{
  "best_metric": 0.4757327735424042,
  "best_model_checkpoint": "miner_id_24/checkpoint-300",
  "epoch": 0.09686989162680874,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032289963875602916,
      "grad_norm": 0.8824386596679688,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.9502,
      "step": 1
    },
    {
      "epoch": 0.00032289963875602916,
      "eval_loss": 1.3877121210098267,
      "eval_runtime": 93.1564,
      "eval_samples_per_second": 2.673,
      "eval_steps_per_second": 2.673,
      "step": 1
    },
    {
      "epoch": 0.0006457992775120583,
      "grad_norm": 0.9450064897537231,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.0243,
      "step": 2
    },
    {
      "epoch": 0.0009686989162680874,
      "grad_norm": 0.8851878046989441,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.0441,
      "step": 3
    },
    {
      "epoch": 0.0012915985550241166,
      "grad_norm": 0.9229115843772888,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.9838,
      "step": 4
    },
    {
      "epoch": 0.0016144981937801458,
      "grad_norm": 0.8223733901977539,
      "learning_rate": 0.00015,
      "loss": 0.9295,
      "step": 5
    },
    {
      "epoch": 0.0019373978325361748,
      "grad_norm": 0.608881950378418,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.8621,
      "step": 6
    },
    {
      "epoch": 0.002260297471292204,
      "grad_norm": 0.5287642478942871,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.7054,
      "step": 7
    },
    {
      "epoch": 0.0025831971100482333,
      "grad_norm": 0.5346184372901917,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.7059,
      "step": 8
    },
    {
      "epoch": 0.0029060967488042625,
      "grad_norm": 0.5089557766914368,
      "learning_rate": 0.00027,
      "loss": 0.697,
      "step": 9
    },
    {
      "epoch": 0.0032289963875602916,
      "grad_norm": 0.5970950722694397,
      "learning_rate": 0.0003,
      "loss": 0.7296,
      "step": 10
    },
    {
      "epoch": 0.0035518960263163203,
      "grad_norm": 0.5149356722831726,
      "learning_rate": 0.0002999911984174669,
      "loss": 0.652,
      "step": 11
    },
    {
      "epoch": 0.0038747956650723495,
      "grad_norm": 0.5151774287223816,
      "learning_rate": 0.0002999647947027726,
      "loss": 0.5781,
      "step": 12
    },
    {
      "epoch": 0.004197695303828379,
      "grad_norm": 0.8652517795562744,
      "learning_rate": 0.0002999207919545099,
      "loss": 0.6031,
      "step": 13
    },
    {
      "epoch": 0.004520594942584408,
      "grad_norm": 0.5327635407447815,
      "learning_rate": 0.0002998591953365965,
      "loss": 0.5459,
      "step": 14
    },
    {
      "epoch": 0.004843494581340437,
      "grad_norm": 0.6640207171440125,
      "learning_rate": 0.00029978001207766854,
      "loss": 0.6103,
      "step": 15
    },
    {
      "epoch": 0.005166394220096467,
      "grad_norm": 0.5555705428123474,
      "learning_rate": 0.00029968325147023263,
      "loss": 0.5229,
      "step": 16
    },
    {
      "epoch": 0.005489293858852495,
      "grad_norm": 0.5247602462768555,
      "learning_rate": 0.000299568924869575,
      "loss": 0.5202,
      "step": 17
    },
    {
      "epoch": 0.005812193497608525,
      "grad_norm": 0.42580658197402954,
      "learning_rate": 0.00029943704569242917,
      "loss": 0.5354,
      "step": 18
    },
    {
      "epoch": 0.006135093136364554,
      "grad_norm": 0.43852224946022034,
      "learning_rate": 0.0002992876294154013,
      "loss": 0.5391,
      "step": 19
    },
    {
      "epoch": 0.006457992775120583,
      "grad_norm": 0.5213896632194519,
      "learning_rate": 0.00029912069357315393,
      "loss": 0.514,
      "step": 20
    },
    {
      "epoch": 0.006780892413876612,
      "grad_norm": 0.4253011643886566,
      "learning_rate": 0.00029893625775634835,
      "loss": 0.5246,
      "step": 21
    },
    {
      "epoch": 0.007103792052632641,
      "grad_norm": 0.6179479956626892,
      "learning_rate": 0.0002987343436093454,
      "loss": 0.5259,
      "step": 22
    },
    {
      "epoch": 0.00742669169138867,
      "grad_norm": 0.4869435429573059,
      "learning_rate": 0.00029851497482766547,
      "loss": 0.4949,
      "step": 23
    },
    {
      "epoch": 0.007749591330144699,
      "grad_norm": 0.46306025981903076,
      "learning_rate": 0.00029827817715520773,
      "loss": 0.5344,
      "step": 24
    },
    {
      "epoch": 0.008072490968900729,
      "grad_norm": 0.5446106195449829,
      "learning_rate": 0.0002980239783812289,
      "loss": 0.6442,
      "step": 25
    },
    {
      "epoch": 0.008395390607656757,
      "grad_norm": 0.4747227430343628,
      "learning_rate": 0.0002977524083370822,
      "loss": 0.5129,
      "step": 26
    },
    {
      "epoch": 0.008718290246412786,
      "grad_norm": 0.4436034560203552,
      "learning_rate": 0.00029746349889271645,
      "loss": 0.5176,
      "step": 27
    },
    {
      "epoch": 0.009041189885168817,
      "grad_norm": 0.458401620388031,
      "learning_rate": 0.0002971572839529358,
      "loss": 0.5984,
      "step": 28
    },
    {
      "epoch": 0.009364089523924845,
      "grad_norm": 0.41444727778434753,
      "learning_rate": 0.00029683379945342125,
      "loss": 0.5384,
      "step": 29
    },
    {
      "epoch": 0.009686989162680874,
      "grad_norm": 0.4278819262981415,
      "learning_rate": 0.000296493083356513,
      "loss": 0.4995,
      "step": 30
    },
    {
      "epoch": 0.010009888801436903,
      "grad_norm": 0.5811014175415039,
      "learning_rate": 0.00029613517564675565,
      "loss": 0.5204,
      "step": 31
    },
    {
      "epoch": 0.010332788440192933,
      "grad_norm": 0.43319976329803467,
      "learning_rate": 0.0002957601183262058,
      "loss": 0.5376,
      "step": 32
    },
    {
      "epoch": 0.010655688078948962,
      "grad_norm": 0.5323597192764282,
      "learning_rate": 0.000295367955409503,
      "loss": 0.5722,
      "step": 33
    },
    {
      "epoch": 0.01097858771770499,
      "grad_norm": 0.49440231919288635,
      "learning_rate": 0.00029495873291870436,
      "loss": 0.519,
      "step": 34
    },
    {
      "epoch": 0.01130148735646102,
      "grad_norm": 0.585383951663971,
      "learning_rate": 0.0002945324988778834,
      "loss": 0.5643,
      "step": 35
    },
    {
      "epoch": 0.01162438699521705,
      "grad_norm": 0.6207253336906433,
      "learning_rate": 0.00029408930330749477,
      "loss": 0.5647,
      "step": 36
    },
    {
      "epoch": 0.011947286633973079,
      "grad_norm": 0.5334969162940979,
      "learning_rate": 0.0002936291982185036,
      "loss": 0.6132,
      "step": 37
    },
    {
      "epoch": 0.012270186272729107,
      "grad_norm": 0.5715814828872681,
      "learning_rate": 0.00029315223760628217,
      "loss": 0.5453,
      "step": 38
    },
    {
      "epoch": 0.012593085911485136,
      "grad_norm": 0.5439808964729309,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.6189,
      "step": 39
    },
    {
      "epoch": 0.012915985550241166,
      "grad_norm": 0.4831181466579437,
      "learning_rate": 0.00029214797567742035,
      "loss": 0.558,
      "step": 40
    },
    {
      "epoch": 0.013238885188997195,
      "grad_norm": 0.44526898860931396,
      "learning_rate": 0.00029162079221537,
      "loss": 0.5486,
      "step": 41
    },
    {
      "epoch": 0.013561784827753224,
      "grad_norm": 0.4262256324291229,
      "learning_rate": 0.0002910769889254386,
      "loss": 0.5953,
      "step": 42
    },
    {
      "epoch": 0.013884684466509253,
      "grad_norm": 1.0412601232528687,
      "learning_rate": 0.0002905166296253533,
      "loss": 0.6746,
      "step": 43
    },
    {
      "epoch": 0.014207584105265281,
      "grad_norm": 0.4333534836769104,
      "learning_rate": 0.0002899397800757626,
      "loss": 0.5598,
      "step": 44
    },
    {
      "epoch": 0.014530483744021312,
      "grad_norm": 0.44549164175987244,
      "learning_rate": 0.0002893465079725187,
      "loss": 0.5453,
      "step": 45
    },
    {
      "epoch": 0.01485338338277734,
      "grad_norm": 0.4520653486251831,
      "learning_rate": 0.0002887368829387333,
      "loss": 0.55,
      "step": 46
    },
    {
      "epoch": 0.01517628302153337,
      "grad_norm": 0.4351714849472046,
      "learning_rate": 0.0002881109765166071,
      "loss": 0.5768,
      "step": 47
    },
    {
      "epoch": 0.015499182660289398,
      "grad_norm": 0.49298447370529175,
      "learning_rate": 0.00028746886215903387,
      "loss": 0.5117,
      "step": 48
    },
    {
      "epoch": 0.01582208229904543,
      "grad_norm": 0.5363653302192688,
      "learning_rate": 0.00028681061522098047,
      "loss": 0.6614,
      "step": 49
    },
    {
      "epoch": 0.016144981937801457,
      "grad_norm": 0.6216686367988586,
      "learning_rate": 0.0002861363129506435,
      "loss": 0.6039,
      "step": 50
    },
    {
      "epoch": 0.016144981937801457,
      "eval_loss": 0.5689713358879089,
      "eval_runtime": 93.1562,
      "eval_samples_per_second": 2.673,
      "eval_steps_per_second": 2.673,
      "step": 50
    },
    {
      "epoch": 0.016467881576557486,
      "grad_norm": 0.4990479052066803,
      "learning_rate": 0.0002854460344803842,
      "loss": 0.6526,
      "step": 51
    },
    {
      "epoch": 0.016790781215313515,
      "grad_norm": 0.45471203327178955,
      "learning_rate": 0.00028473986081744163,
      "loss": 0.5901,
      "step": 52
    },
    {
      "epoch": 0.017113680854069543,
      "grad_norm": 0.3418448567390442,
      "learning_rate": 0.000284017874834426,
      "loss": 0.5179,
      "step": 53
    },
    {
      "epoch": 0.017436580492825572,
      "grad_norm": 0.5214569568634033,
      "learning_rate": 0.0002832801612595937,
      "loss": 0.531,
      "step": 54
    },
    {
      "epoch": 0.017759480131581604,
      "grad_norm": 0.4000888764858246,
      "learning_rate": 0.0002825268066669034,
      "loss": 0.5312,
      "step": 55
    },
    {
      "epoch": 0.018082379770337633,
      "grad_norm": 0.3511790335178375,
      "learning_rate": 0.00028175789946585693,
      "loss": 0.5187,
      "step": 56
    },
    {
      "epoch": 0.018405279409093662,
      "grad_norm": 0.40245896577835083,
      "learning_rate": 0.0002809735298911234,
      "loss": 0.5141,
      "step": 57
    },
    {
      "epoch": 0.01872817904784969,
      "grad_norm": 0.3479350805282593,
      "learning_rate": 0.00028017378999195015,
      "loss": 0.5353,
      "step": 58
    },
    {
      "epoch": 0.01905107868660572,
      "grad_norm": 0.3354577124118805,
      "learning_rate": 0.0002793587736213603,
      "loss": 0.5223,
      "step": 59
    },
    {
      "epoch": 0.019373978325361748,
      "grad_norm": 0.36033692955970764,
      "learning_rate": 0.00027852857642513836,
      "loss": 0.535,
      "step": 60
    },
    {
      "epoch": 0.019696877964117777,
      "grad_norm": 0.40051642060279846,
      "learning_rate": 0.00027768329583060635,
      "loss": 0.4658,
      "step": 61
    },
    {
      "epoch": 0.020019777602873805,
      "grad_norm": 0.41961464285850525,
      "learning_rate": 0.00027682303103518976,
      "loss": 0.5517,
      "step": 62
    },
    {
      "epoch": 0.020342677241629838,
      "grad_norm": 0.4324147403240204,
      "learning_rate": 0.00027594788299477655,
      "loss": 0.5352,
      "step": 63
    },
    {
      "epoch": 0.020665576880385866,
      "grad_norm": 0.39792558550834656,
      "learning_rate": 0.0002750579544118695,
      "loss": 0.5369,
      "step": 64
    },
    {
      "epoch": 0.020988476519141895,
      "grad_norm": 0.4185834228992462,
      "learning_rate": 0.00027415334972353357,
      "loss": 0.5323,
      "step": 65
    },
    {
      "epoch": 0.021311376157897924,
      "grad_norm": 0.36977943778038025,
      "learning_rate": 0.0002732341750891397,
      "loss": 0.4811,
      "step": 66
    },
    {
      "epoch": 0.021634275796653953,
      "grad_norm": 0.38211461901664734,
      "learning_rate": 0.00027230053837790666,
      "loss": 0.508,
      "step": 67
    },
    {
      "epoch": 0.02195717543540998,
      "grad_norm": 0.3872841000556946,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.4985,
      "step": 68
    },
    {
      "epoch": 0.02228007507416601,
      "grad_norm": 0.3474493622779846,
      "learning_rate": 0.0002703903186748843,
      "loss": 0.4411,
      "step": 69
    },
    {
      "epoch": 0.02260297471292204,
      "grad_norm": 0.3461940586566925,
      "learning_rate": 0.00026941395985584653,
      "loss": 0.4987,
      "step": 70
    },
    {
      "epoch": 0.022925874351678067,
      "grad_norm": 0.3902309238910675,
      "learning_rate": 0.00026842358727916524,
      "loss": 0.5151,
      "step": 71
    },
    {
      "epoch": 0.0232487739904341,
      "grad_norm": 0.34906888008117676,
      "learning_rate": 0.0002674193171694533,
      "loss": 0.5087,
      "step": 72
    },
    {
      "epoch": 0.02357167362919013,
      "grad_norm": 0.40804773569107056,
      "learning_rate": 0.0002664012673822609,
      "loss": 0.5772,
      "step": 73
    },
    {
      "epoch": 0.023894573267946157,
      "grad_norm": 0.3935260474681854,
      "learning_rate": 0.0002653695573902443,
      "loss": 0.4854,
      "step": 74
    },
    {
      "epoch": 0.024217472906702186,
      "grad_norm": 0.3976927101612091,
      "learning_rate": 0.0002643243082691454,
      "loss": 0.4943,
      "step": 75
    },
    {
      "epoch": 0.024540372545458215,
      "grad_norm": 0.4370949864387512,
      "learning_rate": 0.0002632656426835831,
      "loss": 0.5562,
      "step": 76
    },
    {
      "epoch": 0.024863272184214243,
      "grad_norm": 0.37720787525177,
      "learning_rate": 0.00026219368487265753,
      "loss": 0.4861,
      "step": 77
    },
    {
      "epoch": 0.025186171822970272,
      "grad_norm": 0.38937804102897644,
      "learning_rate": 0.00026110856063537083,
      "loss": 0.4428,
      "step": 78
    },
    {
      "epoch": 0.0255090714617263,
      "grad_norm": 0.41925427317619324,
      "learning_rate": 0.00026001039731586334,
      "loss": 0.5127,
      "step": 79
    },
    {
      "epoch": 0.025831971100482333,
      "grad_norm": 0.4304789900779724,
      "learning_rate": 0.0002588993237884696,
      "loss": 0.4446,
      "step": 80
    },
    {
      "epoch": 0.02615487073923836,
      "grad_norm": 0.4581892490386963,
      "learning_rate": 0.00025777547044259435,
      "loss": 0.5083,
      "step": 81
    },
    {
      "epoch": 0.02647777037799439,
      "grad_norm": 0.40676695108413696,
      "learning_rate": 0.0002566389691674106,
      "loss": 0.4466,
      "step": 82
    },
    {
      "epoch": 0.02680067001675042,
      "grad_norm": 0.4280904531478882,
      "learning_rate": 0.00025548995333638197,
      "loss": 0.5397,
      "step": 83
    },
    {
      "epoch": 0.027123569655506448,
      "grad_norm": 0.500979483127594,
      "learning_rate": 0.00025432855779161076,
      "loss": 0.5162,
      "step": 84
    },
    {
      "epoch": 0.027446469294262477,
      "grad_norm": 0.46338576078414917,
      "learning_rate": 0.00025315491882801347,
      "loss": 0.52,
      "step": 85
    },
    {
      "epoch": 0.027769368933018505,
      "grad_norm": 0.4408024251461029,
      "learning_rate": 0.00025196917417732615,
      "loss": 0.5225,
      "step": 86
    },
    {
      "epoch": 0.028092268571774534,
      "grad_norm": 0.5076299905776978,
      "learning_rate": 0.0002507714629919409,
      "loss": 0.5791,
      "step": 87
    },
    {
      "epoch": 0.028415168210530563,
      "grad_norm": 0.4352111220359802,
      "learning_rate": 0.0002495619258285757,
      "loss": 0.5098,
      "step": 88
    },
    {
      "epoch": 0.028738067849286595,
      "grad_norm": 0.5041966438293457,
      "learning_rate": 0.0002483407046317794,
      "loss": 0.5932,
      "step": 89
    },
    {
      "epoch": 0.029060967488042624,
      "grad_norm": 0.452606737613678,
      "learning_rate": 0.00024710794271727413,
      "loss": 0.606,
      "step": 90
    },
    {
      "epoch": 0.029383867126798652,
      "grad_norm": 0.40284180641174316,
      "learning_rate": 0.0002458637847551364,
      "loss": 0.537,
      "step": 91
    },
    {
      "epoch": 0.02970676676555468,
      "grad_norm": 0.4412550628185272,
      "learning_rate": 0.00024460837675281926,
      "loss": 0.487,
      "step": 92
    },
    {
      "epoch": 0.03002966640431071,
      "grad_norm": 0.4605487287044525,
      "learning_rate": 0.00024334186603801807,
      "loss": 0.5168,
      "step": 93
    },
    {
      "epoch": 0.03035256604306674,
      "grad_norm": 0.4492901861667633,
      "learning_rate": 0.00024206440124138062,
      "loss": 0.5853,
      "step": 94
    },
    {
      "epoch": 0.030675465681822767,
      "grad_norm": 0.4852229356765747,
      "learning_rate": 0.0002407761322790648,
      "loss": 0.5914,
      "step": 95
    },
    {
      "epoch": 0.030998365320578796,
      "grad_norm": 0.436937153339386,
      "learning_rate": 0.00023947721033514512,
      "loss": 0.5557,
      "step": 96
    },
    {
      "epoch": 0.03132126495933483,
      "grad_norm": 0.49399349093437195,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.5293,
      "step": 97
    },
    {
      "epoch": 0.03164416459809086,
      "grad_norm": 0.4873245358467102,
      "learning_rate": 0.0002368480184717773,
      "loss": 0.4905,
      "step": 98
    },
    {
      "epoch": 0.031967064236846886,
      "grad_norm": 0.5261349678039551,
      "learning_rate": 0.00023551805709965147,
      "loss": 0.512,
      "step": 99
    },
    {
      "epoch": 0.032289963875602914,
      "grad_norm": 0.6633840799331665,
      "learning_rate": 0.00023417805980435736,
      "loss": 0.5687,
      "step": 100
    },
    {
      "epoch": 0.032289963875602914,
      "eval_loss": 0.549869179725647,
      "eval_runtime": 93.2109,
      "eval_samples_per_second": 2.671,
      "eval_steps_per_second": 2.671,
      "step": 100
    },
    {
      "epoch": 0.03261286351435894,
      "grad_norm": 0.5682958960533142,
      "learning_rate": 0.00023282818384051866,
      "loss": 0.6406,
      "step": 101
    },
    {
      "epoch": 0.03293576315311497,
      "grad_norm": 0.4537736773490906,
      "learning_rate": 0.00023146858762206489,
      "loss": 0.5788,
      "step": 102
    },
    {
      "epoch": 0.033258662791871,
      "grad_norm": 0.3675607442855835,
      "learning_rate": 0.00023009943070364044,
      "loss": 0.5094,
      "step": 103
    },
    {
      "epoch": 0.03358156243062703,
      "grad_norm": 0.30980873107910156,
      "learning_rate": 0.0002287208737618801,
      "loss": 0.5131,
      "step": 104
    },
    {
      "epoch": 0.03390446206938306,
      "grad_norm": 0.31538596749305725,
      "learning_rate": 0.00022733307857655325,
      "loss": 0.4996,
      "step": 105
    },
    {
      "epoch": 0.03422736170813909,
      "grad_norm": 0.3792458474636078,
      "learning_rate": 0.00022593620801157808,
      "loss": 0.5272,
      "step": 106
    },
    {
      "epoch": 0.034550261346895116,
      "grad_norm": 0.3597868084907532,
      "learning_rate": 0.00022453042599590882,
      "loss": 0.5219,
      "step": 107
    },
    {
      "epoch": 0.034873160985651144,
      "grad_norm": 0.3305104970932007,
      "learning_rate": 0.00022311589750429787,
      "loss": 0.4561,
      "step": 108
    },
    {
      "epoch": 0.03519606062440717,
      "grad_norm": 0.30127620697021484,
      "learning_rate": 0.00022169278853793545,
      "loss": 0.4988,
      "step": 109
    },
    {
      "epoch": 0.03551896026316321,
      "grad_norm": 0.34320175647735596,
      "learning_rate": 0.00022026126610496852,
      "loss": 0.5181,
      "step": 110
    },
    {
      "epoch": 0.03584185990191924,
      "grad_norm": 0.3284643292427063,
      "learning_rate": 0.0002188214982009016,
      "loss": 0.5342,
      "step": 111
    },
    {
      "epoch": 0.036164759540675266,
      "grad_norm": 0.3455963730812073,
      "learning_rate": 0.00021737365378888187,
      "loss": 0.4768,
      "step": 112
    },
    {
      "epoch": 0.036487659179431295,
      "grad_norm": 0.3220086097717285,
      "learning_rate": 0.00021591790277987043,
      "loss": 0.4888,
      "step": 113
    },
    {
      "epoch": 0.036810558818187324,
      "grad_norm": 0.3551287353038788,
      "learning_rate": 0.00021445441601270276,
      "loss": 0.4567,
      "step": 114
    },
    {
      "epoch": 0.03713345845694335,
      "grad_norm": 0.35259413719177246,
      "learning_rate": 0.00021298336523403968,
      "loss": 0.4779,
      "step": 115
    },
    {
      "epoch": 0.03745635809569938,
      "grad_norm": 0.3786124587059021,
      "learning_rate": 0.0002115049230782124,
      "loss": 0.4885,
      "step": 116
    },
    {
      "epoch": 0.03777925773445541,
      "grad_norm": 0.3437775671482086,
      "learning_rate": 0.00021001926304696296,
      "loss": 0.4335,
      "step": 117
    },
    {
      "epoch": 0.03810215737321144,
      "grad_norm": 0.3531520962715149,
      "learning_rate": 0.00020852655948908316,
      "loss": 0.4604,
      "step": 118
    },
    {
      "epoch": 0.03842505701196747,
      "grad_norm": 0.374508261680603,
      "learning_rate": 0.0002070269875799538,
      "loss": 0.4603,
      "step": 119
    },
    {
      "epoch": 0.038747956650723496,
      "grad_norm": 0.3716915249824524,
      "learning_rate": 0.00020552072330098716,
      "loss": 0.4878,
      "step": 120
    },
    {
      "epoch": 0.039070856289479525,
      "grad_norm": 0.41532278060913086,
      "learning_rate": 0.0002040079434189748,
      "loss": 0.5234,
      "step": 121
    },
    {
      "epoch": 0.03939375592823555,
      "grad_norm": 0.3630126416683197,
      "learning_rate": 0.00020248882546534326,
      "loss": 0.4509,
      "step": 122
    },
    {
      "epoch": 0.03971665556699158,
      "grad_norm": 0.3788343071937561,
      "learning_rate": 0.00020096354771531976,
      "loss": 0.4989,
      "step": 123
    },
    {
      "epoch": 0.04003955520574761,
      "grad_norm": 0.34830769896507263,
      "learning_rate": 0.00019943228916701104,
      "loss": 0.459,
      "step": 124
    },
    {
      "epoch": 0.04036245484450364,
      "grad_norm": 0.3595748543739319,
      "learning_rate": 0.00019789522952039695,
      "loss": 0.4525,
      "step": 125
    },
    {
      "epoch": 0.040685354483259675,
      "grad_norm": 0.3879833519458771,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.483,
      "step": 126
    },
    {
      "epoch": 0.041008254122015704,
      "grad_norm": 0.44336938858032227,
      "learning_rate": 0.00019480442911492702,
      "loss": 0.5148,
      "step": 127
    },
    {
      "epoch": 0.04133115376077173,
      "grad_norm": 0.4268869161605835,
      "learning_rate": 0.00019325105107520263,
      "loss": 0.5186,
      "step": 128
    },
    {
      "epoch": 0.04165405339952776,
      "grad_norm": 0.40015068650245667,
      "learning_rate": 0.00019169259733286913,
      "loss": 0.4856,
      "step": 129
    },
    {
      "epoch": 0.04197695303828379,
      "grad_norm": 0.3713054656982422,
      "learning_rate": 0.00019012925077938314,
      "loss": 0.4546,
      "step": 130
    },
    {
      "epoch": 0.04229985267703982,
      "grad_norm": 0.45219311118125916,
      "learning_rate": 0.0001885611948803941,
      "loss": 0.4606,
      "step": 131
    },
    {
      "epoch": 0.04262275231579585,
      "grad_norm": 0.3732009828090668,
      "learning_rate": 0.0001869886136542143,
      "loss": 0.502,
      "step": 132
    },
    {
      "epoch": 0.042945651954551876,
      "grad_norm": 0.5309696793556213,
      "learning_rate": 0.00018541169165022298,
      "loss": 0.591,
      "step": 133
    },
    {
      "epoch": 0.043268551593307905,
      "grad_norm": 0.4451289772987366,
      "learning_rate": 0.00018383061392720913,
      "loss": 0.5503,
      "step": 134
    },
    {
      "epoch": 0.043591451232063934,
      "grad_norm": 0.49492791295051575,
      "learning_rate": 0.0001822455660316536,
      "loss": 0.6013,
      "step": 135
    },
    {
      "epoch": 0.04391435087081996,
      "grad_norm": 0.4255249500274658,
      "learning_rate": 0.00018065673397595473,
      "loss": 0.5237,
      "step": 136
    },
    {
      "epoch": 0.04423725050957599,
      "grad_norm": 0.35570111870765686,
      "learning_rate": 0.00017906430421659876,
      "loss": 0.4749,
      "step": 137
    },
    {
      "epoch": 0.04456015014833202,
      "grad_norm": 0.4393974840641022,
      "learning_rate": 0.00017746846363227842,
      "loss": 0.5613,
      "step": 138
    },
    {
      "epoch": 0.04488304978708805,
      "grad_norm": 0.4163194000720978,
      "learning_rate": 0.00017586939950196186,
      "loss": 0.5197,
      "step": 139
    },
    {
      "epoch": 0.04520594942584408,
      "grad_norm": 0.40177619457244873,
      "learning_rate": 0.00017426729948291474,
      "loss": 0.5775,
      "step": 140
    },
    {
      "epoch": 0.045528849064600106,
      "grad_norm": 0.38539931178092957,
      "learning_rate": 0.00017266235158867752,
      "loss": 0.5486,
      "step": 141
    },
    {
      "epoch": 0.045851748703356135,
      "grad_norm": 0.3907434642314911,
      "learning_rate": 0.00017105474416700164,
      "loss": 0.52,
      "step": 142
    },
    {
      "epoch": 0.04617464834211217,
      "grad_norm": 0.45413726568222046,
      "learning_rate": 0.0001694446658777458,
      "loss": 0.5052,
      "step": 143
    },
    {
      "epoch": 0.0464975479808682,
      "grad_norm": 0.3584253489971161,
      "learning_rate": 0.00016783230567073596,
      "loss": 0.4945,
      "step": 144
    },
    {
      "epoch": 0.04682044761962423,
      "grad_norm": 0.38787075877189636,
      "learning_rate": 0.00016621785276359127,
      "loss": 0.5507,
      "step": 145
    },
    {
      "epoch": 0.04714334725838026,
      "grad_norm": 0.4273373484611511,
      "learning_rate": 0.0001646014966195185,
      "loss": 0.5588,
      "step": 146
    },
    {
      "epoch": 0.047466246897136286,
      "grad_norm": 0.3610289692878723,
      "learning_rate": 0.00016298342692507763,
      "loss": 0.5056,
      "step": 147
    },
    {
      "epoch": 0.047789146535892314,
      "grad_norm": 0.4982016682624817,
      "learning_rate": 0.00016136383356792156,
      "loss": 0.6056,
      "step": 148
    },
    {
      "epoch": 0.04811204617464834,
      "grad_norm": 0.48546895384788513,
      "learning_rate": 0.0001597429066145116,
      "loss": 0.6287,
      "step": 149
    },
    {
      "epoch": 0.04843494581340437,
      "grad_norm": 0.4680643379688263,
      "learning_rate": 0.0001581208362878126,
      "loss": 0.5451,
      "step": 150
    },
    {
      "epoch": 0.04843494581340437,
      "eval_loss": 0.5126909613609314,
      "eval_runtime": 93.2305,
      "eval_samples_per_second": 2.671,
      "eval_steps_per_second": 2.671,
      "step": 150
    },
    {
      "epoch": 0.0487578454521604,
      "grad_norm": 0.4066923260688782,
      "learning_rate": 0.00015649781294496933,
      "loss": 0.5668,
      "step": 151
    },
    {
      "epoch": 0.04908074509091643,
      "grad_norm": 0.4061080813407898,
      "learning_rate": 0.00015487402705496707,
      "loss": 0.5461,
      "step": 152
    },
    {
      "epoch": 0.04940364472967246,
      "grad_norm": 0.33173874020576477,
      "learning_rate": 0.0001532496691762796,
      "loss": 0.4937,
      "step": 153
    },
    {
      "epoch": 0.04972654436842849,
      "grad_norm": 0.3234449625015259,
      "learning_rate": 0.00015162492993450597,
      "loss": 0.5055,
      "step": 154
    },
    {
      "epoch": 0.050049444007184515,
      "grad_norm": 0.26888391375541687,
      "learning_rate": 0.00015,
      "loss": 0.4302,
      "step": 155
    },
    {
      "epoch": 0.050372343645940544,
      "grad_norm": 0.2688259482383728,
      "learning_rate": 0.00014837507006549403,
      "loss": 0.4681,
      "step": 156
    },
    {
      "epoch": 0.05069524328469657,
      "grad_norm": 0.29257914423942566,
      "learning_rate": 0.00014675033082372038,
      "loss": 0.4916,
      "step": 157
    },
    {
      "epoch": 0.0510181429234526,
      "grad_norm": 0.3311769664287567,
      "learning_rate": 0.00014512597294503293,
      "loss": 0.4852,
      "step": 158
    },
    {
      "epoch": 0.05134104256220863,
      "grad_norm": 0.3170052468776703,
      "learning_rate": 0.00014350218705503067,
      "loss": 0.4772,
      "step": 159
    },
    {
      "epoch": 0.051663942200964666,
      "grad_norm": 0.34309279918670654,
      "learning_rate": 0.00014187916371218736,
      "loss": 0.4622,
      "step": 160
    },
    {
      "epoch": 0.051986841839720695,
      "grad_norm": 0.32580074667930603,
      "learning_rate": 0.00014025709338548836,
      "loss": 0.4839,
      "step": 161
    },
    {
      "epoch": 0.05230974147847672,
      "grad_norm": 0.317793071269989,
      "learning_rate": 0.00013863616643207844,
      "loss": 0.4923,
      "step": 162
    },
    {
      "epoch": 0.05263264111723275,
      "grad_norm": 0.30965691804885864,
      "learning_rate": 0.00013701657307492235,
      "loss": 0.4769,
      "step": 163
    },
    {
      "epoch": 0.05295554075598878,
      "grad_norm": 0.3157210052013397,
      "learning_rate": 0.00013539850338048154,
      "loss": 0.4798,
      "step": 164
    },
    {
      "epoch": 0.05327844039474481,
      "grad_norm": 0.35382428765296936,
      "learning_rate": 0.00013378214723640876,
      "loss": 0.5212,
      "step": 165
    },
    {
      "epoch": 0.05360134003350084,
      "grad_norm": 0.29083287715911865,
      "learning_rate": 0.00013216769432926404,
      "loss": 0.4257,
      "step": 166
    },
    {
      "epoch": 0.05392423967225687,
      "grad_norm": 0.3195495009422302,
      "learning_rate": 0.00013055533412225422,
      "loss": 0.4177,
      "step": 167
    },
    {
      "epoch": 0.054247139311012896,
      "grad_norm": 0.29507699608802795,
      "learning_rate": 0.00012894525583299833,
      "loss": 0.4311,
      "step": 168
    },
    {
      "epoch": 0.054570038949768924,
      "grad_norm": 0.2950059175491333,
      "learning_rate": 0.0001273376484113225,
      "loss": 0.4188,
      "step": 169
    },
    {
      "epoch": 0.05489293858852495,
      "grad_norm": 0.34078386425971985,
      "learning_rate": 0.0001257327005170853,
      "loss": 0.4737,
      "step": 170
    },
    {
      "epoch": 0.05521583822728098,
      "grad_norm": 0.3855750262737274,
      "learning_rate": 0.00012413060049803814,
      "loss": 0.455,
      "step": 171
    },
    {
      "epoch": 0.05553873786603701,
      "grad_norm": 0.34931278228759766,
      "learning_rate": 0.00012253153636772156,
      "loss": 0.4584,
      "step": 172
    },
    {
      "epoch": 0.05586163750479304,
      "grad_norm": 0.3456253707408905,
      "learning_rate": 0.00012093569578340124,
      "loss": 0.4152,
      "step": 173
    },
    {
      "epoch": 0.05618453714354907,
      "grad_norm": 0.3462797999382019,
      "learning_rate": 0.00011934326602404528,
      "loss": 0.4644,
      "step": 174
    },
    {
      "epoch": 0.0565074367823051,
      "grad_norm": 0.3225034475326538,
      "learning_rate": 0.00011775443396834638,
      "loss": 0.4438,
      "step": 175
    },
    {
      "epoch": 0.056830336421061126,
      "grad_norm": 0.3485172986984253,
      "learning_rate": 0.00011616938607279086,
      "loss": 0.4167,
      "step": 176
    },
    {
      "epoch": 0.05715323605981716,
      "grad_norm": 0.36885136365890503,
      "learning_rate": 0.00011458830834977698,
      "loss": 0.4494,
      "step": 177
    },
    {
      "epoch": 0.05747613569857319,
      "grad_norm": 0.40458542108535767,
      "learning_rate": 0.0001130113863457857,
      "loss": 0.4847,
      "step": 178
    },
    {
      "epoch": 0.05779903533732922,
      "grad_norm": 0.3624725043773651,
      "learning_rate": 0.00011143880511960584,
      "loss": 0.4958,
      "step": 179
    },
    {
      "epoch": 0.05812193497608525,
      "grad_norm": 0.3824242949485779,
      "learning_rate": 0.00010987074922061689,
      "loss": 0.4564,
      "step": 180
    },
    {
      "epoch": 0.058444834614841276,
      "grad_norm": 0.3851178288459778,
      "learning_rate": 0.00010830740266713087,
      "loss": 0.4651,
      "step": 181
    },
    {
      "epoch": 0.058767734253597305,
      "grad_norm": 0.43144652247428894,
      "learning_rate": 0.00010674894892479738,
      "loss": 0.4815,
      "step": 182
    },
    {
      "epoch": 0.059090633892353334,
      "grad_norm": 0.389303982257843,
      "learning_rate": 0.00010519557088507298,
      "loss": 0.5031,
      "step": 183
    },
    {
      "epoch": 0.05941353353110936,
      "grad_norm": 0.37136152386665344,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.4521,
      "step": 184
    },
    {
      "epoch": 0.05973643316986539,
      "grad_norm": 0.3901714086532593,
      "learning_rate": 0.00010210477047960302,
      "loss": 0.4977,
      "step": 185
    },
    {
      "epoch": 0.06005933280862142,
      "grad_norm": 0.4063364863395691,
      "learning_rate": 0.00010056771083298893,
      "loss": 0.4808,
      "step": 186
    },
    {
      "epoch": 0.06038223244737745,
      "grad_norm": 0.408845454454422,
      "learning_rate": 9.903645228468024e-05,
      "loss": 0.4782,
      "step": 187
    },
    {
      "epoch": 0.06070513208613348,
      "grad_norm": 0.3464532792568207,
      "learning_rate": 9.751117453465673e-05,
      "loss": 0.4462,
      "step": 188
    },
    {
      "epoch": 0.061028031724889506,
      "grad_norm": 0.41235268115997314,
      "learning_rate": 9.59920565810252e-05,
      "loss": 0.4636,
      "step": 189
    },
    {
      "epoch": 0.061350931363645535,
      "grad_norm": 0.3754219710826874,
      "learning_rate": 9.447927669901282e-05,
      "loss": 0.5001,
      "step": 190
    },
    {
      "epoch": 0.06167383100240156,
      "grad_norm": 0.39120209217071533,
      "learning_rate": 9.297301242004618e-05,
      "loss": 0.5631,
      "step": 191
    },
    {
      "epoch": 0.06199673064115759,
      "grad_norm": 0.47471514344215393,
      "learning_rate": 9.14734405109168e-05,
      "loss": 0.5029,
      "step": 192
    },
    {
      "epoch": 0.06231963027991362,
      "grad_norm": 0.3913878798484802,
      "learning_rate": 8.998073695303701e-05,
      "loss": 0.5068,
      "step": 193
    },
    {
      "epoch": 0.06264252991866966,
      "grad_norm": 0.4407348334789276,
      "learning_rate": 8.849507692178758e-05,
      "loss": 0.4856,
      "step": 194
    },
    {
      "epoch": 0.06296542955742568,
      "grad_norm": 0.41722989082336426,
      "learning_rate": 8.70166347659603e-05,
      "loss": 0.5372,
      "step": 195
    },
    {
      "epoch": 0.06328832919618171,
      "grad_norm": 0.35007795691490173,
      "learning_rate": 8.554558398729725e-05,
      "loss": 0.4814,
      "step": 196
    },
    {
      "epoch": 0.06361122883493774,
      "grad_norm": 0.43563127517700195,
      "learning_rate": 8.408209722012956e-05,
      "loss": 0.5617,
      "step": 197
    },
    {
      "epoch": 0.06393412847369377,
      "grad_norm": 0.5308802723884583,
      "learning_rate": 8.262634621111818e-05,
      "loss": 0.5746,
      "step": 198
    },
    {
      "epoch": 0.0642570281124498,
      "grad_norm": 0.5026018023490906,
      "learning_rate": 8.117850179909842e-05,
      "loss": 0.6231,
      "step": 199
    },
    {
      "epoch": 0.06457992775120583,
      "grad_norm": 0.5310789346694946,
      "learning_rate": 7.973873389503149e-05,
      "loss": 0.6351,
      "step": 200
    },
    {
      "epoch": 0.06457992775120583,
      "eval_loss": 0.4887339770793915,
      "eval_runtime": 92.9821,
      "eval_samples_per_second": 2.678,
      "eval_steps_per_second": 2.678,
      "step": 200
    },
    {
      "epoch": 0.06490282738996185,
      "grad_norm": 0.318142294883728,
      "learning_rate": 7.830721146206451e-05,
      "loss": 0.5384,
      "step": 201
    },
    {
      "epoch": 0.06522572702871789,
      "grad_norm": 0.288631409406662,
      "learning_rate": 7.688410249570214e-05,
      "loss": 0.5078,
      "step": 202
    },
    {
      "epoch": 0.06554862666747392,
      "grad_norm": 0.280100554227829,
      "learning_rate": 7.54695740040912e-05,
      "loss": 0.4788,
      "step": 203
    },
    {
      "epoch": 0.06587152630622994,
      "grad_norm": 0.279681533575058,
      "learning_rate": 7.406379198842189e-05,
      "loss": 0.4447,
      "step": 204
    },
    {
      "epoch": 0.06619442594498598,
      "grad_norm": 0.2892783284187317,
      "learning_rate": 7.266692142344672e-05,
      "loss": 0.4932,
      "step": 205
    },
    {
      "epoch": 0.066517325583742,
      "grad_norm": 0.2658500075340271,
      "learning_rate": 7.127912623811993e-05,
      "loss": 0.4682,
      "step": 206
    },
    {
      "epoch": 0.06684022522249804,
      "grad_norm": 0.2946866452693939,
      "learning_rate": 6.990056929635957e-05,
      "loss": 0.4838,
      "step": 207
    },
    {
      "epoch": 0.06716312486125406,
      "grad_norm": 0.2683822214603424,
      "learning_rate": 6.853141237793506e-05,
      "loss": 0.4408,
      "step": 208
    },
    {
      "epoch": 0.0674860245000101,
      "grad_norm": 0.3225007653236389,
      "learning_rate": 6.717181615948126e-05,
      "loss": 0.4949,
      "step": 209
    },
    {
      "epoch": 0.06780892413876612,
      "grad_norm": 0.25332513451576233,
      "learning_rate": 6.582194019564266e-05,
      "loss": 0.4141,
      "step": 210
    },
    {
      "epoch": 0.06813182377752215,
      "grad_norm": 0.2799530625343323,
      "learning_rate": 6.448194290034848e-05,
      "loss": 0.4445,
      "step": 211
    },
    {
      "epoch": 0.06845472341627817,
      "grad_norm": 0.27327555418014526,
      "learning_rate": 6.315198152822272e-05,
      "loss": 0.4138,
      "step": 212
    },
    {
      "epoch": 0.06877762305503421,
      "grad_norm": 0.3778553903102875,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.4804,
      "step": 213
    },
    {
      "epoch": 0.06910052269379023,
      "grad_norm": 0.3077884614467621,
      "learning_rate": 6.052278966485491e-05,
      "loss": 0.4657,
      "step": 214
    },
    {
      "epoch": 0.06942342233254627,
      "grad_norm": 0.29660362005233765,
      "learning_rate": 5.922386772093526e-05,
      "loss": 0.4297,
      "step": 215
    },
    {
      "epoch": 0.06974632197130229,
      "grad_norm": 0.3540116548538208,
      "learning_rate": 5.793559875861938e-05,
      "loss": 0.466,
      "step": 216
    },
    {
      "epoch": 0.07006922161005832,
      "grad_norm": 0.2957676351070404,
      "learning_rate": 5.6658133961981894e-05,
      "loss": 0.4421,
      "step": 217
    },
    {
      "epoch": 0.07039212124881435,
      "grad_norm": 0.3042965233325958,
      "learning_rate": 5.5391623247180744e-05,
      "loss": 0.441,
      "step": 218
    },
    {
      "epoch": 0.07071502088757038,
      "grad_norm": 0.36982765793800354,
      "learning_rate": 5.413621524486363e-05,
      "loss": 0.4114,
      "step": 219
    },
    {
      "epoch": 0.07103792052632642,
      "grad_norm": 0.3452307879924774,
      "learning_rate": 5.289205728272586e-05,
      "loss": 0.4562,
      "step": 220
    },
    {
      "epoch": 0.07136082016508244,
      "grad_norm": 0.3854043483734131,
      "learning_rate": 5.165929536822059e-05,
      "loss": 0.5003,
      "step": 221
    },
    {
      "epoch": 0.07168371980383847,
      "grad_norm": 0.3237496018409729,
      "learning_rate": 5.043807417142436e-05,
      "loss": 0.4592,
      "step": 222
    },
    {
      "epoch": 0.0720066194425945,
      "grad_norm": 0.32223159074783325,
      "learning_rate": 4.922853700805909e-05,
      "loss": 0.4553,
      "step": 223
    },
    {
      "epoch": 0.07232951908135053,
      "grad_norm": 0.40129488706588745,
      "learning_rate": 4.8030825822673814e-05,
      "loss": 0.4276,
      "step": 224
    },
    {
      "epoch": 0.07265241872010655,
      "grad_norm": 0.34809187054634094,
      "learning_rate": 4.684508117198648e-05,
      "loss": 0.4856,
      "step": 225
    },
    {
      "epoch": 0.07297531835886259,
      "grad_norm": 0.3367185592651367,
      "learning_rate": 4.567144220838923e-05,
      "loss": 0.4555,
      "step": 226
    },
    {
      "epoch": 0.07329821799761861,
      "grad_norm": 0.35933539271354675,
      "learning_rate": 4.4510046663617996e-05,
      "loss": 0.4837,
      "step": 227
    },
    {
      "epoch": 0.07362111763637465,
      "grad_norm": 0.3718101382255554,
      "learning_rate": 4.336103083258942e-05,
      "loss": 0.4789,
      "step": 228
    },
    {
      "epoch": 0.07394401727513067,
      "grad_norm": 0.3542415201663971,
      "learning_rate": 4.2224529557405645e-05,
      "loss": 0.5075,
      "step": 229
    },
    {
      "epoch": 0.0742669169138867,
      "grad_norm": 0.3407626748085022,
      "learning_rate": 4.1100676211530404e-05,
      "loss": 0.4803,
      "step": 230
    },
    {
      "epoch": 0.07458981655264273,
      "grad_norm": 0.39396294951438904,
      "learning_rate": 3.998960268413666e-05,
      "loss": 0.5117,
      "step": 231
    },
    {
      "epoch": 0.07491271619139876,
      "grad_norm": 0.3785285949707031,
      "learning_rate": 3.889143936462914e-05,
      "loss": 0.4925,
      "step": 232
    },
    {
      "epoch": 0.07523561583015478,
      "grad_norm": 0.36613747477531433,
      "learning_rate": 3.780631512734241e-05,
      "loss": 0.4434,
      "step": 233
    },
    {
      "epoch": 0.07555851546891082,
      "grad_norm": 0.3978104591369629,
      "learning_rate": 3.673435731641691e-05,
      "loss": 0.4613,
      "step": 234
    },
    {
      "epoch": 0.07588141510766684,
      "grad_norm": 0.43552708625793457,
      "learning_rate": 3.567569173085454e-05,
      "loss": 0.4177,
      "step": 235
    },
    {
      "epoch": 0.07620431474642288,
      "grad_norm": 0.3718654215335846,
      "learning_rate": 3.463044260975566e-05,
      "loss": 0.4611,
      "step": 236
    },
    {
      "epoch": 0.07652721438517891,
      "grad_norm": 0.41485676169395447,
      "learning_rate": 3.3598732617739036e-05,
      "loss": 0.5586,
      "step": 237
    },
    {
      "epoch": 0.07685011402393493,
      "grad_norm": 0.37860673666000366,
      "learning_rate": 3.258068283054666e-05,
      "loss": 0.4256,
      "step": 238
    },
    {
      "epoch": 0.07717301366269097,
      "grad_norm": 0.4362449645996094,
      "learning_rate": 3.1576412720834746e-05,
      "loss": 0.5763,
      "step": 239
    },
    {
      "epoch": 0.07749591330144699,
      "grad_norm": 0.3914451003074646,
      "learning_rate": 3.058604014415343e-05,
      "loss": 0.4739,
      "step": 240
    },
    {
      "epoch": 0.07781881294020303,
      "grad_norm": 0.3677349388599396,
      "learning_rate": 2.960968132511567e-05,
      "loss": 0.4716,
      "step": 241
    },
    {
      "epoch": 0.07814171257895905,
      "grad_norm": 0.3888345956802368,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.5218,
      "step": 242
    },
    {
      "epoch": 0.07846461221771509,
      "grad_norm": 0.37700045108795166,
      "learning_rate": 2.7699461622093304e-05,
      "loss": 0.4978,
      "step": 243
    },
    {
      "epoch": 0.0787875118564711,
      "grad_norm": 0.41537439823150635,
      "learning_rate": 2.67658249108603e-05,
      "loss": 0.4907,
      "step": 244
    },
    {
      "epoch": 0.07911041149522714,
      "grad_norm": 0.40000054240226746,
      "learning_rate": 2.584665027646643e-05,
      "loss": 0.488,
      "step": 245
    },
    {
      "epoch": 0.07943331113398316,
      "grad_norm": 0.395548552274704,
      "learning_rate": 2.49420455881305e-05,
      "loss": 0.4847,
      "step": 246
    },
    {
      "epoch": 0.0797562107727392,
      "grad_norm": 0.4183206558227539,
      "learning_rate": 2.4052117005223455e-05,
      "loss": 0.5261,
      "step": 247
    },
    {
      "epoch": 0.08007911041149522,
      "grad_norm": 0.37241002917289734,
      "learning_rate": 2.317696896481024e-05,
      "loss": 0.499,
      "step": 248
    },
    {
      "epoch": 0.08040201005025126,
      "grad_norm": 0.4700750410556793,
      "learning_rate": 2.231670416939364e-05,
      "loss": 0.435,
      "step": 249
    },
    {
      "epoch": 0.08072490968900728,
      "grad_norm": 0.47890686988830566,
      "learning_rate": 2.147142357486164e-05,
      "loss": 0.6928,
      "step": 250
    },
    {
      "epoch": 0.08072490968900728,
      "eval_loss": 0.4805048406124115,
      "eval_runtime": 93.118,
      "eval_samples_per_second": 2.674,
      "eval_steps_per_second": 2.674,
      "step": 250
    },
    {
      "epoch": 0.08104780932776331,
      "grad_norm": 0.3123357892036438,
      "learning_rate": 2.0641226378639715e-05,
      "loss": 0.5109,
      "step": 251
    },
    {
      "epoch": 0.08137070896651935,
      "grad_norm": 0.30325785279273987,
      "learning_rate": 1.9826210008049785e-05,
      "loss": 0.498,
      "step": 252
    },
    {
      "epoch": 0.08169360860527537,
      "grad_norm": 0.2983933389186859,
      "learning_rate": 1.902647010887655e-05,
      "loss": 0.508,
      "step": 253
    },
    {
      "epoch": 0.08201650824403141,
      "grad_norm": 0.29377394914627075,
      "learning_rate": 1.8242100534143062e-05,
      "loss": 0.486,
      "step": 254
    },
    {
      "epoch": 0.08233940788278743,
      "grad_norm": 0.28709226846694946,
      "learning_rate": 1.7473193333096575e-05,
      "loss": 0.4685,
      "step": 255
    },
    {
      "epoch": 0.08266230752154347,
      "grad_norm": 0.2827620804309845,
      "learning_rate": 1.671983874040631e-05,
      "loss": 0.4801,
      "step": 256
    },
    {
      "epoch": 0.08298520716029949,
      "grad_norm": 0.3168405294418335,
      "learning_rate": 1.598212516557394e-05,
      "loss": 0.4902,
      "step": 257
    },
    {
      "epoch": 0.08330810679905552,
      "grad_norm": 0.3135143518447876,
      "learning_rate": 1.526013918255836e-05,
      "loss": 0.5243,
      "step": 258
    },
    {
      "epoch": 0.08363100643781154,
      "grad_norm": 0.25695309042930603,
      "learning_rate": 1.4553965519615723e-05,
      "loss": 0.4216,
      "step": 259
    },
    {
      "epoch": 0.08395390607656758,
      "grad_norm": 0.2938316762447357,
      "learning_rate": 1.3863687049356464e-05,
      "loss": 0.4577,
      "step": 260
    },
    {
      "epoch": 0.0842768057153236,
      "grad_norm": 0.2999093234539032,
      "learning_rate": 1.3189384779019535e-05,
      "loss": 0.4935,
      "step": 261
    },
    {
      "epoch": 0.08459970535407964,
      "grad_norm": 0.3224240839481354,
      "learning_rate": 1.25311378409661e-05,
      "loss": 0.4744,
      "step": 262
    },
    {
      "epoch": 0.08492260499283566,
      "grad_norm": 0.29576462507247925,
      "learning_rate": 1.1889023483392879e-05,
      "loss": 0.4506,
      "step": 263
    },
    {
      "epoch": 0.0852455046315917,
      "grad_norm": 0.2991703450679779,
      "learning_rate": 1.1263117061266675e-05,
      "loss": 0.4842,
      "step": 264
    },
    {
      "epoch": 0.08556840427034772,
      "grad_norm": 0.3080856502056122,
      "learning_rate": 1.0653492027481286e-05,
      "loss": 0.4486,
      "step": 265
    },
    {
      "epoch": 0.08589130390910375,
      "grad_norm": 0.2527904510498047,
      "learning_rate": 1.0060219924237379e-05,
      "loss": 0.3798,
      "step": 266
    },
    {
      "epoch": 0.08621420354785977,
      "grad_norm": 0.2680191397666931,
      "learning_rate": 9.48337037464666e-06,
      "loss": 0.4122,
      "step": 267
    },
    {
      "epoch": 0.08653710318661581,
      "grad_norm": 0.29812344908714294,
      "learning_rate": 8.923011074561404e-06,
      "loss": 0.4546,
      "step": 268
    },
    {
      "epoch": 0.08686000282537185,
      "grad_norm": 0.3110487163066864,
      "learning_rate": 8.379207784630004e-06,
      "loss": 0.4445,
      "step": 269
    },
    {
      "epoch": 0.08718290246412787,
      "grad_norm": 0.32935261726379395,
      "learning_rate": 7.852024322579648e-06,
      "loss": 0.482,
      "step": 270
    },
    {
      "epoch": 0.0875058021028839,
      "grad_norm": 0.30921775102615356,
      "learning_rate": 7.34152255572697e-06,
      "loss": 0.4362,
      "step": 271
    },
    {
      "epoch": 0.08782870174163993,
      "grad_norm": 0.3837946951389313,
      "learning_rate": 6.847762393717782e-06,
      "loss": 0.433,
      "step": 272
    },
    {
      "epoch": 0.08815160138039596,
      "grad_norm": 0.2926897406578064,
      "learning_rate": 6.370801781496326e-06,
      "loss": 0.4659,
      "step": 273
    },
    {
      "epoch": 0.08847450101915198,
      "grad_norm": 0.35898199677467346,
      "learning_rate": 5.910696692505201e-06,
      "loss": 0.506,
      "step": 274
    },
    {
      "epoch": 0.08879740065790802,
      "grad_norm": 0.3298279345035553,
      "learning_rate": 5.467501122116563e-06,
      "loss": 0.5052,
      "step": 275
    },
    {
      "epoch": 0.08912030029666404,
      "grad_norm": 0.34559693932533264,
      "learning_rate": 5.0412670812956465e-06,
      "loss": 0.4997,
      "step": 276
    },
    {
      "epoch": 0.08944319993542008,
      "grad_norm": 0.2868078947067261,
      "learning_rate": 4.6320445904969475e-06,
      "loss": 0.4047,
      "step": 277
    },
    {
      "epoch": 0.0897660995741761,
      "grad_norm": 0.3573528528213501,
      "learning_rate": 4.239881673794165e-06,
      "loss": 0.481,
      "step": 278
    },
    {
      "epoch": 0.09008899921293213,
      "grad_norm": 0.3438877463340759,
      "learning_rate": 3.864824353244367e-06,
      "loss": 0.5199,
      "step": 279
    },
    {
      "epoch": 0.09041189885168815,
      "grad_norm": 0.3259707987308502,
      "learning_rate": 3.506916643487001e-06,
      "loss": 0.4441,
      "step": 280
    },
    {
      "epoch": 0.09073479849044419,
      "grad_norm": 0.36126869916915894,
      "learning_rate": 3.166200546578718e-06,
      "loss": 0.4598,
      "step": 281
    },
    {
      "epoch": 0.09105769812920021,
      "grad_norm": 0.29352861642837524,
      "learning_rate": 2.8427160470641253e-06,
      "loss": 0.4116,
      "step": 282
    },
    {
      "epoch": 0.09138059776795625,
      "grad_norm": 0.390318363904953,
      "learning_rate": 2.5365011072835117e-06,
      "loss": 0.457,
      "step": 283
    },
    {
      "epoch": 0.09170349740671227,
      "grad_norm": 0.34145522117614746,
      "learning_rate": 2.2475916629177415e-06,
      "loss": 0.4275,
      "step": 284
    },
    {
      "epoch": 0.0920263970454683,
      "grad_norm": 0.3860124945640564,
      "learning_rate": 1.9760216187710787e-06,
      "loss": 0.5023,
      "step": 285
    },
    {
      "epoch": 0.09234929668422434,
      "grad_norm": 0.36518341302871704,
      "learning_rate": 1.7218228447922867e-06,
      "loss": 0.4925,
      "step": 286
    },
    {
      "epoch": 0.09267219632298036,
      "grad_norm": 0.3913903832435608,
      "learning_rate": 1.4850251723345196e-06,
      "loss": 0.4858,
      "step": 287
    },
    {
      "epoch": 0.0929950959617364,
      "grad_norm": 0.35096660256385803,
      "learning_rate": 1.2656563906545902e-06,
      "loss": 0.4196,
      "step": 288
    },
    {
      "epoch": 0.09331799560049242,
      "grad_norm": 0.4638069272041321,
      "learning_rate": 1.0637422436516274e-06,
      "loss": 0.5741,
      "step": 289
    },
    {
      "epoch": 0.09364089523924846,
      "grad_norm": 0.40387284755706787,
      "learning_rate": 8.793064268460604e-07,
      "loss": 0.4867,
      "step": 290
    },
    {
      "epoch": 0.09396379487800448,
      "grad_norm": 0.39819347858428955,
      "learning_rate": 7.123705845987093e-07,
      "loss": 0.4803,
      "step": 291
    },
    {
      "epoch": 0.09428669451676051,
      "grad_norm": 0.3998761773109436,
      "learning_rate": 5.629543075708176e-07,
      "loss": 0.4755,
      "step": 292
    },
    {
      "epoch": 0.09460959415551654,
      "grad_norm": 0.3553345799446106,
      "learning_rate": 4.310751304249738e-07,
      "loss": 0.5079,
      "step": 293
    },
    {
      "epoch": 0.09493249379427257,
      "grad_norm": 0.35981830954551697,
      "learning_rate": 3.167485297673411e-07,
      "loss": 0.4487,
      "step": 294
    },
    {
      "epoch": 0.09525539343302859,
      "grad_norm": 0.38175123929977417,
      "learning_rate": 2.1998792233142714e-07,
      "loss": 0.5537,
      "step": 295
    },
    {
      "epoch": 0.09557829307178463,
      "grad_norm": 0.42106011509895325,
      "learning_rate": 1.4080466340349316e-07,
      "loss": 0.4318,
      "step": 296
    },
    {
      "epoch": 0.09590119271054065,
      "grad_norm": 0.37637245655059814,
      "learning_rate": 7.92080454900701e-08,
      "loss": 0.5632,
      "step": 297
    },
    {
      "epoch": 0.09622409234929669,
      "grad_norm": 0.3730914890766144,
      "learning_rate": 3.5205297227380855e-08,
      "loss": 0.4611,
      "step": 298
    },
    {
      "epoch": 0.09654699198805271,
      "grad_norm": 0.5511401891708374,
      "learning_rate": 8.801582533035644e-09,
      "loss": 0.5325,
      "step": 299
    },
    {
      "epoch": 0.09686989162680874,
      "grad_norm": 0.5235540270805359,
      "learning_rate": 0.0,
      "loss": 0.6263,
      "step": 300
    },
    {
      "epoch": 0.09686989162680874,
      "eval_loss": 0.4757327735424042,
      "eval_runtime": 92.9521,
      "eval_samples_per_second": 2.679,
      "eval_steps_per_second": 2.679,
      "step": 300
    }
  ],
  "logging_steps": 1,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7681879996301312e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}