{
  "best_metric": 2.4987945556640625,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.5686274509803921,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01568627450980392,
      "grad_norm": 0.9535642266273499,
      "learning_rate": 1e-05,
      "loss": 2.8736,
      "step": 1
    },
    {
      "epoch": 0.01568627450980392,
      "eval_loss": 3.324666738510132,
      "eval_runtime": 7.9996,
      "eval_samples_per_second": 13.501,
      "eval_steps_per_second": 3.375,
      "step": 1
    },
    {
      "epoch": 0.03137254901960784,
      "grad_norm": 1.0703654289245605,
      "learning_rate": 2e-05,
      "loss": 2.8739,
      "step": 2
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 1.0498156547546387,
      "learning_rate": 3e-05,
      "loss": 2.9074,
      "step": 3
    },
    {
      "epoch": 0.06274509803921569,
      "grad_norm": 0.9599528312683105,
      "learning_rate": 4e-05,
      "loss": 2.9035,
      "step": 4
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.9831591248512268,
      "learning_rate": 5e-05,
      "loss": 2.8063,
      "step": 5
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.9782329201698303,
      "learning_rate": 6e-05,
      "loss": 2.9952,
      "step": 6
    },
    {
      "epoch": 0.10980392156862745,
      "grad_norm": 0.859535813331604,
      "learning_rate": 7e-05,
      "loss": 2.9002,
      "step": 7
    },
    {
      "epoch": 0.12549019607843137,
      "grad_norm": 0.9193878769874573,
      "learning_rate": 8e-05,
      "loss": 2.7132,
      "step": 8
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 0.8184499740600586,
      "learning_rate": 9e-05,
      "loss": 2.7317,
      "step": 9
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 0.8140602707862854,
      "learning_rate": 0.0001,
      "loss": 2.6723,
      "step": 10
    },
    {
      "epoch": 0.17254901960784313,
      "grad_norm": 0.9426817893981934,
      "learning_rate": 9.999255120204248e-05,
      "loss": 2.6702,
      "step": 11
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 1.0090997219085693,
      "learning_rate": 9.997020702755353e-05,
      "loss": 2.7346,
      "step": 12
    },
    {
      "epoch": 0.20392156862745098,
      "grad_norm": 1.0597916841506958,
      "learning_rate": 9.99329741340228e-05,
      "loss": 2.678,
      "step": 13
    },
    {
      "epoch": 0.2196078431372549,
      "grad_norm": 1.2650080919265747,
      "learning_rate": 9.98808636150624e-05,
      "loss": 2.6331,
      "step": 14
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.5050358772277832,
      "learning_rate": 9.981389099710132e-05,
      "loss": 3.0748,
      "step": 15
    },
    {
      "epoch": 0.25098039215686274,
      "grad_norm": 0.516484797000885,
      "learning_rate": 9.973207623475965e-05,
      "loss": 2.4093,
      "step": 16
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.6125854849815369,
      "learning_rate": 9.96354437049027e-05,
      "loss": 2.5081,
      "step": 17
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.5779858827590942,
      "learning_rate": 9.952402219937816e-05,
      "loss": 2.5021,
      "step": 18
    },
    {
      "epoch": 0.2980392156862745,
      "grad_norm": 0.5545258522033691,
      "learning_rate": 9.939784491643734e-05,
      "loss": 2.4604,
      "step": 19
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 0.5096269249916077,
      "learning_rate": 9.92569494508437e-05,
      "loss": 2.626,
      "step": 20
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 0.4844023287296295,
      "learning_rate": 9.910137778267152e-05,
      "loss": 2.5395,
      "step": 21
    },
    {
      "epoch": 0.34509803921568627,
      "grad_norm": 0.4641485810279846,
      "learning_rate": 9.893117626479777e-05,
      "loss": 2.5221,
      "step": 22
    },
    {
      "epoch": 0.3607843137254902,
      "grad_norm": 0.47447431087493896,
      "learning_rate": 9.874639560909117e-05,
      "loss": 2.4512,
      "step": 23
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.6421774625778198,
      "learning_rate": 9.85470908713026e-05,
      "loss": 2.4789,
      "step": 24
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.692217230796814,
      "learning_rate": 9.833332143466099e-05,
      "loss": 2.5332,
      "step": 25
    },
    {
      "epoch": 0.40784313725490196,
      "grad_norm": 0.5684048533439636,
      "learning_rate": 9.810515099218003e-05,
      "loss": 2.7136,
      "step": 26
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 0.6432080864906311,
      "learning_rate": 9.78626475276808e-05,
      "loss": 2.5727,
      "step": 27
    },
    {
      "epoch": 0.4392156862745098,
      "grad_norm": 0.7890809774398804,
      "learning_rate": 9.760588329553571e-05,
      "loss": 2.6341,
      "step": 28
    },
    {
      "epoch": 0.4549019607843137,
      "grad_norm": 0.8166062235832214,
      "learning_rate": 9.73349347991403e-05,
      "loss": 2.5955,
      "step": 29
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.1982145309448242,
      "learning_rate": 9.704988276811883e-05,
      "loss": 2.9488,
      "step": 30
    },
    {
      "epoch": 0.48627450980392156,
      "grad_norm": 0.30004727840423584,
      "learning_rate": 9.675081213427076e-05,
      "loss": 2.3561,
      "step": 31
    },
    {
      "epoch": 0.5019607843137255,
      "grad_norm": 0.41050592064857483,
      "learning_rate": 9.643781200626511e-05,
      "loss": 2.425,
      "step": 32
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 0.42230165004730225,
      "learning_rate": 9.611097564309053e-05,
      "loss": 2.5036,
      "step": 33
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.4193224608898163,
      "learning_rate": 9.577040042626833e-05,
      "loss": 2.3797,
      "step": 34
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 0.4057847857475281,
      "learning_rate": 9.54161878308377e-05,
      "loss": 2.4552,
      "step": 35
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.43488991260528564,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.4372,
      "step": 36
    },
    {
      "epoch": 0.5803921568627451,
      "grad_norm": 0.4593192934989929,
      "learning_rate": 9.466727668927816e-05,
      "loss": 2.5748,
      "step": 37
    },
    {
      "epoch": 0.596078431372549,
      "grad_norm": 0.4425160884857178,
      "learning_rate": 9.42728012826605e-05,
      "loss": 2.404,
      "step": 38
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 0.43048760294914246,
      "learning_rate": 9.38651347099721e-05,
      "loss": 2.3847,
      "step": 39
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 0.4540267884731293,
      "learning_rate": 9.344439843625034e-05,
      "loss": 2.4953,
      "step": 40
    },
    {
      "epoch": 0.6431372549019608,
      "grad_norm": 0.4934435486793518,
      "learning_rate": 9.301071782067504e-05,
      "loss": 2.479,
      "step": 41
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.6172159910202026,
      "learning_rate": 9.256422207921757e-05,
      "loss": 2.5236,
      "step": 42
    },
    {
      "epoch": 0.6745098039215687,
      "grad_norm": 0.5735173225402832,
      "learning_rate": 9.210504424614059e-05,
      "loss": 2.452,
      "step": 43
    },
    {
      "epoch": 0.6901960784313725,
      "grad_norm": 0.692180335521698,
      "learning_rate": 9.163332113436032e-05,
      "loss": 2.5363,
      "step": 44
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.1689708232879639,
      "learning_rate": 9.114919329468282e-05,
      "loss": 2.8587,
      "step": 45
    },
    {
      "epoch": 0.7215686274509804,
      "grad_norm": 0.3823428750038147,
      "learning_rate": 9.065280497392663e-05,
      "loss": 2.4599,
      "step": 46
    },
    {
      "epoch": 0.7372549019607844,
      "grad_norm": 0.37304720282554626,
      "learning_rate": 9.014430407194413e-05,
      "loss": 2.4085,
      "step": 47
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.354853093624115,
      "learning_rate": 8.962384209755452e-05,
      "loss": 2.5411,
      "step": 48
    },
    {
      "epoch": 0.7686274509803922,
      "grad_norm": 0.3872363269329071,
      "learning_rate": 8.90915741234015e-05,
      "loss": 2.4203,
      "step": 49
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.40209847688674927,
      "learning_rate": 8.854765873974898e-05,
      "loss": 2.5972,
      "step": 50
    },
    {
      "epoch": 0.7843137254901961,
      "eval_loss": 2.5110836029052734,
      "eval_runtime": 8.1325,
      "eval_samples_per_second": 13.28,
      "eval_steps_per_second": 3.32,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.38388505578041077,
      "learning_rate": 8.799225800722895e-05,
      "loss": 2.4428,
      "step": 51
    },
    {
      "epoch": 0.8156862745098039,
      "grad_norm": 0.4438699185848236,
      "learning_rate": 8.742553740855506e-05,
      "loss": 2.4849,
      "step": 52
    },
    {
      "epoch": 0.8313725490196079,
      "grad_norm": 0.4089072644710541,
      "learning_rate": 8.684766579921684e-05,
      "loss": 2.4612,
      "step": 53
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.45029300451278687,
      "learning_rate": 8.625881535716883e-05,
      "loss": 2.4742,
      "step": 54
    },
    {
      "epoch": 0.8627450980392157,
      "grad_norm": 0.4340762197971344,
      "learning_rate": 8.565916153152983e-05,
      "loss": 2.4731,
      "step": 55
    },
    {
      "epoch": 0.8784313725490196,
      "grad_norm": 0.4764128625392914,
      "learning_rate": 8.504888299030747e-05,
      "loss": 2.6086,
      "step": 56
    },
    {
      "epoch": 0.8941176470588236,
      "grad_norm": 0.5077619552612305,
      "learning_rate": 8.442816156716385e-05,
      "loss": 2.5386,
      "step": 57
    },
    {
      "epoch": 0.9098039215686274,
      "grad_norm": 0.5658111572265625,
      "learning_rate": 8.379718220723773e-05,
      "loss": 2.5659,
      "step": 58
    },
    {
      "epoch": 0.9254901960784314,
      "grad_norm": 0.6542505621910095,
      "learning_rate": 8.315613291203976e-05,
      "loss": 2.5815,
      "step": 59
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.9077744483947754,
      "learning_rate": 8.250520468343722e-05,
      "loss": 2.9127,
      "step": 60
    },
    {
      "epoch": 0.9568627450980393,
      "grad_norm": 0.3028375208377838,
      "learning_rate": 8.184459146674446e-05,
      "loss": 2.3544,
      "step": 61
    },
    {
      "epoch": 0.9725490196078431,
      "grad_norm": 0.37583601474761963,
      "learning_rate": 8.117449009293668e-05,
      "loss": 2.3619,
      "step": 62
    },
    {
      "epoch": 0.9882352941176471,
      "grad_norm": 0.5018683075904846,
      "learning_rate": 8.049510022000364e-05,
      "loss": 2.5821,
      "step": 63
    },
    {
      "epoch": 1.003921568627451,
      "grad_norm": 0.824658989906311,
      "learning_rate": 7.980662427346127e-05,
      "loss": 3.6075,
      "step": 64
    },
    {
      "epoch": 1.0196078431372548,
      "grad_norm": 0.2513439357280731,
      "learning_rate": 7.910926738603854e-05,
      "loss": 2.1654,
      "step": 65
    },
    {
      "epoch": 1.035294117647059,
      "grad_norm": 0.2941010296344757,
      "learning_rate": 7.840323733655778e-05,
      "loss": 2.2546,
      "step": 66
    },
    {
      "epoch": 1.0509803921568628,
      "grad_norm": 0.3366384506225586,
      "learning_rate": 7.768874448802665e-05,
      "loss": 2.41,
      "step": 67
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.32259663939476013,
      "learning_rate": 7.696600172495997e-05,
      "loss": 2.2745,
      "step": 68
    },
    {
      "epoch": 1.0823529411764705,
      "grad_norm": 0.34342584013938904,
      "learning_rate": 7.62352243899504e-05,
      "loss": 2.3813,
      "step": 69
    },
    {
      "epoch": 1.0980392156862746,
      "grad_norm": 0.3747313916683197,
      "learning_rate": 7.54966302195068e-05,
      "loss": 2.4037,
      "step": 70
    },
    {
      "epoch": 1.1137254901960785,
      "grad_norm": 0.3675015866756439,
      "learning_rate": 7.475043927917907e-05,
      "loss": 2.3497,
      "step": 71
    },
    {
      "epoch": 1.1294117647058823,
      "grad_norm": 0.36925432085990906,
      "learning_rate": 7.399687389798933e-05,
      "loss": 2.2603,
      "step": 72
    },
    {
      "epoch": 1.1450980392156862,
      "grad_norm": 0.4180779457092285,
      "learning_rate": 7.323615860218843e-05,
      "loss": 2.3582,
      "step": 73
    },
    {
      "epoch": 1.1607843137254903,
      "grad_norm": 0.47406819462776184,
      "learning_rate": 7.246852004835807e-05,
      "loss": 2.3733,
      "step": 74
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.485302597284317,
      "learning_rate": 7.169418695587791e-05,
      "loss": 2.3337,
      "step": 75
    },
    {
      "epoch": 1.192156862745098,
      "grad_norm": 0.539759635925293,
      "learning_rate": 7.091339003877826e-05,
      "loss": 2.3197,
      "step": 76
    },
    {
      "epoch": 1.2078431372549019,
      "grad_norm": 0.6110227108001709,
      "learning_rate": 7.012636193699837e-05,
      "loss": 2.109,
      "step": 77
    },
    {
      "epoch": 1.223529411764706,
      "grad_norm": 0.7330251336097717,
      "learning_rate": 6.933333714707094e-05,
      "loss": 2.3911,
      "step": 78
    },
    {
      "epoch": 1.2392156862745098,
      "grad_norm": 0.8158701062202454,
      "learning_rate": 6.853455195225338e-05,
      "loss": 2.6754,
      "step": 79
    },
    {
      "epoch": 1.2549019607843137,
      "grad_norm": 0.3269573748111725,
      "learning_rate": 6.773024435212678e-05,
      "loss": 2.1136,
      "step": 80
    },
    {
      "epoch": 1.2705882352941176,
      "grad_norm": 0.4158848226070404,
      "learning_rate": 6.692065399168352e-05,
      "loss": 2.3167,
      "step": 81
    },
    {
      "epoch": 1.2862745098039214,
      "grad_norm": 0.4102843999862671,
      "learning_rate": 6.610602208992454e-05,
      "loss": 2.2767,
      "step": 82
    },
    {
      "epoch": 1.3019607843137255,
      "grad_norm": 0.41636908054351807,
      "learning_rate": 6.528659136798764e-05,
      "loss": 2.2742,
      "step": 83
    },
    {
      "epoch": 1.3176470588235294,
      "grad_norm": 0.4526170492172241,
      "learning_rate": 6.446260597682839e-05,
      "loss": 2.3794,
      "step": 84
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.4637283384799957,
      "learning_rate": 6.363431142447469e-05,
      "loss": 2.3691,
      "step": 85
    },
    {
      "epoch": 1.3490196078431373,
      "grad_norm": 0.48547840118408203,
      "learning_rate": 6.280195450287736e-05,
      "loss": 2.344,
      "step": 86
    },
    {
      "epoch": 1.3647058823529412,
      "grad_norm": 0.48103803396224976,
      "learning_rate": 6.19657832143779e-05,
      "loss": 2.435,
      "step": 87
    },
    {
      "epoch": 1.380392156862745,
      "grad_norm": 0.4679640531539917,
      "learning_rate": 6.112604669781572e-05,
      "loss": 2.2715,
      "step": 88
    },
    {
      "epoch": 1.396078431372549,
      "grad_norm": 0.5256341695785522,
      "learning_rate": 6.028299515429683e-05,
      "loss": 2.3161,
      "step": 89
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.5306299328804016,
      "learning_rate": 5.943687977264584e-05,
      "loss": 2.3116,
      "step": 90
    },
    {
      "epoch": 1.427450980392157,
      "grad_norm": 0.6107631921768188,
      "learning_rate": 5.8587952654563817e-05,
      "loss": 2.3921,
      "step": 91
    },
    {
      "epoch": 1.4431372549019608,
      "grad_norm": 0.6549443006515503,
      "learning_rate": 5.773646673951406e-05,
      "loss": 2.2533,
      "step": 92
    },
    {
      "epoch": 1.4588235294117646,
      "grad_norm": 0.8716562986373901,
      "learning_rate": 5.688267572935842e-05,
      "loss": 2.5249,
      "step": 93
    },
    {
      "epoch": 1.4745098039215687,
      "grad_norm": 0.8429364562034607,
      "learning_rate": 5.602683401276615e-05,
      "loss": 2.5472,
      "step": 94
    },
    {
      "epoch": 1.4901960784313726,
      "grad_norm": 0.3356582224369049,
      "learning_rate": 5.5169196589418504e-05,
      "loss": 2.0268,
      "step": 95
    },
    {
      "epoch": 1.5058823529411764,
      "grad_norm": 0.4084802269935608,
      "learning_rate": 5.431001899403098e-05,
      "loss": 2.2999,
      "step": 96
    },
    {
      "epoch": 1.5215686274509803,
      "grad_norm": 0.4267803430557251,
      "learning_rate": 5.344955722021624e-05,
      "loss": 2.3227,
      "step": 97
    },
    {
      "epoch": 1.5372549019607842,
      "grad_norm": 0.4320634603500366,
      "learning_rate": 5.258806764421048e-05,
      "loss": 2.246,
      "step": 98
    },
    {
      "epoch": 1.5529411764705883,
      "grad_norm": 0.46851688623428345,
      "learning_rate": 5.172580694848541e-05,
      "loss": 2.3576,
      "step": 99
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.4941369593143463,
      "learning_rate": 5.086303204526943e-05,
      "loss": 2.3498,
      "step": 100
    },
    {
      "epoch": 1.5686274509803921,
      "eval_loss": 2.4987945556640625,
      "eval_runtime": 8.1314,
      "eval_samples_per_second": 13.282,
      "eval_steps_per_second": 3.32,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.36553356591104e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}