{
  "best_metric": 0.005914478562772274,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.49443757725587145,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004944375772558714,
      "grad_norm": 0.3109091818332672,
      "learning_rate": 1e-05,
      "loss": 0.0624,
      "step": 1
    },
    {
      "epoch": 0.004944375772558714,
      "eval_loss": 0.6954474449157715,
      "eval_runtime": 49.7001,
      "eval_samples_per_second": 6.861,
      "eval_steps_per_second": 1.73,
      "step": 1
    },
    {
      "epoch": 0.009888751545117428,
      "grad_norm": 0.5469837188720703,
      "learning_rate": 2e-05,
      "loss": 0.1095,
      "step": 2
    },
    {
      "epoch": 0.014833127317676144,
      "grad_norm": 0.576060950756073,
      "learning_rate": 3e-05,
      "loss": 0.1422,
      "step": 3
    },
    {
      "epoch": 0.019777503090234856,
      "grad_norm": 0.5913758873939514,
      "learning_rate": 4e-05,
      "loss": 0.1553,
      "step": 4
    },
    {
      "epoch": 0.024721878862793572,
      "grad_norm": 0.4919019639492035,
      "learning_rate": 5e-05,
      "loss": 0.1514,
      "step": 5
    },
    {
      "epoch": 0.029666254635352288,
      "grad_norm": 0.5478493571281433,
      "learning_rate": 6e-05,
      "loss": 0.1431,
      "step": 6
    },
    {
      "epoch": 0.034610630407911,
      "grad_norm": 0.6365486979484558,
      "learning_rate": 7e-05,
      "loss": 0.1301,
      "step": 7
    },
    {
      "epoch": 0.03955500618046971,
      "grad_norm": 0.8634000420570374,
      "learning_rate": 8e-05,
      "loss": 0.0933,
      "step": 8
    },
    {
      "epoch": 0.04449938195302843,
      "grad_norm": 0.758399486541748,
      "learning_rate": 9e-05,
      "loss": 0.0588,
      "step": 9
    },
    {
      "epoch": 0.049443757725587144,
      "grad_norm": 0.5559531450271606,
      "learning_rate": 0.0001,
      "loss": 0.0311,
      "step": 10
    },
    {
      "epoch": 0.054388133498145856,
      "grad_norm": 0.30050650238990784,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0178,
      "step": 11
    },
    {
      "epoch": 0.059332509270704575,
      "grad_norm": 0.6887413263320923,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0159,
      "step": 12
    },
    {
      "epoch": 0.06427688504326329,
      "grad_norm": 0.6014060378074646,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0072,
      "step": 13
    },
    {
      "epoch": 0.069221260815822,
      "grad_norm": 0.28265437483787537,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0062,
      "step": 14
    },
    {
      "epoch": 0.07416563658838071,
      "grad_norm": 0.20781368017196655,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0018,
      "step": 15
    },
    {
      "epoch": 0.07911001236093942,
      "grad_norm": 0.15154816210269928,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.001,
      "step": 16
    },
    {
      "epoch": 0.08405438813349815,
      "grad_norm": 0.7287437319755554,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0089,
      "step": 17
    },
    {
      "epoch": 0.08899876390605686,
      "grad_norm": 0.2308892160654068,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0009,
      "step": 18
    },
    {
      "epoch": 0.09394313967861558,
      "grad_norm": 0.668213427066803,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0026,
      "step": 19
    },
    {
      "epoch": 0.09888751545117429,
      "grad_norm": 0.1726139783859253,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0013,
      "step": 20
    },
    {
      "epoch": 0.103831891223733,
      "grad_norm": 1.0967801809310913,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0113,
      "step": 21
    },
    {
      "epoch": 0.10877626699629171,
      "grad_norm": 0.4850783348083496,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0042,
      "step": 22
    },
    {
      "epoch": 0.11372064276885044,
      "grad_norm": 0.31693360209465027,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0025,
      "step": 23
    },
    {
      "epoch": 0.11866501854140915,
      "grad_norm": 0.46091321110725403,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0075,
      "step": 24
    },
    {
      "epoch": 0.12360939431396786,
      "grad_norm": 1.6674555540084839,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0103,
      "step": 25
    },
    {
      "epoch": 0.12855377008652658,
      "grad_norm": 0.6519526839256287,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0103,
      "step": 26
    },
    {
      "epoch": 0.1334981458590853,
      "grad_norm": 0.2550012767314911,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0041,
      "step": 27
    },
    {
      "epoch": 0.138442521631644,
      "grad_norm": 0.2458522766828537,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0012,
      "step": 28
    },
    {
      "epoch": 0.1433868974042027,
      "grad_norm": 0.03765624761581421,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0007,
      "step": 29
    },
    {
      "epoch": 0.14833127317676142,
      "grad_norm": 0.01935061626136303,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0003,
      "step": 30
    },
    {
      "epoch": 0.15327564894932014,
      "grad_norm": 0.05717118829488754,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0014,
      "step": 31
    },
    {
      "epoch": 0.15822002472187885,
      "grad_norm": 1.0006184577941895,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0045,
      "step": 32
    },
    {
      "epoch": 0.1631644004944376,
      "grad_norm": 0.5502849817276001,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0075,
      "step": 33
    },
    {
      "epoch": 0.1681087762669963,
      "grad_norm": 0.4707809090614319,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.014,
      "step": 34
    },
    {
      "epoch": 0.173053152039555,
      "grad_norm": 1.3747237920761108,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.009,
      "step": 35
    },
    {
      "epoch": 0.17799752781211373,
      "grad_norm": 4.012235641479492,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0407,
      "step": 36
    },
    {
      "epoch": 0.18294190358467244,
      "grad_norm": 0.22191601991653442,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0039,
      "step": 37
    },
    {
      "epoch": 0.18788627935723115,
      "grad_norm": 0.2527073919773102,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0063,
      "step": 38
    },
    {
      "epoch": 0.19283065512978986,
      "grad_norm": 0.24759742617607117,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0026,
      "step": 39
    },
    {
      "epoch": 0.19777503090234858,
      "grad_norm": 0.7433210611343384,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0055,
      "step": 40
    },
    {
      "epoch": 0.2027194066749073,
      "grad_norm": 0.3171069324016571,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0036,
      "step": 41
    },
    {
      "epoch": 0.207663782447466,
      "grad_norm": 0.009482938796281815,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0002,
      "step": 42
    },
    {
      "epoch": 0.2126081582200247,
      "grad_norm": 0.1378282606601715,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0011,
      "step": 43
    },
    {
      "epoch": 0.21755253399258342,
      "grad_norm": 0.13369594514369965,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0006,
      "step": 44
    },
    {
      "epoch": 0.22249690976514216,
      "grad_norm": 0.008207427337765694,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0002,
      "step": 45
    },
    {
      "epoch": 0.22744128553770088,
      "grad_norm": 0.03537704050540924,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0003,
      "step": 46
    },
    {
      "epoch": 0.2323856613102596,
      "grad_norm": 1.005922555923462,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0171,
      "step": 47
    },
    {
      "epoch": 0.2373300370828183,
      "grad_norm": 6.564137935638428,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0655,
      "step": 48
    },
    {
      "epoch": 0.242274412855377,
      "grad_norm": 0.3192770183086395,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0008,
      "step": 49
    },
    {
      "epoch": 0.24721878862793573,
      "grad_norm": 4.671757221221924,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0257,
      "step": 50
    },
    {
      "epoch": 0.24721878862793573,
      "eval_loss": 0.005914478562772274,
      "eval_runtime": 50.4452,
      "eval_samples_per_second": 6.76,
      "eval_steps_per_second": 1.705,
      "step": 50
    },
    {
      "epoch": 0.2521631644004944,
      "grad_norm": 0.14960375428199768,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0053,
      "step": 51
    },
    {
      "epoch": 0.25710754017305315,
      "grad_norm": 0.13269616663455963,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0026,
      "step": 52
    },
    {
      "epoch": 0.2620519159456119,
      "grad_norm": 0.06501085311174393,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.0013,
      "step": 53
    },
    {
      "epoch": 0.2669962917181706,
      "grad_norm": 0.05674945190548897,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0009,
      "step": 54
    },
    {
      "epoch": 0.2719406674907293,
      "grad_norm": 0.022370589897036552,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0005,
      "step": 55
    },
    {
      "epoch": 0.276885043263288,
      "grad_norm": 0.0845404639840126,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0019,
      "step": 56
    },
    {
      "epoch": 0.28182941903584674,
      "grad_norm": 0.0986766517162323,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.003,
      "step": 57
    },
    {
      "epoch": 0.2867737948084054,
      "grad_norm": 0.19640104472637177,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0053,
      "step": 58
    },
    {
      "epoch": 0.29171817058096416,
      "grad_norm": 0.130096897482872,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0035,
      "step": 59
    },
    {
      "epoch": 0.29666254635352285,
      "grad_norm": 0.16641069948673248,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0039,
      "step": 60
    },
    {
      "epoch": 0.3016069221260816,
      "grad_norm": 0.11631468683481216,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0023,
      "step": 61
    },
    {
      "epoch": 0.3065512978986403,
      "grad_norm": 0.2868841588497162,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0012,
      "step": 62
    },
    {
      "epoch": 0.311495673671199,
      "grad_norm": 0.015549149364233017,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0004,
      "step": 63
    },
    {
      "epoch": 0.3164400494437577,
      "grad_norm": 0.2190394401550293,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0012,
      "step": 64
    },
    {
      "epoch": 0.32138442521631644,
      "grad_norm": 0.05332758650183678,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0012,
      "step": 65
    },
    {
      "epoch": 0.3263288009888752,
      "grad_norm": 0.008343772031366825,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0002,
      "step": 66
    },
    {
      "epoch": 0.33127317676143386,
      "grad_norm": 0.09175986051559448,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0018,
      "step": 67
    },
    {
      "epoch": 0.3362175525339926,
      "grad_norm": 0.2049993872642517,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0021,
      "step": 68
    },
    {
      "epoch": 0.3411619283065513,
      "grad_norm": 0.034642044454813004,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0007,
      "step": 69
    },
    {
      "epoch": 0.34610630407911,
      "grad_norm": 0.009048677049577236,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0002,
      "step": 70
    },
    {
      "epoch": 0.3510506798516687,
      "grad_norm": 0.038504548370838165,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0006,
      "step": 71
    },
    {
      "epoch": 0.35599505562422745,
      "grad_norm": 0.22435835003852844,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.004,
      "step": 72
    },
    {
      "epoch": 0.36093943139678614,
      "grad_norm": 0.00362699618563056,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0001,
      "step": 73
    },
    {
      "epoch": 0.3658838071693449,
      "grad_norm": 0.22229711711406708,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0009,
      "step": 74
    },
    {
      "epoch": 0.37082818294190356,
      "grad_norm": 0.003972846549004316,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0001,
      "step": 75
    },
    {
      "epoch": 0.3757725587144623,
      "grad_norm": 0.005316532216966152,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0001,
      "step": 76
    },
    {
      "epoch": 0.380716934487021,
      "grad_norm": 0.003356312867254019,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0001,
      "step": 77
    },
    {
      "epoch": 0.3856613102595797,
      "grad_norm": 0.023712005466222763,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0006,
      "step": 78
    },
    {
      "epoch": 0.39060568603213847,
      "grad_norm": 0.0036223619244992733,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0001,
      "step": 79
    },
    {
      "epoch": 0.39555006180469715,
      "grad_norm": 0.07850874960422516,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0008,
      "step": 80
    },
    {
      "epoch": 0.4004944375772559,
      "grad_norm": 2.543851852416992,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0112,
      "step": 81
    },
    {
      "epoch": 0.4054388133498146,
      "grad_norm": 0.005454899277538061,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0001,
      "step": 82
    },
    {
      "epoch": 0.4103831891223733,
      "grad_norm": 0.004248406272381544,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0001,
      "step": 83
    },
    {
      "epoch": 0.415327564894932,
      "grad_norm": 0.24411757290363312,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.003,
      "step": 84
    },
    {
      "epoch": 0.42027194066749074,
      "grad_norm": 0.22071103751659393,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0008,
      "step": 85
    },
    {
      "epoch": 0.4252163164400494,
      "grad_norm": 0.35767996311187744,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0045,
      "step": 86
    },
    {
      "epoch": 0.43016069221260816,
      "grad_norm": 0.009658634662628174,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0001,
      "step": 87
    },
    {
      "epoch": 0.43510506798516685,
      "grad_norm": 0.4618425965309143,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0089,
      "step": 88
    },
    {
      "epoch": 0.4400494437577256,
      "grad_norm": 0.039499297738075256,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0005,
      "step": 89
    },
    {
      "epoch": 0.44499381953028433,
      "grad_norm": 0.12824542820453644,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0016,
      "step": 90
    },
    {
      "epoch": 0.449938195302843,
      "grad_norm": 0.04189825803041458,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0005,
      "step": 91
    },
    {
      "epoch": 0.45488257107540175,
      "grad_norm": 0.03173510730266571,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0004,
      "step": 92
    },
    {
      "epoch": 0.45982694684796044,
      "grad_norm": 0.2132241427898407,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0106,
      "step": 93
    },
    {
      "epoch": 0.4647713226205192,
      "grad_norm": 0.5073721408843994,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0038,
      "step": 94
    },
    {
      "epoch": 0.46971569839307786,
      "grad_norm": 0.08248043805360794,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0005,
      "step": 95
    },
    {
      "epoch": 0.4746600741656366,
      "grad_norm": 0.00955149345099926,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0002,
      "step": 96
    },
    {
      "epoch": 0.4796044499381953,
      "grad_norm": 0.09334550052881241,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0006,
      "step": 97
    },
    {
      "epoch": 0.484548825710754,
      "grad_norm": 0.2532207667827606,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0054,
      "step": 98
    },
    {
      "epoch": 0.4894932014833127,
      "grad_norm": 0.030377449467778206,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0005,
      "step": 99
    },
    {
      "epoch": 0.49443757725587145,
      "grad_norm": 0.8488153219223022,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0039,
      "step": 100
    },
    {
      "epoch": 0.49443757725587145,
      "eval_loss": 0.008121917955577374,
      "eval_runtime": 50.4991,
      "eval_samples_per_second": 6.753,
      "eval_steps_per_second": 1.703,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}