{
  "best_metric": 0.056889016181230545,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.03786444528587656,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003786444528587656,
      "grad_norm": 30.30210304260254,
      "learning_rate": 1e-05,
      "loss": 3.454,
      "step": 1
    },
    {
      "epoch": 0.0003786444528587656,
      "eval_loss": 1.2271908521652222,
      "eval_runtime": 344.36,
      "eval_samples_per_second": 12.917,
      "eval_steps_per_second": 3.229,
      "step": 1
    },
    {
      "epoch": 0.0007572889057175312,
      "grad_norm": 28.70562171936035,
      "learning_rate": 2e-05,
      "loss": 3.055,
      "step": 2
    },
    {
      "epoch": 0.001135933358576297,
      "grad_norm": 27.683151245117188,
      "learning_rate": 3e-05,
      "loss": 3.0755,
      "step": 3
    },
    {
      "epoch": 0.0015145778114350624,
      "grad_norm": 21.200279235839844,
      "learning_rate": 4e-05,
      "loss": 2.3776,
      "step": 4
    },
    {
      "epoch": 0.001893222264293828,
      "grad_norm": 20.016876220703125,
      "learning_rate": 5e-05,
      "loss": 2.1317,
      "step": 5
    },
    {
      "epoch": 0.002271866717152594,
      "grad_norm": 13.269105911254883,
      "learning_rate": 6e-05,
      "loss": 1.7241,
      "step": 6
    },
    {
      "epoch": 0.0026505111700113595,
      "grad_norm": 8.53914737701416,
      "learning_rate": 7e-05,
      "loss": 1.2721,
      "step": 7
    },
    {
      "epoch": 0.003029155622870125,
      "grad_norm": 7.634444713592529,
      "learning_rate": 8e-05,
      "loss": 1.0289,
      "step": 8
    },
    {
      "epoch": 0.0034078000757288905,
      "grad_norm": 5.753473281860352,
      "learning_rate": 9e-05,
      "loss": 0.9522,
      "step": 9
    },
    {
      "epoch": 0.003786444528587656,
      "grad_norm": 5.670541286468506,
      "learning_rate": 0.0001,
      "loss": 0.7795,
      "step": 10
    },
    {
      "epoch": 0.0041650889814464215,
      "grad_norm": 5.604635238647461,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7602,
      "step": 11
    },
    {
      "epoch": 0.004543733434305188,
      "grad_norm": 4.307402610778809,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5068,
      "step": 12
    },
    {
      "epoch": 0.004922377887163953,
      "grad_norm": 3.943270444869995,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4283,
      "step": 13
    },
    {
      "epoch": 0.005301022340022719,
      "grad_norm": 4.39333963394165,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4252,
      "step": 14
    },
    {
      "epoch": 0.005679666792881484,
      "grad_norm": 4.685744285583496,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4325,
      "step": 15
    },
    {
      "epoch": 0.00605831124574025,
      "grad_norm": 4.721577167510986,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4541,
      "step": 16
    },
    {
      "epoch": 0.006436955698599016,
      "grad_norm": 3.852276086807251,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4821,
      "step": 17
    },
    {
      "epoch": 0.006815600151457781,
      "grad_norm": 3.1198885440826416,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.3999,
      "step": 18
    },
    {
      "epoch": 0.007194244604316547,
      "grad_norm": 3.4822542667388916,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4251,
      "step": 19
    },
    {
      "epoch": 0.007572889057175312,
      "grad_norm": 3.086282968521118,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3033,
      "step": 20
    },
    {
      "epoch": 0.007951533510034078,
      "grad_norm": 3.2310450077056885,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3489,
      "step": 21
    },
    {
      "epoch": 0.008330177962892843,
      "grad_norm": 3.3141283988952637,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3134,
      "step": 22
    },
    {
      "epoch": 0.00870882241575161,
      "grad_norm": 3.379727363586426,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.2986,
      "step": 23
    },
    {
      "epoch": 0.009087466868610375,
      "grad_norm": 3.217503309249878,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.3165,
      "step": 24
    },
    {
      "epoch": 0.00946611132146914,
      "grad_norm": 9.431246757507324,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4134,
      "step": 25
    },
    {
      "epoch": 0.009844755774327906,
      "grad_norm": 4.396425247192383,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.4735,
      "step": 26
    },
    {
      "epoch": 0.010223400227186671,
      "grad_norm": 3.3436813354492188,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2919,
      "step": 27
    },
    {
      "epoch": 0.010602044680045438,
      "grad_norm": 2.918400764465332,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.3274,
      "step": 28
    },
    {
      "epoch": 0.010980689132904203,
      "grad_norm": 3.9403295516967773,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3571,
      "step": 29
    },
    {
      "epoch": 0.011359333585762969,
      "grad_norm": 3.652174949645996,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3791,
      "step": 30
    },
    {
      "epoch": 0.011737978038621734,
      "grad_norm": 3.4695796966552734,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.3037,
      "step": 31
    },
    {
      "epoch": 0.0121166224914805,
      "grad_norm": 4.472967147827148,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2725,
      "step": 32
    },
    {
      "epoch": 0.012495266944339266,
      "grad_norm": 3.7442424297332764,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3347,
      "step": 33
    },
    {
      "epoch": 0.012873911397198031,
      "grad_norm": 4.048393726348877,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2825,
      "step": 34
    },
    {
      "epoch": 0.013252555850056797,
      "grad_norm": 3.2372047901153564,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3224,
      "step": 35
    },
    {
      "epoch": 0.013631200302915562,
      "grad_norm": 3.886826276779175,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2502,
      "step": 36
    },
    {
      "epoch": 0.014009844755774327,
      "grad_norm": 5.310039520263672,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4031,
      "step": 37
    },
    {
      "epoch": 0.014388489208633094,
      "grad_norm": 3.9522817134857178,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.2867,
      "step": 38
    },
    {
      "epoch": 0.01476713366149186,
      "grad_norm": 4.22894287109375,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.273,
      "step": 39
    },
    {
      "epoch": 0.015145778114350625,
      "grad_norm": 3.847644329071045,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.3251,
      "step": 40
    },
    {
      "epoch": 0.01552442256720939,
      "grad_norm": 4.220029830932617,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.387,
      "step": 41
    },
    {
      "epoch": 0.015903067020068155,
      "grad_norm": 6.5446367263793945,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.501,
      "step": 42
    },
    {
      "epoch": 0.01628171147292692,
      "grad_norm": 4.978550910949707,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.2667,
      "step": 43
    },
    {
      "epoch": 0.016660355925785686,
      "grad_norm": 4.060535430908203,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2507,
      "step": 44
    },
    {
      "epoch": 0.01703900037864445,
      "grad_norm": 6.107398986816406,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.4149,
      "step": 45
    },
    {
      "epoch": 0.01741764483150322,
      "grad_norm": 5.923000335693359,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3435,
      "step": 46
    },
    {
      "epoch": 0.017796289284361985,
      "grad_norm": 5.507021427154541,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.2431,
      "step": 47
    },
    {
      "epoch": 0.01817493373722075,
      "grad_norm": 6.118594646453857,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4265,
      "step": 48
    },
    {
      "epoch": 0.018553578190079516,
      "grad_norm": 8.140854835510254,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3929,
      "step": 49
    },
    {
      "epoch": 0.01893222264293828,
      "grad_norm": 20.28197479248047,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6931,
      "step": 50
    },
    {
      "epoch": 0.01893222264293828,
      "eval_loss": 0.10484325140714645,
      "eval_runtime": 346.7247,
      "eval_samples_per_second": 12.829,
      "eval_steps_per_second": 3.207,
      "step": 50
    },
    {
      "epoch": 0.019310867095797046,
      "grad_norm": 15.64964771270752,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3934,
      "step": 51
    },
    {
      "epoch": 0.01968951154865581,
      "grad_norm": 3.1674065589904785,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3688,
      "step": 52
    },
    {
      "epoch": 0.020068156001514577,
      "grad_norm": 4.302602767944336,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.3721,
      "step": 53
    },
    {
      "epoch": 0.020446800454373342,
      "grad_norm": 2.2917792797088623,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3455,
      "step": 54
    },
    {
      "epoch": 0.020825444907232107,
      "grad_norm": 2.2252116203308105,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.2578,
      "step": 55
    },
    {
      "epoch": 0.021204089360090876,
      "grad_norm": 2.050823211669922,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.3477,
      "step": 56
    },
    {
      "epoch": 0.02158273381294964,
      "grad_norm": 1.7291784286499023,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.1985,
      "step": 57
    },
    {
      "epoch": 0.021961378265808407,
      "grad_norm": 1.78282630443573,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.2512,
      "step": 58
    },
    {
      "epoch": 0.022340022718667172,
      "grad_norm": 1.5709683895111084,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1674,
      "step": 59
    },
    {
      "epoch": 0.022718667171525937,
      "grad_norm": 2.580583095550537,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.2681,
      "step": 60
    },
    {
      "epoch": 0.023097311624384703,
      "grad_norm": 1.7469924688339233,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.1837,
      "step": 61
    },
    {
      "epoch": 0.023475956077243468,
      "grad_norm": 1.8775490522384644,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.16,
      "step": 62
    },
    {
      "epoch": 0.023854600530102233,
      "grad_norm": 2.6333093643188477,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.2646,
      "step": 63
    },
    {
      "epoch": 0.024233244982961,
      "grad_norm": 2.23219895362854,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1811,
      "step": 64
    },
    {
      "epoch": 0.024611889435819764,
      "grad_norm": 2.8453469276428223,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2264,
      "step": 65
    },
    {
      "epoch": 0.024990533888678532,
      "grad_norm": 1.8574113845825195,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2062,
      "step": 66
    },
    {
      "epoch": 0.025369178341537298,
      "grad_norm": 2.065722942352295,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2177,
      "step": 67
    },
    {
      "epoch": 0.025747822794396063,
      "grad_norm": 1.9401975870132446,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.154,
      "step": 68
    },
    {
      "epoch": 0.026126467247254828,
      "grad_norm": 2.319091320037842,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.172,
      "step": 69
    },
    {
      "epoch": 0.026505111700113593,
      "grad_norm": 1.731372356414795,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.1473,
      "step": 70
    },
    {
      "epoch": 0.02688375615297236,
      "grad_norm": 1.685765266418457,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.127,
      "step": 71
    },
    {
      "epoch": 0.027262400605831124,
      "grad_norm": 2.3166072368621826,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1974,
      "step": 72
    },
    {
      "epoch": 0.02764104505868989,
      "grad_norm": 3.6142325401306152,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.2996,
      "step": 73
    },
    {
      "epoch": 0.028019689511548655,
      "grad_norm": 2.9581050872802734,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2075,
      "step": 74
    },
    {
      "epoch": 0.02839833396440742,
      "grad_norm": 2.805510997772217,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.218,
      "step": 75
    },
    {
      "epoch": 0.02877697841726619,
      "grad_norm": 2.2220678329467773,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.2563,
      "step": 76
    },
    {
      "epoch": 0.029155622870124954,
      "grad_norm": 1.5375562906265259,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.1137,
      "step": 77
    },
    {
      "epoch": 0.02953426732298372,
      "grad_norm": 2.0002684593200684,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.2283,
      "step": 78
    },
    {
      "epoch": 0.029912911775842484,
      "grad_norm": 1.6701806783676147,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.1793,
      "step": 79
    },
    {
      "epoch": 0.03029155622870125,
      "grad_norm": 1.9673099517822266,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1513,
      "step": 80
    },
    {
      "epoch": 0.030670200681560015,
      "grad_norm": 2.2128007411956787,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.1565,
      "step": 81
    },
    {
      "epoch": 0.03104884513441878,
      "grad_norm": 2.8963911533355713,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.1956,
      "step": 82
    },
    {
      "epoch": 0.03142748958727755,
      "grad_norm": 1.9358999729156494,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.1098,
      "step": 83
    },
    {
      "epoch": 0.03180613404013631,
      "grad_norm": 2.467489719390869,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.1466,
      "step": 84
    },
    {
      "epoch": 0.03218477849299508,
      "grad_norm": 2.4192018508911133,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.167,
      "step": 85
    },
    {
      "epoch": 0.03256342294585384,
      "grad_norm": 3.016098976135254,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1953,
      "step": 86
    },
    {
      "epoch": 0.03294206739871261,
      "grad_norm": 5.171764850616455,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2195,
      "step": 87
    },
    {
      "epoch": 0.03332071185157137,
      "grad_norm": 3.947794198989868,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.2156,
      "step": 88
    },
    {
      "epoch": 0.03369935630443014,
      "grad_norm": 2.628844738006592,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.1087,
      "step": 89
    },
    {
      "epoch": 0.0340780007572889,
      "grad_norm": 2.4610188007354736,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1795,
      "step": 90
    },
    {
      "epoch": 0.03445664521014767,
      "grad_norm": 3.3710789680480957,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2278,
      "step": 91
    },
    {
      "epoch": 0.03483528966300644,
      "grad_norm": 4.118891716003418,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.202,
      "step": 92
    },
    {
      "epoch": 0.0352139341158652,
      "grad_norm": 2.6067090034484863,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.1338,
      "step": 93
    },
    {
      "epoch": 0.03559257856872397,
      "grad_norm": 4.202768802642822,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2661,
      "step": 94
    },
    {
      "epoch": 0.03597122302158273,
      "grad_norm": 5.873966693878174,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.1864,
      "step": 95
    },
    {
      "epoch": 0.0363498674744415,
      "grad_norm": 2.386099338531494,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1341,
      "step": 96
    },
    {
      "epoch": 0.03672851192730026,
      "grad_norm": 10.880393028259277,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.2691,
      "step": 97
    },
    {
      "epoch": 0.03710715638015903,
      "grad_norm": 7.632635116577148,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.284,
      "step": 98
    },
    {
      "epoch": 0.03748580083301779,
      "grad_norm": 9.015336036682129,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.4067,
      "step": 99
    },
    {
      "epoch": 0.03786444528587656,
      "grad_norm": 16.10353660583496,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2029,
      "step": 100
    },
    {
      "epoch": 0.03786444528587656,
      "eval_loss": 0.056889016181230545,
      "eval_runtime": 347.0888,
      "eval_samples_per_second": 12.815,
      "eval_steps_per_second": 3.204,
      "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": 1.488237929347154e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}