{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 285,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 7.583328114734628,
      "learning_rate": 5.517241379310345e-06,
      "loss": 0.5653,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.166676864027977,
      "step": 5,
      "valid_targets_mean": 3166.7,
      "valid_targets_min": 1420
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 3.1401618568879677,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 0.4991,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1019982397556305,
      "step": 10,
      "valid_targets_mean": 2351.6,
      "valid_targets_min": 1195
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.104245248825641,
      "learning_rate": 1.931034482758621e-05,
      "loss": 0.4163,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11541903018951416,
      "step": 15,
      "valid_targets_mean": 3168.0,
      "valid_targets_min": 1312
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.732712115494436,
      "learning_rate": 2.620689655172414e-05,
      "loss": 0.3658,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.12487722188234329,
      "step": 20,
      "valid_targets_mean": 3523.8,
      "valid_targets_min": 1517
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.5506644308788069,
      "learning_rate": 3.310344827586207e-05,
      "loss": 0.3378,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.08351944386959076,
      "step": 25,
      "valid_targets_mean": 3054.6,
      "valid_targets_min": 1110
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.5212168935643539,
      "learning_rate": 4e-05,
      "loss": 0.3227,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.08309619128704071,
      "step": 30,
      "valid_targets_mean": 2739.4,
      "valid_targets_min": 1178
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.37621279442640654,
      "learning_rate": 3.996236225800298e-05,
      "loss": 0.2841,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.058637700974941254,
      "step": 35,
      "valid_targets_mean": 3032.6,
      "valid_targets_min": 962
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.3740113710680447,
      "learning_rate": 3.9849590691974206e-05,
      "loss": 0.275,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.049976594746112823,
      "step": 40,
      "valid_targets_mean": 2221.6,
      "valid_targets_min": 1249
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3555541947187885,
      "learning_rate": 3.966210974862433e-05,
      "loss": 0.2829,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.047423090785741806,
      "step": 45,
      "valid_targets_mean": 2186.9,
      "valid_targets_min": 1183
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3614830806096002,
      "learning_rate": 3.940062506389089e-05,
      "loss": 0.2688,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07531788945198059,
      "step": 50,
      "valid_targets_mean": 2673.9,
      "valid_targets_min": 1141
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.35164636779651554,
      "learning_rate": 3.9066120807083875e-05,
      "loss": 0.2583,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0835060328245163,
      "step": 55,
      "valid_targets_mean": 3016.2,
      "valid_targets_min": 1526
    },
    {
      "epoch": 1.0533333333333332,
      "grad_norm": 0.4004740105789504,
      "learning_rate": 3.865985597669478e-05,
      "loss": 0.2609,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05621650442481041,
      "step": 60,
      "valid_targets_mean": 2221.8,
      "valid_targets_min": 1151
    },
    {
      "epoch": 1.1422222222222222,
      "grad_norm": 0.3362478514134072,
      "learning_rate": 3.818335966181045e-05,
      "loss": 0.2418,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06041599065065384,
      "step": 65,
      "valid_targets_mean": 2575.6,
      "valid_targets_min": 1126
    },
    {
      "epoch": 1.231111111111111,
      "grad_norm": 0.327805935004158,
      "learning_rate": 3.76384252869671e-05,
      "loss": 0.2527,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05153035372495651,
      "step": 70,
      "valid_targets_mean": 2401.1,
      "valid_targets_min": 1291
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.3344211876841236,
      "learning_rate": 3.702710386210531e-05,
      "loss": 0.2363,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0525384359061718,
      "step": 75,
      "valid_targets_mean": 2742.1,
      "valid_targets_min": 1147
    },
    {
      "epoch": 1.4088888888888889,
      "grad_norm": 0.3391981121560211,
      "learning_rate": 3.635169626303168e-05,
      "loss": 0.238,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06917819380760193,
      "step": 80,
      "valid_targets_mean": 3123.1,
      "valid_targets_min": 1190
    },
    {
      "epoch": 1.4977777777777779,
      "grad_norm": 0.32922754267793913,
      "learning_rate": 3.561474457144189e-05,
      "loss": 0.2449,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05151129886507988,
      "step": 85,
      "valid_targets_mean": 3233.1,
      "valid_targets_min": 1357
    },
    {
      "epoch": 1.5866666666666667,
      "grad_norm": 0.32706014931505833,
      "learning_rate": 3.4819022507099184e-05,
      "loss": 0.2223,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05639180168509483,
      "step": 90,
      "valid_targets_mean": 2922.6,
      "valid_targets_min": 1310
    },
    {
      "epoch": 1.6755555555555555,
      "grad_norm": 0.341988951356744,
      "learning_rate": 3.3967524988179463e-05,
      "loss": 0.2319,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.040721211582422256,
      "step": 95,
      "valid_targets_mean": 2238.1,
      "valid_targets_min": 1199
    },
    {
      "epoch": 1.7644444444444445,
      "grad_norm": 0.3543043397710712,
      "learning_rate": 3.306345685907553e-05,
      "loss": 0.2313,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03705868870019913,
      "step": 100,
      "valid_targets_mean": 2039.1,
      "valid_targets_min": 1054
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 0.3169475427171822,
      "learning_rate": 3.211022082808652e-05,
      "loss": 0.2231,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03866267204284668,
      "step": 105,
      "valid_targets_mean": 2269.2,
      "valid_targets_min": 1244
    },
    {
      "epoch": 1.942222222222222,
      "grad_norm": 0.3626154274513678,
      "learning_rate": 3.111140466039205e-05,
      "loss": 0.2454,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05644143745303154,
      "step": 110,
      "valid_targets_mean": 2740.2,
      "valid_targets_min": 1249
    },
    {
      "epoch": 2.017777777777778,
      "grad_norm": 0.3229168931990422,
      "learning_rate": 3.0070767674514355e-05,
      "loss": 0.231,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.045998841524124146,
      "step": 115,
      "valid_targets_mean": 2432.6,
      "valid_targets_min": 1365
    },
    {
      "epoch": 2.1066666666666665,
      "grad_norm": 0.4074227847296487,
      "learning_rate": 2.8992226593092135e-05,
      "loss": 0.2261,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.041235923767089844,
      "step": 120,
      "valid_targets_mean": 2494.5,
      "valid_targets_min": 1151
    },
    {
      "epoch": 2.1955555555555555,
      "grad_norm": 0.3124502564340804,
      "learning_rate": 2.7879840801220967e-05,
      "loss": 0.2109,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04943722486495972,
      "step": 125,
      "valid_targets_mean": 2937.8,
      "valid_targets_min": 1162
    },
    {
      "epoch": 2.2844444444444445,
      "grad_norm": 0.36347414667971645,
      "learning_rate": 2.6737797067844403e-05,
      "loss": 0.2205,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.041548021137714386,
      "step": 130,
      "valid_targets_mean": 2297.9,
      "valid_targets_min": 1539
    },
    {
      "epoch": 2.3733333333333335,
      "grad_norm": 0.3397949895260685,
      "learning_rate": 2.5570393787701063e-05,
      "loss": 0.2151,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07428301870822906,
      "step": 135,
      "valid_targets_mean": 3256.2,
      "valid_targets_min": 1340
    },
    {
      "epoch": 2.462222222222222,
      "grad_norm": 0.3409669850928538,
      "learning_rate": 2.4382024803137396e-05,
      "loss": 0.214,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05983541160821915,
      "step": 140,
      "valid_targets_mean": 2922.6,
      "valid_targets_min": 1264
    },
    {
      "epoch": 2.551111111111111,
      "grad_norm": 0.33002068625976483,
      "learning_rate": 2.317716286667723e-05,
      "loss": 0.2169,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05062925070524216,
      "step": 145,
      "valid_targets_mean": 2481.7,
      "valid_targets_min": 1088
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.3116815064192726,
      "learning_rate": 2.196034280659122e-05,
      "loss": 0.2099,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03972204774618149,
      "step": 150,
      "valid_targets_mean": 2388.9,
      "valid_targets_min": 1028
    },
    {
      "epoch": 2.728888888888889,
      "grad_norm": 0.32691657273888747,
      "learning_rate": 2.073614445882718e-05,
      "loss": 0.2243,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05966932699084282,
      "step": 155,
      "valid_targets_mean": 2523.2,
      "valid_targets_min": 1338
    },
    {
      "epoch": 2.8177777777777777,
      "grad_norm": 0.32702194667234424,
      "learning_rate": 1.950917542954176e-05,
      "loss": 0.22,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05485967546701431,
      "step": 160,
      "valid_targets_mean": 2835.8,
      "valid_targets_min": 1045
    },
    {
      "epoch": 2.9066666666666667,
      "grad_norm": 0.3371678153197184,
      "learning_rate": 1.8284053753111205e-05,
      "loss": 0.2104,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.034001681953668594,
      "step": 165,
      "valid_targets_mean": 2010.9,
      "valid_targets_min": 1203
    },
    {
      "epoch": 2.9955555555555557,
      "grad_norm": 0.3400453584476225,
      "learning_rate": 1.7065390510892767e-05,
      "loss": 0.2065,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04110487177968025,
      "step": 170,
      "valid_targets_mean": 2373.1,
      "valid_targets_min": 1131
    },
    {
      "epoch": 3.071111111111111,
      "grad_norm": 0.29868424312125685,
      "learning_rate": 1.5857772476155634e-05,
      "loss": 0.2018,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05249975621700287,
      "step": 175,
      "valid_targets_mean": 3154.9,
      "valid_targets_min": 1178
    },
    {
      "epoch": 3.16,
      "grad_norm": 0.3706098125869751,
      "learning_rate": 1.4665744850502035e-05,
      "loss": 0.2145,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.055659279227256775,
      "step": 180,
      "valid_targets_mean": 2609.7,
      "valid_targets_min": 1283
    },
    {
      "epoch": 3.2488888888888887,
      "grad_norm": 0.34761594185958783,
      "learning_rate": 1.3493794156754744e-05,
      "loss": 0.2129,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03931069374084473,
      "step": 185,
      "valid_targets_mean": 2712.7,
      "valid_targets_min": 1002
    },
    {
      "epoch": 3.3377777777777777,
      "grad_norm": 0.3480472578827022,
      "learning_rate": 1.2346331352698206e-05,
      "loss": 0.2032,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06302663683891296,
      "step": 190,
      "valid_targets_mean": 2542.1,
      "valid_targets_min": 1383
    },
    {
      "epoch": 3.4266666666666667,
      "grad_norm": 0.35674083440708165,
      "learning_rate": 1.1227675229229453e-05,
      "loss": 0.1997,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06049852818250656,
      "step": 195,
      "valid_targets_mean": 2524.8,
      "valid_targets_min": 993
    },
    {
      "epoch": 3.5155555555555553,
      "grad_norm": 0.33660537404764074,
      "learning_rate": 1.0142036155404322e-05,
      "loss": 0.2092,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04671245440840721,
      "step": 200,
      "valid_targets_mean": 2890.4,
      "valid_targets_min": 388
    },
    {
      "epoch": 3.6044444444444443,
      "grad_norm": 0.4234454768211141,
      "learning_rate": 9.093500231559076e-06,
      "loss": 0.1932,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.039773087948560715,
      "step": 205,
      "valid_targets_mean": 2687.6,
      "valid_targets_min": 1134
    },
    {
      "epoch": 3.6933333333333334,
      "grad_norm": 0.3462492949486452,
      "learning_rate": 8.086013910151334e-06,
      "loss": 0.206,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0793825015425682,
      "step": 210,
      "valid_targets_mean": 3072.4,
      "valid_targets_min": 1523
    },
    {
      "epoch": 3.7822222222222224,
      "grad_norm": 0.33043166323357076,
      "learning_rate": 7.123369142204175e-06,
      "loss": 0.1978,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05091720446944237,
      "step": 215,
      "valid_targets_mean": 2395.9,
      "valid_targets_min": 1181
    },
    {
      "epoch": 3.871111111111111,
      "grad_norm": 0.3276021134703391,
      "learning_rate": 6.209189105258661e-06,
      "loss": 0.1978,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04009982943534851,
      "step": 220,
      "valid_targets_mean": 2544.8,
      "valid_targets_min": 1459
    },
    {
      "epoch": 3.96,
      "grad_norm": 0.3518358226857207,
      "learning_rate": 5.346914566551746e-06,
      "loss": 0.2057,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05190512537956238,
      "step": 225,
      "valid_targets_mean": 2315.4,
      "valid_targets_min": 1089
    },
    {
      "epoch": 4.035555555555556,
      "grad_norm": 0.446701948663916,
      "learning_rate": 4.53979093274526e-06,
      "loss": 0.1909,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04597758501768112,
      "step": 230,
      "valid_targets_mean": 2736.4,
      "valid_targets_min": 1155
    },
    {
      "epoch": 4.124444444444444,
      "grad_norm": 0.3070256238047938,
      "learning_rate": 3.7908560349481072e-06,
      "loss": 0.1998,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05320999398827553,
      "step": 235,
      "valid_targets_mean": 3201.8,
      "valid_targets_min": 1119
    },
    {
      "epoch": 4.213333333333333,
      "grad_norm": 0.3084555402280151,
      "learning_rate": 3.102928695005858e-06,
      "loss": 0.1975,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.029193339869379997,
      "step": 240,
      "valid_targets_mean": 1924.7,
      "valid_targets_min": 1318
    },
    {
      "epoch": 4.302222222222222,
      "grad_norm": 0.33282212562089014,
      "learning_rate": 2.4785981160918703e-06,
      "loss": 0.2001,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04285688325762749,
      "step": 245,
      "valid_targets_mean": 2463.9,
      "valid_targets_min": 1178
    },
    {
      "epoch": 4.391111111111111,
      "grad_norm": 0.3167323683701005,
      "learning_rate": 1.9202141375311335e-06,
      "loss": 0.2013,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04943656548857689,
      "step": 250,
      "valid_targets_mean": 2726.8,
      "valid_targets_min": 1173
    },
    {
      "epoch": 4.48,
      "grad_norm": 0.33351932332643597,
      "learning_rate": 1.4298783905356906e-06,
      "loss": 0.1954,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04813677817583084,
      "step": 255,
      "valid_targets_mean": 2432.7,
      "valid_targets_min": 942
    },
    {
      "epoch": 4.568888888888889,
      "grad_norm": 0.3163118446536364,
      "learning_rate": 1.0094363881392665e-06,
      "loss": 0.1975,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06139428913593292,
      "step": 260,
      "valid_targets_mean": 3001.4,
      "valid_targets_min": 1329
    },
    {
      "epoch": 4.657777777777778,
      "grad_norm": 0.33335357258605675,
      "learning_rate": 6.604705791029586e-07,
      "loss": 0.1987,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.044643834233284,
      "step": 265,
      "valid_targets_mean": 2461.6,
      "valid_targets_min": 1178
    },
    {
      "epoch": 4.746666666666667,
      "grad_norm": 0.33713590138912286,
      "learning_rate": 3.842943919353914e-07,
      "loss": 0.1881,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03312596306204796,
      "step": 270,
      "valid_targets_mean": 2348.8,
      "valid_targets_min": 1282
    },
    {
      "epoch": 4.835555555555556,
      "grad_norm": 0.32804179691400653,
      "learning_rate": 1.819472914443998e-07,
      "loss": 0.207,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03083619847893715,
      "step": 275,
      "valid_targets_mean": 2106.2,
      "valid_targets_min": 1274
    },
    {
      "epoch": 4.924444444444444,
      "grad_norm": 0.3250869471276454,
      "learning_rate": 5.4190866426195866e-08,
      "loss": 0.1982,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04578050225973129,
      "step": 280,
      "valid_targets_mean": 2654.6,
      "valid_targets_min": 1454
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6141969340231087,
      "learning_rate": 1.5059632171099402e-09,
      "loss": 0.2007,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.2248307466506958,
      "step": 285,
      "valid_targets_mean": 2971.6,
      "valid_targets_min": 1283
    },
    {
      "epoch": 5.0,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.2248307466506958,
      "step": 285,
      "total_flos": 3.151185311610962e+17,
      "train_loss": 0.24082276695653013,
      "train_runtime": 3979.0496,
      "train_samples_per_second": 4.505,
      "train_steps_per_second": 0.072,
      "valid_targets_mean": 2971.6,
      "valid_targets_min": 1283
    }
  ],
  "logging_steps": 5,
  "max_steps": 285,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.151185311610962e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}