e-05,
+      "loss": 2.0602,
+      "step": 1715
+    },
+    {
+      "epoch": 0.9879101899827288,
+      "grad_norm": 3.7126896381378174,
+      "learning_rate": 2.0140444661833786e-05,
+      "loss": 1.3585,
+      "step": 1716
+    },
+    {
+      "epoch": 0.9884858952216465,
+      "grad_norm": 2.8058650493621826,
+      "learning_rate": 2.0127970098050656e-05,
+      "loss": 1.5569,
+      "step": 1717
+    },
+    {
+      "epoch": 0.9890616004605642,
+      "grad_norm": 2.093524217605591,
+      "learning_rate": 2.011607520939171e-05,
+      "loss": 1.6079,
+      "step": 1718
+    },
+    {
+      "epoch": 0.9896373056994818,
+      "grad_norm": 5.721360683441162,
+      "learning_rate": 2.010476007257904e-05,
+      "loss": 1.582,
+      "step": 1719
+    },
+    {
+      "epoch": 0.9902130109383995,
+      "grad_norm": 1.9865312576293945,
+      "learning_rate": 2.0094024760595363e-05,
+      "loss": 1.7107,
+      "step": 1720
+    },
+    {
+      "epoch": 0.9907887161773172,
+      "grad_norm": 3.389556884765625,
+      "learning_rate": 2.0083869342683487e-05,
+      "loss": 1.4773,
+      "step": 1721
+    },
+    {
+      "epoch": 0.9913644214162349,
+      "grad_norm": 1.875075340270996,
+      "learning_rate": 2.0074293884345927e-05,
+      "loss": 1.5939,
+      "step": 1722
+    },
+    {
+      "epoch": 0.9919401266551525,
+      "grad_norm": 2.011084794998169,
+      "learning_rate": 2.0065298447344436e-05,
+      "loss": 1.8241,
+      "step": 1723
+    },
+    {
+      "epoch": 0.9925158318940702,
+      "grad_norm": 2.291151285171509,
+      "learning_rate": 2.0056883089699645e-05,
+      "loss": 2.1278,
+      "step": 1724
+    },
+    {
+      "epoch": 0.9930915371329879,
+      "grad_norm": 2.2964119911193848,
+      "learning_rate": 2.0049047865690667e-05,
+      "loss": 1.8182,
+      "step": 1725
+    },
+    {
+      "epoch": 0.9936672423719056,
+      "grad_norm": 3.768524646759033,
+      "learning_rate": 2.0041792825854718e-05,
+      "loss": 1.7508,
+      "step": 1726
+    },
+    {
+      "epoch": 0.9942429476108232,
+      "grad_norm": 2.3036274909973145,
+      "learning_rate": 2.0035118016986876e-05,
+      "loss": 2.0711,
+      "step": 1727
+    },
+    {
+      "epoch": 0.9948186528497409,
+      "grad_norm": 5.612923622131348,
+      "learning_rate": 2.0029023482139685e-05,
+      "loss": 1.714,
+      "step": 1728
+    },
+    {
+      "epoch": 0.9953943580886586,
+      "grad_norm": 1.937187671661377,
+      "learning_rate": 2.0023509260622924e-05,
+      "loss": 2.1367,
+      "step": 1729
+    },
+    {
+      "epoch": 0.9959700633275763,
+      "grad_norm": 8.280617713928223,
+      "learning_rate": 2.0018575388003364e-05,
+      "loss": 1.862,
+      "step": 1730
+    },
+    {
+      "epoch": 0.9965457685664939,
+      "grad_norm": 2.117215156555176,
+      "learning_rate": 2.0014221896104517e-05,
+      "loss": 1.8717,
+      "step": 1731
+    },
+    {
+      "epoch": 0.9971214738054116,
+      "grad_norm": 2.062620162963867,
+      "learning_rate": 2.0010448813006426e-05,
+      "loss": 2.1525,
+      "step": 1732
+    },
+    {
+      "epoch": 0.9976971790443293,
+      "grad_norm": 2.160541296005249,
+      "learning_rate": 2.0007256163045494e-05,
+      "loss": 1.6432,
+      "step": 1733
+    },
+    {
+      "epoch": 0.998272884283247,
+      "grad_norm": 2.272418975830078,
+      "learning_rate": 2.0004643966814332e-05,
+      "loss": 1.5717,
+      "step": 1734
+    },
+    {
+      "epoch": 0.9988485895221646,
+      "grad_norm": 8.458736419677734,
+      "learning_rate": 2.0002612241161634e-05,
+      "loss": 1.5472,
+      "step": 1735
+    },
+    {
+      "epoch": 0.9994242947610823,
+      "grad_norm": 2.1777946949005127,
+      "learning_rate": 2.0001160999192026e-05,
+      "loss": 1.3693,
+      "step": 1736
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6928577423095703,
+      "learning_rate": 2.0000290250266033e-05,
+      "loss": 2.1227,
+      "step": 1737
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1737,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 348,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0078479785288794e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}