{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 5.43838668916967,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.768,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.20029328763484955,
      "step": 5,
      "valid_targets_mean": 3894.4,
      "valid_targets_min": 1551
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.8173704060845222,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.6809,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.12393468618392944,
      "step": 10,
      "valid_targets_mean": 3313.9,
      "valid_targets_min": 658
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.8994415488525478,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 0.6367,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.15267133712768555,
      "step": 15,
      "valid_targets_mean": 3214.2,
      "valid_targets_min": 748
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.5231491285791463,
      "learning_rate": 3.0400000000000004e-05,
      "loss": 0.603,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1451815664768219,
      "step": 20,
      "valid_targets_mean": 4062.5,
      "valid_targets_min": 752
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 0.48610136532802667,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.5739,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.15977895259857178,
      "step": 25,
      "valid_targets_mean": 4920.6,
      "valid_targets_min": 689
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.3657562059313739,
      "learning_rate": 3.9968815283639625e-05,
      "loss": 0.531,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.12183522433042526,
      "step": 30,
      "valid_targets_mean": 4170.1,
      "valid_targets_min": 848
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 0.3117441303599555,
      "learning_rate": 3.9842294026289565e-05,
      "loss": 0.5137,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11094912886619568,
      "step": 35,
      "valid_targets_mean": 4246.0,
      "valid_targets_min": 626
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.31427213112004465,
      "learning_rate": 3.9619103106983835e-05,
      "loss": 0.5033,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11524395644664764,
      "step": 40,
      "valid_targets_mean": 3335.3,
      "valid_targets_min": 589
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.27843711420334,
      "learning_rate": 3.930032988944623e-05,
      "loss": 0.4921,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.12719261646270752,
      "step": 45,
      "valid_targets_mean": 4673.1,
      "valid_targets_min": 842
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.35336756908591643,
      "learning_rate": 3.888752740474962e-05,
      "loss": 0.4725,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.23522385954856873,
      "step": 50,
      "valid_targets_mean": 4525.1,
      "valid_targets_min": 618
    },
    {
      "epoch": 1.101010101010101,
      "grad_norm": 0.2618047514835116,
      "learning_rate": 3.838270678510469e-05,
      "loss": 0.4631,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0997854694724083,
      "step": 55,
      "valid_targets_mean": 3254.4,
      "valid_targets_min": 620
    },
    {
      "epoch": 1.202020202020202,
      "grad_norm": 0.2596681731982267,
      "learning_rate": 3.778832746582596e-05,
      "loss": 0.4695,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.15060186386108398,
      "step": 60,
      "valid_targets_mean": 5336.2,
      "valid_targets_min": 994
    },
    {
      "epoch": 1.303030303030303,
      "grad_norm": 0.26134191299357834,
      "learning_rate": 3.710728520321014e-05,
      "loss": 0.4622,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10998662561178207,
      "step": 65,
      "valid_targets_mean": 3828.9,
      "valid_targets_min": 813
    },
    {
      "epoch": 1.404040404040404,
      "grad_norm": 0.2505910129541225,
      "learning_rate": 3.634289796670257e-05,
      "loss": 0.4639,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11412525177001953,
      "step": 70,
      "valid_targets_mean": 4118.6,
      "valid_targets_min": 589
    },
    {
      "epoch": 1.5050505050505052,
      "grad_norm": 0.28469306377718256,
      "learning_rate": 3.549888977408359e-05,
      "loss": 0.4547,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10224676132202148,
      "step": 75,
      "valid_targets_mean": 3621.8,
      "valid_targets_min": 807
    },
    {
      "epoch": 1.606060606060606,
      "grad_norm": 0.26506094775038846,
      "learning_rate": 3.457937254842823e-05,
      "loss": 0.4478,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1216074526309967,
      "step": 80,
      "valid_targets_mean": 4121.2,
      "valid_targets_min": 900
    },
    {
      "epoch": 1.7070707070707072,
      "grad_norm": 0.27422041538604486,
      "learning_rate": 3.3588826085230336e-05,
      "loss": 0.4405,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09807954728603363,
      "step": 85,
      "valid_targets_mean": 3189.9,
      "valid_targets_min": 777
    },
    {
      "epoch": 1.808080808080808,
      "grad_norm": 0.25008604850493343,
      "learning_rate": 3.253207622728921e-05,
      "loss": 0.441,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11396118998527527,
      "step": 90,
      "valid_targets_mean": 4577.4,
      "valid_targets_min": 875
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.26410650818418535,
      "learning_rate": 3.141427135368864e-05,
      "loss": 0.4447,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10761921852827072,
      "step": 95,
      "valid_targets_mean": 3803.5,
      "valid_targets_min": 613
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.37011104936880673,
      "learning_rate": 3.024085729741143e-05,
      "loss": 0.4481,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.254130095243454,
      "step": 100,
      "valid_targets_mean": 4326.2,
      "valid_targets_min": 550
    },
    {
      "epoch": 2.101010101010101,
      "grad_norm": 0.2633444829921788,
      "learning_rate": 2.9017550813788616e-05,
      "loss": 0.4286,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10730044543743134,
      "step": 105,
      "valid_targets_mean": 4681.4,
      "valid_targets_min": 808
    },
    {
      "epoch": 2.202020202020202,
      "grad_norm": 0.27947047290967925,
      "learning_rate": 2.7750311729042062e-05,
      "loss": 0.4249,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11274366080760956,
      "step": 110,
      "valid_targets_mean": 4363.5,
      "valid_targets_min": 721
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 0.26878537952096837,
      "learning_rate": 2.6445313904610227e-05,
      "loss": 0.4319,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10825060307979584,
      "step": 115,
      "valid_targets_mean": 3570.9,
      "valid_targets_min": 740
    },
    {
      "epoch": 2.404040404040404,
      "grad_norm": 0.27801838465637635,
      "learning_rate": 2.510891515871581e-05,
      "loss": 0.4335,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09939642250537872,
      "step": 120,
      "valid_targets_mean": 3389.2,
      "valid_targets_min": 712
    },
    {
      "epoch": 2.505050505050505,
      "grad_norm": 0.26781305081846457,
      "learning_rate": 2.37476262917145e-05,
      "loss": 0.4247,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.109991654753685,
      "step": 125,
      "valid_targets_mean": 4646.0,
      "valid_targets_min": 748
    },
    {
      "epoch": 2.606060606060606,
      "grad_norm": 0.26237181084548494,
      "learning_rate": 2.2368079366130028e-05,
      "loss": 0.4187,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11524119973182678,
      "step": 130,
      "valid_targets_mean": 4932.1,
      "valid_targets_min": 845
    },
    {
      "epoch": 2.707070707070707,
      "grad_norm": 0.2585522405239844,
      "learning_rate": 2.097699539591227e-05,
      "loss": 0.4274,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.08941829204559326,
      "step": 135,
      "valid_targets_mean": 3169.6,
      "valid_targets_min": 832
    },
    {
      "epoch": 2.808080808080808,
      "grad_norm": 0.26016350721342923,
      "learning_rate": 1.9581151602332865e-05,
      "loss": 0.4177,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1133737787604332,
      "step": 140,
      "valid_targets_mean": 5011.3,
      "valid_targets_min": 1002
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.27030558024007334,
      "learning_rate": 1.8187348396044402e-05,
      "loss": 0.4231,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10732856392860413,
      "step": 145,
      "valid_targets_mean": 4244.3,
      "valid_targets_min": 849
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3695239483214702,
      "learning_rate": 1.6802376246163307e-05,
      "loss": 0.4307,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.2080117017030716,
      "step": 150,
      "valid_targets_mean": 3466.7,
      "valid_targets_min": 600
    },
    {
      "epoch": 3.101010101010101,
      "grad_norm": 0.2516175673157399,
      "learning_rate": 1.5432982597786886e-05,
      "loss": 0.4228,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11081644892692566,
      "step": 155,
      "valid_targets_mean": 4376.6,
      "valid_targets_min": 1393
    },
    {
      "epoch": 3.202020202020202,
      "grad_norm": 0.25899041127457506,
      "learning_rate": 1.4085838999119075e-05,
      "loss": 0.4183,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10279497504234314,
      "step": 160,
      "valid_targets_mean": 3922.6,
      "valid_targets_min": 1037
    },
    {
      "epoch": 3.303030303030303,
      "grad_norm": 0.2568302854985244,
      "learning_rate": 1.2767508598358158e-05,
      "loss": 0.4119,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10400432348251343,
      "step": 165,
      "valid_targets_mean": 4147.3,
      "valid_targets_min": 840
    },
    {
      "epoch": 3.404040404040404,
      "grad_norm": 0.2575745984749214,
      "learning_rate": 1.1484414168698547e-05,
      "loss": 0.4109,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1014273464679718,
      "step": 170,
      "valid_targets_mean": 3870.5,
      "valid_targets_min": 738
    },
    {
      "epoch": 3.505050505050505,
      "grad_norm": 0.2708052183398422,
      "learning_rate": 1.0242806817225344e-05,
      "loss": 0.4183,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0942554920911789,
      "step": 175,
      "valid_targets_mean": 4129.5,
      "valid_targets_min": 691
    },
    {
      "epoch": 3.606060606060606,
      "grad_norm": 0.39589597035376406,
      "learning_rate": 9.048735530148998e-06,
      "loss": 0.4057,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10414694994688034,
      "step": 180,
      "valid_targets_mean": 3647.8,
      "valid_targets_min": 1355
    },
    {
      "epoch": 3.707070707070707,
      "grad_norm": 0.2754352204699097,
      "learning_rate": 7.908017702752504e-06,
      "loss": 0.4167,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11268728971481323,
      "step": 185,
      "valid_targets_mean": 4025.8,
      "valid_targets_min": 631
    },
    {
      "epoch": 3.808080808080808,
      "grad_norm": 0.26307739642578865,
      "learning_rate": 6.826210797626389e-06,
      "loss": 0.4158,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.08769197762012482,
      "step": 190,
      "valid_targets_mean": 3541.8,
      "valid_targets_min": 1132
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 0.25965429680059315,
      "learning_rate": 5.8085852692695864e-06,
      "loss": 0.4088,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10568307340145111,
      "step": 195,
      "valid_targets_mean": 4072.8,
      "valid_targets_min": 658
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.37112181378749864,
      "learning_rate": 4.8600988869648745e-06,
      "loss": 0.4077,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.18167036771774292,
      "step": 200,
      "valid_targets_mean": 3388.4,
      "valid_targets_min": 757
    },
    {
      "epoch": 4.101010101010101,
      "grad_norm": 0.24190724490489265,
      "learning_rate": 3.985372581025333e-06,
      "loss": 0.3992,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09219323098659515,
      "step": 205,
      "valid_targets_mean": 3395.9,
      "valid_targets_min": 1280
    },
    {
      "epoch": 4.202020202020202,
      "grad_norm": 0.26150260454768026,
      "learning_rate": 3.1886679300863156e-06,
      "loss": 0.407,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09850673377513885,
      "step": 210,
      "valid_targets_mean": 3216.6,
      "valid_targets_min": 784
    },
    {
      "epoch": 4.303030303030303,
      "grad_norm": 0.26872823184659334,
      "learning_rate": 2.473866399122733e-06,
      "loss": 0.4133,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10747270286083221,
      "step": 215,
      "valid_targets_mean": 3487.2,
      "valid_targets_min": 773
    },
    {
      "epoch": 4.404040404040404,
      "grad_norm": 0.2549088626047512,
      "learning_rate": 1.8444504293418286e-06,
      "loss": 0.4124,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10171965509653091,
      "step": 220,
      "valid_targets_mean": 3727.9,
      "valid_targets_min": 928
    },
    {
      "epoch": 4.505050505050505,
      "grad_norm": 0.32301587125223463,
      "learning_rate": 1.3034864720797112e-06,
      "loss": 0.4125,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.11444351077079773,
      "step": 225,
      "valid_targets_mean": 3867.6,
      "valid_targets_min": 791
    },
    {
      "epoch": 4.606060606060606,
      "grad_norm": 0.24811664458418323,
      "learning_rate": 8.536100493586552e-07,
      "loss": 0.4023,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0989425927400589,
      "step": 230,
      "valid_targets_mean": 3649.8,
      "valid_targets_min": 675
    },
    {
      "epoch": 4.707070707070707,
      "grad_norm": 0.24999205236156857,
      "learning_rate": 4.970129138887347e-07,
      "loss": 0.4078,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09448540210723877,
      "step": 235,
      "valid_targets_mean": 3779.3,
      "valid_targets_min": 613
    },
    {
      "epoch": 4.808080808080808,
      "grad_norm": 0.2533525398749002,
      "learning_rate": 2.3543237106894434e-07,
      "loss": 0.4138,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10717539489269257,
      "step": 240,
      "valid_targets_mean": 3630.1,
      "valid_targets_min": 1185
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.2324383918083103,
      "learning_rate": 7.01428150099126e-08,
      "loss": 0.4099,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09807487577199936,
      "step": 245,
      "valid_targets_mean": 4431.1,
      "valid_targets_min": 1588
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3564637724019629,
      "learning_rate": 1.949519813915224e-09,
      "loss": 0.4103,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.20247647166252136,
      "step": 250,
      "valid_targets_mean": 3850.3,
      "valid_targets_min": 771
    },
    {
      "epoch": 5.0,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.20247647166252136,
      "step": 250,
      "total_flos": 4.268418036190413e+17,
      "train_loss": 0.4559480676651001,
      "train_runtime": 5383.7809,
      "train_samples_per_second": 2.935,
      "train_steps_per_second": 0.046,
      "valid_targets_mean": 3850.3,
      "valid_targets_min": 771
    }
  ],
  "logging_steps": 5,
  "max_steps": 250,
  "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": 4.268418036190413e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}