{
  "best_metric": 0.04876178875565529,
  "best_model_checkpoint": "/content/train/Qwen2-VL-7B-Instruct-unsloth-r4-rslora-bf16-tuned/checkpoint-220",
  "epoch": 1.6629001883239172,
  "eval_steps": 10,
  "global_step": 220,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007532956685499058,
      "grad_norm": 0.29860490560531616,
      "learning_rate": 1e-05,
      "loss": 1.462,
      "step": 1
    },
    {
      "epoch": 0.015065913370998116,
      "grad_norm": 0.5057499408721924,
      "learning_rate": 2e-05,
      "loss": 1.5835,
      "step": 2
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 0.32325854897499084,
      "learning_rate": 3e-05,
      "loss": 1.4388,
      "step": 3
    },
    {
      "epoch": 0.030131826741996232,
      "grad_norm": 0.357746422290802,
      "learning_rate": 4e-05,
      "loss": 1.5551,
      "step": 4
    },
    {
      "epoch": 0.03766478342749529,
      "grad_norm": 0.6203590035438538,
      "learning_rate": 5e-05,
      "loss": 1.6868,
      "step": 5
    },
    {
      "epoch": 0.04519774011299435,
      "grad_norm": 0.3148535192012787,
      "learning_rate": 6e-05,
      "loss": 1.2584,
      "step": 6
    },
    {
      "epoch": 0.05273069679849341,
      "grad_norm": 0.8858975768089294,
      "learning_rate": 7e-05,
      "loss": 1.4839,
      "step": 7
    },
    {
      "epoch": 0.060263653483992465,
      "grad_norm": 0.41307175159454346,
      "learning_rate": 8e-05,
      "loss": 1.465,
      "step": 8
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 0.711910605430603,
      "learning_rate": 9e-05,
      "loss": 1.4146,
      "step": 9
    },
    {
      "epoch": 0.07532956685499058,
      "grad_norm": 0.6907219886779785,
      "learning_rate": 0.0001,
      "loss": 1.5244,
      "step": 10
    },
    {
      "epoch": 0.07532956685499058,
      "eval_loss": 1.4021275043487549,
      "eval_runtime": 60.9671,
      "eval_samples_per_second": 1.23,
      "eval_steps_per_second": 0.623,
      "step": 10
    },
    {
      "epoch": 0.08286252354048965,
      "grad_norm": 0.6071083545684814,
      "learning_rate": 9.999834399079165e-05,
      "loss": 1.5861,
      "step": 11
    },
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 0.4335213601589203,
      "learning_rate": 9.99933760728612e-05,
      "loss": 1.3366,
      "step": 12
    },
    {
      "epoch": 0.09792843691148775,
      "grad_norm": 0.43898504972457886,
      "learning_rate": 9.99850965752854e-05,
      "loss": 1.2906,
      "step": 13
    },
    {
      "epoch": 0.10546139359698682,
      "grad_norm": 0.400079607963562,
      "learning_rate": 9.997350604650123e-05,
      "loss": 1.2677,
      "step": 14
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 0.41405242681503296,
      "learning_rate": 9.995860525426954e-05,
      "loss": 1.285,
      "step": 15
    },
    {
      "epoch": 0.12052730696798493,
      "grad_norm": 0.7896008491516113,
      "learning_rate": 9.994039518562432e-05,
      "loss": 1.1366,
      "step": 16
    },
    {
      "epoch": 0.128060263653484,
      "grad_norm": 0.45816895365715027,
      "learning_rate": 9.991887704680724e-05,
      "loss": 1.2656,
      "step": 17
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.5465638637542725,
      "learning_rate": 9.989405226318772e-05,
      "loss": 1.362,
      "step": 18
    },
    {
      "epoch": 0.1431261770244821,
      "grad_norm": 0.46899810433387756,
      "learning_rate": 9.986592247916858e-05,
      "loss": 1.1479,
      "step": 19
    },
    {
      "epoch": 0.15065913370998116,
      "grad_norm": 0.5480923056602478,
      "learning_rate": 9.983448955807708e-05,
      "loss": 1.1834,
      "step": 20
    },
    {
      "epoch": 0.15065913370998116,
      "eval_loss": 1.1339441537857056,
      "eval_runtime": 50.1262,
      "eval_samples_per_second": 1.496,
      "eval_steps_per_second": 0.758,
      "step": 20
    },
    {
      "epoch": 0.15819209039548024,
      "grad_norm": 0.6135687232017517,
      "learning_rate": 9.979975558204147e-05,
      "loss": 1.1895,
      "step": 21
    },
    {
      "epoch": 0.1657250470809793,
      "grad_norm": 0.6562265753746033,
      "learning_rate": 9.976172285185314e-05,
      "loss": 1.1213,
      "step": 22
    },
    {
      "epoch": 0.17325800376647835,
      "grad_norm": 0.7003594040870667,
      "learning_rate": 9.972039388681413e-05,
      "loss": 1.1117,
      "step": 23
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 0.6009169220924377,
      "learning_rate": 9.967577142457032e-05,
      "loss": 1.0146,
      "step": 24
    },
    {
      "epoch": 0.18832391713747645,
      "grad_norm": 0.9375618696212769,
      "learning_rate": 9.962785842093003e-05,
      "loss": 1.0485,
      "step": 25
    },
    {
      "epoch": 0.1958568738229755,
      "grad_norm": 0.7120280861854553,
      "learning_rate": 9.957665804966829e-05,
      "loss": 0.8638,
      "step": 26
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 0.9676161408424377,
      "learning_rate": 9.952217370231653e-05,
      "loss": 0.9569,
      "step": 27
    },
    {
      "epoch": 0.21092278719397364,
      "grad_norm": 0.8478333353996277,
      "learning_rate": 9.946440898793801e-05,
      "loss": 0.8989,
      "step": 28
    },
    {
      "epoch": 0.2184557438794727,
      "grad_norm": 0.9060878753662109,
      "learning_rate": 9.940336773288865e-05,
      "loss": 0.8083,
      "step": 29
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.9778569936752319,
      "learning_rate": 9.933905398056372e-05,
      "loss": 0.7268,
      "step": 30
    },
    {
      "epoch": 0.22598870056497175,
      "eval_loss": 0.7190647125244141,
      "eval_runtime": 50.1226,
      "eval_samples_per_second": 1.496,
      "eval_steps_per_second": 0.758,
      "step": 30
    },
    {
      "epoch": 0.2335216572504708,
      "grad_norm": 0.9858911633491516,
      "learning_rate": 9.92714719911298e-05,
      "loss": 0.6885,
      "step": 31
    },
    {
      "epoch": 0.24105461393596986,
      "grad_norm": 1.0453399419784546,
      "learning_rate": 9.920062624124282e-05,
      "loss": 0.6971,
      "step": 32
    },
    {
      "epoch": 0.24858757062146894,
      "grad_norm": 0.9439508318901062,
      "learning_rate": 9.912652142375132e-05,
      "loss": 0.7523,
      "step": 33
    },
    {
      "epoch": 0.256120527306968,
      "grad_norm": 0.8011656999588013,
      "learning_rate": 9.904916244738571e-05,
      "loss": 0.6094,
      "step": 34
    },
    {
      "epoch": 0.263653483992467,
      "grad_norm": 0.8053231835365295,
      "learning_rate": 9.896855443643308e-05,
      "loss": 0.5719,
      "step": 35
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 0.7347720265388489,
      "learning_rate": 9.888470273039775e-05,
      "loss": 0.5913,
      "step": 36
    },
    {
      "epoch": 0.2787193973634652,
      "grad_norm": 0.8015826344490051,
      "learning_rate": 9.879761288364766e-05,
      "loss": 0.5636,
      "step": 37
    },
    {
      "epoch": 0.2862523540489642,
      "grad_norm": 0.4674820303916931,
      "learning_rate": 9.870729066504629e-05,
      "loss": 0.4962,
      "step": 38
    },
    {
      "epoch": 0.2937853107344633,
      "grad_norm": 0.3237204849720001,
      "learning_rate": 9.861374205757068e-05,
      "loss": 0.5201,
      "step": 39
    },
    {
      "epoch": 0.3013182674199623,
      "grad_norm": 0.3314957320690155,
      "learning_rate": 9.851697325791505e-05,
      "loss": 0.5162,
      "step": 40
    },
    {
      "epoch": 0.3013182674199623,
      "eval_loss": 0.4833310544490814,
      "eval_runtime": 50.1791,
      "eval_samples_per_second": 1.495,
      "eval_steps_per_second": 0.757,
      "step": 40
    },
    {
      "epoch": 0.3088512241054614,
      "grad_norm": 0.44042736291885376,
      "learning_rate": 9.841699067608033e-05,
      "loss": 0.4832,
      "step": 41
    },
    {
      "epoch": 0.3163841807909605,
      "grad_norm": 0.5744893550872803,
      "learning_rate": 9.831380093494957e-05,
      "loss": 0.4676,
      "step": 42
    },
    {
      "epoch": 0.3239171374764595,
      "grad_norm": 0.6231745481491089,
      "learning_rate": 9.820741086984924e-05,
      "loss": 0.4778,
      "step": 43
    },
    {
      "epoch": 0.3314500941619586,
      "grad_norm": 0.652641773223877,
      "learning_rate": 9.809782752809644e-05,
      "loss": 0.4618,
      "step": 44
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.34044504165649414,
      "learning_rate": 9.798505816853208e-05,
      "loss": 0.5053,
      "step": 45
    },
    {
      "epoch": 0.3465160075329567,
      "grad_norm": 0.3873239755630493,
      "learning_rate": 9.786911026104007e-05,
      "loss": 0.4319,
      "step": 46
    },
    {
      "epoch": 0.3540489642184557,
      "grad_norm": 0.34049129486083984,
      "learning_rate": 9.774999148605251e-05,
      "loss": 0.4713,
      "step": 47
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 0.39110735058784485,
      "learning_rate": 9.762770973404094e-05,
      "loss": 0.4605,
      "step": 48
    },
    {
      "epoch": 0.3691148775894539,
      "grad_norm": 0.3248206675052643,
      "learning_rate": 9.750227310499366e-05,
      "loss": 0.4259,
      "step": 49
    },
    {
      "epoch": 0.3766478342749529,
      "grad_norm": 0.624284029006958,
      "learning_rate": 9.737368990787916e-05,
      "loss": 0.3921,
      "step": 50
    },
    {
      "epoch": 0.3766478342749529,
      "eval_loss": 0.42401236295700073,
      "eval_runtime": 50.1482,
      "eval_samples_per_second": 1.496,
      "eval_steps_per_second": 0.758,
      "step": 50
    },
    {
      "epoch": 0.384180790960452,
      "grad_norm": 0.3228764533996582,
      "learning_rate": 9.72419686600958e-05,
      "loss": 0.4269,
      "step": 51
    },
    {
      "epoch": 0.391713747645951,
      "grad_norm": 0.2958717346191406,
      "learning_rate": 9.710711808690754e-05,
      "loss": 0.4804,
      "step": 52
    },
    {
      "epoch": 0.3992467043314501,
      "grad_norm": 0.5469731092453003,
      "learning_rate": 9.696914712086603e-05,
      "loss": 0.4463,
      "step": 53
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 0.35308223962783813,
      "learning_rate": 9.682806490121885e-05,
      "loss": 0.3708,
      "step": 54
    },
    {
      "epoch": 0.4143126177024482,
      "grad_norm": 0.4369649589061737,
      "learning_rate": 9.668388077330421e-05,
      "loss": 0.4226,
      "step": 55
    },
    {
      "epoch": 0.4218455743879473,
      "grad_norm": 0.7406517863273621,
      "learning_rate": 9.653660428793188e-05,
      "loss": 0.4082,
      "step": 56
    },
    {
      "epoch": 0.4293785310734463,
      "grad_norm": 0.4191276729106903,
      "learning_rate": 9.638624520075046e-05,
      "loss": 0.3736,
      "step": 57
    },
    {
      "epoch": 0.4369114877589454,
      "grad_norm": 0.3738877475261688,
      "learning_rate": 9.623281347160127e-05,
      "loss": 0.3987,
      "step": 58
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.3371034562587738,
      "learning_rate": 9.607631926385859e-05,
      "loss": 0.4276,
      "step": 59
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 0.3625945746898651,
      "learning_rate": 9.591677294375636e-05,
      "loss": 0.3952,
      "step": 60
    },
    {
      "epoch": 0.4519774011299435,
      "eval_loss": 0.3758457601070404,
      "eval_runtime": 50.0723,
      "eval_samples_per_second": 1.498,
      "eval_steps_per_second": 0.759,
      "step": 60
    },
    {
      "epoch": 0.4595103578154426,
      "grad_norm": 0.4314848780632019,
      "learning_rate": 9.575418507970161e-05,
      "loss": 0.4264,
      "step": 61
    },
    {
      "epoch": 0.4670433145009416,
      "grad_norm": 0.3458515703678131,
      "learning_rate": 9.558856644157432e-05,
      "loss": 0.3845,
      "step": 62
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 0.30270910263061523,
      "learning_rate": 9.541992800001409e-05,
      "loss": 0.3984,
      "step": 63
    },
    {
      "epoch": 0.4821092278719397,
      "grad_norm": 0.3931046426296234,
      "learning_rate": 9.52482809256934e-05,
      "loss": 0.4019,
      "step": 64
    },
    {
      "epoch": 0.4896421845574388,
      "grad_norm": 0.49052339792251587,
      "learning_rate": 9.507363658857768e-05,
      "loss": 0.4353,
      "step": 65
    },
    {
      "epoch": 0.4971751412429379,
      "grad_norm": 0.3206973075866699,
      "learning_rate": 9.489600655717217e-05,
      "loss": 0.4599,
      "step": 66
    },
    {
      "epoch": 0.504708097928437,
      "grad_norm": 0.36185964941978455,
      "learning_rate": 9.471540259775554e-05,
      "loss": 0.3684,
      "step": 67
    },
    {
      "epoch": 0.512241054613936,
      "grad_norm": 0.4438144266605377,
      "learning_rate": 9.453183667360062e-05,
      "loss": 0.3924,
      "step": 68
    },
    {
      "epoch": 0.519774011299435,
      "grad_norm": 0.408000111579895,
      "learning_rate": 9.43453209441818e-05,
      "loss": 0.3165,
      "step": 69
    },
    {
      "epoch": 0.527306967984934,
      "grad_norm": 0.5293291211128235,
      "learning_rate": 9.415586776436973e-05,
      "loss": 0.3696,
      "step": 70
    },
    {
      "epoch": 0.527306967984934,
      "eval_loss": 0.3250181972980499,
      "eval_runtime": 50.0681,
      "eval_samples_per_second": 1.498,
      "eval_steps_per_second": 0.759,
      "step": 70
    },
    {
      "epoch": 0.5348399246704332,
      "grad_norm": 0.7923517227172852,
      "learning_rate": 9.396348968361281e-05,
      "loss": 0.388,
      "step": 71
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 0.5696645975112915,
      "learning_rate": 9.376819944510598e-05,
      "loss": 0.3383,
      "step": 72
    },
    {
      "epoch": 0.5499058380414312,
      "grad_norm": 0.8812904357910156,
      "learning_rate": 9.357000998494656e-05,
      "loss": 0.2872,
      "step": 73
    },
    {
      "epoch": 0.5574387947269304,
      "grad_norm": 0.4949493110179901,
      "learning_rate": 9.336893443127738e-05,
      "loss": 0.3039,
      "step": 74
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 0.40088051557540894,
      "learning_rate": 9.31649861034172e-05,
      "loss": 0.3246,
      "step": 75
    },
    {
      "epoch": 0.5725047080979284,
      "grad_norm": 0.40099695324897766,
      "learning_rate": 9.295817851097837e-05,
      "loss": 0.3544,
      "step": 76
    },
    {
      "epoch": 0.5800376647834274,
      "grad_norm": 0.4039609432220459,
      "learning_rate": 9.274852535297198e-05,
      "loss": 0.333,
      "step": 77
    },
    {
      "epoch": 0.5875706214689266,
      "grad_norm": 0.46073368191719055,
      "learning_rate": 9.253604051690046e-05,
      "loss": 0.2505,
      "step": 78
    },
    {
      "epoch": 0.5951035781544256,
      "grad_norm": 0.3831747770309448,
      "learning_rate": 9.232073807783759e-05,
      "loss": 0.2545,
      "step": 79
    },
    {
      "epoch": 0.6026365348399246,
      "grad_norm": 0.668875515460968,
      "learning_rate": 9.210263229749626e-05,
      "loss": 0.2892,
      "step": 80
    },
    {
      "epoch": 0.6026365348399246,
      "eval_loss": 0.25938624143600464,
      "eval_runtime": 50.0589,
      "eval_samples_per_second": 1.498,
      "eval_steps_per_second": 0.759,
      "step": 80
    },
    {
      "epoch": 0.6101694915254238,
      "grad_norm": 0.4702552556991577,
      "learning_rate": 9.188173762328367e-05,
      "loss": 0.259,
      "step": 81
    },
    {
      "epoch": 0.6177024482109228,
      "grad_norm": 0.6220546364784241,
      "learning_rate": 9.165806868734444e-05,
      "loss": 0.2636,
      "step": 82
    },
    {
      "epoch": 0.6252354048964218,
      "grad_norm": 0.526050329208374,
      "learning_rate": 9.143164030559122e-05,
      "loss": 0.2903,
      "step": 83
    },
    {
      "epoch": 0.632768361581921,
      "grad_norm": 0.48076707124710083,
      "learning_rate": 9.120246747672347e-05,
      "loss": 0.2847,
      "step": 84
    },
    {
      "epoch": 0.64030131826742,
      "grad_norm": 0.5487018823623657,
      "learning_rate": 9.097056538123376e-05,
      "loss": 0.2625,
      "step": 85
    },
    {
      "epoch": 0.647834274952919,
      "grad_norm": 0.6256678700447083,
      "learning_rate": 9.073594938040231e-05,
      "loss": 0.267,
      "step": 86
    },
    {
      "epoch": 0.655367231638418,
      "grad_norm": 0.6361900568008423,
      "learning_rate": 9.049863501527947e-05,
      "loss": 0.2927,
      "step": 87
    },
    {
      "epoch": 0.6629001883239172,
      "grad_norm": 0.5942044258117676,
      "learning_rate": 9.025863800565613e-05,
      "loss": 0.2995,
      "step": 88
    },
    {
      "epoch": 0.6704331450094162,
      "grad_norm": 0.5061842203140259,
      "learning_rate": 9.001597424902267e-05,
      "loss": 0.232,
      "step": 89
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.826519250869751,
      "learning_rate": 8.977065981951566e-05,
      "loss": 0.2039,
      "step": 90
    },
    {
      "epoch": 0.6779661016949152,
      "eval_loss": 0.2045535147190094,
      "eval_runtime": 50.1117,
      "eval_samples_per_second": 1.497,
      "eval_steps_per_second": 0.758,
      "step": 90
    },
    {
      "epoch": 0.6854990583804144,
      "grad_norm": 0.5888376832008362,
      "learning_rate": 8.952271096685332e-05,
      "loss": 0.1997,
      "step": 91
    },
    {
      "epoch": 0.6930320150659134,
      "grad_norm": 0.7269095182418823,
      "learning_rate": 8.927214411525895e-05,
      "loss": 0.2589,
      "step": 92
    },
    {
      "epoch": 0.7005649717514124,
      "grad_norm": 0.8657869696617126,
      "learning_rate": 8.90189758623731e-05,
      "loss": 0.1956,
      "step": 93
    },
    {
      "epoch": 0.7080979284369114,
      "grad_norm": 0.7702244520187378,
      "learning_rate": 8.876322297815405e-05,
      "loss": 0.2218,
      "step": 94
    },
    {
      "epoch": 0.7156308851224106,
      "grad_norm": 0.6147786974906921,
      "learning_rate": 8.850490240376711e-05,
      "loss": 0.212,
      "step": 95
    },
    {
      "epoch": 0.7231638418079096,
      "grad_norm": 0.5774387717247009,
      "learning_rate": 8.824403125046225e-05,
      "loss": 0.1908,
      "step": 96
    },
    {
      "epoch": 0.7306967984934086,
      "grad_norm": 0.75771164894104,
      "learning_rate": 8.798062679844077e-05,
      "loss": 0.1696,
      "step": 97
    },
    {
      "epoch": 0.7382297551789078,
      "grad_norm": 0.6371806859970093,
      "learning_rate": 8.771470649571056e-05,
      "loss": 0.2085,
      "step": 98
    },
    {
      "epoch": 0.7457627118644068,
      "grad_norm": 0.5286451578140259,
      "learning_rate": 8.744628795693047e-05,
      "loss": 0.1982,
      "step": 99
    },
    {
      "epoch": 0.7532956685499058,
      "grad_norm": 0.5060010552406311,
      "learning_rate": 8.717538896224332e-05,
      "loss": 0.2027,
      "step": 100
    },
    {
      "epoch": 0.7532956685499058,
      "eval_loss": 0.1616896241903305,
      "eval_runtime": 50.0794,
      "eval_samples_per_second": 1.498,
      "eval_steps_per_second": 0.759,
      "step": 100
    },
    {
      "epoch": 0.7608286252354048,
      "grad_norm": 0.7836325764656067,
      "learning_rate": 8.690202745609835e-05,
      "loss": 0.1358,
      "step": 101
    },
    {
      "epoch": 0.768361581920904,
      "grad_norm": 0.675710141658783,
      "learning_rate": 8.662622154606237e-05,
      "loss": 0.1846,
      "step": 102
    },
    {
      "epoch": 0.775894538606403,
      "grad_norm": 0.8798868656158447,
      "learning_rate": 8.634798950162048e-05,
      "loss": 0.1966,
      "step": 103
    },
    {
      "epoch": 0.783427495291902,
      "grad_norm": 0.5943530201911926,
      "learning_rate": 8.606734975296578e-05,
      "loss": 0.1632,
      "step": 104
    },
    {
      "epoch": 0.7909604519774012,
      "grad_norm": 0.4987153708934784,
      "learning_rate": 8.578432088977859e-05,
      "loss": 0.1113,
      "step": 105
    },
    {
      "epoch": 0.7984934086629002,
      "grad_norm": 0.7684951424598694,
      "learning_rate": 8.549892165999505e-05,
      "loss": 0.1434,
      "step": 106
    },
    {
      "epoch": 0.8060263653483992,
      "grad_norm": 0.624474823474884,
      "learning_rate": 8.521117096856528e-05,
      "loss": 0.1754,
      "step": 107
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 1.0357481241226196,
      "learning_rate": 8.492108787620105e-05,
      "loss": 0.1761,
      "step": 108
    },
    {
      "epoch": 0.8210922787193974,
      "grad_norm": 0.7299608588218689,
      "learning_rate": 8.462869159811327e-05,
      "loss": 0.1145,
      "step": 109
    },
    {
      "epoch": 0.8286252354048964,
      "grad_norm": 0.7747260332107544,
      "learning_rate": 8.433400150273906e-05,
      "loss": 0.1494,
      "step": 110
    },
    {
      "epoch": 0.8286252354048964,
      "eval_loss": 0.12168504297733307,
      "eval_runtime": 50.0938,
      "eval_samples_per_second": 1.497,
      "eval_steps_per_second": 0.759,
      "step": 110
    },
    {
      "epoch": 0.8361581920903954,
      "grad_norm": 0.7779563665390015,
      "learning_rate": 8.403703711045892e-05,
      "loss": 0.159,
      "step": 111
    },
    {
      "epoch": 0.8436911487758946,
      "grad_norm": 1.1017848253250122,
      "learning_rate": 8.373781809230355e-05,
      "loss": 0.2012,
      "step": 112
    },
    {
      "epoch": 0.8512241054613936,
      "grad_norm": 0.4848591983318329,
      "learning_rate": 8.343636426865096e-05,
      "loss": 0.1215,
      "step": 113
    },
    {
      "epoch": 0.8587570621468926,
      "grad_norm": 0.8865452408790588,
      "learning_rate": 8.313269560791342e-05,
      "loss": 0.0923,
      "step": 114
    },
    {
      "epoch": 0.8662900188323918,
      "grad_norm": 0.699765145778656,
      "learning_rate": 8.28268322252149e-05,
      "loss": 0.1587,
      "step": 115
    },
    {
      "epoch": 0.8738229755178908,
      "grad_norm": 0.5934118628501892,
      "learning_rate": 8.251879438105854e-05,
      "loss": 0.1288,
      "step": 116
    },
    {
      "epoch": 0.8813559322033898,
      "grad_norm": 0.7120998501777649,
      "learning_rate": 8.220860247998456e-05,
      "loss": 0.101,
      "step": 117
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.0435795783996582,
      "learning_rate": 8.189627706921877e-05,
      "loss": 0.1067,
      "step": 118
    },
    {
      "epoch": 0.896421845574388,
      "grad_norm": 1.4066674709320068,
      "learning_rate": 8.15818388373114e-05,
      "loss": 0.1313,
      "step": 119
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 0.7823694348335266,
      "learning_rate": 8.126530861276677e-05,
      "loss": 0.0863,
      "step": 120
    },
    {
      "epoch": 0.903954802259887,
      "eval_loss": 0.09002000838518143,
      "eval_runtime": 50.1325,
      "eval_samples_per_second": 1.496,
      "eval_steps_per_second": 0.758,
      "step": 120
    },
    {
      "epoch": 0.911487758945386,
      "grad_norm": 0.617436945438385,
      "learning_rate": 8.094670736266353e-05,
      "loss": 0.0868,
      "step": 121
    },
    {
      "epoch": 0.9190207156308852,
      "grad_norm": 0.602743923664093,
      "learning_rate": 8.062605619126584e-05,
      "loss": 0.0983,
      "step": 122
    },
    {
      "epoch": 0.9265536723163842,
      "grad_norm": 1.1149927377700806,
      "learning_rate": 8.030337633862542e-05,
      "loss": 0.1078,
      "step": 123
    },
    {
      "epoch": 0.9340866290018832,
      "grad_norm": 0.688164472579956,
      "learning_rate": 7.997868917917453e-05,
      "loss": 0.0722,
      "step": 124
    },
    {
      "epoch": 0.9416195856873822,
      "grad_norm": 0.6507720351219177,
      "learning_rate": 7.965201622031021e-05,
      "loss": 0.0824,
      "step": 125
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 0.5873366594314575,
      "learning_rate": 7.932337910096961e-05,
      "loss": 0.0633,
      "step": 126
    },
    {
      "epoch": 0.9566854990583804,
      "grad_norm": 0.48810163140296936,
      "learning_rate": 7.899279959019654e-05,
      "loss": 0.0579,
      "step": 127
    },
    {
      "epoch": 0.9642184557438794,
      "grad_norm": 0.7808175086975098,
      "learning_rate": 7.866029958569956e-05,
      "loss": 0.0959,
      "step": 128
    },
    {
      "epoch": 0.9717514124293786,
      "grad_norm": 0.7213129997253418,
      "learning_rate": 7.832590111240145e-05,
      "loss": 0.1074,
      "step": 129
    },
    {
      "epoch": 0.9792843691148776,
      "grad_norm": 0.7429501414299011,
      "learning_rate": 7.798962632098024e-05,
      "loss": 0.0883,
      "step": 130
    },
    {
      "epoch": 0.9792843691148776,
      "eval_loss": 0.07171642780303955,
      "eval_runtime": 50.1218,
      "eval_samples_per_second": 1.496,
      "eval_steps_per_second": 0.758,
      "step": 130
    },
    {
      "epoch": 0.9868173258003766,
      "grad_norm": 1.2204382419586182,
      "learning_rate": 7.765149748640197e-05,
      "loss": 0.0543,
      "step": 131
    },
    {
      "epoch": 0.9943502824858758,
      "grad_norm": 0.4847294092178345,
      "learning_rate": 7.73115370064452e-05,
      "loss": 0.0646,
      "step": 132
    },
    {
      "epoch": 1.0075329566854991,
      "grad_norm": 0.7584130764007568,
      "learning_rate": 7.696976740021733e-05,
      "loss": 0.1122,
      "step": 133
    },
    {
      "epoch": 1.015065913370998,
      "grad_norm": 0.4241285026073456,
      "learning_rate": 7.6626211306663e-05,
      "loss": 0.0382,
      "step": 134
    },
    {
      "epoch": 1.0225988700564972,
      "grad_norm": 0.6364421844482422,
      "learning_rate": 7.628089148306434e-05,
      "loss": 0.0707,
      "step": 135
    },
    {
      "epoch": 1.0301318267419963,
      "grad_norm": 0.6198002099990845,
      "learning_rate": 7.59338308035337e-05,
      "loss": 0.0942,
      "step": 136
    },
    {
      "epoch": 1.0376647834274952,
      "grad_norm": 0.43464764952659607,
      "learning_rate": 7.558505225749827e-05,
      "loss": 0.086,
      "step": 137
    },
    {
      "epoch": 1.0451977401129944,
      "grad_norm": 0.3746040463447571,
      "learning_rate": 7.523457894817745e-05,
      "loss": 0.0426,
      "step": 138
    },
    {
      "epoch": 1.0527306967984935,
      "grad_norm": 0.4349992573261261,
      "learning_rate": 7.488243409105233e-05,
      "loss": 0.0665,
      "step": 139
    },
    {
      "epoch": 1.0602636534839924,
      "grad_norm": 0.44264963269233704,
      "learning_rate": 7.452864101232798e-05,
      "loss": 0.0854,
      "step": 140
    },
    {
      "epoch": 1.0602636534839924,
      "eval_loss": 0.061161428689956665,
      "eval_runtime": 50.0795,
      "eval_samples_per_second": 1.498,
      "eval_steps_per_second": 0.759,
      "step": 140
    },
    {
      "epoch": 1.0677966101694916,
      "grad_norm": 0.535400390625,
      "learning_rate": 7.417322314738822e-05,
      "loss": 0.0502,
      "step": 141
    },
    {
      "epoch": 1.0753295668549905,
      "grad_norm": 0.4334566295146942,
      "learning_rate": 7.381620403924333e-05,
      "loss": 0.0547,
      "step": 142
    },
    {
      "epoch": 1.0828625235404896,
      "grad_norm": 0.6763977408409119,
      "learning_rate": 7.345760733697055e-05,
      "loss": 0.0576,
      "step": 143
    },
    {
      "epoch": 1.0903954802259888,
      "grad_norm": 0.6230652928352356,
      "learning_rate": 7.30974567941475e-05,
      "loss": 0.0746,
      "step": 144
    },
    {
      "epoch": 1.0979284369114877,
      "grad_norm": 0.5115144848823547,
      "learning_rate": 7.273577626727884e-05,
      "loss": 0.0707,
      "step": 145
    },
    {
      "epoch": 1.1054613935969868,
      "grad_norm": 0.4081382751464844,
      "learning_rate": 7.237258971421587e-05,
      "loss": 0.0417,
      "step": 146
    },
    {
      "epoch": 1.112994350282486,
      "grad_norm": 0.45929810404777527,
      "learning_rate": 7.20079211925696e-05,
      "loss": 0.0402,
      "step": 147
    },
    {
      "epoch": 1.1205273069679849,
      "grad_norm": 0.41027042269706726,
      "learning_rate": 7.164179485811727e-05,
      "loss": 0.057,
      "step": 148
    },
    {
      "epoch": 1.128060263653484,
      "grad_norm": 0.732723593711853,
      "learning_rate": 7.127423496320212e-05,
      "loss": 0.0686,
      "step": 149
    },
    {
      "epoch": 1.1355932203389831,
      "grad_norm": 0.4201294481754303,
      "learning_rate": 7.090526585512696e-05,
      "loss": 0.075,
      "step": 150
    },
    {
      "epoch": 1.1355932203389831,
      "eval_loss": 0.056692853569984436,
      "eval_runtime": 50.061,
      "eval_samples_per_second": 1.498,
      "eval_steps_per_second": 0.759,
      "step": 150
    },
    {
      "epoch": 1.143126177024482,
      "grad_norm": 0.3101370930671692,
      "learning_rate": 7.053491197454142e-05,
      "loss": 0.0366,
      "step": 151
    },
    {
      "epoch": 1.1506591337099812,
      "grad_norm": 0.4567885100841522,
      "learning_rate": 7.016319785382296e-05,
      "loss": 0.0778,
      "step": 152
    },
    {
      "epoch": 1.1581920903954803,
      "grad_norm": 0.3678460419178009,
      "learning_rate": 6.979014811545189e-05,
      "loss": 0.0495,
      "step": 153
    },
    {
      "epoch": 1.1657250470809792,
      "grad_norm": 0.5862255096435547,
      "learning_rate": 6.941578747038023e-05,
      "loss": 0.0735,
      "step": 154
    },
    {
      "epoch": 1.1732580037664784,
      "grad_norm": 0.5297702550888062,
      "learning_rate": 6.904014071639503e-05,
      "loss": 0.034,
      "step": 155
    },
    {
      "epoch": 1.1807909604519775,
      "grad_norm": 0.3692375123500824,
      "learning_rate": 6.866323273647563e-05,
      "loss": 0.0587,
      "step": 156
    },
    {
      "epoch": 1.1883239171374764,
      "grad_norm": 0.3478219509124756,
      "learning_rate": 6.828508849714546e-05,
      "loss": 0.0676,
      "step": 157
    },
    {
      "epoch": 1.1958568738229756,
      "grad_norm": 0.5066402554512024,
      "learning_rate": 6.79057330468182e-05,
      "loss": 0.0362,
      "step": 158
    },
    {
      "epoch": 1.2033898305084745,
      "grad_norm": 0.38956108689308167,
      "learning_rate": 6.752519151413861e-05,
      "loss": 0.0475,
      "step": 159
    },
    {
      "epoch": 1.2109227871939736,
      "grad_norm": 0.3372087776660919,
      "learning_rate": 6.7143489106318e-05,
      "loss": 0.0835,
      "step": 160
    },
    {
      "epoch": 1.2109227871939736,
      "eval_loss": 0.054186370223760605,
      "eval_runtime": 50.1057,
      "eval_samples_per_second": 1.497,
      "eval_steps_per_second": 0.758,
      "step": 160
    },
    {
      "epoch": 1.2184557438794728,
      "grad_norm": 0.4884163737297058,
      "learning_rate": 6.676065110746444e-05,
      "loss": 0.057,
      "step": 161
    },
    {
      "epoch": 1.2259887005649717,
      "grad_norm": 0.42741522192955017,
      "learning_rate": 6.637670287690799e-05,
      "loss": 0.0493,
      "step": 162
    },
    {
      "epoch": 1.2335216572504708,
      "grad_norm": 0.37808606028556824,
      "learning_rate": 6.599166984752087e-05,
      "loss": 0.0324,
      "step": 163
    },
    {
      "epoch": 1.24105461393597,
      "grad_norm": 0.6114926934242249,
      "learning_rate": 6.560557752403277e-05,
      "loss": 0.0975,
      "step": 164
    },
    {
      "epoch": 1.2485875706214689,
      "grad_norm": 0.2513774633407593,
      "learning_rate": 6.52184514813414e-05,
      "loss": 0.0323,
      "step": 165
    },
    {
      "epoch": 1.256120527306968,
      "grad_norm": 0.319553941488266,
      "learning_rate": 6.483031736281843e-05,
      "loss": 0.0246,
      "step": 166
    },
    {
      "epoch": 1.2636534839924671,
      "grad_norm": 0.6170870661735535,
      "learning_rate": 6.444120087861081e-05,
      "loss": 0.05,
      "step": 167
    },
    {
      "epoch": 1.271186440677966,
      "grad_norm": 0.4168320596218109,
      "learning_rate": 6.40511278039378e-05,
      "loss": 0.0586,
      "step": 168
    },
    {
      "epoch": 1.2787193973634652,
      "grad_norm": 0.3265027403831482,
      "learning_rate": 6.366012397738355e-05,
      "loss": 0.0666,
      "step": 169
    },
    {
      "epoch": 1.286252354048964,
      "grad_norm": 0.609319806098938,
      "learning_rate": 6.326821529918553e-05,
      "loss": 0.085,
      "step": 170
    },
    {
      "epoch": 1.286252354048964,
      "eval_loss": 0.053176406770944595,
      "eval_runtime": 50.1048,
      "eval_samples_per_second": 1.497,
      "eval_steps_per_second": 0.758,
      "step": 170
    },
    {
      "epoch": 1.2937853107344632,
      "grad_norm": 0.5599777698516846,
      "learning_rate": 6.287542772951897e-05,
      "loss": 0.0723,
      "step": 171
    },
    {
      "epoch": 1.3013182674199624,
      "grad_norm": 0.4176930785179138,
      "learning_rate": 6.248178728677711e-05,
      "loss": 0.0728,
      "step": 172
    },
    {
      "epoch": 1.3088512241054615,
      "grad_norm": 0.3369368314743042,
      "learning_rate": 6.208732004584791e-05,
      "loss": 0.0499,
      "step": 173
    },
    {
      "epoch": 1.3163841807909604,
      "grad_norm": 0.45373421907424927,
      "learning_rate": 6.16920521363867e-05,
      "loss": 0.0792,
      "step": 174
    },
    {
      "epoch": 1.3239171374764596,
      "grad_norm": 0.3415266275405884,
      "learning_rate": 6.129600974108538e-05,
      "loss": 0.048,
      "step": 175
    },
    {
      "epoch": 1.3314500941619585,
      "grad_norm": 0.5422535538673401,
      "learning_rate": 6.089921909393812e-05,
      "loss": 0.0883,
      "step": 176
    },
    {
      "epoch": 1.3389830508474576,
      "grad_norm": 0.25546208024024963,
      "learning_rate": 6.050170647850351e-05,
      "loss": 0.0473,
      "step": 177
    },
    {
      "epoch": 1.3465160075329567,
      "grad_norm": 0.5453774929046631,
      "learning_rate": 6.0103498226163603e-05,
      "loss": 0.0984,
      "step": 178
    },
    {
      "epoch": 1.3540489642184557,
      "grad_norm": 0.340578556060791,
      "learning_rate": 5.970462071437973e-05,
      "loss": 0.0354,
      "step": 179
    },
    {
      "epoch": 1.3615819209039548,
      "grad_norm": 0.4705830216407776,
      "learning_rate": 5.93051003649452e-05,
      "loss": 0.054,
      "step": 180
    },
    {
      "epoch": 1.3615819209039548,
      "eval_loss": 0.051415782421827316,
      "eval_runtime": 50.1031,
      "eval_samples_per_second": 1.497,
      "eval_steps_per_second": 0.758,
      "step": 180
    },
    {
      "epoch": 1.369114877589454,
      "grad_norm": 0.5732293128967285,
      "learning_rate": 5.890496364223509e-05,
      "loss": 0.0626,
      "step": 181
    },
    {
      "epoch": 1.3766478342749529,
      "grad_norm": 0.4315062463283539,
      "learning_rate": 5.850423705145334e-05,
      "loss": 0.0613,
      "step": 182
    },
    {
      "epoch": 1.384180790960452,
      "grad_norm": 0.5873361825942993,
      "learning_rate": 5.8102947136876876e-05,
      "loss": 0.0915,
      "step": 183
    },
    {
      "epoch": 1.3917137476459511,
      "grad_norm": 0.2784740626811981,
      "learning_rate": 5.770112048009747e-05,
      "loss": 0.0259,
      "step": 184
    },
    {
      "epoch": 1.39924670433145,
      "grad_norm": 0.36659327149391174,
      "learning_rate": 5.7298783698260874e-05,
      "loss": 0.0643,
      "step": 185
    },
    {
      "epoch": 1.4067796610169492,
      "grad_norm": 0.31498560309410095,
      "learning_rate": 5.68959634423037e-05,
      "loss": 0.0345,
      "step": 186
    },
    {
      "epoch": 1.414312617702448,
      "grad_norm": 0.4332311451435089,
      "learning_rate": 5.64926863951881e-05,
      "loss": 0.0461,
      "step": 187
    },
    {
      "epoch": 1.4218455743879472,
      "grad_norm": 0.35596826672554016,
      "learning_rate": 5.60889792701342e-05,
      "loss": 0.032,
      "step": 188
    },
    {
      "epoch": 1.4293785310734464,
      "grad_norm": 0.43455907702445984,
      "learning_rate": 5.568486880885068e-05,
      "loss": 0.0283,
      "step": 189
    },
    {
      "epoch": 1.4369114877589455,
      "grad_norm": 2.2231392860412598,
      "learning_rate": 5.52803817797633e-05,
      "loss": 0.0337,
      "step": 190
    },
    {
      "epoch": 1.4369114877589455,
      "eval_loss": 0.050475846976041794,
      "eval_runtime": 50.1291,
      "eval_samples_per_second": 1.496,
      "eval_steps_per_second": 0.758,
      "step": 190
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.3397436738014221,
      "learning_rate": 5.487554497624189e-05,
      "loss": 0.0481,
      "step": 191
    },
    {
      "epoch": 1.4519774011299436,
      "grad_norm": 0.3190496265888214,
      "learning_rate": 5.4470385214825416e-05,
      "loss": 0.0606,
      "step": 192
    },
    {
      "epoch": 1.4595103578154425,
      "grad_norm": 0.3939787447452545,
      "learning_rate": 5.406492933344571e-05,
      "loss": 0.1776,
      "step": 193
    },
    {
      "epoch": 1.4670433145009416,
      "grad_norm": 0.33525291085243225,
      "learning_rate": 5.365920418964973e-05,
      "loss": 0.0516,
      "step": 194
    },
    {
      "epoch": 1.4745762711864407,
      "grad_norm": 0.32538145780563354,
      "learning_rate": 5.3253236658820396e-05,
      "loss": 0.0465,
      "step": 195
    },
    {
      "epoch": 1.4821092278719397,
      "grad_norm": 0.3278179466724396,
      "learning_rate": 5.28470536323965e-05,
      "loss": 0.067,
      "step": 196
    },
    {
      "epoch": 1.4896421845574388,
      "grad_norm": 0.41677576303482056,
      "learning_rate": 5.244068201609133e-05,
      "loss": 0.0519,
      "step": 197
    },
    {
      "epoch": 1.497175141242938,
      "grad_norm": 0.44194525480270386,
      "learning_rate": 5.2034148728110424e-05,
      "loss": 0.0686,
      "step": 198
    },
    {
      "epoch": 1.5047080979284368,
      "grad_norm": 0.3261134922504425,
      "learning_rate": 5.162748069736851e-05,
      "loss": 0.0534,
      "step": 199
    },
    {
      "epoch": 1.512241054613936,
      "grad_norm": 0.4644230008125305,
      "learning_rate": 5.1220704861705774e-05,
      "loss": 0.0421,
      "step": 200
    },
    {
      "epoch": 1.512241054613936,
      "eval_loss": 0.04965050518512726,
      "eval_runtime": 50.0829,
      "eval_samples_per_second": 1.498,
      "eval_steps_per_second": 0.759,
      "step": 200
    },
    {
      "epoch": 1.5197740112994351,
      "grad_norm": 0.3440283238887787,
      "learning_rate": 5.081384816610336e-05,
      "loss": 0.0621,
      "step": 201
    },
    {
      "epoch": 1.527306967984934,
      "grad_norm": 0.2635885179042816,
      "learning_rate": 5.0406937560898646e-05,
      "loss": 0.0443,
      "step": 202
    },
    {
      "epoch": 1.5348399246704332,
      "grad_norm": 0.6189826726913452,
      "learning_rate": 5e-05,
      "loss": 0.084,
      "step": 203
    },
    {
      "epoch": 1.542372881355932,
      "grad_norm": 0.3221701383590698,
      "learning_rate": 4.9593062439101365e-05,
      "loss": 0.0348,
      "step": 204
    },
    {
      "epoch": 1.5499058380414312,
      "grad_norm": 0.30998164415359497,
      "learning_rate": 4.918615183389665e-05,
      "loss": 0.0529,
      "step": 205
    },
    {
      "epoch": 1.5574387947269304,
      "grad_norm": 0.47885751724243164,
      "learning_rate": 4.877929513829424e-05,
      "loss": 0.0454,
      "step": 206
    },
    {
      "epoch": 1.5649717514124295,
      "grad_norm": 0.5070298910140991,
      "learning_rate": 4.8372519302631486e-05,
      "loss": 0.0473,
      "step": 207
    },
    {
      "epoch": 1.5725047080979284,
      "grad_norm": 0.3871539533138275,
      "learning_rate": 4.796585127188958e-05,
      "loss": 0.056,
      "step": 208
    },
    {
      "epoch": 1.5800376647834273,
      "grad_norm": 0.4367206394672394,
      "learning_rate": 4.755931798390867e-05,
      "loss": 0.0734,
      "step": 209
    },
    {
      "epoch": 1.5875706214689265,
      "grad_norm": 0.2854059338569641,
      "learning_rate": 4.715294636760352e-05,
      "loss": 0.0563,
      "step": 210
    },
    {
      "epoch": 1.5875706214689265,
      "eval_loss": 0.04947199299931526,
      "eval_runtime": 50.1478,
      "eval_samples_per_second": 1.496,
      "eval_steps_per_second": 0.758,
      "step": 210
    },
    {
      "epoch": 1.5951035781544256,
      "grad_norm": 0.3172830641269684,
      "learning_rate": 4.674676334117962e-05,
      "loss": 0.0356,
      "step": 211
    },
    {
      "epoch": 1.6026365348399247,
      "grad_norm": 0.5930951237678528,
      "learning_rate": 4.634079581035029e-05,
      "loss": 0.0687,
      "step": 212
    },
    {
      "epoch": 1.6101694915254239,
      "grad_norm": 0.3214702010154724,
      "learning_rate": 4.59350706665543e-05,
      "loss": 0.0433,
      "step": 213
    },
    {
      "epoch": 1.6177024482109228,
      "grad_norm": 0.3200390636920929,
      "learning_rate": 4.55296147851746e-05,
      "loss": 0.0518,
      "step": 214
    },
    {
      "epoch": 1.6252354048964217,
      "grad_norm": 0.32656821608543396,
      "learning_rate": 4.512445502375813e-05,
      "loss": 0.0391,
      "step": 215
    },
    {
      "epoch": 1.6327683615819208,
      "grad_norm": 0.45625510811805725,
      "learning_rate": 4.471961822023671e-05,
      "loss": 0.0244,
      "step": 216
    },
    {
      "epoch": 1.64030131826742,
      "grad_norm": 0.32512399554252625,
      "learning_rate": 4.431513119114934e-05,
      "loss": 0.1139,
      "step": 217
    },
    {
      "epoch": 1.6478342749529191,
      "grad_norm": 0.3270999491214752,
      "learning_rate": 4.391102072986581e-05,
      "loss": 0.0988,
      "step": 218
    },
    {
      "epoch": 1.655367231638418,
      "grad_norm": 0.44575634598731995,
      "learning_rate": 4.350731360481191e-05,
      "loss": 0.0525,
      "step": 219
    },
    {
      "epoch": 1.6629001883239172,
      "grad_norm": 0.3585101366043091,
      "learning_rate": 4.3104036557696295e-05,
      "loss": 0.186,
      "step": 220
    },
    {
      "epoch": 1.6629001883239172,
      "eval_loss": 0.04876178875565529,
      "eval_runtime": 50.0932,
      "eval_samples_per_second": 1.497,
      "eval_steps_per_second": 0.759,
      "step": 220
    },
    {
      "epoch": 1.6629001883239172,
      "step": 220,
      "total_flos": 6.808102961998848e+16,
      "train_loss": 0.33265126400034534,
      "train_runtime": 4751.8019,
      "train_samples_per_second": 0.67,
      "train_steps_per_second": 0.083
    }
  ],
  "logging_steps": 1,
  "max_steps": 396,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0015
      },
      "attributes": {
        "early_stopping_patience_counter": 4
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.808102961998848e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}