{
  "best_metric": 1.1320114135742188,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.09911785112498761,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019823570224997521,
      "eval_loss": 1.3964250087738037,
      "eval_runtime": 129.3952,
      "eval_samples_per_second": 16.415,
      "eval_steps_per_second": 4.104,
      "step": 1
    },
    {
      "epoch": 0.001982357022499752,
      "grad_norm": 6.275260925292969,
      "learning_rate": 4.1400000000000003e-05,
      "loss": 2.0384,
      "step": 10
    },
    {
      "epoch": 0.003964714044999504,
      "grad_norm": 5.881035327911377,
      "learning_rate": 8.280000000000001e-05,
      "loss": 2.1167,
      "step": 20
    },
    {
      "epoch": 0.005947071067499257,
      "grad_norm": 9.9217529296875,
      "learning_rate": 0.00012419999999999998,
      "loss": 2.2128,
      "step": 30
    },
    {
      "epoch": 0.007929428089999009,
      "grad_norm": 13.89786148071289,
      "learning_rate": 0.00016560000000000001,
      "loss": 2.3928,
      "step": 40
    },
    {
      "epoch": 0.009911785112498761,
      "grad_norm": 49.89253234863281,
      "learning_rate": 0.000207,
      "loss": 3.0166,
      "step": 50
    },
    {
      "epoch": 0.009911785112498761,
      "eval_loss": 2.377807378768921,
      "eval_runtime": 129.3871,
      "eval_samples_per_second": 16.416,
      "eval_steps_per_second": 4.104,
      "step": 50
    },
    {
      "epoch": 0.011894142134998514,
      "grad_norm": 4.660886287689209,
      "learning_rate": 0.00020674787920189178,
      "loss": 2.4654,
      "step": 60
    },
    {
      "epoch": 0.013876499157498265,
      "grad_norm": 5.226744174957275,
      "learning_rate": 0.00020599274511475253,
      "loss": 2.2438,
      "step": 70
    },
    {
      "epoch": 0.015858856179998018,
      "grad_norm": 9.301616668701172,
      "learning_rate": 0.00020473827667594888,
      "loss": 2.4871,
      "step": 80
    },
    {
      "epoch": 0.01784121320249777,
      "grad_norm": 11.889968872070312,
      "learning_rate": 0.00020299058552961598,
      "loss": 2.5391,
      "step": 90
    },
    {
      "epoch": 0.019823570224997523,
      "grad_norm": 28.756938934326172,
      "learning_rate": 0.00020075818625134152,
      "loss": 3.021,
      "step": 100
    },
    {
      "epoch": 0.019823570224997523,
      "eval_loss": 1.7476463317871094,
      "eval_runtime": 129.3759,
      "eval_samples_per_second": 16.417,
      "eval_steps_per_second": 4.104,
      "step": 100
    },
    {
      "epoch": 0.021805927247497275,
      "grad_norm": 8.956504821777344,
      "learning_rate": 0.00019805195486600916,
      "loss": 2.4593,
      "step": 110
    },
    {
      "epoch": 0.023788284269997028,
      "grad_norm": 5.725518703460693,
      "learning_rate": 0.00019488507586089894,
      "loss": 2.3297,
      "step": 120
    },
    {
      "epoch": 0.025770641292496777,
      "grad_norm": 8.019457817077637,
      "learning_rate": 0.00019127297795219008,
      "loss": 2.5391,
      "step": 130
    },
    {
      "epoch": 0.02775299831499653,
      "grad_norm": 12.648486137390137,
      "learning_rate": 0.00018723325891780706,
      "loss": 2.7968,
      "step": 140
    },
    {
      "epoch": 0.029735355337496282,
      "grad_norm": 43.71430587768555,
      "learning_rate": 0.0001827855998628142,
      "loss": 3.4261,
      "step": 150
    },
    {
      "epoch": 0.029735355337496282,
      "eval_loss": 1.5400112867355347,
      "eval_runtime": 129.2867,
      "eval_samples_per_second": 16.429,
      "eval_steps_per_second": 4.107,
      "step": 150
    },
    {
      "epoch": 0.031717712359996035,
      "grad_norm": 4.096808910369873,
      "learning_rate": 0.0001779516693350504,
      "loss": 2.293,
      "step": 160
    },
    {
      "epoch": 0.033700069382495784,
      "grad_norm": 5.682216644287109,
      "learning_rate": 0.00017275501775814182,
      "loss": 2.279,
      "step": 170
    },
    {
      "epoch": 0.03568242640499554,
      "grad_norm": 8.98400592803955,
      "learning_rate": 0.00016722096269620562,
      "loss": 2.571,
      "step": 180
    },
    {
      "epoch": 0.03766478342749529,
      "grad_norm": 13.64550495147705,
      "learning_rate": 0.00016137646550922228,
      "loss": 2.9063,
      "step": 190
    },
    {
      "epoch": 0.039647140449995046,
      "grad_norm": 38.4648551940918,
      "learning_rate": 0.00015525,
      "loss": 3.2143,
      "step": 200
    },
    {
      "epoch": 0.039647140449995046,
      "eval_loss": 1.60282564163208,
      "eval_runtime": 129.3819,
      "eval_samples_per_second": 16.417,
      "eval_steps_per_second": 4.104,
      "step": 200
    },
    {
      "epoch": 0.041629497472494795,
      "grad_norm": 5.079794406890869,
      "learning_rate": 0.0001488714136926695,
      "loss": 2.3781,
      "step": 210
    },
    {
      "epoch": 0.04361185449499455,
      "grad_norm": 5.307718753814697,
      "learning_rate": 0.0001422717824185469,
      "loss": 2.3115,
      "step": 220
    },
    {
      "epoch": 0.0455942115174943,
      "grad_norm": 9.006290435791016,
      "learning_rate": 0.00013548325891780705,
      "loss": 2.5917,
      "step": 230
    },
    {
      "epoch": 0.047576568539994056,
      "grad_norm": 13.994711875915527,
      "learning_rate": 0.0001285389161945656,
      "loss": 2.7895,
      "step": 240
    },
    {
      "epoch": 0.049558925562493805,
      "grad_norm": 21.790035247802734,
      "learning_rate": 0.0001214725863885273,
      "loss": 2.6553,
      "step": 250
    },
    {
      "epoch": 0.049558925562493805,
      "eval_loss": 1.7899256944656372,
      "eval_runtime": 129.1236,
      "eval_samples_per_second": 16.449,
      "eval_steps_per_second": 4.112,
      "step": 250
    },
    {
      "epoch": 0.051541282584993554,
      "grad_norm": 5.842795372009277,
      "learning_rate": 0.00011431869594820213,
      "loss": 2.4341,
      "step": 260
    },
    {
      "epoch": 0.05352363960749331,
      "grad_norm": 5.807853698730469,
      "learning_rate": 0.00010711209790870886,
      "loss": 2.3098,
      "step": 270
    },
    {
      "epoch": 0.05550599662999306,
      "grad_norm": 8.860788345336914,
      "learning_rate": 9.988790209129117e-05,
      "loss": 2.418,
      "step": 280
    },
    {
      "epoch": 0.057488353652492816,
      "grad_norm": 11.287921905517578,
      "learning_rate": 9.268130405179787e-05,
      "loss": 2.5827,
      "step": 290
    },
    {
      "epoch": 0.059470710674992565,
      "grad_norm": 23.194669723510742,
      "learning_rate": 8.55274136114727e-05,
      "loss": 2.7311,
      "step": 300
    },
    {
      "epoch": 0.059470710674992565,
      "eval_loss": 1.3962997198104858,
      "eval_runtime": 129.4572,
      "eval_samples_per_second": 16.407,
      "eval_steps_per_second": 4.102,
      "step": 300
    },
    {
      "epoch": 0.06145306769749232,
      "grad_norm": 3.5669214725494385,
      "learning_rate": 7.84610838054344e-05,
      "loss": 2.1451,
      "step": 310
    },
    {
      "epoch": 0.06343542471999207,
      "grad_norm": 4.6063385009765625,
      "learning_rate": 7.151674108219295e-05,
      "loss": 2.2686,
      "step": 320
    },
    {
      "epoch": 0.06541778174249183,
      "grad_norm": 6.335786819458008,
      "learning_rate": 6.472821758145309e-05,
      "loss": 2.3037,
      "step": 330
    },
    {
      "epoch": 0.06740013876499157,
      "grad_norm": 10.314666748046875,
      "learning_rate": 5.8128586307330475e-05,
      "loss": 2.5303,
      "step": 340
    },
    {
      "epoch": 0.06938249578749132,
      "grad_norm": 22.63821029663086,
      "learning_rate": 5.175000000000002e-05,
      "loss": 2.9098,
      "step": 350
    },
    {
      "epoch": 0.06938249578749132,
      "eval_loss": 1.261065125465393,
      "eval_runtime": 129.2566,
      "eval_samples_per_second": 16.432,
      "eval_steps_per_second": 4.108,
      "step": 350
    },
    {
      "epoch": 0.07136485280999108,
      "grad_norm": 3.719794988632202,
      "learning_rate": 4.5623534490777714e-05,
      "loss": 2.0636,
      "step": 360
    },
    {
      "epoch": 0.07334720983249084,
      "grad_norm": 4.633784770965576,
      "learning_rate": 3.9779037303794365e-05,
      "loss": 2.1919,
      "step": 370
    },
    {
      "epoch": 0.07532956685499058,
      "grad_norm": 6.985335350036621,
      "learning_rate": 3.42449822418582e-05,
      "loss": 2.3824,
      "step": 380
    },
    {
      "epoch": 0.07731192387749034,
      "grad_norm": 10.074797630310059,
      "learning_rate": 2.9048330664949622e-05,
      "loss": 2.5754,
      "step": 390
    },
    {
      "epoch": 0.07929428089999009,
      "grad_norm": 47.354488372802734,
      "learning_rate": 2.4214400137185785e-05,
      "loss": 2.7607,
      "step": 400
    },
    {
      "epoch": 0.07929428089999009,
      "eval_loss": 1.1924641132354736,
      "eval_runtime": 129.1322,
      "eval_samples_per_second": 16.448,
      "eval_steps_per_second": 4.112,
      "step": 400
    },
    {
      "epoch": 0.08127663792248985,
      "grad_norm": 3.8752737045288086,
      "learning_rate": 1.976674108219295e-05,
      "loss": 2.018,
      "step": 410
    },
    {
      "epoch": 0.08325899494498959,
      "grad_norm": 5.539064884185791,
      "learning_rate": 1.572702204780991e-05,
      "loss": 2.234,
      "step": 420
    },
    {
      "epoch": 0.08524135196748935,
      "grad_norm": 7.250934600830078,
      "learning_rate": 1.2114924139101056e-05,
      "loss": 2.3844,
      "step": 430
    },
    {
      "epoch": 0.0872237089899891,
      "grad_norm": 11.239484786987305,
      "learning_rate": 8.948045133990798e-06,
      "loss": 2.2897,
      "step": 440
    },
    {
      "epoch": 0.08920606601248884,
      "grad_norm": 31.72355079650879,
      "learning_rate": 6.241813748658489e-06,
      "loss": 2.6709,
      "step": 450
    },
    {
      "epoch": 0.08920606601248884,
      "eval_loss": 1.1373093128204346,
      "eval_runtime": 129.3098,
      "eval_samples_per_second": 16.426,
      "eval_steps_per_second": 4.106,
      "step": 450
    },
    {
      "epoch": 0.0911884230349886,
      "grad_norm": 4.044310569763184,
      "learning_rate": 4.009414470383994e-06,
      "loss": 1.9538,
      "step": 460
    },
    {
      "epoch": 0.09317078005748836,
      "grad_norm": 5.821104526519775,
      "learning_rate": 2.261723324051111e-06,
      "loss": 2.0272,
      "step": 470
    },
    {
      "epoch": 0.09515313707998811,
      "grad_norm": 9.027103424072266,
      "learning_rate": 1.0072548852474675e-06,
      "loss": 2.3058,
      "step": 480
    },
    {
      "epoch": 0.09713549410248785,
      "grad_norm": 10.941502571105957,
      "learning_rate": 2.5212079810819554e-07,
      "loss": 2.3945,
      "step": 490
    },
    {
      "epoch": 0.09911785112498761,
      "grad_norm": 56.49876022338867,
      "learning_rate": 0.0,
      "loss": 2.6685,
      "step": 500
    },
    {
      "epoch": 0.09911785112498761,
      "eval_loss": 1.1320114135742188,
      "eval_runtime": 129.2595,
      "eval_samples_per_second": 16.432,
      "eval_steps_per_second": 4.108,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.158397565442458e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}