{
  "best_metric": 2.09364652633667,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.13802622498274672,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013802622498274672,
      "grad_norm": 1.3106821775436401,
      "learning_rate": 1.004e-05,
      "loss": 3.6649,
      "step": 1
    },
    {
      "epoch": 0.0013802622498274672,
      "eval_loss": 3.9833779335021973,
      "eval_runtime": 7.1368,
      "eval_samples_per_second": 42.736,
      "eval_steps_per_second": 10.789,
      "step": 1
    },
    {
      "epoch": 0.0027605244996549345,
      "grad_norm": 1.2568550109863281,
      "learning_rate": 2.008e-05,
      "loss": 3.4178,
      "step": 2
    },
    {
      "epoch": 0.004140786749482402,
      "grad_norm": 1.7689608335494995,
      "learning_rate": 3.012e-05,
      "loss": 4.1951,
      "step": 3
    },
    {
      "epoch": 0.005521048999309869,
      "grad_norm": 1.5144968032836914,
      "learning_rate": 4.016e-05,
      "loss": 3.4457,
      "step": 4
    },
    {
      "epoch": 0.006901311249137336,
      "grad_norm": 1.4309552907943726,
      "learning_rate": 5.02e-05,
      "loss": 3.1559,
      "step": 5
    },
    {
      "epoch": 0.008281573498964804,
      "grad_norm": 1.4668313264846802,
      "learning_rate": 6.024e-05,
      "loss": 3.1952,
      "step": 6
    },
    {
      "epoch": 0.00966183574879227,
      "grad_norm": 1.4052668809890747,
      "learning_rate": 7.028e-05,
      "loss": 3.7713,
      "step": 7
    },
    {
      "epoch": 0.011042097998619738,
      "grad_norm": 1.7720158100128174,
      "learning_rate": 8.032e-05,
      "loss": 3.3666,
      "step": 8
    },
    {
      "epoch": 0.012422360248447204,
      "grad_norm": 1.3920046091079712,
      "learning_rate": 9.036000000000001e-05,
      "loss": 3.0858,
      "step": 9
    },
    {
      "epoch": 0.013802622498274672,
      "grad_norm": 1.6270596981048584,
      "learning_rate": 0.0001004,
      "loss": 3.4722,
      "step": 10
    },
    {
      "epoch": 0.01518288474810214,
      "grad_norm": 1.4511244297027588,
      "learning_rate": 9.987157894736842e-05,
      "loss": 3.1096,
      "step": 11
    },
    {
      "epoch": 0.016563146997929608,
      "grad_norm": 1.6646735668182373,
      "learning_rate": 9.934315789473684e-05,
      "loss": 3.1367,
      "step": 12
    },
    {
      "epoch": 0.017943409247757072,
      "grad_norm": 1.7026424407958984,
      "learning_rate": 9.881473684210525e-05,
      "loss": 3.3196,
      "step": 13
    },
    {
      "epoch": 0.01932367149758454,
      "grad_norm": 1.546176791191101,
      "learning_rate": 9.828631578947369e-05,
      "loss": 2.9841,
      "step": 14
    },
    {
      "epoch": 0.020703933747412008,
      "grad_norm": 1.343595027923584,
      "learning_rate": 9.77578947368421e-05,
      "loss": 3.0285,
      "step": 15
    },
    {
      "epoch": 0.022084195997239476,
      "grad_norm": 1.4044378995895386,
      "learning_rate": 9.722947368421052e-05,
      "loss": 2.7441,
      "step": 16
    },
    {
      "epoch": 0.023464458247066944,
      "grad_norm": 1.4049690961837769,
      "learning_rate": 9.670105263157895e-05,
      "loss": 3.085,
      "step": 17
    },
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 1.8391739130020142,
      "learning_rate": 9.617263157894737e-05,
      "loss": 2.3826,
      "step": 18
    },
    {
      "epoch": 0.026224982746721876,
      "grad_norm": 1.7621740102767944,
      "learning_rate": 9.564421052631579e-05,
      "loss": 3.0509,
      "step": 19
    },
    {
      "epoch": 0.027605244996549344,
      "grad_norm": 1.8850064277648926,
      "learning_rate": 9.511578947368421e-05,
      "loss": 2.6851,
      "step": 20
    },
    {
      "epoch": 0.028985507246376812,
      "grad_norm": 2.0599141120910645,
      "learning_rate": 9.458736842105264e-05,
      "loss": 2.9651,
      "step": 21
    },
    {
      "epoch": 0.03036576949620428,
      "grad_norm": 1.4605776071548462,
      "learning_rate": 9.405894736842106e-05,
      "loss": 3.0117,
      "step": 22
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 1.492771863937378,
      "learning_rate": 9.353052631578947e-05,
      "loss": 2.2637,
      "step": 23
    },
    {
      "epoch": 0.033126293995859216,
      "grad_norm": 1.553098201751709,
      "learning_rate": 9.300210526315789e-05,
      "loss": 2.8497,
      "step": 24
    },
    {
      "epoch": 0.03450655624568668,
      "grad_norm": 1.5250822305679321,
      "learning_rate": 9.247368421052631e-05,
      "loss": 2.5029,
      "step": 25
    },
    {
      "epoch": 0.035886818495514144,
      "grad_norm": 1.6337836980819702,
      "learning_rate": 9.194526315789473e-05,
      "loss": 2.6613,
      "step": 26
    },
    {
      "epoch": 0.037267080745341616,
      "grad_norm": 1.2553786039352417,
      "learning_rate": 9.141684210526316e-05,
      "loss": 2.7623,
      "step": 27
    },
    {
      "epoch": 0.03864734299516908,
      "grad_norm": 1.3037574291229248,
      "learning_rate": 9.088842105263158e-05,
      "loss": 2.6177,
      "step": 28
    },
    {
      "epoch": 0.04002760524499655,
      "grad_norm": 1.4453455209732056,
      "learning_rate": 9.036000000000001e-05,
      "loss": 2.7302,
      "step": 29
    },
    {
      "epoch": 0.041407867494824016,
      "grad_norm": 1.390273928642273,
      "learning_rate": 8.983157894736843e-05,
      "loss": 2.734,
      "step": 30
    },
    {
      "epoch": 0.04278812974465148,
      "grad_norm": 1.2343300580978394,
      "learning_rate": 8.930315789473684e-05,
      "loss": 2.6957,
      "step": 31
    },
    {
      "epoch": 0.04416839199447895,
      "grad_norm": 1.5033609867095947,
      "learning_rate": 8.877473684210526e-05,
      "loss": 2.7113,
      "step": 32
    },
    {
      "epoch": 0.045548654244306416,
      "grad_norm": 1.31312096118927,
      "learning_rate": 8.824631578947368e-05,
      "loss": 2.2402,
      "step": 33
    },
    {
      "epoch": 0.04692891649413389,
      "grad_norm": 1.6782886981964111,
      "learning_rate": 8.771789473684211e-05,
      "loss": 3.0312,
      "step": 34
    },
    {
      "epoch": 0.04830917874396135,
      "grad_norm": 1.358025074005127,
      "learning_rate": 8.718947368421053e-05,
      "loss": 2.9553,
      "step": 35
    },
    {
      "epoch": 0.049689440993788817,
      "grad_norm": 1.3450242280960083,
      "learning_rate": 8.666105263157895e-05,
      "loss": 2.1944,
      "step": 36
    },
    {
      "epoch": 0.05106970324361629,
      "grad_norm": 1.7064541578292847,
      "learning_rate": 8.613263157894737e-05,
      "loss": 2.8165,
      "step": 37
    },
    {
      "epoch": 0.05244996549344375,
      "grad_norm": 1.2318989038467407,
      "learning_rate": 8.560421052631578e-05,
      "loss": 2.3564,
      "step": 38
    },
    {
      "epoch": 0.053830227743271224,
      "grad_norm": 1.4910681247711182,
      "learning_rate": 8.50757894736842e-05,
      "loss": 2.3236,
      "step": 39
    },
    {
      "epoch": 0.05521048999309869,
      "grad_norm": 1.3855364322662354,
      "learning_rate": 8.454736842105263e-05,
      "loss": 2.0899,
      "step": 40
    },
    {
      "epoch": 0.05659075224292615,
      "grad_norm": 1.4245091676712036,
      "learning_rate": 8.401894736842106e-05,
      "loss": 2.5376,
      "step": 41
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 1.459370732307434,
      "learning_rate": 8.349052631578948e-05,
      "loss": 2.4498,
      "step": 42
    },
    {
      "epoch": 0.05935127674258109,
      "grad_norm": 1.5853793621063232,
      "learning_rate": 8.29621052631579e-05,
      "loss": 2.2517,
      "step": 43
    },
    {
      "epoch": 0.06073153899240856,
      "grad_norm": 1.3990416526794434,
      "learning_rate": 8.243368421052632e-05,
      "loss": 2.2779,
      "step": 44
    },
    {
      "epoch": 0.062111801242236024,
      "grad_norm": 1.500887155532837,
      "learning_rate": 8.190526315789474e-05,
      "loss": 2.6741,
      "step": 45
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 2.369209051132202,
      "learning_rate": 8.137684210526315e-05,
      "loss": 2.6675,
      "step": 46
    },
    {
      "epoch": 0.06487232574189096,
      "grad_norm": 1.673604965209961,
      "learning_rate": 8.084842105263157e-05,
      "loss": 1.6952,
      "step": 47
    },
    {
      "epoch": 0.06625258799171843,
      "grad_norm": 2.053783655166626,
      "learning_rate": 8.032e-05,
      "loss": 1.8816,
      "step": 48
    },
    {
      "epoch": 0.06763285024154589,
      "grad_norm": 2.251725435256958,
      "learning_rate": 7.979157894736842e-05,
      "loss": 2.3692,
      "step": 49
    },
    {
      "epoch": 0.06901311249137336,
      "grad_norm": 3.693898916244507,
      "learning_rate": 7.926315789473684e-05,
      "loss": 2.2844,
      "step": 50
    },
    {
      "epoch": 0.06901311249137336,
      "eval_loss": 2.2726948261260986,
      "eval_runtime": 7.0598,
      "eval_samples_per_second": 43.202,
      "eval_steps_per_second": 10.907,
      "step": 50
    },
    {
      "epoch": 0.07039337474120083,
      "grad_norm": 2.035337209701538,
      "learning_rate": 7.873473684210526e-05,
      "loss": 2.4293,
      "step": 51
    },
    {
      "epoch": 0.07177363699102829,
      "grad_norm": 1.4800270795822144,
      "learning_rate": 7.820631578947369e-05,
      "loss": 1.8436,
      "step": 52
    },
    {
      "epoch": 0.07315389924085576,
      "grad_norm": 1.2643930912017822,
      "learning_rate": 7.76778947368421e-05,
      "loss": 2.451,
      "step": 53
    },
    {
      "epoch": 0.07453416149068323,
      "grad_norm": 1.1129631996154785,
      "learning_rate": 7.714947368421052e-05,
      "loss": 2.1686,
      "step": 54
    },
    {
      "epoch": 0.0759144237405107,
      "grad_norm": 1.9466997385025024,
      "learning_rate": 7.662105263157896e-05,
      "loss": 3.0566,
      "step": 55
    },
    {
      "epoch": 0.07729468599033816,
      "grad_norm": 1.585560917854309,
      "learning_rate": 7.609263157894737e-05,
      "loss": 2.9491,
      "step": 56
    },
    {
      "epoch": 0.07867494824016563,
      "grad_norm": 1.148253321647644,
      "learning_rate": 7.556421052631579e-05,
      "loss": 2.5166,
      "step": 57
    },
    {
      "epoch": 0.0800552104899931,
      "grad_norm": 1.3044848442077637,
      "learning_rate": 7.503578947368421e-05,
      "loss": 2.061,
      "step": 58
    },
    {
      "epoch": 0.08143547273982056,
      "grad_norm": 1.3018648624420166,
      "learning_rate": 7.450736842105263e-05,
      "loss": 2.2174,
      "step": 59
    },
    {
      "epoch": 0.08281573498964803,
      "grad_norm": 1.179358720779419,
      "learning_rate": 7.397894736842105e-05,
      "loss": 1.8668,
      "step": 60
    },
    {
      "epoch": 0.0841959972394755,
      "grad_norm": 1.4359699487686157,
      "learning_rate": 7.345052631578948e-05,
      "loss": 1.8076,
      "step": 61
    },
    {
      "epoch": 0.08557625948930296,
      "grad_norm": 1.429067611694336,
      "learning_rate": 7.29221052631579e-05,
      "loss": 2.0383,
      "step": 62
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 1.4482382535934448,
      "learning_rate": 7.239368421052631e-05,
      "loss": 2.5015,
      "step": 63
    },
    {
      "epoch": 0.0883367839889579,
      "grad_norm": 1.7771934270858765,
      "learning_rate": 7.186526315789474e-05,
      "loss": 2.2055,
      "step": 64
    },
    {
      "epoch": 0.08971704623878538,
      "grad_norm": 1.0457968711853027,
      "learning_rate": 7.133684210526316e-05,
      "loss": 1.5984,
      "step": 65
    },
    {
      "epoch": 0.09109730848861283,
      "grad_norm": 1.2737748622894287,
      "learning_rate": 7.080842105263158e-05,
      "loss": 1.7775,
      "step": 66
    },
    {
      "epoch": 0.0924775707384403,
      "grad_norm": 1.1890259981155396,
      "learning_rate": 7.028e-05,
      "loss": 2.0228,
      "step": 67
    },
    {
      "epoch": 0.09385783298826778,
      "grad_norm": 1.2597479820251465,
      "learning_rate": 6.975157894736843e-05,
      "loss": 2.0629,
      "step": 68
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.0471433401107788,
      "learning_rate": 6.922315789473685e-05,
      "loss": 1.7882,
      "step": 69
    },
    {
      "epoch": 0.0966183574879227,
      "grad_norm": 1.0744673013687134,
      "learning_rate": 6.869473684210527e-05,
      "loss": 1.7844,
      "step": 70
    },
    {
      "epoch": 0.09799861973775018,
      "grad_norm": 1.393317699432373,
      "learning_rate": 6.816631578947368e-05,
      "loss": 2.1979,
      "step": 71
    },
    {
      "epoch": 0.09937888198757763,
      "grad_norm": 1.4898236989974976,
      "learning_rate": 6.76378947368421e-05,
      "loss": 2.5061,
      "step": 72
    },
    {
      "epoch": 0.1007591442374051,
      "grad_norm": 1.1046738624572754,
      "learning_rate": 6.710947368421052e-05,
      "loss": 1.8938,
      "step": 73
    },
    {
      "epoch": 0.10213940648723258,
      "grad_norm": 1.3718451261520386,
      "learning_rate": 6.658105263157894e-05,
      "loss": 2.5167,
      "step": 74
    },
    {
      "epoch": 0.10351966873706005,
      "grad_norm": 1.2800939083099365,
      "learning_rate": 6.605263157894737e-05,
      "loss": 1.8427,
      "step": 75
    },
    {
      "epoch": 0.1048999309868875,
      "grad_norm": 1.2824013233184814,
      "learning_rate": 6.55242105263158e-05,
      "loss": 1.6855,
      "step": 76
    },
    {
      "epoch": 0.10628019323671498,
      "grad_norm": 1.1829575300216675,
      "learning_rate": 6.499578947368422e-05,
      "loss": 2.1127,
      "step": 77
    },
    {
      "epoch": 0.10766045548654245,
      "grad_norm": 1.4018757343292236,
      "learning_rate": 6.446736842105264e-05,
      "loss": 2.6736,
      "step": 78
    },
    {
      "epoch": 0.1090407177363699,
      "grad_norm": 1.1487196683883667,
      "learning_rate": 6.393894736842105e-05,
      "loss": 2.1348,
      "step": 79
    },
    {
      "epoch": 0.11042097998619738,
      "grad_norm": 1.2489293813705444,
      "learning_rate": 6.341052631578947e-05,
      "loss": 2.4025,
      "step": 80
    },
    {
      "epoch": 0.11180124223602485,
      "grad_norm": 1.379892349243164,
      "learning_rate": 6.288210526315789e-05,
      "loss": 2.1926,
      "step": 81
    },
    {
      "epoch": 0.1131815044858523,
      "grad_norm": 1.3127739429473877,
      "learning_rate": 6.235368421052632e-05,
      "loss": 1.6522,
      "step": 82
    },
    {
      "epoch": 0.11456176673567978,
      "grad_norm": 1.0042823553085327,
      "learning_rate": 6.182526315789474e-05,
      "loss": 1.452,
      "step": 83
    },
    {
      "epoch": 0.11594202898550725,
      "grad_norm": 1.0960407257080078,
      "learning_rate": 6.129684210526316e-05,
      "loss": 1.8077,
      "step": 84
    },
    {
      "epoch": 0.11732229123533472,
      "grad_norm": 1.3931646347045898,
      "learning_rate": 6.076842105263158e-05,
      "loss": 1.9234,
      "step": 85
    },
    {
      "epoch": 0.11870255348516218,
      "grad_norm": 1.2463769912719727,
      "learning_rate": 6.024e-05,
      "loss": 2.3322,
      "step": 86
    },
    {
      "epoch": 0.12008281573498965,
      "grad_norm": 1.5501362085342407,
      "learning_rate": 5.971157894736842e-05,
      "loss": 2.214,
      "step": 87
    },
    {
      "epoch": 0.12146307798481712,
      "grad_norm": 1.4971249103546143,
      "learning_rate": 5.9183157894736835e-05,
      "loss": 2.1229,
      "step": 88
    },
    {
      "epoch": 0.12284334023464458,
      "grad_norm": 1.2540746927261353,
      "learning_rate": 5.8654736842105267e-05,
      "loss": 2.319,
      "step": 89
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 1.3296970129013062,
      "learning_rate": 5.8126315789473684e-05,
      "loss": 2.2295,
      "step": 90
    },
    {
      "epoch": 0.12560386473429952,
      "grad_norm": 1.635713815689087,
      "learning_rate": 5.759789473684211e-05,
      "loss": 2.0453,
      "step": 91
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 2.5068306922912598,
      "learning_rate": 5.706947368421053e-05,
      "loss": 3.5522,
      "step": 92
    },
    {
      "epoch": 0.12836438923395446,
      "grad_norm": 1.3130208253860474,
      "learning_rate": 5.6541052631578945e-05,
      "loss": 1.7299,
      "step": 93
    },
    {
      "epoch": 0.12974465148378192,
      "grad_norm": 1.49214768409729,
      "learning_rate": 5.601263157894736e-05,
      "loss": 1.9252,
      "step": 94
    },
    {
      "epoch": 0.13112491373360938,
      "grad_norm": 1.5757135152816772,
      "learning_rate": 5.5484210526315794e-05,
      "loss": 2.0456,
      "step": 95
    },
    {
      "epoch": 0.13250517598343686,
      "grad_norm": 1.3604228496551514,
      "learning_rate": 5.495578947368421e-05,
      "loss": 1.2423,
      "step": 96
    },
    {
      "epoch": 0.13388543823326432,
      "grad_norm": 1.8302099704742432,
      "learning_rate": 5.442736842105264e-05,
      "loss": 2.4817,
      "step": 97
    },
    {
      "epoch": 0.13526570048309178,
      "grad_norm": 1.6365114450454712,
      "learning_rate": 5.3898947368421055e-05,
      "loss": 2.0664,
      "step": 98
    },
    {
      "epoch": 0.13664596273291926,
      "grad_norm": 1.6933999061584473,
      "learning_rate": 5.337052631578947e-05,
      "loss": 1.6216,
      "step": 99
    },
    {
      "epoch": 0.13802622498274672,
      "grad_norm": 3.5092623233795166,
      "learning_rate": 5.284210526315789e-05,
      "loss": 2.9275,
      "step": 100
    },
    {
      "epoch": 0.13802622498274672,
      "eval_loss": 2.09364652633667,
      "eval_runtime": 7.1227,
      "eval_samples_per_second": 42.821,
      "eval_steps_per_second": 10.81,
      "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": 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": 1717219885056000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}