diff --git "a/checkpoint-716/trainer_state.json" "b/checkpoint-716/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-716/trainer_state.json"
@@ -0,0 +1,5174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.99581589958159,
+  "eval_steps": 45,
+  "global_step": 716,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002789400278940028,
+      "grad_norm": 2.008944315843832,
+      "learning_rate": 0.0,
+      "loss": 1.7653,
+      "step": 1
+    },
+    {
+      "epoch": 0.002789400278940028,
+      "eval_loss": 1.7864996194839478,
+      "eval_runtime": 155.6922,
+      "eval_samples_per_second": 2.042,
+      "eval_steps_per_second": 0.128,
+      "step": 1
+    },
+    {
+      "epoch": 0.005578800557880056,
+      "grad_norm": 1.5986956798562522,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.3721,
+      "step": 2
+    },
+    {
+      "epoch": 0.008368200836820083,
+      "grad_norm": 2.487093074085383,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.4468,
+      "step": 3
+    },
+    {
+      "epoch": 0.011157601115760111,
+      "grad_norm": 1.9408908369837041,
+      "learning_rate": 1.5e-06,
+      "loss": 1.8555,
+      "step": 4
+    },
+    {
+      "epoch": 0.01394700139470014,
+      "grad_norm": 1.855397723025267,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.5173,
+      "step": 5
+    },
+    {
+      "epoch": 0.016736401673640166,
+      "grad_norm": 1.6798170163537172,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3812,
+      "step": 6
+    },
+    {
+      "epoch": 0.019525801952580194,
+      "grad_norm": 2.0478066370088133,
+      "learning_rate": 3e-06,
+      "loss": 1.475,
+      "step": 7
+    },
+    {
+      "epoch": 0.022315202231520222,
+      "grad_norm": 1.6541684745930123,
+      "learning_rate": 3.5e-06,
+      "loss": 1.6239,
+      "step": 8
+    },
+    {
+      "epoch": 0.02510460251046025,
+      "grad_norm": 1.5940373225900581,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4474,
+      "step": 9
+    },
+    {
+      "epoch": 0.02789400278940028,
+      "grad_norm": 1.3436762031717087,
+      "learning_rate": 4.5e-06,
+      "loss": 1.5277,
+      "step": 10
+    },
+    {
+      "epoch": 0.030683403068340307,
+      "grad_norm": 1.4820988105255548,
+      "learning_rate": 5e-06,
+      "loss": 1.3905,
+      "step": 11
+    },
+    {
+      "epoch": 0.03347280334728033,
+      "grad_norm": 1.3026823080341792,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 1.2716,
+      "step": 12
+    },
+    {
+      "epoch": 0.03626220362622036,
+      "grad_norm": 1.2786618249049673,
+      "learning_rate": 6e-06,
+      "loss": 1.4357,
+      "step": 13
+    },
+    {
+      "epoch": 0.03905160390516039,
+      "grad_norm": 1.4401448629219828,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 1.5418,
+      "step": 14
+    },
+    {
+      "epoch": 0.04184100418410042,
+      "grad_norm": 1.4108691585319235,
+      "learning_rate": 7e-06,
+      "loss": 1.419,
+      "step": 15
+    },
+    {
+      "epoch": 0.044630404463040445,
+      "grad_norm": 1.434665713671276,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.4042,
+      "step": 16
+    },
+    {
+      "epoch": 0.04741980474198047,
+      "grad_norm": 1.4864898541989087,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.4338,
+      "step": 17
+    },
+    {
+      "epoch": 0.0502092050209205,
+      "grad_norm": 1.7497952919365851,
+      "learning_rate": 8.5e-06,
+      "loss": 1.5988,
+      "step": 18
+    },
+    {
+      "epoch": 0.05299860529986053,
+      "grad_norm": 1.5825124800137,
+      "learning_rate": 9e-06,
+      "loss": 1.4817,
+      "step": 19
+    },
+    {
+      "epoch": 0.05578800557880056,
+      "grad_norm": 1.5639582937511203,
+      "learning_rate": 9.5e-06,
+      "loss": 1.3795,
+      "step": 20
+    },
+    {
+      "epoch": 0.058577405857740586,
+      "grad_norm": 1.5512627729747626,
+      "learning_rate": 1e-05,
+      "loss": 1.4833,
+      "step": 21
+    },
+    {
+      "epoch": 0.061366806136680614,
+      "grad_norm": 1.4462678614801439,
+      "learning_rate": 1.0500000000000001e-05,
+      "loss": 1.3781,
+      "step": 22
+    },
+    {
+      "epoch": 0.06415620641562064,
+      "grad_norm": 1.5995776178618928,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.4862,
+      "step": 23
+    },
+    {
+      "epoch": 0.06694560669456066,
+      "grad_norm": 1.2623925872690254,
+      "learning_rate": 1.15e-05,
+      "loss": 1.4222,
+      "step": 24
+    },
+    {
+      "epoch": 0.0697350069735007,
+      "grad_norm": 1.2816346894508914,
+      "learning_rate": 1.2e-05,
+      "loss": 1.3473,
+      "step": 25
+    },
+    {
+      "epoch": 0.07252440725244072,
+      "grad_norm": 1.4528035335148701,
+      "learning_rate": 1.25e-05,
+      "loss": 1.5278,
+      "step": 26
+    },
+    {
+      "epoch": 0.07531380753138076,
+      "grad_norm": 1.3415339044507064,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 1.3939,
+      "step": 27
+    },
+    {
+      "epoch": 0.07810320781032078,
+      "grad_norm": 1.6072610009319113,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 1.5401,
+      "step": 28
+    },
+    {
+      "epoch": 0.08089260808926081,
+      "grad_norm": 1.5988215139386146,
+      "learning_rate": 1.4e-05,
+      "loss": 1.3995,
+      "step": 29
+    },
+    {
+      "epoch": 0.08368200836820083,
+      "grad_norm": 1.4507828208303803,
+      "learning_rate": 1.45e-05,
+      "loss": 1.4584,
+      "step": 30
+    },
+    {
+      "epoch": 0.08647140864714087,
+      "grad_norm": 1.4975002404633069,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.3834,
+      "step": 31
+    },
+    {
+      "epoch": 0.08926080892608089,
+      "grad_norm": 1.4128570529331854,
+      "learning_rate": 1.55e-05,
+      "loss": 1.4216,
+      "step": 32
+    },
+    {
+      "epoch": 0.09205020920502092,
+      "grad_norm": 1.3616495178863832,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.5167,
+      "step": 33
+    },
+    {
+      "epoch": 0.09483960948396095,
+      "grad_norm": 1.1988790310990909,
+      "learning_rate": 1.65e-05,
+      "loss": 1.4525,
+      "step": 34
+    },
+    {
+      "epoch": 0.09762900976290098,
+      "grad_norm": 1.4483022749153813,
+      "learning_rate": 1.7e-05,
+      "loss": 1.5741,
+      "step": 35
+    },
+    {
+      "epoch": 0.100418410041841,
+      "grad_norm": 1.394589777246842,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.6437,
+      "step": 36
+    },
+    {
+      "epoch": 0.10320781032078104,
+      "grad_norm": 1.4186049044929165,
+      "learning_rate": 1.8e-05,
+      "loss": 1.5162,
+      "step": 37
+    },
+    {
+      "epoch": 0.10599721059972106,
+      "grad_norm": 1.4241876007622027,
+      "learning_rate": 1.8500000000000002e-05,
+      "loss": 1.2395,
+      "step": 38
+    },
+    {
+      "epoch": 0.1087866108786611,
+      "grad_norm": 1.3743075911034852,
+      "learning_rate": 1.9e-05,
+      "loss": 1.4631,
+      "step": 39
+    },
+    {
+      "epoch": 0.11157601115760112,
+      "grad_norm": 1.2863497247985725,
+      "learning_rate": 1.95e-05,
+      "loss": 1.3611,
+      "step": 40
+    },
+    {
+      "epoch": 0.11436541143654114,
+      "grad_norm": 1.3054075793205129,
+      "learning_rate": 2e-05,
+      "loss": 1.2375,
+      "step": 41
+    },
+    {
+      "epoch": 0.11715481171548117,
+      "grad_norm": 1.447249035073335,
+      "learning_rate": 1.9999892011980525e-05,
+      "loss": 1.4044,
+      "step": 42
+    },
+    {
+      "epoch": 0.1199442119944212,
+      "grad_norm": 1.3461748028257197,
+      "learning_rate": 1.9999568050254373e-05,
+      "loss": 1.4081,
+      "step": 43
+    },
+    {
+      "epoch": 0.12273361227336123,
+      "grad_norm": 1.6035229132022362,
+      "learning_rate": 1.999902812181835e-05,
+      "loss": 1.4167,
+      "step": 44
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "grad_norm": 1.7750306011999208,
+      "learning_rate": 1.9998272238333606e-05,
+      "loss": 1.3533,
+      "step": 45
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "eval_loss": 1.6828460693359375,
+      "eval_runtime": 158.4193,
+      "eval_samples_per_second": 2.007,
+      "eval_steps_per_second": 0.126,
+      "step": 45
+    },
+    {
+      "epoch": 0.12831241283124128,
+      "grad_norm": 1.354470787639867,
+      "learning_rate": 1.9997300416125426e-05,
+      "loss": 1.3901,
+      "step": 46
+    },
+    {
+      "epoch": 0.13110181311018132,
+      "grad_norm": 1.23248602443203,
+      "learning_rate": 1.999611267618283e-05,
+      "loss": 1.3485,
+      "step": 47
+    },
+    {
+      "epoch": 0.13389121338912133,
+      "grad_norm": 1.314827114627873,
+      "learning_rate": 1.9994709044158157e-05,
+      "loss": 1.3195,
+      "step": 48
+    },
+    {
+      "epoch": 0.13668061366806136,
+      "grad_norm": 1.3741001015735983,
+      "learning_rate": 1.99930895503665e-05,
+      "loss": 1.4394,
+      "step": 49
+    },
+    {
+      "epoch": 0.1394700139470014,
+      "grad_norm": 1.1624406309888304,
+      "learning_rate": 1.9991254229785043e-05,
+      "loss": 1.2943,
+      "step": 50
+    },
+    {
+      "epoch": 0.14225941422594143,
+      "grad_norm": 1.431188759221728,
+      "learning_rate": 1.998920312205231e-05,
+      "loss": 1.4614,
+      "step": 51
+    },
+    {
+      "epoch": 0.14504881450488144,
+      "grad_norm": 1.2513371987994648,
+      "learning_rate": 1.9986936271467316e-05,
+      "loss": 1.328,
+      "step": 52
+    },
+    {
+      "epoch": 0.14783821478382148,
+      "grad_norm": 1.6084481811469094,
+      "learning_rate": 1.99844537269886e-05,
+      "loss": 1.4579,
+      "step": 53
+    },
+    {
+      "epoch": 0.1506276150627615,
+      "grad_norm": 1.3643143080926854,
+      "learning_rate": 1.9981755542233175e-05,
+      "loss": 1.4471,
+      "step": 54
+    },
+    {
+      "epoch": 0.15341701534170155,
+      "grad_norm": 1.443453372098446,
+      "learning_rate": 1.9978841775475368e-05,
+      "loss": 1.3931,
+      "step": 55
+    },
+    {
+      "epoch": 0.15620641562064155,
+      "grad_norm": 1.186174044031903,
+      "learning_rate": 1.997571248964556e-05,
+      "loss": 1.2935,
+      "step": 56
+    },
+    {
+      "epoch": 0.1589958158995816,
+      "grad_norm": 1.3967845728055575,
+      "learning_rate": 1.9972367752328824e-05,
+      "loss": 1.3819,
+      "step": 57
+    },
+    {
+      "epoch": 0.16178521617852162,
+      "grad_norm": 1.585201984076838,
+      "learning_rate": 1.9968807635763472e-05,
+      "loss": 1.5391,
+      "step": 58
+    },
+    {
+      "epoch": 0.16457461645746166,
+      "grad_norm": 1.515327450581085,
+      "learning_rate": 1.9965032216839493e-05,
+      "loss": 1.3969,
+      "step": 59
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 1.3595894447160555,
+      "learning_rate": 1.996104157709689e-05,
+      "loss": 1.3598,
+      "step": 60
+    },
+    {
+      "epoch": 0.1701534170153417,
+      "grad_norm": 1.4252798961269173,
+      "learning_rate": 1.9956835802723916e-05,
+      "loss": 1.447,
+      "step": 61
+    },
+    {
+      "epoch": 0.17294281729428174,
+      "grad_norm": 1.4269613254937963,
+      "learning_rate": 1.9952414984555225e-05,
+      "loss": 1.4354,
+      "step": 62
+    },
+    {
+      "epoch": 0.17573221757322174,
+      "grad_norm": 1.5984564978735487,
+      "learning_rate": 1.994777921806989e-05,
+      "loss": 1.5493,
+      "step": 63
+    },
+    {
+      "epoch": 0.17852161785216178,
+      "grad_norm": 1.5396475514798837,
+      "learning_rate": 1.9942928603389366e-05,
+      "loss": 1.4095,
+      "step": 64
+    },
+    {
+      "epoch": 0.18131101813110181,
+      "grad_norm": 1.381818615640278,
+      "learning_rate": 1.9937863245275303e-05,
+      "loss": 1.381,
+      "step": 65
+    },
+    {
+      "epoch": 0.18410041841004185,
+      "grad_norm": 1.3411933307262995,
+      "learning_rate": 1.9932583253127302e-05,
+      "loss": 1.4514,
+      "step": 66
+    },
+    {
+      "epoch": 0.18688981868898186,
+      "grad_norm": 1.4666636741675445,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 1.378,
+      "step": 67
+    },
+    {
+      "epoch": 0.1896792189679219,
+      "grad_norm": 1.321297415086869,
+      "learning_rate": 1.9921379827503316e-05,
+      "loss": 1.3916,
+      "step": 68
+    },
+    {
+      "epoch": 0.19246861924686193,
+      "grad_norm": 1.3031514888132292,
+      "learning_rate": 1.991545663599448e-05,
+      "loss": 1.3568,
+      "step": 69
+    },
+    {
+      "epoch": 0.19525801952580196,
+      "grad_norm": 1.3252501098302665,
+      "learning_rate": 1.990931929438078e-05,
+      "loss": 1.3691,
+      "step": 70
+    },
+    {
+      "epoch": 0.19804741980474197,
+      "grad_norm": 1.3190300203004819,
+      "learning_rate": 1.990296793521408e-05,
+      "loss": 1.425,
+      "step": 71
+    },
+    {
+      "epoch": 0.200836820083682,
+      "grad_norm": 1.221728638105595,
+      "learning_rate": 1.989640269566853e-05,
+      "loss": 1.3669,
+      "step": 72
+    },
+    {
+      "epoch": 0.20362622036262204,
+      "grad_norm": 1.2519446160682244,
+      "learning_rate": 1.9889623717537564e-05,
+      "loss": 1.5065,
+      "step": 73
+    },
+    {
+      "epoch": 0.20641562064156208,
+      "grad_norm": 1.3192555240060455,
+      "learning_rate": 1.9882631147230874e-05,
+      "loss": 1.3077,
+      "step": 74
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 1.811281511932427,
+      "learning_rate": 1.987542513577122e-05,
+      "loss": 1.4737,
+      "step": 75
+    },
+    {
+      "epoch": 0.21199442119944212,
+      "grad_norm": 1.2107466822843787,
+      "learning_rate": 1.9868005838791185e-05,
+      "loss": 1.3632,
+      "step": 76
+    },
+    {
+      "epoch": 0.21478382147838215,
+      "grad_norm": 1.4506886695952612,
+      "learning_rate": 1.9860373416529804e-05,
+      "loss": 1.3707,
+      "step": 77
+    },
+    {
+      "epoch": 0.2175732217573222,
+      "grad_norm": 1.129475911714987,
+      "learning_rate": 1.985252803382911e-05,
+      "loss": 1.2879,
+      "step": 78
+    },
+    {
+      "epoch": 0.2203626220362622,
+      "grad_norm": 1.2378410441125478,
+      "learning_rate": 1.984446986013057e-05,
+      "loss": 1.4352,
+      "step": 79
+    },
+    {
+      "epoch": 0.22315202231520223,
+      "grad_norm": 1.2497274548196218,
+      "learning_rate": 1.983619906947144e-05,
+      "loss": 1.2929,
+      "step": 80
+    },
+    {
+      "epoch": 0.22594142259414227,
+      "grad_norm": 1.2860272115066647,
+      "learning_rate": 1.9827715840480962e-05,
+      "loss": 1.2595,
+      "step": 81
+    },
+    {
+      "epoch": 0.22873082287308227,
+      "grad_norm": 1.3259601590310435,
+      "learning_rate": 1.9819020356376562e-05,
+      "loss": 1.5421,
+      "step": 82
+    },
+    {
+      "epoch": 0.2315202231520223,
+      "grad_norm": 1.3823289295025785,
+      "learning_rate": 1.9810112804959867e-05,
+      "loss": 1.4379,
+      "step": 83
+    },
+    {
+      "epoch": 0.23430962343096234,
+      "grad_norm": 1.2790636696723037,
+      "learning_rate": 1.980099337861264e-05,
+      "loss": 1.4045,
+      "step": 84
+    },
+    {
+      "epoch": 0.23709902370990238,
+      "grad_norm": 1.2621634213682735,
+      "learning_rate": 1.9791662274292638e-05,
+      "loss": 1.3433,
+      "step": 85
+    },
+    {
+      "epoch": 0.2398884239888424,
+      "grad_norm": 1.4041226411604562,
+      "learning_rate": 1.9782119693529358e-05,
+      "loss": 1.6292,
+      "step": 86
+    },
+    {
+      "epoch": 0.24267782426778242,
+      "grad_norm": 1.4238393471976662,
+      "learning_rate": 1.977236584241968e-05,
+      "loss": 1.398,
+      "step": 87
+    },
+    {
+      "epoch": 0.24546722454672246,
+      "grad_norm": 1.3721757997449184,
+      "learning_rate": 1.9762400931623413e-05,
+      "loss": 1.372,
+      "step": 88
+    },
+    {
+      "epoch": 0.2482566248256625,
+      "grad_norm": 1.3049726438204359,
+      "learning_rate": 1.9752225176358757e-05,
+      "loss": 1.4366,
+      "step": 89
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "grad_norm": 1.319316702022308,
+      "learning_rate": 1.9741838796397638e-05,
+      "loss": 1.2807,
+      "step": 90
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "eval_loss": 1.6544907093048096,
+      "eval_runtime": 157.4295,
+      "eval_samples_per_second": 2.02,
+      "eval_steps_per_second": 0.127,
+      "step": 90
+    },
+    {
+      "epoch": 0.25383542538354253,
+      "grad_norm": 1.3259568867589984,
+      "learning_rate": 1.9731242016060985e-05,
+      "loss": 1.3566,
+      "step": 91
+    },
+    {
+      "epoch": 0.25662482566248257,
+      "grad_norm": 1.3318698765554446,
+      "learning_rate": 1.972043506421386e-05,
+      "loss": 1.3304,
+      "step": 92
+    },
+    {
+      "epoch": 0.2594142259414226,
+      "grad_norm": 1.210762982291795,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 1.3663,
+      "step": 93
+    },
+    {
+      "epoch": 0.26220362622036264,
+      "grad_norm": 1.322366639833671,
+      "learning_rate": 1.9698191584139402e-05,
+      "loss": 1.4099,
+      "step": 94
+    },
+    {
+      "epoch": 0.2649930264993027,
+      "grad_norm": 1.286954377653034,
+      "learning_rate": 1.9686755536317945e-05,
+      "loss": 1.3539,
+      "step": 95
+    },
+    {
+      "epoch": 0.26778242677824265,
+      "grad_norm": 1.1590651579123286,
+      "learning_rate": 1.967511027778738e-05,
+      "loss": 1.2147,
+      "step": 96
+    },
+    {
+      "epoch": 0.2705718270571827,
+      "grad_norm": 1.3100829080105303,
+      "learning_rate": 1.9663256060057395e-05,
+      "loss": 1.4093,
+      "step": 97
+    },
+    {
+      "epoch": 0.2733612273361227,
+      "grad_norm": 1.346265752760783,
+      "learning_rate": 1.965119313915068e-05,
+      "loss": 1.491,
+      "step": 98
+    },
+    {
+      "epoch": 0.27615062761506276,
+      "grad_norm": 1.378168477135006,
+      "learning_rate": 1.9638921775597428e-05,
+      "loss": 1.5049,
+      "step": 99
+    },
+    {
+      "epoch": 0.2789400278940028,
+      "grad_norm": 1.4182107155054933,
+      "learning_rate": 1.9626442234429684e-05,
+      "loss": 1.5013,
+      "step": 100
+    },
+    {
+      "epoch": 0.28172942817294283,
+      "grad_norm": 1.3165711654218712,
+      "learning_rate": 1.961375478517564e-05,
+      "loss": 1.5105,
+      "step": 101
+    },
+    {
+      "epoch": 0.28451882845188287,
+      "grad_norm": 1.364780296172199,
+      "learning_rate": 1.9600859701853796e-05,
+      "loss": 1.5207,
+      "step": 102
+    },
+    {
+      "epoch": 0.28730822873082285,
+      "grad_norm": 1.2988922679076684,
+      "learning_rate": 1.958775726296706e-05,
+      "loss": 1.2881,
+      "step": 103
+    },
+    {
+      "epoch": 0.2900976290097629,
+      "grad_norm": 1.3450528168801636,
+      "learning_rate": 1.9574447751496706e-05,
+      "loss": 1.2877,
+      "step": 104
+    },
+    {
+      "epoch": 0.2928870292887029,
+      "grad_norm": 1.4142239844479165,
+      "learning_rate": 1.95609314548963e-05,
+      "loss": 1.5604,
+      "step": 105
+    },
+    {
+      "epoch": 0.29567642956764295,
+      "grad_norm": 1.3452993293539794,
+      "learning_rate": 1.954720866508546e-05,
+      "loss": 1.3447,
+      "step": 106
+    },
+    {
+      "epoch": 0.298465829846583,
+      "grad_norm": 1.4534491830895881,
+      "learning_rate": 1.953327967844356e-05,
+      "loss": 1.3643,
+      "step": 107
+    },
+    {
+      "epoch": 0.301255230125523,
+      "grad_norm": 1.350966370835706,
+      "learning_rate": 1.9519144795803342e-05,
+      "loss": 1.5196,
+      "step": 108
+    },
+    {
+      "epoch": 0.30404463040446306,
+      "grad_norm": 1.3487778511447879,
+      "learning_rate": 1.95048043224444e-05,
+      "loss": 1.4243,
+      "step": 109
+    },
+    {
+      "epoch": 0.3068340306834031,
+      "grad_norm": 1.3479508491141639,
+      "learning_rate": 1.94902585680866e-05,
+      "loss": 1.2869,
+      "step": 110
+    },
+    {
+      "epoch": 0.30962343096234307,
+      "grad_norm": 1.5555627133101146,
+      "learning_rate": 1.9475507846883377e-05,
+      "loss": 1.4626,
+      "step": 111
+    },
+    {
+      "epoch": 0.3124128312412831,
+      "grad_norm": 1.264890715784298,
+      "learning_rate": 1.9460552477414972e-05,
+      "loss": 1.2826,
+      "step": 112
+    },
+    {
+      "epoch": 0.31520223152022314,
+      "grad_norm": 1.2628748380778831,
+      "learning_rate": 1.9445392782681523e-05,
+      "loss": 1.232,
+      "step": 113
+    },
+    {
+      "epoch": 0.3179916317991632,
+      "grad_norm": 1.3550404859387195,
+      "learning_rate": 1.9430029090096118e-05,
+      "loss": 1.3034,
+      "step": 114
+    },
+    {
+      "epoch": 0.3207810320781032,
+      "grad_norm": 1.1496127251687267,
+      "learning_rate": 1.94144617314777e-05,
+      "loss": 1.3215,
+      "step": 115
+    },
+    {
+      "epoch": 0.32357043235704325,
+      "grad_norm": 1.3116085375581363,
+      "learning_rate": 1.939869104304392e-05,
+      "loss": 1.4154,
+      "step": 116
+    },
+    {
+      "epoch": 0.3263598326359833,
+      "grad_norm": 1.2589366985022925,
+      "learning_rate": 1.9382717365403854e-05,
+      "loss": 1.517,
+      "step": 117
+    },
+    {
+      "epoch": 0.3291492329149233,
+      "grad_norm": 1.3051575397158521,
+      "learning_rate": 1.9366541043550667e-05,
+      "loss": 1.3795,
+      "step": 118
+    },
+    {
+      "epoch": 0.3319386331938633,
+      "grad_norm": 1.514184766493585,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 1.5974,
+      "step": 119
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 1.3773144705212048,
+      "learning_rate": 1.933358186905318e-05,
+      "loss": 1.3696,
+      "step": 120
+    },
+    {
+      "epoch": 0.33751743375174337,
+      "grad_norm": 1.070700275666401,
+      "learning_rate": 1.9316799728248074e-05,
+      "loss": 1.1661,
+      "step": 121
+    },
+    {
+      "epoch": 0.3403068340306834,
+      "grad_norm": 1.4181760004495874,
+      "learning_rate": 1.9299816366892865e-05,
+      "loss": 1.4376,
+      "step": 122
+    },
+    {
+      "epoch": 0.34309623430962344,
+      "grad_norm": 1.6034791315185046,
+      "learning_rate": 1.9282632151787462e-05,
+      "loss": 1.5891,
+      "step": 123
+    },
+    {
+      "epoch": 0.3458856345885635,
+      "grad_norm": 1.1884570183288778,
+      "learning_rate": 1.9265247454069736e-05,
+      "loss": 1.3432,
+      "step": 124
+    },
+    {
+      "epoch": 0.3486750348675035,
+      "grad_norm": 1.477555714731358,
+      "learning_rate": 1.924766264920751e-05,
+      "loss": 1.3683,
+      "step": 125
+    },
+    {
+      "epoch": 0.3514644351464435,
+      "grad_norm": 1.2504857458807423,
+      "learning_rate": 1.922987811699042e-05,
+      "loss": 1.2643,
+      "step": 126
+    },
+    {
+      "epoch": 0.3542538354253835,
+      "grad_norm": 1.3679090790056112,
+      "learning_rate": 1.9211894241521757e-05,
+      "loss": 1.5962,
+      "step": 127
+    },
+    {
+      "epoch": 0.35704323570432356,
+      "grad_norm": 1.2309836816544464,
+      "learning_rate": 1.9193711411210138e-05,
+      "loss": 1.3361,
+      "step": 128
+    },
+    {
+      "epoch": 0.3598326359832636,
+      "grad_norm": 1.1714321663378802,
+      "learning_rate": 1.917533001876113e-05,
+      "loss": 1.3019,
+      "step": 129
+    },
+    {
+      "epoch": 0.36262203626220363,
+      "grad_norm": 1.2813447334304535,
+      "learning_rate": 1.9156750461168768e-05,
+      "loss": 1.4319,
+      "step": 130
+    },
+    {
+      "epoch": 0.36541143654114366,
+      "grad_norm": 1.427767209588848,
+      "learning_rate": 1.9137973139706973e-05,
+      "loss": 1.4712,
+      "step": 131
+    },
+    {
+      "epoch": 0.3682008368200837,
+      "grad_norm": 1.3426640935974619,
+      "learning_rate": 1.91189984599209e-05,
+      "loss": 1.4397,
+      "step": 132
+    },
+    {
+      "epoch": 0.37099023709902373,
+      "grad_norm": 1.3173830250699687,
+      "learning_rate": 1.9099826831618168e-05,
+      "loss": 1.4799,
+      "step": 133
+    },
+    {
+      "epoch": 0.3737796373779637,
+      "grad_norm": 1.5260053920559482,
+      "learning_rate": 1.908045866886001e-05,
+      "loss": 1.5167,
+      "step": 134
+    },
+    {
+      "epoch": 0.37656903765690375,
+      "grad_norm": 1.2838799058228236,
+      "learning_rate": 1.9060894389952328e-05,
+      "loss": 1.3957,
+      "step": 135
+    },
+    {
+      "epoch": 0.37656903765690375,
+      "eval_loss": 1.629968523979187,
+      "eval_runtime": 155.8796,
+      "eval_samples_per_second": 2.04,
+      "eval_steps_per_second": 0.128,
+      "step": 135
+    },
+    {
+      "epoch": 0.3793584379358438,
+      "grad_norm": 1.2595723963522658,
+      "learning_rate": 1.9041134417436674e-05,
+      "loss": 1.3773,
+      "step": 136
+    },
+    {
+      "epoch": 0.3821478382147838,
+      "grad_norm": 1.380977078216302,
+      "learning_rate": 1.9021179178081107e-05,
+      "loss": 1.5358,
+      "step": 137
+    },
+    {
+      "epoch": 0.38493723849372385,
+      "grad_norm": 1.3245015694120374,
+      "learning_rate": 1.9001029102870982e-05,
+      "loss": 1.506,
+      "step": 138
+    },
+    {
+      "epoch": 0.3877266387726639,
+      "grad_norm": 1.2602456347612,
+      "learning_rate": 1.898068462699964e-05,
+      "loss": 1.4246,
+      "step": 139
+    },
+    {
+      "epoch": 0.3905160390516039,
+      "grad_norm": 1.3989105118625398,
+      "learning_rate": 1.8960146189859014e-05,
+      "loss": 1.4692,
+      "step": 140
+    },
+    {
+      "epoch": 0.39330543933054396,
+      "grad_norm": 1.2616111800783727,
+      "learning_rate": 1.8939414235030137e-05,
+      "loss": 1.3755,
+      "step": 141
+    },
+    {
+      "epoch": 0.39609483960948394,
+      "grad_norm": 1.2686523296470786,
+      "learning_rate": 1.891848921027355e-05,
+      "loss": 1.3442,
+      "step": 142
+    },
+    {
+      "epoch": 0.398884239888424,
+      "grad_norm": 1.37417212405681,
+      "learning_rate": 1.889737156751965e-05,
+      "loss": 1.3651,
+      "step": 143
+    },
+    {
+      "epoch": 0.401673640167364,
+      "grad_norm": 1.373244156828418,
+      "learning_rate": 1.887606176285893e-05,
+      "loss": 1.4961,
+      "step": 144
+    },
+    {
+      "epoch": 0.40446304044630405,
+      "grad_norm": 1.1872961109156253,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 1.2587,
+      "step": 145
+    },
+    {
+      "epoch": 0.4072524407252441,
+      "grad_norm": 1.313036403643509,
+      "learning_rate": 1.883286751292018e-05,
+      "loss": 1.4575,
+      "step": 146
+    },
+    {
+      "epoch": 0.4100418410041841,
+      "grad_norm": 1.390974479025736,
+      "learning_rate": 1.8810984000534457e-05,
+      "loss": 1.3891,
+      "step": 147
+    },
+    {
+      "epoch": 0.41283124128312415,
+      "grad_norm": 1.3368020257438076,
+      "learning_rate": 1.8788910192006363e-05,
+      "loss": 1.3415,
+      "step": 148
+    },
+    {
+      "epoch": 0.41562064156206413,
+      "grad_norm": 1.2329515511987332,
+      "learning_rate": 1.8766646564077265e-05,
+      "loss": 1.3339,
+      "step": 149
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 1.276208090352136,
+      "learning_rate": 1.8744193597588185e-05,
+      "loss": 1.4495,
+      "step": 150
+    },
+    {
+      "epoch": 0.4211994421199442,
+      "grad_norm": 1.1548092334953926,
+      "learning_rate": 1.8721551777469397e-05,
+      "loss": 1.2099,
+      "step": 151
+    },
+    {
+      "epoch": 0.42398884239888424,
+      "grad_norm": 1.3184986062317001,
+      "learning_rate": 1.869872159272997e-05,
+      "loss": 1.2136,
+      "step": 152
+    },
+    {
+      "epoch": 0.42677824267782427,
+      "grad_norm": 1.1962726760049636,
+      "learning_rate": 1.8675703536447178e-05,
+      "loss": 1.2598,
+      "step": 153
+    },
+    {
+      "epoch": 0.4295676429567643,
+      "grad_norm": 1.3302312487017707,
+      "learning_rate": 1.8652498105755898e-05,
+      "loss": 1.3719,
+      "step": 154
+    },
+    {
+      "epoch": 0.43235704323570434,
+      "grad_norm": 1.55872330252289,
+      "learning_rate": 1.862910580183782e-05,
+      "loss": 1.4867,
+      "step": 155
+    },
+    {
+      "epoch": 0.4351464435146444,
+      "grad_norm": 1.3004017172912832,
+      "learning_rate": 1.8605527129910663e-05,
+      "loss": 1.3089,
+      "step": 156
+    },
+    {
+      "epoch": 0.43793584379358436,
+      "grad_norm": 1.2650294480346138,
+      "learning_rate": 1.858176259921724e-05,
+      "loss": 1.2856,
+      "step": 157
+    },
+    {
+      "epoch": 0.4407252440725244,
+      "grad_norm": 1.414189467122214,
+      "learning_rate": 1.8557812723014476e-05,
+      "loss": 1.4827,
+      "step": 158
+    },
+    {
+      "epoch": 0.4435146443514644,
+      "grad_norm": 1.2634959665686347,
+      "learning_rate": 1.853367801856231e-05,
+      "loss": 1.3568,
+      "step": 159
+    },
+    {
+      "epoch": 0.44630404463040446,
+      "grad_norm": 1.3164047095667806,
+      "learning_rate": 1.8509359007112523e-05,
+      "loss": 1.5306,
+      "step": 160
+    },
+    {
+      "epoch": 0.4490934449093445,
+      "grad_norm": 1.3232600329575266,
+      "learning_rate": 1.8484856213897496e-05,
+      "loss": 1.4279,
+      "step": 161
+    },
+    {
+      "epoch": 0.45188284518828453,
+      "grad_norm": 1.286194256752095,
+      "learning_rate": 1.8460170168118857e-05,
+      "loss": 1.2656,
+      "step": 162
+    },
+    {
+      "epoch": 0.45467224546722457,
+      "grad_norm": 1.393553888811773,
+      "learning_rate": 1.843530140293603e-05,
+      "loss": 1.4003,
+      "step": 163
+    },
+    {
+      "epoch": 0.45746164574616455,
+      "grad_norm": 1.2952418440030533,
+      "learning_rate": 1.841025045545477e-05,
+      "loss": 1.365,
+      "step": 164
+    },
+    {
+      "epoch": 0.4602510460251046,
+      "grad_norm": 1.2556167978994803,
+      "learning_rate": 1.8385017866715507e-05,
+      "loss": 1.3313,
+      "step": 165
+    },
+    {
+      "epoch": 0.4630404463040446,
+      "grad_norm": 1.3067564204278406,
+      "learning_rate": 1.8359604181681703e-05,
+      "loss": 1.4114,
+      "step": 166
+    },
+    {
+      "epoch": 0.46582984658298465,
+      "grad_norm": 1.2088590174928828,
+      "learning_rate": 1.833400994922806e-05,
+      "loss": 1.1866,
+      "step": 167
+    },
+    {
+      "epoch": 0.4686192468619247,
+      "grad_norm": 1.334753865529686,
+      "learning_rate": 1.8308235722128674e-05,
+      "loss": 1.2744,
+      "step": 168
+    },
+    {
+      "epoch": 0.4714086471408647,
+      "grad_norm": 1.3612556693462265,
+      "learning_rate": 1.8282282057045087e-05,
+      "loss": 1.3558,
+      "step": 169
+    },
+    {
+      "epoch": 0.47419804741980476,
+      "grad_norm": 1.2660924285869366,
+      "learning_rate": 1.8256149514514284e-05,
+      "loss": 1.2804,
+      "step": 170
+    },
+    {
+      "epoch": 0.4769874476987448,
+      "grad_norm": 1.3192403133250346,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 1.3874,
+      "step": 171
+    },
+    {
+      "epoch": 0.4797768479776848,
+      "grad_norm": 1.3924722985838183,
+      "learning_rate": 1.8203350058563366e-05,
+      "loss": 1.5013,
+      "step": 172
+    },
+    {
+      "epoch": 0.4825662482566248,
+      "grad_norm": 1.2874077296032287,
+      "learning_rate": 1.8176684285484985e-05,
+      "loss": 1.3261,
+      "step": 173
+    },
+    {
+      "epoch": 0.48535564853556484,
+      "grad_norm": 1.309597924994118,
+      "learning_rate": 1.814984191561823e-05,
+      "loss": 1.4157,
+      "step": 174
+    },
+    {
+      "epoch": 0.4881450488145049,
+      "grad_norm": 1.1912282212302885,
+      "learning_rate": 1.8122823528693966e-05,
+      "loss": 1.2585,
+      "step": 175
+    },
+    {
+      "epoch": 0.4909344490934449,
+      "grad_norm": 1.2765007106705224,
+      "learning_rate": 1.809562970824462e-05,
+      "loss": 1.3437,
+      "step": 176
+    },
+    {
+      "epoch": 0.49372384937238495,
+      "grad_norm": 1.2571675750543854,
+      "learning_rate": 1.8068261041591548e-05,
+      "loss": 1.4383,
+      "step": 177
+    },
+    {
+      "epoch": 0.496513249651325,
+      "grad_norm": 1.1735759325774886,
+      "learning_rate": 1.8040718119832378e-05,
+      "loss": 1.3234,
+      "step": 178
+    },
+    {
+      "epoch": 0.499302649930265,
+      "grad_norm": 1.1634243266804525,
+      "learning_rate": 1.8013001537828213e-05,
+      "loss": 1.2169,
+      "step": 179
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 1.2251535095230563,
+      "learning_rate": 1.7985111894190827e-05,
+      "loss": 1.2727,
+      "step": 180
+    },
+    {
+      "epoch": 0.502092050209205,
+      "eval_loss": 1.6175622940063477,
+      "eval_runtime": 183.4681,
+      "eval_samples_per_second": 1.733,
+      "eval_steps_per_second": 0.109,
+      "step": 180
+    },
+    {
+      "epoch": 0.504881450488145,
+      "grad_norm": 1.2927502437198448,
+      "learning_rate": 1.7957049791269684e-05,
+      "loss": 1.3752,
+      "step": 181
+    },
+    {
+      "epoch": 0.5076708507670851,
+      "grad_norm": 1.2697109314581512,
+      "learning_rate": 1.7928815835138976e-05,
+      "loss": 1.502,
+      "step": 182
+    },
+    {
+      "epoch": 0.5104602510460251,
+      "grad_norm": 1.3004080082594036,
+      "learning_rate": 1.79004106355845e-05,
+      "loss": 1.49,
+      "step": 183
+    },
+    {
+      "epoch": 0.5132496513249651,
+      "grad_norm": 1.2620161230293547,
+      "learning_rate": 1.7871834806090502e-05,
+      "loss": 1.258,
+      "step": 184
+    },
+    {
+      "epoch": 0.5160390516039052,
+      "grad_norm": 1.2238216229925647,
+      "learning_rate": 1.7843088963826437e-05,
+      "loss": 1.2829,
+      "step": 185
+    },
+    {
+      "epoch": 0.5188284518828452,
+      "grad_norm": 1.2320397894400665,
+      "learning_rate": 1.7814173729633607e-05,
+      "loss": 1.2767,
+      "step": 186
+    },
+    {
+      "epoch": 0.5216178521617852,
+      "grad_norm": 1.3637977851134857,
+      "learning_rate": 1.7785089728011798e-05,
+      "loss": 1.3635,
+      "step": 187
+    },
+    {
+      "epoch": 0.5244072524407253,
+      "grad_norm": 1.2685139570979558,
+      "learning_rate": 1.775583758710575e-05,
+      "loss": 1.4145,
+      "step": 188
+    },
+    {
+      "epoch": 0.5271966527196653,
+      "grad_norm": 1.3355216229358506,
+      "learning_rate": 1.772641793869162e-05,
+      "loss": 1.3068,
+      "step": 189
+    },
+    {
+      "epoch": 0.5299860529986054,
+      "grad_norm": 1.3597618241983527,
+      "learning_rate": 1.7696831418163318e-05,
+      "loss": 1.4446,
+      "step": 190
+    },
+    {
+      "epoch": 0.5327754532775453,
+      "grad_norm": 1.2542157271291101,
+      "learning_rate": 1.7667078664518796e-05,
+      "loss": 1.4184,
+      "step": 191
+    },
+    {
+      "epoch": 0.5355648535564853,
+      "grad_norm": 1.3244864911198961,
+      "learning_rate": 1.763716032034624e-05,
+      "loss": 1.3889,
+      "step": 192
+    },
+    {
+      "epoch": 0.5383542538354253,
+      "grad_norm": 1.261772883234437,
+      "learning_rate": 1.7607077031810204e-05,
+      "loss": 1.343,
+      "step": 193
+    },
+    {
+      "epoch": 0.5411436541143654,
+      "grad_norm": 1.404601026428458,
+      "learning_rate": 1.7576829448637628e-05,
+      "loss": 1.4606,
+      "step": 194
+    },
+    {
+      "epoch": 0.5439330543933054,
+      "grad_norm": 1.3091211707895143,
+      "learning_rate": 1.7546418224103838e-05,
+      "loss": 1.2931,
+      "step": 195
+    },
+    {
+      "epoch": 0.5467224546722455,
+      "grad_norm": 1.2631117467582635,
+      "learning_rate": 1.7515844015018416e-05,
+      "loss": 1.2999,
+      "step": 196
+    },
+    {
+      "epoch": 0.5495118549511855,
+      "grad_norm": 1.4560900819743723,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 1.5475,
+      "step": 197
+    },
+    {
+      "epoch": 0.5523012552301255,
+      "grad_norm": 1.4468059745173558,
+      "learning_rate": 1.7454209288017105e-05,
+      "loss": 1.4191,
+      "step": 198
+    },
+    {
+      "epoch": 0.5550906555090656,
+      "grad_norm": 1.315266510590906,
+      "learning_rate": 1.7423150101263645e-05,
+      "loss": 1.4005,
+      "step": 199
+    },
+    {
+      "epoch": 0.5578800557880056,
+      "grad_norm": 1.474348076413936,
+      "learning_rate": 1.7391930592254636e-05,
+      "loss": 1.3192,
+      "step": 200
+    },
+    {
+      "epoch": 0.5606694560669456,
+      "grad_norm": 1.3652476074142217,
+      "learning_rate": 1.7360551435256673e-05,
+      "loss": 1.2574,
+      "step": 201
+    },
+    {
+      "epoch": 0.5634588563458857,
+      "grad_norm": 1.3798373173542198,
+      "learning_rate": 1.7329013307984363e-05,
+      "loss": 1.3117,
+      "step": 202
+    },
+    {
+      "epoch": 0.5662482566248257,
+      "grad_norm": 1.209790296025406,
+      "learning_rate": 1.729731689158568e-05,
+      "loss": 1.3107,
+      "step": 203
+    },
+    {
+      "epoch": 0.5690376569037657,
+      "grad_norm": 1.1868593994582228,
+      "learning_rate": 1.726546287062727e-05,
+      "loss": 1.2752,
+      "step": 204
+    },
+    {
+      "epoch": 0.5718270571827058,
+      "grad_norm": 1.3235161134829174,
+      "learning_rate": 1.7233451933079663e-05,
+      "loss": 1.3399,
+      "step": 205
+    },
+    {
+      "epoch": 0.5746164574616457,
+      "grad_norm": 1.353859989844425,
+      "learning_rate": 1.720128477030241e-05,
+      "loss": 1.3181,
+      "step": 206
+    },
+    {
+      "epoch": 0.5774058577405857,
+      "grad_norm": 1.3778332664676014,
+      "learning_rate": 1.7168962077029146e-05,
+      "loss": 1.372,
+      "step": 207
+    },
+    {
+      "epoch": 0.5801952580195258,
+      "grad_norm": 1.3065213179222184,
+      "learning_rate": 1.7136484551352608e-05,
+      "loss": 1.2717,
+      "step": 208
+    },
+    {
+      "epoch": 0.5829846582984658,
+      "grad_norm": 1.3461935265014031,
+      "learning_rate": 1.7103852894709517e-05,
+      "loss": 1.3716,
+      "step": 209
+    },
+    {
+      "epoch": 0.5857740585774058,
+      "grad_norm": 1.5238199082532498,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.4732,
+      "step": 210
+    },
+    {
+      "epoch": 0.5885634588563459,
+      "grad_norm": 1.2661008215508678,
+      "learning_rate": 1.7038130010899716e-05,
+      "loss": 1.3884,
+      "step": 211
+    },
+    {
+      "epoch": 0.5913528591352859,
+      "grad_norm": 1.3340050909328596,
+      "learning_rate": 1.7005040203189818e-05,
+      "loss": 1.3851,
+      "step": 212
+    },
+    {
+      "epoch": 0.5941422594142259,
+      "grad_norm": 1.2956837583785732,
+      "learning_rate": 1.6971799103396332e-05,
+      "loss": 1.4221,
+      "step": 213
+    },
+    {
+      "epoch": 0.596931659693166,
+      "grad_norm": 1.1561140429998333,
+      "learning_rate": 1.693840742944738e-05,
+      "loss": 1.2218,
+      "step": 214
+    },
+    {
+      "epoch": 0.599721059972106,
+      "grad_norm": 1.313764720344347,
+      "learning_rate": 1.6904865902523098e-05,
+      "loss": 1.264,
+      "step": 215
+    },
+    {
+      "epoch": 0.602510460251046,
+      "grad_norm": 1.3302384495066342,
+      "learning_rate": 1.68711752470401e-05,
+      "loss": 1.2776,
+      "step": 216
+    },
+    {
+      "epoch": 0.6052998605299861,
+      "grad_norm": 1.2191909895274562,
+      "learning_rate": 1.6837336190635824e-05,
+      "loss": 1.3539,
+      "step": 217
+    },
+    {
+      "epoch": 0.6080892608089261,
+      "grad_norm": 1.3373684634352505,
+      "learning_rate": 1.6803349464152798e-05,
+      "loss": 1.4503,
+      "step": 218
+    },
+    {
+      "epoch": 0.6108786610878661,
+      "grad_norm": 1.363619941169918,
+      "learning_rate": 1.6769215801622884e-05,
+      "loss": 1.5192,
+      "step": 219
+    },
+    {
+      "epoch": 0.6136680613668062,
+      "grad_norm": 1.4606054239168875,
+      "learning_rate": 1.6734935940251404e-05,
+      "loss": 1.5595,
+      "step": 220
+    },
+    {
+      "epoch": 0.6164574616457462,
+      "grad_norm": 1.231599938466119,
+      "learning_rate": 1.6700510620401223e-05,
+      "loss": 1.2604,
+      "step": 221
+    },
+    {
+      "epoch": 0.6192468619246861,
+      "grad_norm": 1.5101877585841448,
+      "learning_rate": 1.666594058557677e-05,
+      "loss": 1.4834,
+      "step": 222
+    },
+    {
+      "epoch": 0.6220362622036262,
+      "grad_norm": 1.39399625488815,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 1.3877,
+      "step": 223
+    },
+    {
+      "epoch": 0.6248256624825662,
+      "grad_norm": 1.453409874433298,
+      "learning_rate": 1.659636936063407e-05,
+      "loss": 1.5218,
+      "step": 224
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "grad_norm": 1.2538819898580684,
+      "learning_rate": 1.6561369673087588e-05,
+      "loss": 1.2438,
+      "step": 225
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "eval_loss": 1.6073960065841675,
+      "eval_runtime": 160.2272,
+      "eval_samples_per_second": 1.985,
+      "eval_steps_per_second": 0.125,
+      "step": 225
+    },
+    {
+      "epoch": 0.6304044630404463,
+      "grad_norm": 1.5406663292943368,
+      "learning_rate": 1.6526228275677892e-05,
+      "loss": 1.4646,
+      "step": 226
+    },
+    {
+      "epoch": 0.6331938633193863,
+      "grad_norm": 1.2629740380853072,
+      "learning_rate": 1.649094592737497e-05,
+      "loss": 1.3459,
+      "step": 227
+    },
+    {
+      "epoch": 0.6359832635983264,
+      "grad_norm": 1.302608797313638,
+      "learning_rate": 1.6455523390193e-05,
+      "loss": 1.2689,
+      "step": 228
+    },
+    {
+      "epoch": 0.6387726638772664,
+      "grad_norm": 1.1773849504199476,
+      "learning_rate": 1.641996142917391e-05,
+      "loss": 1.2342,
+      "step": 229
+    },
+    {
+      "epoch": 0.6415620641562064,
+      "grad_norm": 1.3493891917660983,
+      "learning_rate": 1.638426081237085e-05,
+      "loss": 1.2569,
+      "step": 230
+    },
+    {
+      "epoch": 0.6443514644351465,
+      "grad_norm": 1.388250997836812,
+      "learning_rate": 1.63484223108316e-05,
+      "loss": 1.3979,
+      "step": 231
+    },
+    {
+      "epoch": 0.6471408647140865,
+      "grad_norm": 1.1928671464502947,
+      "learning_rate": 1.6312446698581915e-05,
+      "loss": 1.23,
+      "step": 232
+    },
+    {
+      "epoch": 0.6499302649930265,
+      "grad_norm": 1.2633309780727078,
+      "learning_rate": 1.6276334752608823e-05,
+      "loss": 1.4891,
+      "step": 233
+    },
+    {
+      "epoch": 0.6527196652719666,
+      "grad_norm": 1.304711639719216,
+      "learning_rate": 1.624008725284383e-05,
+      "loss": 1.3034,
+      "step": 234
+    },
+    {
+      "epoch": 0.6555090655509066,
+      "grad_norm": 1.2217261096543481,
+      "learning_rate": 1.6203704982146073e-05,
+      "loss": 1.2068,
+      "step": 235
+    },
+    {
+      "epoch": 0.6582984658298466,
+      "grad_norm": 1.288441898801668,
+      "learning_rate": 1.6167188726285433e-05,
+      "loss": 1.2461,
+      "step": 236
+    },
+    {
+      "epoch": 0.6610878661087866,
+      "grad_norm": 1.590492811559281,
+      "learning_rate": 1.613053927392553e-05,
+      "loss": 1.5137,
+      "step": 237
+    },
+    {
+      "epoch": 0.6638772663877266,
+      "grad_norm": 1.2477326342958976,
+      "learning_rate": 1.6093757416606725e-05,
+      "loss": 1.3189,
+      "step": 238
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.2127950915475818,
+      "learning_rate": 1.6056843948729e-05,
+      "loss": 1.2682,
+      "step": 239
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 1.4271242774536947,
+      "learning_rate": 1.6019799667534813e-05,
+      "loss": 1.5004,
+      "step": 240
+    },
+    {
+      "epoch": 0.6722454672245467,
+      "grad_norm": 1.3666477545942404,
+      "learning_rate": 1.5982625373091877e-05,
+      "loss": 1.5493,
+      "step": 241
+    },
+    {
+      "epoch": 0.6750348675034867,
+      "grad_norm": 1.1483091382024733,
+      "learning_rate": 1.594532186827588e-05,
+      "loss": 1.3191,
+      "step": 242
+    },
+    {
+      "epoch": 0.6778242677824268,
+      "grad_norm": 3.1947518624580136,
+      "learning_rate": 1.5907889958753134e-05,
+      "loss": 1.3046,
+      "step": 243
+    },
+    {
+      "epoch": 0.6806136680613668,
+      "grad_norm": 1.3099413581809563,
+      "learning_rate": 1.5870330452963206e-05,
+      "loss": 1.2706,
+      "step": 244
+    },
+    {
+      "epoch": 0.6834030683403068,
+      "grad_norm": 1.461185290486486,
+      "learning_rate": 1.5832644162101417e-05,
+      "loss": 1.4886,
+      "step": 245
+    },
+    {
+      "epoch": 0.6861924686192469,
+      "grad_norm": 1.2442836680144551,
+      "learning_rate": 1.5794831900101352e-05,
+      "loss": 1.27,
+      "step": 246
+    },
+    {
+      "epoch": 0.6889818688981869,
+      "grad_norm": 1.248119979843789,
+      "learning_rate": 1.5756894483617268e-05,
+      "loss": 1.2831,
+      "step": 247
+    },
+    {
+      "epoch": 0.691771269177127,
+      "grad_norm": 1.3703323165735684,
+      "learning_rate": 1.571883273200646e-05,
+      "loss": 1.5584,
+      "step": 248
+    },
+    {
+      "epoch": 0.694560669456067,
+      "grad_norm": 1.3183958125038406,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 1.5037,
+      "step": 249
+    },
+    {
+      "epoch": 0.697350069735007,
+      "grad_norm": 1.1844817674941481,
+      "learning_rate": 1.564233951424279e-05,
+      "loss": 1.4209,
+      "step": 250
+    },
+    {
+      "epoch": 0.700139470013947,
+      "grad_norm": 1.5190227626319008,
+      "learning_rate": 1.560390970016015e-05,
+      "loss": 1.4738,
+      "step": 251
+    },
+    {
+      "epoch": 0.702928870292887,
+      "grad_norm": 1.2922540957047237,
+      "learning_rate": 1.5565358855055535e-05,
+      "loss": 1.4749,
+      "step": 252
+    },
+    {
+      "epoch": 0.705718270571827,
+      "grad_norm": 1.2755003379456324,
+      "learning_rate": 1.552668781153484e-05,
+      "loss": 1.3514,
+      "step": 253
+    },
+    {
+      "epoch": 0.708507670850767,
+      "grad_norm": 1.333525201907311,
+      "learning_rate": 1.5487897404799932e-05,
+      "loss": 1.4833,
+      "step": 254
+    },
+    {
+      "epoch": 0.7112970711297071,
+      "grad_norm": 1.2366281388101243,
+      "learning_rate": 1.5448988472630654e-05,
+      "loss": 1.3055,
+      "step": 255
+    },
+    {
+      "epoch": 0.7140864714086471,
+      "grad_norm": 1.2656677555514606,
+      "learning_rate": 1.5409961855366718e-05,
+      "loss": 1.2858,
+      "step": 256
+    },
+    {
+      "epoch": 0.7168758716875872,
+      "grad_norm": 1.3893320030810534,
+      "learning_rate": 1.5370818395889536e-05,
+      "loss": 1.2958,
+      "step": 257
+    },
+    {
+      "epoch": 0.7196652719665272,
+      "grad_norm": 1.2262571768039963,
+      "learning_rate": 1.533155893960405e-05,
+      "loss": 1.3797,
+      "step": 258
+    },
+    {
+      "epoch": 0.7224546722454672,
+      "grad_norm": 1.3752885859305817,
+      "learning_rate": 1.5292184334420434e-05,
+      "loss": 1.5324,
+      "step": 259
+    },
+    {
+      "epoch": 0.7252440725244073,
+      "grad_norm": 1.349973458041763,
+      "learning_rate": 1.5252695430735824e-05,
+      "loss": 1.3828,
+      "step": 260
+    },
+    {
+      "epoch": 0.7280334728033473,
+      "grad_norm": 1.214154217005644,
+      "learning_rate": 1.521309308141592e-05,
+      "loss": 1.3081,
+      "step": 261
+    },
+    {
+      "epoch": 0.7308228730822873,
+      "grad_norm": 1.2681774984772773,
+      "learning_rate": 1.5173378141776569e-05,
+      "loss": 1.5341,
+      "step": 262
+    },
+    {
+      "epoch": 0.7336122733612274,
+      "grad_norm": 1.2265782510592125,
+      "learning_rate": 1.5133551469565313e-05,
+      "loss": 1.2877,
+      "step": 263
+    },
+    {
+      "epoch": 0.7364016736401674,
+      "grad_norm": 1.2084693848644321,
+      "learning_rate": 1.5093613924942837e-05,
+      "loss": 1.3773,
+      "step": 264
+    },
+    {
+      "epoch": 0.7391910739191074,
+      "grad_norm": 1.1437825395668497,
+      "learning_rate": 1.5053566370464416e-05,
+      "loss": 1.2808,
+      "step": 265
+    },
+    {
+      "epoch": 0.7419804741980475,
+      "grad_norm": 1.3197967431830404,
+      "learning_rate": 1.5013409671061267e-05,
+      "loss": 1.289,
+      "step": 266
+    },
+    {
+      "epoch": 0.7447698744769874,
+      "grad_norm": 1.382635793553147,
+      "learning_rate": 1.4973144694021874e-05,
+      "loss": 1.2638,
+      "step": 267
+    },
+    {
+      "epoch": 0.7475592747559274,
+      "grad_norm": 1.3988324864350785,
+      "learning_rate": 1.4932772308973267e-05,
+      "loss": 1.3403,
+      "step": 268
+    },
+    {
+      "epoch": 0.7503486750348675,
+      "grad_norm": 1.2731407752985473,
+      "learning_rate": 1.4892293387862221e-05,
+      "loss": 1.3312,
+      "step": 269
+    },
+    {
+      "epoch": 0.7531380753138075,
+      "grad_norm": 1.1572040227672067,
+      "learning_rate": 1.4851708804936449e-05,
+      "loss": 1.3147,
+      "step": 270
+    },
+    {
+      "epoch": 0.7531380753138075,
+      "eval_loss": 1.5958304405212402,
+      "eval_runtime": 158.3728,
+      "eval_samples_per_second": 2.008,
+      "eval_steps_per_second": 0.126,
+      "step": 270
+    },
+    {
+      "epoch": 0.7559274755927475,
+      "grad_norm": 1.3990082254921117,
+      "learning_rate": 1.4811019436725684e-05,
+      "loss": 1.3162,
+      "step": 271
+    },
+    {
+      "epoch": 0.7587168758716876,
+      "grad_norm": 1.2418130090749915,
+      "learning_rate": 1.4770226162022799e-05,
+      "loss": 1.2594,
+      "step": 272
+    },
+    {
+      "epoch": 0.7615062761506276,
+      "grad_norm": 1.1503772215035513,
+      "learning_rate": 1.472932986186477e-05,
+      "loss": 1.2827,
+      "step": 273
+    },
+    {
+      "epoch": 0.7642956764295676,
+      "grad_norm": 1.459940130878171,
+      "learning_rate": 1.4688331419513693e-05,
+      "loss": 1.3126,
+      "step": 274
+    },
+    {
+      "epoch": 0.7670850767085077,
+      "grad_norm": 1.3252355330703371,
+      "learning_rate": 1.4647231720437687e-05,
+      "loss": 1.4367,
+      "step": 275
+    },
+    {
+      "epoch": 0.7698744769874477,
+      "grad_norm": 1.4888619740632927,
+      "learning_rate": 1.4606031652291772e-05,
+      "loss": 1.4275,
+      "step": 276
+    },
+    {
+      "epoch": 0.7726638772663877,
+      "grad_norm": 1.3069850449838218,
+      "learning_rate": 1.4564732104898702e-05,
+      "loss": 1.3533,
+      "step": 277
+    },
+    {
+      "epoch": 0.7754532775453278,
+      "grad_norm": 1.268759058345783,
+      "learning_rate": 1.4523333970229741e-05,
+      "loss": 1.337,
+      "step": 278
+    },
+    {
+      "epoch": 0.7782426778242678,
+      "grad_norm": 1.1520224898754043,
+      "learning_rate": 1.4481838142385403e-05,
+      "loss": 1.2454,
+      "step": 279
+    },
+    {
+      "epoch": 0.7810320781032078,
+      "grad_norm": 1.3031384394432615,
+      "learning_rate": 1.4440245517576141e-05,
+      "loss": 1.4125,
+      "step": 280
+    },
+    {
+      "epoch": 0.7838214783821479,
+      "grad_norm": 1.4528549714436811,
+      "learning_rate": 1.4398556994102996e-05,
+      "loss": 1.3641,
+      "step": 281
+    },
+    {
+      "epoch": 0.7866108786610879,
+      "grad_norm": 1.4236584359239257,
+      "learning_rate": 1.4356773472338174e-05,
+      "loss": 1.48,
+      "step": 282
+    },
+    {
+      "epoch": 0.7894002789400278,
+      "grad_norm": 1.4626745792933868,
+      "learning_rate": 1.4314895854705641e-05,
+      "loss": 1.4765,
+      "step": 283
+    },
+    {
+      "epoch": 0.7921896792189679,
+      "grad_norm": 1.2910417535844496,
+      "learning_rate": 1.4272925045661583e-05,
+      "loss": 1.419,
+      "step": 284
+    },
+    {
+      "epoch": 0.7949790794979079,
+      "grad_norm": 1.2373977812672998,
+      "learning_rate": 1.4230861951674914e-05,
+      "loss": 1.2251,
+      "step": 285
+    },
+    {
+      "epoch": 0.797768479776848,
+      "grad_norm": 1.2785831952874724,
+      "learning_rate": 1.4188707481207677e-05,
+      "loss": 1.3471,
+      "step": 286
+    },
+    {
+      "epoch": 0.800557880055788,
+      "grad_norm": 1.3683445048689633,
+      "learning_rate": 1.4146462544695428e-05,
+      "loss": 1.425,
+      "step": 287
+    },
+    {
+      "epoch": 0.803347280334728,
+      "grad_norm": 1.1296732873251845,
+      "learning_rate": 1.410412805452757e-05,
+      "loss": 1.2578,
+      "step": 288
+    },
+    {
+      "epoch": 0.806136680613668,
+      "grad_norm": 1.0829712122726374,
+      "learning_rate": 1.4061704925027653e-05,
+      "loss": 1.1799,
+      "step": 289
+    },
+    {
+      "epoch": 0.8089260808926081,
+      "grad_norm": 1.3309074955401459,
+      "learning_rate": 1.4019194072433626e-05,
+      "loss": 1.1379,
+      "step": 290
+    },
+    {
+      "epoch": 0.8117154811715481,
+      "grad_norm": 1.2343728023741232,
+      "learning_rate": 1.3976596414878044e-05,
+      "loss": 1.2411,
+      "step": 291
+    },
+    {
+      "epoch": 0.8145048814504882,
+      "grad_norm": 1.214883458073917,
+      "learning_rate": 1.393391287236824e-05,
+      "loss": 1.3405,
+      "step": 292
+    },
+    {
+      "epoch": 0.8172942817294282,
+      "grad_norm": 1.3091690676466778,
+      "learning_rate": 1.3891144366766457e-05,
+      "loss": 1.2606,
+      "step": 293
+    },
+    {
+      "epoch": 0.8200836820083682,
+      "grad_norm": 13.631918339692971,
+      "learning_rate": 1.3848291821769944e-05,
+      "loss": 1.656,
+      "step": 294
+    },
+    {
+      "epoch": 0.8228730822873083,
+      "grad_norm": 1.1657018881567924,
+      "learning_rate": 1.380535616289099e-05,
+      "loss": 1.2156,
+      "step": 295
+    },
+    {
+      "epoch": 0.8256624825662483,
+      "grad_norm": 1.2347632552018992,
+      "learning_rate": 1.3762338317436948e-05,
+      "loss": 1.2669,
+      "step": 296
+    },
+    {
+      "epoch": 0.8284518828451883,
+      "grad_norm": 1.4274262176368255,
+      "learning_rate": 1.3719239214490203e-05,
+      "loss": 1.3072,
+      "step": 297
+    },
+    {
+      "epoch": 0.8312412831241283,
+      "grad_norm": 1.2894927915175798,
+      "learning_rate": 1.3676059784888112e-05,
+      "loss": 1.4573,
+      "step": 298
+    },
+    {
+      "epoch": 0.8340306834030683,
+      "grad_norm": 1.4646947685259242,
+      "learning_rate": 1.363280096120289e-05,
+      "loss": 1.4956,
+      "step": 299
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 1.2835331667441359,
+      "learning_rate": 1.358946367772148e-05,
+      "loss": 1.3713,
+      "step": 300
+    },
+    {
+      "epoch": 0.8396094839609484,
+      "grad_norm": 1.3024578071081172,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 1.345,
+      "step": 301
+    },
+    {
+      "epoch": 0.8423988842398884,
+      "grad_norm": 1.144812031373234,
+      "learning_rate": 1.3502557476970339e-05,
+      "loss": 1.3447,
+      "step": 302
+    },
+    {
+      "epoch": 0.8451882845188284,
+      "grad_norm": 1.255722753075089,
+      "learning_rate": 1.3458990436666313e-05,
+      "loss": 1.5169,
+      "step": 303
+    },
+    {
+      "epoch": 0.8479776847977685,
+      "grad_norm": 1.1632268233137957,
+      "learning_rate": 1.3415348690456955e-05,
+      "loss": 1.289,
+      "step": 304
+    },
+    {
+      "epoch": 0.8507670850767085,
+      "grad_norm": 1.2357758677374722,
+      "learning_rate": 1.3371633180899417e-05,
+      "loss": 1.4063,
+      "step": 305
+    },
+    {
+      "epoch": 0.8535564853556485,
+      "grad_norm": 1.2854100609241097,
+      "learning_rate": 1.3327844852143956e-05,
+      "loss": 1.3677,
+      "step": 306
+    },
+    {
+      "epoch": 0.8563458856345886,
+      "grad_norm": 1.2395591163738042,
+      "learning_rate": 1.3283984649913552e-05,
+      "loss": 1.3656,
+      "step": 307
+    },
+    {
+      "epoch": 0.8591352859135286,
+      "grad_norm": 1.309692041297723,
+      "learning_rate": 1.3240053521483483e-05,
+      "loss": 1.3191,
+      "step": 308
+    },
+    {
+      "epoch": 0.8619246861924686,
+      "grad_norm": 1.306594190283498,
+      "learning_rate": 1.3196052415660856e-05,
+      "loss": 1.2964,
+      "step": 309
+    },
+    {
+      "epoch": 0.8647140864714087,
+      "grad_norm": 1.2332822767216993,
+      "learning_rate": 1.3151982282764126e-05,
+      "loss": 1.3172,
+      "step": 310
+    },
+    {
+      "epoch": 0.8675034867503487,
+      "grad_norm": 1.2248947416069507,
+      "learning_rate": 1.3107844074602566e-05,
+      "loss": 1.2215,
+      "step": 311
+    },
+    {
+      "epoch": 0.8702928870292888,
+      "grad_norm": 1.0883399467851869,
+      "learning_rate": 1.3063638744455713e-05,
+      "loss": 1.2487,
+      "step": 312
+    },
+    {
+      "epoch": 0.8730822873082287,
+      "grad_norm": 1.3561694142459044,
+      "learning_rate": 1.3019367247052781e-05,
+      "loss": 1.5192,
+      "step": 313
+    },
+    {
+      "epoch": 0.8758716875871687,
+      "grad_norm": 1.2195540202949509,
+      "learning_rate": 1.297503053855203e-05,
+      "loss": 1.315,
+      "step": 314
+    },
+    {
+      "epoch": 0.8786610878661087,
+      "grad_norm": 1.2398989428685936,
+      "learning_rate": 1.2930629576520133e-05,
+      "loss": 1.2466,
+      "step": 315
+    },
+    {
+      "epoch": 0.8786610878661087,
+      "eval_loss": 1.590497612953186,
+      "eval_runtime": 158.7725,
+      "eval_samples_per_second": 2.003,
+      "eval_steps_per_second": 0.126,
+      "step": 315
+    },
+    {
+      "epoch": 0.8814504881450488,
+      "grad_norm": 1.1820530696430398,
+      "learning_rate": 1.2886165319911474e-05,
+      "loss": 1.3187,
+      "step": 316
+    },
+    {
+      "epoch": 0.8842398884239888,
+      "grad_norm": 1.2411796795161567,
+      "learning_rate": 1.2841638729047463e-05,
+      "loss": 1.3681,
+      "step": 317
+    },
+    {
+      "epoch": 0.8870292887029289,
+      "grad_norm": 1.2561131847214293,
+      "learning_rate": 1.2797050765595767e-05,
+      "loss": 1.2601,
+      "step": 318
+    },
+    {
+      "epoch": 0.8898186889818689,
+      "grad_norm": 1.415729283991149,
+      "learning_rate": 1.2752402392549556e-05,
+      "loss": 1.4896,
+      "step": 319
+    },
+    {
+      "epoch": 0.8926080892608089,
+      "grad_norm": 1.3261631641702796,
+      "learning_rate": 1.2707694574206712e-05,
+      "loss": 1.5607,
+      "step": 320
+    },
+    {
+      "epoch": 0.895397489539749,
+      "grad_norm": 1.240314237616232,
+      "learning_rate": 1.2662928276148985e-05,
+      "loss": 1.3429,
+      "step": 321
+    },
+    {
+      "epoch": 0.898186889818689,
+      "grad_norm": 1.3000617526029077,
+      "learning_rate": 1.2618104465221148e-05,
+      "loss": 1.4272,
+      "step": 322
+    },
+    {
+      "epoch": 0.900976290097629,
+      "grad_norm": 1.16464364915601,
+      "learning_rate": 1.2573224109510112e-05,
+      "loss": 1.2306,
+      "step": 323
+    },
+    {
+      "epoch": 0.9037656903765691,
+      "grad_norm": 1.2109886144147917,
+      "learning_rate": 1.2528288178324029e-05,
+      "loss": 1.353,
+      "step": 324
+    },
+    {
+      "epoch": 0.9065550906555091,
+      "grad_norm": 1.1714274928342496,
+      "learning_rate": 1.2483297642171332e-05,
+      "loss": 1.2997,
+      "step": 325
+    },
+    {
+      "epoch": 0.9093444909344491,
+      "grad_norm": 1.1814072235776383,
+      "learning_rate": 1.2438253472739805e-05,
+      "loss": 1.3144,
+      "step": 326
+    },
+    {
+      "epoch": 0.9121338912133892,
+      "grad_norm": 1.3461681399899779,
+      "learning_rate": 1.2393156642875579e-05,
+      "loss": 1.3618,
+      "step": 327
+    },
+    {
+      "epoch": 0.9149232914923291,
+      "grad_norm": 1.456924757382429,
+      "learning_rate": 1.234800812656212e-05,
+      "loss": 1.3796,
+      "step": 328
+    },
+    {
+      "epoch": 0.9177126917712691,
+      "grad_norm": 1.2321016000046479,
+      "learning_rate": 1.23028088988992e-05,
+      "loss": 1.3771,
+      "step": 329
+    },
+    {
+      "epoch": 0.9205020920502092,
+      "grad_norm": 1.2405013760966828,
+      "learning_rate": 1.2257559936081833e-05,
+      "loss": 1.2744,
+      "step": 330
+    },
+    {
+      "epoch": 0.9232914923291492,
+      "grad_norm": 1.2677524234506234,
+      "learning_rate": 1.2212262215379199e-05,
+      "loss": 1.3578,
+      "step": 331
+    },
+    {
+      "epoch": 0.9260808926080892,
+      "grad_norm": 1.2230537842102542,
+      "learning_rate": 1.2166916715113521e-05,
+      "loss": 1.4323,
+      "step": 332
+    },
+    {
+      "epoch": 0.9288702928870293,
+      "grad_norm": 1.2690522272930789,
+      "learning_rate": 1.2121524414638958e-05,
+      "loss": 1.2845,
+      "step": 333
+    },
+    {
+      "epoch": 0.9316596931659693,
+      "grad_norm": 1.2822697397851108,
+      "learning_rate": 1.207608629432043e-05,
+      "loss": 1.6128,
+      "step": 334
+    },
+    {
+      "epoch": 0.9344490934449093,
+      "grad_norm": 1.2997575387211082,
+      "learning_rate": 1.2030603335512467e-05,
+      "loss": 1.3401,
+      "step": 335
+    },
+    {
+      "epoch": 0.9372384937238494,
+      "grad_norm": 1.5059463142396166,
+      "learning_rate": 1.1985076520537995e-05,
+      "loss": 1.2793,
+      "step": 336
+    },
+    {
+      "epoch": 0.9400278940027894,
+      "grad_norm": 1.5118948746263785,
+      "learning_rate": 1.1939506832667129e-05,
+      "loss": 1.3152,
+      "step": 337
+    },
+    {
+      "epoch": 0.9428172942817294,
+      "grad_norm": 1.2816385360112317,
+      "learning_rate": 1.1893895256095937e-05,
+      "loss": 1.4573,
+      "step": 338
+    },
+    {
+      "epoch": 0.9456066945606695,
+      "grad_norm": 1.1973723679649781,
+      "learning_rate": 1.1848242775925188e-05,
+      "loss": 1.1473,
+      "step": 339
+    },
+    {
+      "epoch": 0.9483960948396095,
+      "grad_norm": 1.157556800970344,
+      "learning_rate": 1.180255037813906e-05,
+      "loss": 1.362,
+      "step": 340
+    },
+    {
+      "epoch": 0.9511854951185496,
+      "grad_norm": 1.3366940604017197,
+      "learning_rate": 1.1756819049583861e-05,
+      "loss": 1.5201,
+      "step": 341
+    },
+    {
+      "epoch": 0.9539748953974896,
+      "grad_norm": 1.396951726353029,
+      "learning_rate": 1.1711049777946717e-05,
+      "loss": 1.4882,
+      "step": 342
+    },
+    {
+      "epoch": 0.9567642956764296,
+      "grad_norm": 1.1789267346275334,
+      "learning_rate": 1.166524355173422e-05,
+      "loss": 1.3806,
+      "step": 343
+    },
+    {
+      "epoch": 0.9595536959553695,
+      "grad_norm": 1.2075413726006268,
+      "learning_rate": 1.1619401360251104e-05,
+      "loss": 1.2451,
+      "step": 344
+    },
+    {
+      "epoch": 0.9623430962343096,
+      "grad_norm": 1.2379647427390967,
+      "learning_rate": 1.1573524193578863e-05,
+      "loss": 1.1581,
+      "step": 345
+    },
+    {
+      "epoch": 0.9651324965132496,
+      "grad_norm": 1.1953475180567759,
+      "learning_rate": 1.1527613042554368e-05,
+      "loss": 1.3765,
+      "step": 346
+    },
+    {
+      "epoch": 0.9679218967921897,
+      "grad_norm": 1.2657967489739972,
+      "learning_rate": 1.1481668898748474e-05,
+      "loss": 1.335,
+      "step": 347
+    },
+    {
+      "epoch": 0.9707112970711297,
+      "grad_norm": 1.2590876717921935,
+      "learning_rate": 1.1435692754444604e-05,
+      "loss": 1.339,
+      "step": 348
+    },
+    {
+      "epoch": 0.9735006973500697,
+      "grad_norm": 1.3430351369524687,
+      "learning_rate": 1.1389685602617302e-05,
+      "loss": 1.3618,
+      "step": 349
+    },
+    {
+      "epoch": 0.9762900976290098,
+      "grad_norm": 1.216928490077423,
+      "learning_rate": 1.134364843691082e-05,
+      "loss": 1.4504,
+      "step": 350
+    },
+    {
+      "epoch": 0.9790794979079498,
+      "grad_norm": 1.2961172668976244,
+      "learning_rate": 1.1297582251617618e-05,
+      "loss": 1.3752,
+      "step": 351
+    },
+    {
+      "epoch": 0.9818688981868898,
+      "grad_norm": 1.3163958626398011,
+      "learning_rate": 1.1251488041656929e-05,
+      "loss": 1.2906,
+      "step": 352
+    },
+    {
+      "epoch": 0.9846582984658299,
+      "grad_norm": 1.2499583055181795,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 1.3641,
+      "step": 353
+    },
+    {
+      "epoch": 0.9874476987447699,
+      "grad_norm": 1.5088593864499633,
+      "learning_rate": 1.1159219530414786e-05,
+      "loss": 1.4534,
+      "step": 354
+    },
+    {
+      "epoch": 0.9902370990237099,
+      "grad_norm": 1.1931538459250062,
+      "learning_rate": 1.1113047221912097e-05,
+      "loss": 1.3285,
+      "step": 355
+    },
+    {
+      "epoch": 0.99302649930265,
+      "grad_norm": 1.1763206233025147,
+      "learning_rate": 1.1066850874256387e-05,
+      "loss": 1.3928,
+      "step": 356
+    },
+    {
+      "epoch": 0.99581589958159,
+      "grad_norm": 1.2398324928784012,
+      "learning_rate": 1.1020631485178084e-05,
+      "loss": 1.4118,
+      "step": 357
+    },
+    {
+      "epoch": 0.99860529986053,
+      "grad_norm": 1.1658511676647905,
+      "learning_rate": 1.0974390052905238e-05,
+      "loss": 1.2735,
+      "step": 358
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1658511676647905,
+      "learning_rate": 1.0928127576141992e-05,
+      "loss": 0.631,
+      "step": 359
+    },
+    {
+      "epoch": 1.00278940027894,
+      "grad_norm": 1.2279956840576842,
+      "learning_rate": 1.0881845054046988e-05,
+      "loss": 1.3144,
+      "step": 360
+    },
+    {
+      "epoch": 1.00278940027894,
+      "eval_loss": 1.5843528509140015,
+      "eval_runtime": 158.9441,
+      "eval_samples_per_second": 2.001,
+      "eval_steps_per_second": 0.126,
+      "step": 360
+    },
+    {
+      "epoch": 1.00557880055788,
+      "grad_norm": 1.122956387667915,
+      "learning_rate": 1.0835543486211815e-05,
+      "loss": 1.1875,
+      "step": 361
+    },
+    {
+      "epoch": 1.00836820083682,
+      "grad_norm": 1.1487145048815297,
+      "learning_rate": 1.0789223872639385e-05,
+      "loss": 1.3283,
+      "step": 362
+    },
+    {
+      "epoch": 1.0111576011157601,
+      "grad_norm": 1.210362167885254,
+      "learning_rate": 1.0742887213722372e-05,
+      "loss": 1.1607,
+      "step": 363
+    },
+    {
+      "epoch": 1.0139470013947,
+      "grad_norm": 1.167683710016959,
+      "learning_rate": 1.0696534510221575e-05,
+      "loss": 1.3125,
+      "step": 364
+    },
+    {
+      "epoch": 1.0167364016736402,
+      "grad_norm": 1.224749951044779,
+      "learning_rate": 1.065016676324433e-05,
+      "loss": 1.2384,
+      "step": 365
+    },
+    {
+      "epoch": 1.0195258019525801,
+      "grad_norm": 1.1566624177175886,
+      "learning_rate": 1.0603784974222862e-05,
+      "loss": 1.3956,
+      "step": 366
+    },
+    {
+      "epoch": 1.0223152022315203,
+      "grad_norm": 1.2969848771007706,
+      "learning_rate": 1.0557390144892684e-05,
+      "loss": 1.3216,
+      "step": 367
+    },
+    {
+      "epoch": 1.0251046025104602,
+      "grad_norm": 1.1557275837790277,
+      "learning_rate": 1.0510983277270945e-05,
+      "loss": 1.1656,
+      "step": 368
+    },
+    {
+      "epoch": 1.0278940027894004,
+      "grad_norm": 1.1274495156209017,
+      "learning_rate": 1.0464565373634784e-05,
+      "loss": 1.234,
+      "step": 369
+    },
+    {
+      "epoch": 1.0306834030683403,
+      "grad_norm": 1.2136920982158583,
+      "learning_rate": 1.0418137436499699e-05,
+      "loss": 1.1579,
+      "step": 370
+    },
+    {
+      "epoch": 1.0334728033472804,
+      "grad_norm": 1.2136361742646686,
+      "learning_rate": 1.0371700468597886e-05,
+      "loss": 1.3869,
+      "step": 371
+    },
+    {
+      "epoch": 1.0362622036262203,
+      "grad_norm": 1.1175097910575362,
+      "learning_rate": 1.0325255472856586e-05,
+      "loss": 1.214,
+      "step": 372
+    },
+    {
+      "epoch": 1.0390516039051605,
+      "grad_norm": 1.1395096520260177,
+      "learning_rate": 1.0278803452376416e-05,
+      "loss": 1.436,
+      "step": 373
+    },
+    {
+      "epoch": 1.0418410041841004,
+      "grad_norm": 1.1082860671382055,
+      "learning_rate": 1.0232345410409718e-05,
+      "loss": 1.2397,
+      "step": 374
+    },
+    {
+      "epoch": 1.0446304044630403,
+      "grad_norm": 1.1045608548981312,
+      "learning_rate": 1.018588235033888e-05,
+      "loss": 1.2764,
+      "step": 375
+    },
+    {
+      "epoch": 1.0474198047419805,
+      "grad_norm": 1.1792908172632213,
+      "learning_rate": 1.0139415275654671e-05,
+      "loss": 1.3103,
+      "step": 376
+    },
+    {
+      "epoch": 1.0502092050209204,
+      "grad_norm": 1.1928217784395125,
+      "learning_rate": 1.0092945189934558e-05,
+      "loss": 1.2358,
+      "step": 377
+    },
+    {
+      "epoch": 1.0529986052998606,
+      "grad_norm": 1.2145452681867133,
+      "learning_rate": 1.0046473096821047e-05,
+      "loss": 1.196,
+      "step": 378
+    },
+    {
+      "epoch": 1.0557880055788005,
+      "grad_norm": 1.2041436209676546,
+      "learning_rate": 1e-05,
+      "loss": 1.3178,
+      "step": 379
+    },
+    {
+      "epoch": 1.0585774058577406,
+      "grad_norm": 1.148399751524864,
+      "learning_rate": 9.953526903178956e-06,
+      "loss": 1.4499,
+      "step": 380
+    },
+    {
+      "epoch": 1.0613668061366806,
+      "grad_norm": 1.1974026865483098,
+      "learning_rate": 9.907054810065446e-06,
+      "loss": 1.2057,
+      "step": 381
+    },
+    {
+      "epoch": 1.0641562064156207,
+      "grad_norm": 1.5812229698878382,
+      "learning_rate": 9.860584724345334e-06,
+      "loss": 1.482,
+      "step": 382
+    },
+    {
+      "epoch": 1.0669456066945606,
+      "grad_norm": 1.1834008069729351,
+      "learning_rate": 9.81411764966112e-06,
+      "loss": 1.3193,
+      "step": 383
+    },
+    {
+      "epoch": 1.0697350069735008,
+      "grad_norm": 1.0680962669389744,
+      "learning_rate": 9.767654589590284e-06,
+      "loss": 1.1936,
+      "step": 384
+    },
+    {
+      "epoch": 1.0725244072524407,
+      "grad_norm": 1.2433855122802504,
+      "learning_rate": 9.721196547623585e-06,
+      "loss": 1.3485,
+      "step": 385
+    },
+    {
+      "epoch": 1.0753138075313808,
+      "grad_norm": 1.1818473383563528,
+      "learning_rate": 9.674744527143419e-06,
+      "loss": 1.2435,
+      "step": 386
+    },
+    {
+      "epoch": 1.0781032078103208,
+      "grad_norm": 1.1606102472129574,
+      "learning_rate": 9.628299531402118e-06,
+      "loss": 1.352,
+      "step": 387
+    },
+    {
+      "epoch": 1.080892608089261,
+      "grad_norm": 1.3474388049187347,
+      "learning_rate": 9.581862563500305e-06,
+      "loss": 1.3987,
+      "step": 388
+    },
+    {
+      "epoch": 1.0836820083682008,
+      "grad_norm": 1.2419068969830154,
+      "learning_rate": 9.535434626365221e-06,
+      "loss": 1.3226,
+      "step": 389
+    },
+    {
+      "epoch": 1.086471408647141,
+      "grad_norm": 1.1382928547735685,
+      "learning_rate": 9.489016722729059e-06,
+      "loss": 1.2358,
+      "step": 390
+    },
+    {
+      "epoch": 1.089260808926081,
+      "grad_norm": 1.062780531568017,
+      "learning_rate": 9.442609855107317e-06,
+      "loss": 1.1819,
+      "step": 391
+    },
+    {
+      "epoch": 1.0920502092050208,
+      "grad_norm": 1.10859906931155,
+      "learning_rate": 9.39621502577714e-06,
+      "loss": 1.2527,
+      "step": 392
+    },
+    {
+      "epoch": 1.094839609483961,
+      "grad_norm": 1.2185757174534009,
+      "learning_rate": 9.349833236755675e-06,
+      "loss": 1.3156,
+      "step": 393
+    },
+    {
+      "epoch": 1.097629009762901,
+      "grad_norm": 1.225759251550299,
+      "learning_rate": 9.30346548977843e-06,
+      "loss": 1.1902,
+      "step": 394
+    },
+    {
+      "epoch": 1.100418410041841,
+      "grad_norm": 1.143304170948198,
+      "learning_rate": 9.257112786277631e-06,
+      "loss": 1.6164,
+      "step": 395
+    },
+    {
+      "epoch": 1.103207810320781,
+      "grad_norm": 1.1929513674684669,
+      "learning_rate": 9.21077612736062e-06,
+      "loss": 1.3059,
+      "step": 396
+    },
+    {
+      "epoch": 1.1059972105997211,
+      "grad_norm": 1.2652518498481602,
+      "learning_rate": 9.164456513788186e-06,
+      "loss": 1.3585,
+      "step": 397
+    },
+    {
+      "epoch": 1.108786610878661,
+      "grad_norm": 1.181284519624733,
+      "learning_rate": 9.118154945953015e-06,
+      "loss": 1.3096,
+      "step": 398
+    },
+    {
+      "epoch": 1.1115760111576012,
+      "grad_norm": 1.1391566905227906,
+      "learning_rate": 9.07187242385801e-06,
+      "loss": 1.2707,
+      "step": 399
+    },
+    {
+      "epoch": 1.114365411436541,
+      "grad_norm": 1.0825559641774511,
+      "learning_rate": 9.025609947094765e-06,
+      "loss": 1.2668,
+      "step": 400
+    },
+    {
+      "epoch": 1.1171548117154813,
+      "grad_norm": 1.1830262642050864,
+      "learning_rate": 8.979368514821917e-06,
+      "loss": 1.5181,
+      "step": 401
+    },
+    {
+      "epoch": 1.1199442119944212,
+      "grad_norm": 1.3026726939018842,
+      "learning_rate": 8.933149125743615e-06,
+      "loss": 1.219,
+      "step": 402
+    },
+    {
+      "epoch": 1.1227336122733613,
+      "grad_norm": 1.144101939773731,
+      "learning_rate": 8.88695277808791e-06,
+      "loss": 1.3683,
+      "step": 403
+    },
+    {
+      "epoch": 1.1255230125523012,
+      "grad_norm": 1.2305348777008256,
+      "learning_rate": 8.840780469585215e-06,
+      "loss": 1.3366,
+      "step": 404
+    },
+    {
+      "epoch": 1.1283124128312414,
+      "grad_norm": 1.209754151387273,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 1.1868,
+      "step": 405
+    },
+    {
+      "epoch": 1.1283124128312414,
+      "eval_loss": 1.5783870220184326,
+      "eval_runtime": 158.6338,
+      "eval_samples_per_second": 2.005,
+      "eval_steps_per_second": 0.126,
+      "step": 405
+    },
+    {
+      "epoch": 1.1311018131101813,
+      "grad_norm": 1.1895020228803659,
+      "learning_rate": 8.748511958343076e-06,
+      "loss": 1.2254,
+      "step": 406
+    },
+    {
+      "epoch": 1.1338912133891212,
+      "grad_norm": 1.0698636977312026,
+      "learning_rate": 8.702417748382384e-06,
+      "loss": 1.2746,
+      "step": 407
+    },
+    {
+      "epoch": 1.1366806136680614,
+      "grad_norm": 1.1610395502416724,
+      "learning_rate": 8.656351563089185e-06,
+      "loss": 1.1515,
+      "step": 408
+    },
+    {
+      "epoch": 1.1394700139470013,
+      "grad_norm": 1.0723262933707627,
+      "learning_rate": 8.610314397382701e-06,
+      "loss": 1.2238,
+      "step": 409
+    },
+    {
+      "epoch": 1.1422594142259415,
+      "grad_norm": 1.1092261729942694,
+      "learning_rate": 8.564307245555403e-06,
+      "loss": 1.2052,
+      "step": 410
+    },
+    {
+      "epoch": 1.1450488145048814,
+      "grad_norm": 1.0779129863872163,
+      "learning_rate": 8.51833110125153e-06,
+      "loss": 1.3471,
+      "step": 411
+    },
+    {
+      "epoch": 1.1478382147838215,
+      "grad_norm": 1.2861746029314869,
+      "learning_rate": 8.472386957445635e-06,
+      "loss": 1.2837,
+      "step": 412
+    },
+    {
+      "epoch": 1.1506276150627615,
+      "grad_norm": 1.0742534390601233,
+      "learning_rate": 8.426475806421139e-06,
+      "loss": 1.3086,
+      "step": 413
+    },
+    {
+      "epoch": 1.1534170153417016,
+      "grad_norm": 1.1872147964682518,
+      "learning_rate": 8.380598639748898e-06,
+      "loss": 1.2254,
+      "step": 414
+    },
+    {
+      "epoch": 1.1562064156206415,
+      "grad_norm": 1.07165806884352,
+      "learning_rate": 8.334756448265782e-06,
+      "loss": 1.275,
+      "step": 415
+    },
+    {
+      "epoch": 1.1589958158995817,
+      "grad_norm": 1.2751759485563616,
+      "learning_rate": 8.288950222053287e-06,
+      "loss": 1.1922,
+      "step": 416
+    },
+    {
+      "epoch": 1.1617852161785216,
+      "grad_norm": 1.1196667842580768,
+      "learning_rate": 8.243180950416142e-06,
+      "loss": 1.2673,
+      "step": 417
+    },
+    {
+      "epoch": 1.1645746164574617,
+      "grad_norm": 1.1440592720887446,
+      "learning_rate": 8.197449621860944e-06,
+      "loss": 1.3993,
+      "step": 418
+    },
+    {
+      "epoch": 1.1673640167364017,
+      "grad_norm": 1.176436140811514,
+      "learning_rate": 8.151757224074815e-06,
+      "loss": 1.3844,
+      "step": 419
+    },
+    {
+      "epoch": 1.1701534170153418,
+      "grad_norm": 1.2831755398630933,
+      "learning_rate": 8.106104743904065e-06,
+      "loss": 1.4343,
+      "step": 420
+    },
+    {
+      "epoch": 1.1729428172942817,
+      "grad_norm": 1.181724274442928,
+      "learning_rate": 8.060493167332874e-06,
+      "loss": 1.3049,
+      "step": 421
+    },
+    {
+      "epoch": 1.1757322175732217,
+      "grad_norm": 1.1464276027570777,
+      "learning_rate": 8.014923479462007e-06,
+      "loss": 1.234,
+      "step": 422
+    },
+    {
+      "epoch": 1.1785216178521618,
+      "grad_norm": 1.1377604892058606,
+      "learning_rate": 7.969396664487534e-06,
+      "loss": 1.2889,
+      "step": 423
+    },
+    {
+      "epoch": 1.1813110181311017,
+      "grad_norm": 1.1339458036648977,
+      "learning_rate": 7.923913705679573e-06,
+      "loss": 1.2602,
+      "step": 424
+    },
+    {
+      "epoch": 1.1841004184100419,
+      "grad_norm": 1.0197395887525806,
+      "learning_rate": 7.878475585361045e-06,
+      "loss": 1.126,
+      "step": 425
+    },
+    {
+      "epoch": 1.1868898186889818,
+      "grad_norm": 1.080702461827881,
+      "learning_rate": 7.833083284886484e-06,
+      "loss": 1.1639,
+      "step": 426
+    },
+    {
+      "epoch": 1.189679218967922,
+      "grad_norm": 1.2607987099270583,
+      "learning_rate": 7.787737784620803e-06,
+      "loss": 1.4396,
+      "step": 427
+    },
+    {
+      "epoch": 1.1924686192468619,
+      "grad_norm": 1.1254779807057225,
+      "learning_rate": 7.74244006391817e-06,
+      "loss": 1.3822,
+      "step": 428
+    },
+    {
+      "epoch": 1.195258019525802,
+      "grad_norm": 1.1774004879920348,
+      "learning_rate": 7.697191101100802e-06,
+      "loss": 1.3326,
+      "step": 429
+    },
+    {
+      "epoch": 1.198047419804742,
+      "grad_norm": 1.0896896006152201,
+      "learning_rate": 7.651991873437884e-06,
+      "loss": 1.2928,
+      "step": 430
+    },
+    {
+      "epoch": 1.200836820083682,
+      "grad_norm": 1.1261304598713149,
+      "learning_rate": 7.606843357124426e-06,
+      "loss": 1.2123,
+      "step": 431
+    },
+    {
+      "epoch": 1.203626220362622,
+      "grad_norm": 1.1658455006742379,
+      "learning_rate": 7.561746527260197e-06,
+      "loss": 1.3404,
+      "step": 432
+    },
+    {
+      "epoch": 1.2064156206415622,
+      "grad_norm": 1.233442454888862,
+      "learning_rate": 7.516702357828672e-06,
+      "loss": 1.4484,
+      "step": 433
+    },
+    {
+      "epoch": 1.209205020920502,
+      "grad_norm": 1.20274243777343,
+      "learning_rate": 7.471711821675973e-06,
+      "loss": 1.1722,
+      "step": 434
+    },
+    {
+      "epoch": 1.2119944211994422,
+      "grad_norm": 1.0643983498668543,
+      "learning_rate": 7.42677589048989e-06,
+      "loss": 1.1699,
+      "step": 435
+    },
+    {
+      "epoch": 1.2147838214783822,
+      "grad_norm": 1.0591582855658968,
+      "learning_rate": 7.381895534778852e-06,
+      "loss": 1.3417,
+      "step": 436
+    },
+    {
+      "epoch": 1.217573221757322,
+      "grad_norm": 1.1587399832790362,
+      "learning_rate": 7.337071723851018e-06,
+      "loss": 1.2767,
+      "step": 437
+    },
+    {
+      "epoch": 1.2203626220362622,
+      "grad_norm": 1.1559690690845343,
+      "learning_rate": 7.292305425793291e-06,
+      "loss": 1.3692,
+      "step": 438
+    },
+    {
+      "epoch": 1.2231520223152021,
+      "grad_norm": 1.1477911804467655,
+      "learning_rate": 7.247597607450446e-06,
+      "loss": 1.4562,
+      "step": 439
+    },
+    {
+      "epoch": 1.2259414225941423,
+      "grad_norm": 1.244415118958711,
+      "learning_rate": 7.2029492344042395e-06,
+      "loss": 1.3252,
+      "step": 440
+    },
+    {
+      "epoch": 1.2287308228730822,
+      "grad_norm": 1.1256137359133935,
+      "learning_rate": 7.1583612709525405e-06,
+      "loss": 1.1368,
+      "step": 441
+    },
+    {
+      "epoch": 1.2315202231520224,
+      "grad_norm": 1.1793196712059852,
+      "learning_rate": 7.113834680088527e-06,
+      "loss": 1.3781,
+      "step": 442
+    },
+    {
+      "epoch": 1.2343096234309623,
+      "grad_norm": 1.2150025131043334,
+      "learning_rate": 7.06937042347987e-06,
+      "loss": 1.2111,
+      "step": 443
+    },
+    {
+      "epoch": 1.2370990237099024,
+      "grad_norm": 1.1023846781294708,
+      "learning_rate": 7.024969461447973e-06,
+      "loss": 1.2601,
+      "step": 444
+    },
+    {
+      "epoch": 1.2398884239888424,
+      "grad_norm": 1.0716238418458055,
+      "learning_rate": 6.980632752947221e-06,
+      "loss": 1.153,
+      "step": 445
+    },
+    {
+      "epoch": 1.2426778242677825,
+      "grad_norm": 1.2507786838071617,
+      "learning_rate": 6.936361255544288e-06,
+      "loss": 1.2586,
+      "step": 446
+    },
+    {
+      "epoch": 1.2454672245467224,
+      "grad_norm": 1.214628056363252,
+      "learning_rate": 6.892155925397437e-06,
+      "loss": 1.2378,
+      "step": 447
+    },
+    {
+      "epoch": 1.2482566248256626,
+      "grad_norm": 1.1603500824157453,
+      "learning_rate": 6.848017717235878e-06,
+      "loss": 1.3192,
+      "step": 448
+    },
+    {
+      "epoch": 1.2510460251046025,
+      "grad_norm": 1.1687329408420344,
+      "learning_rate": 6.803947584339148e-06,
+      "loss": 1.2094,
+      "step": 449
+    },
+    {
+      "epoch": 1.2538354253835426,
+      "grad_norm": 1.2918425935100006,
+      "learning_rate": 6.7599464785165195e-06,
+      "loss": 1.3102,
+      "step": 450
+    },
+    {
+      "epoch": 1.2538354253835426,
+      "eval_loss": 1.5750354528427124,
+      "eval_runtime": 158.0557,
+      "eval_samples_per_second": 2.012,
+      "eval_steps_per_second": 0.127,
+      "step": 450
+    },
+    {
+      "epoch": 1.2566248256624826,
+      "grad_norm": 1.2510681039370228,
+      "learning_rate": 6.716015350086449e-06,
+      "loss": 1.2365,
+      "step": 451
+    },
+    {
+      "epoch": 1.2594142259414225,
+      "grad_norm": 1.1439803976132223,
+      "learning_rate": 6.672155147856046e-06,
+      "loss": 1.2992,
+      "step": 452
+    },
+    {
+      "epoch": 1.2622036262203626,
+      "grad_norm": 1.2149245156903248,
+      "learning_rate": 6.628366819100586e-06,
+      "loss": 1.4374,
+      "step": 453
+    },
+    {
+      "epoch": 1.2649930264993028,
+      "grad_norm": 1.1763769310735905,
+      "learning_rate": 6.584651309543049e-06,
+      "loss": 1.2003,
+      "step": 454
+    },
+    {
+      "epoch": 1.2677824267782427,
+      "grad_norm": 1.127070003440945,
+      "learning_rate": 6.54100956333369e-06,
+      "loss": 1.1715,
+      "step": 455
+    },
+    {
+      "epoch": 1.2705718270571826,
+      "grad_norm": 1.019865022262857,
+      "learning_rate": 6.497442523029663e-06,
+      "loss": 1.3491,
+      "step": 456
+    },
+    {
+      "epoch": 1.2733612273361228,
+      "grad_norm": 1.1857253940298278,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 1.2559,
+      "step": 457
+    },
+    {
+      "epoch": 1.2761506276150627,
+      "grad_norm": 1.082634058798414,
+      "learning_rate": 6.410536322278523e-06,
+      "loss": 1.1154,
+      "step": 458
+    },
+    {
+      "epoch": 1.2789400278940029,
+      "grad_norm": 1.212134850206044,
+      "learning_rate": 6.3671990387971096e-06,
+      "loss": 1.3202,
+      "step": 459
+    },
+    {
+      "epoch": 1.2817294281729428,
+      "grad_norm": 1.0917010213427312,
+      "learning_rate": 6.32394021511189e-06,
+      "loss": 1.3484,
+      "step": 460
+    },
+    {
+      "epoch": 1.284518828451883,
+      "grad_norm": 1.1428008219567098,
+      "learning_rate": 6.280760785509802e-06,
+      "loss": 1.1919,
+      "step": 461
+    },
+    {
+      "epoch": 1.2873082287308228,
+      "grad_norm": 1.0825996728928653,
+      "learning_rate": 6.237661682563055e-06,
+      "loss": 1.2082,
+      "step": 462
+    },
+    {
+      "epoch": 1.2900976290097628,
+      "grad_norm": 1.1848809666798936,
+      "learning_rate": 6.194643837109015e-06,
+      "loss": 1.2828,
+      "step": 463
+    },
+    {
+      "epoch": 1.292887029288703,
+      "grad_norm": 1.0895688626081312,
+      "learning_rate": 6.151708178230057e-06,
+      "loss": 1.2387,
+      "step": 464
+    },
+    {
+      "epoch": 1.295676429567643,
+      "grad_norm": 1.1868518830616108,
+      "learning_rate": 6.108855633233546e-06,
+      "loss": 1.297,
+      "step": 465
+    },
+    {
+      "epoch": 1.298465829846583,
+      "grad_norm": 1.1228238807592477,
+      "learning_rate": 6.066087127631761e-06,
+      "loss": 1.4407,
+      "step": 466
+    },
+    {
+      "epoch": 1.301255230125523,
+      "grad_norm": 1.17982652645882,
+      "learning_rate": 6.0234035851219604e-06,
+      "loss": 1.2222,
+      "step": 467
+    },
+    {
+      "epoch": 1.304044630404463,
+      "grad_norm": 1.2059016405123564,
+      "learning_rate": 5.9808059275663775e-06,
+      "loss": 1.2743,
+      "step": 468
+    },
+    {
+      "epoch": 1.3068340306834032,
+      "grad_norm": 1.2223828433454567,
+      "learning_rate": 5.93829507497235e-06,
+      "loss": 1.4048,
+      "step": 469
+    },
+    {
+      "epoch": 1.3096234309623431,
+      "grad_norm": 1.2327820107615224,
+      "learning_rate": 5.895871945472434e-06,
+      "loss": 1.5033,
+      "step": 470
+    },
+    {
+      "epoch": 1.312412831241283,
+      "grad_norm": 1.1838495789031667,
+      "learning_rate": 5.853537455304575e-06,
+      "loss": 1.2618,
+      "step": 471
+    },
+    {
+      "epoch": 1.3152022315202232,
+      "grad_norm": 1.0841644055995976,
+      "learning_rate": 5.811292518792324e-06,
+      "loss": 1.453,
+      "step": 472
+    },
+    {
+      "epoch": 1.3179916317991631,
+      "grad_norm": 1.3004967203117666,
+      "learning_rate": 5.769138048325087e-06,
+      "loss": 1.2257,
+      "step": 473
+    },
+    {
+      "epoch": 1.3207810320781033,
+      "grad_norm": 1.1043354920526318,
+      "learning_rate": 5.72707495433842e-06,
+      "loss": 1.2821,
+      "step": 474
+    },
+    {
+      "epoch": 1.3235704323570432,
+      "grad_norm": 1.2877538618327764,
+      "learning_rate": 5.685104145294364e-06,
+      "loss": 1.214,
+      "step": 475
+    },
+    {
+      "epoch": 1.3263598326359833,
+      "grad_norm": 1.1788804153888472,
+      "learning_rate": 5.643226527661825e-06,
+      "loss": 1.3006,
+      "step": 476
+    },
+    {
+      "epoch": 1.3291492329149233,
+      "grad_norm": 1.0526011395627175,
+      "learning_rate": 5.601443005897012e-06,
+      "loss": 1.3178,
+      "step": 477
+    },
+    {
+      "epoch": 1.3319386331938632,
+      "grad_norm": 1.0726595908035388,
+      "learning_rate": 5.55975448242386e-06,
+      "loss": 1.3458,
+      "step": 478
+    },
+    {
+      "epoch": 1.3347280334728033,
+      "grad_norm": 1.0976574017960397,
+      "learning_rate": 5.5181618576146e-06,
+      "loss": 1.3022,
+      "step": 479
+    },
+    {
+      "epoch": 1.3375174337517435,
+      "grad_norm": 1.2225185516827237,
+      "learning_rate": 5.476666029770259e-06,
+      "loss": 1.3442,
+      "step": 480
+    },
+    {
+      "epoch": 1.3403068340306834,
+      "grad_norm": 1.0680703822354123,
+      "learning_rate": 5.435267895101303e-06,
+      "loss": 1.2985,
+      "step": 481
+    },
+    {
+      "epoch": 1.3430962343096233,
+      "grad_norm": 1.186589064765597,
+      "learning_rate": 5.393968347708233e-06,
+      "loss": 1.1773,
+      "step": 482
+    },
+    {
+      "epoch": 1.3458856345885635,
+      "grad_norm": 1.0143150489355277,
+      "learning_rate": 5.352768279562315e-06,
+      "loss": 1.313,
+      "step": 483
+    },
+    {
+      "epoch": 1.3486750348675036,
+      "grad_norm": 1.2351862249444747,
+      "learning_rate": 5.311668580486311e-06,
+      "loss": 1.3821,
+      "step": 484
+    },
+    {
+      "epoch": 1.3514644351464435,
+      "grad_norm": 1.1346210320256067,
+      "learning_rate": 5.270670138135234e-06,
+      "loss": 1.334,
+      "step": 485
+    },
+    {
+      "epoch": 1.3542538354253835,
+      "grad_norm": 1.2118710215904622,
+      "learning_rate": 5.229773837977208e-06,
+      "loss": 1.3088,
+      "step": 486
+    },
+    {
+      "epoch": 1.3570432357043236,
+      "grad_norm": 1.0342577775352215,
+      "learning_rate": 5.188980563274315e-06,
+      "loss": 1.1462,
+      "step": 487
+    },
+    {
+      "epoch": 1.3598326359832635,
+      "grad_norm": 1.0728116890130244,
+      "learning_rate": 5.148291195063555e-06,
+      "loss": 1.2636,
+      "step": 488
+    },
+    {
+      "epoch": 1.3626220362622037,
+      "grad_norm": 1.1893323626916112,
+      "learning_rate": 5.107706612137776e-06,
+      "loss": 1.2052,
+      "step": 489
+    },
+    {
+      "epoch": 1.3654114365411436,
+      "grad_norm": 1.0157712327690198,
+      "learning_rate": 5.067227691026737e-06,
+      "loss": 1.1938,
+      "step": 490
+    },
+    {
+      "epoch": 1.3682008368200838,
+      "grad_norm": 1.2326467093213043,
+      "learning_rate": 5.026855305978129e-06,
+      "loss": 1.2607,
+      "step": 491
+    },
+    {
+      "epoch": 1.3709902370990237,
+      "grad_norm": 1.049878301655513,
+      "learning_rate": 4.986590328938734e-06,
+      "loss": 1.3024,
+      "step": 492
+    },
+    {
+      "epoch": 1.3737796373779636,
+      "grad_norm": 1.0826344733380577,
+      "learning_rate": 4.946433629535585e-06,
+      "loss": 1.2758,
+      "step": 493
+    },
+    {
+      "epoch": 1.3765690376569037,
+      "grad_norm": 1.1061892981697474,
+      "learning_rate": 4.906386075057164e-06,
+      "loss": 1.1803,
+      "step": 494
+    },
+    {
+      "epoch": 1.379358437935844,
+      "grad_norm": 1.08675011661269,
+      "learning_rate": 4.866448530434692e-06,
+      "loss": 1.2746,
+      "step": 495
+    },
+    {
+      "epoch": 1.379358437935844,
+      "eval_loss": 1.573391318321228,
+      "eval_runtime": 157.8173,
+      "eval_samples_per_second": 2.015,
+      "eval_steps_per_second": 0.127,
+      "step": 495
+    },
+    {
+      "epoch": 1.3821478382147838,
+      "grad_norm": 1.1281238857498397,
+      "learning_rate": 4.826621858223431e-06,
+      "loss": 1.357,
+      "step": 496
+    },
+    {
+      "epoch": 1.3849372384937237,
+      "grad_norm": 1.055676305380402,
+      "learning_rate": 4.786906918584083e-06,
+      "loss": 1.2167,
+      "step": 497
+    },
+    {
+      "epoch": 1.387726638772664,
+      "grad_norm": 1.213376805413726,
+      "learning_rate": 4.747304569264179e-06,
+      "loss": 1.4123,
+      "step": 498
+    },
+    {
+      "epoch": 1.390516039051604,
+      "grad_norm": 1.0574410266065954,
+      "learning_rate": 4.707815665579569e-06,
+      "loss": 1.3955,
+      "step": 499
+    },
+    {
+      "epoch": 1.393305439330544,
+      "grad_norm": 1.2166871008897608,
+      "learning_rate": 4.668441060395958e-06,
+      "loss": 1.3053,
+      "step": 500
+    },
+    {
+      "epoch": 1.3960948396094839,
+      "grad_norm": 1.0626532706218652,
+      "learning_rate": 4.629181604110464e-06,
+      "loss": 1.2975,
+      "step": 501
+    },
+    {
+      "epoch": 1.398884239888424,
+      "grad_norm": 1.2021150374539924,
+      "learning_rate": 4.5900381446332854e-06,
+      "loss": 1.2329,
+      "step": 502
+    },
+    {
+      "epoch": 1.401673640167364,
+      "grad_norm": 1.121645372017073,
+      "learning_rate": 4.551011527369348e-06,
+      "loss": 1.2224,
+      "step": 503
+    },
+    {
+      "epoch": 1.404463040446304,
+      "grad_norm": 1.1242323642605798,
+      "learning_rate": 4.512102595200073e-06,
+      "loss": 1.2218,
+      "step": 504
+    },
+    {
+      "epoch": 1.407252440725244,
+      "grad_norm": 1.1250999334354057,
+      "learning_rate": 4.4733121884651665e-06,
+      "loss": 1.3524,
+      "step": 505
+    },
+    {
+      "epoch": 1.4100418410041842,
+      "grad_norm": 1.190748096280525,
+      "learning_rate": 4.434641144944464e-06,
+      "loss": 1.2794,
+      "step": 506
+    },
+    {
+      "epoch": 1.412831241283124,
+      "grad_norm": 1.1256136466982283,
+      "learning_rate": 4.3960902998398524e-06,
+      "loss": 1.2871,
+      "step": 507
+    },
+    {
+      "epoch": 1.415620641562064,
+      "grad_norm": 1.3231624966545141,
+      "learning_rate": 4.357660485757211e-06,
+      "loss": 1.3109,
+      "step": 508
+    },
+    {
+      "epoch": 1.4184100418410042,
+      "grad_norm": 1.1507561161367288,
+      "learning_rate": 4.319352532688444e-06,
+      "loss": 1.2732,
+      "step": 509
+    },
+    {
+      "epoch": 1.4211994421199443,
+      "grad_norm": 1.2022076233431473,
+      "learning_rate": 4.281167267993541e-06,
+      "loss": 1.2193,
+      "step": 510
+    },
+    {
+      "epoch": 1.4239888423988842,
+      "grad_norm": 1.1014114088374245,
+      "learning_rate": 4.243105516382732e-06,
+      "loss": 1.2282,
+      "step": 511
+    },
+    {
+      "epoch": 1.4267782426778242,
+      "grad_norm": 1.1851428019160586,
+      "learning_rate": 4.205168099898652e-06,
+      "loss": 1.3455,
+      "step": 512
+    },
+    {
+      "epoch": 1.4295676429567643,
+      "grad_norm": 1.262340605187208,
+      "learning_rate": 4.167355837898585e-06,
+      "loss": 1.3841,
+      "step": 513
+    },
+    {
+      "epoch": 1.4323570432357045,
+      "grad_norm": 1.1995371048652899,
+      "learning_rate": 4.129669547036798e-06,
+      "loss": 1.3889,
+      "step": 514
+    },
+    {
+      "epoch": 1.4351464435146444,
+      "grad_norm": 1.1534627899877103,
+      "learning_rate": 4.092110041246865e-06,
+      "loss": 1.323,
+      "step": 515
+    },
+    {
+      "epoch": 1.4379358437935843,
+      "grad_norm": 1.0717749801066352,
+      "learning_rate": 4.054678131724128e-06,
+      "loss": 1.1756,
+      "step": 516
+    },
+    {
+      "epoch": 1.4407252440725244,
+      "grad_norm": 1.0332565205169049,
+      "learning_rate": 4.017374626908125e-06,
+      "loss": 1.2921,
+      "step": 517
+    },
+    {
+      "epoch": 1.4435146443514644,
+      "grad_norm": 1.299221266861857,
+      "learning_rate": 3.980200332465189e-06,
+      "loss": 1.503,
+      "step": 518
+    },
+    {
+      "epoch": 1.4463040446304045,
+      "grad_norm": 1.1258042918602684,
+      "learning_rate": 3.943156051271003e-06,
+      "loss": 1.326,
+      "step": 519
+    },
+    {
+      "epoch": 1.4490934449093444,
+      "grad_norm": 1.1498347580379522,
+      "learning_rate": 3.906242583393279e-06,
+      "loss": 1.2696,
+      "step": 520
+    },
+    {
+      "epoch": 1.4518828451882846,
+      "grad_norm": 1.0518934141037535,
+      "learning_rate": 3.8694607260744745e-06,
+      "loss": 1.2943,
+      "step": 521
+    },
+    {
+      "epoch": 1.4546722454672245,
+      "grad_norm": 1.0909311949978682,
+      "learning_rate": 3.832811273714569e-06,
+      "loss": 1.2605,
+      "step": 522
+    },
+    {
+      "epoch": 1.4574616457461644,
+      "grad_norm": 1.085659967414048,
+      "learning_rate": 3.7962950178539282e-06,
+      "loss": 1.162,
+      "step": 523
+    },
+    {
+      "epoch": 1.4602510460251046,
+      "grad_norm": 1.0373035764107983,
+      "learning_rate": 3.7599127471561746e-06,
+      "loss": 1.2543,
+      "step": 524
+    },
+    {
+      "epoch": 1.4630404463040447,
+      "grad_norm": 1.195186829033534,
+      "learning_rate": 3.7236652473911817e-06,
+      "loss": 1.1093,
+      "step": 525
+    },
+    {
+      "epoch": 1.4658298465829847,
+      "grad_norm": 1.060512460431333,
+      "learning_rate": 3.687553301418092e-06,
+      "loss": 1.1976,
+      "step": 526
+    },
+    {
+      "epoch": 1.4686192468619246,
+      "grad_norm": 1.0036394866362008,
+      "learning_rate": 3.651577689168405e-06,
+      "loss": 1.3004,
+      "step": 527
+    },
+    {
+      "epoch": 1.4714086471408647,
+      "grad_norm": 1.113980704434126,
+      "learning_rate": 3.6157391876291535e-06,
+      "loss": 1.2108,
+      "step": 528
+    },
+    {
+      "epoch": 1.4741980474198049,
+      "grad_norm": 1.0528377393119437,
+      "learning_rate": 3.580038570826093e-06,
+      "loss": 1.1086,
+      "step": 529
+    },
+    {
+      "epoch": 1.4769874476987448,
+      "grad_norm": 1.1766676130844111,
+      "learning_rate": 3.5444766098070037e-06,
+      "loss": 1.4426,
+      "step": 530
+    },
+    {
+      "epoch": 1.4797768479776847,
+      "grad_norm": 1.2618504608225378,
+      "learning_rate": 3.509054072625031e-06,
+      "loss": 1.3814,
+      "step": 531
+    },
+    {
+      "epoch": 1.4825662482566249,
+      "grad_norm": 1.2891981764585003,
+      "learning_rate": 3.473771724322108e-06,
+      "loss": 1.2466,
+      "step": 532
+    },
+    {
+      "epoch": 1.4853556485355648,
+      "grad_norm": 1.0110218638691248,
+      "learning_rate": 3.4386303269124142e-06,
+      "loss": 1.1999,
+      "step": 533
+    },
+    {
+      "epoch": 1.488145048814505,
+      "grad_norm": 1.2034400983007125,
+      "learning_rate": 3.4036306393659324e-06,
+      "loss": 1.3068,
+      "step": 534
+    },
+    {
+      "epoch": 1.4909344490934449,
+      "grad_norm": 1.1385421777709188,
+      "learning_rate": 3.3687734175920505e-06,
+      "loss": 1.1693,
+      "step": 535
+    },
+    {
+      "epoch": 1.493723849372385,
+      "grad_norm": 1.1564188245202627,
+      "learning_rate": 3.334059414423233e-06,
+      "loss": 1.2479,
+      "step": 536
+    },
+    {
+      "epoch": 1.496513249651325,
+      "grad_norm": 1.0632144492289124,
+      "learning_rate": 3.299489379598777e-06,
+      "loss": 1.2818,
+      "step": 537
+    },
+    {
+      "epoch": 1.499302649930265,
+      "grad_norm": 1.1128511815039133,
+      "learning_rate": 3.265064059748597e-06,
+      "loss": 1.2709,
+      "step": 538
+    },
+    {
+      "epoch": 1.502092050209205,
+      "grad_norm": 1.1560070366323953,
+      "learning_rate": 3.2307841983771182e-06,
+      "loss": 1.2745,
+      "step": 539
+    },
+    {
+      "epoch": 1.5048814504881451,
+      "grad_norm": 1.0217133320576668,
+      "learning_rate": 3.196650535847201e-06,
+      "loss": 1.1794,
+      "step": 540
+    },
+    {
+      "epoch": 1.5048814504881451,
+      "eval_loss": 1.5692052841186523,
+      "eval_runtime": 157.6777,
+      "eval_samples_per_second": 2.017,
+      "eval_steps_per_second": 0.127,
+      "step": 540
+    },
+    {
+      "epoch": 1.507670850767085,
+      "grad_norm": 1.0737456883772618,
+      "learning_rate": 3.162663809364178e-06,
+      "loss": 1.225,
+      "step": 541
+    },
+    {
+      "epoch": 1.510460251046025,
+      "grad_norm": 1.0374293851760548,
+      "learning_rate": 3.1288247529599035e-06,
+      "loss": 1.1417,
+      "step": 542
+    },
+    {
+      "epoch": 1.5132496513249651,
+      "grad_norm": 1.0980653797401247,
+      "learning_rate": 3.095134097476904e-06,
+      "loss": 1.3211,
+      "step": 543
+    },
+    {
+      "epoch": 1.5160390516039053,
+      "grad_norm": 1.164741159420771,
+      "learning_rate": 3.061592570552623e-06,
+      "loss": 1.2578,
+      "step": 544
+    },
+    {
+      "epoch": 1.5188284518828452,
+      "grad_norm": 1.0189005727543412,
+      "learning_rate": 3.0282008966036647e-06,
+      "loss": 1.2959,
+      "step": 545
+    },
+    {
+      "epoch": 1.5216178521617851,
+      "grad_norm": 1.208051694511716,
+      "learning_rate": 2.9949597968101883e-06,
+      "loss": 1.1262,
+      "step": 546
+    },
+    {
+      "epoch": 1.5244072524407253,
+      "grad_norm": 1.1335684047851176,
+      "learning_rate": 2.9618699891002843e-06,
+      "loss": 1.3335,
+      "step": 547
+    },
+    {
+      "epoch": 1.5271966527196654,
+      "grad_norm": 1.1202431404000823,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 1.3486,
+      "step": 548
+    },
+    {
+      "epoch": 1.5299860529986054,
+      "grad_norm": 1.2028343451745414,
+      "learning_rate": 2.8961471052904855e-06,
+      "loss": 1.271,
+      "step": 549
+    },
+    {
+      "epoch": 1.5327754532775453,
+      "grad_norm": 1.4110270438588248,
+      "learning_rate": 2.8635154486473935e-06,
+      "loss": 1.5144,
+      "step": 550
+    },
+    {
+      "epoch": 1.5355648535564854,
+      "grad_norm": 1.2457401488648763,
+      "learning_rate": 2.831037922970855e-06,
+      "loss": 1.2106,
+      "step": 551
+    },
+    {
+      "epoch": 1.5383542538354253,
+      "grad_norm": 1.1795479805808884,
+      "learning_rate": 2.798715229697592e-06,
+      "loss": 1.397,
+      "step": 552
+    },
+    {
+      "epoch": 1.5411436541143653,
+      "grad_norm": 1.079451545181616,
+      "learning_rate": 2.7665480669203383e-06,
+      "loss": 1.1888,
+      "step": 553
+    },
+    {
+      "epoch": 1.5439330543933054,
+      "grad_norm": 1.1389012691863731,
+      "learning_rate": 2.7345371293727306e-06,
+      "loss": 1.4245,
+      "step": 554
+    },
+    {
+      "epoch": 1.5467224546722456,
+      "grad_norm": 1.2537407788152353,
+      "learning_rate": 2.702683108414326e-06,
+      "loss": 1.1767,
+      "step": 555
+    },
+    {
+      "epoch": 1.5495118549511855,
+      "grad_norm": 1.1869960292618957,
+      "learning_rate": 2.6709866920156434e-06,
+      "loss": 1.2403,
+      "step": 556
+    },
+    {
+      "epoch": 1.5523012552301254,
+      "grad_norm": 1.1984799417334413,
+      "learning_rate": 2.639448564743328e-06,
+      "loss": 1.1762,
+      "step": 557
+    },
+    {
+      "epoch": 1.5550906555090656,
+      "grad_norm": 1.0508009270090828,
+      "learning_rate": 2.6080694077453663e-06,
+      "loss": 1.2374,
+      "step": 558
+    },
+    {
+      "epoch": 1.5578800557880057,
+      "grad_norm": 0.9958047904038109,
+      "learning_rate": 2.57684989873636e-06,
+      "loss": 1.1931,
+      "step": 559
+    },
+    {
+      "epoch": 1.5606694560669456,
+      "grad_norm": 1.4532459122588939,
+      "learning_rate": 2.545790711982897e-06,
+      "loss": 1.2112,
+      "step": 560
+    },
+    {
+      "epoch": 1.5634588563458856,
+      "grad_norm": 1.0915855125380947,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 1.2518,
+      "step": 561
+    },
+    {
+      "epoch": 1.5662482566248257,
+      "grad_norm": 1.1643223936142897,
+      "learning_rate": 2.484155984981588e-06,
+      "loss": 1.3178,
+      "step": 562
+    },
+    {
+      "epoch": 1.5690376569037658,
+      "grad_norm": 1.022111849112051,
+      "learning_rate": 2.4535817758961644e-06,
+      "loss": 1.2716,
+      "step": 563
+    },
+    {
+      "epoch": 1.5718270571827058,
+      "grad_norm": 1.095023581771314,
+      "learning_rate": 2.423170551362375e-06,
+      "loss": 1.2788,
+      "step": 564
+    },
+    {
+      "epoch": 1.5746164574616457,
+      "grad_norm": 1.1372999724043513,
+      "learning_rate": 2.3929229681898005e-06,
+      "loss": 1.3119,
+      "step": 565
+    },
+    {
+      "epoch": 1.5774058577405858,
+      "grad_norm": 1.1591219486471167,
+      "learning_rate": 2.3628396796537588e-06,
+      "loss": 1.2631,
+      "step": 566
+    },
+    {
+      "epoch": 1.5801952580195258,
+      "grad_norm": 1.172516182274785,
+      "learning_rate": 2.332921335481205e-06,
+      "loss": 1.1941,
+      "step": 567
+    },
+    {
+      "epoch": 1.5829846582984657,
+      "grad_norm": 1.0361078535539063,
+      "learning_rate": 2.3031685818366844e-06,
+      "loss": 1.4233,
+      "step": 568
+    },
+    {
+      "epoch": 1.5857740585774058,
+      "grad_norm": 1.1410393864290862,
+      "learning_rate": 2.2735820613083837e-06,
+      "loss": 1.2099,
+      "step": 569
+    },
+    {
+      "epoch": 1.588563458856346,
+      "grad_norm": 1.0458954860259906,
+      "learning_rate": 2.2441624128942496e-06,
+      "loss": 1.1334,
+      "step": 570
+    },
+    {
+      "epoch": 1.591352859135286,
+      "grad_norm": 0.9922646637863874,
+      "learning_rate": 2.2149102719882044e-06,
+      "loss": 1.2161,
+      "step": 571
+    },
+    {
+      "epoch": 1.5941422594142258,
+      "grad_norm": 1.223669783642085,
+      "learning_rate": 2.185826270366395e-06,
+      "loss": 1.2298,
+      "step": 572
+    },
+    {
+      "epoch": 1.596931659693166,
+      "grad_norm": 1.130588399655404,
+      "learning_rate": 2.156911036173568e-06,
+      "loss": 1.3821,
+      "step": 573
+    },
+    {
+      "epoch": 1.5997210599721061,
+      "grad_norm": 1.1640107614447786,
+      "learning_rate": 2.1281651939094996e-06,
+      "loss": 1.355,
+      "step": 574
+    },
+    {
+      "epoch": 1.602510460251046,
+      "grad_norm": 1.0361339199236095,
+      "learning_rate": 2.0995893644155007e-06,
+      "loss": 1.1427,
+      "step": 575
+    },
+    {
+      "epoch": 1.605299860529986,
+      "grad_norm": 1.0756714810106114,
+      "learning_rate": 2.0711841648610254e-06,
+      "loss": 1.4321,
+      "step": 576
+    },
+    {
+      "epoch": 1.6080892608089261,
+      "grad_norm": 1.2293913938862664,
+      "learning_rate": 2.0429502087303164e-06,
+      "loss": 1.2833,
+      "step": 577
+    },
+    {
+      "epoch": 1.6108786610878663,
+      "grad_norm": 1.0940351824479477,
+      "learning_rate": 2.0148881058091764e-06,
+      "loss": 1.2686,
+      "step": 578
+    },
+    {
+      "epoch": 1.6136680613668062,
+      "grad_norm": 1.1484352102687134,
+      "learning_rate": 1.9869984621717888e-06,
+      "loss": 1.3778,
+      "step": 579
+    },
+    {
+      "epoch": 1.616457461645746,
+      "grad_norm": 1.0880304504137697,
+      "learning_rate": 1.959281880167626e-06,
+      "loss": 1.1422,
+      "step": 580
+    },
+    {
+      "epoch": 1.6192468619246863,
+      "grad_norm": 1.0783569825622126,
+      "learning_rate": 1.931738958408457e-06,
+      "loss": 1.1755,
+      "step": 581
+    },
+    {
+      "epoch": 1.6220362622036262,
+      "grad_norm": 1.164727739321155,
+      "learning_rate": 1.904370291755383e-06,
+      "loss": 1.2424,
+      "step": 582
+    },
+    {
+      "epoch": 1.624825662482566,
+      "grad_norm": 0.9860870493237442,
+      "learning_rate": 1.8771764713060359e-06,
+      "loss": 1.1261,
+      "step": 583
+    },
+    {
+      "epoch": 1.6276150627615062,
+      "grad_norm": 1.0665626106580621,
+      "learning_rate": 1.8501580843817724e-06,
+      "loss": 1.1584,
+      "step": 584
+    },
+    {
+      "epoch": 1.6304044630404464,
+      "grad_norm": 1.0530713538661243,
+      "learning_rate": 1.8233157145150183e-06,
+      "loss": 1.2141,
+      "step": 585
+    },
+    {
+      "epoch": 1.6304044630404464,
+      "eval_loss": 1.567124605178833,
+      "eval_runtime": 156.7218,
+      "eval_samples_per_second": 2.029,
+      "eval_steps_per_second": 0.128,
+      "step": 585
+    },
+    {
+      "epoch": 1.6331938633193863,
+      "grad_norm": 1.0952013416862578,
+      "learning_rate": 1.796649941436638e-06,
+      "loss": 1.5202,
+      "step": 586
+    },
+    {
+      "epoch": 1.6359832635983262,
+      "grad_norm": 1.0394591589506494,
+      "learning_rate": 1.7701613410634367e-06,
+      "loss": 1.089,
+      "step": 587
+    },
+    {
+      "epoch": 1.6387726638772664,
+      "grad_norm": 1.1385837446661573,
+      "learning_rate": 1.7438504854857164e-06,
+      "loss": 1.4171,
+      "step": 588
+    },
+    {
+      "epoch": 1.6415620641562065,
+      "grad_norm": 1.1579845229078256,
+      "learning_rate": 1.717717942954914e-06,
+      "loss": 1.2647,
+      "step": 589
+    },
+    {
+      "epoch": 1.6443514644351465,
+      "grad_norm": 1.1031285177601524,
+      "learning_rate": 1.6917642778713294e-06,
+      "loss": 1.2457,
+      "step": 590
+    },
+    {
+      "epoch": 1.6471408647140864,
+      "grad_norm": 1.0508122526584638,
+      "learning_rate": 1.6659900507719406e-06,
+      "loss": 1.0069,
+      "step": 591
+    },
+    {
+      "epoch": 1.6499302649930265,
+      "grad_norm": 1.0068175097731142,
+      "learning_rate": 1.6403958183182977e-06,
+      "loss": 1.1628,
+      "step": 592
+    },
+    {
+      "epoch": 1.6527196652719667,
+      "grad_norm": 1.0401833631623687,
+      "learning_rate": 1.614982133284495e-06,
+      "loss": 1.2582,
+      "step": 593
+    },
+    {
+      "epoch": 1.6555090655509066,
+      "grad_norm": 1.144936824787253,
+      "learning_rate": 1.5897495445452338e-06,
+      "loss": 1.1106,
+      "step": 594
+    },
+    {
+      "epoch": 1.6582984658298465,
+      "grad_norm": 1.0918460272521961,
+      "learning_rate": 1.5646985970639717e-06,
+      "loss": 1.3263,
+      "step": 595
+    },
+    {
+      "epoch": 1.6610878661087867,
+      "grad_norm": 1.0858377257764582,
+      "learning_rate": 1.5398298318811467e-06,
+      "loss": 1.3094,
+      "step": 596
+    },
+    {
+      "epoch": 1.6638772663877266,
+      "grad_norm": 1.0118984847794699,
+      "learning_rate": 1.5151437861025032e-06,
+      "loss": 1.1784,
+      "step": 597
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.0751551188626693,
+      "learning_rate": 1.4906409928874788e-06,
+      "loss": 1.3051,
+      "step": 598
+    },
+    {
+      "epoch": 1.6694560669456067,
+      "grad_norm": 1.0516245409484366,
+      "learning_rate": 1.466321981437694e-06,
+      "loss": 1.1268,
+      "step": 599
+    },
+    {
+      "epoch": 1.6722454672245468,
+      "grad_norm": 1.1788465793610776,
+      "learning_rate": 1.4421872769855262e-06,
+      "loss": 1.308,
+      "step": 600
+    },
+    {
+      "epoch": 1.6750348675034867,
+      "grad_norm": 1.2007034931476699,
+      "learning_rate": 1.4182374007827605e-06,
+      "loss": 1.4343,
+      "step": 601
+    },
+    {
+      "epoch": 1.6778242677824267,
+      "grad_norm": 1.2103949946678392,
+      "learning_rate": 1.3944728700893395e-06,
+      "loss": 1.2218,
+      "step": 602
+    },
+    {
+      "epoch": 1.6806136680613668,
+      "grad_norm": 1.0584542090538895,
+      "learning_rate": 1.3708941981621814e-06,
+      "loss": 1.224,
+      "step": 603
+    },
+    {
+      "epoch": 1.683403068340307,
+      "grad_norm": 1.0336649248685688,
+      "learning_rate": 1.3475018942441055e-06,
+      "loss": 1.2935,
+      "step": 604
+    },
+    {
+      "epoch": 1.6861924686192469,
+      "grad_norm": 1.1512837538473248,
+      "learning_rate": 1.324296463552821e-06,
+      "loss": 1.381,
+      "step": 605
+    },
+    {
+      "epoch": 1.6889818688981868,
+      "grad_norm": 1.290033668736083,
+      "learning_rate": 1.3012784072700335e-06,
+      "loss": 1.3635,
+      "step": 606
+    },
+    {
+      "epoch": 1.691771269177127,
+      "grad_norm": 1.0146444183334564,
+      "learning_rate": 1.2784482225306061e-06,
+      "loss": 1.443,
+      "step": 607
+    },
+    {
+      "epoch": 1.694560669456067,
+      "grad_norm": 1.1412978490213836,
+      "learning_rate": 1.2558064024118177e-06,
+      "loss": 1.3073,
+      "step": 608
+    },
+    {
+      "epoch": 1.697350069735007,
+      "grad_norm": 1.1777814520870202,
+      "learning_rate": 1.2333534359227383e-06,
+      "loss": 1.2376,
+      "step": 609
+    },
+    {
+      "epoch": 1.700139470013947,
+      "grad_norm": 1.1085356099373989,
+      "learning_rate": 1.2110898079936394e-06,
+      "loss": 1.3031,
+      "step": 610
+    },
+    {
+      "epoch": 1.702928870292887,
+      "grad_norm": 0.9946576676439562,
+      "learning_rate": 1.1890159994655425e-06,
+      "loss": 1.2625,
+      "step": 611
+    },
+    {
+      "epoch": 1.705718270571827,
+      "grad_norm": 1.0714426792098188,
+      "learning_rate": 1.1671324870798195e-06,
+      "loss": 1.2853,
+      "step": 612
+    },
+    {
+      "epoch": 1.708507670850767,
+      "grad_norm": 1.0522568487043535,
+      "learning_rate": 1.1454397434679022e-06,
+      "loss": 1.1105,
+      "step": 613
+    },
+    {
+      "epoch": 1.711297071129707,
+      "grad_norm": 1.0522857112160622,
+      "learning_rate": 1.1239382371410713e-06,
+      "loss": 1.2473,
+      "step": 614
+    },
+    {
+      "epoch": 1.7140864714086472,
+      "grad_norm": 1.0336259276395867,
+      "learning_rate": 1.1026284324803493e-06,
+      "loss": 1.2868,
+      "step": 615
+    },
+    {
+      "epoch": 1.7168758716875872,
+      "grad_norm": 1.2751218435331244,
+      "learning_rate": 1.0815107897264555e-06,
+      "loss": 1.2264,
+      "step": 616
+    },
+    {
+      "epoch": 1.719665271966527,
+      "grad_norm": 1.1350263226089796,
+      "learning_rate": 1.060585764969867e-06,
+      "loss": 1.395,
+      "step": 617
+    },
+    {
+      "epoch": 1.7224546722454672,
+      "grad_norm": 1.1178186477812129,
+      "learning_rate": 1.039853810140987e-06,
+      "loss": 1.2731,
+      "step": 618
+    },
+    {
+      "epoch": 1.7252440725244074,
+      "grad_norm": 1.1204071361063843,
+      "learning_rate": 1.0193153730003603e-06,
+      "loss": 1.2937,
+      "step": 619
+    },
+    {
+      "epoch": 1.7280334728033473,
+      "grad_norm": 1.1132725442704139,
+      "learning_rate": 9.989708971290212e-07,
+      "loss": 1.1601,
+      "step": 620
+    },
+    {
+      "epoch": 1.7308228730822872,
+      "grad_norm": 1.0581136550779104,
+      "learning_rate": 9.788208219188932e-07,
+      "loss": 1.2412,
+      "step": 621
+    },
+    {
+      "epoch": 1.7336122733612274,
+      "grad_norm": 1.1604202470265874,
+      "learning_rate": 9.588655825633274e-07,
+      "loss": 1.3738,
+      "step": 622
+    },
+    {
+      "epoch": 1.7364016736401675,
+      "grad_norm": 1.0474443993366487,
+      "learning_rate": 9.391056100476736e-07,
+      "loss": 1.2614,
+      "step": 623
+    },
+    {
+      "epoch": 1.7391910739191074,
+      "grad_norm": 1.157197894710453,
+      "learning_rate": 9.195413311399948e-07,
+      "loss": 1.2351,
+      "step": 624
+    },
+    {
+      "epoch": 1.7419804741980474,
+      "grad_norm": 1.0010635765579132,
+      "learning_rate": 9.001731683818338e-07,
+      "loss": 1.2271,
+      "step": 625
+    },
+    {
+      "epoch": 1.7447698744769875,
+      "grad_norm": 1.1156313217870746,
+      "learning_rate": 8.810015400790994e-07,
+      "loss": 1.3973,
+      "step": 626
+    },
+    {
+      "epoch": 1.7475592747559274,
+      "grad_norm": 1.1100544753368768,
+      "learning_rate": 8.620268602930271e-07,
+      "loss": 1.2771,
+      "step": 627
+    },
+    {
+      "epoch": 1.7503486750348674,
+      "grad_norm": 1.0209108814380907,
+      "learning_rate": 8.432495388312345e-07,
+      "loss": 1.1404,
+      "step": 628
+    },
+    {
+      "epoch": 1.7531380753138075,
+      "grad_norm": 1.0264564550590858,
+      "learning_rate": 8.246699812388714e-07,
+      "loss": 1.1826,
+      "step": 629
+    },
+    {
+      "epoch": 1.7559274755927476,
+      "grad_norm": 1.1456496522168542,
+      "learning_rate": 8.062885887898642e-07,
+      "loss": 1.1795,
+      "step": 630
+    },
+    {
+      "epoch": 1.7559274755927476,
+      "eval_loss": 1.566035270690918,
+      "eval_runtime": 156.576,
+      "eval_samples_per_second": 2.031,
+      "eval_steps_per_second": 0.128,
+      "step": 630
+    },
+    {
+      "epoch": 1.7587168758716876,
+      "grad_norm": 1.209657377296861,
+      "learning_rate": 7.881057584782448e-07,
+      "loss": 1.2647,
+      "step": 631
+    },
+    {
+      "epoch": 1.7615062761506275,
+      "grad_norm": 1.106313249918267,
+      "learning_rate": 7.701218830095825e-07,
+      "loss": 1.2989,
+      "step": 632
+    },
+    {
+      "epoch": 1.7642956764295676,
+      "grad_norm": 1.061607452064161,
+      "learning_rate": 7.523373507924947e-07,
+      "loss": 1.127,
+      "step": 633
+    },
+    {
+      "epoch": 1.7670850767085078,
+      "grad_norm": 1.0309962944155062,
+      "learning_rate": 7.34752545930264e-07,
+      "loss": 1.365,
+      "step": 634
+    },
+    {
+      "epoch": 1.7698744769874477,
+      "grad_norm": 1.0740382538755116,
+      "learning_rate": 7.17367848212539e-07,
+      "loss": 1.1811,
+      "step": 635
+    },
+    {
+      "epoch": 1.7726638772663876,
+      "grad_norm": 1.0118161768941756,
+      "learning_rate": 7.001836331071365e-07,
+      "loss": 1.1549,
+      "step": 636
+    },
+    {
+      "epoch": 1.7754532775453278,
+      "grad_norm": 1.0783526848995528,
+      "learning_rate": 6.83200271751927e-07,
+      "loss": 1.3528,
+      "step": 637
+    },
+    {
+      "epoch": 1.778242677824268,
+      "grad_norm": 1.2637211185830795,
+      "learning_rate": 6.664181309468232e-07,
+      "loss": 1.4158,
+      "step": 638
+    },
+    {
+      "epoch": 1.7810320781032078,
+      "grad_norm": 0.9850477816960693,
+      "learning_rate": 6.498375731458529e-07,
+      "loss": 1.178,
+      "step": 639
+    },
+    {
+      "epoch": 1.7838214783821478,
+      "grad_norm": 1.229804093046329,
+      "learning_rate": 6.334589564493343e-07,
+      "loss": 1.521,
+      "step": 640
+    },
+    {
+      "epoch": 1.786610878661088,
+      "grad_norm": 1.177611617767322,
+      "learning_rate": 6.17282634596148e-07,
+      "loss": 1.3065,
+      "step": 641
+    },
+    {
+      "epoch": 1.7894002789400278,
+      "grad_norm": 1.0078560722736492,
+      "learning_rate": 6.013089569560826e-07,
+      "loss": 1.2331,
+      "step": 642
+    },
+    {
+      "epoch": 1.7921896792189678,
+      "grad_norm": 1.098699610719127,
+      "learning_rate": 5.85538268522301e-07,
+      "loss": 1.3184,
+      "step": 643
+    },
+    {
+      "epoch": 1.794979079497908,
+      "grad_norm": 1.0487509124500176,
+      "learning_rate": 5.699709099038852e-07,
+      "loss": 1.2638,
+      "step": 644
+    },
+    {
+      "epoch": 1.797768479776848,
+      "grad_norm": 1.0890541943234957,
+      "learning_rate": 5.546072173184791e-07,
+      "loss": 1.2163,
+      "step": 645
+    },
+    {
+      "epoch": 1.800557880055788,
+      "grad_norm": 1.0567320167434624,
+      "learning_rate": 5.394475225850338e-07,
+      "loss": 1.2271,
+      "step": 646
+    },
+    {
+      "epoch": 1.803347280334728,
+      "grad_norm": 1.1317365221900546,
+      "learning_rate": 5.244921531166247e-07,
+      "loss": 1.1866,
+      "step": 647
+    },
+    {
+      "epoch": 1.806136680613668,
+      "grad_norm": 1.0330011534115215,
+      "learning_rate": 5.097414319134042e-07,
+      "loss": 1.1212,
+      "step": 648
+    },
+    {
+      "epoch": 1.8089260808926082,
+      "grad_norm": 1.015573816046942,
+      "learning_rate": 4.951956775556e-07,
+      "loss": 1.2419,
+      "step": 649
+    },
+    {
+      "epoch": 1.8117154811715481,
+      "grad_norm": 1.1529960692876453,
+      "learning_rate": 4.808552041966608e-07,
+      "loss": 1.2704,
+      "step": 650
+    },
+    {
+      "epoch": 1.814504881450488,
+      "grad_norm": 1.1756706995531485,
+      "learning_rate": 4.667203215564431e-07,
+      "loss": 1.2621,
+      "step": 651
+    },
+    {
+      "epoch": 1.8172942817294282,
+      "grad_norm": 1.1561630667450327,
+      "learning_rate": 4.5279133491454406e-07,
+      "loss": 1.1975,
+      "step": 652
+    },
+    {
+      "epoch": 1.8200836820083683,
+      "grad_norm": 1.0163918973404071,
+      "learning_rate": 4.3906854510370245e-07,
+      "loss": 1.3134,
+      "step": 653
+    },
+    {
+      "epoch": 1.8228730822873083,
+      "grad_norm": 1.0875438781955151,
+      "learning_rate": 4.255522485032959e-07,
+      "loss": 1.2165,
+      "step": 654
+    },
+    {
+      "epoch": 1.8256624825662482,
+      "grad_norm": 1.1001170561409346,
+      "learning_rate": 4.1224273703294515e-07,
+      "loss": 1.2211,
+      "step": 655
+    },
+    {
+      "epoch": 1.8284518828451883,
+      "grad_norm": 1.2508157828119448,
+      "learning_rate": 3.991402981462045e-07,
+      "loss": 1.196,
+      "step": 656
+    },
+    {
+      "epoch": 1.8312412831241283,
+      "grad_norm": 1.116690750175023,
+      "learning_rate": 3.862452148243623e-07,
+      "loss": 1.2891,
+      "step": 657
+    },
+    {
+      "epoch": 1.8340306834030682,
+      "grad_norm": 1.0513074080819311,
+      "learning_rate": 3.735577655703171e-07,
+      "loss": 1.2379,
+      "step": 658
+    },
+    {
+      "epoch": 1.8368200836820083,
+      "grad_norm": 1.080338244933159,
+      "learning_rate": 3.610782244025768e-07,
+      "loss": 1.2624,
+      "step": 659
+    },
+    {
+      "epoch": 1.8396094839609485,
+      "grad_norm": 1.091397768273919,
+      "learning_rate": 3.488068608493245e-07,
+      "loss": 1.1787,
+      "step": 660
+    },
+    {
+      "epoch": 1.8423988842398884,
+      "grad_norm": 1.057025164258322,
+      "learning_rate": 3.367439399426087e-07,
+      "loss": 1.2321,
+      "step": 661
+    },
+    {
+      "epoch": 1.8451882845188283,
+      "grad_norm": 1.0549536904866916,
+      "learning_rate": 3.2488972221262125e-07,
+      "loss": 1.2471,
+      "step": 662
+    },
+    {
+      "epoch": 1.8479776847977685,
+      "grad_norm": 1.1325587091161893,
+      "learning_rate": 3.132444636820575e-07,
+      "loss": 1.3322,
+      "step": 663
+    },
+    {
+      "epoch": 1.8507670850767086,
+      "grad_norm": 0.9899621873046871,
+      "learning_rate": 3.018084158606005e-07,
+      "loss": 1.303,
+      "step": 664
+    },
+    {
+      "epoch": 1.8535564853556485,
+      "grad_norm": 1.1125409681766663,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 1.2377,
+      "step": 665
+    },
+    {
+      "epoch": 1.8563458856345885,
+      "grad_norm": 1.0259685972073294,
+      "learning_rate": 2.79564935786143e-07,
+      "loss": 1.2921,
+      "step": 666
+    },
+    {
+      "epoch": 1.8591352859135286,
+      "grad_norm": 1.0955040567135619,
+      "learning_rate": 2.687579839390153e-07,
+      "loss": 1.2584,
+      "step": 667
+    },
+    {
+      "epoch": 1.8619246861924688,
+      "grad_norm": 1.0075912628262043,
+      "learning_rate": 2.5816120360236176e-07,
+      "loss": 1.0987,
+      "step": 668
+    },
+    {
+      "epoch": 1.8647140864714087,
+      "grad_norm": 1.1261524385918704,
+      "learning_rate": 2.4777482364124695e-07,
+      "loss": 1.1685,
+      "step": 669
+    },
+    {
+      "epoch": 1.8675034867503486,
+      "grad_norm": 1.0461353702295435,
+      "learning_rate": 2.375990683765894e-07,
+      "loss": 1.1753,
+      "step": 670
+    },
+    {
+      "epoch": 1.8702928870292888,
+      "grad_norm": 1.2303056718670446,
+      "learning_rate": 2.2763415758032316e-07,
+      "loss": 1.4123,
+      "step": 671
+    },
+    {
+      "epoch": 1.8730822873082287,
+      "grad_norm": 1.1576581446135057,
+      "learning_rate": 2.1788030647064363e-07,
+      "loss": 1.2674,
+      "step": 672
+    },
+    {
+      "epoch": 1.8758716875871686,
+      "grad_norm": 1.026907055744568,
+      "learning_rate": 2.0833772570736376e-07,
+      "loss": 1.2099,
+      "step": 673
+    },
+    {
+      "epoch": 1.8786610878661087,
+      "grad_norm": 1.1791758006752504,
+      "learning_rate": 1.9900662138736204e-07,
+      "loss": 1.3735,
+      "step": 674
+    },
+    {
+      "epoch": 1.881450488145049,
+      "grad_norm": 1.1279876288402806,
+      "learning_rate": 1.8988719504013375e-07,
+      "loss": 1.4297,
+      "step": 675
+    },
+    {
+      "epoch": 1.881450488145049,
+      "eval_loss": 1.5654959678649902,
+      "eval_runtime": 159.1028,
+      "eval_samples_per_second": 1.999,
+      "eval_steps_per_second": 0.126,
+      "step": 675
+    },
+    {
+      "epoch": 1.8842398884239888,
+      "grad_norm": 1.1213114912871756,
+      "learning_rate": 1.809796436234379e-07,
+      "loss": 1.2678,
+      "step": 676
+    },
+    {
+      "epoch": 1.8870292887029287,
+      "grad_norm": 1.0231468542671707,
+      "learning_rate": 1.7228415951904165e-07,
+      "loss": 1.2013,
+      "step": 677
+    },
+    {
+      "epoch": 1.8898186889818689,
+      "grad_norm": 1.0510276191815386,
+      "learning_rate": 1.6380093052856482e-07,
+      "loss": 1.1256,
+      "step": 678
+    },
+    {
+      "epoch": 1.892608089260809,
+      "grad_norm": 1.0191912341158118,
+      "learning_rate": 1.5553013986942645e-07,
+      "loss": 1.082,
+      "step": 679
+    },
+    {
+      "epoch": 1.895397489539749,
+      "grad_norm": 1.207566562721887,
+      "learning_rate": 1.474719661708901e-07,
+      "loss": 1.2673,
+      "step": 680
+    },
+    {
+      "epoch": 1.8981868898186889,
+      "grad_norm": 1.0338184707057456,
+      "learning_rate": 1.3962658347019819e-07,
+      "loss": 1.2071,
+      "step": 681
+    },
+    {
+      "epoch": 1.900976290097629,
+      "grad_norm": 0.9931451101369468,
+      "learning_rate": 1.3199416120881714e-07,
+      "loss": 1.1395,
+      "step": 682
+    },
+    {
+      "epoch": 1.9037656903765692,
+      "grad_norm": 1.0474529441467644,
+      "learning_rate": 1.245748642287814e-07,
+      "loss": 1.4288,
+      "step": 683
+    },
+    {
+      "epoch": 1.906555090655509,
+      "grad_norm": 1.1607216939431546,
+      "learning_rate": 1.1736885276912747e-07,
+      "loss": 1.1854,
+      "step": 684
+    },
+    {
+      "epoch": 1.909344490934449,
+      "grad_norm": 1.1608661429089615,
+      "learning_rate": 1.103762824624377e-07,
+      "loss": 1.2324,
+      "step": 685
+    },
+    {
+      "epoch": 1.9121338912133892,
+      "grad_norm": 1.1506898890364043,
+      "learning_rate": 1.0359730433147308e-07,
+      "loss": 1.21,
+      "step": 686
+    },
+    {
+      "epoch": 1.914923291492329,
+      "grad_norm": 1.0906516636448746,
+      "learning_rate": 9.70320647859213e-08,
+      "loss": 1.1794,
+      "step": 687
+    },
+    {
+      "epoch": 1.917712691771269,
+      "grad_norm": 1.1330946112091915,
+      "learning_rate": 9.068070561922382e-08,
+      "loss": 1.5722,
+      "step": 688
+    },
+    {
+      "epoch": 1.9205020920502092,
+      "grad_norm": 1.1295013861816299,
+      "learning_rate": 8.454336400552154e-08,
+      "loss": 1.3525,
+      "step": 689
+    },
+    {
+      "epoch": 1.9232914923291493,
+      "grad_norm": 1.1286978983557747,
+      "learning_rate": 7.862017249668507e-08,
+      "loss": 1.3517,
+      "step": 690
+    },
+    {
+      "epoch": 1.9260808926080892,
+      "grad_norm": 1.1387934858630715,
+      "learning_rate": 7.291125901946027e-08,
+      "loss": 1.2812,
+      "step": 691
+    },
+    {
+      "epoch": 1.9288702928870292,
+      "grad_norm": 1.0805575638942468,
+      "learning_rate": 6.741674687269828e-08,
+      "loss": 1.2045,
+      "step": 692
+    },
+    {
+      "epoch": 1.9316596931659693,
+      "grad_norm": 1.0744214697690395,
+      "learning_rate": 6.21367547246976e-08,
+      "loss": 1.1589,
+      "step": 693
+    },
+    {
+      "epoch": 1.9344490934449095,
+      "grad_norm": 1.0235585599512225,
+      "learning_rate": 5.70713966106351e-08,
+      "loss": 1.2926,
+      "step": 694
+    },
+    {
+      "epoch": 1.9372384937238494,
+      "grad_norm": 1.1802905924340767,
+      "learning_rate": 5.2220781930111263e-08,
+      "loss": 1.1622,
+      "step": 695
+    },
+    {
+      "epoch": 1.9400278940027893,
+      "grad_norm": 1.1656421842233815,
+      "learning_rate": 4.758501544477767e-08,
+      "loss": 1.3938,
+      "step": 696
+    },
+    {
+      "epoch": 1.9428172942817294,
+      "grad_norm": 1.067790059159501,
+      "learning_rate": 4.316419727608434e-08,
+      "loss": 1.2852,
+      "step": 697
+    },
+    {
+      "epoch": 1.9456066945606696,
+      "grad_norm": 1.1935070336816525,
+      "learning_rate": 3.895842290311147e-08,
+      "loss": 1.4083,
+      "step": 698
+    },
+    {
+      "epoch": 1.9483960948396095,
+      "grad_norm": 1.065042379517144,
+      "learning_rate": 3.4967783160507753e-08,
+      "loss": 1.2027,
+      "step": 699
+    },
+    {
+      "epoch": 1.9511854951185494,
+      "grad_norm": 1.0656424373795819,
+      "learning_rate": 3.1192364236528606e-08,
+      "loss": 1.2319,
+      "step": 700
+    },
+    {
+      "epoch": 1.9539748953974896,
+      "grad_norm": 1.0984360801120403,
+      "learning_rate": 2.763224767117767e-08,
+      "loss": 1.3806,
+      "step": 701
+    },
+    {
+      "epoch": 1.9567642956764297,
+      "grad_norm": 1.1607449042507518,
+      "learning_rate": 2.4287510354441547e-08,
+      "loss": 1.4186,
+      "step": 702
+    },
+    {
+      "epoch": 1.9595536959553694,
+      "grad_norm": 1.086242716677333,
+      "learning_rate": 2.115822452463223e-08,
+      "loss": 1.4163,
+      "step": 703
+    },
+    {
+      "epoch": 1.9623430962343096,
+      "grad_norm": 1.153441075255345,
+      "learning_rate": 1.824445776682504e-08,
+      "loss": 1.4069,
+      "step": 704
+    },
+    {
+      "epoch": 1.9651324965132497,
+      "grad_norm": 1.182011664361845,
+      "learning_rate": 1.554627301140199e-08,
+      "loss": 1.3192,
+      "step": 705
+    },
+    {
+      "epoch": 1.9679218967921897,
+      "grad_norm": 1.1297529991451876,
+      "learning_rate": 1.3063728532686225e-08,
+      "loss": 1.3927,
+      "step": 706
+    },
+    {
+      "epoch": 1.9707112970711296,
+      "grad_norm": 1.156781945646368,
+      "learning_rate": 1.0796877947691909e-08,
+      "loss": 1.3695,
+      "step": 707
+    },
+    {
+      "epoch": 1.9735006973500697,
+      "grad_norm": 1.0922775917479406,
+      "learning_rate": 8.745770214959592e-09,
+      "loss": 1.4199,
+      "step": 708
+    },
+    {
+      "epoch": 1.9762900976290099,
+      "grad_norm": 1.1820051106743557,
+      "learning_rate": 6.910449633501515e-09,
+      "loss": 1.4922,
+      "step": 709
+    },
+    {
+      "epoch": 1.9790794979079498,
+      "grad_norm": 1.1679810963701596,
+      "learning_rate": 5.290955841843471e-09,
+      "loss": 1.2322,
+      "step": 710
+    },
+    {
+      "epoch": 1.9818688981868897,
+      "grad_norm": 1.0936947420752203,
+      "learning_rate": 3.887323817173272e-09,
+      "loss": 1.3895,
+      "step": 711
+    },
+    {
+      "epoch": 1.9846582984658299,
+      "grad_norm": 1.1188292476177197,
+      "learning_rate": 2.699583874578027e-09,
+      "loss": 1.3052,
+      "step": 712
+    },
+    {
+      "epoch": 1.98744769874477,
+      "grad_norm": 1.2140293339255397,
+      "learning_rate": 1.7277616663946562e-09,
+      "loss": 1.2469,
+      "step": 713
+    },
+    {
+      "epoch": 1.99023709902371,
+      "grad_norm": 1.1295059733866153,
+      "learning_rate": 9.718781816536738e-10,
+      "loss": 1.275,
+      "step": 714
+    },
+    {
+      "epoch": 1.9930264993026499,
+      "grad_norm": 1.0320785394496956,
+      "learning_rate": 4.319497456273247e-10,
+      "loss": 1.3604,
+      "step": 715
+    },
+    {
+      "epoch": 1.99581589958159,
+      "grad_norm": 1.2124847139889416,
+      "learning_rate": 1.0798801947764503e-10,
+      "loss": 1.3216,
+      "step": 716
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 179,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 466393183027200.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}