{
  "best_metric": 0.6945011615753174,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.02516910492370615,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.292276230926537e-05,
      "grad_norm": 4.59516716003418,
      "learning_rate": 1e-05,
      "loss": 3.1281,
      "step": 1
    },
    {
      "epoch": 6.292276230926537e-05,
      "eval_loss": 3.3380603790283203,
      "eval_runtime": 1980.002,
      "eval_samples_per_second": 13.519,
      "eval_steps_per_second": 3.38,
      "step": 1
    },
    {
      "epoch": 0.00012584552461853074,
      "grad_norm": 5.216956615447998,
      "learning_rate": 2e-05,
      "loss": 3.3234,
      "step": 2
    },
    {
      "epoch": 0.00018876828692779613,
      "grad_norm": 4.922913074493408,
      "learning_rate": 3e-05,
      "loss": 3.1657,
      "step": 3
    },
    {
      "epoch": 0.0002516910492370615,
      "grad_norm": 3.8697447776794434,
      "learning_rate": 4e-05,
      "loss": 2.998,
      "step": 4
    },
    {
      "epoch": 0.0003146138115463269,
      "grad_norm": 3.7430148124694824,
      "learning_rate": 5e-05,
      "loss": 2.6709,
      "step": 5
    },
    {
      "epoch": 0.00037753657385559226,
      "grad_norm": 3.408188819885254,
      "learning_rate": 6e-05,
      "loss": 2.3179,
      "step": 6
    },
    {
      "epoch": 0.00044045933616485765,
      "grad_norm": 3.0654706954956055,
      "learning_rate": 7e-05,
      "loss": 2.1039,
      "step": 7
    },
    {
      "epoch": 0.000503382098474123,
      "grad_norm": 3.04288387298584,
      "learning_rate": 8e-05,
      "loss": 1.7594,
      "step": 8
    },
    {
      "epoch": 0.0005663048607833884,
      "grad_norm": 2.724019765853882,
      "learning_rate": 9e-05,
      "loss": 1.5574,
      "step": 9
    },
    {
      "epoch": 0.0006292276230926538,
      "grad_norm": 2.3080849647521973,
      "learning_rate": 0.0001,
      "loss": 1.4881,
      "step": 10
    },
    {
      "epoch": 0.0006921503854019191,
      "grad_norm": 2.039785861968994,
      "learning_rate": 9.99983777858264e-05,
      "loss": 1.422,
      "step": 11
    },
    {
      "epoch": 0.0007550731477111845,
      "grad_norm": 1.599783182144165,
      "learning_rate": 9.999351124856874e-05,
      "loss": 1.1494,
      "step": 12
    },
    {
      "epoch": 0.0008179959100204499,
      "grad_norm": 1.685577392578125,
      "learning_rate": 9.998540070400966e-05,
      "loss": 1.1811,
      "step": 13
    },
    {
      "epoch": 0.0008809186723297153,
      "grad_norm": 1.5412378311157227,
      "learning_rate": 9.997404667843075e-05,
      "loss": 1.1081,
      "step": 14
    },
    {
      "epoch": 0.0009438414346389807,
      "grad_norm": 1.567974328994751,
      "learning_rate": 9.995944990857849e-05,
      "loss": 1.1671,
      "step": 15
    },
    {
      "epoch": 0.001006764196948246,
      "grad_norm": 1.5965992212295532,
      "learning_rate": 9.994161134161634e-05,
      "loss": 1.138,
      "step": 16
    },
    {
      "epoch": 0.0010696869592575113,
      "grad_norm": 1.4739341735839844,
      "learning_rate": 9.992053213506334e-05,
      "loss": 1.1432,
      "step": 17
    },
    {
      "epoch": 0.0011326097215667767,
      "grad_norm": 1.693847894668579,
      "learning_rate": 9.989621365671902e-05,
      "loss": 0.9893,
      "step": 18
    },
    {
      "epoch": 0.0011955324838760421,
      "grad_norm": 1.262269377708435,
      "learning_rate": 9.986865748457457e-05,
      "loss": 0.9833,
      "step": 19
    },
    {
      "epoch": 0.0012584552461853075,
      "grad_norm": 1.2658629417419434,
      "learning_rate": 9.983786540671051e-05,
      "loss": 0.9171,
      "step": 20
    },
    {
      "epoch": 0.0013213780084945729,
      "grad_norm": 1.2282474040985107,
      "learning_rate": 9.980383942118066e-05,
      "loss": 0.9978,
      "step": 21
    },
    {
      "epoch": 0.0013843007708038383,
      "grad_norm": 0.960390567779541,
      "learning_rate": 9.976658173588244e-05,
      "loss": 0.9271,
      "step": 22
    },
    {
      "epoch": 0.0014472235331131037,
      "grad_norm": 1.1571574211120605,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.8878,
      "step": 23
    },
    {
      "epoch": 0.001510146295422369,
      "grad_norm": 1.1556771993637085,
      "learning_rate": 9.968238114591566e-05,
      "loss": 0.9895,
      "step": 24
    },
    {
      "epoch": 0.0015730690577316344,
      "grad_norm": 0.8927937746047974,
      "learning_rate": 9.96354437049027e-05,
      "loss": 0.7841,
      "step": 25
    },
    {
      "epoch": 0.0016359918200408998,
      "grad_norm": 1.126304030418396,
      "learning_rate": 9.95852854910781e-05,
      "loss": 0.9274,
      "step": 26
    },
    {
      "epoch": 0.0016989145823501652,
      "grad_norm": 1.238614797592163,
      "learning_rate": 9.953190975913647e-05,
      "loss": 0.9173,
      "step": 27
    },
    {
      "epoch": 0.0017618373446594306,
      "grad_norm": 0.9778956174850464,
      "learning_rate": 9.947531997255256e-05,
      "loss": 0.8841,
      "step": 28
    },
    {
      "epoch": 0.001824760106968696,
      "grad_norm": 1.1729629039764404,
      "learning_rate": 9.941551980335652e-05,
      "loss": 0.8547,
      "step": 29
    },
    {
      "epoch": 0.0018876828692779614,
      "grad_norm": 0.9491772651672363,
      "learning_rate": 9.935251313189564e-05,
      "loss": 0.841,
      "step": 30
    },
    {
      "epoch": 0.0019506056315872267,
      "grad_norm": 1.2383917570114136,
      "learning_rate": 9.928630404658255e-05,
      "loss": 0.8724,
      "step": 31
    },
    {
      "epoch": 0.002013528393896492,
      "grad_norm": 1.1126729249954224,
      "learning_rate": 9.921689684362989e-05,
      "loss": 0.8463,
      "step": 32
    },
    {
      "epoch": 0.0020764511562057575,
      "grad_norm": 1.2784355878829956,
      "learning_rate": 9.914429602677162e-05,
      "loss": 0.9435,
      "step": 33
    },
    {
      "epoch": 0.0021393739185150227,
      "grad_norm": 1.074558138847351,
      "learning_rate": 9.906850630697068e-05,
      "loss": 0.8062,
      "step": 34
    },
    {
      "epoch": 0.0022022966808242883,
      "grad_norm": 1.165006160736084,
      "learning_rate": 9.898953260211338e-05,
      "loss": 0.8545,
      "step": 35
    },
    {
      "epoch": 0.0022652194431335535,
      "grad_norm": 1.1657222509384155,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9286,
      "step": 36
    },
    {
      "epoch": 0.002328142205442819,
      "grad_norm": 1.1474952697753906,
      "learning_rate": 9.882205394146361e-05,
      "loss": 0.9362,
      "step": 37
    },
    {
      "epoch": 0.0023910649677520842,
      "grad_norm": 1.2673144340515137,
      "learning_rate": 9.87335598531214e-05,
      "loss": 0.8964,
      "step": 38
    },
    {
      "epoch": 0.00245398773006135,
      "grad_norm": 1.1087899208068848,
      "learning_rate": 9.864190351391822e-05,
      "loss": 0.852,
      "step": 39
    },
    {
      "epoch": 0.002516910492370615,
      "grad_norm": 0.9186160564422607,
      "learning_rate": 9.85470908713026e-05,
      "loss": 0.8565,
      "step": 40
    },
    {
      "epoch": 0.0025798332546798806,
      "grad_norm": 1.0054467916488647,
      "learning_rate": 9.844912807753104e-05,
      "loss": 0.9039,
      "step": 41
    },
    {
      "epoch": 0.0026427560169891458,
      "grad_norm": 0.9011829495429993,
      "learning_rate": 9.834802148926882e-05,
      "loss": 0.8552,
      "step": 42
    },
    {
      "epoch": 0.0027056787792984114,
      "grad_norm": 0.8763337135314941,
      "learning_rate": 9.824377766717759e-05,
      "loss": 0.8425,
      "step": 43
    },
    {
      "epoch": 0.0027686015416076766,
      "grad_norm": 1.0176167488098145,
      "learning_rate": 9.813640337548954e-05,
      "loss": 0.9245,
      "step": 44
    },
    {
      "epoch": 0.002831524303916942,
      "grad_norm": 0.9574334621429443,
      "learning_rate": 9.802590558156862e-05,
      "loss": 0.8706,
      "step": 45
    },
    {
      "epoch": 0.0028944470662262073,
      "grad_norm": 1.0388308763504028,
      "learning_rate": 9.791229145545831e-05,
      "loss": 0.9249,
      "step": 46
    },
    {
      "epoch": 0.0029573698285354725,
      "grad_norm": 1.0037546157836914,
      "learning_rate": 9.779556836941645e-05,
      "loss": 0.9104,
      "step": 47
    },
    {
      "epoch": 0.003020292590844738,
      "grad_norm": 0.877053439617157,
      "learning_rate": 9.767574389743682e-05,
      "loss": 0.9356,
      "step": 48
    },
    {
      "epoch": 0.0030832153531540033,
      "grad_norm": 0.9509828686714172,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8892,
      "step": 49
    },
    {
      "epoch": 0.003146138115463269,
      "grad_norm": 1.2426848411560059,
      "learning_rate": 9.742682209735727e-05,
      "loss": 0.9818,
      "step": 50
    },
    {
      "epoch": 0.003146138115463269,
      "eval_loss": 0.9876257181167603,
      "eval_runtime": 1992.3189,
      "eval_samples_per_second": 13.435,
      "eval_steps_per_second": 3.359,
      "step": 50
    },
    {
      "epoch": 0.003209060877772534,
      "grad_norm": 2.743227481842041,
      "learning_rate": 9.729774092143627e-05,
      "loss": 1.1564,
      "step": 51
    },
    {
      "epoch": 0.0032719836400817996,
      "grad_norm": 2.042041301727295,
      "learning_rate": 9.716559066288715e-05,
      "loss": 1.1023,
      "step": 52
    },
    {
      "epoch": 0.003334906402391065,
      "grad_norm": 1.4456409215927124,
      "learning_rate": 9.703037989675087e-05,
      "loss": 1.0536,
      "step": 53
    },
    {
      "epoch": 0.0033978291647003304,
      "grad_norm": 1.1415081024169922,
      "learning_rate": 9.689211739666023e-05,
      "loss": 0.8627,
      "step": 54
    },
    {
      "epoch": 0.0034607519270095956,
      "grad_norm": 0.9333504438400269,
      "learning_rate": 9.675081213427076e-05,
      "loss": 0.9348,
      "step": 55
    },
    {
      "epoch": 0.003523674689318861,
      "grad_norm": 0.7401662468910217,
      "learning_rate": 9.66064732786784e-05,
      "loss": 0.8109,
      "step": 56
    },
    {
      "epoch": 0.0035865974516281264,
      "grad_norm": 1.0346910953521729,
      "learning_rate": 9.645911019582467e-05,
      "loss": 0.9177,
      "step": 57
    },
    {
      "epoch": 0.003649520213937392,
      "grad_norm": 0.9704263806343079,
      "learning_rate": 9.630873244788883e-05,
      "loss": 0.9524,
      "step": 58
    },
    {
      "epoch": 0.003712442976246657,
      "grad_norm": 0.9952749609947205,
      "learning_rate": 9.615534979266745e-05,
      "loss": 0.8763,
      "step": 59
    },
    {
      "epoch": 0.0037753657385559227,
      "grad_norm": 0.7279119491577148,
      "learning_rate": 9.599897218294122e-05,
      "loss": 0.72,
      "step": 60
    },
    {
      "epoch": 0.003838288500865188,
      "grad_norm": 0.8951886892318726,
      "learning_rate": 9.583960976582913e-05,
      "loss": 0.8242,
      "step": 61
    },
    {
      "epoch": 0.0039012112631744535,
      "grad_norm": 1.0600823163986206,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8879,
      "step": 62
    },
    {
      "epoch": 0.003964134025483719,
      "grad_norm": 0.9607635736465454,
      "learning_rate": 9.551197206565173e-05,
      "loss": 0.8622,
      "step": 63
    },
    {
      "epoch": 0.004027056787792984,
      "grad_norm": 0.8205705285072327,
      "learning_rate": 9.534371804252728e-05,
      "loss": 0.8198,
      "step": 64
    },
    {
      "epoch": 0.00408997955010225,
      "grad_norm": 0.9197847247123718,
      "learning_rate": 9.517252173051911e-05,
      "loss": 0.7708,
      "step": 65
    },
    {
      "epoch": 0.004152902312411515,
      "grad_norm": 1.0398162603378296,
      "learning_rate": 9.49983942383106e-05,
      "loss": 0.8404,
      "step": 66
    },
    {
      "epoch": 0.00421582507472078,
      "grad_norm": 0.937667965888977,
      "learning_rate": 9.482134686478519e-05,
      "loss": 0.7937,
      "step": 67
    },
    {
      "epoch": 0.004278747837030045,
      "grad_norm": 0.7911063432693481,
      "learning_rate": 9.464139109829321e-05,
      "loss": 0.7707,
      "step": 68
    },
    {
      "epoch": 0.004341670599339311,
      "grad_norm": 0.9090245366096497,
      "learning_rate": 9.445853861590647e-05,
      "loss": 0.8013,
      "step": 69
    },
    {
      "epoch": 0.004404593361648577,
      "grad_norm": 0.7896239757537842,
      "learning_rate": 9.42728012826605e-05,
      "loss": 0.7714,
      "step": 70
    },
    {
      "epoch": 0.004467516123957842,
      "grad_norm": 0.8394172191619873,
      "learning_rate": 9.408419115078471e-05,
      "loss": 0.7667,
      "step": 71
    },
    {
      "epoch": 0.004530438886267107,
      "grad_norm": 0.9385750889778137,
      "learning_rate": 9.389272045892024e-05,
      "loss": 0.7939,
      "step": 72
    },
    {
      "epoch": 0.004593361648576372,
      "grad_norm": 0.8299635052680969,
      "learning_rate": 9.36984016313259e-05,
      "loss": 0.8294,
      "step": 73
    },
    {
      "epoch": 0.004656284410885638,
      "grad_norm": 0.7701219916343689,
      "learning_rate": 9.350124727707197e-05,
      "loss": 0.8171,
      "step": 74
    },
    {
      "epoch": 0.004719207173194903,
      "grad_norm": 0.7639235258102417,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.8171,
      "step": 75
    },
    {
      "epoch": 0.0047821299355041685,
      "grad_norm": 0.8286775946617126,
      "learning_rate": 9.309848334400246e-05,
      "loss": 0.7997,
      "step": 76
    },
    {
      "epoch": 0.004845052697813434,
      "grad_norm": 0.8708102703094482,
      "learning_rate": 9.289289989996133e-05,
      "loss": 0.8435,
      "step": 77
    },
    {
      "epoch": 0.0049079754601227,
      "grad_norm": 0.7374812960624695,
      "learning_rate": 9.268453319711363e-05,
      "loss": 0.7903,
      "step": 78
    },
    {
      "epoch": 0.004970898222431965,
      "grad_norm": 0.7260936498641968,
      "learning_rate": 9.247339675607605e-05,
      "loss": 0.7556,
      "step": 79
    },
    {
      "epoch": 0.00503382098474123,
      "grad_norm": 0.78413987159729,
      "learning_rate": 9.225950427718975e-05,
      "loss": 0.7595,
      "step": 80
    },
    {
      "epoch": 0.005096743747050495,
      "grad_norm": 0.9290556907653809,
      "learning_rate": 9.204286963963111e-05,
      "loss": 0.8279,
      "step": 81
    },
    {
      "epoch": 0.005159666509359761,
      "grad_norm": 0.8330967426300049,
      "learning_rate": 9.182350690051133e-05,
      "loss": 0.8712,
      "step": 82
    },
    {
      "epoch": 0.005222589271669026,
      "grad_norm": 0.9688509702682495,
      "learning_rate": 9.160143029396422e-05,
      "loss": 0.8465,
      "step": 83
    },
    {
      "epoch": 0.0052855120339782916,
      "grad_norm": 0.862083375453949,
      "learning_rate": 9.13766542302225e-05,
      "loss": 0.7303,
      "step": 84
    },
    {
      "epoch": 0.005348434796287557,
      "grad_norm": 0.6805185675621033,
      "learning_rate": 9.114919329468282e-05,
      "loss": 0.7395,
      "step": 85
    },
    {
      "epoch": 0.005411357558596823,
      "grad_norm": 0.8476338982582092,
      "learning_rate": 9.091906224695935e-05,
      "loss": 0.871,
      "step": 86
    },
    {
      "epoch": 0.005474280320906088,
      "grad_norm": 0.7605541348457336,
      "learning_rate": 9.068627601992598e-05,
      "loss": 0.8041,
      "step": 87
    },
    {
      "epoch": 0.005537203083215353,
      "grad_norm": 0.7872311472892761,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7563,
      "step": 88
    },
    {
      "epoch": 0.005600125845524618,
      "grad_norm": 0.7678333520889282,
      "learning_rate": 9.021279861989885e-05,
      "loss": 0.8247,
      "step": 89
    },
    {
      "epoch": 0.005663048607833884,
      "grad_norm": 0.7843219637870789,
      "learning_rate": 8.997213817017507e-05,
      "loss": 0.8162,
      "step": 90
    },
    {
      "epoch": 0.0057259713701431495,
      "grad_norm": 0.6998229622840881,
      "learning_rate": 8.972888398568772e-05,
      "loss": 0.7625,
      "step": 91
    },
    {
      "epoch": 0.005788894132452415,
      "grad_norm": 0.7472991943359375,
      "learning_rate": 8.948305185085225e-05,
      "loss": 0.81,
      "step": 92
    },
    {
      "epoch": 0.00585181689476168,
      "grad_norm": 0.7633485198020935,
      "learning_rate": 8.92346577173636e-05,
      "loss": 0.8172,
      "step": 93
    },
    {
      "epoch": 0.005914739657070945,
      "grad_norm": 0.759559690952301,
      "learning_rate": 8.898371770316111e-05,
      "loss": 0.8616,
      "step": 94
    },
    {
      "epoch": 0.005977662419380211,
      "grad_norm": 0.8597033619880676,
      "learning_rate": 8.873024809138272e-05,
      "loss": 0.8313,
      "step": 95
    },
    {
      "epoch": 0.006040585181689476,
      "grad_norm": 0.7939256429672241,
      "learning_rate": 8.847426532930831e-05,
      "loss": 0.8815,
      "step": 96
    },
    {
      "epoch": 0.006103507943998741,
      "grad_norm": 0.8816700577735901,
      "learning_rate": 8.821578602729242e-05,
      "loss": 0.8923,
      "step": 97
    },
    {
      "epoch": 0.0061664307063080065,
      "grad_norm": 0.9676582217216492,
      "learning_rate": 8.795482695768658e-05,
      "loss": 0.8964,
      "step": 98
    },
    {
      "epoch": 0.0062293534686172726,
      "grad_norm": 0.8678397536277771,
      "learning_rate": 8.769140505375085e-05,
      "loss": 0.8964,
      "step": 99
    },
    {
      "epoch": 0.006292276230926538,
      "grad_norm": 0.9837563633918762,
      "learning_rate": 8.742553740855506e-05,
      "loss": 0.8875,
      "step": 100
    },
    {
      "epoch": 0.006292276230926538,
      "eval_loss": 0.9126793146133423,
      "eval_runtime": 1993.501,
      "eval_samples_per_second": 13.427,
      "eval_steps_per_second": 3.357,
      "step": 100
    },
    {
      "epoch": 0.006355198993235803,
      "grad_norm": 1.4781923294067383,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.9134,
      "step": 101
    },
    {
      "epoch": 0.006418121755545068,
      "grad_norm": 1.337426781654358,
      "learning_rate": 8.688653405904652e-05,
      "loss": 0.9012,
      "step": 102
    },
    {
      "epoch": 0.006481044517854334,
      "grad_norm": 1.006500244140625,
      "learning_rate": 8.661343332988869e-05,
      "loss": 0.8645,
      "step": 103
    },
    {
      "epoch": 0.006543967280163599,
      "grad_norm": 0.842659592628479,
      "learning_rate": 8.633795680751116e-05,
      "loss": 0.8778,
      "step": 104
    },
    {
      "epoch": 0.0066068900424728644,
      "grad_norm": 0.7573593854904175,
      "learning_rate": 8.606012236719073e-05,
      "loss": 0.8292,
      "step": 105
    },
    {
      "epoch": 0.00666981280478213,
      "grad_norm": 0.8174044489860535,
      "learning_rate": 8.577994803720606e-05,
      "loss": 0.8189,
      "step": 106
    },
    {
      "epoch": 0.006732735567091396,
      "grad_norm": 0.8135045766830444,
      "learning_rate": 8.549745199766792e-05,
      "loss": 0.7401,
      "step": 107
    },
    {
      "epoch": 0.006795658329400661,
      "grad_norm": 0.8730856776237488,
      "learning_rate": 8.521265257933948e-05,
      "loss": 0.7662,
      "step": 108
    },
    {
      "epoch": 0.006858581091709926,
      "grad_norm": 0.8787916898727417,
      "learning_rate": 8.492556826244687e-05,
      "loss": 0.8372,
      "step": 109
    },
    {
      "epoch": 0.006921503854019191,
      "grad_norm": 0.7037457227706909,
      "learning_rate": 8.463621767547998e-05,
      "loss": 0.7454,
      "step": 110
    },
    {
      "epoch": 0.006984426616328457,
      "grad_norm": 0.7457066774368286,
      "learning_rate": 8.434461959398376e-05,
      "loss": 0.7488,
      "step": 111
    },
    {
      "epoch": 0.007047349378637722,
      "grad_norm": 0.7018367648124695,
      "learning_rate": 8.405079293933986e-05,
      "loss": 0.7122,
      "step": 112
    },
    {
      "epoch": 0.0071102721409469875,
      "grad_norm": 0.7626819610595703,
      "learning_rate": 8.375475677753881e-05,
      "loss": 0.7963,
      "step": 113
    },
    {
      "epoch": 0.007173194903256253,
      "grad_norm": 0.7396589517593384,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8108,
      "step": 114
    },
    {
      "epoch": 0.007236117665565519,
      "grad_norm": 0.7143003344535828,
      "learning_rate": 8.315613291203976e-05,
      "loss": 0.8086,
      "step": 115
    },
    {
      "epoch": 0.007299040427874784,
      "grad_norm": 0.8025134205818176,
      "learning_rate": 8.285358405218655e-05,
      "loss": 0.7624,
      "step": 116
    },
    {
      "epoch": 0.007361963190184049,
      "grad_norm": 0.7734766602516174,
      "learning_rate": 8.25489033703452e-05,
      "loss": 0.7575,
      "step": 117
    },
    {
      "epoch": 0.007424885952493314,
      "grad_norm": 0.6909343600273132,
      "learning_rate": 8.224211063680853e-05,
      "loss": 0.7947,
      "step": 118
    },
    {
      "epoch": 0.007487808714802579,
      "grad_norm": 0.7197896838188171,
      "learning_rate": 8.19332257589174e-05,
      "loss": 0.7929,
      "step": 119
    },
    {
      "epoch": 0.0075507314771118455,
      "grad_norm": 0.7764743566513062,
      "learning_rate": 8.162226877976887e-05,
      "loss": 0.8279,
      "step": 120
    },
    {
      "epoch": 0.007613654239421111,
      "grad_norm": 0.824350118637085,
      "learning_rate": 8.130925987691569e-05,
      "loss": 0.868,
      "step": 121
    },
    {
      "epoch": 0.007676577001730376,
      "grad_norm": 0.7358341813087463,
      "learning_rate": 8.099421936105702e-05,
      "loss": 0.7942,
      "step": 122
    },
    {
      "epoch": 0.007739499764039641,
      "grad_norm": 0.6394578218460083,
      "learning_rate": 8.067716767472045e-05,
      "loss": 0.766,
      "step": 123
    },
    {
      "epoch": 0.007802422526348907,
      "grad_norm": 0.860275149345398,
      "learning_rate": 8.035812539093557e-05,
      "loss": 0.8043,
      "step": 124
    },
    {
      "epoch": 0.007865345288658171,
      "grad_norm": 0.7427248358726501,
      "learning_rate": 8.003711321189895e-05,
      "loss": 0.7719,
      "step": 125
    },
    {
      "epoch": 0.007928268050967437,
      "grad_norm": 0.7343852519989014,
      "learning_rate": 7.971415196763088e-05,
      "loss": 0.7928,
      "step": 126
    },
    {
      "epoch": 0.007991190813276703,
      "grad_norm": 0.7235080003738403,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.753,
      "step": 127
    },
    {
      "epoch": 0.008054113575585968,
      "grad_norm": 0.6687210202217102,
      "learning_rate": 7.906246623448183e-05,
      "loss": 0.738,
      "step": 128
    },
    {
      "epoch": 0.008117036337895234,
      "grad_norm": 0.7192130088806152,
      "learning_rate": 7.873378403255419e-05,
      "loss": 0.7538,
      "step": 129
    },
    {
      "epoch": 0.0081799591002045,
      "grad_norm": 0.7208861708641052,
      "learning_rate": 7.840323733655778e-05,
      "loss": 0.7941,
      "step": 130
    },
    {
      "epoch": 0.008242881862513764,
      "grad_norm": 0.8294458985328674,
      "learning_rate": 7.807084759519405e-05,
      "loss": 0.7723,
      "step": 131
    },
    {
      "epoch": 0.00830580462482303,
      "grad_norm": 0.7591488361358643,
      "learning_rate": 7.773663637675694e-05,
      "loss": 0.837,
      "step": 132
    },
    {
      "epoch": 0.008368727387132294,
      "grad_norm": 0.6974380612373352,
      "learning_rate": 7.740062536773352e-05,
      "loss": 0.6939,
      "step": 133
    },
    {
      "epoch": 0.00843165014944156,
      "grad_norm": 0.6800892353057861,
      "learning_rate": 7.706283637139658e-05,
      "loss": 0.8119,
      "step": 134
    },
    {
      "epoch": 0.008494572911750826,
      "grad_norm": 0.7402788996696472,
      "learning_rate": 7.672329130639005e-05,
      "loss": 0.8032,
      "step": 135
    },
    {
      "epoch": 0.00855749567406009,
      "grad_norm": 0.7551749348640442,
      "learning_rate": 7.638201220530665e-05,
      "loss": 0.7905,
      "step": 136
    },
    {
      "epoch": 0.008620418436369357,
      "grad_norm": 0.6108826398849487,
      "learning_rate": 7.603902121325813e-05,
      "loss": 0.7494,
      "step": 137
    },
    {
      "epoch": 0.008683341198678623,
      "grad_norm": 0.7117067575454712,
      "learning_rate": 7.569434058643844e-05,
      "loss": 0.7418,
      "step": 138
    },
    {
      "epoch": 0.008746263960987887,
      "grad_norm": 0.6873885989189148,
      "learning_rate": 7.534799269067953e-05,
      "loss": 0.7915,
      "step": 139
    },
    {
      "epoch": 0.008809186723297153,
      "grad_norm": 0.7516224384307861,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7748,
      "step": 140
    },
    {
      "epoch": 0.008872109485606417,
      "grad_norm": 0.724405825138092,
      "learning_rate": 7.465038509514688e-05,
      "loss": 0.8016,
      "step": 141
    },
    {
      "epoch": 0.008935032247915684,
      "grad_norm": 0.7117589116096497,
      "learning_rate": 7.42991706621303e-05,
      "loss": 0.7227,
      "step": 142
    },
    {
      "epoch": 0.00899795501022495,
      "grad_norm": 0.7572246193885803,
      "learning_rate": 7.394637949075154e-05,
      "loss": 0.7636,
      "step": 143
    },
    {
      "epoch": 0.009060877772534214,
      "grad_norm": 0.7657356858253479,
      "learning_rate": 7.35920344731241e-05,
      "loss": 0.7762,
      "step": 144
    },
    {
      "epoch": 0.00912380053484348,
      "grad_norm": 0.8046727776527405,
      "learning_rate": 7.323615860218843e-05,
      "loss": 0.7803,
      "step": 145
    },
    {
      "epoch": 0.009186723297152744,
      "grad_norm": 0.7643633484840393,
      "learning_rate": 7.287877497021978e-05,
      "loss": 0.8089,
      "step": 146
    },
    {
      "epoch": 0.00924964605946201,
      "grad_norm": 0.9501251578330994,
      "learning_rate": 7.251990676732984e-05,
      "loss": 0.828,
      "step": 147
    },
    {
      "epoch": 0.009312568821771276,
      "grad_norm": 0.7604308724403381,
      "learning_rate": 7.215957727996207e-05,
      "loss": 0.7821,
      "step": 148
    },
    {
      "epoch": 0.00937549158408054,
      "grad_norm": 0.8432756662368774,
      "learning_rate": 7.179780988938051e-05,
      "loss": 0.9183,
      "step": 149
    },
    {
      "epoch": 0.009438414346389807,
      "grad_norm": 0.9484951496124268,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.8954,
      "step": 150
    },
    {
      "epoch": 0.009438414346389807,
      "eval_loss": 0.8508211374282837,
      "eval_runtime": 1993.8307,
      "eval_samples_per_second": 13.425,
      "eval_steps_per_second": 3.356,
      "step": 150
    },
    {
      "epoch": 0.009501337108699073,
      "grad_norm": 1.1908949613571167,
      "learning_rate": 7.107005538862646e-05,
      "loss": 0.8596,
      "step": 151
    },
    {
      "epoch": 0.009564259871008337,
      "grad_norm": 1.1169883012771606,
      "learning_rate": 7.07041155014006e-05,
      "loss": 0.9571,
      "step": 152
    },
    {
      "epoch": 0.009627182633317603,
      "grad_norm": 0.7980979681015015,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7766,
      "step": 153
    },
    {
      "epoch": 0.009690105395626867,
      "grad_norm": 0.7071455717086792,
      "learning_rate": 6.996822917828477e-05,
      "loss": 0.8339,
      "step": 154
    },
    {
      "epoch": 0.009753028157936133,
      "grad_norm": 0.7221279144287109,
      "learning_rate": 6.959833049300377e-05,
      "loss": 0.7941,
      "step": 155
    },
    {
      "epoch": 0.0098159509202454,
      "grad_norm": 0.6975688934326172,
      "learning_rate": 6.922716010014255e-05,
      "loss": 0.7402,
      "step": 156
    },
    {
      "epoch": 0.009878873682554664,
      "grad_norm": 0.6575108170509338,
      "learning_rate": 6.885474208441603e-05,
      "loss": 0.7297,
      "step": 157
    },
    {
      "epoch": 0.00994179644486393,
      "grad_norm": 0.7444519996643066,
      "learning_rate": 6.848110061149556e-05,
      "loss": 0.7287,
      "step": 158
    },
    {
      "epoch": 0.010004719207173196,
      "grad_norm": 0.7170855402946472,
      "learning_rate": 6.810625992644085e-05,
      "loss": 0.7978,
      "step": 159
    },
    {
      "epoch": 0.01006764196948246,
      "grad_norm": 0.6473238468170166,
      "learning_rate": 6.773024435212678e-05,
      "loss": 0.7296,
      "step": 160
    },
    {
      "epoch": 0.010130564731791726,
      "grad_norm": 0.6617797017097473,
      "learning_rate": 6.735307828766515e-05,
      "loss": 0.6883,
      "step": 161
    },
    {
      "epoch": 0.01019348749410099,
      "grad_norm": 0.7170284390449524,
      "learning_rate": 6.697478620682137e-05,
      "loss": 0.7134,
      "step": 162
    },
    {
      "epoch": 0.010256410256410256,
      "grad_norm": 0.653538167476654,
      "learning_rate": 6.659539265642643e-05,
      "loss": 0.7518,
      "step": 163
    },
    {
      "epoch": 0.010319333018719522,
      "grad_norm": 0.6872601509094238,
      "learning_rate": 6.621492225478414e-05,
      "loss": 0.7379,
      "step": 164
    },
    {
      "epoch": 0.010382255781028787,
      "grad_norm": 0.7626883387565613,
      "learning_rate": 6.583339969007363e-05,
      "loss": 0.7486,
      "step": 165
    },
    {
      "epoch": 0.010445178543338053,
      "grad_norm": 0.7144574522972107,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7396,
      "step": 166
    },
    {
      "epoch": 0.010508101305647317,
      "grad_norm": 0.7148804664611816,
      "learning_rate": 6.506729716392481e-05,
      "loss": 0.7176,
      "step": 167
    },
    {
      "epoch": 0.010571024067956583,
      "grad_norm": 0.7021417021751404,
      "learning_rate": 6.468276691378155e-05,
      "loss": 0.7104,
      "step": 168
    },
    {
      "epoch": 0.01063394683026585,
      "grad_norm": 0.7372605204582214,
      "learning_rate": 6.429728391993446e-05,
      "loss": 0.8647,
      "step": 169
    },
    {
      "epoch": 0.010696869592575113,
      "grad_norm": 0.7560912370681763,
      "learning_rate": 6.391087319582264e-05,
      "loss": 0.7326,
      "step": 170
    },
    {
      "epoch": 0.01075979235488438,
      "grad_norm": 0.6679472923278809,
      "learning_rate": 6.35235598150842e-05,
      "loss": 0.7417,
      "step": 171
    },
    {
      "epoch": 0.010822715117193646,
      "grad_norm": 0.6532546281814575,
      "learning_rate": 6.313536890992935e-05,
      "loss": 0.6867,
      "step": 172
    },
    {
      "epoch": 0.01088563787950291,
      "grad_norm": 0.6303436160087585,
      "learning_rate": 6.274632566950967e-05,
      "loss": 0.7392,
      "step": 173
    },
    {
      "epoch": 0.010948560641812176,
      "grad_norm": 0.6903069019317627,
      "learning_rate": 6.235645533828349e-05,
      "loss": 0.7651,
      "step": 174
    },
    {
      "epoch": 0.01101148340412144,
      "grad_norm": 0.6938333511352539,
      "learning_rate": 6.19657832143779e-05,
      "loss": 0.6829,
      "step": 175
    },
    {
      "epoch": 0.011074406166430706,
      "grad_norm": 0.6610081791877747,
      "learning_rate": 6.157433464794716e-05,
      "loss": 0.7268,
      "step": 176
    },
    {
      "epoch": 0.011137328928739972,
      "grad_norm": 0.6725570559501648,
      "learning_rate": 6.118213503952779e-05,
      "loss": 0.7439,
      "step": 177
    },
    {
      "epoch": 0.011200251691049237,
      "grad_norm": 0.6829043626785278,
      "learning_rate": 6.078920983839031e-05,
      "loss": 0.7467,
      "step": 178
    },
    {
      "epoch": 0.011263174453358503,
      "grad_norm": 0.6502189040184021,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.7015,
      "step": 179
    },
    {
      "epoch": 0.011326097215667769,
      "grad_norm": 0.661758303642273,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 0.7296,
      "step": 180
    },
    {
      "epoch": 0.011389019977977033,
      "grad_norm": 0.7520274519920349,
      "learning_rate": 5.960633586768543e-05,
      "loss": 0.7552,
      "step": 181
    },
    {
      "epoch": 0.011451942740286299,
      "grad_norm": 0.7441068291664124,
      "learning_rate": 5.921076370520058e-05,
      "loss": 0.7236,
      "step": 182
    },
    {
      "epoch": 0.011514865502595563,
      "grad_norm": 0.6942856311798096,
      "learning_rate": 5.8814593869458455e-05,
      "loss": 0.7201,
      "step": 183
    },
    {
      "epoch": 0.01157778826490483,
      "grad_norm": 0.6812763810157776,
      "learning_rate": 5.841785206735192e-05,
      "loss": 0.7475,
      "step": 184
    },
    {
      "epoch": 0.011640711027214095,
      "grad_norm": 0.6556635499000549,
      "learning_rate": 5.8020564042888015e-05,
      "loss": 0.8007,
      "step": 185
    },
    {
      "epoch": 0.01170363378952336,
      "grad_norm": 0.684214174747467,
      "learning_rate": 5.762275557551727e-05,
      "loss": 0.7799,
      "step": 186
    },
    {
      "epoch": 0.011766556551832626,
      "grad_norm": 0.7426326870918274,
      "learning_rate": 5.7224452478461064e-05,
      "loss": 0.8322,
      "step": 187
    },
    {
      "epoch": 0.01182947931414189,
      "grad_norm": 0.681393027305603,
      "learning_rate": 5.682568059703659e-05,
      "loss": 0.7452,
      "step": 188
    },
    {
      "epoch": 0.011892402076451156,
      "grad_norm": 0.6602080464363098,
      "learning_rate": 5.642646580697973e-05,
      "loss": 0.764,
      "step": 189
    },
    {
      "epoch": 0.011955324838760422,
      "grad_norm": 0.6899963021278381,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.7555,
      "step": 190
    },
    {
      "epoch": 0.012018247601069686,
      "grad_norm": 0.5832464098930359,
      "learning_rate": 5.562681114593028e-05,
      "loss": 0.7499,
      "step": 191
    },
    {
      "epoch": 0.012081170363378952,
      "grad_norm": 0.6253865957260132,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7261,
      "step": 192
    },
    {
      "epoch": 0.012144093125688218,
      "grad_norm": 0.7363515496253967,
      "learning_rate": 5.482569604572576e-05,
      "loss": 0.7222,
      "step": 193
    },
    {
      "epoch": 0.012207015887997483,
      "grad_norm": 0.7669686079025269,
      "learning_rate": 5.442465579556793e-05,
      "loss": 0.7768,
      "step": 194
    },
    {
      "epoch": 0.012269938650306749,
      "grad_norm": 0.6593098640441895,
      "learning_rate": 5.402332843583631e-05,
      "loss": 0.7953,
      "step": 195
    },
    {
      "epoch": 0.012332861412616013,
      "grad_norm": 0.6666168570518494,
      "learning_rate": 5.3621740008088126e-05,
      "loss": 0.7774,
      "step": 196
    },
    {
      "epoch": 0.012395784174925279,
      "grad_norm": 0.7173077464103699,
      "learning_rate": 5.321991657082097e-05,
      "loss": 0.7483,
      "step": 197
    },
    {
      "epoch": 0.012458706937234545,
      "grad_norm": 0.7566263675689697,
      "learning_rate": 5.281788419778187e-05,
      "loss": 0.7738,
      "step": 198
    },
    {
      "epoch": 0.01252162969954381,
      "grad_norm": 0.7862094044685364,
      "learning_rate": 5.2415668976275355e-05,
      "loss": 0.815,
      "step": 199
    },
    {
      "epoch": 0.012584552461853075,
      "grad_norm": 0.9621549844741821,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.8267,
      "step": 200
    },
    {
      "epoch": 0.012584552461853075,
      "eval_loss": 0.8121484518051147,
      "eval_runtime": 1992.7213,
      "eval_samples_per_second": 13.432,
      "eval_steps_per_second": 3.358,
      "step": 200
    },
    {
      "epoch": 0.012647475224162342,
      "grad_norm": 1.1414529085159302,
      "learning_rate": 5.161079439470866e-05,
      "loss": 0.8951,
      "step": 201
    },
    {
      "epoch": 0.012710397986471606,
      "grad_norm": 0.9856881499290466,
      "learning_rate": 5.1208187261806615e-05,
      "loss": 0.8464,
      "step": 202
    },
    {
      "epoch": 0.012773320748780872,
      "grad_norm": 0.7981590628623962,
      "learning_rate": 5.080550173136457e-05,
      "loss": 0.7748,
      "step": 203
    },
    {
      "epoch": 0.012836243511090136,
      "grad_norm": 0.7538502216339111,
      "learning_rate": 5.0402763933069496e-05,
      "loss": 0.7969,
      "step": 204
    },
    {
      "epoch": 0.012899166273399402,
      "grad_norm": 0.6282597184181213,
      "learning_rate": 5e-05,
      "loss": 0.7767,
      "step": 205
    },
    {
      "epoch": 0.012962089035708668,
      "grad_norm": 0.5800930261611938,
      "learning_rate": 4.9597236066930516e-05,
      "loss": 0.7049,
      "step": 206
    },
    {
      "epoch": 0.013025011798017933,
      "grad_norm": 0.5951983332633972,
      "learning_rate": 4.919449826863544e-05,
      "loss": 0.7179,
      "step": 207
    },
    {
      "epoch": 0.013087934560327199,
      "grad_norm": 0.6343929171562195,
      "learning_rate": 4.87918127381934e-05,
      "loss": 0.7377,
      "step": 208
    },
    {
      "epoch": 0.013150857322636465,
      "grad_norm": 0.6349851489067078,
      "learning_rate": 4.8389205605291365e-05,
      "loss": 0.6433,
      "step": 209
    },
    {
      "epoch": 0.013213780084945729,
      "grad_norm": 0.6455802321434021,
      "learning_rate": 4.798670299452926e-05,
      "loss": 0.7163,
      "step": 210
    },
    {
      "epoch": 0.013276702847254995,
      "grad_norm": 0.6890186071395874,
      "learning_rate": 4.758433102372466e-05,
      "loss": 0.7404,
      "step": 211
    },
    {
      "epoch": 0.01333962560956426,
      "grad_norm": 0.6462453007698059,
      "learning_rate": 4.7182115802218126e-05,
      "loss": 0.7984,
      "step": 212
    },
    {
      "epoch": 0.013402548371873525,
      "grad_norm": 0.6188192963600159,
      "learning_rate": 4.678008342917903e-05,
      "loss": 0.7616,
      "step": 213
    },
    {
      "epoch": 0.013465471134182791,
      "grad_norm": 0.7416461706161499,
      "learning_rate": 4.6378259991911886e-05,
      "loss": 0.7367,
      "step": 214
    },
    {
      "epoch": 0.013528393896492056,
      "grad_norm": 0.5736991167068481,
      "learning_rate": 4.597667156416371e-05,
      "loss": 0.6972,
      "step": 215
    },
    {
      "epoch": 0.013591316658801322,
      "grad_norm": 0.6165981292724609,
      "learning_rate": 4.5575344204432084e-05,
      "loss": 0.7462,
      "step": 216
    },
    {
      "epoch": 0.013654239421110586,
      "grad_norm": 0.6969764828681946,
      "learning_rate": 4.5174303954274244e-05,
      "loss": 0.7823,
      "step": 217
    },
    {
      "epoch": 0.013717162183419852,
      "grad_norm": 0.6673752069473267,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7428,
      "step": 218
    },
    {
      "epoch": 0.013780084945729118,
      "grad_norm": 0.6823404431343079,
      "learning_rate": 4.437318885406973e-05,
      "loss": 0.7402,
      "step": 219
    },
    {
      "epoch": 0.013843007708038382,
      "grad_norm": 0.6113579273223877,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.7455,
      "step": 220
    },
    {
      "epoch": 0.013905930470347648,
      "grad_norm": 0.6530716419219971,
      "learning_rate": 4.3573534193020274e-05,
      "loss": 0.7278,
      "step": 221
    },
    {
      "epoch": 0.013968853232656914,
      "grad_norm": 0.6049585342407227,
      "learning_rate": 4.317431940296343e-05,
      "loss": 0.698,
      "step": 222
    },
    {
      "epoch": 0.014031775994966179,
      "grad_norm": 0.5957211256027222,
      "learning_rate": 4.277554752153895e-05,
      "loss": 0.692,
      "step": 223
    },
    {
      "epoch": 0.014094698757275445,
      "grad_norm": 0.6721015572547913,
      "learning_rate": 4.237724442448273e-05,
      "loss": 0.7595,
      "step": 224
    },
    {
      "epoch": 0.014157621519584709,
      "grad_norm": 0.6083941459655762,
      "learning_rate": 4.197943595711198e-05,
      "loss": 0.7301,
      "step": 225
    },
    {
      "epoch": 0.014220544281893975,
      "grad_norm": 0.6055333614349365,
      "learning_rate": 4.1582147932648074e-05,
      "loss": 0.673,
      "step": 226
    },
    {
      "epoch": 0.014283467044203241,
      "grad_norm": 0.6080695390701294,
      "learning_rate": 4.118540613054156e-05,
      "loss": 0.7346,
      "step": 227
    },
    {
      "epoch": 0.014346389806512505,
      "grad_norm": 0.6798868179321289,
      "learning_rate": 4.078923629479943e-05,
      "loss": 0.7636,
      "step": 228
    },
    {
      "epoch": 0.014409312568821771,
      "grad_norm": 0.6028340458869934,
      "learning_rate": 4.039366413231458e-05,
      "loss": 0.7008,
      "step": 229
    },
    {
      "epoch": 0.014472235331131037,
      "grad_norm": 0.6678457856178284,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 0.7236,
      "step": 230
    },
    {
      "epoch": 0.014535158093440302,
      "grad_norm": 0.6005433201789856,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.6898,
      "step": 231
    },
    {
      "epoch": 0.014598080855749568,
      "grad_norm": 0.6036130785942078,
      "learning_rate": 3.92107901616097e-05,
      "loss": 0.7337,
      "step": 232
    },
    {
      "epoch": 0.014661003618058832,
      "grad_norm": 0.6133017539978027,
      "learning_rate": 3.8817864960472236e-05,
      "loss": 0.7035,
      "step": 233
    },
    {
      "epoch": 0.014723926380368098,
      "grad_norm": 0.6579994559288025,
      "learning_rate": 3.842566535205286e-05,
      "loss": 0.7428,
      "step": 234
    },
    {
      "epoch": 0.014786849142677364,
      "grad_norm": 0.6396896839141846,
      "learning_rate": 3.803421678562213e-05,
      "loss": 0.7253,
      "step": 235
    },
    {
      "epoch": 0.014849771904986628,
      "grad_norm": 0.5843393206596375,
      "learning_rate": 3.764354466171652e-05,
      "loss": 0.6655,
      "step": 236
    },
    {
      "epoch": 0.014912694667295895,
      "grad_norm": 0.732956051826477,
      "learning_rate": 3.725367433049033e-05,
      "loss": 0.7606,
      "step": 237
    },
    {
      "epoch": 0.014975617429605159,
      "grad_norm": 0.5860475897789001,
      "learning_rate": 3.6864631090070655e-05,
      "loss": 0.6058,
      "step": 238
    },
    {
      "epoch": 0.015038540191914425,
      "grad_norm": 0.6364427208900452,
      "learning_rate": 3.6476440184915815e-05,
      "loss": 0.7429,
      "step": 239
    },
    {
      "epoch": 0.015101462954223691,
      "grad_norm": 0.7146442532539368,
      "learning_rate": 3.608912680417737e-05,
      "loss": 0.7055,
      "step": 240
    },
    {
      "epoch": 0.015164385716532955,
      "grad_norm": 0.8253147602081299,
      "learning_rate": 3.570271608006555e-05,
      "loss": 0.7516,
      "step": 241
    },
    {
      "epoch": 0.015227308478842221,
      "grad_norm": 0.6781508326530457,
      "learning_rate": 3.531723308621847e-05,
      "loss": 0.6859,
      "step": 242
    },
    {
      "epoch": 0.015290231241151487,
      "grad_norm": 0.7546252012252808,
      "learning_rate": 3.493270283607522e-05,
      "loss": 0.7951,
      "step": 243
    },
    {
      "epoch": 0.015353154003460752,
      "grad_norm": 0.6175801753997803,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7232,
      "step": 244
    },
    {
      "epoch": 0.015416076765770018,
      "grad_norm": 0.7104986906051636,
      "learning_rate": 3.4166600309926387e-05,
      "loss": 0.7164,
      "step": 245
    },
    {
      "epoch": 0.015478999528079282,
      "grad_norm": 0.761751115322113,
      "learning_rate": 3.3785077745215873e-05,
      "loss": 0.7805,
      "step": 246
    },
    {
      "epoch": 0.015541922290388548,
      "grad_norm": 0.7329543232917786,
      "learning_rate": 3.340460734357359e-05,
      "loss": 0.7607,
      "step": 247
    },
    {
      "epoch": 0.015604845052697814,
      "grad_norm": 0.8153419494628906,
      "learning_rate": 3.3025213793178646e-05,
      "loss": 0.8694,
      "step": 248
    },
    {
      "epoch": 0.01566776781500708,
      "grad_norm": 0.8363320231437683,
      "learning_rate": 3.264692171233485e-05,
      "loss": 0.8512,
      "step": 249
    },
    {
      "epoch": 0.015730690577316343,
      "grad_norm": 0.8638584613800049,
      "learning_rate": 3.226975564787322e-05,
      "loss": 0.9056,
      "step": 250
    },
    {
      "epoch": 0.015730690577316343,
      "eval_loss": 0.7725260853767395,
      "eval_runtime": 1991.309,
      "eval_samples_per_second": 13.442,
      "eval_steps_per_second": 3.361,
      "step": 250
    },
    {
      "epoch": 0.01579361333962561,
      "grad_norm": 0.9017981290817261,
      "learning_rate": 3.189374007355917e-05,
      "loss": 0.7322,
      "step": 251
    },
    {
      "epoch": 0.015856536101934875,
      "grad_norm": 0.784041166305542,
      "learning_rate": 3.151889938850445e-05,
      "loss": 0.7285,
      "step": 252
    },
    {
      "epoch": 0.01591945886424414,
      "grad_norm": 0.8192543387413025,
      "learning_rate": 3.114525791558398e-05,
      "loss": 0.7494,
      "step": 253
    },
    {
      "epoch": 0.015982381626553407,
      "grad_norm": 0.7851762175559998,
      "learning_rate": 3.0772839899857464e-05,
      "loss": 0.8101,
      "step": 254
    },
    {
      "epoch": 0.01604530438886267,
      "grad_norm": 0.6676402688026428,
      "learning_rate": 3.0401669506996256e-05,
      "loss": 0.7238,
      "step": 255
    },
    {
      "epoch": 0.016108227151171935,
      "grad_norm": 0.6430277824401855,
      "learning_rate": 3.003177082171523e-05,
      "loss": 0.7751,
      "step": 256
    },
    {
      "epoch": 0.016171149913481203,
      "grad_norm": 0.6109689474105835,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.7016,
      "step": 257
    },
    {
      "epoch": 0.016234072675790467,
      "grad_norm": 0.6223710775375366,
      "learning_rate": 2.9295884498599414e-05,
      "loss": 0.7558,
      "step": 258
    },
    {
      "epoch": 0.01629699543809973,
      "grad_norm": 0.6088758707046509,
      "learning_rate": 2.8929944611373554e-05,
      "loss": 0.7324,
      "step": 259
    },
    {
      "epoch": 0.016359918200409,
      "grad_norm": 0.5436838865280151,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 0.6773,
      "step": 260
    },
    {
      "epoch": 0.016422840962718264,
      "grad_norm": 0.5857248306274414,
      "learning_rate": 2.8202190110619493e-05,
      "loss": 0.7294,
      "step": 261
    },
    {
      "epoch": 0.016485763725027528,
      "grad_norm": 0.5640518069267273,
      "learning_rate": 2.784042272003794e-05,
      "loss": 0.709,
      "step": 262
    },
    {
      "epoch": 0.016548686487336792,
      "grad_norm": 0.6003010869026184,
      "learning_rate": 2.7480093232670158e-05,
      "loss": 0.8003,
      "step": 263
    },
    {
      "epoch": 0.01661160924964606,
      "grad_norm": 0.6455116868019104,
      "learning_rate": 2.712122502978024e-05,
      "loss": 0.7943,
      "step": 264
    },
    {
      "epoch": 0.016674532011955324,
      "grad_norm": 0.5922764539718628,
      "learning_rate": 2.6763841397811573e-05,
      "loss": 0.723,
      "step": 265
    },
    {
      "epoch": 0.01673745477426459,
      "grad_norm": 0.5494192838668823,
      "learning_rate": 2.64079655268759e-05,
      "loss": 0.7551,
      "step": 266
    },
    {
      "epoch": 0.016800377536573857,
      "grad_norm": 0.6045573949813843,
      "learning_rate": 2.605362050924848e-05,
      "loss": 0.836,
      "step": 267
    },
    {
      "epoch": 0.01686330029888312,
      "grad_norm": 0.601265549659729,
      "learning_rate": 2.57008293378697e-05,
      "loss": 0.7308,
      "step": 268
    },
    {
      "epoch": 0.016926223061192385,
      "grad_norm": 0.6050641536712646,
      "learning_rate": 2.534961490485313e-05,
      "loss": 0.7363,
      "step": 269
    },
    {
      "epoch": 0.016989145823501653,
      "grad_norm": 0.5850335955619812,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6857,
      "step": 270
    },
    {
      "epoch": 0.017052068585810917,
      "grad_norm": 0.5859873294830322,
      "learning_rate": 2.4652007309320498e-05,
      "loss": 0.738,
      "step": 271
    },
    {
      "epoch": 0.01711499134812018,
      "grad_norm": 0.5759584307670593,
      "learning_rate": 2.430565941356157e-05,
      "loss": 0.7003,
      "step": 272
    },
    {
      "epoch": 0.01717791411042945,
      "grad_norm": 0.568520724773407,
      "learning_rate": 2.3960978786741877e-05,
      "loss": 0.6084,
      "step": 273
    },
    {
      "epoch": 0.017240836872738714,
      "grad_norm": 0.5545433759689331,
      "learning_rate": 2.361798779469336e-05,
      "loss": 0.6588,
      "step": 274
    },
    {
      "epoch": 0.017303759635047978,
      "grad_norm": 0.5918384194374084,
      "learning_rate": 2.3276708693609943e-05,
      "loss": 0.7023,
      "step": 275
    },
    {
      "epoch": 0.017366682397357246,
      "grad_norm": 0.5700395107269287,
      "learning_rate": 2.2937163628603435e-05,
      "loss": 0.738,
      "step": 276
    },
    {
      "epoch": 0.01742960515966651,
      "grad_norm": 0.5376745462417603,
      "learning_rate": 2.259937463226651e-05,
      "loss": 0.7345,
      "step": 277
    },
    {
      "epoch": 0.017492527921975774,
      "grad_norm": 0.5538782477378845,
      "learning_rate": 2.2263363623243054e-05,
      "loss": 0.7037,
      "step": 278
    },
    {
      "epoch": 0.01755545068428504,
      "grad_norm": 0.5734386444091797,
      "learning_rate": 2.192915240480596e-05,
      "loss": 0.6757,
      "step": 279
    },
    {
      "epoch": 0.017618373446594306,
      "grad_norm": 0.6654324531555176,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 0.7392,
      "step": 280
    },
    {
      "epoch": 0.01768129620890357,
      "grad_norm": 0.6778509020805359,
      "learning_rate": 2.1266215967445824e-05,
      "loss": 0.7742,
      "step": 281
    },
    {
      "epoch": 0.017744218971212835,
      "grad_norm": 0.5633755326271057,
      "learning_rate": 2.0937533765518187e-05,
      "loss": 0.6952,
      "step": 282
    },
    {
      "epoch": 0.017807141733522103,
      "grad_norm": 0.6291466951370239,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.691,
      "step": 283
    },
    {
      "epoch": 0.017870064495831367,
      "grad_norm": 0.6446377038955688,
      "learning_rate": 2.0285848032369137e-05,
      "loss": 0.7298,
      "step": 284
    },
    {
      "epoch": 0.01793298725814063,
      "grad_norm": 0.6178613901138306,
      "learning_rate": 1.996288678810105e-05,
      "loss": 0.6924,
      "step": 285
    },
    {
      "epoch": 0.0179959100204499,
      "grad_norm": 0.5817842483520508,
      "learning_rate": 1.9641874609064443e-05,
      "loss": 0.6699,
      "step": 286
    },
    {
      "epoch": 0.018058832782759163,
      "grad_norm": 0.6187658309936523,
      "learning_rate": 1.932283232527956e-05,
      "loss": 0.7599,
      "step": 287
    },
    {
      "epoch": 0.018121755545068428,
      "grad_norm": 0.594488799571991,
      "learning_rate": 1.9005780638942982e-05,
      "loss": 0.7158,
      "step": 288
    },
    {
      "epoch": 0.018184678307377695,
      "grad_norm": 0.6769745945930481,
      "learning_rate": 1.8690740123084316e-05,
      "loss": 0.7599,
      "step": 289
    },
    {
      "epoch": 0.01824760106968696,
      "grad_norm": 0.6411002278327942,
      "learning_rate": 1.837773122023114e-05,
      "loss": 0.7427,
      "step": 290
    },
    {
      "epoch": 0.018310523831996224,
      "grad_norm": 0.6521747708320618,
      "learning_rate": 1.8066774241082612e-05,
      "loss": 0.7293,
      "step": 291
    },
    {
      "epoch": 0.01837344659430549,
      "grad_norm": 0.6916580200195312,
      "learning_rate": 1.7757889363191483e-05,
      "loss": 0.7342,
      "step": 292
    },
    {
      "epoch": 0.018436369356614756,
      "grad_norm": 0.6757326722145081,
      "learning_rate": 1.745109662965481e-05,
      "loss": 0.7279,
      "step": 293
    },
    {
      "epoch": 0.01849929211892402,
      "grad_norm": 0.6940987706184387,
      "learning_rate": 1.714641594781347e-05,
      "loss": 0.7043,
      "step": 294
    },
    {
      "epoch": 0.018562214881233285,
      "grad_norm": 0.733060896396637,
      "learning_rate": 1.684386708796025e-05,
      "loss": 0.7816,
      "step": 295
    },
    {
      "epoch": 0.018625137643542553,
      "grad_norm": 0.6440508961677551,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7928,
      "step": 296
    },
    {
      "epoch": 0.018688060405851817,
      "grad_norm": 0.7244382500648499,
      "learning_rate": 1.62452432224612e-05,
      "loss": 0.7793,
      "step": 297
    },
    {
      "epoch": 0.01875098316816108,
      "grad_norm": 0.7814667224884033,
      "learning_rate": 1.5949207060660138e-05,
      "loss": 0.7547,
      "step": 298
    },
    {
      "epoch": 0.01881390593047035,
      "grad_norm": 0.8025712370872498,
      "learning_rate": 1.5655380406016235e-05,
      "loss": 0.8875,
      "step": 299
    },
    {
      "epoch": 0.018876828692779613,
      "grad_norm": 0.7935718894004822,
      "learning_rate": 1.536378232452003e-05,
      "loss": 0.8375,
      "step": 300
    },
    {
      "epoch": 0.018876828692779613,
      "eval_loss": 0.7229760885238647,
      "eval_runtime": 1993.5614,
      "eval_samples_per_second": 13.427,
      "eval_steps_per_second": 3.357,
      "step": 300
    },
    {
      "epoch": 0.018939751455088878,
      "grad_norm": 0.6894450783729553,
      "learning_rate": 1.5074431737553157e-05,
      "loss": 0.7444,
      "step": 301
    },
    {
      "epoch": 0.019002674217398145,
      "grad_norm": 0.6789616942405701,
      "learning_rate": 1.4787347420660541e-05,
      "loss": 0.7414,
      "step": 302
    },
    {
      "epoch": 0.01906559697970741,
      "grad_norm": 0.7387858033180237,
      "learning_rate": 1.4502548002332088e-05,
      "loss": 0.7901,
      "step": 303
    },
    {
      "epoch": 0.019128519742016674,
      "grad_norm": 0.6375578045845032,
      "learning_rate": 1.422005196279395e-05,
      "loss": 0.6224,
      "step": 304
    },
    {
      "epoch": 0.019191442504325938,
      "grad_norm": 0.7267337441444397,
      "learning_rate": 1.3939877632809278e-05,
      "loss": 0.7372,
      "step": 305
    },
    {
      "epoch": 0.019254365266635206,
      "grad_norm": 0.6559906601905823,
      "learning_rate": 1.3662043192488849e-05,
      "loss": 0.7395,
      "step": 306
    },
    {
      "epoch": 0.01931728802894447,
      "grad_norm": 0.6069934964179993,
      "learning_rate": 1.338656667011134e-05,
      "loss": 0.7066,
      "step": 307
    },
    {
      "epoch": 0.019380210791253735,
      "grad_norm": 0.6166743040084839,
      "learning_rate": 1.3113465940953495e-05,
      "loss": 0.7179,
      "step": 308
    },
    {
      "epoch": 0.019443133553563002,
      "grad_norm": 0.7378328442573547,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.7793,
      "step": 309
    },
    {
      "epoch": 0.019506056315872267,
      "grad_norm": 0.6443124413490295,
      "learning_rate": 1.257446259144494e-05,
      "loss": 0.7157,
      "step": 310
    },
    {
      "epoch": 0.01956897907818153,
      "grad_norm": 0.5678501129150391,
      "learning_rate": 1.2308594946249163e-05,
      "loss": 0.7045,
      "step": 311
    },
    {
      "epoch": 0.0196319018404908,
      "grad_norm": 0.6501772403717041,
      "learning_rate": 1.204517304231343e-05,
      "loss": 0.7822,
      "step": 312
    },
    {
      "epoch": 0.019694824602800063,
      "grad_norm": 0.5607977509498596,
      "learning_rate": 1.178421397270758e-05,
      "loss": 0.6364,
      "step": 313
    },
    {
      "epoch": 0.019757747365109327,
      "grad_norm": 0.6143155694007874,
      "learning_rate": 1.1525734670691701e-05,
      "loss": 0.7455,
      "step": 314
    },
    {
      "epoch": 0.019820670127418595,
      "grad_norm": 0.5648209452629089,
      "learning_rate": 1.1269751908617277e-05,
      "loss": 0.6528,
      "step": 315
    },
    {
      "epoch": 0.01988359288972786,
      "grad_norm": 0.5944265723228455,
      "learning_rate": 1.1016282296838887e-05,
      "loss": 0.7613,
      "step": 316
    },
    {
      "epoch": 0.019946515652037124,
      "grad_norm": 0.643968403339386,
      "learning_rate": 1.0765342282636416e-05,
      "loss": 0.7188,
      "step": 317
    },
    {
      "epoch": 0.02000943841434639,
      "grad_norm": 0.5592343211174011,
      "learning_rate": 1.0516948149147754e-05,
      "loss": 0.7049,
      "step": 318
    },
    {
      "epoch": 0.020072361176655656,
      "grad_norm": 0.5851125717163086,
      "learning_rate": 1.0271116014312293e-05,
      "loss": 0.684,
      "step": 319
    },
    {
      "epoch": 0.02013528393896492,
      "grad_norm": 0.6031101942062378,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 0.7494,
      "step": 320
    },
    {
      "epoch": 0.020198206701274184,
      "grad_norm": 0.5463895201683044,
      "learning_rate": 9.787201380101157e-06,
      "loss": 0.6859,
      "step": 321
    },
    {
      "epoch": 0.020261129463583452,
      "grad_norm": 0.5959100723266602,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7081,
      "step": 322
    },
    {
      "epoch": 0.020324052225892716,
      "grad_norm": 0.6021979451179504,
      "learning_rate": 9.313723980074018e-06,
      "loss": 0.7436,
      "step": 323
    },
    {
      "epoch": 0.02038697498820198,
      "grad_norm": 0.5806286931037903,
      "learning_rate": 9.080937753040646e-06,
      "loss": 0.6912,
      "step": 324
    },
    {
      "epoch": 0.02044989775051125,
      "grad_norm": 0.5796635150909424,
      "learning_rate": 8.850806705317183e-06,
      "loss": 0.6992,
      "step": 325
    },
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 0.5652114152908325,
      "learning_rate": 8.623345769777514e-06,
      "loss": 0.64,
      "step": 326
    },
    {
      "epoch": 0.020575743275129777,
      "grad_norm": 0.5946077704429626,
      "learning_rate": 8.398569706035792e-06,
      "loss": 0.6805,
      "step": 327
    },
    {
      "epoch": 0.020638666037439045,
      "grad_norm": 0.5399512052536011,
      "learning_rate": 8.176493099488663e-06,
      "loss": 0.6716,
      "step": 328
    },
    {
      "epoch": 0.02070158879974831,
      "grad_norm": 0.5655412673950195,
      "learning_rate": 7.957130360368898e-06,
      "loss": 0.6901,
      "step": 329
    },
    {
      "epoch": 0.020764511562057573,
      "grad_norm": 0.5360169410705566,
      "learning_rate": 7.740495722810271e-06,
      "loss": 0.6565,
      "step": 330
    },
    {
      "epoch": 0.02082743432436684,
      "grad_norm": 0.5519473552703857,
      "learning_rate": 7.526603243923957e-06,
      "loss": 0.6759,
      "step": 331
    },
    {
      "epoch": 0.020890357086676106,
      "grad_norm": 0.6575800180435181,
      "learning_rate": 7.315466802886401e-06,
      "loss": 0.7317,
      "step": 332
    },
    {
      "epoch": 0.02095327984898537,
      "grad_norm": 0.5860657691955566,
      "learning_rate": 7.107100100038671e-06,
      "loss": 0.7099,
      "step": 333
    },
    {
      "epoch": 0.021016202611294634,
      "grad_norm": 0.5698612332344055,
      "learning_rate": 6.901516655997536e-06,
      "loss": 0.6872,
      "step": 334
    },
    {
      "epoch": 0.021079125373603902,
      "grad_norm": 0.6097320914268494,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6447,
      "step": 335
    },
    {
      "epoch": 0.021142048135913166,
      "grad_norm": 0.645949125289917,
      "learning_rate": 6.498752722928042e-06,
      "loss": 0.742,
      "step": 336
    },
    {
      "epoch": 0.02120497089822243,
      "grad_norm": 0.6028321385383606,
      "learning_rate": 6.301598368674105e-06,
      "loss": 0.677,
      "step": 337
    },
    {
      "epoch": 0.0212678936605317,
      "grad_norm": 0.6465116143226624,
      "learning_rate": 6.107279541079769e-06,
      "loss": 0.7062,
      "step": 338
    },
    {
      "epoch": 0.021330816422840963,
      "grad_norm": 0.5715640187263489,
      "learning_rate": 5.915808849215304e-06,
      "loss": 0.6684,
      "step": 339
    },
    {
      "epoch": 0.021393739185150227,
      "grad_norm": 0.6341311931610107,
      "learning_rate": 5.727198717339511e-06,
      "loss": 0.7215,
      "step": 340
    },
    {
      "epoch": 0.021456661947459495,
      "grad_norm": 0.5924866795539856,
      "learning_rate": 5.54146138409355e-06,
      "loss": 0.6658,
      "step": 341
    },
    {
      "epoch": 0.02151958470976876,
      "grad_norm": 0.6136569380760193,
      "learning_rate": 5.358608901706802e-06,
      "loss": 0.7325,
      "step": 342
    },
    {
      "epoch": 0.021582507472078023,
      "grad_norm": 0.6864028573036194,
      "learning_rate": 5.178653135214812e-06,
      "loss": 0.7257,
      "step": 343
    },
    {
      "epoch": 0.02164543023438729,
      "grad_norm": 0.7612612247467041,
      "learning_rate": 5.001605761689398e-06,
      "loss": 0.7581,
      "step": 344
    },
    {
      "epoch": 0.021708352996696555,
      "grad_norm": 0.6227344870567322,
      "learning_rate": 4.827478269480895e-06,
      "loss": 0.627,
      "step": 345
    },
    {
      "epoch": 0.02177127575900582,
      "grad_norm": 0.7695668339729309,
      "learning_rate": 4.65628195747273e-06,
      "loss": 0.7749,
      "step": 346
    },
    {
      "epoch": 0.021834198521315087,
      "grad_norm": 0.7633891105651855,
      "learning_rate": 4.488027934348271e-06,
      "loss": 0.7784,
      "step": 347
    },
    {
      "epoch": 0.02189712128362435,
      "grad_norm": 0.7154384851455688,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.7125,
      "step": 348
    },
    {
      "epoch": 0.021960044045933616,
      "grad_norm": 0.831569492816925,
      "learning_rate": 4.16039023417088e-06,
      "loss": 0.7757,
      "step": 349
    },
    {
      "epoch": 0.02202296680824288,
      "grad_norm": 1.0594757795333862,
      "learning_rate": 4.001027817058789e-06,
      "loss": 0.8293,
      "step": 350
    },
    {
      "epoch": 0.02202296680824288,
      "eval_loss": 0.6978302001953125,
      "eval_runtime": 1993.2949,
      "eval_samples_per_second": 13.429,
      "eval_steps_per_second": 3.357,
      "step": 350
    },
    {
      "epoch": 0.022085889570552148,
      "grad_norm": 0.6362000703811646,
      "learning_rate": 3.844650207332562e-06,
      "loss": 0.6765,
      "step": 351
    },
    {
      "epoch": 0.022148812332861412,
      "grad_norm": 0.5263391733169556,
      "learning_rate": 3.691267552111183e-06,
      "loss": 0.6235,
      "step": 352
    },
    {
      "epoch": 0.022211735095170677,
      "grad_norm": 0.5333245992660522,
      "learning_rate": 3.54088980417534e-06,
      "loss": 0.6275,
      "step": 353
    },
    {
      "epoch": 0.022274657857479944,
      "grad_norm": 0.6024055480957031,
      "learning_rate": 3.393526721321616e-06,
      "loss": 0.6344,
      "step": 354
    },
    {
      "epoch": 0.02233758061978921,
      "grad_norm": 0.56202632188797,
      "learning_rate": 3.249187865729264e-06,
      "loss": 0.667,
      "step": 355
    },
    {
      "epoch": 0.022400503382098473,
      "grad_norm": 0.6126339435577393,
      "learning_rate": 3.1078826033397843e-06,
      "loss": 0.7108,
      "step": 356
    },
    {
      "epoch": 0.02246342614440774,
      "grad_norm": 0.5996975302696228,
      "learning_rate": 2.9696201032491434e-06,
      "loss": 0.6846,
      "step": 357
    },
    {
      "epoch": 0.022526348906717005,
      "grad_norm": 0.6046069264411926,
      "learning_rate": 2.8344093371128424e-06,
      "loss": 0.6398,
      "step": 358
    },
    {
      "epoch": 0.02258927166902627,
      "grad_norm": 0.5685755014419556,
      "learning_rate": 2.70225907856374e-06,
      "loss": 0.5936,
      "step": 359
    },
    {
      "epoch": 0.022652194431335537,
      "grad_norm": 0.5690946578979492,
      "learning_rate": 2.573177902642726e-06,
      "loss": 0.6451,
      "step": 360
    },
    {
      "epoch": 0.0227151171936448,
      "grad_norm": 0.6844279170036316,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7307,
      "step": 361
    },
    {
      "epoch": 0.022778039955954066,
      "grad_norm": 0.5816213488578796,
      "learning_rate": 2.324256102563188e-06,
      "loss": 0.6763,
      "step": 362
    },
    {
      "epoch": 0.02284096271826333,
      "grad_norm": 0.6306328177452087,
      "learning_rate": 2.204431630583548e-06,
      "loss": 0.7201,
      "step": 363
    },
    {
      "epoch": 0.022903885480572598,
      "grad_norm": 0.5840525031089783,
      "learning_rate": 2.087708544541689e-06,
      "loss": 0.6618,
      "step": 364
    },
    {
      "epoch": 0.022966808242881862,
      "grad_norm": 0.5952986478805542,
      "learning_rate": 1.974094418431388e-06,
      "loss": 0.7408,
      "step": 365
    },
    {
      "epoch": 0.023029731005191127,
      "grad_norm": 0.6626343131065369,
      "learning_rate": 1.8635966245104664e-06,
      "loss": 0.7118,
      "step": 366
    },
    {
      "epoch": 0.023092653767500394,
      "grad_norm": 0.561195433139801,
      "learning_rate": 1.7562223328224325e-06,
      "loss": 0.6572,
      "step": 367
    },
    {
      "epoch": 0.02315557652980966,
      "grad_norm": 0.605522632598877,
      "learning_rate": 1.6519785107311891e-06,
      "loss": 0.6959,
      "step": 368
    },
    {
      "epoch": 0.023218499292118923,
      "grad_norm": 0.6060965657234192,
      "learning_rate": 1.5508719224689717e-06,
      "loss": 0.7534,
      "step": 369
    },
    {
      "epoch": 0.02328142205442819,
      "grad_norm": 0.5786964893341064,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 0.6837,
      "step": 370
    },
    {
      "epoch": 0.023344344816737455,
      "grad_norm": 0.554511308670044,
      "learning_rate": 1.358096486081778e-06,
      "loss": 0.6633,
      "step": 371
    },
    {
      "epoch": 0.02340726757904672,
      "grad_norm": 0.561881422996521,
      "learning_rate": 1.2664401468786114e-06,
      "loss": 0.6633,
      "step": 372
    },
    {
      "epoch": 0.023470190341355987,
      "grad_norm": 0.6631070971488953,
      "learning_rate": 1.1779460585363944e-06,
      "loss": 0.7833,
      "step": 373
    },
    {
      "epoch": 0.02353311310366525,
      "grad_norm": 0.5902887582778931,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7127,
      "step": 374
    },
    {
      "epoch": 0.023596035865974516,
      "grad_norm": 0.5488584041595459,
      "learning_rate": 1.0104673978866164e-06,
      "loss": 0.65,
      "step": 375
    },
    {
      "epoch": 0.02365895862828378,
      "grad_norm": 0.549534022808075,
      "learning_rate": 9.314936930293283e-07,
      "loss": 0.649,
      "step": 376
    },
    {
      "epoch": 0.023721881390593048,
      "grad_norm": 0.6492491364479065,
      "learning_rate": 8.557039732283944e-07,
      "loss": 0.7449,
      "step": 377
    },
    {
      "epoch": 0.023784804152902312,
      "grad_norm": 0.603671669960022,
      "learning_rate": 7.83103156370113e-07,
      "loss": 0.6647,
      "step": 378
    },
    {
      "epoch": 0.023847726915211576,
      "grad_norm": 0.60027676820755,
      "learning_rate": 7.136959534174592e-07,
      "loss": 0.6557,
      "step": 379
    },
    {
      "epoch": 0.023910649677520844,
      "grad_norm": 0.5764393210411072,
      "learning_rate": 6.474868681043578e-07,
      "loss": 0.6449,
      "step": 380
    },
    {
      "epoch": 0.02397357243983011,
      "grad_norm": 0.6350451707839966,
      "learning_rate": 5.844801966434832e-07,
      "loss": 0.7452,
      "step": 381
    },
    {
      "epoch": 0.024036495202139373,
      "grad_norm": 0.5474420189857483,
      "learning_rate": 5.246800274474439e-07,
      "loss": 0.6484,
      "step": 382
    },
    {
      "epoch": 0.02409941796444864,
      "grad_norm": 0.6028091907501221,
      "learning_rate": 4.680902408635335e-07,
      "loss": 0.7082,
      "step": 383
    },
    {
      "epoch": 0.024162340726757905,
      "grad_norm": 0.6048222184181213,
      "learning_rate": 4.1471450892189846e-07,
      "loss": 0.7395,
      "step": 384
    },
    {
      "epoch": 0.02422526348906717,
      "grad_norm": 0.6276510953903198,
      "learning_rate": 3.6455629509730136e-07,
      "loss": 0.6713,
      "step": 385
    },
    {
      "epoch": 0.024288186251376437,
      "grad_norm": 0.5658819675445557,
      "learning_rate": 3.1761885408435054e-07,
      "loss": 0.6423,
      "step": 386
    },
    {
      "epoch": 0.0243511090136857,
      "grad_norm": 0.6045307517051697,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.6774,
      "step": 387
    },
    {
      "epoch": 0.024414031775994965,
      "grad_norm": 0.589821457862854,
      "learning_rate": 2.334182641175686e-07,
      "loss": 0.6838,
      "step": 388
    },
    {
      "epoch": 0.024476954538304233,
      "grad_norm": 0.5758050680160522,
      "learning_rate": 1.9616057881935436e-07,
      "loss": 0.704,
      "step": 389
    },
    {
      "epoch": 0.024539877300613498,
      "grad_norm": 0.619819700717926,
      "learning_rate": 1.6213459328950352e-07,
      "loss": 0.658,
      "step": 390
    },
    {
      "epoch": 0.024602800062922762,
      "grad_norm": 0.6557899713516235,
      "learning_rate": 1.3134251542544774e-07,
      "loss": 0.6725,
      "step": 391
    },
    {
      "epoch": 0.024665722825232026,
      "grad_norm": 0.6236681342124939,
      "learning_rate": 1.0378634328099269e-07,
      "loss": 0.6717,
      "step": 392
    },
    {
      "epoch": 0.024728645587541294,
      "grad_norm": 0.6441242098808289,
      "learning_rate": 7.946786493666647e-08,
      "loss": 0.7222,
      "step": 393
    },
    {
      "epoch": 0.024791568349850558,
      "grad_norm": 0.6634582281112671,
      "learning_rate": 5.838865838366792e-08,
      "loss": 0.7297,
      "step": 394
    },
    {
      "epoch": 0.024854491112159822,
      "grad_norm": 0.6949135661125183,
      "learning_rate": 4.055009142152067e-08,
      "loss": 0.6816,
      "step": 395
    },
    {
      "epoch": 0.02491741387446909,
      "grad_norm": 0.7237213850021362,
      "learning_rate": 2.595332156925534e-08,
      "loss": 0.6885,
      "step": 396
    },
    {
      "epoch": 0.024980336636778355,
      "grad_norm": 0.7857411503791809,
      "learning_rate": 1.4599295990352924e-08,
      "loss": 0.767,
      "step": 397
    },
    {
      "epoch": 0.02504325939908762,
      "grad_norm": 0.8778714537620544,
      "learning_rate": 6.488751431266149e-09,
      "loss": 0.7826,
      "step": 398
    },
    {
      "epoch": 0.025106182161396887,
      "grad_norm": 0.8500857353210449,
      "learning_rate": 1.622214173602199e-09,
      "loss": 0.7738,
      "step": 399
    },
    {
      "epoch": 0.02516910492370615,
      "grad_norm": 0.9884042143821716,
      "learning_rate": 0.0,
      "loss": 0.8359,
      "step": 400
    },
    {
      "epoch": 0.02516910492370615,
      "eval_loss": 0.6945011615753174,
      "eval_runtime": 1990.894,
      "eval_samples_per_second": 13.445,
      "eval_steps_per_second": 3.361,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 6.034054314983424e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}