{
  "best_metric": 1.700640082359314,
  "best_model_checkpoint": "miner_id_24/checkpoint-300",
  "epoch": 0.11954274898513187,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00039847582995043956,
      "grad_norm": 0.8249958157539368,
      "learning_rate": 2e-05,
      "loss": 3.7705,
      "step": 1
    },
    {
      "epoch": 0.00039847582995043956,
      "eval_loss": 3.994760274887085,
      "eval_runtime": 599.7212,
      "eval_samples_per_second": 14.097,
      "eval_steps_per_second": 3.525,
      "step": 1
    },
    {
      "epoch": 0.0007969516599008791,
      "grad_norm": 0.9214300513267517,
      "learning_rate": 4e-05,
      "loss": 3.9395,
      "step": 2
    },
    {
      "epoch": 0.0011954274898513188,
      "grad_norm": 0.7693865299224854,
      "learning_rate": 6e-05,
      "loss": 3.7306,
      "step": 3
    },
    {
      "epoch": 0.0015939033198017582,
      "grad_norm": 0.8011671304702759,
      "learning_rate": 8e-05,
      "loss": 3.3512,
      "step": 4
    },
    {
      "epoch": 0.001992379149752198,
      "grad_norm": 0.8984593749046326,
      "learning_rate": 0.0001,
      "loss": 3.6375,
      "step": 5
    },
    {
      "epoch": 0.0023908549797026376,
      "grad_norm": 1.0371809005737305,
      "learning_rate": 0.00012,
      "loss": 3.8592,
      "step": 6
    },
    {
      "epoch": 0.002789330809653077,
      "grad_norm": 1.1792114973068237,
      "learning_rate": 0.00014,
      "loss": 3.8321,
      "step": 7
    },
    {
      "epoch": 0.0031878066396035165,
      "grad_norm": 1.3046059608459473,
      "learning_rate": 0.00016,
      "loss": 3.3336,
      "step": 8
    },
    {
      "epoch": 0.003586282469553956,
      "grad_norm": 1.4238650798797607,
      "learning_rate": 0.00018,
      "loss": 2.9386,
      "step": 9
    },
    {
      "epoch": 0.003984758299504396,
      "grad_norm": 1.1028273105621338,
      "learning_rate": 0.0002,
      "loss": 2.7003,
      "step": 10
    },
    {
      "epoch": 0.0043832341294548355,
      "grad_norm": 1.1997171640396118,
      "learning_rate": 0.00019999741592564903,
      "loss": 2.4654,
      "step": 11
    },
    {
      "epoch": 0.004781709959405275,
      "grad_norm": 1.5336440801620483,
      "learning_rate": 0.00019998966383614488,
      "loss": 2.4423,
      "step": 12
    },
    {
      "epoch": 0.005180185789355715,
      "grad_norm": 1.8468828201293945,
      "learning_rate": 0.00019997674413212708,
      "loss": 2.4003,
      "step": 13
    },
    {
      "epoch": 0.005578661619306154,
      "grad_norm": 1.7681652307510376,
      "learning_rate": 0.00019995865748130516,
      "loss": 2.3207,
      "step": 14
    },
    {
      "epoch": 0.005977137449256593,
      "grad_norm": 1.0762815475463867,
      "learning_rate": 0.0001999354048184241,
      "loss": 2.2285,
      "step": 15
    },
    {
      "epoch": 0.006375613279207033,
      "grad_norm": 0.8622324466705322,
      "learning_rate": 0.00019990698734521613,
      "loss": 1.9898,
      "step": 16
    },
    {
      "epoch": 0.006774089109157473,
      "grad_norm": 0.9870002865791321,
      "learning_rate": 0.0001998734065303385,
      "loss": 1.923,
      "step": 17
    },
    {
      "epoch": 0.007172564939107912,
      "grad_norm": 1.0574088096618652,
      "learning_rate": 0.00019983466410929764,
      "loss": 2.08,
      "step": 18
    },
    {
      "epoch": 0.007571040769058352,
      "grad_norm": 0.8685367107391357,
      "learning_rate": 0.0001997907620843595,
      "loss": 1.9477,
      "step": 19
    },
    {
      "epoch": 0.007969516599008792,
      "grad_norm": 0.7225976586341858,
      "learning_rate": 0.00019974170272444604,
      "loss": 1.9725,
      "step": 20
    },
    {
      "epoch": 0.00836799242895923,
      "grad_norm": 0.7834375500679016,
      "learning_rate": 0.00019968748856501788,
      "loss": 1.9877,
      "step": 21
    },
    {
      "epoch": 0.008766468258909671,
      "grad_norm": 0.7260671257972717,
      "learning_rate": 0.00019962812240794343,
      "loss": 1.9946,
      "step": 22
    },
    {
      "epoch": 0.00916494408886011,
      "grad_norm": 0.8711982369422913,
      "learning_rate": 0.000199563607321354,
      "loss": 1.8275,
      "step": 23
    },
    {
      "epoch": 0.00956341991881055,
      "grad_norm": 0.5631409287452698,
      "learning_rate": 0.0001994939466394851,
      "loss": 1.7041,
      "step": 24
    },
    {
      "epoch": 0.009961895748760989,
      "grad_norm": 0.5470976829528809,
      "learning_rate": 0.00019941914396250446,
      "loss": 1.7129,
      "step": 25
    },
    {
      "epoch": 0.01036037157871143,
      "grad_norm": 0.5513713359832764,
      "learning_rate": 0.00019933920315632557,
      "loss": 1.8914,
      "step": 26
    },
    {
      "epoch": 0.010758847408661868,
      "grad_norm": 0.5356898903846741,
      "learning_rate": 0.00019925412835240826,
      "loss": 1.9072,
      "step": 27
    },
    {
      "epoch": 0.011157323238612307,
      "grad_norm": 0.5035513043403625,
      "learning_rate": 0.0001991639239475448,
      "loss": 1.9054,
      "step": 28
    },
    {
      "epoch": 0.011555799068562748,
      "grad_norm": 0.5602848529815674,
      "learning_rate": 0.00019906859460363307,
      "loss": 1.8175,
      "step": 29
    },
    {
      "epoch": 0.011954274898513187,
      "grad_norm": 0.5118929743766785,
      "learning_rate": 0.00019896814524743528,
      "loss": 1.7964,
      "step": 30
    },
    {
      "epoch": 0.012352750728463627,
      "grad_norm": 0.45721983909606934,
      "learning_rate": 0.0001988625810703235,
      "loss": 1.8377,
      "step": 31
    },
    {
      "epoch": 0.012751226558414066,
      "grad_norm": 0.44319745898246765,
      "learning_rate": 0.0001987519075280114,
      "loss": 1.8383,
      "step": 32
    },
    {
      "epoch": 0.013149702388364506,
      "grad_norm": 0.49430009722709656,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.7603,
      "step": 33
    },
    {
      "epoch": 0.013548178218314945,
      "grad_norm": 0.4535483419895172,
      "learning_rate": 0.00019851525549064323,
      "loss": 1.6921,
      "step": 34
    },
    {
      "epoch": 0.013946654048265384,
      "grad_norm": 0.48142871260643005,
      "learning_rate": 0.00019838928922611632,
      "loss": 1.8217,
      "step": 35
    },
    {
      "epoch": 0.014345129878215825,
      "grad_norm": 0.6872768402099609,
      "learning_rate": 0.00019825823805681543,
      "loss": 1.8212,
      "step": 36
    },
    {
      "epoch": 0.014743605708166263,
      "grad_norm": 0.4731607437133789,
      "learning_rate": 0.0001981221087556598,
      "loss": 1.6508,
      "step": 37
    },
    {
      "epoch": 0.015142081538116704,
      "grad_norm": 0.42979615926742554,
      "learning_rate": 0.00019798090835801418,
      "loss": 1.4883,
      "step": 38
    },
    {
      "epoch": 0.015540557368067143,
      "grad_norm": 0.5217059254646301,
      "learning_rate": 0.00019783464416132506,
      "loss": 1.6702,
      "step": 39
    },
    {
      "epoch": 0.015939033198017583,
      "grad_norm": 0.5023307204246521,
      "learning_rate": 0.00019768332372474366,
      "loss": 1.7604,
      "step": 40
    },
    {
      "epoch": 0.016337509027968024,
      "grad_norm": 0.5037193894386292,
      "learning_rate": 0.00019752695486873517,
      "loss": 1.7254,
      "step": 41
    },
    {
      "epoch": 0.01673598485791846,
      "grad_norm": 0.4970403015613556,
      "learning_rate": 0.00019736554567467452,
      "loss": 1.726,
      "step": 42
    },
    {
      "epoch": 0.0171344606878689,
      "grad_norm": 0.4856554865837097,
      "learning_rate": 0.00019719910448442893,
      "loss": 1.5681,
      "step": 43
    },
    {
      "epoch": 0.017532936517819342,
      "grad_norm": 0.4940697252750397,
      "learning_rate": 0.00019702763989992662,
      "loss": 1.58,
      "step": 44
    },
    {
      "epoch": 0.01793141234776978,
      "grad_norm": 0.46332672238349915,
      "learning_rate": 0.00019685116078271223,
      "loss": 1.4937,
      "step": 45
    },
    {
      "epoch": 0.01832988817772022,
      "grad_norm": 0.4996075928211212,
      "learning_rate": 0.00019666967625348906,
      "loss": 1.8633,
      "step": 46
    },
    {
      "epoch": 0.01872836400767066,
      "grad_norm": 0.4581417143344879,
      "learning_rate": 0.00019648319569164736,
      "loss": 1.6708,
      "step": 47
    },
    {
      "epoch": 0.0191268398376211,
      "grad_norm": 0.49805447459220886,
      "learning_rate": 0.00019629172873477995,
      "loss": 1.6956,
      "step": 48
    },
    {
      "epoch": 0.019525315667571538,
      "grad_norm": 0.5399609208106995,
      "learning_rate": 0.0001960952852781838,
      "loss": 1.8536,
      "step": 49
    },
    {
      "epoch": 0.019923791497521978,
      "grad_norm": 0.5043647289276123,
      "learning_rate": 0.0001958938754743489,
      "loss": 1.9073,
      "step": 50
    },
    {
      "epoch": 0.02032226732747242,
      "grad_norm": 0.5041136741638184,
      "learning_rate": 0.0001956875097324334,
      "loss": 1.8891,
      "step": 51
    },
    {
      "epoch": 0.02072074315742286,
      "grad_norm": 0.48425522446632385,
      "learning_rate": 0.00019547619871772574,
      "loss": 1.7636,
      "step": 52
    },
    {
      "epoch": 0.021119218987373296,
      "grad_norm": 0.501112163066864,
      "learning_rate": 0.00019525995335109334,
      "loss": 1.6945,
      "step": 53
    },
    {
      "epoch": 0.021517694817323737,
      "grad_norm": 0.4796481132507324,
      "learning_rate": 0.0001950387848084183,
      "loss": 1.7757,
      "step": 54
    },
    {
      "epoch": 0.021916170647274177,
      "grad_norm": 0.5773142576217651,
      "learning_rate": 0.00019481270452001987,
      "loss": 1.7415,
      "step": 55
    },
    {
      "epoch": 0.022314646477224614,
      "grad_norm": 0.4900719225406647,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.6834,
      "step": 56
    },
    {
      "epoch": 0.022713122307175055,
      "grad_norm": 0.4695626497268677,
      "learning_rate": 0.00019434585569595708,
      "loss": 1.7537,
      "step": 57
    },
    {
      "epoch": 0.023111598137125496,
      "grad_norm": 0.49179011583328247,
      "learning_rate": 0.00019410511128773418,
      "loss": 1.685,
      "step": 58
    },
    {
      "epoch": 0.023510073967075936,
      "grad_norm": 0.5011521577835083,
      "learning_rate": 0.0001938595033874238,
      "loss": 1.6088,
      "step": 59
    },
    {
      "epoch": 0.023908549797026373,
      "grad_norm": 0.47553250193595886,
      "learning_rate": 0.0001936090446884074,
      "loss": 1.6502,
      "step": 60
    },
    {
      "epoch": 0.024307025626976814,
      "grad_norm": 0.4945161044597626,
      "learning_rate": 0.00019335374813476302,
      "loss": 1.7799,
      "step": 61
    },
    {
      "epoch": 0.024705501456927254,
      "grad_norm": 0.5294601917266846,
      "learning_rate": 0.00019309362692059617,
      "loss": 1.6993,
      "step": 62
    },
    {
      "epoch": 0.02510397728687769,
      "grad_norm": 0.5426062941551208,
      "learning_rate": 0.00019282869448935798,
      "loss": 1.915,
      "step": 63
    },
    {
      "epoch": 0.025502453116828132,
      "grad_norm": 0.49963027238845825,
      "learning_rate": 0.00019255896453315052,
      "loss": 1.7709,
      "step": 64
    },
    {
      "epoch": 0.025900928946778572,
      "grad_norm": 0.5086182355880737,
      "learning_rate": 0.000192284450992019,
      "loss": 1.6436,
      "step": 65
    },
    {
      "epoch": 0.026299404776729013,
      "grad_norm": 0.4630321264266968,
      "learning_rate": 0.0001920051680532314,
      "loss": 1.6038,
      "step": 66
    },
    {
      "epoch": 0.02669788060667945,
      "grad_norm": 0.4538319408893585,
      "learning_rate": 0.00019172113015054532,
      "loss": 1.5576,
      "step": 67
    },
    {
      "epoch": 0.02709635643662989,
      "grad_norm": 0.511547863483429,
      "learning_rate": 0.0001914323519634619,
      "loss": 1.6114,
      "step": 68
    },
    {
      "epoch": 0.02749483226658033,
      "grad_norm": 0.5467154383659363,
      "learning_rate": 0.00019113884841646736,
      "loss": 1.8275,
      "step": 69
    },
    {
      "epoch": 0.027893308096530768,
      "grad_norm": 0.44893792271614075,
      "learning_rate": 0.00019084063467826137,
      "loss": 1.6006,
      "step": 70
    },
    {
      "epoch": 0.02829178392648121,
      "grad_norm": 0.4380510747432709,
      "learning_rate": 0.00019053772616097337,
      "loss": 1.5283,
      "step": 71
    },
    {
      "epoch": 0.02869025975643165,
      "grad_norm": 0.4855054020881653,
      "learning_rate": 0.000190230138519366,
      "loss": 1.949,
      "step": 72
    },
    {
      "epoch": 0.02908873558638209,
      "grad_norm": 0.509174108505249,
      "learning_rate": 0.000189917887650026,
      "loss": 1.9279,
      "step": 73
    },
    {
      "epoch": 0.029487211416332527,
      "grad_norm": 0.4690839946269989,
      "learning_rate": 0.00018960098969054255,
      "loss": 1.8505,
      "step": 74
    },
    {
      "epoch": 0.029885687246282967,
      "grad_norm": 0.5497538447380066,
      "learning_rate": 0.00018927946101867347,
      "loss": 1.9063,
      "step": 75
    },
    {
      "epoch": 0.030284163076233408,
      "grad_norm": 0.5328514575958252,
      "learning_rate": 0.0001889533182514986,
      "loss": 1.8781,
      "step": 76
    },
    {
      "epoch": 0.03068263890618385,
      "grad_norm": 0.42769238352775574,
      "learning_rate": 0.0001886225782445612,
      "loss": 1.5811,
      "step": 77
    },
    {
      "epoch": 0.031081114736134285,
      "grad_norm": 0.6662131547927856,
      "learning_rate": 0.00018828725809099655,
      "loss": 1.8193,
      "step": 78
    },
    {
      "epoch": 0.03147959056608472,
      "grad_norm": 0.4854792058467865,
      "learning_rate": 0.0001879473751206489,
      "loss": 1.6416,
      "step": 79
    },
    {
      "epoch": 0.031878066396035167,
      "grad_norm": 0.5450350046157837,
      "learning_rate": 0.00018760294689917553,
      "loss": 1.9132,
      "step": 80
    },
    {
      "epoch": 0.032276542225985604,
      "grad_norm": 0.5068654417991638,
      "learning_rate": 0.00018725399122713912,
      "loss": 1.7539,
      "step": 81
    },
    {
      "epoch": 0.03267501805593605,
      "grad_norm": 0.500575065612793,
      "learning_rate": 0.00018690052613908772,
      "loss": 1.7219,
      "step": 82
    },
    {
      "epoch": 0.033073493885886485,
      "grad_norm": 0.481229692697525,
      "learning_rate": 0.0001865425699026226,
      "loss": 1.6467,
      "step": 83
    },
    {
      "epoch": 0.03347196971583692,
      "grad_norm": 0.5118649005889893,
      "learning_rate": 0.00018618014101745442,
      "loss": 1.8061,
      "step": 84
    },
    {
      "epoch": 0.033870445545787366,
      "grad_norm": 0.5075271725654602,
      "learning_rate": 0.0001858132582144469,
      "loss": 1.7179,
      "step": 85
    },
    {
      "epoch": 0.0342689213757378,
      "grad_norm": 0.455424427986145,
      "learning_rate": 0.00018544194045464886,
      "loss": 1.5479,
      "step": 86
    },
    {
      "epoch": 0.03466739720568824,
      "grad_norm": 0.5024828910827637,
      "learning_rate": 0.00018506620692831428,
      "loss": 1.726,
      "step": 87
    },
    {
      "epoch": 0.035065873035638684,
      "grad_norm": 0.5479703545570374,
      "learning_rate": 0.0001846860770539105,
      "loss": 1.7982,
      "step": 88
    },
    {
      "epoch": 0.03546434886558912,
      "grad_norm": 0.4849150478839874,
      "learning_rate": 0.00018430157047711474,
      "loss": 1.6496,
      "step": 89
    },
    {
      "epoch": 0.03586282469553956,
      "grad_norm": 0.5472909212112427,
      "learning_rate": 0.00018391270706979862,
      "loss": 1.8333,
      "step": 90
    },
    {
      "epoch": 0.03626130052549,
      "grad_norm": 0.4992446005344391,
      "learning_rate": 0.00018351950692900126,
      "loss": 1.761,
      "step": 91
    },
    {
      "epoch": 0.03665977635544044,
      "grad_norm": 0.4649079144001007,
      "learning_rate": 0.00018312199037589068,
      "loss": 1.5256,
      "step": 92
    },
    {
      "epoch": 0.03705825218539088,
      "grad_norm": 0.5369842648506165,
      "learning_rate": 0.00018272017795471345,
      "loss": 1.78,
      "step": 93
    },
    {
      "epoch": 0.03745672801534132,
      "grad_norm": 0.4625012278556824,
      "learning_rate": 0.000182314090431733,
      "loss": 1.5817,
      "step": 94
    },
    {
      "epoch": 0.03785520384529176,
      "grad_norm": 0.5325396060943604,
      "learning_rate": 0.00018190374879415632,
      "loss": 1.698,
      "step": 95
    },
    {
      "epoch": 0.0382536796752422,
      "grad_norm": 0.4603791832923889,
      "learning_rate": 0.00018148917424904953,
      "loss": 1.5092,
      "step": 96
    },
    {
      "epoch": 0.03865215550519264,
      "grad_norm": 0.4525664746761322,
      "learning_rate": 0.0001810703882222415,
      "loss": 1.4083,
      "step": 97
    },
    {
      "epoch": 0.039050631335143075,
      "grad_norm": 0.5617400407791138,
      "learning_rate": 0.00018064741235721687,
      "loss": 1.6626,
      "step": 98
    },
    {
      "epoch": 0.03944910716509352,
      "grad_norm": 0.5286575555801392,
      "learning_rate": 0.00018022026851399737,
      "loss": 1.7368,
      "step": 99
    },
    {
      "epoch": 0.039847582995043956,
      "grad_norm": 0.5342997908592224,
      "learning_rate": 0.0001797889787680119,
      "loss": 1.8665,
      "step": 100
    },
    {
      "epoch": 0.039847582995043956,
      "eval_loss": 1.7500040531158447,
      "eval_runtime": 602.8533,
      "eval_samples_per_second": 14.023,
      "eval_steps_per_second": 3.507,
      "step": 100
    },
    {
      "epoch": 0.04024605882499439,
      "grad_norm": 0.4774135649204254,
      "learning_rate": 0.00017935356540895597,
      "loss": 1.6952,
      "step": 101
    },
    {
      "epoch": 0.04064453465494484,
      "grad_norm": 0.6040295362472534,
      "learning_rate": 0.00017891405093963938,
      "loss": 1.8068,
      "step": 102
    },
    {
      "epoch": 0.041043010484895275,
      "grad_norm": 0.5168588757514954,
      "learning_rate": 0.00017847045807482345,
      "loss": 1.7252,
      "step": 103
    },
    {
      "epoch": 0.04144148631484572,
      "grad_norm": 0.4739170968532562,
      "learning_rate": 0.00017802280974004716,
      "loss": 1.7146,
      "step": 104
    },
    {
      "epoch": 0.041839962144796156,
      "grad_norm": 0.5354509353637695,
      "learning_rate": 0.000177571129070442,
      "loss": 1.868,
      "step": 105
    },
    {
      "epoch": 0.04223843797474659,
      "grad_norm": 0.46404990553855896,
      "learning_rate": 0.00017711543940953668,
      "loss": 1.698,
      "step": 106
    },
    {
      "epoch": 0.04263691380469704,
      "grad_norm": 0.45692166686058044,
      "learning_rate": 0.00017665576430805053,
      "loss": 1.649,
      "step": 107
    },
    {
      "epoch": 0.043035389634647474,
      "grad_norm": 0.4770927131175995,
      "learning_rate": 0.0001761921275226763,
      "loss": 1.8552,
      "step": 108
    },
    {
      "epoch": 0.04343386546459791,
      "grad_norm": 0.4677036702632904,
      "learning_rate": 0.00017572455301485249,
      "loss": 1.6415,
      "step": 109
    },
    {
      "epoch": 0.043832341294548355,
      "grad_norm": 0.49166563153266907,
      "learning_rate": 0.00017525306494952498,
      "loss": 1.5864,
      "step": 110
    },
    {
      "epoch": 0.04423081712449879,
      "grad_norm": 0.551313579082489,
      "learning_rate": 0.0001747776876938981,
      "loss": 1.8246,
      "step": 111
    },
    {
      "epoch": 0.04462929295444923,
      "grad_norm": 0.5011689066886902,
      "learning_rate": 0.00017429844581617532,
      "loss": 1.6335,
      "step": 112
    },
    {
      "epoch": 0.04502776878439967,
      "grad_norm": 0.510704755783081,
      "learning_rate": 0.00017381536408428948,
      "loss": 1.7084,
      "step": 113
    },
    {
      "epoch": 0.04542624461435011,
      "grad_norm": 0.4545946419239044,
      "learning_rate": 0.00017332846746462288,
      "loss": 1.5209,
      "step": 114
    },
    {
      "epoch": 0.04582472044430055,
      "grad_norm": 0.4840458631515503,
      "learning_rate": 0.0001728377811207168,
      "loss": 1.7235,
      "step": 115
    },
    {
      "epoch": 0.04622319627425099,
      "grad_norm": 0.4970642626285553,
      "learning_rate": 0.00017234333041197126,
      "loss": 1.6567,
      "step": 116
    },
    {
      "epoch": 0.04662167210420143,
      "grad_norm": 0.5095712542533875,
      "learning_rate": 0.00017184514089233405,
      "loss": 1.7205,
      "step": 117
    },
    {
      "epoch": 0.04702014793415187,
      "grad_norm": 0.5349841713905334,
      "learning_rate": 0.00017134323830898037,
      "loss": 1.7285,
      "step": 118
    },
    {
      "epoch": 0.04741862376410231,
      "grad_norm": 0.5475637316703796,
      "learning_rate": 0.00017083764860098205,
      "loss": 1.6601,
      "step": 119
    },
    {
      "epoch": 0.047817099594052746,
      "grad_norm": 0.5360651016235352,
      "learning_rate": 0.0001703283978979671,
      "loss": 1.6062,
      "step": 120
    },
    {
      "epoch": 0.04821557542400319,
      "grad_norm": 0.49149248003959656,
      "learning_rate": 0.00016981551251876904,
      "loss": 1.7332,
      "step": 121
    },
    {
      "epoch": 0.04861405125395363,
      "grad_norm": 0.46091562509536743,
      "learning_rate": 0.00016929901897006698,
      "loss": 1.5933,
      "step": 122
    },
    {
      "epoch": 0.049012527083904064,
      "grad_norm": 0.5389519333839417,
      "learning_rate": 0.0001687789439450156,
      "loss": 1.9277,
      "step": 123
    },
    {
      "epoch": 0.04941100291385451,
      "grad_norm": 0.4960940182209015,
      "learning_rate": 0.00016825531432186543,
      "loss": 1.7398,
      "step": 124
    },
    {
      "epoch": 0.049809478743804945,
      "grad_norm": 0.5458736419677734,
      "learning_rate": 0.00016772815716257412,
      "loss": 1.7824,
      "step": 125
    },
    {
      "epoch": 0.05020795457375538,
      "grad_norm": 0.5217113494873047,
      "learning_rate": 0.00016719749971140754,
      "loss": 1.8169,
      "step": 126
    },
    {
      "epoch": 0.05060643040370583,
      "grad_norm": 0.49912309646606445,
      "learning_rate": 0.0001666633693935319,
      "loss": 1.7099,
      "step": 127
    },
    {
      "epoch": 0.051004906233656264,
      "grad_norm": 0.519611120223999,
      "learning_rate": 0.00016612579381359622,
      "loss": 1.5635,
      "step": 128
    },
    {
      "epoch": 0.05140338206360671,
      "grad_norm": 0.5147966146469116,
      "learning_rate": 0.00016558480075430594,
      "loss": 1.6643,
      "step": 129
    },
    {
      "epoch": 0.051801857893557145,
      "grad_norm": 0.539840817451477,
      "learning_rate": 0.00016504041817498678,
      "loss": 1.796,
      "step": 130
    },
    {
      "epoch": 0.05220033372350758,
      "grad_norm": 0.5166546106338501,
      "learning_rate": 0.00016449267421013994,
      "loss": 1.5948,
      "step": 131
    },
    {
      "epoch": 0.052598809553458026,
      "grad_norm": 0.5418827533721924,
      "learning_rate": 0.00016394159716798807,
      "loss": 1.8935,
      "step": 132
    },
    {
      "epoch": 0.05299728538340846,
      "grad_norm": 0.5098159313201904,
      "learning_rate": 0.00016338721552901212,
      "loss": 1.6439,
      "step": 133
    },
    {
      "epoch": 0.0533957612133589,
      "grad_norm": 0.5153954029083252,
      "learning_rate": 0.0001628295579444796,
      "loss": 1.7484,
      "step": 134
    },
    {
      "epoch": 0.053794237043309344,
      "grad_norm": 0.5499337315559387,
      "learning_rate": 0.0001622686532349637,
      "loss": 1.665,
      "step": 135
    },
    {
      "epoch": 0.05419271287325978,
      "grad_norm": 0.5195444226264954,
      "learning_rate": 0.00016170453038885394,
      "loss": 1.6813,
      "step": 136
    },
    {
      "epoch": 0.05459118870321022,
      "grad_norm": 0.5251967310905457,
      "learning_rate": 0.0001611372185608578,
      "loss": 1.7325,
      "step": 137
    },
    {
      "epoch": 0.05498966453316066,
      "grad_norm": 0.5916984677314758,
      "learning_rate": 0.0001605667470704942,
      "loss": 1.8083,
      "step": 138
    },
    {
      "epoch": 0.0553881403631111,
      "grad_norm": 0.5287485718727112,
      "learning_rate": 0.0001599931454005781,
      "loss": 1.8145,
      "step": 139
    },
    {
      "epoch": 0.055786616193061536,
      "grad_norm": 0.5018830299377441,
      "learning_rate": 0.00015941644319569665,
      "loss": 1.6038,
      "step": 140
    },
    {
      "epoch": 0.05618509202301198,
      "grad_norm": 0.4870772063732147,
      "learning_rate": 0.00015883667026067745,
      "loss": 1.6,
      "step": 141
    },
    {
      "epoch": 0.05658356785296242,
      "grad_norm": 0.4964452087879181,
      "learning_rate": 0.00015825385655904788,
      "loss": 1.7953,
      "step": 142
    },
    {
      "epoch": 0.05698204368291286,
      "grad_norm": 0.4588499367237091,
      "learning_rate": 0.00015766803221148673,
      "loss": 1.5708,
      "step": 143
    },
    {
      "epoch": 0.0573805195128633,
      "grad_norm": 0.521144449710846,
      "learning_rate": 0.00015707922749426737,
      "loss": 1.7794,
      "step": 144
    },
    {
      "epoch": 0.057778995342813735,
      "grad_norm": 0.5591409206390381,
      "learning_rate": 0.00015648747283769317,
      "loss": 1.9377,
      "step": 145
    },
    {
      "epoch": 0.05817747117276418,
      "grad_norm": 0.43348705768585205,
      "learning_rate": 0.00015589279882452476,
      "loss": 1.396,
      "step": 146
    },
    {
      "epoch": 0.058575947002714616,
      "grad_norm": 0.46277427673339844,
      "learning_rate": 0.0001552952361883994,
      "loss": 1.6397,
      "step": 147
    },
    {
      "epoch": 0.058974422832665054,
      "grad_norm": 0.49379056692123413,
      "learning_rate": 0.00015469481581224272,
      "loss": 1.7281,
      "step": 148
    },
    {
      "epoch": 0.0593728986626155,
      "grad_norm": 0.49816733598709106,
      "learning_rate": 0.00015409156872667258,
      "loss": 1.6383,
      "step": 149
    },
    {
      "epoch": 0.059771374492565935,
      "grad_norm": 0.44194599986076355,
      "learning_rate": 0.0001534855261083954,
      "loss": 1.552,
      "step": 150
    },
    {
      "epoch": 0.06016985032251637,
      "grad_norm": 0.4125038683414459,
      "learning_rate": 0.00015287671927859494,
      "loss": 1.4642,
      "step": 151
    },
    {
      "epoch": 0.060568326152466816,
      "grad_norm": 0.4800686836242676,
      "learning_rate": 0.00015226517970131343,
      "loss": 1.5824,
      "step": 152
    },
    {
      "epoch": 0.06096680198241725,
      "grad_norm": 0.5546180605888367,
      "learning_rate": 0.00015165093898182562,
      "loss": 1.8809,
      "step": 153
    },
    {
      "epoch": 0.0613652778123677,
      "grad_norm": 0.45037057995796204,
      "learning_rate": 0.00015103402886500525,
      "loss": 1.4952,
      "step": 154
    },
    {
      "epoch": 0.061763753642318134,
      "grad_norm": 0.531578004360199,
      "learning_rate": 0.00015041448123368455,
      "loss": 1.7191,
      "step": 155
    },
    {
      "epoch": 0.06216222947226857,
      "grad_norm": 0.48476216197013855,
      "learning_rate": 0.00014979232810700637,
      "loss": 1.7732,
      "step": 156
    },
    {
      "epoch": 0.06256070530221901,
      "grad_norm": 0.48990944027900696,
      "learning_rate": 0.0001491676016387694,
      "loss": 1.6629,
      "step": 157
    },
    {
      "epoch": 0.06295918113216945,
      "grad_norm": 0.5288809537887573,
      "learning_rate": 0.00014854033411576659,
      "loss": 1.6989,
      "step": 158
    },
    {
      "epoch": 0.0633576569621199,
      "grad_norm": 0.520767331123352,
      "learning_rate": 0.00014791055795611624,
      "loss": 1.6098,
      "step": 159
    },
    {
      "epoch": 0.06375613279207033,
      "grad_norm": 0.49702882766723633,
      "learning_rate": 0.00014727830570758678,
      "loss": 1.5923,
      "step": 160
    },
    {
      "epoch": 0.06415460862202077,
      "grad_norm": 0.555203378200531,
      "learning_rate": 0.0001466436100459146,
      "loss": 1.8835,
      "step": 161
    },
    {
      "epoch": 0.06455308445197121,
      "grad_norm": 0.49902498722076416,
      "learning_rate": 0.00014600650377311522,
      "loss": 1.6217,
      "step": 162
    },
    {
      "epoch": 0.06495156028192164,
      "grad_norm": 0.4641701877117157,
      "learning_rate": 0.0001453670198157883,
      "loss": 1.6337,
      "step": 163
    },
    {
      "epoch": 0.0653500361118721,
      "grad_norm": 0.5301873087882996,
      "learning_rate": 0.00014472519122341566,
      "loss": 1.7073,
      "step": 164
    },
    {
      "epoch": 0.06574851194182253,
      "grad_norm": 0.5231285095214844,
      "learning_rate": 0.00014408105116665336,
      "loss": 1.8093,
      "step": 165
    },
    {
      "epoch": 0.06614698777177297,
      "grad_norm": 0.45359745621681213,
      "learning_rate": 0.00014343463293561734,
      "loss": 1.6956,
      "step": 166
    },
    {
      "epoch": 0.0665454636017234,
      "grad_norm": 0.44360700249671936,
      "learning_rate": 0.00014278596993816308,
      "loss": 1.6548,
      "step": 167
    },
    {
      "epoch": 0.06694393943167384,
      "grad_norm": 0.4991564452648163,
      "learning_rate": 0.00014213509569815884,
      "loss": 1.7701,
      "step": 168
    },
    {
      "epoch": 0.06734241526162428,
      "grad_norm": 0.4743082821369171,
      "learning_rate": 0.00014148204385375321,
      "loss": 1.7401,
      "step": 169
    },
    {
      "epoch": 0.06774089109157473,
      "grad_norm": 0.5044605731964111,
      "learning_rate": 0.0001408268481556366,
      "loss": 1.6009,
      "step": 170
    },
    {
      "epoch": 0.06813936692152517,
      "grad_norm": 0.49447423219680786,
      "learning_rate": 0.00014016954246529696,
      "loss": 1.6208,
      "step": 171
    },
    {
      "epoch": 0.0685378427514756,
      "grad_norm": 0.46173223853111267,
      "learning_rate": 0.0001395101607532698,
      "loss": 1.6046,
      "step": 172
    },
    {
      "epoch": 0.06893631858142604,
      "grad_norm": 0.5149829983711243,
      "learning_rate": 0.00013884873709738257,
      "loss": 1.6744,
      "step": 173
    },
    {
      "epoch": 0.06933479441137648,
      "grad_norm": 0.4951649010181427,
      "learning_rate": 0.00013818530568099327,
      "loss": 1.7894,
      "step": 174
    },
    {
      "epoch": 0.06973327024132693,
      "grad_norm": 0.4963831603527069,
      "learning_rate": 0.00013751990079122412,
      "loss": 1.7119,
      "step": 175
    },
    {
      "epoch": 0.07013174607127737,
      "grad_norm": 0.48155760765075684,
      "learning_rate": 0.00013685255681718922,
      "loss": 1.6867,
      "step": 176
    },
    {
      "epoch": 0.0705302219012278,
      "grad_norm": 0.4654506742954254,
      "learning_rate": 0.0001361833082482175,
      "loss": 1.535,
      "step": 177
    },
    {
      "epoch": 0.07092869773117824,
      "grad_norm": 0.4506324827671051,
      "learning_rate": 0.0001355121896720703,
      "loss": 1.5751,
      "step": 178
    },
    {
      "epoch": 0.07132717356112868,
      "grad_norm": 0.5030463933944702,
      "learning_rate": 0.00013483923577315348,
      "loss": 1.7494,
      "step": 179
    },
    {
      "epoch": 0.07172564939107912,
      "grad_norm": 0.4498404264450073,
      "learning_rate": 0.00013416448133072526,
      "loss": 1.5368,
      "step": 180
    },
    {
      "epoch": 0.07212412522102957,
      "grad_norm": 0.5255778431892395,
      "learning_rate": 0.00013348796121709862,
      "loss": 1.6465,
      "step": 181
    },
    {
      "epoch": 0.07252260105098,
      "grad_norm": 0.566211998462677,
      "learning_rate": 0.00013280971039583906,
      "loss": 1.6151,
      "step": 182
    },
    {
      "epoch": 0.07292107688093044,
      "grad_norm": 0.5025095343589783,
      "learning_rate": 0.0001321297639199575,
      "loss": 1.6099,
      "step": 183
    },
    {
      "epoch": 0.07331955271088088,
      "grad_norm": 0.5001662969589233,
      "learning_rate": 0.000131448156930099,
      "loss": 1.5435,
      "step": 184
    },
    {
      "epoch": 0.07371802854083132,
      "grad_norm": 0.5104225277900696,
      "learning_rate": 0.0001307649246527263,
      "loss": 1.7083,
      "step": 185
    },
    {
      "epoch": 0.07411650437078177,
      "grad_norm": 0.4568442404270172,
      "learning_rate": 0.0001300801023982995,
      "loss": 1.555,
      "step": 186
    },
    {
      "epoch": 0.0745149802007322,
      "grad_norm": 0.5155336856842041,
      "learning_rate": 0.00012939372555945112,
      "loss": 1.6897,
      "step": 187
    },
    {
      "epoch": 0.07491345603068264,
      "grad_norm": 0.5319402813911438,
      "learning_rate": 0.0001287058296091567,
      "loss": 1.7909,
      "step": 188
    },
    {
      "epoch": 0.07531193186063308,
      "grad_norm": 0.5743489861488342,
      "learning_rate": 0.00012801645009890195,
      "loss": 1.9705,
      "step": 189
    },
    {
      "epoch": 0.07571040769058351,
      "grad_norm": 0.4790689945220947,
      "learning_rate": 0.0001273256226568451,
      "loss": 1.4495,
      "step": 190
    },
    {
      "epoch": 0.07610888352053395,
      "grad_norm": 0.47618716955184937,
      "learning_rate": 0.00012663338298597563,
      "loss": 1.7269,
      "step": 191
    },
    {
      "epoch": 0.0765073593504844,
      "grad_norm": 0.429544597864151,
      "learning_rate": 0.00012593976686226904,
      "loss": 1.488,
      "step": 192
    },
    {
      "epoch": 0.07690583518043484,
      "grad_norm": 0.5185227394104004,
      "learning_rate": 0.0001252448101328381,
      "loss": 1.6479,
      "step": 193
    },
    {
      "epoch": 0.07730431101038528,
      "grad_norm": 0.44675058126449585,
      "learning_rate": 0.00012454854871407994,
      "loss": 1.5254,
      "step": 194
    },
    {
      "epoch": 0.07770278684033571,
      "grad_norm": 0.5390235185623169,
      "learning_rate": 0.00012385101858982005,
      "loss": 1.4862,
      "step": 195
    },
    {
      "epoch": 0.07810126267028615,
      "grad_norm": 0.4766441583633423,
      "learning_rate": 0.00012315225580945252,
      "loss": 1.6441,
      "step": 196
    },
    {
      "epoch": 0.0784997385002366,
      "grad_norm": 0.46869808435440063,
      "learning_rate": 0.0001224522964860769,
      "loss": 1.7038,
      "step": 197
    },
    {
      "epoch": 0.07889821433018704,
      "grad_norm": 0.42946845293045044,
      "learning_rate": 0.00012175117679463187,
      "loss": 1.5641,
      "step": 198
    },
    {
      "epoch": 0.07929669016013748,
      "grad_norm": 0.4762909412384033,
      "learning_rate": 0.00012104893297002567,
      "loss": 1.6807,
      "step": 199
    },
    {
      "epoch": 0.07969516599008791,
      "grad_norm": 0.4462391138076782,
      "learning_rate": 0.0001203456013052634,
      "loss": 1.5805,
      "step": 200
    },
    {
      "epoch": 0.07969516599008791,
      "eval_loss": 1.7198740243911743,
      "eval_runtime": 603.1346,
      "eval_samples_per_second": 14.017,
      "eval_steps_per_second": 3.505,
      "step": 200
    },
    {
      "epoch": 0.08009364182003835,
      "grad_norm": 0.5120438933372498,
      "learning_rate": 0.00011964121814957137,
      "loss": 1.7626,
      "step": 201
    },
    {
      "epoch": 0.08049211764998879,
      "grad_norm": 0.5081213712692261,
      "learning_rate": 0.00011893581990651848,
      "loss": 1.7664,
      "step": 202
    },
    {
      "epoch": 0.08089059347993924,
      "grad_norm": 0.45303136110305786,
      "learning_rate": 0.00011822944303213486,
      "loss": 1.4845,
      "step": 203
    },
    {
      "epoch": 0.08128906930988967,
      "grad_norm": 0.4521328806877136,
      "learning_rate": 0.00011752212403302784,
      "loss": 1.4534,
      "step": 204
    },
    {
      "epoch": 0.08168754513984011,
      "grad_norm": 0.4870966970920563,
      "learning_rate": 0.00011681389946449504,
      "loss": 1.568,
      "step": 205
    },
    {
      "epoch": 0.08208602096979055,
      "grad_norm": 0.5694287419319153,
      "learning_rate": 0.00011610480592863531,
      "loss": 1.9597,
      "step": 206
    },
    {
      "epoch": 0.08248449679974099,
      "grad_norm": 0.5484179258346558,
      "learning_rate": 0.00011539488007245702,
      "loss": 1.8557,
      "step": 207
    },
    {
      "epoch": 0.08288297262969144,
      "grad_norm": 0.44166100025177,
      "learning_rate": 0.00011468415858598411,
      "loss": 1.5371,
      "step": 208
    },
    {
      "epoch": 0.08328144845964187,
      "grad_norm": 0.5365661978721619,
      "learning_rate": 0.00011397267820035986,
      "loss": 1.7778,
      "step": 209
    },
    {
      "epoch": 0.08367992428959231,
      "grad_norm": 0.45911017060279846,
      "learning_rate": 0.00011326047568594851,
      "loss": 1.5729,
      "step": 210
    },
    {
      "epoch": 0.08407840011954275,
      "grad_norm": 0.5417599678039551,
      "learning_rate": 0.00011254758785043515,
      "loss": 1.8296,
      "step": 211
    },
    {
      "epoch": 0.08447687594949319,
      "grad_norm": 0.48594942688941956,
      "learning_rate": 0.0001118340515369232,
      "loss": 1.7837,
      "step": 212
    },
    {
      "epoch": 0.08487535177944362,
      "grad_norm": 0.4888298511505127,
      "learning_rate": 0.00011111990362203033,
      "loss": 1.6575,
      "step": 213
    },
    {
      "epoch": 0.08527382760939407,
      "grad_norm": 0.5313907265663147,
      "learning_rate": 0.00011040518101398276,
      "loss": 1.7803,
      "step": 214
    },
    {
      "epoch": 0.08567230343934451,
      "grad_norm": 0.5065906643867493,
      "learning_rate": 0.00010968992065070769,
      "loss": 1.6539,
      "step": 215
    },
    {
      "epoch": 0.08607077926929495,
      "grad_norm": 0.46294957399368286,
      "learning_rate": 0.00010897415949792427,
      "loss": 1.6412,
      "step": 216
    },
    {
      "epoch": 0.08646925509924538,
      "grad_norm": 0.5068647861480713,
      "learning_rate": 0.00010825793454723325,
      "loss": 1.7173,
      "step": 217
    },
    {
      "epoch": 0.08686773092919582,
      "grad_norm": 0.45219966769218445,
      "learning_rate": 0.0001075412828142051,
      "loss": 1.4531,
      "step": 218
    },
    {
      "epoch": 0.08726620675914626,
      "grad_norm": 0.48035022616386414,
      "learning_rate": 0.0001068242413364671,
      "loss": 1.6187,
      "step": 219
    },
    {
      "epoch": 0.08766468258909671,
      "grad_norm": 0.5463985204696655,
      "learning_rate": 0.00010610684717178905,
      "loss": 1.749,
      "step": 220
    },
    {
      "epoch": 0.08806315841904715,
      "grad_norm": 0.4818764626979828,
      "learning_rate": 0.00010538913739616816,
      "loss": 1.4508,
      "step": 221
    },
    {
      "epoch": 0.08846163424899758,
      "grad_norm": 0.5018213987350464,
      "learning_rate": 0.00010467114910191289,
      "loss": 1.6853,
      "step": 222
    },
    {
      "epoch": 0.08886011007894802,
      "grad_norm": 0.5122075080871582,
      "learning_rate": 0.00010395291939572593,
      "loss": 1.6991,
      "step": 223
    },
    {
      "epoch": 0.08925858590889846,
      "grad_norm": 0.48191148042678833,
      "learning_rate": 0.00010323448539678653,
      "loss": 1.6428,
      "step": 224
    },
    {
      "epoch": 0.08965706173884891,
      "grad_norm": 0.4748276472091675,
      "learning_rate": 0.00010251588423483205,
      "loss": 1.7059,
      "step": 225
    },
    {
      "epoch": 0.09005553756879935,
      "grad_norm": 0.5150067806243896,
      "learning_rate": 0.0001017971530482392,
      "loss": 1.7409,
      "step": 226
    },
    {
      "epoch": 0.09045401339874978,
      "grad_norm": 0.5893855094909668,
      "learning_rate": 0.00010107832898210439,
      "loss": 1.7183,
      "step": 227
    },
    {
      "epoch": 0.09085248922870022,
      "grad_norm": 0.5195055603981018,
      "learning_rate": 0.00010035944918632429,
      "loss": 1.8396,
      "step": 228
    },
    {
      "epoch": 0.09125096505865066,
      "grad_norm": 0.5996953845024109,
      "learning_rate": 9.96405508136757e-05,
      "loss": 1.9944,
      "step": 229
    },
    {
      "epoch": 0.0916494408886011,
      "grad_norm": 0.5057780146598816,
      "learning_rate": 9.892167101789564e-05,
      "loss": 1.6473,
      "step": 230
    },
    {
      "epoch": 0.09204791671855155,
      "grad_norm": 0.46774283051490784,
      "learning_rate": 9.820284695176082e-05,
      "loss": 1.5973,
      "step": 231
    },
    {
      "epoch": 0.09244639254850198,
      "grad_norm": 0.46982142329216003,
      "learning_rate": 9.748411576516794e-05,
      "loss": 1.6464,
      "step": 232
    },
    {
      "epoch": 0.09284486837845242,
      "grad_norm": 0.4873621165752411,
      "learning_rate": 9.676551460321349e-05,
      "loss": 1.6629,
      "step": 233
    },
    {
      "epoch": 0.09324334420840286,
      "grad_norm": 0.4866909682750702,
      "learning_rate": 9.60470806042741e-05,
      "loss": 1.6262,
      "step": 234
    },
    {
      "epoch": 0.0936418200383533,
      "grad_norm": 0.5320809483528137,
      "learning_rate": 9.532885089808713e-05,
      "loss": 1.7158,
      "step": 235
    },
    {
      "epoch": 0.09404029586830374,
      "grad_norm": 0.47346270084381104,
      "learning_rate": 9.461086260383187e-05,
      "loss": 1.6044,
      "step": 236
    },
    {
      "epoch": 0.09443877169825418,
      "grad_norm": 0.5696609616279602,
      "learning_rate": 9.389315282821097e-05,
      "loss": 1.7883,
      "step": 237
    },
    {
      "epoch": 0.09483724752820462,
      "grad_norm": 0.4926949441432953,
      "learning_rate": 9.317575866353292e-05,
      "loss": 1.7306,
      "step": 238
    },
    {
      "epoch": 0.09523572335815506,
      "grad_norm": 0.5241943001747131,
      "learning_rate": 9.245871718579491e-05,
      "loss": 1.732,
      "step": 239
    },
    {
      "epoch": 0.09563419918810549,
      "grad_norm": 0.5425236225128174,
      "learning_rate": 9.174206545276677e-05,
      "loss": 1.6209,
      "step": 240
    },
    {
      "epoch": 0.09603267501805593,
      "grad_norm": 0.5216458439826965,
      "learning_rate": 9.102584050207578e-05,
      "loss": 1.74,
      "step": 241
    },
    {
      "epoch": 0.09643115084800638,
      "grad_norm": 0.5082316994667053,
      "learning_rate": 9.031007934929236e-05,
      "loss": 1.6836,
      "step": 242
    },
    {
      "epoch": 0.09682962667795682,
      "grad_norm": 0.48965132236480713,
      "learning_rate": 8.959481898601728e-05,
      "loss": 1.7055,
      "step": 243
    },
    {
      "epoch": 0.09722810250790725,
      "grad_norm": 0.514946699142456,
      "learning_rate": 8.888009637796968e-05,
      "loss": 1.684,
      "step": 244
    },
    {
      "epoch": 0.09762657833785769,
      "grad_norm": 0.551802396774292,
      "learning_rate": 8.81659484630768e-05,
      "loss": 1.8566,
      "step": 245
    },
    {
      "epoch": 0.09802505416780813,
      "grad_norm": 0.4790934920310974,
      "learning_rate": 8.745241214956483e-05,
      "loss": 1.6461,
      "step": 246
    },
    {
      "epoch": 0.09842352999775858,
      "grad_norm": 0.5450412631034851,
      "learning_rate": 8.673952431405148e-05,
      "loss": 1.7215,
      "step": 247
    },
    {
      "epoch": 0.09882200582770902,
      "grad_norm": 0.5299497842788696,
      "learning_rate": 8.602732179964017e-05,
      "loss": 1.7454,
      "step": 248
    },
    {
      "epoch": 0.09922048165765945,
      "grad_norm": 0.5010784268379211,
      "learning_rate": 8.531584141401591e-05,
      "loss": 1.6028,
      "step": 249
    },
    {
      "epoch": 0.09961895748760989,
      "grad_norm": 0.4926188886165619,
      "learning_rate": 8.4605119927543e-05,
      "loss": 1.6837,
      "step": 250
    },
    {
      "epoch": 0.10001743331756033,
      "grad_norm": 0.5703017115592957,
      "learning_rate": 8.38951940713647e-05,
      "loss": 1.8639,
      "step": 251
    },
    {
      "epoch": 0.10041590914751077,
      "grad_norm": 0.5429261326789856,
      "learning_rate": 8.318610053550497e-05,
      "loss": 1.7258,
      "step": 252
    },
    {
      "epoch": 0.10081438497746122,
      "grad_norm": 0.48338782787323,
      "learning_rate": 8.247787596697218e-05,
      "loss": 1.5873,
      "step": 253
    },
    {
      "epoch": 0.10121286080741165,
      "grad_norm": 0.506877601146698,
      "learning_rate": 8.177055696786516e-05,
      "loss": 1.6736,
      "step": 254
    },
    {
      "epoch": 0.10161133663736209,
      "grad_norm": 0.537820041179657,
      "learning_rate": 8.106418009348157e-05,
      "loss": 1.9075,
      "step": 255
    },
    {
      "epoch": 0.10200981246731253,
      "grad_norm": 0.4729152023792267,
      "learning_rate": 8.035878185042868e-05,
      "loss": 1.5359,
      "step": 256
    },
    {
      "epoch": 0.10240828829726296,
      "grad_norm": 0.4413747191429138,
      "learning_rate": 7.965439869473664e-05,
      "loss": 1.6245,
      "step": 257
    },
    {
      "epoch": 0.10280676412721342,
      "grad_norm": 0.5398510694503784,
      "learning_rate": 7.895106702997437e-05,
      "loss": 1.6318,
      "step": 258
    },
    {
      "epoch": 0.10320523995716385,
      "grad_norm": 0.5172785520553589,
      "learning_rate": 7.824882320536814e-05,
      "loss": 1.6601,
      "step": 259
    },
    {
      "epoch": 0.10360371578711429,
      "grad_norm": 0.4824993908405304,
      "learning_rate": 7.754770351392311e-05,
      "loss": 1.5672,
      "step": 260
    },
    {
      "epoch": 0.10400219161706473,
      "grad_norm": 0.4745709300041199,
      "learning_rate": 7.684774419054747e-05,
      "loss": 1.7128,
      "step": 261
    },
    {
      "epoch": 0.10440066744701516,
      "grad_norm": 0.5071855783462524,
      "learning_rate": 7.614898141017996e-05,
      "loss": 1.7368,
      "step": 262
    },
    {
      "epoch": 0.1047991432769656,
      "grad_norm": 0.5377690196037292,
      "learning_rate": 7.54514512859201e-05,
      "loss": 1.8659,
      "step": 263
    },
    {
      "epoch": 0.10519761910691605,
      "grad_norm": 0.4762866199016571,
      "learning_rate": 7.475518986716194e-05,
      "loss": 1.6012,
      "step": 264
    },
    {
      "epoch": 0.10559609493686649,
      "grad_norm": 0.46296924352645874,
      "learning_rate": 7.406023313773097e-05,
      "loss": 1.5484,
      "step": 265
    },
    {
      "epoch": 0.10599457076681693,
      "grad_norm": 0.47845426201820374,
      "learning_rate": 7.336661701402439e-05,
      "loss": 1.6248,
      "step": 266
    },
    {
      "epoch": 0.10639304659676736,
      "grad_norm": 0.48351001739501953,
      "learning_rate": 7.267437734315492e-05,
      "loss": 1.5549,
      "step": 267
    },
    {
      "epoch": 0.1067915224267178,
      "grad_norm": 0.48554375767707825,
      "learning_rate": 7.198354990109805e-05,
      "loss": 1.5708,
      "step": 268
    },
    {
      "epoch": 0.10718999825666825,
      "grad_norm": 0.47755077481269836,
      "learning_rate": 7.129417039084333e-05,
      "loss": 1.5864,
      "step": 269
    },
    {
      "epoch": 0.10758847408661869,
      "grad_norm": 0.4970269799232483,
      "learning_rate": 7.060627444054893e-05,
      "loss": 1.6373,
      "step": 270
    },
    {
      "epoch": 0.10798694991656912,
      "grad_norm": 0.47547978162765503,
      "learning_rate": 6.99198976017005e-05,
      "loss": 1.7433,
      "step": 271
    },
    {
      "epoch": 0.10838542574651956,
      "grad_norm": 0.5408848524093628,
      "learning_rate": 6.923507534727373e-05,
      "loss": 1.77,
      "step": 272
    },
    {
      "epoch": 0.10878390157647,
      "grad_norm": 0.49777430295944214,
      "learning_rate": 6.855184306990106e-05,
      "loss": 1.6071,
      "step": 273
    },
    {
      "epoch": 0.10918237740642044,
      "grad_norm": 0.4691534638404846,
      "learning_rate": 6.78702360800425e-05,
      "loss": 1.5913,
      "step": 274
    },
    {
      "epoch": 0.10958085323637089,
      "grad_norm": 0.5284269452095032,
      "learning_rate": 6.719028960416098e-05,
      "loss": 1.8038,
      "step": 275
    },
    {
      "epoch": 0.10997932906632132,
      "grad_norm": 0.49061042070388794,
      "learning_rate": 6.651203878290139e-05,
      "loss": 1.5991,
      "step": 276
    },
    {
      "epoch": 0.11037780489627176,
      "grad_norm": 0.5676330327987671,
      "learning_rate": 6.583551866927475e-05,
      "loss": 1.8924,
      "step": 277
    },
    {
      "epoch": 0.1107762807262222,
      "grad_norm": 0.5392544865608215,
      "learning_rate": 6.516076422684654e-05,
      "loss": 1.7611,
      "step": 278
    },
    {
      "epoch": 0.11117475655617264,
      "grad_norm": 0.5719506740570068,
      "learning_rate": 6.448781032792972e-05,
      "loss": 1.756,
      "step": 279
    },
    {
      "epoch": 0.11157323238612307,
      "grad_norm": 0.4809233248233795,
      "learning_rate": 6.381669175178248e-05,
      "loss": 1.641,
      "step": 280
    },
    {
      "epoch": 0.11197170821607352,
      "grad_norm": 0.48434188961982727,
      "learning_rate": 6.31474431828108e-05,
      "loss": 1.579,
      "step": 281
    },
    {
      "epoch": 0.11237018404602396,
      "grad_norm": 0.5024405717849731,
      "learning_rate": 6.248009920877592e-05,
      "loss": 1.6653,
      "step": 282
    },
    {
      "epoch": 0.1127686598759744,
      "grad_norm": 0.441279798746109,
      "learning_rate": 6.181469431900672e-05,
      "loss": 1.5105,
      "step": 283
    },
    {
      "epoch": 0.11316713570592483,
      "grad_norm": 0.5233234763145447,
      "learning_rate": 6.115126290261745e-05,
      "loss": 1.7695,
      "step": 284
    },
    {
      "epoch": 0.11356561153587527,
      "grad_norm": 0.5281261801719666,
      "learning_rate": 6.048983924673022e-05,
      "loss": 1.76,
      "step": 285
    },
    {
      "epoch": 0.11396408736582572,
      "grad_norm": 0.534590482711792,
      "learning_rate": 5.983045753470308e-05,
      "loss": 1.8155,
      "step": 286
    },
    {
      "epoch": 0.11436256319577616,
      "grad_norm": 0.5247072577476501,
      "learning_rate": 5.917315184436345e-05,
      "loss": 1.6073,
      "step": 287
    },
    {
      "epoch": 0.1147610390257266,
      "grad_norm": 0.4829355776309967,
      "learning_rate": 5.851795614624682e-05,
      "loss": 1.5224,
      "step": 288
    },
    {
      "epoch": 0.11515951485567703,
      "grad_norm": 0.516015887260437,
      "learning_rate": 5.786490430184115e-05,
      "loss": 1.6813,
      "step": 289
    },
    {
      "epoch": 0.11555799068562747,
      "grad_norm": 0.48894891142845154,
      "learning_rate": 5.72140300618369e-05,
      "loss": 1.7965,
      "step": 290
    },
    {
      "epoch": 0.11595646651557791,
      "grad_norm": 0.49149996042251587,
      "learning_rate": 5.656536706438267e-05,
      "loss": 1.6388,
      "step": 291
    },
    {
      "epoch": 0.11635494234552836,
      "grad_norm": 0.4835774898529053,
      "learning_rate": 5.591894883334667e-05,
      "loss": 1.6856,
      "step": 292
    },
    {
      "epoch": 0.1167534181754788,
      "grad_norm": 0.5278857946395874,
      "learning_rate": 5.5274808776584367e-05,
      "loss": 1.6883,
      "step": 293
    },
    {
      "epoch": 0.11715189400542923,
      "grad_norm": 0.4995588958263397,
      "learning_rate": 5.463298018421171e-05,
      "loss": 1.519,
      "step": 294
    },
    {
      "epoch": 0.11755036983537967,
      "grad_norm": 0.5236543416976929,
      "learning_rate": 5.399349622688479e-05,
      "loss": 1.7372,
      "step": 295
    },
    {
      "epoch": 0.11794884566533011,
      "grad_norm": 0.45699524879455566,
      "learning_rate": 5.335638995408545e-05,
      "loss": 1.6082,
      "step": 296
    },
    {
      "epoch": 0.11834732149528056,
      "grad_norm": 0.5191316604614258,
      "learning_rate": 5.272169429241325e-05,
      "loss": 1.7123,
      "step": 297
    },
    {
      "epoch": 0.118745797325231,
      "grad_norm": 0.42880895733833313,
      "learning_rate": 5.208944204388377e-05,
      "loss": 1.4809,
      "step": 298
    },
    {
      "epoch": 0.11914427315518143,
      "grad_norm": 0.5574065446853638,
      "learning_rate": 5.145966588423341e-05,
      "loss": 1.8128,
      "step": 299
    },
    {
      "epoch": 0.11954274898513187,
      "grad_norm": 0.47847244143486023,
      "learning_rate": 5.0832398361230596e-05,
      "loss": 1.5699,
      "step": 300
    },
    {
      "epoch": 0.11954274898513187,
      "eval_loss": 1.700640082359314,
      "eval_runtime": 603.0633,
      "eval_samples_per_second": 14.018,
      "eval_steps_per_second": 3.505,
      "step": 300
    }
  ],
  "logging_steps": 1,
  "max_steps": 447,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.388464319922176e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}