{
  "best_metric": 0.6116148751910341,
  "best_model_checkpoint": "outputs/t5-tiny/weak_tiny_poe/mnli_21/checkpoint-61360",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 61360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 1.0741028785705566,
      "learning_rate": 4.9592568448500655e-05,
      "loss": 1.2614,
      "step": 500
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6355718374252319,
      "learning_rate": 4.918513689700131e-05,
      "loss": 1.2516,
      "step": 1000
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.8562185168266296,
      "learning_rate": 4.877770534550195e-05,
      "loss": 1.2444,
      "step": 1500
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.435200810432434,
      "learning_rate": 4.8370273794002606e-05,
      "loss": 1.2294,
      "step": 2000
    },
    {
      "epoch": 0.2,
      "grad_norm": 2.3618035316467285,
      "learning_rate": 4.7962842242503265e-05,
      "loss": 1.2231,
      "step": 2500
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.9568185806274414,
      "learning_rate": 4.755541069100392e-05,
      "loss": 1.2171,
      "step": 3000
    },
    {
      "epoch": 0.29,
      "grad_norm": 2.025542974472046,
      "learning_rate": 4.7147979139504564e-05,
      "loss": 1.2158,
      "step": 3500
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.468313217163086,
      "learning_rate": 4.6740547588005216e-05,
      "loss": 1.1951,
      "step": 4000
    },
    {
      "epoch": 0.37,
      "grad_norm": 2.4365932941436768,
      "learning_rate": 4.633311603650587e-05,
      "loss": 1.203,
      "step": 4500
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.7032877206802368,
      "learning_rate": 4.592568448500652e-05,
      "loss": 1.1952,
      "step": 5000
    },
    {
      "epoch": 0.45,
      "grad_norm": 2.0673813819885254,
      "learning_rate": 4.5518252933507174e-05,
      "loss": 1.1958,
      "step": 5500
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.7614480257034302,
      "learning_rate": 4.511082138200782e-05,
      "loss": 1.1933,
      "step": 6000
    },
    {
      "epoch": 0.53,
      "grad_norm": 3.3648741245269775,
      "learning_rate": 4.470338983050847e-05,
      "loss": 1.1862,
      "step": 6500
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.8836809396743774,
      "learning_rate": 4.429595827900913e-05,
      "loss": 1.1926,
      "step": 7000
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.070249080657959,
      "learning_rate": 4.3888526727509784e-05,
      "loss": 1.1841,
      "step": 7500
    },
    {
      "epoch": 0.65,
      "grad_norm": 2.4235424995422363,
      "learning_rate": 4.348109517601043e-05,
      "loss": 1.1755,
      "step": 8000
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.2773147821426392,
      "learning_rate": 4.307366362451108e-05,
      "loss": 1.1906,
      "step": 8500
    },
    {
      "epoch": 0.73,
      "grad_norm": 4.709882736206055,
      "learning_rate": 4.2666232073011735e-05,
      "loss": 1.1683,
      "step": 9000
    },
    {
      "epoch": 0.77,
      "grad_norm": 2.064504384994507,
      "learning_rate": 4.225880052151239e-05,
      "loss": 1.1703,
      "step": 9500
    },
    {
      "epoch": 0.81,
      "grad_norm": 2.670032262802124,
      "learning_rate": 4.185136897001304e-05,
      "loss": 1.1622,
      "step": 10000
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.9821618795394897,
      "learning_rate": 4.144393741851369e-05,
      "loss": 1.1571,
      "step": 10500
    },
    {
      "epoch": 0.9,
      "grad_norm": 2.3936009407043457,
      "learning_rate": 4.103650586701434e-05,
      "loss": 1.1616,
      "step": 11000
    },
    {
      "epoch": 0.94,
      "grad_norm": 2.637899398803711,
      "learning_rate": 4.0629074315515e-05,
      "loss": 1.1677,
      "step": 11500
    },
    {
      "epoch": 0.98,
      "grad_norm": 2.4801619052886963,
      "learning_rate": 4.022164276401565e-05,
      "loss": 1.1514,
      "step": 12000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4945491594498217,
      "eval_combined_score": 0.4945491594498217,
      "eval_loss": 1.0730257034301758,
      "eval_runtime": 4.8512,
      "eval_samples_per_second": 2023.214,
      "eval_steps_per_second": 8.039,
      "step": 12272
    },
    {
      "epoch": 1.02,
      "grad_norm": 2.4936630725860596,
      "learning_rate": 3.98142112125163e-05,
      "loss": 1.1492,
      "step": 12500
    },
    {
      "epoch": 1.06,
      "grad_norm": 2.4125094413757324,
      "learning_rate": 3.940677966101695e-05,
      "loss": 1.1456,
      "step": 13000
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.6422048807144165,
      "learning_rate": 3.89993481095176e-05,
      "loss": 1.1404,
      "step": 13500
    },
    {
      "epoch": 1.14,
      "grad_norm": 2.566889762878418,
      "learning_rate": 3.8591916558018254e-05,
      "loss": 1.145,
      "step": 14000
    },
    {
      "epoch": 1.18,
      "grad_norm": 2.594127893447876,
      "learning_rate": 3.818448500651891e-05,
      "loss": 1.1498,
      "step": 14500
    },
    {
      "epoch": 1.22,
      "grad_norm": 2.0145516395568848,
      "learning_rate": 3.777705345501956e-05,
      "loss": 1.1434,
      "step": 15000
    },
    {
      "epoch": 1.26,
      "grad_norm": 2.318466901779175,
      "learning_rate": 3.7369621903520205e-05,
      "loss": 1.1339,
      "step": 15500
    },
    {
      "epoch": 1.3,
      "grad_norm": 2.0532548427581787,
      "learning_rate": 3.6962190352020865e-05,
      "loss": 1.1474,
      "step": 16000
    },
    {
      "epoch": 1.34,
      "grad_norm": 2.050147294998169,
      "learning_rate": 3.655475880052152e-05,
      "loss": 1.1398,
      "step": 16500
    },
    {
      "epoch": 1.39,
      "grad_norm": 2.1561617851257324,
      "learning_rate": 3.614732724902217e-05,
      "loss": 1.139,
      "step": 17000
    },
    {
      "epoch": 1.43,
      "grad_norm": 2.1412413120269775,
      "learning_rate": 3.5739895697522816e-05,
      "loss": 1.1429,
      "step": 17500
    },
    {
      "epoch": 1.47,
      "grad_norm": 1.999888300895691,
      "learning_rate": 3.533246414602347e-05,
      "loss": 1.1335,
      "step": 18000
    },
    {
      "epoch": 1.51,
      "grad_norm": 3.487457275390625,
      "learning_rate": 3.492503259452412e-05,
      "loss": 1.134,
      "step": 18500
    },
    {
      "epoch": 1.55,
      "grad_norm": 2.8775036334991455,
      "learning_rate": 3.451760104302477e-05,
      "loss": 1.1441,
      "step": 19000
    },
    {
      "epoch": 1.59,
      "grad_norm": 2.7384023666381836,
      "learning_rate": 3.4110169491525426e-05,
      "loss": 1.1341,
      "step": 19500
    },
    {
      "epoch": 1.63,
      "grad_norm": 3.0970985889434814,
      "learning_rate": 3.370273794002607e-05,
      "loss": 1.1268,
      "step": 20000
    },
    {
      "epoch": 1.67,
      "grad_norm": 3.6261987686157227,
      "learning_rate": 3.329530638852673e-05,
      "loss": 1.1328,
      "step": 20500
    },
    {
      "epoch": 1.71,
      "grad_norm": 2.8419606685638428,
      "learning_rate": 3.2887874837027384e-05,
      "loss": 1.1249,
      "step": 21000
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.8945815563201904,
      "learning_rate": 3.2480443285528036e-05,
      "loss": 1.1294,
      "step": 21500
    },
    {
      "epoch": 1.79,
      "grad_norm": 2.6052589416503906,
      "learning_rate": 3.207301173402868e-05,
      "loss": 1.1336,
      "step": 22000
    },
    {
      "epoch": 1.83,
      "grad_norm": 2.4897425174713135,
      "learning_rate": 3.1665580182529335e-05,
      "loss": 1.1297,
      "step": 22500
    },
    {
      "epoch": 1.87,
      "grad_norm": 2.1377058029174805,
      "learning_rate": 3.125814863102999e-05,
      "loss": 1.117,
      "step": 23000
    },
    {
      "epoch": 1.91,
      "grad_norm": 2.3489041328430176,
      "learning_rate": 3.085071707953064e-05,
      "loss": 1.1242,
      "step": 23500
    },
    {
      "epoch": 1.96,
      "grad_norm": 2.4663751125335693,
      "learning_rate": 3.044328552803129e-05,
      "loss": 1.1249,
      "step": 24000
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7375434637069702,
      "learning_rate": 3.003585397653194e-05,
      "loss": 1.1148,
      "step": 24500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5651553744268976,
      "eval_combined_score": 0.5651553744268976,
      "eval_loss": 0.956773579120636,
      "eval_runtime": 4.3422,
      "eval_samples_per_second": 2260.392,
      "eval_steps_per_second": 8.982,
      "step": 24544
    },
    {
      "epoch": 2.04,
      "grad_norm": 3.0487465858459473,
      "learning_rate": 2.9628422425032598e-05,
      "loss": 1.1135,
      "step": 25000
    },
    {
      "epoch": 2.08,
      "grad_norm": 2.7948238849639893,
      "learning_rate": 2.922099087353325e-05,
      "loss": 1.1193,
      "step": 25500
    },
    {
      "epoch": 2.12,
      "grad_norm": 2.9265005588531494,
      "learning_rate": 2.88135593220339e-05,
      "loss": 1.1221,
      "step": 26000
    },
    {
      "epoch": 2.16,
      "grad_norm": 2.115213632583618,
      "learning_rate": 2.8406127770534552e-05,
      "loss": 1.1178,
      "step": 26500
    },
    {
      "epoch": 2.2,
      "grad_norm": 2.7759642601013184,
      "learning_rate": 2.7998696219035204e-05,
      "loss": 1.1106,
      "step": 27000
    },
    {
      "epoch": 2.24,
      "grad_norm": 3.3535237312316895,
      "learning_rate": 2.7591264667535854e-05,
      "loss": 1.1223,
      "step": 27500
    },
    {
      "epoch": 2.28,
      "grad_norm": 4.240155220031738,
      "learning_rate": 2.7183833116036506e-05,
      "loss": 1.1006,
      "step": 28000
    },
    {
      "epoch": 2.32,
      "grad_norm": 2.35819411277771,
      "learning_rate": 2.6776401564537155e-05,
      "loss": 1.1082,
      "step": 28500
    },
    {
      "epoch": 2.36,
      "grad_norm": 2.635653257369995,
      "learning_rate": 2.6368970013037815e-05,
      "loss": 1.1047,
      "step": 29000
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.2701103687286377,
      "learning_rate": 2.5961538461538464e-05,
      "loss": 1.1003,
      "step": 29500
    },
    {
      "epoch": 2.44,
      "grad_norm": 3.0462381839752197,
      "learning_rate": 2.5554106910039117e-05,
      "loss": 1.1127,
      "step": 30000
    },
    {
      "epoch": 2.49,
      "grad_norm": 2.489602565765381,
      "learning_rate": 2.5146675358539766e-05,
      "loss": 1.1028,
      "step": 30500
    },
    {
      "epoch": 2.53,
      "grad_norm": 2.6888344287872314,
      "learning_rate": 2.473924380704042e-05,
      "loss": 1.0982,
      "step": 31000
    },
    {
      "epoch": 2.57,
      "grad_norm": 3.001851797103882,
      "learning_rate": 2.433181225554107e-05,
      "loss": 1.1097,
      "step": 31500
    },
    {
      "epoch": 2.61,
      "grad_norm": 2.212657928466797,
      "learning_rate": 2.392438070404172e-05,
      "loss": 1.11,
      "step": 32000
    },
    {
      "epoch": 2.65,
      "grad_norm": 2.230945110321045,
      "learning_rate": 2.3516949152542376e-05,
      "loss": 1.0993,
      "step": 32500
    },
    {
      "epoch": 2.69,
      "grad_norm": 3.2973270416259766,
      "learning_rate": 2.3109517601043025e-05,
      "loss": 1.1137,
      "step": 33000
    },
    {
      "epoch": 2.73,
      "grad_norm": 3.0208470821380615,
      "learning_rate": 2.2702086049543678e-05,
      "loss": 1.1057,
      "step": 33500
    },
    {
      "epoch": 2.77,
      "grad_norm": 1.68820059299469,
      "learning_rate": 2.229465449804433e-05,
      "loss": 1.1048,
      "step": 34000
    },
    {
      "epoch": 2.81,
      "grad_norm": 3.023021936416626,
      "learning_rate": 2.188722294654498e-05,
      "loss": 1.091,
      "step": 34500
    },
    {
      "epoch": 2.85,
      "grad_norm": 2.254213571548462,
      "learning_rate": 2.1479791395045636e-05,
      "loss": 1.1049,
      "step": 35000
    },
    {
      "epoch": 2.89,
      "grad_norm": 3.3968422412872314,
      "learning_rate": 2.1072359843546285e-05,
      "loss": 1.0982,
      "step": 35500
    },
    {
      "epoch": 2.93,
      "grad_norm": 2.841524124145508,
      "learning_rate": 2.0664928292046937e-05,
      "loss": 1.0937,
      "step": 36000
    },
    {
      "epoch": 2.97,
      "grad_norm": 3.070187568664551,
      "learning_rate": 2.0257496740547587e-05,
      "loss": 1.1048,
      "step": 36500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5710646968925115,
      "eval_combined_score": 0.5710646968925115,
      "eval_loss": 0.9583811163902283,
      "eval_runtime": 4.5767,
      "eval_samples_per_second": 2144.543,
      "eval_steps_per_second": 8.521,
      "step": 36816
    },
    {
      "epoch": 3.01,
      "grad_norm": 2.1366419792175293,
      "learning_rate": 1.9850065189048242e-05,
      "loss": 1.094,
      "step": 37000
    },
    {
      "epoch": 3.06,
      "grad_norm": 3.5920097827911377,
      "learning_rate": 1.944263363754889e-05,
      "loss": 1.0943,
      "step": 37500
    },
    {
      "epoch": 3.1,
      "grad_norm": 3.099132537841797,
      "learning_rate": 1.9035202086049544e-05,
      "loss": 1.1039,
      "step": 38000
    },
    {
      "epoch": 3.14,
      "grad_norm": 2.7153160572052,
      "learning_rate": 1.8627770534550197e-05,
      "loss": 1.0928,
      "step": 38500
    },
    {
      "epoch": 3.18,
      "grad_norm": 2.752225875854492,
      "learning_rate": 1.8220338983050846e-05,
      "loss": 1.098,
      "step": 39000
    },
    {
      "epoch": 3.22,
      "grad_norm": 2.1102657318115234,
      "learning_rate": 1.7812907431551502e-05,
      "loss": 1.0968,
      "step": 39500
    },
    {
      "epoch": 3.26,
      "grad_norm": 2.7974390983581543,
      "learning_rate": 1.740547588005215e-05,
      "loss": 1.09,
      "step": 40000
    },
    {
      "epoch": 3.3,
      "grad_norm": 2.8349063396453857,
      "learning_rate": 1.6998044328552804e-05,
      "loss": 1.0862,
      "step": 40500
    },
    {
      "epoch": 3.34,
      "grad_norm": 2.360250234603882,
      "learning_rate": 1.6590612777053456e-05,
      "loss": 1.0953,
      "step": 41000
    },
    {
      "epoch": 3.38,
      "grad_norm": 3.601504325866699,
      "learning_rate": 1.618318122555411e-05,
      "loss": 1.0841,
      "step": 41500
    },
    {
      "epoch": 3.42,
      "grad_norm": 2.5209643840789795,
      "learning_rate": 1.577574967405476e-05,
      "loss": 1.0847,
      "step": 42000
    },
    {
      "epoch": 3.46,
      "grad_norm": 3.1257715225219727,
      "learning_rate": 1.536831812255541e-05,
      "loss": 1.0991,
      "step": 42500
    },
    {
      "epoch": 3.5,
      "grad_norm": 3.250303268432617,
      "learning_rate": 1.4960886571056063e-05,
      "loss": 1.098,
      "step": 43000
    },
    {
      "epoch": 3.54,
      "grad_norm": 3.4005048274993896,
      "learning_rate": 1.4553455019556716e-05,
      "loss": 1.0839,
      "step": 43500
    },
    {
      "epoch": 3.59,
      "grad_norm": 2.8816983699798584,
      "learning_rate": 1.4146023468057368e-05,
      "loss": 1.0849,
      "step": 44000
    },
    {
      "epoch": 3.63,
      "grad_norm": 2.870222568511963,
      "learning_rate": 1.373859191655802e-05,
      "loss": 1.0994,
      "step": 44500
    },
    {
      "epoch": 3.67,
      "grad_norm": 3.1101572513580322,
      "learning_rate": 1.333116036505867e-05,
      "loss": 1.0927,
      "step": 45000
    },
    {
      "epoch": 3.71,
      "grad_norm": 3.555572986602783,
      "learning_rate": 1.2923728813559321e-05,
      "loss": 1.0915,
      "step": 45500
    },
    {
      "epoch": 3.75,
      "grad_norm": 3.06459379196167,
      "learning_rate": 1.2516297262059975e-05,
      "loss": 1.0952,
      "step": 46000
    },
    {
      "epoch": 3.79,
      "grad_norm": 3.103626012802124,
      "learning_rate": 1.2108865710560626e-05,
      "loss": 1.0859,
      "step": 46500
    },
    {
      "epoch": 3.83,
      "grad_norm": 3.8208911418914795,
      "learning_rate": 1.1701434159061279e-05,
      "loss": 1.0966,
      "step": 47000
    },
    {
      "epoch": 3.87,
      "grad_norm": 2.8707382678985596,
      "learning_rate": 1.1294002607561931e-05,
      "loss": 1.0752,
      "step": 47500
    },
    {
      "epoch": 3.91,
      "grad_norm": 4.298058032989502,
      "learning_rate": 1.0886571056062582e-05,
      "loss": 1.092,
      "step": 48000
    },
    {
      "epoch": 3.95,
      "grad_norm": 2.011492967605591,
      "learning_rate": 1.0479139504563235e-05,
      "loss": 1.0789,
      "step": 48500
    },
    {
      "epoch": 3.99,
      "grad_norm": 3.2206387519836426,
      "learning_rate": 1.0071707953063886e-05,
      "loss": 1.075,
      "step": 49000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5978604177279674,
      "eval_combined_score": 0.5978604177279674,
      "eval_loss": 0.9132007360458374,
      "eval_runtime": 3.8437,
      "eval_samples_per_second": 2553.526,
      "eval_steps_per_second": 10.146,
      "step": 49088
    },
    {
      "epoch": 4.03,
      "grad_norm": 3.0595147609710693,
      "learning_rate": 9.664276401564537e-06,
      "loss": 1.0901,
      "step": 49500
    },
    {
      "epoch": 4.07,
      "grad_norm": 2.2460098266601562,
      "learning_rate": 9.25684485006519e-06,
      "loss": 1.0802,
      "step": 50000
    },
    {
      "epoch": 4.12,
      "grad_norm": 2.1211585998535156,
      "learning_rate": 8.84941329856584e-06,
      "loss": 1.0886,
      "step": 50500
    },
    {
      "epoch": 4.16,
      "grad_norm": 2.7433323860168457,
      "learning_rate": 8.441981747066494e-06,
      "loss": 1.0814,
      "step": 51000
    },
    {
      "epoch": 4.2,
      "grad_norm": 3.3154397010803223,
      "learning_rate": 8.034550195567145e-06,
      "loss": 1.0877,
      "step": 51500
    },
    {
      "epoch": 4.24,
      "grad_norm": 3.0281894207000732,
      "learning_rate": 7.627118644067798e-06,
      "loss": 1.0773,
      "step": 52000
    },
    {
      "epoch": 4.28,
      "grad_norm": 2.553225517272949,
      "learning_rate": 7.219687092568449e-06,
      "loss": 1.0869,
      "step": 52500
    },
    {
      "epoch": 4.32,
      "grad_norm": 2.8887219429016113,
      "learning_rate": 6.812255541069101e-06,
      "loss": 1.0756,
      "step": 53000
    },
    {
      "epoch": 4.36,
      "grad_norm": 2.1609950065612793,
      "learning_rate": 6.404823989569752e-06,
      "loss": 1.0884,
      "step": 53500
    },
    {
      "epoch": 4.4,
      "grad_norm": 3.0557539463043213,
      "learning_rate": 5.997392438070405e-06,
      "loss": 1.0886,
      "step": 54000
    },
    {
      "epoch": 4.44,
      "grad_norm": 2.783965587615967,
      "learning_rate": 5.5899608865710565e-06,
      "loss": 1.0827,
      "step": 54500
    },
    {
      "epoch": 4.48,
      "grad_norm": 3.0575108528137207,
      "learning_rate": 5.182529335071708e-06,
      "loss": 1.0886,
      "step": 55000
    },
    {
      "epoch": 4.52,
      "grad_norm": 2.5954906940460205,
      "learning_rate": 4.77509778357236e-06,
      "loss": 1.0773,
      "step": 55500
    },
    {
      "epoch": 4.56,
      "grad_norm": 2.1589512825012207,
      "learning_rate": 4.367666232073012e-06,
      "loss": 1.0693,
      "step": 56000
    },
    {
      "epoch": 4.6,
      "grad_norm": 2.5202431678771973,
      "learning_rate": 3.9602346805736635e-06,
      "loss": 1.0803,
      "step": 56500
    },
    {
      "epoch": 4.64,
      "grad_norm": 2.588782787322998,
      "learning_rate": 3.5528031290743156e-06,
      "loss": 1.0816,
      "step": 57000
    },
    {
      "epoch": 4.69,
      "grad_norm": 2.994828701019287,
      "learning_rate": 3.1453715775749674e-06,
      "loss": 1.0682,
      "step": 57500
    },
    {
      "epoch": 4.73,
      "grad_norm": 2.9718551635742188,
      "learning_rate": 2.7379400260756195e-06,
      "loss": 1.0786,
      "step": 58000
    },
    {
      "epoch": 4.77,
      "grad_norm": 3.181231737136841,
      "learning_rate": 2.3305084745762712e-06,
      "loss": 1.0818,
      "step": 58500
    },
    {
      "epoch": 4.81,
      "grad_norm": 2.3970162868499756,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 1.0816,
      "step": 59000
    },
    {
      "epoch": 4.85,
      "grad_norm": 2.8263609409332275,
      "learning_rate": 1.5156453715775751e-06,
      "loss": 1.0755,
      "step": 59500
    },
    {
      "epoch": 4.89,
      "grad_norm": 3.2032511234283447,
      "learning_rate": 1.108213820078227e-06,
      "loss": 1.0764,
      "step": 60000
    },
    {
      "epoch": 4.93,
      "grad_norm": 3.6272828578948975,
      "learning_rate": 7.007822685788788e-07,
      "loss": 1.0855,
      "step": 60500
    },
    {
      "epoch": 4.97,
      "grad_norm": 2.672410249710083,
      "learning_rate": 2.9335071707953065e-07,
      "loss": 1.0755,
      "step": 61000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6116148751910341,
      "eval_combined_score": 0.6116148751910341,
      "eval_loss": 0.8905634880065918,
      "eval_runtime": 4.8808,
      "eval_samples_per_second": 2010.92,
      "eval_steps_per_second": 7.99,
      "step": 61360
    },
    {
      "epoch": 5.0,
      "step": 61360,
      "total_flos": 0.0,
      "train_loss": 1.1215235922762437,
      "train_runtime": 4186.3943,
      "train_samples_per_second": 469.022,
      "train_steps_per_second": 14.657
    }
  ],
  "logging_steps": 500,
  "max_steps": 61360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}