{
  "best_metric": 0.8629807233810425,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.663716814159292,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017699115044247787,
      "grad_norm": 2.280963897705078,
      "learning_rate": 1e-05,
      "loss": 1.6006,
      "step": 1
    },
    {
      "epoch": 0.017699115044247787,
      "eval_loss": 2.295236349105835,
      "eval_runtime": 6.8162,
      "eval_samples_per_second": 13.937,
      "eval_steps_per_second": 3.521,
      "step": 1
    },
    {
      "epoch": 0.035398230088495575,
      "grad_norm": 2.509812593460083,
      "learning_rate": 2e-05,
      "loss": 1.9744,
      "step": 2
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": 2.4870777130126953,
      "learning_rate": 3e-05,
      "loss": 2.151,
      "step": 3
    },
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 3.0523364543914795,
      "learning_rate": 4e-05,
      "loss": 2.2439,
      "step": 4
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 2.856015205383301,
      "learning_rate": 5e-05,
      "loss": 1.9178,
      "step": 5
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 2.473170757293701,
      "learning_rate": 6e-05,
      "loss": 1.625,
      "step": 6
    },
    {
      "epoch": 0.12389380530973451,
      "grad_norm": 2.4284801483154297,
      "learning_rate": 7e-05,
      "loss": 1.4498,
      "step": 7
    },
    {
      "epoch": 0.1415929203539823,
      "grad_norm": 3.074007987976074,
      "learning_rate": 8e-05,
      "loss": 1.4779,
      "step": 8
    },
    {
      "epoch": 0.1592920353982301,
      "grad_norm": 1.903256893157959,
      "learning_rate": 9e-05,
      "loss": 0.9667,
      "step": 9
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 1.8827953338623047,
      "learning_rate": 0.0001,
      "loss": 1.2711,
      "step": 10
    },
    {
      "epoch": 0.19469026548672566,
      "grad_norm": 1.4443219900131226,
      "learning_rate": 9.999036202410325e-05,
      "loss": 1.1201,
      "step": 11
    },
    {
      "epoch": 0.21238938053097345,
      "grad_norm": 1.6327110528945923,
      "learning_rate": 9.996145181203615e-05,
      "loss": 1.2773,
      "step": 12
    },
    {
      "epoch": 0.23008849557522124,
      "grad_norm": 1.7427234649658203,
      "learning_rate": 9.991328050923581e-05,
      "loss": 1.5374,
      "step": 13
    },
    {
      "epoch": 0.24778761061946902,
      "grad_norm": 4.107868671417236,
      "learning_rate": 9.98458666866564e-05,
      "loss": 1.9677,
      "step": 14
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 1.2882623672485352,
      "learning_rate": 9.975923633360985e-05,
      "loss": 0.6889,
      "step": 15
    },
    {
      "epoch": 0.2831858407079646,
      "grad_norm": 1.568882703781128,
      "learning_rate": 9.965342284774632e-05,
      "loss": 0.8211,
      "step": 16
    },
    {
      "epoch": 0.3008849557522124,
      "grad_norm": 1.8820855617523193,
      "learning_rate": 9.952846702217886e-05,
      "loss": 1.0151,
      "step": 17
    },
    {
      "epoch": 0.3185840707964602,
      "grad_norm": 1.6098060607910156,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.0105,
      "step": 18
    },
    {
      "epoch": 0.336283185840708,
      "grad_norm": 1.0769816637039185,
      "learning_rate": 9.922132840449459e-05,
      "loss": 0.8687,
      "step": 19
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.9652581810951233,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9425,
      "step": 20
    },
    {
      "epoch": 0.37168141592920356,
      "grad_norm": 1.15622878074646,
      "learning_rate": 9.883829406604363e-05,
      "loss": 1.1651,
      "step": 21
    },
    {
      "epoch": 0.3893805309734513,
      "grad_norm": 0.9711587429046631,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.929,
      "step": 22
    },
    {
      "epoch": 0.40707964601769914,
      "grad_norm": 1.1409817934036255,
      "learning_rate": 9.837995461801299e-05,
      "loss": 0.8177,
      "step": 23
    },
    {
      "epoch": 0.4247787610619469,
      "grad_norm": 1.1862760782241821,
      "learning_rate": 9.812276182268236e-05,
      "loss": 0.8939,
      "step": 24
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 1.4299732446670532,
      "learning_rate": 9.784701678661045e-05,
      "loss": 1.211,
      "step": 25
    },
    {
      "epoch": 0.46017699115044247,
      "grad_norm": 1.1160023212432861,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0373,
      "step": 26
    },
    {
      "epoch": 0.4778761061946903,
      "grad_norm": 1.0652543306350708,
      "learning_rate": 9.724030232334391e-05,
      "loss": 1.0916,
      "step": 27
    },
    {
      "epoch": 0.49557522123893805,
      "grad_norm": 1.3456246852874756,
      "learning_rate": 9.690956679612421e-05,
      "loss": 1.439,
      "step": 28
    },
    {
      "epoch": 0.5132743362831859,
      "grad_norm": 0.8845888376235962,
      "learning_rate": 9.656074673794018e-05,
      "loss": 0.6948,
      "step": 29
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 0.9293695092201233,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8672,
      "step": 30
    },
    {
      "epoch": 0.5486725663716814,
      "grad_norm": 0.9480873942375183,
      "learning_rate": 9.580939785585681e-05,
      "loss": 0.914,
      "step": 31
    },
    {
      "epoch": 0.5663716814159292,
      "grad_norm": 0.945064127445221,
      "learning_rate": 9.540715869125407e-05,
      "loss": 0.8962,
      "step": 32
    },
    {
      "epoch": 0.584070796460177,
      "grad_norm": 1.8173238039016724,
      "learning_rate": 9.498741420261108e-05,
      "loss": 0.7806,
      "step": 33
    },
    {
      "epoch": 0.6017699115044248,
      "grad_norm": 1.9008045196533203,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.183,
      "step": 34
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 0.8381111025810242,
      "learning_rate": 9.409606321741775e-05,
      "loss": 0.8236,
      "step": 35
    },
    {
      "epoch": 0.6371681415929203,
      "grad_norm": 0.8810117840766907,
      "learning_rate": 9.362480035363986e-05,
      "loss": 0.9894,
      "step": 36
    },
    {
      "epoch": 0.6548672566371682,
      "grad_norm": 1.0025238990783691,
      "learning_rate": 9.31367192988896e-05,
      "loss": 1.0978,
      "step": 37
    },
    {
      "epoch": 0.672566371681416,
      "grad_norm": 0.8731153011322021,
      "learning_rate": 9.263200821770461e-05,
      "loss": 0.9889,
      "step": 38
    },
    {
      "epoch": 0.6902654867256637,
      "grad_norm": 0.8915436267852783,
      "learning_rate": 9.211086168581433e-05,
      "loss": 1.0382,
      "step": 39
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.9948314428329468,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.1075,
      "step": 40
    },
    {
      "epoch": 0.7256637168141593,
      "grad_norm": 1.0864626169204712,
      "learning_rate": 9.102007217627568e-05,
      "loss": 1.2494,
      "step": 41
    },
    {
      "epoch": 0.7433628318584071,
      "grad_norm": 1.2462245225906372,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4589,
      "step": 42
    },
    {
      "epoch": 0.7610619469026548,
      "grad_norm": 0.6787369251251221,
      "learning_rate": 8.986603268863536e-05,
      "loss": 0.8135,
      "step": 43
    },
    {
      "epoch": 0.7787610619469026,
      "grad_norm": 0.6781764030456543,
      "learning_rate": 8.926584654403724e-05,
      "loss": 0.7703,
      "step": 44
    },
    {
      "epoch": 0.7964601769911505,
      "grad_norm": 0.8601434826850891,
      "learning_rate": 8.865052266813685e-05,
      "loss": 0.9327,
      "step": 45
    },
    {
      "epoch": 0.8141592920353983,
      "grad_norm": 0.7944732308387756,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.8526,
      "step": 46
    },
    {
      "epoch": 0.831858407079646,
      "grad_norm": 0.7232624888420105,
      "learning_rate": 8.737541634312985e-05,
      "loss": 0.6354,
      "step": 47
    },
    {
      "epoch": 0.8495575221238938,
      "grad_norm": 0.8034805059432983,
      "learning_rate": 8.671612547178428e-05,
      "loss": 0.7852,
      "step": 48
    },
    {
      "epoch": 0.8672566371681416,
      "grad_norm": 0.8037271499633789,
      "learning_rate": 8.604267983514594e-05,
      "loss": 0.8371,
      "step": 49
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 0.8748500943183899,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8886,
      "step": 50
    },
    {
      "epoch": 0.8849557522123894,
      "eval_loss": 0.8629807233810425,
      "eval_runtime": 6.986,
      "eval_samples_per_second": 13.599,
      "eval_steps_per_second": 3.435,
      "step": 50
    },
    {
      "epoch": 0.9026548672566371,
      "grad_norm": 0.8342791199684143,
      "learning_rate": 8.46543681272818e-05,
      "loss": 0.8257,
      "step": 51
    },
    {
      "epoch": 0.9203539823008849,
      "grad_norm": 0.9353609681129456,
      "learning_rate": 8.39400372766471e-05,
      "loss": 1.1307,
      "step": 52
    },
    {
      "epoch": 0.9380530973451328,
      "grad_norm": 1.022132396697998,
      "learning_rate": 8.321262189556409e-05,
      "loss": 1.1414,
      "step": 53
    },
    {
      "epoch": 0.9557522123893806,
      "grad_norm": 1.032721996307373,
      "learning_rate": 8.247240241650918e-05,
      "loss": 1.0249,
      "step": 54
    },
    {
      "epoch": 0.9734513274336283,
      "grad_norm": 1.0308945178985596,
      "learning_rate": 8.171966420818228e-05,
      "loss": 1.0607,
      "step": 55
    },
    {
      "epoch": 0.9911504424778761,
      "grad_norm": 1.2551980018615723,
      "learning_rate": 8.095469746549172e-05,
      "loss": 1.5497,
      "step": 56
    },
    {
      "epoch": 1.0132743362831858,
      "grad_norm": 1.5172427892684937,
      "learning_rate": 8.017779709767858e-05,
      "loss": 1.1828,
      "step": 57
    },
    {
      "epoch": 1.0309734513274336,
      "grad_norm": 0.7486307621002197,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6634,
      "step": 58
    },
    {
      "epoch": 1.0486725663716814,
      "grad_norm": 0.7508041858673096,
      "learning_rate": 7.858939801138061e-05,
      "loss": 0.8152,
      "step": 59
    },
    {
      "epoch": 1.0663716814159292,
      "grad_norm": 0.7589112520217896,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.6895,
      "step": 60
    },
    {
      "epoch": 1.084070796460177,
      "grad_norm": 0.7142118215560913,
      "learning_rate": 7.695691614555003e-05,
      "loss": 0.5247,
      "step": 61
    },
    {
      "epoch": 1.1017699115044248,
      "grad_norm": 0.7129442095756531,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.6682,
      "step": 62
    },
    {
      "epoch": 1.1194690265486726,
      "grad_norm": 0.7287638187408447,
      "learning_rate": 7.528286866889924e-05,
      "loss": 0.7053,
      "step": 63
    },
    {
      "epoch": 1.1371681415929205,
      "grad_norm": 0.9455931186676025,
      "learning_rate": 7.443106207484776e-05,
      "loss": 0.7347,
      "step": 64
    },
    {
      "epoch": 1.154867256637168,
      "grad_norm": 0.760444700717926,
      "learning_rate": 7.35698368412999e-05,
      "loss": 0.7523,
      "step": 65
    },
    {
      "epoch": 1.1725663716814159,
      "grad_norm": 0.7031366229057312,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.5242,
      "step": 66
    },
    {
      "epoch": 1.1902654867256637,
      "grad_norm": 0.8057155013084412,
      "learning_rate": 7.18204620336671e-05,
      "loss": 0.6423,
      "step": 67
    },
    {
      "epoch": 1.2079646017699115,
      "grad_norm": 0.9145888090133667,
      "learning_rate": 7.09329868768714e-05,
      "loss": 0.8114,
      "step": 68
    },
    {
      "epoch": 1.2256637168141593,
      "grad_norm": 0.957840085029602,
      "learning_rate": 7.003744165515705e-05,
      "loss": 0.7889,
      "step": 69
    },
    {
      "epoch": 1.2433628318584071,
      "grad_norm": 1.1084387302398682,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8842,
      "step": 70
    },
    {
      "epoch": 1.261061946902655,
      "grad_norm": 0.8518170118331909,
      "learning_rate": 6.82235249939575e-05,
      "loss": 0.5889,
      "step": 71
    },
    {
      "epoch": 1.2787610619469025,
      "grad_norm": 0.761696994304657,
      "learning_rate": 6.730585285387465e-05,
      "loss": 0.4945,
      "step": 72
    },
    {
      "epoch": 1.2964601769911503,
      "grad_norm": 0.8722968101501465,
      "learning_rate": 6.638150897808468e-05,
      "loss": 0.5406,
      "step": 73
    },
    {
      "epoch": 1.3141592920353982,
      "grad_norm": 0.9867381453514099,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.812,
      "step": 74
    },
    {
      "epoch": 1.331858407079646,
      "grad_norm": 1.058192491531372,
      "learning_rate": 6.451423386272312e-05,
      "loss": 0.597,
      "step": 75
    },
    {
      "epoch": 1.3495575221238938,
      "grad_norm": 1.0891320705413818,
      "learning_rate": 6.357202249325371e-05,
      "loss": 0.6035,
      "step": 76
    },
    {
      "epoch": 1.3672566371681416,
      "grad_norm": 1.0673609972000122,
      "learning_rate": 6.26245788507579e-05,
      "loss": 0.7171,
      "step": 77
    },
    {
      "epoch": 1.3849557522123894,
      "grad_norm": 0.856677770614624,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.5655,
      "step": 78
    },
    {
      "epoch": 1.4026548672566372,
      "grad_norm": 1.0465450286865234,
      "learning_rate": 6.071545765325254e-05,
      "loss": 0.4403,
      "step": 79
    },
    {
      "epoch": 1.420353982300885,
      "grad_norm": 0.9781056046485901,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7209,
      "step": 80
    },
    {
      "epoch": 1.4380530973451329,
      "grad_norm": 0.9389674067497253,
      "learning_rate": 5.8789813996717736e-05,
      "loss": 0.6367,
      "step": 81
    },
    {
      "epoch": 1.4557522123893805,
      "grad_norm": 0.9528778195381165,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.7008,
      "step": 82
    },
    {
      "epoch": 1.4734513274336283,
      "grad_norm": 1.0513659715652466,
      "learning_rate": 5.685061708409841e-05,
      "loss": 0.641,
      "step": 83
    },
    {
      "epoch": 1.491150442477876,
      "grad_norm": 1.2438160181045532,
      "learning_rate": 5.587686987289189e-05,
      "loss": 1.0257,
      "step": 84
    },
    {
      "epoch": 1.508849557522124,
      "grad_norm": 0.9585502743721008,
      "learning_rate": 5.490085701647805e-05,
      "loss": 0.6353,
      "step": 85
    },
    {
      "epoch": 1.5265486725663717,
      "grad_norm": 1.3222746849060059,
      "learning_rate": 5.392295478639225e-05,
      "loss": 0.6635,
      "step": 86
    },
    {
      "epoch": 1.5442477876106193,
      "grad_norm": 1.1059401035308838,
      "learning_rate": 5.294354018255945e-05,
      "loss": 0.6694,
      "step": 87
    },
    {
      "epoch": 1.5619469026548671,
      "grad_norm": 0.9538819789886475,
      "learning_rate": 5.196299078795344e-05,
      "loss": 0.536,
      "step": 88
    },
    {
      "epoch": 1.579646017699115,
      "grad_norm": 0.9908929467201233,
      "learning_rate": 5.0981684623031415e-05,
      "loss": 0.6028,
      "step": 89
    },
    {
      "epoch": 1.5973451327433628,
      "grad_norm": 0.9496501684188843,
      "learning_rate": 5e-05,
      "loss": 0.4547,
      "step": 90
    },
    {
      "epoch": 1.6150442477876106,
      "grad_norm": 0.9586553573608398,
      "learning_rate": 4.901831537696859e-05,
      "loss": 0.6183,
      "step": 91
    },
    {
      "epoch": 1.6327433628318584,
      "grad_norm": 0.9949407577514648,
      "learning_rate": 4.8037009212046586e-05,
      "loss": 0.5747,
      "step": 92
    },
    {
      "epoch": 1.6504424778761062,
      "grad_norm": 1.0018373727798462,
      "learning_rate": 4.7056459817440544e-05,
      "loss": 0.5943,
      "step": 93
    },
    {
      "epoch": 1.668141592920354,
      "grad_norm": 1.0088860988616943,
      "learning_rate": 4.607704521360776e-05,
      "loss": 0.6541,
      "step": 94
    },
    {
      "epoch": 1.6858407079646018,
      "grad_norm": 1.0395617485046387,
      "learning_rate": 4.509914298352197e-05,
      "loss": 0.614,
      "step": 95
    },
    {
      "epoch": 1.7035398230088497,
      "grad_norm": 1.2786129713058472,
      "learning_rate": 4.412313012710813e-05,
      "loss": 0.6389,
      "step": 96
    },
    {
      "epoch": 1.7212389380530975,
      "grad_norm": 1.1238988637924194,
      "learning_rate": 4.3149382915901606e-05,
      "loss": 0.8043,
      "step": 97
    },
    {
      "epoch": 1.7389380530973453,
      "grad_norm": 1.5196340084075928,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.959,
      "step": 98
    },
    {
      "epoch": 1.7566371681415929,
      "grad_norm": 1.0669888257980347,
      "learning_rate": 4.1210186003282275e-05,
      "loss": 0.6601,
      "step": 99
    },
    {
      "epoch": 1.7743362831858407,
      "grad_norm": 0.8285733461380005,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.4862,
      "step": 100
    },
    {
      "epoch": 1.7743362831858407,
      "eval_loss": 0.9206369519233704,
      "eval_runtime": 6.9876,
      "eval_samples_per_second": 13.595,
      "eval_steps_per_second": 3.435,
      "step": 100
    },
    {
      "epoch": 1.7920353982300885,
      "grad_norm": 1.2100951671600342,
      "learning_rate": 3.928454234674747e-05,
      "loss": 0.6735,
      "step": 101
    },
    {
      "epoch": 1.8097345132743363,
      "grad_norm": 1.019980788230896,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.4795,
      "step": 102
    },
    {
      "epoch": 1.827433628318584,
      "grad_norm": 0.9808886051177979,
      "learning_rate": 3.73754211492421e-05,
      "loss": 0.605,
      "step": 103
    },
    {
      "epoch": 1.8451327433628317,
      "grad_norm": 1.0874282121658325,
      "learning_rate": 3.642797750674629e-05,
      "loss": 0.7412,
      "step": 104
    },
    {
      "epoch": 1.8628318584070795,
      "grad_norm": 1.1271072626113892,
      "learning_rate": 3.5485766137276894e-05,
      "loss": 0.6797,
      "step": 105
    },
    {
      "epoch": 1.8805309734513274,
      "grad_norm": 1.0317531824111938,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4929,
      "step": 106
    },
    {
      "epoch": 1.8982300884955752,
      "grad_norm": 1.1021236181259155,
      "learning_rate": 3.361849102191533e-05,
      "loss": 0.6134,
      "step": 107
    },
    {
      "epoch": 1.915929203539823,
      "grad_norm": 1.095332145690918,
      "learning_rate": 3.2694147146125345e-05,
      "loss": 0.5781,
      "step": 108
    },
    {
      "epoch": 1.9336283185840708,
      "grad_norm": 1.1151381731033325,
      "learning_rate": 3.177647500604252e-05,
      "loss": 0.6545,
      "step": 109
    },
    {
      "epoch": 1.9513274336283186,
      "grad_norm": 1.2261312007904053,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7223,
      "step": 110
    },
    {
      "epoch": 1.9690265486725664,
      "grad_norm": 1.0669209957122803,
      "learning_rate": 2.996255834484296e-05,
      "loss": 0.5042,
      "step": 111
    },
    {
      "epoch": 1.9867256637168142,
      "grad_norm": 1.3711998462677002,
      "learning_rate": 2.9067013123128613e-05,
      "loss": 0.9739,
      "step": 112
    },
    {
      "epoch": 2.0088495575221237,
      "grad_norm": 1.9376322031021118,
      "learning_rate": 2.8179537966332887e-05,
      "loss": 0.7555,
      "step": 113
    },
    {
      "epoch": 2.0265486725663715,
      "grad_norm": 0.781846821308136,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.3182,
      "step": 114
    },
    {
      "epoch": 2.0442477876106193,
      "grad_norm": 0.9402307868003845,
      "learning_rate": 2.6430163158700115e-05,
      "loss": 0.4366,
      "step": 115
    },
    {
      "epoch": 2.061946902654867,
      "grad_norm": 0.9695858359336853,
      "learning_rate": 2.556893792515227e-05,
      "loss": 0.2303,
      "step": 116
    },
    {
      "epoch": 2.079646017699115,
      "grad_norm": 1.2189714908599854,
      "learning_rate": 2.471713133110078e-05,
      "loss": 0.4529,
      "step": 117
    },
    {
      "epoch": 2.0973451327433628,
      "grad_norm": 0.7794205546379089,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 0.2843,
      "step": 118
    },
    {
      "epoch": 2.1150442477876106,
      "grad_norm": 0.8974909782409668,
      "learning_rate": 2.3043083854449988e-05,
      "loss": 0.4039,
      "step": 119
    },
    {
      "epoch": 2.1327433628318584,
      "grad_norm": 0.9793106913566589,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.3848,
      "step": 120
    },
    {
      "epoch": 2.150442477876106,
      "grad_norm": 0.9427468180656433,
      "learning_rate": 2.1410601988619394e-05,
      "loss": 0.3134,
      "step": 121
    },
    {
      "epoch": 2.168141592920354,
      "grad_norm": 1.0571012496948242,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3331,
      "step": 122
    },
    {
      "epoch": 2.185840707964602,
      "grad_norm": 1.081581473350525,
      "learning_rate": 1.982220290232143e-05,
      "loss": 0.3525,
      "step": 123
    },
    {
      "epoch": 2.2035398230088497,
      "grad_norm": 1.3777657747268677,
      "learning_rate": 1.9045302534508297e-05,
      "loss": 0.4149,
      "step": 124
    },
    {
      "epoch": 2.2212389380530975,
      "grad_norm": 0.9454907774925232,
      "learning_rate": 1.8280335791817733e-05,
      "loss": 0.2463,
      "step": 125
    },
    {
      "epoch": 2.2389380530973453,
      "grad_norm": 1.1618309020996094,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 0.3783,
      "step": 126
    },
    {
      "epoch": 2.256637168141593,
      "grad_norm": 1.170831561088562,
      "learning_rate": 1.678737810443593e-05,
      "loss": 0.3626,
      "step": 127
    },
    {
      "epoch": 2.274336283185841,
      "grad_norm": 1.1366978883743286,
      "learning_rate": 1.605996272335291e-05,
      "loss": 0.2512,
      "step": 128
    },
    {
      "epoch": 2.2920353982300883,
      "grad_norm": 1.2076972723007202,
      "learning_rate": 1.5345631872718214e-05,
      "loss": 0.3422,
      "step": 129
    },
    {
      "epoch": 2.309734513274336,
      "grad_norm": 1.2742947340011597,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.3533,
      "step": 130
    },
    {
      "epoch": 2.327433628318584,
      "grad_norm": 1.1574723720550537,
      "learning_rate": 1.3957320164854059e-05,
      "loss": 0.3042,
      "step": 131
    },
    {
      "epoch": 2.3451327433628317,
      "grad_norm": 1.438873052597046,
      "learning_rate": 1.3283874528215733e-05,
      "loss": 0.3407,
      "step": 132
    },
    {
      "epoch": 2.3628318584070795,
      "grad_norm": 2.25028133392334,
      "learning_rate": 1.2624583656870154e-05,
      "loss": 0.3244,
      "step": 133
    },
    {
      "epoch": 2.3805309734513274,
      "grad_norm": 1.5336682796478271,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 0.4788,
      "step": 134
    },
    {
      "epoch": 2.398230088495575,
      "grad_norm": 1.2398130893707275,
      "learning_rate": 1.134947733186315e-05,
      "loss": 0.3341,
      "step": 135
    },
    {
      "epoch": 2.415929203539823,
      "grad_norm": 1.1453783512115479,
      "learning_rate": 1.0734153455962765e-05,
      "loss": 0.2069,
      "step": 136
    },
    {
      "epoch": 2.433628318584071,
      "grad_norm": 1.406343936920166,
      "learning_rate": 1.013396731136465e-05,
      "loss": 0.365,
      "step": 137
    },
    {
      "epoch": 2.4513274336283186,
      "grad_norm": 1.3453893661499023,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3082,
      "step": 138
    },
    {
      "epoch": 2.4690265486725664,
      "grad_norm": 1.331973671913147,
      "learning_rate": 8.97992782372432e-06,
      "loss": 0.3943,
      "step": 139
    },
    {
      "epoch": 2.4867256637168142,
      "grad_norm": 1.3919755220413208,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.4101,
      "step": 140
    },
    {
      "epoch": 2.504424778761062,
      "grad_norm": 1.3736562728881836,
      "learning_rate": 7.889138314185678e-06,
      "loss": 0.3286,
      "step": 141
    },
    {
      "epoch": 2.52212389380531,
      "grad_norm": 1.3815242052078247,
      "learning_rate": 7.367991782295391e-06,
      "loss": 0.3418,
      "step": 142
    },
    {
      "epoch": 2.5398230088495577,
      "grad_norm": 1.343965768814087,
      "learning_rate": 6.863280701110408e-06,
      "loss": 0.4067,
      "step": 143
    },
    {
      "epoch": 2.557522123893805,
      "grad_norm": 1.2378324270248413,
      "learning_rate": 6.375199646360142e-06,
      "loss": 0.3246,
      "step": 144
    },
    {
      "epoch": 2.5752212389380533,
      "grad_norm": 1.2089776992797852,
      "learning_rate": 5.903936782582253e-06,
      "loss": 0.4119,
      "step": 145
    },
    {
      "epoch": 2.5929203539823007,
      "grad_norm": 0.982158362865448,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.2026,
      "step": 146
    },
    {
      "epoch": 2.6106194690265485,
      "grad_norm": 1.264430046081543,
      "learning_rate": 5.012585797388936e-06,
      "loss": 0.312,
      "step": 147
    },
    {
      "epoch": 2.6283185840707963,
      "grad_norm": 1.0391494035720825,
      "learning_rate": 4.592841308745932e-06,
      "loss": 0.2517,
      "step": 148
    },
    {
      "epoch": 2.646017699115044,
      "grad_norm": 1.2044720649719238,
      "learning_rate": 4.190602144143207e-06,
      "loss": 0.2401,
      "step": 149
    },
    {
      "epoch": 2.663716814159292,
      "grad_norm": 1.0556868314743042,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.2354,
      "step": 150
    },
    {
      "epoch": 2.663716814159292,
      "eval_loss": 1.0171345472335815,
      "eval_runtime": 6.9871,
      "eval_samples_per_second": 13.597,
      "eval_steps_per_second": 3.435,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 170,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.018651406336e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}