{
  "best_metric": 0.565327525138855,
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
  "epoch": 0.04033303563711792,
  "eval_steps": 50,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011523724467747976,
      "grad_norm": 0.7461973428726196,
      "learning_rate": 1e-05,
      "loss": 0.6764,
      "step": 1
    },
    {
      "epoch": 0.00011523724467747976,
      "eval_loss": 0.9687025547027588,
      "eval_runtime": 545.4381,
      "eval_samples_per_second": 26.795,
      "eval_steps_per_second": 6.699,
      "step": 1
    },
    {
      "epoch": 0.0002304744893549595,
      "grad_norm": 0.9859816431999207,
      "learning_rate": 2e-05,
      "loss": 0.6287,
      "step": 2
    },
    {
      "epoch": 0.0003457117340324393,
      "grad_norm": 1.0724681615829468,
      "learning_rate": 3e-05,
      "loss": 0.7866,
      "step": 3
    },
    {
      "epoch": 0.000460948978709919,
      "grad_norm": 1.011637806892395,
      "learning_rate": 4e-05,
      "loss": 0.7134,
      "step": 4
    },
    {
      "epoch": 0.0005761862233873988,
      "grad_norm": 0.818691611289978,
      "learning_rate": 5e-05,
      "loss": 0.7764,
      "step": 5
    },
    {
      "epoch": 0.0006914234680648786,
      "grad_norm": 0.7848404049873352,
      "learning_rate": 6e-05,
      "loss": 0.8435,
      "step": 6
    },
    {
      "epoch": 0.0008066607127423584,
      "grad_norm": 0.9838979244232178,
      "learning_rate": 7e-05,
      "loss": 0.7446,
      "step": 7
    },
    {
      "epoch": 0.000921897957419838,
      "grad_norm": 1.3054728507995605,
      "learning_rate": 8e-05,
      "loss": 0.705,
      "step": 8
    },
    {
      "epoch": 0.0010371352020973178,
      "grad_norm": 1.2515887022018433,
      "learning_rate": 9e-05,
      "loss": 0.6567,
      "step": 9
    },
    {
      "epoch": 0.0011523724467747975,
      "grad_norm": 0.9352166652679443,
      "learning_rate": 0.0001,
      "loss": 0.6788,
      "step": 10
    },
    {
      "epoch": 0.0012676096914522774,
      "grad_norm": 0.8308036923408508,
      "learning_rate": 9.99983777858264e-05,
      "loss": 0.7393,
      "step": 11
    },
    {
      "epoch": 0.0013828469361297571,
      "grad_norm": 0.7662054896354675,
      "learning_rate": 9.999351124856874e-05,
      "loss": 0.7728,
      "step": 12
    },
    {
      "epoch": 0.0014980841808072368,
      "grad_norm": 0.9175456762313843,
      "learning_rate": 9.998540070400966e-05,
      "loss": 0.7545,
      "step": 13
    },
    {
      "epoch": 0.0016133214254847167,
      "grad_norm": 0.9114332795143127,
      "learning_rate": 9.997404667843075e-05,
      "loss": 0.8675,
      "step": 14
    },
    {
      "epoch": 0.0017285586701621964,
      "grad_norm": 0.8873140215873718,
      "learning_rate": 9.995944990857849e-05,
      "loss": 0.707,
      "step": 15
    },
    {
      "epoch": 0.001843795914839676,
      "grad_norm": 0.848321259021759,
      "learning_rate": 9.994161134161634e-05,
      "loss": 0.7408,
      "step": 16
    },
    {
      "epoch": 0.0019590331595171558,
      "grad_norm": 0.9329268932342529,
      "learning_rate": 9.992053213506334e-05,
      "loss": 0.7772,
      "step": 17
    },
    {
      "epoch": 0.0020742704041946357,
      "grad_norm": 0.9922827482223511,
      "learning_rate": 9.989621365671902e-05,
      "loss": 0.7095,
      "step": 18
    },
    {
      "epoch": 0.0021895076488721156,
      "grad_norm": 1.0125304460525513,
      "learning_rate": 9.986865748457457e-05,
      "loss": 0.8506,
      "step": 19
    },
    {
      "epoch": 0.002304744893549595,
      "grad_norm": 1.0258866548538208,
      "learning_rate": 9.983786540671051e-05,
      "loss": 0.8553,
      "step": 20
    },
    {
      "epoch": 0.002419982138227075,
      "grad_norm": 1.1118699312210083,
      "learning_rate": 9.980383942118066e-05,
      "loss": 0.7704,
      "step": 21
    },
    {
      "epoch": 0.002535219382904555,
      "grad_norm": 1.235855221748352,
      "learning_rate": 9.976658173588244e-05,
      "loss": 0.8872,
      "step": 22
    },
    {
      "epoch": 0.0026504566275820343,
      "grad_norm": 1.1165136098861694,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.8303,
      "step": 23
    },
    {
      "epoch": 0.0027656938722595142,
      "grad_norm": 1.1215505599975586,
      "learning_rate": 9.968238114591566e-05,
      "loss": 0.7298,
      "step": 24
    },
    {
      "epoch": 0.002880931116936994,
      "grad_norm": 1.0933395624160767,
      "learning_rate": 9.96354437049027e-05,
      "loss": 0.7708,
      "step": 25
    },
    {
      "epoch": 0.0029961683616144736,
      "grad_norm": 1.3705003261566162,
      "learning_rate": 9.95852854910781e-05,
      "loss": 0.7554,
      "step": 26
    },
    {
      "epoch": 0.0031114056062919535,
      "grad_norm": 1.1887904405593872,
      "learning_rate": 9.953190975913647e-05,
      "loss": 0.6981,
      "step": 27
    },
    {
      "epoch": 0.0032266428509694334,
      "grad_norm": 1.286866545677185,
      "learning_rate": 9.947531997255256e-05,
      "loss": 0.7432,
      "step": 28
    },
    {
      "epoch": 0.003341880095646913,
      "grad_norm": 1.2123883962631226,
      "learning_rate": 9.941551980335652e-05,
      "loss": 0.6754,
      "step": 29
    },
    {
      "epoch": 0.003457117340324393,
      "grad_norm": 1.3810746669769287,
      "learning_rate": 9.935251313189564e-05,
      "loss": 0.7364,
      "step": 30
    },
    {
      "epoch": 0.0035723545850018727,
      "grad_norm": 1.2287622690200806,
      "learning_rate": 9.928630404658255e-05,
      "loss": 0.7362,
      "step": 31
    },
    {
      "epoch": 0.003687591829679352,
      "grad_norm": 1.0121726989746094,
      "learning_rate": 9.921689684362989e-05,
      "loss": 0.7264,
      "step": 32
    },
    {
      "epoch": 0.003802829074356832,
      "grad_norm": 1.083332896232605,
      "learning_rate": 9.914429602677162e-05,
      "loss": 0.6878,
      "step": 33
    },
    {
      "epoch": 0.0039180663190343116,
      "grad_norm": 0.9687482118606567,
      "learning_rate": 9.906850630697068e-05,
      "loss": 0.6582,
      "step": 34
    },
    {
      "epoch": 0.004033303563711792,
      "grad_norm": 1.047886848449707,
      "learning_rate": 9.898953260211338e-05,
      "loss": 0.6259,
      "step": 35
    },
    {
      "epoch": 0.004148540808389271,
      "grad_norm": 0.8944975137710571,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.6844,
      "step": 36
    },
    {
      "epoch": 0.004263778053066751,
      "grad_norm": 0.9275309443473816,
      "learning_rate": 9.882205394146361e-05,
      "loss": 0.6108,
      "step": 37
    },
    {
      "epoch": 0.004379015297744231,
      "grad_norm": 0.9693747162818909,
      "learning_rate": 9.87335598531214e-05,
      "loss": 0.6563,
      "step": 38
    },
    {
      "epoch": 0.004494252542421711,
      "grad_norm": 1.1269587278366089,
      "learning_rate": 9.864190351391822e-05,
      "loss": 0.7205,
      "step": 39
    },
    {
      "epoch": 0.00460948978709919,
      "grad_norm": 1.247700572013855,
      "learning_rate": 9.85470908713026e-05,
      "loss": 0.6948,
      "step": 40
    },
    {
      "epoch": 0.0047247270317766705,
      "grad_norm": 1.555729627609253,
      "learning_rate": 9.844912807753104e-05,
      "loss": 0.6225,
      "step": 41
    },
    {
      "epoch": 0.00483996427645415,
      "grad_norm": 1.2079527378082275,
      "learning_rate": 9.834802148926882e-05,
      "loss": 0.6886,
      "step": 42
    },
    {
      "epoch": 0.004955201521131629,
      "grad_norm": 1.253836750984192,
      "learning_rate": 9.824377766717759e-05,
      "loss": 0.8655,
      "step": 43
    },
    {
      "epoch": 0.00507043876580911,
      "grad_norm": 1.0194092988967896,
      "learning_rate": 9.813640337548954e-05,
      "loss": 0.6824,
      "step": 44
    },
    {
      "epoch": 0.005185676010486589,
      "grad_norm": 1.059622883796692,
      "learning_rate": 9.802590558156862e-05,
      "loss": 0.7002,
      "step": 45
    },
    {
      "epoch": 0.005300913255164069,
      "grad_norm": 1.1622421741485596,
      "learning_rate": 9.791229145545831e-05,
      "loss": 0.6609,
      "step": 46
    },
    {
      "epoch": 0.005416150499841549,
      "grad_norm": 1.3024383783340454,
      "learning_rate": 9.779556836941645e-05,
      "loss": 0.6287,
      "step": 47
    },
    {
      "epoch": 0.0055313877445190285,
      "grad_norm": 1.2196540832519531,
      "learning_rate": 9.767574389743682e-05,
      "loss": 0.5385,
      "step": 48
    },
    {
      "epoch": 0.005646624989196508,
      "grad_norm": 1.4395736455917358,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6211,
      "step": 49
    },
    {
      "epoch": 0.005761862233873988,
      "grad_norm": 1.6215977668762207,
      "learning_rate": 9.742682209735727e-05,
      "loss": 0.6201,
      "step": 50
    },
    {
      "epoch": 0.005761862233873988,
      "eval_loss": 0.7081581354141235,
      "eval_runtime": 546.452,
      "eval_samples_per_second": 26.745,
      "eval_steps_per_second": 6.687,
      "step": 50
    },
    {
      "epoch": 0.005877099478551468,
      "grad_norm": 0.6722015142440796,
      "learning_rate": 9.729774092143627e-05,
      "loss": 0.5825,
      "step": 51
    },
    {
      "epoch": 0.005992336723228947,
      "grad_norm": 0.6303715705871582,
      "learning_rate": 9.716559066288715e-05,
      "loss": 0.6244,
      "step": 52
    },
    {
      "epoch": 0.006107573967906428,
      "grad_norm": 0.6753822565078735,
      "learning_rate": 9.703037989675087e-05,
      "loss": 0.7524,
      "step": 53
    },
    {
      "epoch": 0.006222811212583907,
      "grad_norm": 0.571438729763031,
      "learning_rate": 9.689211739666023e-05,
      "loss": 0.5751,
      "step": 54
    },
    {
      "epoch": 0.0063380484572613865,
      "grad_norm": 0.6231772303581238,
      "learning_rate": 9.675081213427076e-05,
      "loss": 0.74,
      "step": 55
    },
    {
      "epoch": 0.006453285701938867,
      "grad_norm": 0.5662903189659119,
      "learning_rate": 9.66064732786784e-05,
      "loss": 0.5992,
      "step": 56
    },
    {
      "epoch": 0.006568522946616346,
      "grad_norm": 0.7178725600242615,
      "learning_rate": 9.645911019582467e-05,
      "loss": 0.7747,
      "step": 57
    },
    {
      "epoch": 0.006683760191293826,
      "grad_norm": 0.6594935655593872,
      "learning_rate": 9.630873244788883e-05,
      "loss": 0.6761,
      "step": 58
    },
    {
      "epoch": 0.006798997435971306,
      "grad_norm": 0.6650819778442383,
      "learning_rate": 9.615534979266745e-05,
      "loss": 0.8188,
      "step": 59
    },
    {
      "epoch": 0.006914234680648786,
      "grad_norm": 0.6455956101417542,
      "learning_rate": 9.599897218294122e-05,
      "loss": 0.6711,
      "step": 60
    },
    {
      "epoch": 0.007029471925326265,
      "grad_norm": 0.6445301175117493,
      "learning_rate": 9.583960976582913e-05,
      "loss": 0.7227,
      "step": 61
    },
    {
      "epoch": 0.007144709170003745,
      "grad_norm": 1.0128474235534668,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.6944,
      "step": 62
    },
    {
      "epoch": 0.007259946414681225,
      "grad_norm": 0.7492349147796631,
      "learning_rate": 9.551197206565173e-05,
      "loss": 0.7062,
      "step": 63
    },
    {
      "epoch": 0.007375183659358704,
      "grad_norm": 0.7735145092010498,
      "learning_rate": 9.534371804252728e-05,
      "loss": 0.7259,
      "step": 64
    },
    {
      "epoch": 0.007490420904036185,
      "grad_norm": 0.8398394584655762,
      "learning_rate": 9.517252173051911e-05,
      "loss": 0.6226,
      "step": 65
    },
    {
      "epoch": 0.007605658148713664,
      "grad_norm": 0.8292278051376343,
      "learning_rate": 9.49983942383106e-05,
      "loss": 0.658,
      "step": 66
    },
    {
      "epoch": 0.007720895393391144,
      "grad_norm": 0.7968212962150574,
      "learning_rate": 9.482134686478519e-05,
      "loss": 0.6969,
      "step": 67
    },
    {
      "epoch": 0.007836132638068623,
      "grad_norm": 0.9180437326431274,
      "learning_rate": 9.464139109829321e-05,
      "loss": 0.7717,
      "step": 68
    },
    {
      "epoch": 0.007951369882746103,
      "grad_norm": 0.9269341826438904,
      "learning_rate": 9.445853861590647e-05,
      "loss": 0.7169,
      "step": 69
    },
    {
      "epoch": 0.008066607127423584,
      "grad_norm": 0.9348207712173462,
      "learning_rate": 9.42728012826605e-05,
      "loss": 0.6536,
      "step": 70
    },
    {
      "epoch": 0.008181844372101062,
      "grad_norm": 1.1747376918792725,
      "learning_rate": 9.408419115078471e-05,
      "loss": 0.7902,
      "step": 71
    },
    {
      "epoch": 0.008297081616778543,
      "grad_norm": 1.1941821575164795,
      "learning_rate": 9.389272045892024e-05,
      "loss": 0.8089,
      "step": 72
    },
    {
      "epoch": 0.008412318861456023,
      "grad_norm": 1.107926368713379,
      "learning_rate": 9.36984016313259e-05,
      "loss": 0.6773,
      "step": 73
    },
    {
      "epoch": 0.008527556106133502,
      "grad_norm": 1.135667324066162,
      "learning_rate": 9.350124727707197e-05,
      "loss": 0.7162,
      "step": 74
    },
    {
      "epoch": 0.008642793350810982,
      "grad_norm": 1.1049367189407349,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.81,
      "step": 75
    },
    {
      "epoch": 0.008758030595488462,
      "grad_norm": 1.4167182445526123,
      "learning_rate": 9.309848334400246e-05,
      "loss": 0.7369,
      "step": 76
    },
    {
      "epoch": 0.008873267840165941,
      "grad_norm": 1.6046768426895142,
      "learning_rate": 9.289289989996133e-05,
      "loss": 0.7633,
      "step": 77
    },
    {
      "epoch": 0.008988505084843421,
      "grad_norm": 1.4069336652755737,
      "learning_rate": 9.268453319711363e-05,
      "loss": 0.7567,
      "step": 78
    },
    {
      "epoch": 0.009103742329520902,
      "grad_norm": 1.0434424877166748,
      "learning_rate": 9.247339675607605e-05,
      "loss": 0.5982,
      "step": 79
    },
    {
      "epoch": 0.00921897957419838,
      "grad_norm": 1.1521142721176147,
      "learning_rate": 9.225950427718975e-05,
      "loss": 0.6323,
      "step": 80
    },
    {
      "epoch": 0.00933421681887586,
      "grad_norm": 0.8314908742904663,
      "learning_rate": 9.204286963963111e-05,
      "loss": 0.6323,
      "step": 81
    },
    {
      "epoch": 0.009449454063553341,
      "grad_norm": 0.8419124484062195,
      "learning_rate": 9.182350690051133e-05,
      "loss": 0.6278,
      "step": 82
    },
    {
      "epoch": 0.00956469130823082,
      "grad_norm": 0.9470197558403015,
      "learning_rate": 9.160143029396422e-05,
      "loss": 0.6473,
      "step": 83
    },
    {
      "epoch": 0.0096799285529083,
      "grad_norm": 0.8800526857376099,
      "learning_rate": 9.13766542302225e-05,
      "loss": 0.5913,
      "step": 84
    },
    {
      "epoch": 0.00979516579758578,
      "grad_norm": 0.9016923308372498,
      "learning_rate": 9.114919329468282e-05,
      "loss": 0.5914,
      "step": 85
    },
    {
      "epoch": 0.009910403042263259,
      "grad_norm": 0.9425757527351379,
      "learning_rate": 9.091906224695935e-05,
      "loss": 0.6713,
      "step": 86
    },
    {
      "epoch": 0.010025640286940739,
      "grad_norm": 1.0047729015350342,
      "learning_rate": 9.068627601992598e-05,
      "loss": 0.6046,
      "step": 87
    },
    {
      "epoch": 0.01014087753161822,
      "grad_norm": 1.045275092124939,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6654,
      "step": 88
    },
    {
      "epoch": 0.010256114776295698,
      "grad_norm": 1.0444538593292236,
      "learning_rate": 9.021279861989885e-05,
      "loss": 0.6605,
      "step": 89
    },
    {
      "epoch": 0.010371352020973178,
      "grad_norm": 1.0272176265716553,
      "learning_rate": 8.997213817017507e-05,
      "loss": 0.7068,
      "step": 90
    },
    {
      "epoch": 0.010486589265650659,
      "grad_norm": 1.094701886177063,
      "learning_rate": 8.972888398568772e-05,
      "loss": 0.6086,
      "step": 91
    },
    {
      "epoch": 0.010601826510328137,
      "grad_norm": 1.1884337663650513,
      "learning_rate": 8.948305185085225e-05,
      "loss": 0.6948,
      "step": 92
    },
    {
      "epoch": 0.010717063755005618,
      "grad_norm": 1.0921660661697388,
      "learning_rate": 8.92346577173636e-05,
      "loss": 0.664,
      "step": 93
    },
    {
      "epoch": 0.010832300999683098,
      "grad_norm": 1.253016710281372,
      "learning_rate": 8.898371770316111e-05,
      "loss": 0.6962,
      "step": 94
    },
    {
      "epoch": 0.010947538244360577,
      "grad_norm": 1.1953667402267456,
      "learning_rate": 8.873024809138272e-05,
      "loss": 0.6155,
      "step": 95
    },
    {
      "epoch": 0.011062775489038057,
      "grad_norm": 1.0429881811141968,
      "learning_rate": 8.847426532930831e-05,
      "loss": 0.5882,
      "step": 96
    },
    {
      "epoch": 0.011178012733715537,
      "grad_norm": 1.3511476516723633,
      "learning_rate": 8.821578602729242e-05,
      "loss": 0.6557,
      "step": 97
    },
    {
      "epoch": 0.011293249978393016,
      "grad_norm": 1.132889986038208,
      "learning_rate": 8.795482695768658e-05,
      "loss": 0.6294,
      "step": 98
    },
    {
      "epoch": 0.011408487223070496,
      "grad_norm": 1.3862687349319458,
      "learning_rate": 8.769140505375085e-05,
      "loss": 0.6493,
      "step": 99
    },
    {
      "epoch": 0.011523724467747977,
      "grad_norm": 1.5808641910552979,
      "learning_rate": 8.742553740855506e-05,
      "loss": 0.5728,
      "step": 100
    },
    {
      "epoch": 0.011523724467747977,
      "eval_loss": 0.6656689643859863,
      "eval_runtime": 547.0519,
      "eval_samples_per_second": 26.716,
      "eval_steps_per_second": 6.679,
      "step": 100
    },
    {
      "epoch": 0.011638961712425455,
      "grad_norm": 0.6208635568618774,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.5428,
      "step": 101
    },
    {
      "epoch": 0.011754198957102936,
      "grad_norm": 0.6623407602310181,
      "learning_rate": 8.688653405904652e-05,
      "loss": 0.6547,
      "step": 102
    },
    {
      "epoch": 0.011869436201780416,
      "grad_norm": 0.6228560209274292,
      "learning_rate": 8.661343332988869e-05,
      "loss": 0.586,
      "step": 103
    },
    {
      "epoch": 0.011984673446457894,
      "grad_norm": 0.5910748243331909,
      "learning_rate": 8.633795680751116e-05,
      "loss": 0.6342,
      "step": 104
    },
    {
      "epoch": 0.012099910691135375,
      "grad_norm": 0.6204082369804382,
      "learning_rate": 8.606012236719073e-05,
      "loss": 0.7092,
      "step": 105
    },
    {
      "epoch": 0.012215147935812855,
      "grad_norm": 0.6246654391288757,
      "learning_rate": 8.577994803720606e-05,
      "loss": 0.8196,
      "step": 106
    },
    {
      "epoch": 0.012330385180490334,
      "grad_norm": 0.5755138993263245,
      "learning_rate": 8.549745199766792e-05,
      "loss": 0.6955,
      "step": 107
    },
    {
      "epoch": 0.012445622425167814,
      "grad_norm": 0.5705171227455139,
      "learning_rate": 8.521265257933948e-05,
      "loss": 0.6706,
      "step": 108
    },
    {
      "epoch": 0.012560859669845294,
      "grad_norm": 0.6388005018234253,
      "learning_rate": 8.492556826244687e-05,
      "loss": 0.6809,
      "step": 109
    },
    {
      "epoch": 0.012676096914522773,
      "grad_norm": 0.6977410316467285,
      "learning_rate": 8.463621767547998e-05,
      "loss": 0.7271,
      "step": 110
    },
    {
      "epoch": 0.012791334159200253,
      "grad_norm": 0.6099151968955994,
      "learning_rate": 8.434461959398376e-05,
      "loss": 0.7123,
      "step": 111
    },
    {
      "epoch": 0.012906571403877734,
      "grad_norm": 0.7898553609848022,
      "learning_rate": 8.405079293933986e-05,
      "loss": 0.7064,
      "step": 112
    },
    {
      "epoch": 0.013021808648555212,
      "grad_norm": 0.7140493392944336,
      "learning_rate": 8.375475677753881e-05,
      "loss": 0.6898,
      "step": 113
    },
    {
      "epoch": 0.013137045893232693,
      "grad_norm": 1.0986034870147705,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.754,
      "step": 114
    },
    {
      "epoch": 0.013252283137910173,
      "grad_norm": 0.829111635684967,
      "learning_rate": 8.315613291203976e-05,
      "loss": 0.7179,
      "step": 115
    },
    {
      "epoch": 0.013367520382587652,
      "grad_norm": 0.778800904750824,
      "learning_rate": 8.285358405218655e-05,
      "loss": 0.5743,
      "step": 116
    },
    {
      "epoch": 0.013482757627265132,
      "grad_norm": 0.8650482296943665,
      "learning_rate": 8.25489033703452e-05,
      "loss": 0.7462,
      "step": 117
    },
    {
      "epoch": 0.013597994871942612,
      "grad_norm": 0.8594391345977783,
      "learning_rate": 8.224211063680853e-05,
      "loss": 0.7918,
      "step": 118
    },
    {
      "epoch": 0.01371323211662009,
      "grad_norm": 0.8802257180213928,
      "learning_rate": 8.19332257589174e-05,
      "loss": 0.7046,
      "step": 119
    },
    {
      "epoch": 0.013828469361297571,
      "grad_norm": 0.9820117354393005,
      "learning_rate": 8.162226877976887e-05,
      "loss": 0.8009,
      "step": 120
    },
    {
      "epoch": 0.013943706605975052,
      "grad_norm": 0.9804040193557739,
      "learning_rate": 8.130925987691569e-05,
      "loss": 0.7213,
      "step": 121
    },
    {
      "epoch": 0.01405894385065253,
      "grad_norm": 0.9773142337799072,
      "learning_rate": 8.099421936105702e-05,
      "loss": 0.6519,
      "step": 122
    },
    {
      "epoch": 0.01417418109533001,
      "grad_norm": 1.0842269659042358,
      "learning_rate": 8.067716767472045e-05,
      "loss": 0.653,
      "step": 123
    },
    {
      "epoch": 0.01428941834000749,
      "grad_norm": 1.1096503734588623,
      "learning_rate": 8.035812539093557e-05,
      "loss": 0.7775,
      "step": 124
    },
    {
      "epoch": 0.01440465558468497,
      "grad_norm": 1.3610727787017822,
      "learning_rate": 8.003711321189895e-05,
      "loss": 0.6345,
      "step": 125
    },
    {
      "epoch": 0.01451989282936245,
      "grad_norm": 1.216774582862854,
      "learning_rate": 7.971415196763088e-05,
      "loss": 0.694,
      "step": 126
    },
    {
      "epoch": 0.01463513007403993,
      "grad_norm": 1.4049333333969116,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6201,
      "step": 127
    },
    {
      "epoch": 0.014750367318717409,
      "grad_norm": 1.0875705480575562,
      "learning_rate": 7.906246623448183e-05,
      "loss": 0.6244,
      "step": 128
    },
    {
      "epoch": 0.014865604563394889,
      "grad_norm": 1.0095276832580566,
      "learning_rate": 7.873378403255419e-05,
      "loss": 0.5977,
      "step": 129
    },
    {
      "epoch": 0.01498084180807237,
      "grad_norm": 0.9484551548957825,
      "learning_rate": 7.840323733655778e-05,
      "loss": 0.6159,
      "step": 130
    },
    {
      "epoch": 0.015096079052749848,
      "grad_norm": 0.8636478781700134,
      "learning_rate": 7.807084759519405e-05,
      "loss": 0.5963,
      "step": 131
    },
    {
      "epoch": 0.015211316297427328,
      "grad_norm": 1.010664939880371,
      "learning_rate": 7.773663637675694e-05,
      "loss": 0.6228,
      "step": 132
    },
    {
      "epoch": 0.015326553542104809,
      "grad_norm": 0.8741911053657532,
      "learning_rate": 7.740062536773352e-05,
      "loss": 0.4789,
      "step": 133
    },
    {
      "epoch": 0.015441790786782287,
      "grad_norm": 0.9093407988548279,
      "learning_rate": 7.706283637139658e-05,
      "loss": 0.6464,
      "step": 134
    },
    {
      "epoch": 0.015557028031459768,
      "grad_norm": 0.8352158665657043,
      "learning_rate": 7.672329130639005e-05,
      "loss": 0.6021,
      "step": 135
    },
    {
      "epoch": 0.015672265276137246,
      "grad_norm": 0.9724483489990234,
      "learning_rate": 7.638201220530665e-05,
      "loss": 0.6069,
      "step": 136
    },
    {
      "epoch": 0.015787502520814727,
      "grad_norm": 0.9229646921157837,
      "learning_rate": 7.603902121325813e-05,
      "loss": 0.6661,
      "step": 137
    },
    {
      "epoch": 0.015902739765492207,
      "grad_norm": 0.894641637802124,
      "learning_rate": 7.569434058643844e-05,
      "loss": 0.4953,
      "step": 138
    },
    {
      "epoch": 0.016017977010169687,
      "grad_norm": 0.9383701682090759,
      "learning_rate": 7.534799269067953e-05,
      "loss": 0.6165,
      "step": 139
    },
    {
      "epoch": 0.016133214254847168,
      "grad_norm": 1.0712255239486694,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5982,
      "step": 140
    },
    {
      "epoch": 0.016248451499524648,
      "grad_norm": 1.1666333675384521,
      "learning_rate": 7.465038509514688e-05,
      "loss": 0.6132,
      "step": 141
    },
    {
      "epoch": 0.016363688744202125,
      "grad_norm": 1.1935205459594727,
      "learning_rate": 7.42991706621303e-05,
      "loss": 0.6188,
      "step": 142
    },
    {
      "epoch": 0.016478925988879605,
      "grad_norm": 1.1012414693832397,
      "learning_rate": 7.394637949075154e-05,
      "loss": 0.6483,
      "step": 143
    },
    {
      "epoch": 0.016594163233557085,
      "grad_norm": 1.2057948112487793,
      "learning_rate": 7.35920344731241e-05,
      "loss": 0.5955,
      "step": 144
    },
    {
      "epoch": 0.016709400478234566,
      "grad_norm": 1.210904836654663,
      "learning_rate": 7.323615860218843e-05,
      "loss": 0.6094,
      "step": 145
    },
    {
      "epoch": 0.016824637722912046,
      "grad_norm": 1.1792796850204468,
      "learning_rate": 7.287877497021978e-05,
      "loss": 0.5172,
      "step": 146
    },
    {
      "epoch": 0.016939874967589526,
      "grad_norm": 1.3119630813598633,
      "learning_rate": 7.251990676732984e-05,
      "loss": 0.5774,
      "step": 147
    },
    {
      "epoch": 0.017055112212267003,
      "grad_norm": 1.3735464811325073,
      "learning_rate": 7.215957727996207e-05,
      "loss": 0.5789,
      "step": 148
    },
    {
      "epoch": 0.017170349456944484,
      "grad_norm": 1.3045659065246582,
      "learning_rate": 7.179780988938051e-05,
      "loss": 0.6074,
      "step": 149
    },
    {
      "epoch": 0.017285586701621964,
      "grad_norm": 1.5275754928588867,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.4802,
      "step": 150
    },
    {
      "epoch": 0.017285586701621964,
      "eval_loss": 0.6325949430465698,
      "eval_runtime": 546.5133,
      "eval_samples_per_second": 26.742,
      "eval_steps_per_second": 6.686,
      "step": 150
    },
    {
      "epoch": 0.017400823946299444,
      "grad_norm": 0.6129029393196106,
      "learning_rate": 7.107005538862646e-05,
      "loss": 0.5457,
      "step": 151
    },
    {
      "epoch": 0.017516061190976925,
      "grad_norm": 0.6865366101264954,
      "learning_rate": 7.07041155014006e-05,
      "loss": 0.6037,
      "step": 152
    },
    {
      "epoch": 0.017631298435654405,
      "grad_norm": 0.6349140405654907,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.6006,
      "step": 153
    },
    {
      "epoch": 0.017746535680331882,
      "grad_norm": 0.6397451162338257,
      "learning_rate": 6.996822917828477e-05,
      "loss": 0.6904,
      "step": 154
    },
    {
      "epoch": 0.017861772925009362,
      "grad_norm": 0.5073702335357666,
      "learning_rate": 6.959833049300377e-05,
      "loss": 0.5711,
      "step": 155
    },
    {
      "epoch": 0.017977010169686843,
      "grad_norm": 0.5888249278068542,
      "learning_rate": 6.922716010014255e-05,
      "loss": 0.7033,
      "step": 156
    },
    {
      "epoch": 0.018092247414364323,
      "grad_norm": 0.5774878263473511,
      "learning_rate": 6.885474208441603e-05,
      "loss": 0.6928,
      "step": 157
    },
    {
      "epoch": 0.018207484659041803,
      "grad_norm": 0.6262368559837341,
      "learning_rate": 6.848110061149556e-05,
      "loss": 0.7691,
      "step": 158
    },
    {
      "epoch": 0.018322721903719284,
      "grad_norm": 0.6418235301971436,
      "learning_rate": 6.810625992644085e-05,
      "loss": 0.6263,
      "step": 159
    },
    {
      "epoch": 0.01843795914839676,
      "grad_norm": 0.6563417911529541,
      "learning_rate": 6.773024435212678e-05,
      "loss": 0.692,
      "step": 160
    },
    {
      "epoch": 0.01855319639307424,
      "grad_norm": 0.654928982257843,
      "learning_rate": 6.735307828766515e-05,
      "loss": 0.6949,
      "step": 161
    },
    {
      "epoch": 0.01866843363775172,
      "grad_norm": 0.7155853509902954,
      "learning_rate": 6.697478620682137e-05,
      "loss": 0.6591,
      "step": 162
    },
    {
      "epoch": 0.0187836708824292,
      "grad_norm": 0.7285525798797607,
      "learning_rate": 6.659539265642643e-05,
      "loss": 0.7245,
      "step": 163
    },
    {
      "epoch": 0.018898908127106682,
      "grad_norm": 0.7615992426872253,
      "learning_rate": 6.621492225478414e-05,
      "loss": 0.5962,
      "step": 164
    },
    {
      "epoch": 0.019014145371784162,
      "grad_norm": 0.7541478872299194,
      "learning_rate": 6.583339969007363e-05,
      "loss": 0.6226,
      "step": 165
    },
    {
      "epoch": 0.01912938261646164,
      "grad_norm": 1.3453112840652466,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7385,
      "step": 166
    },
    {
      "epoch": 0.01924461986113912,
      "grad_norm": 0.8395344614982605,
      "learning_rate": 6.506729716392481e-05,
      "loss": 0.7463,
      "step": 167
    },
    {
      "epoch": 0.0193598571058166,
      "grad_norm": 0.8182184100151062,
      "learning_rate": 6.468276691378155e-05,
      "loss": 0.643,
      "step": 168
    },
    {
      "epoch": 0.01947509435049408,
      "grad_norm": 1.2326037883758545,
      "learning_rate": 6.429728391993446e-05,
      "loss": 0.6738,
      "step": 169
    },
    {
      "epoch": 0.01959033159517156,
      "grad_norm": 0.9027764797210693,
      "learning_rate": 6.391087319582264e-05,
      "loss": 0.721,
      "step": 170
    },
    {
      "epoch": 0.01970556883984904,
      "grad_norm": 0.955884575843811,
      "learning_rate": 6.35235598150842e-05,
      "loss": 0.65,
      "step": 171
    },
    {
      "epoch": 0.019820806084526518,
      "grad_norm": 0.9886214137077332,
      "learning_rate": 6.313536890992935e-05,
      "loss": 0.7256,
      "step": 172
    },
    {
      "epoch": 0.019936043329203998,
      "grad_norm": 0.9550946354866028,
      "learning_rate": 6.274632566950967e-05,
      "loss": 0.7296,
      "step": 173
    },
    {
      "epoch": 0.020051280573881478,
      "grad_norm": 1.1125203371047974,
      "learning_rate": 6.235645533828349e-05,
      "loss": 0.6658,
      "step": 174
    },
    {
      "epoch": 0.02016651781855896,
      "grad_norm": 1.145430326461792,
      "learning_rate": 6.19657832143779e-05,
      "loss": 0.6213,
      "step": 175
    },
    {
      "epoch": 0.02028175506323644,
      "grad_norm": 1.138908863067627,
      "learning_rate": 6.157433464794716e-05,
      "loss": 0.6373,
      "step": 176
    },
    {
      "epoch": 0.02039699230791392,
      "grad_norm": 1.2511849403381348,
      "learning_rate": 6.118213503952779e-05,
      "loss": 0.6691,
      "step": 177
    },
    {
      "epoch": 0.020512229552591396,
      "grad_norm": 1.3821207284927368,
      "learning_rate": 6.078920983839031e-05,
      "loss": 0.7503,
      "step": 178
    },
    {
      "epoch": 0.020627466797268876,
      "grad_norm": 1.0743690729141235,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.6563,
      "step": 179
    },
    {
      "epoch": 0.020742704041946357,
      "grad_norm": 0.9574199318885803,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 0.613,
      "step": 180
    },
    {
      "epoch": 0.020857941286623837,
      "grad_norm": 0.9797923564910889,
      "learning_rate": 5.960633586768543e-05,
      "loss": 0.4921,
      "step": 181
    },
    {
      "epoch": 0.020973178531301317,
      "grad_norm": 1.0329078435897827,
      "learning_rate": 5.921076370520058e-05,
      "loss": 0.5424,
      "step": 182
    },
    {
      "epoch": 0.021088415775978798,
      "grad_norm": 1.081237554550171,
      "learning_rate": 5.8814593869458455e-05,
      "loss": 0.593,
      "step": 183
    },
    {
      "epoch": 0.021203653020656275,
      "grad_norm": 0.9744309782981873,
      "learning_rate": 5.841785206735192e-05,
      "loss": 0.6247,
      "step": 184
    },
    {
      "epoch": 0.021318890265333755,
      "grad_norm": 0.9277073740959167,
      "learning_rate": 5.8020564042888015e-05,
      "loss": 0.5272,
      "step": 185
    },
    {
      "epoch": 0.021434127510011235,
      "grad_norm": 0.9203082323074341,
      "learning_rate": 5.762275557551727e-05,
      "loss": 0.5604,
      "step": 186
    },
    {
      "epoch": 0.021549364754688716,
      "grad_norm": 1.002752661705017,
      "learning_rate": 5.7224452478461064e-05,
      "loss": 0.6614,
      "step": 187
    },
    {
      "epoch": 0.021664601999366196,
      "grad_norm": 1.1859053373336792,
      "learning_rate": 5.682568059703659e-05,
      "loss": 0.6258,
      "step": 188
    },
    {
      "epoch": 0.021779839244043676,
      "grad_norm": 0.9486787915229797,
      "learning_rate": 5.642646580697973e-05,
      "loss": 0.5797,
      "step": 189
    },
    {
      "epoch": 0.021895076488721153,
      "grad_norm": 1.088105320930481,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.5081,
      "step": 190
    },
    {
      "epoch": 0.022010313733398634,
      "grad_norm": 1.0794477462768555,
      "learning_rate": 5.562681114593028e-05,
      "loss": 0.6171,
      "step": 191
    },
    {
      "epoch": 0.022125550978076114,
      "grad_norm": 1.1164370775222778,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.604,
      "step": 192
    },
    {
      "epoch": 0.022240788222753594,
      "grad_norm": 1.020864725112915,
      "learning_rate": 5.482569604572576e-05,
      "loss": 0.5079,
      "step": 193
    },
    {
      "epoch": 0.022356025467431075,
      "grad_norm": 0.9936183094978333,
      "learning_rate": 5.442465579556793e-05,
      "loss": 0.5903,
      "step": 194
    },
    {
      "epoch": 0.022471262712108555,
      "grad_norm": 1.3103758096694946,
      "learning_rate": 5.402332843583631e-05,
      "loss": 0.6436,
      "step": 195
    },
    {
      "epoch": 0.022586499956786032,
      "grad_norm": 1.2461060285568237,
      "learning_rate": 5.3621740008088126e-05,
      "loss": 0.5836,
      "step": 196
    },
    {
      "epoch": 0.022701737201463512,
      "grad_norm": 1.5536116361618042,
      "learning_rate": 5.321991657082097e-05,
      "loss": 0.5672,
      "step": 197
    },
    {
      "epoch": 0.022816974446140992,
      "grad_norm": 1.3643299341201782,
      "learning_rate": 5.281788419778187e-05,
      "loss": 0.4866,
      "step": 198
    },
    {
      "epoch": 0.022932211690818473,
      "grad_norm": 1.5207157135009766,
      "learning_rate": 5.2415668976275355e-05,
      "loss": 0.4737,
      "step": 199
    },
    {
      "epoch": 0.023047448935495953,
      "grad_norm": 1.5689412355422974,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.4415,
      "step": 200
    },
    {
      "epoch": 0.023047448935495953,
      "eval_loss": 0.608009397983551,
      "eval_runtime": 545.5348,
      "eval_samples_per_second": 26.79,
      "eval_steps_per_second": 6.698,
      "step": 200
    },
    {
      "epoch": 0.023162686180173434,
      "grad_norm": 0.5872024893760681,
      "learning_rate": 5.161079439470866e-05,
      "loss": 0.6496,
      "step": 201
    },
    {
      "epoch": 0.02327792342485091,
      "grad_norm": 0.5686631798744202,
      "learning_rate": 5.1208187261806615e-05,
      "loss": 0.5287,
      "step": 202
    },
    {
      "epoch": 0.02339316066952839,
      "grad_norm": 0.5892530083656311,
      "learning_rate": 5.080550173136457e-05,
      "loss": 0.6187,
      "step": 203
    },
    {
      "epoch": 0.02350839791420587,
      "grad_norm": 0.754984438419342,
      "learning_rate": 5.0402763933069496e-05,
      "loss": 0.5892,
      "step": 204
    },
    {
      "epoch": 0.02362363515888335,
      "grad_norm": 0.5711228847503662,
      "learning_rate": 5e-05,
      "loss": 0.4912,
      "step": 205
    },
    {
      "epoch": 0.02373887240356083,
      "grad_norm": 0.8867496252059937,
      "learning_rate": 4.9597236066930516e-05,
      "loss": 0.7261,
      "step": 206
    },
    {
      "epoch": 0.023854109648238312,
      "grad_norm": 0.6213980317115784,
      "learning_rate": 4.919449826863544e-05,
      "loss": 0.5705,
      "step": 207
    },
    {
      "epoch": 0.02396934689291579,
      "grad_norm": 0.6462709903717041,
      "learning_rate": 4.87918127381934e-05,
      "loss": 0.7501,
      "step": 208
    },
    {
      "epoch": 0.02408458413759327,
      "grad_norm": 0.6636618375778198,
      "learning_rate": 4.8389205605291365e-05,
      "loss": 0.6899,
      "step": 209
    },
    {
      "epoch": 0.02419982138227075,
      "grad_norm": 0.5810405611991882,
      "learning_rate": 4.798670299452926e-05,
      "loss": 0.5939,
      "step": 210
    },
    {
      "epoch": 0.02431505862694823,
      "grad_norm": 0.6413638591766357,
      "learning_rate": 4.758433102372466e-05,
      "loss": 0.5566,
      "step": 211
    },
    {
      "epoch": 0.02443029587162571,
      "grad_norm": 0.708579957485199,
      "learning_rate": 4.7182115802218126e-05,
      "loss": 0.6541,
      "step": 212
    },
    {
      "epoch": 0.02454553311630319,
      "grad_norm": 0.648512065410614,
      "learning_rate": 4.678008342917903e-05,
      "loss": 0.626,
      "step": 213
    },
    {
      "epoch": 0.024660770360980667,
      "grad_norm": 0.6940747499465942,
      "learning_rate": 4.6378259991911886e-05,
      "loss": 0.6072,
      "step": 214
    },
    {
      "epoch": 0.024776007605658148,
      "grad_norm": 0.6784055829048157,
      "learning_rate": 4.597667156416371e-05,
      "loss": 0.6203,
      "step": 215
    },
    {
      "epoch": 0.024891244850335628,
      "grad_norm": 0.8279077410697937,
      "learning_rate": 4.5575344204432084e-05,
      "loss": 0.6603,
      "step": 216
    },
    {
      "epoch": 0.02500648209501311,
      "grad_norm": 1.2922221422195435,
      "learning_rate": 4.5174303954274244e-05,
      "loss": 0.7691,
      "step": 217
    },
    {
      "epoch": 0.02512171933969059,
      "grad_norm": 0.8495535850524902,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7552,
      "step": 218
    },
    {
      "epoch": 0.02523695658436807,
      "grad_norm": 0.8626475930213928,
      "learning_rate": 4.437318885406973e-05,
      "loss": 0.7286,
      "step": 219
    },
    {
      "epoch": 0.025352193829045546,
      "grad_norm": 0.8560473918914795,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.6934,
      "step": 220
    },
    {
      "epoch": 0.025467431073723026,
      "grad_norm": 0.8979941606521606,
      "learning_rate": 4.3573534193020274e-05,
      "loss": 0.7408,
      "step": 221
    },
    {
      "epoch": 0.025582668318400507,
      "grad_norm": 0.8926584720611572,
      "learning_rate": 4.317431940296343e-05,
      "loss": 0.6998,
      "step": 222
    },
    {
      "epoch": 0.025697905563077987,
      "grad_norm": 1.0287340879440308,
      "learning_rate": 4.277554752153895e-05,
      "loss": 0.6588,
      "step": 223
    },
    {
      "epoch": 0.025813142807755467,
      "grad_norm": 1.906563401222229,
      "learning_rate": 4.237724442448273e-05,
      "loss": 0.6557,
      "step": 224
    },
    {
      "epoch": 0.025928380052432948,
      "grad_norm": 1.0948593616485596,
      "learning_rate": 4.197943595711198e-05,
      "loss": 0.5973,
      "step": 225
    },
    {
      "epoch": 0.026043617297110425,
      "grad_norm": 1.3332748413085938,
      "learning_rate": 4.1582147932648074e-05,
      "loss": 0.6465,
      "step": 226
    },
    {
      "epoch": 0.026158854541787905,
      "grad_norm": 1.3926104307174683,
      "learning_rate": 4.118540613054156e-05,
      "loss": 0.6133,
      "step": 227
    },
    {
      "epoch": 0.026274091786465385,
      "grad_norm": 1.373544454574585,
      "learning_rate": 4.078923629479943e-05,
      "loss": 0.6587,
      "step": 228
    },
    {
      "epoch": 0.026389329031142866,
      "grad_norm": 1.4265940189361572,
      "learning_rate": 4.039366413231458e-05,
      "loss": 0.6224,
      "step": 229
    },
    {
      "epoch": 0.026504566275820346,
      "grad_norm": 1.0143760442733765,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 0.5808,
      "step": 230
    },
    {
      "epoch": 0.026619803520497826,
      "grad_norm": 0.9024608731269836,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.4964,
      "step": 231
    },
    {
      "epoch": 0.026735040765175303,
      "grad_norm": 1.010740876197815,
      "learning_rate": 3.92107901616097e-05,
      "loss": 0.6209,
      "step": 232
    },
    {
      "epoch": 0.026850278009852784,
      "grad_norm": 0.9866460561752319,
      "learning_rate": 3.8817864960472236e-05,
      "loss": 0.6106,
      "step": 233
    },
    {
      "epoch": 0.026965515254530264,
      "grad_norm": 0.9405643343925476,
      "learning_rate": 3.842566535205286e-05,
      "loss": 0.5751,
      "step": 234
    },
    {
      "epoch": 0.027080752499207744,
      "grad_norm": 0.9639310240745544,
      "learning_rate": 3.803421678562213e-05,
      "loss": 0.5764,
      "step": 235
    },
    {
      "epoch": 0.027195989743885225,
      "grad_norm": 0.9636418223381042,
      "learning_rate": 3.764354466171652e-05,
      "loss": 0.4725,
      "step": 236
    },
    {
      "epoch": 0.027311226988562705,
      "grad_norm": 0.9855490922927856,
      "learning_rate": 3.725367433049033e-05,
      "loss": 0.5208,
      "step": 237
    },
    {
      "epoch": 0.02742646423324018,
      "grad_norm": 1.095041275024414,
      "learning_rate": 3.6864631090070655e-05,
      "loss": 0.5492,
      "step": 238
    },
    {
      "epoch": 0.027541701477917662,
      "grad_norm": 0.9551463723182678,
      "learning_rate": 3.6476440184915815e-05,
      "loss": 0.4841,
      "step": 239
    },
    {
      "epoch": 0.027656938722595142,
      "grad_norm": 0.9834778308868408,
      "learning_rate": 3.608912680417737e-05,
      "loss": 0.4802,
      "step": 240
    },
    {
      "epoch": 0.027772175967272623,
      "grad_norm": 1.0290888547897339,
      "learning_rate": 3.570271608006555e-05,
      "loss": 0.4678,
      "step": 241
    },
    {
      "epoch": 0.027887413211950103,
      "grad_norm": 1.1884846687316895,
      "learning_rate": 3.531723308621847e-05,
      "loss": 0.6124,
      "step": 242
    },
    {
      "epoch": 0.028002650456627583,
      "grad_norm": 1.1768547296524048,
      "learning_rate": 3.493270283607522e-05,
      "loss": 0.5453,
      "step": 243
    },
    {
      "epoch": 0.02811788770130506,
      "grad_norm": 1.2450060844421387,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5197,
      "step": 244
    },
    {
      "epoch": 0.02823312494598254,
      "grad_norm": 1.1013474464416504,
      "learning_rate": 3.4166600309926387e-05,
      "loss": 0.4784,
      "step": 245
    },
    {
      "epoch": 0.02834836219066002,
      "grad_norm": 1.2103960514068604,
      "learning_rate": 3.3785077745215873e-05,
      "loss": 0.5579,
      "step": 246
    },
    {
      "epoch": 0.0284635994353375,
      "grad_norm": 1.3629238605499268,
      "learning_rate": 3.340460734357359e-05,
      "loss": 0.521,
      "step": 247
    },
    {
      "epoch": 0.02857883668001498,
      "grad_norm": 1.3528265953063965,
      "learning_rate": 3.3025213793178646e-05,
      "loss": 0.4699,
      "step": 248
    },
    {
      "epoch": 0.028694073924692462,
      "grad_norm": 1.7364858388900757,
      "learning_rate": 3.264692171233485e-05,
      "loss": 0.5086,
      "step": 249
    },
    {
      "epoch": 0.02880931116936994,
      "grad_norm": 1.2796268463134766,
      "learning_rate": 3.226975564787322e-05,
      "loss": 0.4677,
      "step": 250
    },
    {
      "epoch": 0.02880931116936994,
      "eval_loss": 0.5864402651786804,
      "eval_runtime": 546.8732,
      "eval_samples_per_second": 26.725,
      "eval_steps_per_second": 6.682,
      "step": 250
    },
    {
      "epoch": 0.02892454841404742,
      "grad_norm": 0.49436643719673157,
      "learning_rate": 3.189374007355917e-05,
      "loss": 0.5239,
      "step": 251
    },
    {
      "epoch": 0.0290397856587249,
      "grad_norm": 0.5220190286636353,
      "learning_rate": 3.151889938850445e-05,
      "loss": 0.6093,
      "step": 252
    },
    {
      "epoch": 0.02915502290340238,
      "grad_norm": 0.596616268157959,
      "learning_rate": 3.114525791558398e-05,
      "loss": 0.591,
      "step": 253
    },
    {
      "epoch": 0.02927026014807986,
      "grad_norm": 0.6420341730117798,
      "learning_rate": 3.0772839899857464e-05,
      "loss": 0.6168,
      "step": 254
    },
    {
      "epoch": 0.02938549739275734,
      "grad_norm": 0.591904878616333,
      "learning_rate": 3.0401669506996256e-05,
      "loss": 0.5331,
      "step": 255
    },
    {
      "epoch": 0.029500734637434817,
      "grad_norm": 0.6355295777320862,
      "learning_rate": 3.003177082171523e-05,
      "loss": 0.7249,
      "step": 256
    },
    {
      "epoch": 0.029615971882112298,
      "grad_norm": 0.6406742930412292,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.592,
      "step": 257
    },
    {
      "epoch": 0.029731209126789778,
      "grad_norm": 0.6385841369628906,
      "learning_rate": 2.9295884498599414e-05,
      "loss": 0.6364,
      "step": 258
    },
    {
      "epoch": 0.02984644637146726,
      "grad_norm": 0.692854642868042,
      "learning_rate": 2.8929944611373554e-05,
      "loss": 0.7044,
      "step": 259
    },
    {
      "epoch": 0.02996168361614474,
      "grad_norm": 0.690500795841217,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 0.6743,
      "step": 260
    },
    {
      "epoch": 0.03007692086082222,
      "grad_norm": 0.7187701463699341,
      "learning_rate": 2.8202190110619493e-05,
      "loss": 0.5568,
      "step": 261
    },
    {
      "epoch": 0.030192158105499696,
      "grad_norm": 0.6858519315719604,
      "learning_rate": 2.784042272003794e-05,
      "loss": 0.5427,
      "step": 262
    },
    {
      "epoch": 0.030307395350177176,
      "grad_norm": 0.728316605091095,
      "learning_rate": 2.7480093232670158e-05,
      "loss": 0.6825,
      "step": 263
    },
    {
      "epoch": 0.030422632594854657,
      "grad_norm": 0.7076228260993958,
      "learning_rate": 2.712122502978024e-05,
      "loss": 0.7327,
      "step": 264
    },
    {
      "epoch": 0.030537869839532137,
      "grad_norm": 0.9509554505348206,
      "learning_rate": 2.6763841397811573e-05,
      "loss": 0.5248,
      "step": 265
    },
    {
      "epoch": 0.030653107084209617,
      "grad_norm": 0.733241617679596,
      "learning_rate": 2.64079655268759e-05,
      "loss": 0.5209,
      "step": 266
    },
    {
      "epoch": 0.030768344328887098,
      "grad_norm": 0.8173394799232483,
      "learning_rate": 2.605362050924848e-05,
      "loss": 0.5888,
      "step": 267
    },
    {
      "epoch": 0.030883581573564575,
      "grad_norm": 0.7932162284851074,
      "learning_rate": 2.57008293378697e-05,
      "loss": 0.7154,
      "step": 268
    },
    {
      "epoch": 0.030998818818242055,
      "grad_norm": 0.8659783601760864,
      "learning_rate": 2.534961490485313e-05,
      "loss": 0.5691,
      "step": 269
    },
    {
      "epoch": 0.031114056062919535,
      "grad_norm": 0.8032422661781311,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.5285,
      "step": 270
    },
    {
      "epoch": 0.031229293307597016,
      "grad_norm": 0.9526371359825134,
      "learning_rate": 2.4652007309320498e-05,
      "loss": 0.6952,
      "step": 271
    },
    {
      "epoch": 0.03134453055227449,
      "grad_norm": 0.933838427066803,
      "learning_rate": 2.430565941356157e-05,
      "loss": 0.6856,
      "step": 272
    },
    {
      "epoch": 0.031459767796951976,
      "grad_norm": 1.056208848953247,
      "learning_rate": 2.3960978786741877e-05,
      "loss": 0.6652,
      "step": 273
    },
    {
      "epoch": 0.03157500504162945,
      "grad_norm": 0.9815629720687866,
      "learning_rate": 2.361798779469336e-05,
      "loss": 0.5508,
      "step": 274
    },
    {
      "epoch": 0.03169024228630694,
      "grad_norm": 0.9763931035995483,
      "learning_rate": 2.3276708693609943e-05,
      "loss": 0.5162,
      "step": 275
    },
    {
      "epoch": 0.031805479530984414,
      "grad_norm": 2.0040676593780518,
      "learning_rate": 2.2937163628603435e-05,
      "loss": 0.7866,
      "step": 276
    },
    {
      "epoch": 0.03192071677566189,
      "grad_norm": 1.1686058044433594,
      "learning_rate": 2.259937463226651e-05,
      "loss": 0.5514,
      "step": 277
    },
    {
      "epoch": 0.032035954020339374,
      "grad_norm": 1.249847412109375,
      "learning_rate": 2.2263363623243054e-05,
      "loss": 0.6229,
      "step": 278
    },
    {
      "epoch": 0.03215119126501685,
      "grad_norm": 1.0815333127975464,
      "learning_rate": 2.192915240480596e-05,
      "loss": 0.5628,
      "step": 279
    },
    {
      "epoch": 0.032266428509694335,
      "grad_norm": 0.8114826083183289,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 0.5534,
      "step": 280
    },
    {
      "epoch": 0.03238166575437181,
      "grad_norm": 0.8990956544876099,
      "learning_rate": 2.1266215967445824e-05,
      "loss": 0.6225,
      "step": 281
    },
    {
      "epoch": 0.032496902999049296,
      "grad_norm": 0.9672009944915771,
      "learning_rate": 2.0937533765518187e-05,
      "loss": 0.5707,
      "step": 282
    },
    {
      "epoch": 0.03261214024372677,
      "grad_norm": 0.9714505076408386,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5974,
      "step": 283
    },
    {
      "epoch": 0.03272737748840425,
      "grad_norm": 1.074284315109253,
      "learning_rate": 2.0285848032369137e-05,
      "loss": 0.6089,
      "step": 284
    },
    {
      "epoch": 0.03284261473308173,
      "grad_norm": 0.9929256439208984,
      "learning_rate": 1.996288678810105e-05,
      "loss": 0.4241,
      "step": 285
    },
    {
      "epoch": 0.03295785197775921,
      "grad_norm": 0.9622356295585632,
      "learning_rate": 1.9641874609064443e-05,
      "loss": 0.4916,
      "step": 286
    },
    {
      "epoch": 0.033073089222436694,
      "grad_norm": 1.044762372970581,
      "learning_rate": 1.932283232527956e-05,
      "loss": 0.6892,
      "step": 287
    },
    {
      "epoch": 0.03318832646711417,
      "grad_norm": 0.9555506706237793,
      "learning_rate": 1.9005780638942982e-05,
      "loss": 0.5201,
      "step": 288
    },
    {
      "epoch": 0.03330356371179165,
      "grad_norm": 1.053078055381775,
      "learning_rate": 1.8690740123084316e-05,
      "loss": 0.6296,
      "step": 289
    },
    {
      "epoch": 0.03341880095646913,
      "grad_norm": 1.1646440029144287,
      "learning_rate": 1.837773122023114e-05,
      "loss": 0.5341,
      "step": 290
    },
    {
      "epoch": 0.03353403820114661,
      "grad_norm": 1.0825483798980713,
      "learning_rate": 1.8066774241082612e-05,
      "loss": 0.4564,
      "step": 291
    },
    {
      "epoch": 0.03364927544582409,
      "grad_norm": 1.0500282049179077,
      "learning_rate": 1.7757889363191483e-05,
      "loss": 0.4674,
      "step": 292
    },
    {
      "epoch": 0.03376451269050157,
      "grad_norm": 1.2521641254425049,
      "learning_rate": 1.745109662965481e-05,
      "loss": 0.543,
      "step": 293
    },
    {
      "epoch": 0.03387974993517905,
      "grad_norm": 1.1742342710494995,
      "learning_rate": 1.714641594781347e-05,
      "loss": 0.537,
      "step": 294
    },
    {
      "epoch": 0.03399498717985653,
      "grad_norm": 1.0398088693618774,
      "learning_rate": 1.684386708796025e-05,
      "loss": 0.4332,
      "step": 295
    },
    {
      "epoch": 0.03411022442453401,
      "grad_norm": 1.2116755247116089,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4955,
      "step": 296
    },
    {
      "epoch": 0.03422546166921149,
      "grad_norm": 1.2733010053634644,
      "learning_rate": 1.62452432224612e-05,
      "loss": 0.5968,
      "step": 297
    },
    {
      "epoch": 0.03434069891388897,
      "grad_norm": 1.2947372198104858,
      "learning_rate": 1.5949207060660138e-05,
      "loss": 0.4119,
      "step": 298
    },
    {
      "epoch": 0.03445593615856645,
      "grad_norm": 1.4762217998504639,
      "learning_rate": 1.5655380406016235e-05,
      "loss": 0.4468,
      "step": 299
    },
    {
      "epoch": 0.03457117340324393,
      "grad_norm": 1.39065420627594,
      "learning_rate": 1.536378232452003e-05,
      "loss": 0.3888,
      "step": 300
    },
    {
      "epoch": 0.03457117340324393,
      "eval_loss": 0.5709081292152405,
      "eval_runtime": 545.5086,
      "eval_samples_per_second": 26.792,
      "eval_steps_per_second": 6.698,
      "step": 300
    },
    {
      "epoch": 0.034686410647921405,
      "grad_norm": 0.44936424493789673,
      "learning_rate": 1.5074431737553157e-05,
      "loss": 0.5426,
      "step": 301
    },
    {
      "epoch": 0.03480164789259889,
      "grad_norm": 0.5097118616104126,
      "learning_rate": 1.4787347420660541e-05,
      "loss": 0.4921,
      "step": 302
    },
    {
      "epoch": 0.034916885137276366,
      "grad_norm": 0.5721942782402039,
      "learning_rate": 1.4502548002332088e-05,
      "loss": 0.7171,
      "step": 303
    },
    {
      "epoch": 0.03503212238195385,
      "grad_norm": 0.5862175226211548,
      "learning_rate": 1.422005196279395e-05,
      "loss": 0.5825,
      "step": 304
    },
    {
      "epoch": 0.035147359626631326,
      "grad_norm": 0.610176682472229,
      "learning_rate": 1.3939877632809278e-05,
      "loss": 0.5593,
      "step": 305
    },
    {
      "epoch": 0.03526259687130881,
      "grad_norm": 0.6718563437461853,
      "learning_rate": 1.3662043192488849e-05,
      "loss": 0.6023,
      "step": 306
    },
    {
      "epoch": 0.03537783411598629,
      "grad_norm": 0.7071716785430908,
      "learning_rate": 1.338656667011134e-05,
      "loss": 0.7905,
      "step": 307
    },
    {
      "epoch": 0.035493071360663764,
      "grad_norm": 0.6894174814224243,
      "learning_rate": 1.3113465940953495e-05,
      "loss": 0.6028,
      "step": 308
    },
    {
      "epoch": 0.03560830860534125,
      "grad_norm": 0.6270958781242371,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.5373,
      "step": 309
    },
    {
      "epoch": 0.035723545850018724,
      "grad_norm": 0.7721391916275024,
      "learning_rate": 1.257446259144494e-05,
      "loss": 0.5485,
      "step": 310
    },
    {
      "epoch": 0.03583878309469621,
      "grad_norm": 0.7311829328536987,
      "learning_rate": 1.2308594946249163e-05,
      "loss": 0.6111,
      "step": 311
    },
    {
      "epoch": 0.035954020339373685,
      "grad_norm": 0.7510440349578857,
      "learning_rate": 1.204517304231343e-05,
      "loss": 0.5879,
      "step": 312
    },
    {
      "epoch": 0.03606925758405116,
      "grad_norm": 0.8949467539787292,
      "learning_rate": 1.178421397270758e-05,
      "loss": 0.7171,
      "step": 313
    },
    {
      "epoch": 0.036184494828728646,
      "grad_norm": 0.7741400003433228,
      "learning_rate": 1.1525734670691701e-05,
      "loss": 0.5864,
      "step": 314
    },
    {
      "epoch": 0.03629973207340612,
      "grad_norm": 0.7592278122901917,
      "learning_rate": 1.1269751908617277e-05,
      "loss": 0.559,
      "step": 315
    },
    {
      "epoch": 0.036414969318083606,
      "grad_norm": 0.7965648770332336,
      "learning_rate": 1.1016282296838887e-05,
      "loss": 0.5493,
      "step": 316
    },
    {
      "epoch": 0.03653020656276108,
      "grad_norm": 0.8162243366241455,
      "learning_rate": 1.0765342282636416e-05,
      "loss": 0.6576,
      "step": 317
    },
    {
      "epoch": 0.03664544380743857,
      "grad_norm": 0.8158289194107056,
      "learning_rate": 1.0516948149147754e-05,
      "loss": 0.6477,
      "step": 318
    },
    {
      "epoch": 0.036760681052116044,
      "grad_norm": 0.9171628355979919,
      "learning_rate": 1.0271116014312293e-05,
      "loss": 0.5811,
      "step": 319
    },
    {
      "epoch": 0.03687591829679352,
      "grad_norm": 0.8957247138023376,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 0.578,
      "step": 320
    },
    {
      "epoch": 0.036991155541471005,
      "grad_norm": 0.8826591968536377,
      "learning_rate": 9.787201380101157e-06,
      "loss": 0.6718,
      "step": 321
    },
    {
      "epoch": 0.03710639278614848,
      "grad_norm": 1.0377730131149292,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7081,
      "step": 322
    },
    {
      "epoch": 0.037221630030825965,
      "grad_norm": 0.8994547724723816,
      "learning_rate": 9.313723980074018e-06,
      "loss": 0.5559,
      "step": 323
    },
    {
      "epoch": 0.03733686727550344,
      "grad_norm": 1.031438946723938,
      "learning_rate": 9.080937753040646e-06,
      "loss": 0.7033,
      "step": 324
    },
    {
      "epoch": 0.03745210452018092,
      "grad_norm": 1.041542649269104,
      "learning_rate": 8.850806705317183e-06,
      "loss": 0.5513,
      "step": 325
    },
    {
      "epoch": 0.0375673417648584,
      "grad_norm": 1.2182027101516724,
      "learning_rate": 8.623345769777514e-06,
      "loss": 0.8364,
      "step": 326
    },
    {
      "epoch": 0.03768257900953588,
      "grad_norm": 0.9404509663581848,
      "learning_rate": 8.398569706035792e-06,
      "loss": 0.537,
      "step": 327
    },
    {
      "epoch": 0.037797816254213364,
      "grad_norm": 1.1761248111724854,
      "learning_rate": 8.176493099488663e-06,
      "loss": 0.6538,
      "step": 328
    },
    {
      "epoch": 0.03791305349889084,
      "grad_norm": 1.344883680343628,
      "learning_rate": 7.957130360368898e-06,
      "loss": 0.6001,
      "step": 329
    },
    {
      "epoch": 0.038028290743568324,
      "grad_norm": 0.831625759601593,
      "learning_rate": 7.740495722810271e-06,
      "loss": 0.4481,
      "step": 330
    },
    {
      "epoch": 0.0381435279882458,
      "grad_norm": 0.8212209343910217,
      "learning_rate": 7.526603243923957e-06,
      "loss": 0.4851,
      "step": 331
    },
    {
      "epoch": 0.03825876523292328,
      "grad_norm": 0.902117908000946,
      "learning_rate": 7.315466802886401e-06,
      "loss": 0.5776,
      "step": 332
    },
    {
      "epoch": 0.03837400247760076,
      "grad_norm": 0.8807656764984131,
      "learning_rate": 7.107100100038671e-06,
      "loss": 0.4749,
      "step": 333
    },
    {
      "epoch": 0.03848923972227824,
      "grad_norm": 1.0799822807312012,
      "learning_rate": 6.901516655997536e-06,
      "loss": 0.6281,
      "step": 334
    },
    {
      "epoch": 0.03860447696695572,
      "grad_norm": 0.8429787158966064,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4242,
      "step": 335
    },
    {
      "epoch": 0.0387197142116332,
      "grad_norm": 1.0487651824951172,
      "learning_rate": 6.498752722928042e-06,
      "loss": 0.6525,
      "step": 336
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 1.1070475578308105,
      "learning_rate": 6.301598368674105e-06,
      "loss": 0.5714,
      "step": 337
    },
    {
      "epoch": 0.03895018870098816,
      "grad_norm": 1.008655071258545,
      "learning_rate": 6.107279541079769e-06,
      "loss": 0.5121,
      "step": 338
    },
    {
      "epoch": 0.03906542594566564,
      "grad_norm": 1.107851266860962,
      "learning_rate": 5.915808849215304e-06,
      "loss": 0.5654,
      "step": 339
    },
    {
      "epoch": 0.03918066319034312,
      "grad_norm": 0.9551889300346375,
      "learning_rate": 5.727198717339511e-06,
      "loss": 0.4666,
      "step": 340
    },
    {
      "epoch": 0.0392959004350206,
      "grad_norm": 1.1649274826049805,
      "learning_rate": 5.54146138409355e-06,
      "loss": 0.4918,
      "step": 341
    },
    {
      "epoch": 0.03941113767969808,
      "grad_norm": 1.1512972116470337,
      "learning_rate": 5.358608901706802e-06,
      "loss": 0.5748,
      "step": 342
    },
    {
      "epoch": 0.03952637492437556,
      "grad_norm": 1.2667012214660645,
      "learning_rate": 5.178653135214812e-06,
      "loss": 0.5099,
      "step": 343
    },
    {
      "epoch": 0.039641612169053035,
      "grad_norm": 1.1603896617889404,
      "learning_rate": 5.001605761689398e-06,
      "loss": 0.5842,
      "step": 344
    },
    {
      "epoch": 0.03975684941373052,
      "grad_norm": 1.1110482215881348,
      "learning_rate": 4.827478269480895e-06,
      "loss": 0.525,
      "step": 345
    },
    {
      "epoch": 0.039872086658407996,
      "grad_norm": 1.1846598386764526,
      "learning_rate": 4.65628195747273e-06,
      "loss": 0.5712,
      "step": 346
    },
    {
      "epoch": 0.03998732390308548,
      "grad_norm": 1.3512845039367676,
      "learning_rate": 4.488027934348271e-06,
      "loss": 0.5105,
      "step": 347
    },
    {
      "epoch": 0.040102561147762956,
      "grad_norm": 1.2469724416732788,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.495,
      "step": 348
    },
    {
      "epoch": 0.04021779839244043,
      "grad_norm": 1.583885908126831,
      "learning_rate": 4.16039023417088e-06,
      "loss": 0.4817,
      "step": 349
    },
    {
      "epoch": 0.04033303563711792,
      "grad_norm": 1.6261035203933716,
      "learning_rate": 4.001027817058789e-06,
      "loss": 0.3422,
      "step": 350
    },
    {
      "epoch": 0.04033303563711792,
      "eval_loss": 0.565327525138855,
      "eval_runtime": 545.9327,
      "eval_samples_per_second": 26.771,
      "eval_steps_per_second": 6.693,
      "step": 350
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.345339247276851e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}