{
  "best_metric": 0.152464359998703,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.205761316872428,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00205761316872428,
      "grad_norm": 2.40505051612854,
      "learning_rate": 7e-06,
      "loss": 3.9248,
      "step": 1
    },
    {
      "epoch": 0.00205761316872428,
      "eval_loss": 1.5612297058105469,
      "eval_runtime": 38.7459,
      "eval_samples_per_second": 21.138,
      "eval_steps_per_second": 5.291,
      "step": 1
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 3.6444056034088135,
      "learning_rate": 1.4e-05,
      "loss": 4.3553,
      "step": 2
    },
    {
      "epoch": 0.006172839506172839,
      "grad_norm": 4.6960368156433105,
      "learning_rate": 2.1e-05,
      "loss": 5.058,
      "step": 3
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 5.9922943115234375,
      "learning_rate": 2.8e-05,
      "loss": 5.1701,
      "step": 4
    },
    {
      "epoch": 0.0102880658436214,
      "grad_norm": 4.798070907592773,
      "learning_rate": 3.5e-05,
      "loss": 5.3173,
      "step": 5
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": 5.446530818939209,
      "learning_rate": 4.2e-05,
      "loss": 4.8157,
      "step": 6
    },
    {
      "epoch": 0.01440329218106996,
      "grad_norm": 4.692366123199463,
      "learning_rate": 4.899999999999999e-05,
      "loss": 4.4251,
      "step": 7
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 3.962667942047119,
      "learning_rate": 5.6e-05,
      "loss": 4.1365,
      "step": 8
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 3.6138181686401367,
      "learning_rate": 6.3e-05,
      "loss": 3.507,
      "step": 9
    },
    {
      "epoch": 0.0205761316872428,
      "grad_norm": 3.06467604637146,
      "learning_rate": 7e-05,
      "loss": 3.1751,
      "step": 10
    },
    {
      "epoch": 0.02263374485596708,
      "grad_norm": 3.0617806911468506,
      "learning_rate": 6.999521567473641e-05,
      "loss": 2.6366,
      "step": 11
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 3.125230550765991,
      "learning_rate": 6.998086400693241e-05,
      "loss": 1.9493,
      "step": 12
    },
    {
      "epoch": 0.026748971193415638,
      "grad_norm": 2.617583751678467,
      "learning_rate": 6.995694892019065e-05,
      "loss": 2.1773,
      "step": 13
    },
    {
      "epoch": 0.02880658436213992,
      "grad_norm": 2.810847282409668,
      "learning_rate": 6.99234769526571e-05,
      "loss": 1.7846,
      "step": 14
    },
    {
      "epoch": 0.030864197530864196,
      "grad_norm": 2.3002936840057373,
      "learning_rate": 6.988045725523343e-05,
      "loss": 1.5039,
      "step": 15
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 2.374920606613159,
      "learning_rate": 6.982790158907539e-05,
      "loss": 1.7564,
      "step": 16
    },
    {
      "epoch": 0.03497942386831276,
      "grad_norm": 2.1841278076171875,
      "learning_rate": 6.976582432237733e-05,
      "loss": 1.3906,
      "step": 17
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.971739411354065,
      "learning_rate": 6.969424242644413e-05,
      "loss": 0.9276,
      "step": 18
    },
    {
      "epoch": 0.03909465020576132,
      "grad_norm": 1.8726739883422852,
      "learning_rate": 6.961317547105138e-05,
      "loss": 1.0064,
      "step": 19
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 1.9627259969711304,
      "learning_rate": 6.952264561909527e-05,
      "loss": 1.0283,
      "step": 20
    },
    {
      "epoch": 0.043209876543209874,
      "grad_norm": 1.958211064338684,
      "learning_rate": 6.942267762053337e-05,
      "loss": 0.8451,
      "step": 21
    },
    {
      "epoch": 0.04526748971193416,
      "grad_norm": 1.9346603155136108,
      "learning_rate": 6.931329880561832e-05,
      "loss": 0.8608,
      "step": 22
    },
    {
      "epoch": 0.047325102880658436,
      "grad_norm": 1.9274400472640991,
      "learning_rate": 6.919453907742597e-05,
      "loss": 0.8977,
      "step": 23
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 1.5571010112762451,
      "learning_rate": 6.90664309036802e-05,
      "loss": 0.7522,
      "step": 24
    },
    {
      "epoch": 0.051440329218107,
      "grad_norm": 1.8345186710357666,
      "learning_rate": 6.892900930787656e-05,
      "loss": 0.8573,
      "step": 25
    },
    {
      "epoch": 0.053497942386831275,
      "grad_norm": 2.217470645904541,
      "learning_rate": 6.87823118597072e-05,
      "loss": 1.1688,
      "step": 26
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 2.0658411979675293,
      "learning_rate": 6.862637866478969e-05,
      "loss": 1.2216,
      "step": 27
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 2.4393527507781982,
      "learning_rate": 6.846125235370252e-05,
      "loss": 1.6207,
      "step": 28
    },
    {
      "epoch": 0.059670781893004114,
      "grad_norm": 2.7012267112731934,
      "learning_rate": 6.828697807033038e-05,
      "loss": 1.263,
      "step": 29
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 2.90848445892334,
      "learning_rate": 6.81036034595222e-05,
      "loss": 1.7342,
      "step": 30
    },
    {
      "epoch": 0.06378600823045268,
      "grad_norm": 2.188056468963623,
      "learning_rate": 6.791117865406564e-05,
      "loss": 1.2297,
      "step": 31
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 2.465306520462036,
      "learning_rate": 6.770975626098112e-05,
      "loss": 1.2353,
      "step": 32
    },
    {
      "epoch": 0.06790123456790123,
      "grad_norm": 2.3670384883880615,
      "learning_rate": 6.749939134713974e-05,
      "loss": 1.2893,
      "step": 33
    },
    {
      "epoch": 0.06995884773662552,
      "grad_norm": 3.023275375366211,
      "learning_rate": 6.728014142420846e-05,
      "loss": 1.5351,
      "step": 34
    },
    {
      "epoch": 0.0720164609053498,
      "grad_norm": 2.6416513919830322,
      "learning_rate": 6.7052066432927e-05,
      "loss": 1.0203,
      "step": 35
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.6644809246063232,
      "learning_rate": 6.681522872672069e-05,
      "loss": 1.013,
      "step": 36
    },
    {
      "epoch": 0.07613168724279835,
      "grad_norm": 1.9997481107711792,
      "learning_rate": 6.656969305465356e-05,
      "loss": 0.8877,
      "step": 37
    },
    {
      "epoch": 0.07818930041152264,
      "grad_norm": 2.4777352809906006,
      "learning_rate": 6.631552654372672e-05,
      "loss": 0.8846,
      "step": 38
    },
    {
      "epoch": 0.08024691358024691,
      "grad_norm": 2.6934351921081543,
      "learning_rate": 6.60527986805264e-05,
      "loss": 0.926,
      "step": 39
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 3.536698341369629,
      "learning_rate": 6.578158129222711e-05,
      "loss": 0.6958,
      "step": 40
    },
    {
      "epoch": 0.08436213991769548,
      "grad_norm": 3.0982742309570312,
      "learning_rate": 6.550194852695469e-05,
      "loss": 0.6446,
      "step": 41
    },
    {
      "epoch": 0.08641975308641975,
      "grad_norm": 3.977778434753418,
      "learning_rate": 6.521397683351509e-05,
      "loss": 0.7436,
      "step": 42
    },
    {
      "epoch": 0.08847736625514403,
      "grad_norm": 3.3363654613494873,
      "learning_rate": 6.491774494049386e-05,
      "loss": 0.7582,
      "step": 43
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 3.820716142654419,
      "learning_rate": 6.461333383473272e-05,
      "loss": 0.7784,
      "step": 44
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 6.108582019805908,
      "learning_rate": 6.430082673918849e-05,
      "loss": 0.5698,
      "step": 45
    },
    {
      "epoch": 0.09465020576131687,
      "grad_norm": 5.08290958404541,
      "learning_rate": 6.398030909018069e-05,
      "loss": 0.6677,
      "step": 46
    },
    {
      "epoch": 0.09670781893004116,
      "grad_norm": 2.945241689682007,
      "learning_rate": 6.365186851403423e-05,
      "loss": 0.6415,
      "step": 47
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 2.914973020553589,
      "learning_rate": 6.331559480312315e-05,
      "loss": 0.6783,
      "step": 48
    },
    {
      "epoch": 0.10082304526748971,
      "grad_norm": 2.141970634460449,
      "learning_rate": 6.297157989132236e-05,
      "loss": 0.6053,
      "step": 49
    },
    {
      "epoch": 0.102880658436214,
      "grad_norm": 2.8987009525299072,
      "learning_rate": 6.261991782887377e-05,
      "loss": 0.5968,
      "step": 50
    },
    {
      "epoch": 0.102880658436214,
      "eval_loss": 0.3833325207233429,
      "eval_runtime": 39.56,
      "eval_samples_per_second": 20.703,
      "eval_steps_per_second": 5.182,
      "step": 50
    },
    {
      "epoch": 0.10493827160493827,
      "grad_norm": 21.277009963989258,
      "learning_rate": 6.226070475667393e-05,
      "loss": 7.9373,
      "step": 51
    },
    {
      "epoch": 0.10699588477366255,
      "grad_norm": 12.284491539001465,
      "learning_rate": 6.189403887999006e-05,
      "loss": 5.3044,
      "step": 52
    },
    {
      "epoch": 0.10905349794238683,
      "grad_norm": 10.717970848083496,
      "learning_rate": 6.152002044161171e-05,
      "loss": 2.2028,
      "step": 53
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 6.60059118270874,
      "learning_rate": 6.113875169444539e-05,
      "loss": 1.7998,
      "step": 54
    },
    {
      "epoch": 0.11316872427983539,
      "grad_norm": 4.140441417694092,
      "learning_rate": 6.0750336873559605e-05,
      "loss": 1.008,
      "step": 55
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 2.533043622970581,
      "learning_rate": 6.035488216768811e-05,
      "loss": 0.7792,
      "step": 56
    },
    {
      "epoch": 0.11728395061728394,
      "grad_norm": 1.9595946073532104,
      "learning_rate": 5.9952495690198894e-05,
      "loss": 0.7045,
      "step": 57
    },
    {
      "epoch": 0.11934156378600823,
      "grad_norm": 1.5208021402359009,
      "learning_rate": 5.954328744953709e-05,
      "loss": 0.604,
      "step": 58
    },
    {
      "epoch": 0.12139917695473251,
      "grad_norm": 1.1410841941833496,
      "learning_rate": 5.91273693191498e-05,
      "loss": 0.4636,
      "step": 59
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 1.3440451622009277,
      "learning_rate": 5.870485500690094e-05,
      "loss": 0.5507,
      "step": 60
    },
    {
      "epoch": 0.12551440329218108,
      "grad_norm": 1.9705235958099365,
      "learning_rate": 5.827586002398468e-05,
      "loss": 0.6043,
      "step": 61
    },
    {
      "epoch": 0.12757201646090535,
      "grad_norm": 1.21955406665802,
      "learning_rate": 5.784050165334589e-05,
      "loss": 0.4929,
      "step": 62
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 1.155280351638794,
      "learning_rate": 5.739889891761608e-05,
      "loss": 0.4327,
      "step": 63
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 1.0522754192352295,
      "learning_rate": 5.6951172546573794e-05,
      "loss": 0.3859,
      "step": 64
    },
    {
      "epoch": 0.1337448559670782,
      "grad_norm": 0.9591506719589233,
      "learning_rate": 5.6497444944138376e-05,
      "loss": 0.4154,
      "step": 65
    },
    {
      "epoch": 0.13580246913580246,
      "grad_norm": 1.126166820526123,
      "learning_rate": 5.603784015490587e-05,
      "loss": 0.4482,
      "step": 66
    },
    {
      "epoch": 0.13786008230452676,
      "grad_norm": 1.1399197578430176,
      "learning_rate": 5.557248383023655e-05,
      "loss": 0.3882,
      "step": 67
    },
    {
      "epoch": 0.13991769547325103,
      "grad_norm": 1.0086866617202759,
      "learning_rate": 5.510150319390302e-05,
      "loss": 0.3451,
      "step": 68
    },
    {
      "epoch": 0.1419753086419753,
      "grad_norm": 1.1888667345046997,
      "learning_rate": 5.4625027007308546e-05,
      "loss": 0.4558,
      "step": 69
    },
    {
      "epoch": 0.1440329218106996,
      "grad_norm": 1.1290650367736816,
      "learning_rate": 5.414318553428494e-05,
      "loss": 0.4067,
      "step": 70
    },
    {
      "epoch": 0.14609053497942387,
      "grad_norm": 1.6422878503799438,
      "learning_rate": 5.3656110505479776e-05,
      "loss": 0.3683,
      "step": 71
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.2845423221588135,
      "learning_rate": 5.316393508234253e-05,
      "loss": 0.2984,
      "step": 72
    },
    {
      "epoch": 0.15020576131687244,
      "grad_norm": 1.0456984043121338,
      "learning_rate": 5.266679382071953e-05,
      "loss": 0.3511,
      "step": 73
    },
    {
      "epoch": 0.1522633744855967,
      "grad_norm": 0.9409389495849609,
      "learning_rate": 5.216482263406778e-05,
      "loss": 0.307,
      "step": 74
    },
    {
      "epoch": 0.15432098765432098,
      "grad_norm": 1.100905418395996,
      "learning_rate": 5.1658158756297576e-05,
      "loss": 0.4262,
      "step": 75
    },
    {
      "epoch": 0.15637860082304528,
      "grad_norm": 1.0456651449203491,
      "learning_rate": 5.114694070425407e-05,
      "loss": 0.4237,
      "step": 76
    },
    {
      "epoch": 0.15843621399176955,
      "grad_norm": 1.660601258277893,
      "learning_rate": 5.063130823984823e-05,
      "loss": 0.635,
      "step": 77
    },
    {
      "epoch": 0.16049382716049382,
      "grad_norm": 1.9623562097549438,
      "learning_rate": 5.011140233184724e-05,
      "loss": 0.6901,
      "step": 78
    },
    {
      "epoch": 0.16255144032921812,
      "grad_norm": 1.5435357093811035,
      "learning_rate": 4.958736511733516e-05,
      "loss": 0.5541,
      "step": 79
    },
    {
      "epoch": 0.1646090534979424,
      "grad_norm": 1.3062795400619507,
      "learning_rate": 4.905933986285393e-05,
      "loss": 0.4875,
      "step": 80
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.2251200675964355,
      "learning_rate": 4.8527470925235824e-05,
      "loss": 0.4161,
      "step": 81
    },
    {
      "epoch": 0.16872427983539096,
      "grad_norm": 1.052963137626648,
      "learning_rate": 4.799190371213772e-05,
      "loss": 0.3798,
      "step": 82
    },
    {
      "epoch": 0.17078189300411523,
      "grad_norm": 1.3962211608886719,
      "learning_rate": 4.745278464228808e-05,
      "loss": 0.4614,
      "step": 83
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 1.0526316165924072,
      "learning_rate": 4.69102611054575e-05,
      "loss": 0.3336,
      "step": 84
    },
    {
      "epoch": 0.1748971193415638,
      "grad_norm": 1.447713017463684,
      "learning_rate": 4.6364481422163926e-05,
      "loss": 0.3422,
      "step": 85
    },
    {
      "epoch": 0.17695473251028807,
      "grad_norm": 1.987180233001709,
      "learning_rate": 4.581559480312316e-05,
      "loss": 0.4365,
      "step": 86
    },
    {
      "epoch": 0.17901234567901234,
      "grad_norm": 2.7361459732055664,
      "learning_rate": 4.526375130845627e-05,
      "loss": 0.3779,
      "step": 87
    },
    {
      "epoch": 0.18106995884773663,
      "grad_norm": 2.2039506435394287,
      "learning_rate": 4.4709101806664554e-05,
      "loss": 0.3907,
      "step": 88
    },
    {
      "epoch": 0.1831275720164609,
      "grad_norm": 1.2355520725250244,
      "learning_rate": 4.4151797933383685e-05,
      "loss": 0.2849,
      "step": 89
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 2.4810612201690674,
      "learning_rate": 4.359199204992797e-05,
      "loss": 0.4476,
      "step": 90
    },
    {
      "epoch": 0.18724279835390947,
      "grad_norm": 2.8064424991607666,
      "learning_rate": 4.30298372016363e-05,
      "loss": 0.5126,
      "step": 91
    },
    {
      "epoch": 0.18930041152263374,
      "grad_norm": 1.7459629774093628,
      "learning_rate": 4.246548707603114e-05,
      "loss": 0.3313,
      "step": 92
    },
    {
      "epoch": 0.19135802469135801,
      "grad_norm": 1.216896414756775,
      "learning_rate": 4.1899095960801805e-05,
      "loss": 0.2666,
      "step": 93
    },
    {
      "epoch": 0.1934156378600823,
      "grad_norm": 1.6271848678588867,
      "learning_rate": 4.133081870162385e-05,
      "loss": 0.3523,
      "step": 94
    },
    {
      "epoch": 0.19547325102880658,
      "grad_norm": 2.0596134662628174,
      "learning_rate": 4.076081065982569e-05,
      "loss": 0.3127,
      "step": 95
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.5387978553771973,
      "learning_rate": 4.018922766991447e-05,
      "loss": 0.268,
      "step": 96
    },
    {
      "epoch": 0.19958847736625515,
      "grad_norm": 1.8610491752624512,
      "learning_rate": 3.961622599697241e-05,
      "loss": 0.2759,
      "step": 97
    },
    {
      "epoch": 0.20164609053497942,
      "grad_norm": 1.53598952293396,
      "learning_rate": 3.9041962293935516e-05,
      "loss": 0.2989,
      "step": 98
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 1.305046796798706,
      "learning_rate": 3.84665935587662e-05,
      "loss": 0.2431,
      "step": 99
    },
    {
      "epoch": 0.205761316872428,
      "grad_norm": 1.9852741956710815,
      "learning_rate": 3.7890277091531636e-05,
      "loss": 0.276,
      "step": 100
    },
    {
      "epoch": 0.205761316872428,
      "eval_loss": 0.152464359998703,
      "eval_runtime": 39.5141,
      "eval_samples_per_second": 20.727,
      "eval_steps_per_second": 5.188,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "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": 7.55390862065664e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}