{
  "best_metric": 0.48943638801574707,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.0940203083866115,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000188040616773223,
      "eval_loss": 1.0817307233810425,
      "eval_runtime": 133.3846,
      "eval_samples_per_second": 16.794,
      "eval_steps_per_second": 4.198,
      "step": 1
    },
    {
      "epoch": 0.00188040616773223,
      "grad_norm": 5.176900863647461,
      "learning_rate": 4.22e-05,
      "loss": 1.7009,
      "step": 10
    },
    {
      "epoch": 0.00376081233546446,
      "grad_norm": 3.7416343688964844,
      "learning_rate": 8.44e-05,
      "loss": 1.21,
      "step": 20
    },
    {
      "epoch": 0.005641218503196691,
      "grad_norm": 3.444662570953369,
      "learning_rate": 0.0001266,
      "loss": 1.1852,
      "step": 30
    },
    {
      "epoch": 0.00752162467092892,
      "grad_norm": 3.319375991821289,
      "learning_rate": 0.0001688,
      "loss": 1.1785,
      "step": 40
    },
    {
      "epoch": 0.009402030838661151,
      "grad_norm": 5.216305255889893,
      "learning_rate": 0.000211,
      "loss": 1.3661,
      "step": 50
    },
    {
      "epoch": 0.009402030838661151,
      "eval_loss": 0.7779666185379028,
      "eval_runtime": 133.0975,
      "eval_samples_per_second": 16.83,
      "eval_steps_per_second": 4.207,
      "step": 50
    },
    {
      "epoch": 0.011282437006393382,
      "grad_norm": 2.7655200958251953,
      "learning_rate": 0.00021074300730241147,
      "loss": 1.3996,
      "step": 60
    },
    {
      "epoch": 0.013162843174125612,
      "grad_norm": 2.7388007640838623,
      "learning_rate": 0.00020997328125223568,
      "loss": 1.2458,
      "step": 70
    },
    {
      "epoch": 0.01504324934185784,
      "grad_norm": 2.6569647789001465,
      "learning_rate": 0.0002086945718774165,
      "loss": 1.3008,
      "step": 80
    },
    {
      "epoch": 0.01692365550959007,
      "grad_norm": 2.989269733428955,
      "learning_rate": 0.00020691310892149265,
      "loss": 1.2504,
      "step": 90
    },
    {
      "epoch": 0.018804061677322303,
      "grad_norm": 4.817940711975098,
      "learning_rate": 0.00020463757149291335,
      "loss": 1.4111,
      "step": 100
    },
    {
      "epoch": 0.018804061677322303,
      "eval_loss": 0.8434422016143799,
      "eval_runtime": 133.1617,
      "eval_samples_per_second": 16.822,
      "eval_steps_per_second": 4.205,
      "step": 100
    },
    {
      "epoch": 0.02068446784505453,
      "grad_norm": 2.5777533054351807,
      "learning_rate": 0.0002018790457812944,
      "loss": 1.5197,
      "step": 110
    },
    {
      "epoch": 0.022564874012786763,
      "grad_norm": 2.3088767528533936,
      "learning_rate": 0.0001986509710466168,
      "loss": 1.2673,
      "step": 120
    },
    {
      "epoch": 0.024445280180518992,
      "grad_norm": 2.4268999099731445,
      "learning_rate": 0.00019496907414450293,
      "loss": 1.2102,
      "step": 130
    },
    {
      "epoch": 0.026325686348251224,
      "grad_norm": 2.8331105709075928,
      "learning_rate": 0.00019085129290655697,
      "loss": 1.192,
      "step": 140
    },
    {
      "epoch": 0.028206092515983452,
      "grad_norm": 5.091329574584961,
      "learning_rate": 0.00018631768874905217,
      "loss": 1.3753,
      "step": 150
    },
    {
      "epoch": 0.028206092515983452,
      "eval_loss": 0.7753247618675232,
      "eval_runtime": 133.6028,
      "eval_samples_per_second": 16.766,
      "eval_steps_per_second": 4.192,
      "step": 150
    },
    {
      "epoch": 0.03008649868371568,
      "grad_norm": 251.54493713378906,
      "learning_rate": 0.0001813903489357277,
      "loss": 1.5184,
      "step": 160
    },
    {
      "epoch": 0.03196690485144791,
      "grad_norm": 2.6304538249969482,
      "learning_rate": 0.00017609327897085954,
      "loss": 1.2063,
      "step": 170
    },
    {
      "epoch": 0.03384731101918014,
      "grad_norm": 2.115901231765747,
      "learning_rate": 0.00017045228564685694,
      "loss": 1.1798,
      "step": 180
    },
    {
      "epoch": 0.035727717186912374,
      "grad_norm": 2.3057830333709717,
      "learning_rate": 0.0001644948513161638,
      "loss": 1.0979,
      "step": 190
    },
    {
      "epoch": 0.037608123354644606,
      "grad_norm": 4.125862121582031,
      "learning_rate": 0.00015825,
      "loss": 1.356,
      "step": 200
    },
    {
      "epoch": 0.037608123354644606,
      "eval_loss": 0.7662692666053772,
      "eval_runtime": 133.4554,
      "eval_samples_per_second": 16.785,
      "eval_steps_per_second": 4.196,
      "step": 200
    },
    {
      "epoch": 0.03948852952237683,
      "grad_norm": 2.323758125305176,
      "learning_rate": 0.00015174815598624768,
      "loss": 1.4656,
      "step": 210
    },
    {
      "epoch": 0.04136893569010906,
      "grad_norm": 2.185595750808716,
      "learning_rate": 0.00014502099560537873,
      "loss": 1.1591,
      "step": 220
    },
    {
      "epoch": 0.043249341857841295,
      "grad_norm": 2.143188953399658,
      "learning_rate": 0.00013810129290655696,
      "loss": 1.0983,
      "step": 230
    },
    {
      "epoch": 0.04512974802557353,
      "grad_norm": 2.9297232627868652,
      "learning_rate": 0.00013102275998576495,
      "loss": 1.158,
      "step": 240
    },
    {
      "epoch": 0.04701015419330575,
      "grad_norm": 3.86443829536438,
      "learning_rate": 0.00012381988274386116,
      "loss": 1.2593,
      "step": 250
    },
    {
      "epoch": 0.04701015419330575,
      "eval_loss": 0.669979989528656,
      "eval_runtime": 134.6215,
      "eval_samples_per_second": 16.639,
      "eval_steps_per_second": 4.16,
      "step": 250
    },
    {
      "epoch": 0.048890560361037984,
      "grad_norm": 1.8978098630905151,
      "learning_rate": 0.00011652775287473745,
      "loss": 1.3589,
      "step": 260
    },
    {
      "epoch": 0.050770966528770216,
      "grad_norm": 1.964809536933899,
      "learning_rate": 0.00010918189690211387,
      "loss": 1.1163,
      "step": 270
    },
    {
      "epoch": 0.05265137269650245,
      "grad_norm": 1.9690378904342651,
      "learning_rate": 0.00010181810309788618,
      "loss": 1.1062,
      "step": 280
    },
    {
      "epoch": 0.05453177886423467,
      "grad_norm": 2.6126410961151123,
      "learning_rate": 9.447224712526258e-05,
      "loss": 1.0986,
      "step": 290
    },
    {
      "epoch": 0.056412185031966905,
      "grad_norm": 3.1689352989196777,
      "learning_rate": 8.718011725613886e-05,
      "loss": 1.1686,
      "step": 300
    },
    {
      "epoch": 0.056412185031966905,
      "eval_loss": 0.6255946755409241,
      "eval_runtime": 133.189,
      "eval_samples_per_second": 16.818,
      "eval_steps_per_second": 4.205,
      "step": 300
    },
    {
      "epoch": 0.05829259119969914,
      "grad_norm": 2.104492664337158,
      "learning_rate": 7.997724001423507e-05,
      "loss": 1.3156,
      "step": 310
    },
    {
      "epoch": 0.06017299736743136,
      "grad_norm": 2.1799798011779785,
      "learning_rate": 7.289870709344306e-05,
      "loss": 1.0996,
      "step": 320
    },
    {
      "epoch": 0.062053403535163594,
      "grad_norm": 2.0943219661712646,
      "learning_rate": 6.597900439462128e-05,
      "loss": 0.9772,
      "step": 330
    },
    {
      "epoch": 0.06393380970289582,
      "grad_norm": 2.013209819793701,
      "learning_rate": 5.9251844013752326e-05,
      "loss": 0.9912,
      "step": 340
    },
    {
      "epoch": 0.06581421587062805,
      "grad_norm": 3.92903733253479,
      "learning_rate": 5.275000000000002e-05,
      "loss": 1.1292,
      "step": 350
    },
    {
      "epoch": 0.06581421587062805,
      "eval_loss": 0.5762282609939575,
      "eval_runtime": 133.4566,
      "eval_samples_per_second": 16.784,
      "eval_steps_per_second": 4.196,
      "step": 350
    },
    {
      "epoch": 0.06769462203836028,
      "grad_norm": 1.7651203870773315,
      "learning_rate": 4.650514868383623e-05,
      "loss": 1.2481,
      "step": 360
    },
    {
      "epoch": 0.06957502820609252,
      "grad_norm": 1.6707273721694946,
      "learning_rate": 4.054771435314305e-05,
      "loss": 1.0573,
      "step": 370
    },
    {
      "epoch": 0.07145543437382475,
      "grad_norm": 1.9455937147140503,
      "learning_rate": 3.4906721029140495e-05,
      "loss": 1.0288,
      "step": 380
    },
    {
      "epoch": 0.07333584054155698,
      "grad_norm": 1.6634033918380737,
      "learning_rate": 2.9609651064272323e-05,
      "loss": 0.9095,
      "step": 390
    },
    {
      "epoch": 0.07521624670928921,
      "grad_norm": 2.96443510055542,
      "learning_rate": 2.468231125094783e-05,
      "loss": 1.0613,
      "step": 400
    },
    {
      "epoch": 0.07521624670928921,
      "eval_loss": 0.5196256637573242,
      "eval_runtime": 133.6892,
      "eval_samples_per_second": 16.755,
      "eval_steps_per_second": 4.189,
      "step": 400
    },
    {
      "epoch": 0.07709665287702144,
      "grad_norm": 1.5204122066497803,
      "learning_rate": 2.0148707093443057e-05,
      "loss": 1.1007,
      "step": 410
    },
    {
      "epoch": 0.07897705904475366,
      "grad_norm": 1.678540587425232,
      "learning_rate": 1.603092585549706e-05,
      "loss": 0.9935,
      "step": 420
    },
    {
      "epoch": 0.0808574652124859,
      "grad_norm": 1.6980760097503662,
      "learning_rate": 1.2349028953383204e-05,
      "loss": 0.9701,
      "step": 430
    },
    {
      "epoch": 0.08273787138021813,
      "grad_norm": 1.9784950017929077,
      "learning_rate": 9.120954218705596e-06,
      "loss": 0.908,
      "step": 440
    },
    {
      "epoch": 0.08461827754795036,
      "grad_norm": 2.8648924827575684,
      "learning_rate": 6.362428507086673e-06,
      "loss": 1.1085,
      "step": 450
    },
    {
      "epoch": 0.08461827754795036,
      "eval_loss": 0.49475958943367004,
      "eval_runtime": 133.6063,
      "eval_samples_per_second": 16.766,
      "eval_steps_per_second": 4.191,
      "step": 450
    },
    {
      "epoch": 0.08649868371568259,
      "grad_norm": 1.6609992980957031,
      "learning_rate": 4.0868910785073565e-06,
      "loss": 1.0254,
      "step": 460
    },
    {
      "epoch": 0.08837908988341482,
      "grad_norm": 1.700790524482727,
      "learning_rate": 2.3054281225835e-06,
      "loss": 0.9438,
      "step": 470
    },
    {
      "epoch": 0.09025949605114705,
      "grad_norm": 1.5010980367660522,
      "learning_rate": 1.026718747764327e-06,
      "loss": 0.897,
      "step": 480
    },
    {
      "epoch": 0.09213990221887927,
      "grad_norm": 1.916372537612915,
      "learning_rate": 2.5699269758854715e-07,
      "loss": 0.9306,
      "step": 490
    },
    {
      "epoch": 0.0940203083866115,
      "grad_norm": 3.343224048614502,
      "learning_rate": 0.0,
      "loss": 1.0691,
      "step": 500
    },
    {
      "epoch": 0.0940203083866115,
      "eval_loss": 0.48943638801574707,
      "eval_runtime": 134.0884,
      "eval_samples_per_second": 16.705,
      "eval_steps_per_second": 4.176,
      "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": 8.988466360614912e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}