{
  "best_metric": 1.1331982612609863,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03266372693124286,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016331863465621427,
      "grad_norm": 1.6851118803024292,
      "learning_rate": 1.002e-05,
      "loss": 1.0081,
      "step": 1
    },
    {
      "epoch": 0.00016331863465621427,
      "eval_loss": 1.9000940322875977,
      "eval_runtime": 344.5542,
      "eval_samples_per_second": 7.482,
      "eval_steps_per_second": 1.872,
      "step": 1
    },
    {
      "epoch": 0.00032663726931242854,
      "grad_norm": 2.2044219970703125,
      "learning_rate": 2.004e-05,
      "loss": 1.0249,
      "step": 2
    },
    {
      "epoch": 0.0004899559039686428,
      "grad_norm": 2.0698764324188232,
      "learning_rate": 3.0059999999999997e-05,
      "loss": 1.086,
      "step": 3
    },
    {
      "epoch": 0.0006532745386248571,
      "grad_norm": 2.0256564617156982,
      "learning_rate": 4.008e-05,
      "loss": 1.2085,
      "step": 4
    },
    {
      "epoch": 0.0008165931732810714,
      "grad_norm": 1.3296934366226196,
      "learning_rate": 5.01e-05,
      "loss": 0.9578,
      "step": 5
    },
    {
      "epoch": 0.0009799118079372856,
      "grad_norm": 1.1940107345581055,
      "learning_rate": 6.0119999999999994e-05,
      "loss": 1.0005,
      "step": 6
    },
    {
      "epoch": 0.0011432304425935,
      "grad_norm": 1.0048428773880005,
      "learning_rate": 7.013999999999999e-05,
      "loss": 1.0273,
      "step": 7
    },
    {
      "epoch": 0.0013065490772497142,
      "grad_norm": 0.9456784129142761,
      "learning_rate": 8.016e-05,
      "loss": 1.0385,
      "step": 8
    },
    {
      "epoch": 0.0014698677119059284,
      "grad_norm": 0.99244225025177,
      "learning_rate": 9.018e-05,
      "loss": 0.9732,
      "step": 9
    },
    {
      "epoch": 0.0016331863465621427,
      "grad_norm": 0.9175916314125061,
      "learning_rate": 0.0001002,
      "loss": 1.0126,
      "step": 10
    },
    {
      "epoch": 0.001796504981218357,
      "grad_norm": 0.9574170112609863,
      "learning_rate": 9.967263157894736e-05,
      "loss": 0.8922,
      "step": 11
    },
    {
      "epoch": 0.0019598236158745713,
      "grad_norm": 1.8157280683517456,
      "learning_rate": 9.914526315789473e-05,
      "loss": 0.9965,
      "step": 12
    },
    {
      "epoch": 0.0021231422505307855,
      "grad_norm": 0.8389182090759277,
      "learning_rate": 9.861789473684209e-05,
      "loss": 1.0657,
      "step": 13
    },
    {
      "epoch": 0.002286460885187,
      "grad_norm": 0.920594334602356,
      "learning_rate": 9.809052631578947e-05,
      "loss": 1.0575,
      "step": 14
    },
    {
      "epoch": 0.002449779519843214,
      "grad_norm": 0.9322181940078735,
      "learning_rate": 9.756315789473684e-05,
      "loss": 1.1032,
      "step": 15
    },
    {
      "epoch": 0.0026130981544994283,
      "grad_norm": 0.8384012579917908,
      "learning_rate": 9.70357894736842e-05,
      "loss": 1.0087,
      "step": 16
    },
    {
      "epoch": 0.0027764167891556426,
      "grad_norm": 0.8646233677864075,
      "learning_rate": 9.650842105263158e-05,
      "loss": 1.0182,
      "step": 17
    },
    {
      "epoch": 0.002939735423811857,
      "grad_norm": 1.0053048133850098,
      "learning_rate": 9.598105263157895e-05,
      "loss": 0.9359,
      "step": 18
    },
    {
      "epoch": 0.003103054058468071,
      "grad_norm": 0.8383069634437561,
      "learning_rate": 9.545368421052631e-05,
      "loss": 0.9231,
      "step": 19
    },
    {
      "epoch": 0.0032663726931242854,
      "grad_norm": 1.0205601453781128,
      "learning_rate": 9.492631578947368e-05,
      "loss": 1.0473,
      "step": 20
    },
    {
      "epoch": 0.0034296913277804997,
      "grad_norm": 1.1337229013442993,
      "learning_rate": 9.439894736842106e-05,
      "loss": 1.01,
      "step": 21
    },
    {
      "epoch": 0.003593009962436714,
      "grad_norm": 1.0072332620620728,
      "learning_rate": 9.387157894736842e-05,
      "loss": 1.094,
      "step": 22
    },
    {
      "epoch": 0.0037563285970929282,
      "grad_norm": 1.0758895874023438,
      "learning_rate": 9.334421052631579e-05,
      "loss": 1.2812,
      "step": 23
    },
    {
      "epoch": 0.0039196472317491425,
      "grad_norm": 1.0436909198760986,
      "learning_rate": 9.281684210526315e-05,
      "loss": 0.9926,
      "step": 24
    },
    {
      "epoch": 0.004082965866405357,
      "grad_norm": 1.1592437028884888,
      "learning_rate": 9.228947368421052e-05,
      "loss": 1.2151,
      "step": 25
    },
    {
      "epoch": 0.004246284501061571,
      "grad_norm": 1.1979281902313232,
      "learning_rate": 9.176210526315788e-05,
      "loss": 1.1807,
      "step": 26
    },
    {
      "epoch": 0.004409603135717786,
      "grad_norm": 1.2203060388565063,
      "learning_rate": 9.123473684210526e-05,
      "loss": 0.8416,
      "step": 27
    },
    {
      "epoch": 0.004572921770374,
      "grad_norm": 1.426841139793396,
      "learning_rate": 9.070736842105263e-05,
      "loss": 1.0486,
      "step": 28
    },
    {
      "epoch": 0.004736240405030214,
      "grad_norm": 3.254582643508911,
      "learning_rate": 9.018e-05,
      "loss": 1.1406,
      "step": 29
    },
    {
      "epoch": 0.004899559039686428,
      "grad_norm": 1.349916696548462,
      "learning_rate": 8.965263157894736e-05,
      "loss": 0.9975,
      "step": 30
    },
    {
      "epoch": 0.005062877674342643,
      "grad_norm": 1.5444021224975586,
      "learning_rate": 8.912526315789474e-05,
      "loss": 1.2578,
      "step": 31
    },
    {
      "epoch": 0.005226196308998857,
      "grad_norm": 1.5829365253448486,
      "learning_rate": 8.85978947368421e-05,
      "loss": 1.016,
      "step": 32
    },
    {
      "epoch": 0.005389514943655071,
      "grad_norm": 1.857584834098816,
      "learning_rate": 8.807052631578947e-05,
      "loss": 0.9408,
      "step": 33
    },
    {
      "epoch": 0.005552833578311285,
      "grad_norm": 1.739058256149292,
      "learning_rate": 8.754315789473685e-05,
      "loss": 1.055,
      "step": 34
    },
    {
      "epoch": 0.0057161522129675,
      "grad_norm": 2.821774482727051,
      "learning_rate": 8.701578947368421e-05,
      "loss": 1.3456,
      "step": 35
    },
    {
      "epoch": 0.005879470847623714,
      "grad_norm": 2.193387508392334,
      "learning_rate": 8.648842105263158e-05,
      "loss": 1.2526,
      "step": 36
    },
    {
      "epoch": 0.0060427894822799285,
      "grad_norm": 2.5872952938079834,
      "learning_rate": 8.596105263157894e-05,
      "loss": 1.4246,
      "step": 37
    },
    {
      "epoch": 0.006206108116936142,
      "grad_norm": 2.5345852375030518,
      "learning_rate": 8.543368421052631e-05,
      "loss": 1.2144,
      "step": 38
    },
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 3.2303738594055176,
      "learning_rate": 8.490631578947368e-05,
      "loss": 1.0199,
      "step": 39
    },
    {
      "epoch": 0.006532745386248571,
      "grad_norm": 4.121665000915527,
      "learning_rate": 8.437894736842104e-05,
      "loss": 1.6419,
      "step": 40
    },
    {
      "epoch": 0.0066960640209047856,
      "grad_norm": 4.449281692504883,
      "learning_rate": 8.385157894736842e-05,
      "loss": 1.7489,
      "step": 41
    },
    {
      "epoch": 0.006859382655560999,
      "grad_norm": 3.9495317935943604,
      "learning_rate": 8.332421052631579e-05,
      "loss": 1.5623,
      "step": 42
    },
    {
      "epoch": 0.007022701290217214,
      "grad_norm": 2.803144931793213,
      "learning_rate": 8.279684210526315e-05,
      "loss": 1.1089,
      "step": 43
    },
    {
      "epoch": 0.007186019924873428,
      "grad_norm": 4.1833038330078125,
      "learning_rate": 8.226947368421053e-05,
      "loss": 1.6404,
      "step": 44
    },
    {
      "epoch": 0.007349338559529643,
      "grad_norm": 4.866119861602783,
      "learning_rate": 8.17421052631579e-05,
      "loss": 1.314,
      "step": 45
    },
    {
      "epoch": 0.0075126571941858565,
      "grad_norm": 4.199403285980225,
      "learning_rate": 8.121473684210526e-05,
      "loss": 1.661,
      "step": 46
    },
    {
      "epoch": 0.007675975828842071,
      "grad_norm": 3.925476551055908,
      "learning_rate": 8.068736842105263e-05,
      "loss": 1.4702,
      "step": 47
    },
    {
      "epoch": 0.007839294463498285,
      "grad_norm": 4.335568428039551,
      "learning_rate": 8.016e-05,
      "loss": 2.0748,
      "step": 48
    },
    {
      "epoch": 0.008002613098154499,
      "grad_norm": 6.924542427062988,
      "learning_rate": 7.963263157894737e-05,
      "loss": 2.0374,
      "step": 49
    },
    {
      "epoch": 0.008165931732810714,
      "grad_norm": 13.009639739990234,
      "learning_rate": 7.910526315789474e-05,
      "loss": 3.4481,
      "step": 50
    },
    {
      "epoch": 0.008165931732810714,
      "eval_loss": 1.2892735004425049,
      "eval_runtime": 344.1613,
      "eval_samples_per_second": 7.491,
      "eval_steps_per_second": 1.874,
      "step": 50
    },
    {
      "epoch": 0.008329250367466928,
      "grad_norm": 1.8733032941818237,
      "learning_rate": 7.85778947368421e-05,
      "loss": 0.91,
      "step": 51
    },
    {
      "epoch": 0.008492569002123142,
      "grad_norm": 1.351426124572754,
      "learning_rate": 7.805052631578947e-05,
      "loss": 1.0789,
      "step": 52
    },
    {
      "epoch": 0.008655887636779356,
      "grad_norm": 0.9720818400382996,
      "learning_rate": 7.752315789473683e-05,
      "loss": 0.9113,
      "step": 53
    },
    {
      "epoch": 0.008819206271435572,
      "grad_norm": 0.7470458745956421,
      "learning_rate": 7.69957894736842e-05,
      "loss": 0.917,
      "step": 54
    },
    {
      "epoch": 0.008982524906091785,
      "grad_norm": 0.6289156079292297,
      "learning_rate": 7.646842105263158e-05,
      "loss": 0.8513,
      "step": 55
    },
    {
      "epoch": 0.009145843540748,
      "grad_norm": 0.6980412006378174,
      "learning_rate": 7.594105263157894e-05,
      "loss": 1.036,
      "step": 56
    },
    {
      "epoch": 0.009309162175404213,
      "grad_norm": 0.6612934470176697,
      "learning_rate": 7.541368421052631e-05,
      "loss": 0.9251,
      "step": 57
    },
    {
      "epoch": 0.009472480810060429,
      "grad_norm": 0.6878615021705627,
      "learning_rate": 7.488631578947369e-05,
      "loss": 0.8502,
      "step": 58
    },
    {
      "epoch": 0.009635799444716642,
      "grad_norm": 0.7292014360427856,
      "learning_rate": 7.435894736842105e-05,
      "loss": 0.9259,
      "step": 59
    },
    {
      "epoch": 0.009799118079372856,
      "grad_norm": 0.7414498329162598,
      "learning_rate": 7.383157894736842e-05,
      "loss": 0.9209,
      "step": 60
    },
    {
      "epoch": 0.00996243671402907,
      "grad_norm": 0.7968541383743286,
      "learning_rate": 7.33042105263158e-05,
      "loss": 1.006,
      "step": 61
    },
    {
      "epoch": 0.010125755348685286,
      "grad_norm": 0.7785654067993164,
      "learning_rate": 7.277684210526316e-05,
      "loss": 0.998,
      "step": 62
    },
    {
      "epoch": 0.0102890739833415,
      "grad_norm": 0.7336849570274353,
      "learning_rate": 7.224947368421053e-05,
      "loss": 0.9043,
      "step": 63
    },
    {
      "epoch": 0.010452392617997713,
      "grad_norm": 0.6646738648414612,
      "learning_rate": 7.172210526315789e-05,
      "loss": 0.8958,
      "step": 64
    },
    {
      "epoch": 0.010615711252653927,
      "grad_norm": 0.8088564872741699,
      "learning_rate": 7.119473684210526e-05,
      "loss": 1.0874,
      "step": 65
    },
    {
      "epoch": 0.010779029887310143,
      "grad_norm": 0.7672606706619263,
      "learning_rate": 7.066736842105262e-05,
      "loss": 0.9482,
      "step": 66
    },
    {
      "epoch": 0.010942348521966357,
      "grad_norm": 0.9228386878967285,
      "learning_rate": 7.013999999999999e-05,
      "loss": 1.1435,
      "step": 67
    },
    {
      "epoch": 0.01110566715662257,
      "grad_norm": 0.8074588179588318,
      "learning_rate": 6.961263157894737e-05,
      "loss": 1.1595,
      "step": 68
    },
    {
      "epoch": 0.011268985791278784,
      "grad_norm": 0.7998431324958801,
      "learning_rate": 6.908526315789473e-05,
      "loss": 0.9535,
      "step": 69
    },
    {
      "epoch": 0.011432304425935,
      "grad_norm": 0.8504302501678467,
      "learning_rate": 6.85578947368421e-05,
      "loss": 1.0123,
      "step": 70
    },
    {
      "epoch": 0.011595623060591214,
      "grad_norm": 1.089838981628418,
      "learning_rate": 6.803052631578946e-05,
      "loss": 1.0045,
      "step": 71
    },
    {
      "epoch": 0.011758941695247428,
      "grad_norm": 0.89869225025177,
      "learning_rate": 6.750315789473684e-05,
      "loss": 0.7452,
      "step": 72
    },
    {
      "epoch": 0.011922260329903641,
      "grad_norm": 0.943939745426178,
      "learning_rate": 6.697578947368421e-05,
      "loss": 0.9891,
      "step": 73
    },
    {
      "epoch": 0.012085578964559857,
      "grad_norm": 0.9160717725753784,
      "learning_rate": 6.644842105263157e-05,
      "loss": 0.9342,
      "step": 74
    },
    {
      "epoch": 0.01224889759921607,
      "grad_norm": 1.082808256149292,
      "learning_rate": 6.592105263157895e-05,
      "loss": 0.8208,
      "step": 75
    },
    {
      "epoch": 0.012412216233872285,
      "grad_norm": 1.2106088399887085,
      "learning_rate": 6.539368421052632e-05,
      "loss": 1.2033,
      "step": 76
    },
    {
      "epoch": 0.012575534868528498,
      "grad_norm": 1.1063079833984375,
      "learning_rate": 6.486631578947368e-05,
      "loss": 0.9361,
      "step": 77
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 1.1758522987365723,
      "learning_rate": 6.433894736842105e-05,
      "loss": 0.8596,
      "step": 78
    },
    {
      "epoch": 0.012902172137840928,
      "grad_norm": 1.644689679145813,
      "learning_rate": 6.381157894736842e-05,
      "loss": 0.9575,
      "step": 79
    },
    {
      "epoch": 0.013065490772497142,
      "grad_norm": 1.4819023609161377,
      "learning_rate": 6.328421052631578e-05,
      "loss": 1.0894,
      "step": 80
    },
    {
      "epoch": 0.013228809407153356,
      "grad_norm": 1.3677387237548828,
      "learning_rate": 6.275684210526315e-05,
      "loss": 1.1177,
      "step": 81
    },
    {
      "epoch": 0.013392128041809571,
      "grad_norm": 2.352775812149048,
      "learning_rate": 6.222947368421053e-05,
      "loss": 1.5418,
      "step": 82
    },
    {
      "epoch": 0.013555446676465785,
      "grad_norm": 3.2826321125030518,
      "learning_rate": 6.170210526315789e-05,
      "loss": 1.056,
      "step": 83
    },
    {
      "epoch": 0.013718765311121999,
      "grad_norm": 1.8273366689682007,
      "learning_rate": 6.117473684210526e-05,
      "loss": 1.4655,
      "step": 84
    },
    {
      "epoch": 0.013882083945778213,
      "grad_norm": 3.2411186695098877,
      "learning_rate": 6.064736842105263e-05,
      "loss": 1.4192,
      "step": 85
    },
    {
      "epoch": 0.014045402580434428,
      "grad_norm": 1.9905811548233032,
      "learning_rate": 6.0119999999999994e-05,
      "loss": 1.3103,
      "step": 86
    },
    {
      "epoch": 0.014208721215090642,
      "grad_norm": 1.930762529373169,
      "learning_rate": 5.959263157894736e-05,
      "loss": 0.9912,
      "step": 87
    },
    {
      "epoch": 0.014372039849746856,
      "grad_norm": 2.365586280822754,
      "learning_rate": 5.906526315789473e-05,
      "loss": 1.1073,
      "step": 88
    },
    {
      "epoch": 0.01453535848440307,
      "grad_norm": 2.24143648147583,
      "learning_rate": 5.853789473684211e-05,
      "loss": 1.1891,
      "step": 89
    },
    {
      "epoch": 0.014698677119059285,
      "grad_norm": 2.7449162006378174,
      "learning_rate": 5.8010526315789476e-05,
      "loss": 1.3695,
      "step": 90
    },
    {
      "epoch": 0.014861995753715499,
      "grad_norm": 3.0811843872070312,
      "learning_rate": 5.748315789473684e-05,
      "loss": 0.7728,
      "step": 91
    },
    {
      "epoch": 0.015025314388371713,
      "grad_norm": 2.499147891998291,
      "learning_rate": 5.6955789473684207e-05,
      "loss": 1.2178,
      "step": 92
    },
    {
      "epoch": 0.015188633023027927,
      "grad_norm": 3.266294240951538,
      "learning_rate": 5.642842105263157e-05,
      "loss": 1.3692,
      "step": 93
    },
    {
      "epoch": 0.015351951657684142,
      "grad_norm": 3.7990870475769043,
      "learning_rate": 5.5901052631578944e-05,
      "loss": 1.5496,
      "step": 94
    },
    {
      "epoch": 0.015515270292340356,
      "grad_norm": 2.9418234825134277,
      "learning_rate": 5.5373684210526316e-05,
      "loss": 1.4258,
      "step": 95
    },
    {
      "epoch": 0.01567858892699657,
      "grad_norm": 3.900726795196533,
      "learning_rate": 5.484631578947369e-05,
      "loss": 1.4664,
      "step": 96
    },
    {
      "epoch": 0.015841907561652786,
      "grad_norm": 3.98392391204834,
      "learning_rate": 5.4318947368421054e-05,
      "loss": 2.07,
      "step": 97
    },
    {
      "epoch": 0.016005226196308998,
      "grad_norm": 4.655868053436279,
      "learning_rate": 5.379157894736842e-05,
      "loss": 1.5402,
      "step": 98
    },
    {
      "epoch": 0.016168544830965213,
      "grad_norm": 5.109676837921143,
      "learning_rate": 5.3264210526315785e-05,
      "loss": 1.723,
      "step": 99
    },
    {
      "epoch": 0.01633186346562143,
      "grad_norm": 7.739476680755615,
      "learning_rate": 5.273684210526315e-05,
      "loss": 2.4745,
      "step": 100
    },
    {
      "epoch": 0.01633186346562143,
      "eval_loss": 1.202304482460022,
      "eval_runtime": 344.5693,
      "eval_samples_per_second": 7.482,
      "eval_steps_per_second": 1.872,
      "step": 100
    },
    {
      "epoch": 0.01649518210027764,
      "grad_norm": 0.7410888671875,
      "learning_rate": 5.220947368421052e-05,
      "loss": 0.7999,
      "step": 101
    },
    {
      "epoch": 0.016658500734933857,
      "grad_norm": 0.7798357605934143,
      "learning_rate": 5.1682105263157895e-05,
      "loss": 0.932,
      "step": 102
    },
    {
      "epoch": 0.01682181936959007,
      "grad_norm": 0.7108080983161926,
      "learning_rate": 5.115473684210527e-05,
      "loss": 0.9403,
      "step": 103
    },
    {
      "epoch": 0.016985138004246284,
      "grad_norm": 0.7301442623138428,
      "learning_rate": 5.062736842105263e-05,
      "loss": 0.8655,
      "step": 104
    },
    {
      "epoch": 0.0171484566389025,
      "grad_norm": 0.6835742592811584,
      "learning_rate": 5.01e-05,
      "loss": 0.8765,
      "step": 105
    },
    {
      "epoch": 0.017311775273558712,
      "grad_norm": 0.6745396256446838,
      "learning_rate": 4.9572631578947363e-05,
      "loss": 0.9458,
      "step": 106
    },
    {
      "epoch": 0.017475093908214927,
      "grad_norm": 0.6688428521156311,
      "learning_rate": 4.9045263157894736e-05,
      "loss": 0.8976,
      "step": 107
    },
    {
      "epoch": 0.017638412542871143,
      "grad_norm": 0.6025101542472839,
      "learning_rate": 4.85178947368421e-05,
      "loss": 1.007,
      "step": 108
    },
    {
      "epoch": 0.017801731177527355,
      "grad_norm": 0.5355660319328308,
      "learning_rate": 4.799052631578947e-05,
      "loss": 0.893,
      "step": 109
    },
    {
      "epoch": 0.01796504981218357,
      "grad_norm": 0.6081918478012085,
      "learning_rate": 4.746315789473684e-05,
      "loss": 1.0356,
      "step": 110
    },
    {
      "epoch": 0.018128368446839783,
      "grad_norm": 0.6432203650474548,
      "learning_rate": 4.693578947368421e-05,
      "loss": 1.0259,
      "step": 111
    },
    {
      "epoch": 0.018291687081496,
      "grad_norm": 0.6371332406997681,
      "learning_rate": 4.6408421052631576e-05,
      "loss": 0.9714,
      "step": 112
    },
    {
      "epoch": 0.018455005716152214,
      "grad_norm": 0.632469117641449,
      "learning_rate": 4.588105263157894e-05,
      "loss": 0.7899,
      "step": 113
    },
    {
      "epoch": 0.018618324350808426,
      "grad_norm": 0.6865615248680115,
      "learning_rate": 4.5353684210526314e-05,
      "loss": 1.0136,
      "step": 114
    },
    {
      "epoch": 0.01878164298546464,
      "grad_norm": 0.735899031162262,
      "learning_rate": 4.482631578947368e-05,
      "loss": 0.9631,
      "step": 115
    },
    {
      "epoch": 0.018944961620120857,
      "grad_norm": 0.7938647270202637,
      "learning_rate": 4.429894736842105e-05,
      "loss": 1.0312,
      "step": 116
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": 0.7992541790008545,
      "learning_rate": 4.3771578947368424e-05,
      "loss": 1.1253,
      "step": 117
    },
    {
      "epoch": 0.019271598889433285,
      "grad_norm": 0.7731001377105713,
      "learning_rate": 4.324421052631579e-05,
      "loss": 1.1413,
      "step": 118
    },
    {
      "epoch": 0.019434917524089497,
      "grad_norm": 0.8240691423416138,
      "learning_rate": 4.2716842105263155e-05,
      "loss": 0.9722,
      "step": 119
    },
    {
      "epoch": 0.019598236158745713,
      "grad_norm": 0.7312250733375549,
      "learning_rate": 4.218947368421052e-05,
      "loss": 0.8119,
      "step": 120
    },
    {
      "epoch": 0.019761554793401928,
      "grad_norm": 0.8575920462608337,
      "learning_rate": 4.166210526315789e-05,
      "loss": 0.9616,
      "step": 121
    },
    {
      "epoch": 0.01992487342805814,
      "grad_norm": 0.8943201899528503,
      "learning_rate": 4.1134736842105265e-05,
      "loss": 0.9458,
      "step": 122
    },
    {
      "epoch": 0.020088192062714356,
      "grad_norm": 0.7860243916511536,
      "learning_rate": 4.060736842105263e-05,
      "loss": 1.006,
      "step": 123
    },
    {
      "epoch": 0.02025151069737057,
      "grad_norm": 0.9303942918777466,
      "learning_rate": 4.008e-05,
      "loss": 0.9787,
      "step": 124
    },
    {
      "epoch": 0.020414829332026783,
      "grad_norm": 1.0351006984710693,
      "learning_rate": 3.955263157894737e-05,
      "loss": 1.1954,
      "step": 125
    },
    {
      "epoch": 0.020578147966683,
      "grad_norm": 0.9931172728538513,
      "learning_rate": 3.9025263157894733e-05,
      "loss": 0.9572,
      "step": 126
    },
    {
      "epoch": 0.02074146660133921,
      "grad_norm": 1.0373263359069824,
      "learning_rate": 3.84978947368421e-05,
      "loss": 0.9803,
      "step": 127
    },
    {
      "epoch": 0.020904785235995427,
      "grad_norm": 1.018931269645691,
      "learning_rate": 3.797052631578947e-05,
      "loss": 0.69,
      "step": 128
    },
    {
      "epoch": 0.021068103870651642,
      "grad_norm": 1.324196696281433,
      "learning_rate": 3.744315789473684e-05,
      "loss": 1.0059,
      "step": 129
    },
    {
      "epoch": 0.021231422505307854,
      "grad_norm": 1.19536554813385,
      "learning_rate": 3.691578947368421e-05,
      "loss": 0.9141,
      "step": 130
    },
    {
      "epoch": 0.02139474113996407,
      "grad_norm": 1.2916719913482666,
      "learning_rate": 3.638842105263158e-05,
      "loss": 1.0181,
      "step": 131
    },
    {
      "epoch": 0.021558059774620286,
      "grad_norm": 1.313924789428711,
      "learning_rate": 3.5861052631578946e-05,
      "loss": 1.0114,
      "step": 132
    },
    {
      "epoch": 0.021721378409276498,
      "grad_norm": 1.6728382110595703,
      "learning_rate": 3.533368421052631e-05,
      "loss": 1.151,
      "step": 133
    },
    {
      "epoch": 0.021884697043932713,
      "grad_norm": 1.9813265800476074,
      "learning_rate": 3.4806315789473684e-05,
      "loss": 1.209,
      "step": 134
    },
    {
      "epoch": 0.022048015678588925,
      "grad_norm": 2.619920015335083,
      "learning_rate": 3.427894736842105e-05,
      "loss": 1.4013,
      "step": 135
    },
    {
      "epoch": 0.02221133431324514,
      "grad_norm": 3.543386936187744,
      "learning_rate": 3.375157894736842e-05,
      "loss": 1.2687,
      "step": 136
    },
    {
      "epoch": 0.022374652947901356,
      "grad_norm": 2.107569932937622,
      "learning_rate": 3.322421052631579e-05,
      "loss": 1.1479,
      "step": 137
    },
    {
      "epoch": 0.02253797158255757,
      "grad_norm": 2.548245429992676,
      "learning_rate": 3.269684210526316e-05,
      "loss": 1.1627,
      "step": 138
    },
    {
      "epoch": 0.022701290217213784,
      "grad_norm": 3.172882556915283,
      "learning_rate": 3.2169473684210525e-05,
      "loss": 1.4478,
      "step": 139
    },
    {
      "epoch": 0.02286460885187,
      "grad_norm": 3.1833114624023438,
      "learning_rate": 3.164210526315789e-05,
      "loss": 1.4387,
      "step": 140
    },
    {
      "epoch": 0.023027927486526212,
      "grad_norm": 3.0594396591186523,
      "learning_rate": 3.111473684210526e-05,
      "loss": 0.975,
      "step": 141
    },
    {
      "epoch": 0.023191246121182427,
      "grad_norm": 3.2839081287384033,
      "learning_rate": 3.058736842105263e-05,
      "loss": 1.3071,
      "step": 142
    },
    {
      "epoch": 0.02335456475583864,
      "grad_norm": 4.123104095458984,
      "learning_rate": 3.0059999999999997e-05,
      "loss": 1.6883,
      "step": 143
    },
    {
      "epoch": 0.023517883390494855,
      "grad_norm": 3.278013229370117,
      "learning_rate": 2.9532631578947366e-05,
      "loss": 1.5988,
      "step": 144
    },
    {
      "epoch": 0.02368120202515107,
      "grad_norm": 2.856154680252075,
      "learning_rate": 2.9005263157894738e-05,
      "loss": 0.9376,
      "step": 145
    },
    {
      "epoch": 0.023844520659807283,
      "grad_norm": 3.468996524810791,
      "learning_rate": 2.8477894736842103e-05,
      "loss": 1.8904,
      "step": 146
    },
    {
      "epoch": 0.0240078392944635,
      "grad_norm": 3.6459338665008545,
      "learning_rate": 2.7950526315789472e-05,
      "loss": 1.1922,
      "step": 147
    },
    {
      "epoch": 0.024171157929119714,
      "grad_norm": 4.6464948654174805,
      "learning_rate": 2.7423157894736844e-05,
      "loss": 2.2418,
      "step": 148
    },
    {
      "epoch": 0.024334476563775926,
      "grad_norm": 6.070025444030762,
      "learning_rate": 2.689578947368421e-05,
      "loss": 2.1127,
      "step": 149
    },
    {
      "epoch": 0.02449779519843214,
      "grad_norm": 11.722772598266602,
      "learning_rate": 2.6368421052631575e-05,
      "loss": 2.0128,
      "step": 150
    },
    {
      "epoch": 0.02449779519843214,
      "eval_loss": 1.1496460437774658,
      "eval_runtime": 344.5868,
      "eval_samples_per_second": 7.481,
      "eval_steps_per_second": 1.872,
      "step": 150
    },
    {
      "epoch": 0.024661113833088357,
      "grad_norm": 0.5295467972755432,
      "learning_rate": 2.5841052631578947e-05,
      "loss": 0.9102,
      "step": 151
    },
    {
      "epoch": 0.02482443246774457,
      "grad_norm": 0.42944419384002686,
      "learning_rate": 2.5313684210526316e-05,
      "loss": 0.7221,
      "step": 152
    },
    {
      "epoch": 0.024987751102400785,
      "grad_norm": 0.4469304084777832,
      "learning_rate": 2.4786315789473682e-05,
      "loss": 0.7679,
      "step": 153
    },
    {
      "epoch": 0.025151069737056997,
      "grad_norm": 0.6193202137947083,
      "learning_rate": 2.425894736842105e-05,
      "loss": 0.9083,
      "step": 154
    },
    {
      "epoch": 0.025314388371713212,
      "grad_norm": 0.5847591161727905,
      "learning_rate": 2.373157894736842e-05,
      "loss": 0.72,
      "step": 155
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.5906417965888977,
      "learning_rate": 2.3204210526315788e-05,
      "loss": 0.9138,
      "step": 156
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.4926919639110565,
      "learning_rate": 2.2676842105263157e-05,
      "loss": 0.9187,
      "step": 157
    },
    {
      "epoch": 0.025804344275681856,
      "grad_norm": 0.5422658920288086,
      "learning_rate": 2.2149473684210526e-05,
      "loss": 1.0084,
      "step": 158
    },
    {
      "epoch": 0.02596766291033807,
      "grad_norm": 0.5664920210838318,
      "learning_rate": 2.1622105263157895e-05,
      "loss": 0.9221,
      "step": 159
    },
    {
      "epoch": 0.026130981544994283,
      "grad_norm": 0.5593885779380798,
      "learning_rate": 2.109473684210526e-05,
      "loss": 0.8757,
      "step": 160
    },
    {
      "epoch": 0.0262943001796505,
      "grad_norm": 0.6178870797157288,
      "learning_rate": 2.0567368421052632e-05,
      "loss": 1.0018,
      "step": 161
    },
    {
      "epoch": 0.02645761881430671,
      "grad_norm": 0.5820048451423645,
      "learning_rate": 2.004e-05,
      "loss": 0.8186,
      "step": 162
    },
    {
      "epoch": 0.026620937448962927,
      "grad_norm": 0.606930673122406,
      "learning_rate": 1.9512631578947367e-05,
      "loss": 0.915,
      "step": 163
    },
    {
      "epoch": 0.026784256083619142,
      "grad_norm": 0.5813213586807251,
      "learning_rate": 1.8985263157894736e-05,
      "loss": 0.8943,
      "step": 164
    },
    {
      "epoch": 0.026947574718275354,
      "grad_norm": 0.7827402949333191,
      "learning_rate": 1.8457894736842104e-05,
      "loss": 0.6757,
      "step": 165
    },
    {
      "epoch": 0.02711089335293157,
      "grad_norm": 0.7083070874214172,
      "learning_rate": 1.7930526315789473e-05,
      "loss": 0.797,
      "step": 166
    },
    {
      "epoch": 0.027274211987587785,
      "grad_norm": 0.6508756875991821,
      "learning_rate": 1.7403157894736842e-05,
      "loss": 0.98,
      "step": 167
    },
    {
      "epoch": 0.027437530622243998,
      "grad_norm": 0.681760847568512,
      "learning_rate": 1.687578947368421e-05,
      "loss": 0.8936,
      "step": 168
    },
    {
      "epoch": 0.027600849256900213,
      "grad_norm": 0.7164104580879211,
      "learning_rate": 1.634842105263158e-05,
      "loss": 0.866,
      "step": 169
    },
    {
      "epoch": 0.027764167891556425,
      "grad_norm": 0.8126941919326782,
      "learning_rate": 1.5821052631578945e-05,
      "loss": 0.8797,
      "step": 170
    },
    {
      "epoch": 0.02792748652621264,
      "grad_norm": 0.7941915988922119,
      "learning_rate": 1.5293684210526314e-05,
      "loss": 1.0358,
      "step": 171
    },
    {
      "epoch": 0.028090805160868856,
      "grad_norm": 0.9106842875480652,
      "learning_rate": 1.4766315789473683e-05,
      "loss": 1.0669,
      "step": 172
    },
    {
      "epoch": 0.02825412379552507,
      "grad_norm": 0.9008748531341553,
      "learning_rate": 1.4238947368421052e-05,
      "loss": 1.0582,
      "step": 173
    },
    {
      "epoch": 0.028417442430181284,
      "grad_norm": 0.916495144367218,
      "learning_rate": 1.3711578947368422e-05,
      "loss": 0.7787,
      "step": 174
    },
    {
      "epoch": 0.0285807610648375,
      "grad_norm": 0.9486830234527588,
      "learning_rate": 1.3184210526315788e-05,
      "loss": 0.9648,
      "step": 175
    },
    {
      "epoch": 0.02874407969949371,
      "grad_norm": 0.975587785243988,
      "learning_rate": 1.2656842105263158e-05,
      "loss": 0.9214,
      "step": 176
    },
    {
      "epoch": 0.028907398334149927,
      "grad_norm": 1.2781733274459839,
      "learning_rate": 1.2129473684210525e-05,
      "loss": 1.2543,
      "step": 177
    },
    {
      "epoch": 0.02907071696880614,
      "grad_norm": 1.1123965978622437,
      "learning_rate": 1.1602105263157894e-05,
      "loss": 0.9457,
      "step": 178
    },
    {
      "epoch": 0.029234035603462355,
      "grad_norm": 1.0323660373687744,
      "learning_rate": 1.1074736842105263e-05,
      "loss": 0.8505,
      "step": 179
    },
    {
      "epoch": 0.02939735423811857,
      "grad_norm": 1.3954451084136963,
      "learning_rate": 1.054736842105263e-05,
      "loss": 1.1639,
      "step": 180
    },
    {
      "epoch": 0.029560672872774783,
      "grad_norm": 1.4453262090682983,
      "learning_rate": 1.002e-05,
      "loss": 1.1046,
      "step": 181
    },
    {
      "epoch": 0.029723991507430998,
      "grad_norm": 1.371714472770691,
      "learning_rate": 9.492631578947368e-06,
      "loss": 1.1104,
      "step": 182
    },
    {
      "epoch": 0.029887310142087214,
      "grad_norm": 1.7723652124404907,
      "learning_rate": 8.965263157894737e-06,
      "loss": 1.1258,
      "step": 183
    },
    {
      "epoch": 0.030050628776743426,
      "grad_norm": 1.6344342231750488,
      "learning_rate": 8.437894736842105e-06,
      "loss": 1.1028,
      "step": 184
    },
    {
      "epoch": 0.03021394741139964,
      "grad_norm": 2.0994627475738525,
      "learning_rate": 7.910526315789473e-06,
      "loss": 1.0568,
      "step": 185
    },
    {
      "epoch": 0.030377266046055854,
      "grad_norm": 2.0363705158233643,
      "learning_rate": 7.383157894736841e-06,
      "loss": 1.5804,
      "step": 186
    },
    {
      "epoch": 0.03054058468071207,
      "grad_norm": 2.4229798316955566,
      "learning_rate": 6.855789473684211e-06,
      "loss": 1.1893,
      "step": 187
    },
    {
      "epoch": 0.030703903315368285,
      "grad_norm": 3.015899181365967,
      "learning_rate": 6.328421052631579e-06,
      "loss": 1.2766,
      "step": 188
    },
    {
      "epoch": 0.030867221950024497,
      "grad_norm": 2.2767412662506104,
      "learning_rate": 5.801052631578947e-06,
      "loss": 1.22,
      "step": 189
    },
    {
      "epoch": 0.031030540584680712,
      "grad_norm": 3.660109758377075,
      "learning_rate": 5.273684210526315e-06,
      "loss": 1.2292,
      "step": 190
    },
    {
      "epoch": 0.031193859219336928,
      "grad_norm": 4.029131889343262,
      "learning_rate": 4.746315789473684e-06,
      "loss": 1.7373,
      "step": 191
    },
    {
      "epoch": 0.03135717785399314,
      "grad_norm": 3.336766242980957,
      "learning_rate": 4.218947368421053e-06,
      "loss": 1.44,
      "step": 192
    },
    {
      "epoch": 0.03152049648864935,
      "grad_norm": 3.1067514419555664,
      "learning_rate": 3.6915789473684207e-06,
      "loss": 1.512,
      "step": 193
    },
    {
      "epoch": 0.03168381512330557,
      "grad_norm": 3.971158981323242,
      "learning_rate": 3.1642105263157895e-06,
      "loss": 1.5966,
      "step": 194
    },
    {
      "epoch": 0.03184713375796178,
      "grad_norm": 2.507552146911621,
      "learning_rate": 2.6368421052631575e-06,
      "loss": 1.0217,
      "step": 195
    },
    {
      "epoch": 0.032010452392617995,
      "grad_norm": 3.831817865371704,
      "learning_rate": 2.1094736842105264e-06,
      "loss": 0.9842,
      "step": 196
    },
    {
      "epoch": 0.032173771027274214,
      "grad_norm": 5.005215167999268,
      "learning_rate": 1.5821052631578948e-06,
      "loss": 2.8562,
      "step": 197
    },
    {
      "epoch": 0.03233708966193043,
      "grad_norm": 4.721521377563477,
      "learning_rate": 1.0547368421052632e-06,
      "loss": 2.4518,
      "step": 198
    },
    {
      "epoch": 0.03250040829658664,
      "grad_norm": 5.0478363037109375,
      "learning_rate": 5.273684210526316e-07,
      "loss": 2.0353,
      "step": 199
    },
    {
      "epoch": 0.03266372693124286,
      "grad_norm": 6.368497371673584,
      "learning_rate": 0.0,
      "loss": 1.6937,
      "step": 200
    },
    {
      "epoch": 0.03266372693124286,
      "eval_loss": 1.1331982612609863,
      "eval_runtime": 344.2422,
      "eval_samples_per_second": 7.489,
      "eval_steps_per_second": 1.874,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": 8.65769979075625e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}