{
  "best_metric": 1.2959579229354858,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.17006802721088435,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017006802721088435,
      "grad_norm": 6.931743621826172,
      "learning_rate": 1e-05,
      "loss": 7.4319,
      "step": 1
    },
    {
      "epoch": 0.0017006802721088435,
      "eval_loss": 1.859765648841858,
      "eval_runtime": 12.9757,
      "eval_samples_per_second": 76.297,
      "eval_steps_per_second": 19.113,
      "step": 1
    },
    {
      "epoch": 0.003401360544217687,
      "grad_norm": 7.650826930999756,
      "learning_rate": 2e-05,
      "loss": 8.0915,
      "step": 2
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 5.860412120819092,
      "learning_rate": 3e-05,
      "loss": 8.0486,
      "step": 3
    },
    {
      "epoch": 0.006802721088435374,
      "grad_norm": 2.7964353561401367,
      "learning_rate": 4e-05,
      "loss": 7.5261,
      "step": 4
    },
    {
      "epoch": 0.008503401360544218,
      "grad_norm": 4.755170822143555,
      "learning_rate": 5e-05,
      "loss": 7.8163,
      "step": 5
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 6.899176120758057,
      "learning_rate": 6e-05,
      "loss": 8.1841,
      "step": 6
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 6.282437324523926,
      "learning_rate": 7e-05,
      "loss": 8.0738,
      "step": 7
    },
    {
      "epoch": 0.013605442176870748,
      "grad_norm": 4.9840874671936035,
      "learning_rate": 8e-05,
      "loss": 7.899,
      "step": 8
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 3.864417314529419,
      "learning_rate": 9e-05,
      "loss": 7.7532,
      "step": 9
    },
    {
      "epoch": 0.017006802721088437,
      "grad_norm": 3.3192386627197266,
      "learning_rate": 0.0001,
      "loss": 7.301,
      "step": 10
    },
    {
      "epoch": 0.01870748299319728,
      "grad_norm": 3.984121322631836,
      "learning_rate": 9.999316524962345e-05,
      "loss": 7.407,
      "step": 11
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 3.4357244968414307,
      "learning_rate": 9.997266286704631e-05,
      "loss": 6.9992,
      "step": 12
    },
    {
      "epoch": 0.022108843537414966,
      "grad_norm": 3.4906866550445557,
      "learning_rate": 9.993849845741524e-05,
      "loss": 7.0795,
      "step": 13
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 3.1637258529663086,
      "learning_rate": 9.989068136093873e-05,
      "loss": 7.1903,
      "step": 14
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": 2.611268997192383,
      "learning_rate": 9.98292246503335e-05,
      "loss": 7.1778,
      "step": 15
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": 2.6145622730255127,
      "learning_rate": 9.975414512725057e-05,
      "loss": 7.135,
      "step": 16
    },
    {
      "epoch": 0.02891156462585034,
      "grad_norm": 3.0810394287109375,
      "learning_rate": 9.966546331768191e-05,
      "loss": 6.89,
      "step": 17
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 2.5337579250335693,
      "learning_rate": 9.956320346634876e-05,
      "loss": 6.6764,
      "step": 18
    },
    {
      "epoch": 0.03231292517006803,
      "grad_norm": 2.274829149246216,
      "learning_rate": 9.944739353007344e-05,
      "loss": 6.2675,
      "step": 19
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 2.468628406524658,
      "learning_rate": 9.931806517013612e-05,
      "loss": 6.6116,
      "step": 20
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 2.902904987335205,
      "learning_rate": 9.917525374361912e-05,
      "loss": 6.5356,
      "step": 21
    },
    {
      "epoch": 0.03741496598639456,
      "grad_norm": 2.6827621459960938,
      "learning_rate": 9.901899829374047e-05,
      "loss": 6.4791,
      "step": 22
    },
    {
      "epoch": 0.0391156462585034,
      "grad_norm": 2.9359898567199707,
      "learning_rate": 9.884934153917997e-05,
      "loss": 6.2004,
      "step": 23
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 3.0745341777801514,
      "learning_rate": 9.86663298624003e-05,
      "loss": 6.0221,
      "step": 24
    },
    {
      "epoch": 0.04251700680272109,
      "grad_norm": 2.6942429542541504,
      "learning_rate": 9.847001329696653e-05,
      "loss": 5.8074,
      "step": 25
    },
    {
      "epoch": 0.04421768707482993,
      "grad_norm": 3.127678871154785,
      "learning_rate": 9.826044551386744e-05,
      "loss": 6.169,
      "step": 26
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 2.942544460296631,
      "learning_rate": 9.803768380684242e-05,
      "loss": 6.1049,
      "step": 27
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 2.9104082584381104,
      "learning_rate": 9.780178907671789e-05,
      "loss": 5.9182,
      "step": 28
    },
    {
      "epoch": 0.04931972789115646,
      "grad_norm": 2.9256160259246826,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.4293,
      "step": 29
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 3.1799166202545166,
      "learning_rate": 9.729086208503174e-05,
      "loss": 5.4475,
      "step": 30
    },
    {
      "epoch": 0.05272108843537415,
      "grad_norm": 2.750669002532959,
      "learning_rate": 9.701596950580806e-05,
      "loss": 5.2014,
      "step": 31
    },
    {
      "epoch": 0.05442176870748299,
      "grad_norm": 3.036323308944702,
      "learning_rate": 9.672822322997305e-05,
      "loss": 5.4431,
      "step": 32
    },
    {
      "epoch": 0.05612244897959184,
      "grad_norm": 3.4452264308929443,
      "learning_rate": 9.642770192448536e-05,
      "loss": 5.518,
      "step": 33
    },
    {
      "epoch": 0.05782312925170068,
      "grad_norm": 3.5561699867248535,
      "learning_rate": 9.611448774886924e-05,
      "loss": 5.5546,
      "step": 34
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 3.008066415786743,
      "learning_rate": 9.578866633275288e-05,
      "loss": 5.0755,
      "step": 35
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 3.3522846698760986,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.7796,
      "step": 36
    },
    {
      "epoch": 0.06292517006802721,
      "grad_norm": 3.256880283355713,
      "learning_rate": 9.509956150664796e-05,
      "loss": 5.0336,
      "step": 37
    },
    {
      "epoch": 0.06462585034013606,
      "grad_norm": 3.6797640323638916,
      "learning_rate": 9.473646649103818e-05,
      "loss": 5.0734,
      "step": 38
    },
    {
      "epoch": 0.0663265306122449,
      "grad_norm": 3.1642258167266846,
      "learning_rate": 9.43611409721806e-05,
      "loss": 4.7698,
      "step": 39
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 3.1769208908081055,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.071,
      "step": 40
    },
    {
      "epoch": 0.06972789115646258,
      "grad_norm": 3.909738779067993,
      "learning_rate": 9.357421218136386e-05,
      "loss": 5.2977,
      "step": 41
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 3.3455698490142822,
      "learning_rate": 9.316282404787871e-05,
      "loss": 4.224,
      "step": 42
    },
    {
      "epoch": 0.07312925170068027,
      "grad_norm": 3.1520206928253174,
      "learning_rate": 9.273963562927695e-05,
      "loss": 4.433,
      "step": 43
    },
    {
      "epoch": 0.07482993197278912,
      "grad_norm": 3.0218124389648438,
      "learning_rate": 9.230476262104677e-05,
      "loss": 4.5114,
      "step": 44
    },
    {
      "epoch": 0.07653061224489796,
      "grad_norm": 3.826742172241211,
      "learning_rate": 9.185832391312644e-05,
      "loss": 4.9469,
      "step": 45
    },
    {
      "epoch": 0.0782312925170068,
      "grad_norm": 3.3043854236602783,
      "learning_rate": 9.140044155740101e-05,
      "loss": 4.201,
      "step": 46
    },
    {
      "epoch": 0.07993197278911565,
      "grad_norm": 3.2852389812469482,
      "learning_rate": 9.093124073433463e-05,
      "loss": 4.444,
      "step": 47
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 3.6611533164978027,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.1278,
      "step": 48
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 3.6009016036987305,
      "learning_rate": 8.995939984474624e-05,
      "loss": 4.9994,
      "step": 49
    },
    {
      "epoch": 0.08503401360544217,
      "grad_norm": 3.9169812202453613,
      "learning_rate": 8.945702546981969e-05,
      "loss": 5.2766,
      "step": 50
    },
    {
      "epoch": 0.08503401360544217,
      "eval_loss": 1.5149801969528198,
      "eval_runtime": 12.9513,
      "eval_samples_per_second": 76.44,
      "eval_steps_per_second": 19.149,
      "step": 50
    },
    {
      "epoch": 0.08673469387755102,
      "grad_norm": 31.29947280883789,
      "learning_rate": 8.894386393810563e-05,
      "loss": 8.953,
      "step": 51
    },
    {
      "epoch": 0.08843537414965986,
      "grad_norm": 19.800573348999023,
      "learning_rate": 8.842005554284296e-05,
      "loss": 8.6754,
      "step": 52
    },
    {
      "epoch": 0.09013605442176871,
      "grad_norm": 10.068018913269043,
      "learning_rate": 8.788574348801675e-05,
      "loss": 8.3737,
      "step": 53
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": 6.965304851531982,
      "learning_rate": 8.73410738492077e-05,
      "loss": 8.0596,
      "step": 54
    },
    {
      "epoch": 0.0935374149659864,
      "grad_norm": 5.657329559326172,
      "learning_rate": 8.678619553365659e-05,
      "loss": 8.0187,
      "step": 55
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 5.521895408630371,
      "learning_rate": 8.622126023955446e-05,
      "loss": 8.3002,
      "step": 56
    },
    {
      "epoch": 0.09693877551020408,
      "grad_norm": 5.181872367858887,
      "learning_rate": 8.564642241456986e-05,
      "loss": 7.8668,
      "step": 57
    },
    {
      "epoch": 0.09863945578231292,
      "grad_norm": 3.7792327404022217,
      "learning_rate": 8.506183921362443e-05,
      "loss": 7.7171,
      "step": 58
    },
    {
      "epoch": 0.10034013605442177,
      "grad_norm": 3.6012377738952637,
      "learning_rate": 8.44676704559283e-05,
      "loss": 7.7714,
      "step": 59
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 3.5614826679229736,
      "learning_rate": 8.386407858128706e-05,
      "loss": 7.6338,
      "step": 60
    },
    {
      "epoch": 0.10374149659863946,
      "grad_norm": 3.0117275714874268,
      "learning_rate": 8.32512286056924e-05,
      "loss": 6.851,
      "step": 61
    },
    {
      "epoch": 0.1054421768707483,
      "grad_norm": 2.835902452468872,
      "learning_rate": 8.262928807620843e-05,
      "loss": 6.632,
      "step": 62
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 2.604902982711792,
      "learning_rate": 8.199842702516583e-05,
      "loss": 7.361,
      "step": 63
    },
    {
      "epoch": 0.10884353741496598,
      "grad_norm": 2.41507625579834,
      "learning_rate": 8.135881792367686e-05,
      "loss": 6.6733,
      "step": 64
    },
    {
      "epoch": 0.11054421768707483,
      "grad_norm": 2.388829231262207,
      "learning_rate": 8.07106356344834e-05,
      "loss": 6.5074,
      "step": 65
    },
    {
      "epoch": 0.11224489795918367,
      "grad_norm": 2.281676769256592,
      "learning_rate": 8.005405736415126e-05,
      "loss": 6.9262,
      "step": 66
    },
    {
      "epoch": 0.11394557823129252,
      "grad_norm": 2.2224345207214355,
      "learning_rate": 7.938926261462366e-05,
      "loss": 6.1642,
      "step": 67
    },
    {
      "epoch": 0.11564625850340136,
      "grad_norm": 2.092848062515259,
      "learning_rate": 7.871643313414718e-05,
      "loss": 6.546,
      "step": 68
    },
    {
      "epoch": 0.11734693877551021,
      "grad_norm": 2.2295429706573486,
      "learning_rate": 7.803575286758364e-05,
      "loss": 6.0603,
      "step": 69
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 2.278090476989746,
      "learning_rate": 7.734740790612136e-05,
      "loss": 5.9574,
      "step": 70
    },
    {
      "epoch": 0.12074829931972789,
      "grad_norm": 2.1992435455322266,
      "learning_rate": 7.66515864363997e-05,
      "loss": 5.388,
      "step": 71
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 2.3004751205444336,
      "learning_rate": 7.594847868906076e-05,
      "loss": 5.2624,
      "step": 72
    },
    {
      "epoch": 0.12414965986394558,
      "grad_norm": 2.23673415184021,
      "learning_rate": 7.52382768867422e-05,
      "loss": 5.3418,
      "step": 73
    },
    {
      "epoch": 0.12585034013605442,
      "grad_norm": 2.3521363735198975,
      "learning_rate": 7.452117519152542e-05,
      "loss": 4.8446,
      "step": 74
    },
    {
      "epoch": 0.12755102040816327,
      "grad_norm": 2.3602993488311768,
      "learning_rate": 7.379736965185368e-05,
      "loss": 4.7427,
      "step": 75
    },
    {
      "epoch": 0.1292517006802721,
      "grad_norm": 2.3233556747436523,
      "learning_rate": 7.30670581489344e-05,
      "loss": 4.6049,
      "step": 76
    },
    {
      "epoch": 0.13095238095238096,
      "grad_norm": 2.472208261489868,
      "learning_rate": 7.233044034264034e-05,
      "loss": 4.9653,
      "step": 77
    },
    {
      "epoch": 0.1326530612244898,
      "grad_norm": 2.291001796722412,
      "learning_rate": 7.158771761692464e-05,
      "loss": 4.0857,
      "step": 78
    },
    {
      "epoch": 0.13435374149659865,
      "grad_norm": 2.5723509788513184,
      "learning_rate": 7.083909302476453e-05,
      "loss": 4.7477,
      "step": 79
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 2.36112117767334,
      "learning_rate": 7.008477123264848e-05,
      "loss": 4.4179,
      "step": 80
    },
    {
      "epoch": 0.1377551020408163,
      "grad_norm": 2.3954625129699707,
      "learning_rate": 6.932495846462261e-05,
      "loss": 4.5658,
      "step": 81
    },
    {
      "epoch": 0.13945578231292516,
      "grad_norm": 2.5020458698272705,
      "learning_rate": 6.855986244591104e-05,
      "loss": 3.931,
      "step": 82
    },
    {
      "epoch": 0.141156462585034,
      "grad_norm": 2.430371046066284,
      "learning_rate": 6.778969234612584e-05,
      "loss": 3.8719,
      "step": 83
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.54176664352417,
      "learning_rate": 6.701465872208216e-05,
      "loss": 3.854,
      "step": 84
    },
    {
      "epoch": 0.1445578231292517,
      "grad_norm": 2.2303836345672607,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.628,
      "step": 85
    },
    {
      "epoch": 0.14625850340136054,
      "grad_norm": 2.6136372089385986,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.1457,
      "step": 86
    },
    {
      "epoch": 0.14795918367346939,
      "grad_norm": 3.0256564617156982,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.5252,
      "step": 87
    },
    {
      "epoch": 0.14965986394557823,
      "grad_norm": 2.7025537490844727,
      "learning_rate": 6.387014543809223e-05,
      "loss": 4.2225,
      "step": 88
    },
    {
      "epoch": 0.15136054421768708,
      "grad_norm": 2.871462106704712,
      "learning_rate": 6.307399704769099e-05,
      "loss": 4.1871,
      "step": 89
    },
    {
      "epoch": 0.15306122448979592,
      "grad_norm": 2.799994468688965,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.3875,
      "step": 90
    },
    {
      "epoch": 0.15476190476190477,
      "grad_norm": 2.823847770690918,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.487,
      "step": 91
    },
    {
      "epoch": 0.1564625850340136,
      "grad_norm": 2.71280837059021,
      "learning_rate": 6.066498153718735e-05,
      "loss": 3.9466,
      "step": 92
    },
    {
      "epoch": 0.15816326530612246,
      "grad_norm": 2.875120162963867,
      "learning_rate": 5.985585137257401e-05,
      "loss": 3.8248,
      "step": 93
    },
    {
      "epoch": 0.1598639455782313,
      "grad_norm": 2.8695144653320312,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.8059,
      "step": 94
    },
    {
      "epoch": 0.16156462585034015,
      "grad_norm": 2.7744107246398926,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.5612,
      "step": 95
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 2.414188861846924,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.3415,
      "step": 96
    },
    {
      "epoch": 0.1649659863945578,
      "grad_norm": 2.907362937927246,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 4.2475,
      "step": 97
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 2.715144634246826,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.7618,
      "step": 98
    },
    {
      "epoch": 0.1683673469387755,
      "grad_norm": 2.6227142810821533,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.9515,
      "step": 99
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 3.2439918518066406,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 5.1032,
      "step": 100
    },
    {
      "epoch": 0.17006802721088435,
      "eval_loss": 1.2959579229354858,
      "eval_runtime": 12.9706,
      "eval_samples_per_second": 76.326,
      "eval_steps_per_second": 19.12,
      "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": 7764456373223424.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}