{
  "best_metric": 3.7859156131744385,
  "best_model_checkpoint": "seq2seq_results/combined_nl_prompt_base_features_baseline_codet5small/checkpoint-144856",
  "epoch": 2.0,
  "global_step": 144856,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.001999861931849561,
      "loss": 4.6701,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.001999723863699122,
      "loss": 4.3041,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001999585795548683,
      "loss": 4.37,
      "step": 1500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019994477273982438,
      "loss": 4.3707,
      "step": 2000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019993096592478047,
      "loss": 4.4073,
      "step": 2500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019991715910973656,
      "loss": 4.34,
      "step": 3000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001999033522946927,
      "loss": 4.377,
      "step": 3500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019988954547964875,
      "loss": 4.3965,
      "step": 4000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019987573866460484,
      "loss": 4.3162,
      "step": 4500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019986193184956093,
      "loss": 4.4539,
      "step": 5000
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019984812503451702,
      "loss": 4.4049,
      "step": 5500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001998343182194731,
      "loss": 4.4302,
      "step": 6000
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001998205114044292,
      "loss": 4.4396,
      "step": 6500
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001998067045893853,
      "loss": 4.3968,
      "step": 7000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019979289777434144,
      "loss": 4.3686,
      "step": 7500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019977909095929753,
      "loss": 4.2784,
      "step": 8000
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019976528414425362,
      "loss": 4.3356,
      "step": 8500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001997514773292097,
      "loss": 4.3909,
      "step": 9000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001997376705141658,
      "loss": 4.3739,
      "step": 9500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001997238636991219,
      "loss": 4.364,
      "step": 10000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00199710056884078,
      "loss": 4.3889,
      "step": 10500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001996962500690341,
      "loss": 4.3619,
      "step": 11000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001996824432539902,
      "loss": 4.2707,
      "step": 11500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019966863643894627,
      "loss": 4.3321,
      "step": 12000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019965482962390237,
      "loss": 4.337,
      "step": 12500
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0019964102280885846,
      "loss": 4.3264,
      "step": 13000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0019962721599381455,
      "loss": 4.2258,
      "step": 13500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0019961340917877064,
      "loss": 4.2702,
      "step": 14000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0019959960236372674,
      "loss": 4.2741,
      "step": 14500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0019958579554868283,
      "loss": 4.173,
      "step": 15000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0019957198873363892,
      "loss": 4.2405,
      "step": 15500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00199558181918595,
      "loss": 4.1739,
      "step": 16000
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001995443751035511,
      "loss": 4.2301,
      "step": 16500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001995305682885072,
      "loss": 4.1023,
      "step": 17000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001995167614734633,
      "loss": 4.1918,
      "step": 17500
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0019950295465841943,
      "loss": 4.2123,
      "step": 18000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001994891478433755,
      "loss": 4.1345,
      "step": 18500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0019947534102833157,
      "loss": 4.0942,
      "step": 19000
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0019946153421328766,
      "loss": 4.1234,
      "step": 19500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0019944772739824376,
      "loss": 4.1437,
      "step": 20000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0019943392058319985,
      "loss": 4.0807,
      "step": 20500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0019942011376815594,
      "loss": 4.1128,
      "step": 21000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001994063069531121,
      "loss": 4.1238,
      "step": 21500
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0019939250013806817,
      "loss": 4.1071,
      "step": 22000
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0019937869332302426,
      "loss": 4.1466,
      "step": 22500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0019936488650798036,
      "loss": 4.1327,
      "step": 23000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0019935107969293645,
      "loss": 4.0238,
      "step": 23500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0019933727287789254,
      "loss": 4.1153,
      "step": 24000
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0019932346606284864,
      "loss": 4.04,
      "step": 24500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0019930965924780473,
      "loss": 4.0657,
      "step": 25000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001992958524327608,
      "loss": 4.1566,
      "step": 25500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001992820456177169,
      "loss": 4.1009,
      "step": 26000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00199268238802673,
      "loss": 4.0373,
      "step": 26500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001992544319876291,
      "loss": 4.1002,
      "step": 27000
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001992406251725852,
      "loss": 4.0799,
      "step": 27500
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001992268183575413,
      "loss": 4.1071,
      "step": 28000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0019921301154249738,
      "loss": 4.004,
      "step": 28500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0019919920472745347,
      "loss": 4.0756,
      "step": 29000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0019918539791240956,
      "loss": 4.0442,
      "step": 29500
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0019917159109736566,
      "loss": 4.0467,
      "step": 30000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0019915778428232175,
      "loss": 3.9504,
      "step": 30500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0019914397746727784,
      "loss": 4.0131,
      "step": 31000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0019913017065223393,
      "loss": 3.9668,
      "step": 31500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0019911636383719007,
      "loss": 4.0255,
      "step": 32000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001991025570221461,
      "loss": 3.9381,
      "step": 32500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001990887502071022,
      "loss": 4.0031,
      "step": 33000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001990749433920583,
      "loss": 3.9848,
      "step": 33500
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001990611365770144,
      "loss": 4.0021,
      "step": 34000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001990473297619705,
      "loss": 4.0027,
      "step": 34500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001990335229469266,
      "loss": 3.9172,
      "step": 35000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001990197161318827,
      "loss": 3.9527,
      "step": 35500
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001990059093168388,
      "loss": 3.9484,
      "step": 36000
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001989921025017949,
      "loss": 3.9383,
      "step": 36500
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00198978295686751,
      "loss": 3.9678,
      "step": 37000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.001989644888717071,
      "loss": 3.9641,
      "step": 37500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.001989506820566632,
      "loss": 3.9309,
      "step": 38000
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0019893687524161928,
      "loss": 3.9796,
      "step": 38500
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0019892306842657537,
      "loss": 3.8781,
      "step": 39000
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0019890926161153146,
      "loss": 3.9941,
      "step": 39500
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0019889545479648755,
      "loss": 3.9713,
      "step": 40000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0019888164798144365,
      "loss": 4.0011,
      "step": 40500
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0019886784116639974,
      "loss": 3.9279,
      "step": 41000
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0019885403435135583,
      "loss": 3.9176,
      "step": 41500
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0019884022753631193,
      "loss": 3.9786,
      "step": 42000
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00198826420721268,
      "loss": 4.0188,
      "step": 42500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.001988126139062241,
      "loss": 3.9148,
      "step": 43000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.001987988070911802,
      "loss": 3.9541,
      "step": 43500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.001987850002761363,
      "loss": 3.9026,
      "step": 44000
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.001987711934610924,
      "loss": 3.9408,
      "step": 44500
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.001987573866460485,
      "loss": 3.9297,
      "step": 45000
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0019874357983100457,
      "loss": 3.8746,
      "step": 45500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.001987297730159607,
      "loss": 3.9165,
      "step": 46000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.001987159662009168,
      "loss": 3.9406,
      "step": 46500
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0019870215938587285,
      "loss": 3.934,
      "step": 47000
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0019868835257082895,
      "loss": 3.9324,
      "step": 47500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0019867454575578504,
      "loss": 3.9349,
      "step": 48000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0019866073894074113,
      "loss": 3.9627,
      "step": 48500
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0019864693212569722,
      "loss": 3.9866,
      "step": 49000
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0019863312531065336,
      "loss": 3.9169,
      "step": 49500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0019861931849560945,
      "loss": 3.9981,
      "step": 50000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0019860551168056555,
      "loss": 3.9435,
      "step": 50500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0019859170486552164,
      "loss": 3.9869,
      "step": 51000
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0019857789805047773,
      "loss": 3.8722,
      "step": 51500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019856409123543382,
      "loss": 4.038,
      "step": 52000
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001985502844203899,
      "loss": 3.9329,
      "step": 52500
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00198536477605346,
      "loss": 3.9034,
      "step": 53000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.001985226707903021,
      "loss": 3.9563,
      "step": 53500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001985088639752582,
      "loss": 3.9504,
      "step": 54000
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001984950571602143,
      "loss": 3.9527,
      "step": 54500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001984812503451704,
      "loss": 4.0248,
      "step": 55000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0019846744353012647,
      "loss": 3.9452,
      "step": 55500
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0019845363671508257,
      "loss": 4.023,
      "step": 56000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0019843982990003866,
      "loss": 4.1163,
      "step": 56500
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0019842602308499475,
      "loss": 4.0406,
      "step": 57000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0019841221626995084,
      "loss": 3.9629,
      "step": 57500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0019839840945490694,
      "loss": 4.0088,
      "step": 58000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0019838460263986303,
      "loss": 4.0681,
      "step": 58500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0019837079582481912,
      "loss": 4.0537,
      "step": 59000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.001983569890097752,
      "loss": 4.0625,
      "step": 59500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0019834318219473135,
      "loss": 4.1052,
      "step": 60000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0019832937537968744,
      "loss": 4.1331,
      "step": 60500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0019831556856464354,
      "loss": 4.1319,
      "step": 61000
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.001983017617495996,
      "loss": 4.0927,
      "step": 61500
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0019828795493455568,
      "loss": 4.0494,
      "step": 62000
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0019827414811951177,
      "loss": 4.1262,
      "step": 62500
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0019826034130446786,
      "loss": 3.9996,
      "step": 63000
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00198246534489424,
      "loss": 4.0418,
      "step": 63500
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.001982327276743801,
      "loss": 3.976,
      "step": 64000
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.001982189208593362,
      "loss": 4.0928,
      "step": 64500
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0019820511404429228,
      "loss": 4.1164,
      "step": 65000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0019819130722924837,
      "loss": 3.9452,
      "step": 65500
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0019817750041420446,
      "loss": 4.033,
      "step": 66000
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0019816369359916056,
      "loss": 3.9945,
      "step": 66500
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0019814988678411665,
      "loss": 3.9676,
      "step": 67000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0019813607996907274,
      "loss": 4.0068,
      "step": 67500
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0019812227315402883,
      "loss": 3.9709,
      "step": 68000
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0019810846633898493,
      "loss": 4.0048,
      "step": 68500
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00198094659523941,
      "loss": 3.995,
      "step": 69000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.001980808527088971,
      "loss": 4.064,
      "step": 69500
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.001980670458938532,
      "loss": 4.0621,
      "step": 70000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.001980532390788093,
      "loss": 4.0397,
      "step": 70500
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.001980394322637654,
      "loss": 4.1456,
      "step": 71000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.001980256254487215,
      "loss": 4.0672,
      "step": 71500
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0019801181863367758,
      "loss": 4.0551,
      "step": 72000
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.511486530303955,
      "eval_runtime": 111.9469,
      "eval_samples_per_second": 176.432,
      "eval_steps_per_second": 11.032,
      "step": 72428
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0019799801181863367,
      "loss": 4.1848,
      "step": 72500
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0019798420500358976,
      "loss": 4.0794,
      "step": 73000
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0019797039818854585,
      "loss": 4.1764,
      "step": 73500
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00197956591373502,
      "loss": 4.086,
      "step": 74000
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.001979427845584581,
      "loss": 4.0969,
      "step": 74500
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0019792897774341418,
      "loss": 4.1175,
      "step": 75000
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0019791517092837027,
      "loss": 4.0663,
      "step": 75500
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.001979013641133263,
      "loss": 4.0281,
      "step": 76000
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.001978875572982824,
      "loss": 4.1221,
      "step": 76500
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.001978737504832385,
      "loss": 4.2072,
      "step": 77000
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0019785994366819464,
      "loss": 4.0445,
      "step": 77500
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0019784613685315073,
      "loss": 4.1667,
      "step": 78000
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0019783233003810683,
      "loss": 4.1388,
      "step": 78500
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.001978185232230629,
      "loss": 4.1253,
      "step": 79000
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00197804716408019,
      "loss": 4.1804,
      "step": 79500
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.001977909095929751,
      "loss": 4.0465,
      "step": 80000
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.001977771027779312,
      "loss": 4.01,
      "step": 80500
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.001977632959628873,
      "loss": 4.0643,
      "step": 81000
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.001977494891478434,
      "loss": 4.0639,
      "step": 81500
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0019773568233279947,
      "loss": 4.0322,
      "step": 82000
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0019772187551775557,
      "loss": 4.0383,
      "step": 82500
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0019770806870271166,
      "loss": 4.0777,
      "step": 83000
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0019769426188766775,
      "loss": 4.0972,
      "step": 83500
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0019768045507262385,
      "loss": 4.1713,
      "step": 84000
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0019766664825757994,
      "loss": 4.0441,
      "step": 84500
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0019765284144253603,
      "loss": 4.0923,
      "step": 85000
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0019763903462749212,
      "loss": 4.0889,
      "step": 85500
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.001976252278124482,
      "loss": 4.0687,
      "step": 86000
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.001976114209974043,
      "loss": 4.0273,
      "step": 86500
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.001975976141823604,
      "loss": 4.1192,
      "step": 87000
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.001975838073673165,
      "loss": 4.0272,
      "step": 87500
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0019757000055227263,
      "loss": 4.054,
      "step": 88000
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0019755619373722872,
      "loss": 4.0947,
      "step": 88500
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.001975423869221848,
      "loss": 4.1307,
      "step": 89000
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.001975285801071409,
      "loss": 4.0405,
      "step": 89500
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00197514773292097,
      "loss": 4.0817,
      "step": 90000
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0019750096647705305,
      "loss": 4.0129,
      "step": 90500
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0019748715966200914,
      "loss": 4.1245,
      "step": 91000
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.001974733528469653,
      "loss": 4.0581,
      "step": 91500
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0019745954603192137,
      "loss": 4.0563,
      "step": 92000
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0019744573921687747,
      "loss": 4.0469,
      "step": 92500
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0019743193240183356,
      "loss": 3.978,
      "step": 93000
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0019741812558678965,
      "loss": 3.941,
      "step": 93500
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0019740431877174574,
      "loss": 4.0216,
      "step": 94000
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0019739051195670184,
      "loss": 4.0471,
      "step": 94500
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0019737670514165793,
      "loss": 3.9967,
      "step": 95000
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0019736289832661402,
      "loss": 4.0091,
      "step": 95500
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.001973490915115701,
      "loss": 3.9558,
      "step": 96000
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.001973352846965262,
      "loss": 4.0075,
      "step": 96500
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.001973214778814823,
      "loss": 3.9662,
      "step": 97000
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.001973076710664384,
      "loss": 3.9896,
      "step": 97500
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.001972938642513945,
      "loss": 4.0709,
      "step": 98000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.001972800574363506,
      "loss": 4.0645,
      "step": 98500
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0019726625062130667,
      "loss": 4.0215,
      "step": 99000
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0019725244380626276,
      "loss": 4.0326,
      "step": 99500
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0019723863699121886,
      "loss": 3.9966,
      "step": 100000
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0019722483017617495,
      "loss": 4.0232,
      "step": 100500
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0019721102336113104,
      "loss": 4.0139,
      "step": 101000
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0019719721654608714,
      "loss": 4.0067,
      "step": 101500
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0019718340973104327,
      "loss": 3.9949,
      "step": 102000
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0019716960291599936,
      "loss": 4.0542,
      "step": 102500
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0019715579610095546,
      "loss": 3.9849,
      "step": 103000
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0019714198928591155,
      "loss": 4.119,
      "step": 103500
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0019712818247086764,
      "loss": 3.9913,
      "step": 104000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.001971143756558237,
      "loss": 4.0074,
      "step": 104500
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.001971005688407798,
      "loss": 3.9604,
      "step": 105000
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.001970867620257359,
      "loss": 4.0134,
      "step": 105500
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00197072955210692,
      "loss": 4.021,
      "step": 106000
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.001970591483956481,
      "loss": 3.9878,
      "step": 106500
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.001970453415806042,
      "loss": 3.9759,
      "step": 107000
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.001970315347655603,
      "loss": 3.9569,
      "step": 107500
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.001970177279505164,
      "loss": 3.9763,
      "step": 108000
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0019700392113547248,
      "loss": 3.8924,
      "step": 108500
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0019699011432042857,
      "loss": 3.9378,
      "step": 109000
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0019697630750538466,
      "loss": 3.9423,
      "step": 109500
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0019696250069034076,
      "loss": 3.9732,
      "step": 110000
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0019694869387529685,
      "loss": 3.961,
      "step": 110500
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0019693488706025294,
      "loss": 3.9872,
      "step": 111000
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0019692108024520903,
      "loss": 3.9157,
      "step": 111500
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0019690727343016513,
      "loss": 3.9561,
      "step": 112000
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.001968934666151212,
      "loss": 3.9836,
      "step": 112500
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.001968796598000773,
      "loss": 3.8875,
      "step": 113000
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.001968658529850334,
      "loss": 3.8598,
      "step": 113500
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.001968520461699895,
      "loss": 4.0,
      "step": 114000
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.001968382393549456,
      "loss": 3.976,
      "step": 114500
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.001968244325399017,
      "loss": 4.0193,
      "step": 115000
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0019681062572485778,
      "loss": 4.027,
      "step": 115500
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.001967968189098139,
      "loss": 4.0129,
      "step": 116000
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0019678301209477,
      "loss": 3.9996,
      "step": 116500
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.001967692052797261,
      "loss": 3.8491,
      "step": 117000
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.001967553984646822,
      "loss": 3.9668,
      "step": 117500
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.001967415916496383,
      "loss": 3.9194,
      "step": 118000
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0019672778483459438,
      "loss": 3.8736,
      "step": 118500
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0019671397801955042,
      "loss": 3.9618,
      "step": 119000
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0019670017120450656,
      "loss": 3.9653,
      "step": 119500
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0019668636438946265,
      "loss": 3.8935,
      "step": 120000
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0019667255757441875,
      "loss": 3.9393,
      "step": 120500
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0019665875075937484,
      "loss": 3.8719,
      "step": 121000
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0019664494394433093,
      "loss": 3.881,
      "step": 121500
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0019663113712928702,
      "loss": 3.7973,
      "step": 122000
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.001966173303142431,
      "loss": 3.8897,
      "step": 122500
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.001966035234991992,
      "loss": 3.8499,
      "step": 123000
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.001965897166841553,
      "loss": 3.8924,
      "step": 123500
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.001965759098691114,
      "loss": 3.9056,
      "step": 124000
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.001965621030540675,
      "loss": 4.0077,
      "step": 124500
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.001965482962390236,
      "loss": 3.8725,
      "step": 125000
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0019653448942397967,
      "loss": 4.0384,
      "step": 125500
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0019652068260893577,
      "loss": 4.0188,
      "step": 126000
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0019650687579389186,
      "loss": 3.9961,
      "step": 126500
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0019649306897884795,
      "loss": 3.9249,
      "step": 127000
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0019647926216380404,
      "loss": 3.9624,
      "step": 127500
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0019646545534876014,
      "loss": 3.9348,
      "step": 128000
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0019645164853371623,
      "loss": 3.9695,
      "step": 128500
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0019643784171867232,
      "loss": 3.9816,
      "step": 129000
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.001964240349036284,
      "loss": 3.9832,
      "step": 129500
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0019641022808858455,
      "loss": 3.9284,
      "step": 130000
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0019639642127354064,
      "loss": 3.9135,
      "step": 130500
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0019638261445849674,
      "loss": 3.9262,
      "step": 131000
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0019636880764345283,
      "loss": 3.8446,
      "step": 131500
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0019635500082840892,
      "loss": 3.8439,
      "step": 132000
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00196341194013365,
      "loss": 3.9125,
      "step": 132500
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.001963273871983211,
      "loss": 3.9033,
      "step": 133000
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0019631358038327716,
      "loss": 3.8268,
      "step": 133500
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.001962997735682333,
      "loss": 3.8309,
      "step": 134000
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.001962859667531894,
      "loss": 3.8943,
      "step": 134500
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.001962721599381455,
      "loss": 3.8645,
      "step": 135000
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0019625835312310157,
      "loss": 3.8826,
      "step": 135500
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0019624454630805767,
      "loss": 3.8056,
      "step": 136000
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0019623073949301376,
      "loss": 3.835,
      "step": 136500
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0019621693267796985,
      "loss": 3.801,
      "step": 137000
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0019620312586292594,
      "loss": 3.7232,
      "step": 137500
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0019618931904788204,
      "loss": 3.7806,
      "step": 138000
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0019617551223283813,
      "loss": 3.8155,
      "step": 138500
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.001961617054177942,
      "loss": 3.8579,
      "step": 139000
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.001961478986027503,
      "loss": 3.8498,
      "step": 139500
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.001961340917877064,
      "loss": 3.8688,
      "step": 140000
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.001961202849726625,
      "loss": 3.7867,
      "step": 140500
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.001961064781576186,
      "loss": 3.7469,
      "step": 141000
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.001960926713425747,
      "loss": 3.862,
      "step": 141500
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0019607886452753078,
      "loss": 3.9004,
      "step": 142000
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0019606505771248687,
      "loss": 3.8185,
      "step": 142500
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0019605125089744296,
      "loss": 3.8896,
      "step": 143000
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0019603744408239906,
      "loss": 3.9049,
      "step": 143500
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0019602363726735515,
      "loss": 3.8464,
      "step": 144000
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.001960098304523113,
      "loss": 3.7932,
      "step": 144500
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.7859156131744385,
      "eval_runtime": 111.4844,
      "eval_samples_per_second": 177.164,
      "eval_steps_per_second": 11.078,
      "step": 144856
    }
  ],
  "max_steps": 7242800,
  "num_train_epochs": 100,
  "total_flos": 3.136735727635661e+17,
  "trial_name": null,
  "trial_params": null
}