{
  "best_metric": 2.0897529125213623,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.3436426116838488,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003436426116838488,
      "grad_norm": 2.598952531814575,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.6926,
      "step": 1
    },
    {
      "epoch": 0.003436426116838488,
      "eval_loss": 2.560588836669922,
      "eval_runtime": 5.717,
      "eval_samples_per_second": 85.709,
      "eval_steps_per_second": 42.854,
      "step": 1
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 0.9321181178092957,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.4309,
      "step": 2
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 0.8906644582748413,
      "learning_rate": 1e-05,
      "loss": 2.4272,
      "step": 3
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 0.9309356212615967,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.352,
      "step": 4
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 0.9476458430290222,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.3942,
      "step": 5
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.84200119972229,
      "learning_rate": 2e-05,
      "loss": 2.4314,
      "step": 6
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": 0.813735842704773,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 2.3328,
      "step": 7
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 0.7815460562705994,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 2.3069,
      "step": 8
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 0.9551405906677246,
      "learning_rate": 3e-05,
      "loss": 2.4007,
      "step": 9
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 0.9483513236045837,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3146,
      "step": 10
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": 0.7717857956886292,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 2.3159,
      "step": 11
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.6075471043586731,
      "learning_rate": 4e-05,
      "loss": 2.35,
      "step": 12
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": 0.7033193707466125,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 2.2876,
      "step": 13
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 1.1663984060287476,
      "learning_rate": 4.666666666666667e-05,
      "loss": 2.3147,
      "step": 14
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.9267627596855164,
      "learning_rate": 5e-05,
      "loss": 2.2235,
      "step": 15
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 0.5572108030319214,
      "learning_rate": 5.333333333333333e-05,
      "loss": 2.232,
      "step": 16
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": 0.7132498621940613,
      "learning_rate": 5.666666666666667e-05,
      "loss": 2.2246,
      "step": 17
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.7393128275871277,
      "learning_rate": 6e-05,
      "loss": 2.3398,
      "step": 18
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": 1.1601158380508423,
      "learning_rate": 6.333333333333333e-05,
      "loss": 2.2403,
      "step": 19
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.7413552403450012,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.2669,
      "step": 20
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 0.787192165851593,
      "learning_rate": 7e-05,
      "loss": 2.1568,
      "step": 21
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 0.534079372882843,
      "learning_rate": 7.333333333333333e-05,
      "loss": 2.1813,
      "step": 22
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": 0.659359335899353,
      "learning_rate": 7.666666666666667e-05,
      "loss": 2.2229,
      "step": 23
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 1.122572422027588,
      "learning_rate": 8e-05,
      "loss": 2.2512,
      "step": 24
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 0.6070332527160645,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.2574,
      "step": 25
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 0.6394221782684326,
      "learning_rate": 8.666666666666667e-05,
      "loss": 2.284,
      "step": 26
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 0.6970255374908447,
      "learning_rate": 9e-05,
      "loss": 2.2624,
      "step": 27
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 0.6242474317550659,
      "learning_rate": 9.333333333333334e-05,
      "loss": 2.3183,
      "step": 28
    },
    {
      "epoch": 0.09965635738831616,
      "grad_norm": 1.235068678855896,
      "learning_rate": 9.666666666666667e-05,
      "loss": 2.2588,
      "step": 29
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.8682904839515686,
      "learning_rate": 0.0001,
      "loss": 2.1751,
      "step": 30
    },
    {
      "epoch": 0.10652920962199312,
      "grad_norm": 0.526172399520874,
      "learning_rate": 9.994965332706573e-05,
      "loss": 2.2512,
      "step": 31
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 0.5551455616950989,
      "learning_rate": 9.979871469976196e-05,
      "loss": 2.2022,
      "step": 32
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 1.1410373449325562,
      "learning_rate": 9.954748808839674e-05,
      "loss": 2.1849,
      "step": 33
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 0.8865669965744019,
      "learning_rate": 9.919647942993148e-05,
      "loss": 2.2,
      "step": 34
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 0.7990866899490356,
      "learning_rate": 9.874639560909117e-05,
      "loss": 2.2292,
      "step": 35
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.663706362247467,
      "learning_rate": 9.819814303479267e-05,
      "loss": 2.2103,
      "step": 36
    },
    {
      "epoch": 0.12714776632302405,
      "grad_norm": 0.7638304829597473,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.2755,
      "step": 37
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 0.5578743815422058,
      "learning_rate": 9.681174353198687e-05,
      "loss": 2.1697,
      "step": 38
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 0.6033037900924683,
      "learning_rate": 9.597638862757255e-05,
      "loss": 2.1311,
      "step": 39
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.6790174841880798,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.2376,
      "step": 40
    },
    {
      "epoch": 0.140893470790378,
      "grad_norm": 0.6558031439781189,
      "learning_rate": 9.40297765928369e-05,
      "loss": 2.2629,
      "step": 41
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.7051690816879272,
      "learning_rate": 9.292243968009331e-05,
      "loss": 2.1542,
      "step": 42
    },
    {
      "epoch": 0.14776632302405499,
      "grad_norm": 0.6233033537864685,
      "learning_rate": 9.172866268606513e-05,
      "loss": 2.0878,
      "step": 43
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.6979764103889465,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.2168,
      "step": 44
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.6884151697158813,
      "learning_rate": 8.90915741234015e-05,
      "loss": 2.1874,
      "step": 45
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 0.7308196425437927,
      "learning_rate": 8.765357330018056e-05,
      "loss": 2.2639,
      "step": 46
    },
    {
      "epoch": 0.16151202749140894,
      "grad_norm": 1.1044234037399292,
      "learning_rate": 8.613974319136958e-05,
      "loss": 2.2313,
      "step": 47
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.8167080283164978,
      "learning_rate": 8.455313244934324e-05,
      "loss": 2.2786,
      "step": 48
    },
    {
      "epoch": 0.16838487972508592,
      "grad_norm": 0.9312572479248047,
      "learning_rate": 8.289693629698564e-05,
      "loss": 2.3531,
      "step": 49
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 0.8995051980018616,
      "learning_rate": 8.117449009293668e-05,
      "loss": 2.4697,
      "step": 50
    },
    {
      "epoch": 0.1718213058419244,
      "eval_loss": 2.247523784637451,
      "eval_runtime": 5.6668,
      "eval_samples_per_second": 86.468,
      "eval_steps_per_second": 43.234,
      "step": 50
    },
    {
      "epoch": 0.17525773195876287,
      "grad_norm": 2.528313159942627,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.3671,
      "step": 51
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 2.315145969390869,
      "learning_rate": 7.754484907260513e-05,
      "loss": 2.3046,
      "step": 52
    },
    {
      "epoch": 0.18213058419243985,
      "grad_norm": 1.7192437648773193,
      "learning_rate": 7.564496387029532e-05,
      "loss": 2.1694,
      "step": 53
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 1.133732557296753,
      "learning_rate": 7.369343312364993e-05,
      "loss": 2.1953,
      "step": 54
    },
    {
      "epoch": 0.18900343642611683,
      "grad_norm": 0.713290274143219,
      "learning_rate": 7.169418695587791e-05,
      "loss": 2.053,
      "step": 55
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 0.5978623032569885,
      "learning_rate": 6.965125158269619e-05,
      "loss": 2.12,
      "step": 56
    },
    {
      "epoch": 0.1958762886597938,
      "grad_norm": 0.5948276519775391,
      "learning_rate": 6.756874120406714e-05,
      "loss": 2.1898,
      "step": 57
    },
    {
      "epoch": 0.19931271477663232,
      "grad_norm": 0.6025165319442749,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1185,
      "step": 58
    },
    {
      "epoch": 0.2027491408934708,
      "grad_norm": 0.5380327105522156,
      "learning_rate": 6.330184227833376e-05,
      "loss": 2.0913,
      "step": 59
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.5481085777282715,
      "learning_rate": 6.112604669781572e-05,
      "loss": 1.9754,
      "step": 60
    },
    {
      "epoch": 0.20962199312714777,
      "grad_norm": 0.5363459587097168,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 2.1673,
      "step": 61
    },
    {
      "epoch": 0.21305841924398625,
      "grad_norm": 0.4893956482410431,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 2.0366,
      "step": 62
    },
    {
      "epoch": 0.21649484536082475,
      "grad_norm": 0.4866885542869568,
      "learning_rate": 5.448196544517168e-05,
      "loss": 2.0198,
      "step": 63
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 0.4834136664867401,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 2.058,
      "step": 64
    },
    {
      "epoch": 0.22336769759450173,
      "grad_norm": 0.47863930463790894,
      "learning_rate": 5e-05,
      "loss": 2.0112,
      "step": 65
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.5112380385398865,
      "learning_rate": 4.775675848247427e-05,
      "loss": 2.0965,
      "step": 66
    },
    {
      "epoch": 0.23024054982817868,
      "grad_norm": 0.4476987421512604,
      "learning_rate": 4.551803455482833e-05,
      "loss": 2.013,
      "step": 67
    },
    {
      "epoch": 0.23367697594501718,
      "grad_norm": 0.4423470199108124,
      "learning_rate": 4.328833670911724e-05,
      "loss": 1.9623,
      "step": 68
    },
    {
      "epoch": 0.23711340206185566,
      "grad_norm": 0.4461471140384674,
      "learning_rate": 4.107215526006817e-05,
      "loss": 2.0052,
      "step": 69
    },
    {
      "epoch": 0.24054982817869416,
      "grad_norm": 0.5078745484352112,
      "learning_rate": 3.887395330218429e-05,
      "loss": 2.0747,
      "step": 70
    },
    {
      "epoch": 0.24398625429553264,
      "grad_norm": 0.4781670868396759,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 2.125,
      "step": 71
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.47303977608680725,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9952,
      "step": 72
    },
    {
      "epoch": 0.2508591065292096,
      "grad_norm": 0.4364500343799591,
      "learning_rate": 3.243125879593286e-05,
      "loss": 2.0303,
      "step": 73
    },
    {
      "epoch": 0.2542955326460481,
      "grad_norm": 0.47456878423690796,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 2.1002,
      "step": 74
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 0.4605971872806549,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 2.0942,
      "step": 75
    },
    {
      "epoch": 0.2611683848797251,
      "grad_norm": 0.4621974229812622,
      "learning_rate": 2.630656687635007e-05,
      "loss": 2.0768,
      "step": 76
    },
    {
      "epoch": 0.2646048109965636,
      "grad_norm": 0.4659442603588104,
      "learning_rate": 2.43550361297047e-05,
      "loss": 2.0493,
      "step": 77
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 0.47574934363365173,
      "learning_rate": 2.245515092739488e-05,
      "loss": 2.0854,
      "step": 78
    },
    {
      "epoch": 0.27147766323024053,
      "grad_norm": 0.46890461444854736,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0456,
      "step": 79
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 0.4491337239742279,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 2.0834,
      "step": 80
    },
    {
      "epoch": 0.27835051546391754,
      "grad_norm": 0.46741199493408203,
      "learning_rate": 1.7103063703014372e-05,
      "loss": 2.0842,
      "step": 81
    },
    {
      "epoch": 0.281786941580756,
      "grad_norm": 0.47655144333839417,
      "learning_rate": 1.544686755065677e-05,
      "loss": 2.1256,
      "step": 82
    },
    {
      "epoch": 0.2852233676975945,
      "grad_norm": 0.45900094509124756,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 2.1237,
      "step": 83
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.4810255169868469,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 2.1193,
      "step": 84
    },
    {
      "epoch": 0.2920962199312715,
      "grad_norm": 0.4391408860683441,
      "learning_rate": 1.090842587659851e-05,
      "loss": 2.0282,
      "step": 85
    },
    {
      "epoch": 0.29553264604810997,
      "grad_norm": 0.4718332886695862,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.1053,
      "step": 86
    },
    {
      "epoch": 0.29896907216494845,
      "grad_norm": 0.48831039667129517,
      "learning_rate": 8.271337313934869e-06,
      "loss": 2.0954,
      "step": 87
    },
    {
      "epoch": 0.3024054982817869,
      "grad_norm": 0.4913262128829956,
      "learning_rate": 7.077560319906695e-06,
      "loss": 1.9763,
      "step": 88
    },
    {
      "epoch": 0.30584192439862545,
      "grad_norm": 0.5028262734413147,
      "learning_rate": 5.9702234071631e-06,
      "loss": 2.1451,
      "step": 89
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 0.5151122808456421,
      "learning_rate": 4.951556604879048e-06,
      "loss": 2.1428,
      "step": 90
    },
    {
      "epoch": 0.3127147766323024,
      "grad_norm": 0.5513173937797546,
      "learning_rate": 4.023611372427471e-06,
      "loss": 2.1041,
      "step": 91
    },
    {
      "epoch": 0.3161512027491409,
      "grad_norm": 0.541987955570221,
      "learning_rate": 3.18825646801314e-06,
      "loss": 2.2697,
      "step": 92
    },
    {
      "epoch": 0.31958762886597936,
      "grad_norm": 0.638981282711029,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.2158,
      "step": 93
    },
    {
      "epoch": 0.3230240549828179,
      "grad_norm": 0.6572893261909485,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 2.1798,
      "step": 94
    },
    {
      "epoch": 0.32646048109965636,
      "grad_norm": 0.6969611644744873,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 2.2424,
      "step": 95
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.7528119087219238,
      "learning_rate": 8.035205700685167e-07,
      "loss": 2.1574,
      "step": 96
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.8161905407905579,
      "learning_rate": 4.52511911603265e-07,
      "loss": 2.3423,
      "step": 97
    },
    {
      "epoch": 0.33676975945017185,
      "grad_norm": 0.9732829928398132,
      "learning_rate": 2.012853002380466e-07,
      "loss": 2.164,
      "step": 98
    },
    {
      "epoch": 0.3402061855670103,
      "grad_norm": 1.047484278678894,
      "learning_rate": 5.0346672934270534e-08,
      "loss": 2.2618,
      "step": 99
    },
    {
      "epoch": 0.3436426116838488,
      "grad_norm": 1.2029303312301636,
      "learning_rate": 0.0,
      "loss": 2.36,
      "step": 100
    },
    {
      "epoch": 0.3436426116838488,
      "eval_loss": 2.0897529125213623,
      "eval_runtime": 5.6482,
      "eval_samples_per_second": 86.753,
      "eval_steps_per_second": 43.376,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3200049060249600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}