{
  "best_metric": 1.9183450937271118,
  "best_model_checkpoint": "models/GPT2_more_function_53/checkpoint-155680",
  "epoch": 10.0,
  "global_step": 155680,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 1e-05,
      "loss": 6.0974,
      "step": 1000
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 3.7504,
      "step": 2000
    },
    {
      "epoch": 0.19,
      "learning_rate": 3e-05,
      "loss": 3.1766,
      "step": 3000
    },
    {
      "epoch": 0.26,
      "learning_rate": 4e-05,
      "loss": 2.8933,
      "step": 4000
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 2.7463,
      "step": 5000
    },
    {
      "epoch": 0.39,
      "learning_rate": 6e-05,
      "loss": 2.6511,
      "step": 6000
    },
    {
      "epoch": 0.45,
      "learning_rate": 7e-05,
      "loss": 2.5785,
      "step": 7000
    },
    {
      "epoch": 0.51,
      "learning_rate": 8e-05,
      "loss": 2.5222,
      "step": 8000
    },
    {
      "epoch": 0.58,
      "learning_rate": 9e-05,
      "loss": 2.4721,
      "step": 9000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 2.4349,
      "step": 10000
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.931425041186162e-05,
      "loss": 2.4,
      "step": 11000
    },
    {
      "epoch": 0.77,
      "learning_rate": 9.862781438769907e-05,
      "loss": 2.3671,
      "step": 12000
    },
    {
      "epoch": 0.84,
      "learning_rate": 9.794206479956069e-05,
      "loss": 2.3407,
      "step": 13000
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.725562877539814e-05,
      "loss": 2.3166,
      "step": 14000
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.656987918725975e-05,
      "loss": 2.297,
      "step": 15000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5112671312299146,
      "eval_loss": 2.240675687789917,
      "eval_runtime": 4.688,
      "eval_samples_per_second": 608.363,
      "eval_steps_per_second": 4.906,
      "step": 15568
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.58834431630972e-05,
      "loss": 2.2735,
      "step": 16000
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.519769357495882e-05,
      "loss": 2.2539,
      "step": 17000
    },
    {
      "epoch": 1.16,
      "learning_rate": 9.451125755079627e-05,
      "loss": 2.2432,
      "step": 18000
    },
    {
      "epoch": 1.22,
      "learning_rate": 9.382550796265789e-05,
      "loss": 2.231,
      "step": 19000
    },
    {
      "epoch": 1.28,
      "learning_rate": 9.313907193849534e-05,
      "loss": 2.2216,
      "step": 20000
    },
    {
      "epoch": 1.35,
      "learning_rate": 9.245332235035696e-05,
      "loss": 2.2111,
      "step": 21000
    },
    {
      "epoch": 1.41,
      "learning_rate": 9.17668863261944e-05,
      "loss": 2.205,
      "step": 22000
    },
    {
      "epoch": 1.48,
      "learning_rate": 9.108113673805602e-05,
      "loss": 2.1938,
      "step": 23000
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.039470071389346e-05,
      "loss": 2.1852,
      "step": 24000
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.970895112575508e-05,
      "loss": 2.1784,
      "step": 25000
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.902251510159254e-05,
      "loss": 2.1713,
      "step": 26000
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.833676551345414e-05,
      "loss": 2.1637,
      "step": 27000
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.765032948929161e-05,
      "loss": 2.1584,
      "step": 28000
    },
    {
      "epoch": 1.86,
      "learning_rate": 8.696457990115322e-05,
      "loss": 2.1517,
      "step": 29000
    },
    {
      "epoch": 1.93,
      "learning_rate": 8.627814387699067e-05,
      "loss": 2.1458,
      "step": 30000
    },
    {
      "epoch": 1.99,
      "learning_rate": 8.559239428885229e-05,
      "loss": 2.1414,
      "step": 31000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5348781349736612,
      "eval_loss": 2.101914167404175,
      "eval_runtime": 4.8416,
      "eval_samples_per_second": 589.065,
      "eval_steps_per_second": 4.751,
      "step": 31136
    },
    {
      "epoch": 2.06,
      "learning_rate": 8.490595826468973e-05,
      "loss": 2.1209,
      "step": 32000
    },
    {
      "epoch": 2.12,
      "learning_rate": 8.422020867655134e-05,
      "loss": 2.1174,
      "step": 33000
    },
    {
      "epoch": 2.18,
      "learning_rate": 8.35337726523888e-05,
      "loss": 2.1125,
      "step": 34000
    },
    {
      "epoch": 2.25,
      "learning_rate": 8.284733662822626e-05,
      "loss": 2.1084,
      "step": 35000
    },
    {
      "epoch": 2.31,
      "learning_rate": 8.216158704008787e-05,
      "loss": 2.1072,
      "step": 36000
    },
    {
      "epoch": 2.38,
      "learning_rate": 8.147515101592533e-05,
      "loss": 2.1029,
      "step": 37000
    },
    {
      "epoch": 2.44,
      "learning_rate": 8.078940142778694e-05,
      "loss": 2.1,
      "step": 38000
    },
    {
      "epoch": 2.51,
      "learning_rate": 8.010296540362439e-05,
      "loss": 2.097,
      "step": 39000
    },
    {
      "epoch": 2.57,
      "learning_rate": 7.941652937946183e-05,
      "loss": 2.0943,
      "step": 40000
    },
    {
      "epoch": 2.63,
      "learning_rate": 7.873077979132345e-05,
      "loss": 2.0907,
      "step": 41000
    },
    {
      "epoch": 2.7,
      "learning_rate": 7.80443437671609e-05,
      "loss": 2.0887,
      "step": 42000
    },
    {
      "epoch": 2.76,
      "learning_rate": 7.735859417902251e-05,
      "loss": 2.0848,
      "step": 43000
    },
    {
      "epoch": 2.83,
      "learning_rate": 7.667215815485998e-05,
      "loss": 2.0833,
      "step": 44000
    },
    {
      "epoch": 2.89,
      "learning_rate": 7.598640856672159e-05,
      "loss": 2.0794,
      "step": 45000
    },
    {
      "epoch": 2.95,
      "learning_rate": 7.529997254255904e-05,
      "loss": 2.0769,
      "step": 46000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5440276750118718,
      "eval_loss": 2.0458028316497803,
      "eval_runtime": 4.8031,
      "eval_samples_per_second": 593.781,
      "eval_steps_per_second": 4.789,
      "step": 46704
    },
    {
      "epoch": 3.02,
      "learning_rate": 7.461422295442066e-05,
      "loss": 2.0689,
      "step": 47000
    },
    {
      "epoch": 3.08,
      "learning_rate": 7.39277869302581e-05,
      "loss": 2.0524,
      "step": 48000
    },
    {
      "epoch": 3.15,
      "learning_rate": 7.324203734211971e-05,
      "loss": 2.0519,
      "step": 49000
    },
    {
      "epoch": 3.21,
      "learning_rate": 7.255560131795716e-05,
      "loss": 2.0508,
      "step": 50000
    },
    {
      "epoch": 3.28,
      "learning_rate": 7.186985172981878e-05,
      "loss": 2.0502,
      "step": 51000
    },
    {
      "epoch": 3.34,
      "learning_rate": 7.118341570565623e-05,
      "loss": 2.0495,
      "step": 52000
    },
    {
      "epoch": 3.4,
      "learning_rate": 7.049766611751785e-05,
      "loss": 2.0476,
      "step": 53000
    },
    {
      "epoch": 3.47,
      "learning_rate": 6.981123009335531e-05,
      "loss": 2.0457,
      "step": 54000
    },
    {
      "epoch": 3.53,
      "learning_rate": 6.912548050521693e-05,
      "loss": 2.0455,
      "step": 55000
    },
    {
      "epoch": 3.6,
      "learning_rate": 6.843904448105436e-05,
      "loss": 2.0432,
      "step": 56000
    },
    {
      "epoch": 3.66,
      "learning_rate": 6.775329489291598e-05,
      "loss": 2.0418,
      "step": 57000
    },
    {
      "epoch": 3.73,
      "learning_rate": 6.706685886875343e-05,
      "loss": 2.0401,
      "step": 58000
    },
    {
      "epoch": 3.79,
      "learning_rate": 6.638042284459088e-05,
      "loss": 2.0394,
      "step": 59000
    },
    {
      "epoch": 3.85,
      "learning_rate": 6.56946732564525e-05,
      "loss": 2.0376,
      "step": 60000
    },
    {
      "epoch": 3.92,
      "learning_rate": 6.500823723228996e-05,
      "loss": 2.0354,
      "step": 61000
    },
    {
      "epoch": 3.98,
      "learning_rate": 6.432248764415157e-05,
      "loss": 2.0352,
      "step": 62000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5512446024892049,
      "eval_loss": 2.008540391921997,
      "eval_runtime": 4.7884,
      "eval_samples_per_second": 595.602,
      "eval_steps_per_second": 4.803,
      "step": 62272
    },
    {
      "epoch": 4.05,
      "learning_rate": 6.363605161998903e-05,
      "loss": 2.0153,
      "step": 63000
    },
    {
      "epoch": 4.11,
      "learning_rate": 6.295030203185063e-05,
      "loss": 2.0116,
      "step": 64000
    },
    {
      "epoch": 4.18,
      "learning_rate": 6.226386600768808e-05,
      "loss": 2.0113,
      "step": 65000
    },
    {
      "epoch": 4.24,
      "learning_rate": 6.15781164195497e-05,
      "loss": 2.0106,
      "step": 66000
    },
    {
      "epoch": 4.3,
      "learning_rate": 6.089168039538715e-05,
      "loss": 2.0116,
      "step": 67000
    },
    {
      "epoch": 4.37,
      "learning_rate": 6.0205930807248766e-05,
      "loss": 2.0118,
      "step": 68000
    },
    {
      "epoch": 4.43,
      "learning_rate": 5.951949478308622e-05,
      "loss": 2.0089,
      "step": 69000
    },
    {
      "epoch": 4.5,
      "learning_rate": 5.883374519494783e-05,
      "loss": 2.0095,
      "step": 70000
    },
    {
      "epoch": 4.56,
      "learning_rate": 5.814730917078528e-05,
      "loss": 2.0088,
      "step": 71000
    },
    {
      "epoch": 4.62,
      "learning_rate": 5.746155958264689e-05,
      "loss": 2.0074,
      "step": 72000
    },
    {
      "epoch": 4.69,
      "learning_rate": 5.677512355848436e-05,
      "loss": 2.007,
      "step": 73000
    },
    {
      "epoch": 4.75,
      "learning_rate": 5.60886875343218e-05,
      "loss": 2.0058,
      "step": 74000
    },
    {
      "epoch": 4.82,
      "learning_rate": 5.540293794618342e-05,
      "loss": 2.0056,
      "step": 75000
    },
    {
      "epoch": 4.88,
      "learning_rate": 5.471650192202087e-05,
      "loss": 2.005,
      "step": 76000
    },
    {
      "epoch": 4.95,
      "learning_rate": 5.4030752333882485e-05,
      "loss": 2.0034,
      "step": 77000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5555073936234829,
      "eval_loss": 1.9856412410736084,
      "eval_runtime": 4.7852,
      "eval_samples_per_second": 595.998,
      "eval_steps_per_second": 4.806,
      "step": 77840
    },
    {
      "epoch": 5.01,
      "learning_rate": 5.3344316309719936e-05,
      "loss": 1.9962,
      "step": 78000
    },
    {
      "epoch": 5.07,
      "learning_rate": 5.2658566721581545e-05,
      "loss": 1.9772,
      "step": 79000
    },
    {
      "epoch": 5.14,
      "learning_rate": 5.197213069741901e-05,
      "loss": 1.9792,
      "step": 80000
    },
    {
      "epoch": 5.2,
      "learning_rate": 5.128638110928061e-05,
      "loss": 1.981,
      "step": 81000
    },
    {
      "epoch": 5.27,
      "learning_rate": 5.059994508511807e-05,
      "loss": 1.9816,
      "step": 82000
    },
    {
      "epoch": 5.33,
      "learning_rate": 4.9914195496979685e-05,
      "loss": 1.9803,
      "step": 83000
    },
    {
      "epoch": 5.4,
      "learning_rate": 4.9227759472817136e-05,
      "loss": 1.9806,
      "step": 84000
    },
    {
      "epoch": 5.46,
      "learning_rate": 4.854200988467875e-05,
      "loss": 1.9807,
      "step": 85000
    },
    {
      "epoch": 5.52,
      "learning_rate": 4.78555738605162e-05,
      "loss": 1.9806,
      "step": 86000
    },
    {
      "epoch": 5.59,
      "learning_rate": 4.716982427237782e-05,
      "loss": 1.9804,
      "step": 87000
    },
    {
      "epoch": 5.65,
      "learning_rate": 4.648338824821527e-05,
      "loss": 1.9793,
      "step": 88000
    },
    {
      "epoch": 5.72,
      "learning_rate": 4.579763866007688e-05,
      "loss": 1.9783,
      "step": 89000
    },
    {
      "epoch": 5.78,
      "learning_rate": 4.511120263591434e-05,
      "loss": 1.9783,
      "step": 90000
    },
    {
      "epoch": 5.85,
      "learning_rate": 4.442476661175179e-05,
      "loss": 1.9776,
      "step": 91000
    },
    {
      "epoch": 5.91,
      "learning_rate": 4.37390170236134e-05,
      "loss": 1.9764,
      "step": 92000
    },
    {
      "epoch": 5.97,
      "learning_rate": 4.3052580999450855e-05,
      "loss": 1.9762,
      "step": 93000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5583510949630595,
      "eval_loss": 1.965383768081665,
      "eval_runtime": 4.7681,
      "eval_samples_per_second": 598.141,
      "eval_steps_per_second": 4.824,
      "step": 93408
    },
    {
      "epoch": 6.04,
      "learning_rate": 4.236683141131247e-05,
      "loss": 1.9612,
      "step": 94000
    },
    {
      "epoch": 6.1,
      "learning_rate": 4.1680395387149915e-05,
      "loss": 1.9518,
      "step": 95000
    },
    {
      "epoch": 6.17,
      "learning_rate": 4.099464579901153e-05,
      "loss": 1.9535,
      "step": 96000
    },
    {
      "epoch": 6.23,
      "learning_rate": 4.030820977484899e-05,
      "loss": 1.9532,
      "step": 97000
    },
    {
      "epoch": 6.29,
      "learning_rate": 3.9622460186710605e-05,
      "loss": 1.9556,
      "step": 98000
    },
    {
      "epoch": 6.36,
      "learning_rate": 3.893602416254805e-05,
      "loss": 1.9562,
      "step": 99000
    },
    {
      "epoch": 6.42,
      "learning_rate": 3.8250274574409665e-05,
      "loss": 1.955,
      "step": 100000
    },
    {
      "epoch": 6.49,
      "learning_rate": 3.756383855024712e-05,
      "loss": 1.9569,
      "step": 101000
    },
    {
      "epoch": 6.55,
      "learning_rate": 3.687808896210873e-05,
      "loss": 1.9532,
      "step": 102000
    },
    {
      "epoch": 6.62,
      "learning_rate": 3.619165293794618e-05,
      "loss": 1.9554,
      "step": 103000
    },
    {
      "epoch": 6.68,
      "learning_rate": 3.55059033498078e-05,
      "loss": 1.9542,
      "step": 104000
    },
    {
      "epoch": 6.74,
      "learning_rate": 3.481946732564525e-05,
      "loss": 1.954,
      "step": 105000
    },
    {
      "epoch": 6.81,
      "learning_rate": 3.4133717737506865e-05,
      "loss": 1.9531,
      "step": 106000
    },
    {
      "epoch": 6.87,
      "learning_rate": 3.3447281713344316e-05,
      "loss": 1.9527,
      "step": 107000
    },
    {
      "epoch": 6.94,
      "learning_rate": 3.276153212520593e-05,
      "loss": 1.9536,
      "step": 108000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5617856235712472,
      "eval_loss": 1.9492745399475098,
      "eval_runtime": 4.7695,
      "eval_samples_per_second": 597.965,
      "eval_steps_per_second": 4.822,
      "step": 108976
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.207509610104338e-05,
      "loss": 1.9502,
      "step": 109000
    },
    {
      "epoch": 7.07,
      "learning_rate": 3.138866007688084e-05,
      "loss": 1.9267,
      "step": 110000
    },
    {
      "epoch": 7.13,
      "learning_rate": 3.070291048874245e-05,
      "loss": 1.931,
      "step": 111000
    },
    {
      "epoch": 7.19,
      "learning_rate": 3.00164744645799e-05,
      "loss": 1.9306,
      "step": 112000
    },
    {
      "epoch": 7.26,
      "learning_rate": 2.9330724876441517e-05,
      "loss": 1.9327,
      "step": 113000
    },
    {
      "epoch": 7.32,
      "learning_rate": 2.8644288852278968e-05,
      "loss": 1.9317,
      "step": 114000
    },
    {
      "epoch": 7.39,
      "learning_rate": 2.795853926414058e-05,
      "loss": 1.9319,
      "step": 115000
    },
    {
      "epoch": 7.45,
      "learning_rate": 2.7272103239978035e-05,
      "loss": 1.9317,
      "step": 116000
    },
    {
      "epoch": 7.52,
      "learning_rate": 2.658635365183965e-05,
      "loss": 1.9319,
      "step": 117000
    },
    {
      "epoch": 7.58,
      "learning_rate": 2.5899917627677102e-05,
      "loss": 1.9321,
      "step": 118000
    },
    {
      "epoch": 7.64,
      "learning_rate": 2.5214168039538714e-05,
      "loss": 1.9316,
      "step": 119000
    },
    {
      "epoch": 7.71,
      "learning_rate": 2.452773201537617e-05,
      "loss": 1.9311,
      "step": 120000
    },
    {
      "epoch": 7.77,
      "learning_rate": 2.384198242723778e-05,
      "loss": 1.9314,
      "step": 121000
    },
    {
      "epoch": 7.84,
      "learning_rate": 2.3155546403075236e-05,
      "loss": 1.9297,
      "step": 122000
    },
    {
      "epoch": 7.9,
      "learning_rate": 2.2469110378912686e-05,
      "loss": 1.9302,
      "step": 123000
    },
    {
      "epoch": 7.97,
      "learning_rate": 2.1783360790774302e-05,
      "loss": 1.9281,
      "step": 124000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5641958675221699,
      "eval_loss": 1.9358315467834473,
      "eval_runtime": 4.7877,
      "eval_samples_per_second": 595.693,
      "eval_steps_per_second": 4.804,
      "step": 124544
    },
    {
      "epoch": 8.03,
      "learning_rate": 2.1096924766611753e-05,
      "loss": 1.9201,
      "step": 125000
    },
    {
      "epoch": 8.09,
      "learning_rate": 2.041117517847337e-05,
      "loss": 1.9086,
      "step": 126000
    },
    {
      "epoch": 8.16,
      "learning_rate": 1.972473915431082e-05,
      "loss": 1.9107,
      "step": 127000
    },
    {
      "epoch": 8.22,
      "learning_rate": 1.903830313014827e-05,
      "loss": 1.9099,
      "step": 128000
    },
    {
      "epoch": 8.29,
      "learning_rate": 1.8352553542009884e-05,
      "loss": 1.9112,
      "step": 129000
    },
    {
      "epoch": 8.35,
      "learning_rate": 1.7666117517847338e-05,
      "loss": 1.9099,
      "step": 130000
    },
    {
      "epoch": 8.41,
      "learning_rate": 1.697968149368479e-05,
      "loss": 1.9092,
      "step": 131000
    },
    {
      "epoch": 8.48,
      "learning_rate": 1.62939319055464e-05,
      "loss": 1.9101,
      "step": 132000
    },
    {
      "epoch": 8.54,
      "learning_rate": 1.5607495881383856e-05,
      "loss": 1.9104,
      "step": 133000
    },
    {
      "epoch": 8.61,
      "learning_rate": 1.492174629324547e-05,
      "loss": 1.909,
      "step": 134000
    },
    {
      "epoch": 8.67,
      "learning_rate": 1.4235310269082921e-05,
      "loss": 1.9087,
      "step": 135000
    },
    {
      "epoch": 8.74,
      "learning_rate": 1.3549560680944537e-05,
      "loss": 1.9079,
      "step": 136000
    },
    {
      "epoch": 8.8,
      "learning_rate": 1.2863124656781988e-05,
      "loss": 1.9074,
      "step": 137000
    },
    {
      "epoch": 8.86,
      "learning_rate": 1.217668863261944e-05,
      "loss": 1.9087,
      "step": 138000
    },
    {
      "epoch": 8.93,
      "learning_rate": 1.1490939044481055e-05,
      "loss": 1.9076,
      "step": 139000
    },
    {
      "epoch": 8.99,
      "learning_rate": 1.0804503020318507e-05,
      "loss": 1.9065,
      "step": 140000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.5664294154675266,
      "eval_loss": 1.9251179695129395,
      "eval_runtime": 4.7856,
      "eval_samples_per_second": 595.949,
      "eval_steps_per_second": 4.806,
      "step": 140112
    },
    {
      "epoch": 9.06,
      "learning_rate": 1.0118753432180122e-05,
      "loss": 1.8912,
      "step": 141000
    },
    {
      "epoch": 9.12,
      "learning_rate": 9.432317408017572e-06,
      "loss": 1.8903,
      "step": 142000
    },
    {
      "epoch": 9.19,
      "learning_rate": 8.745881383855025e-06,
      "loss": 1.8892,
      "step": 143000
    },
    {
      "epoch": 9.25,
      "learning_rate": 8.059445359692478e-06,
      "loss": 1.8894,
      "step": 144000
    },
    {
      "epoch": 9.31,
      "learning_rate": 7.373695771554091e-06,
      "loss": 1.8906,
      "step": 145000
    },
    {
      "epoch": 9.38,
      "learning_rate": 6.6879461834157054e-06,
      "loss": 1.8913,
      "step": 146000
    },
    {
      "epoch": 9.44,
      "learning_rate": 6.001510159253158e-06,
      "loss": 1.8893,
      "step": 147000
    },
    {
      "epoch": 9.51,
      "learning_rate": 5.31507413509061e-06,
      "loss": 1.889,
      "step": 148000
    },
    {
      "epoch": 9.57,
      "learning_rate": 4.628638110928061e-06,
      "loss": 1.8894,
      "step": 149000
    },
    {
      "epoch": 9.64,
      "learning_rate": 3.942888522789677e-06,
      "loss": 1.8889,
      "step": 150000
    },
    {
      "epoch": 9.7,
      "learning_rate": 3.256452498627128e-06,
      "loss": 1.8899,
      "step": 151000
    },
    {
      "epoch": 9.76,
      "learning_rate": 2.5707029104887426e-06,
      "loss": 1.8881,
      "step": 152000
    },
    {
      "epoch": 9.83,
      "learning_rate": 1.8842668863261946e-06,
      "loss": 1.8868,
      "step": 153000
    },
    {
      "epoch": 9.89,
      "learning_rate": 1.1985172981878091e-06,
      "loss": 1.8879,
      "step": 154000
    },
    {
      "epoch": 9.96,
      "learning_rate": 5.120812740252608e-07,
      "loss": 1.8871,
      "step": 155000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5679064836390543,
      "eval_loss": 1.9183450937271118,
      "eval_runtime": 4.7588,
      "eval_samples_per_second": 599.309,
      "eval_steps_per_second": 4.833,
      "step": 155680
    },
    {
      "epoch": 10.0,
      "step": 155680,
      "total_flos": 1.30166022537216e+18,
      "train_loss": 2.0850467458413293,
      "train_runtime": 67879.3856,
      "train_samples_per_second": 293.558,
      "train_steps_per_second": 2.293
    }
  ],
  "max_steps": 155680,
  "num_train_epochs": 10,
  "total_flos": 1.30166022537216e+18,
  "trial_name": null,
  "trial_params": null
}