{
  "best_metric": 1.5963640213012695,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.14245014245014245,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014245014245014246,
      "grad_norm": 1.0951812267303467,
      "learning_rate": 1e-05,
      "loss": 1.0342,
      "step": 1
    },
    {
      "epoch": 0.0014245014245014246,
      "eval_loss": 3.0569612979888916,
      "eval_runtime": 52.5534,
      "eval_samples_per_second": 22.491,
      "eval_steps_per_second": 5.632,
      "step": 1
    },
    {
      "epoch": 0.002849002849002849,
      "grad_norm": 1.2440255880355835,
      "learning_rate": 2e-05,
      "loss": 1.23,
      "step": 2
    },
    {
      "epoch": 0.004273504273504274,
      "grad_norm": 1.2522715330123901,
      "learning_rate": 3e-05,
      "loss": 1.1836,
      "step": 3
    },
    {
      "epoch": 0.005698005698005698,
      "grad_norm": 1.0097229480743408,
      "learning_rate": 4e-05,
      "loss": 1.1769,
      "step": 4
    },
    {
      "epoch": 0.007122507122507123,
      "grad_norm": 0.8267636895179749,
      "learning_rate": 5e-05,
      "loss": 1.1482,
      "step": 5
    },
    {
      "epoch": 0.008547008547008548,
      "grad_norm": 0.8028005957603455,
      "learning_rate": 6e-05,
      "loss": 1.1643,
      "step": 6
    },
    {
      "epoch": 0.009971509971509971,
      "grad_norm": 0.9496132135391235,
      "learning_rate": 7e-05,
      "loss": 1.1892,
      "step": 7
    },
    {
      "epoch": 0.011396011396011397,
      "grad_norm": 0.907049834728241,
      "learning_rate": 8e-05,
      "loss": 1.1762,
      "step": 8
    },
    {
      "epoch": 0.01282051282051282,
      "grad_norm": 0.8857720494270325,
      "learning_rate": 9e-05,
      "loss": 1.182,
      "step": 9
    },
    {
      "epoch": 0.014245014245014245,
      "grad_norm": 0.904456615447998,
      "learning_rate": 0.0001,
      "loss": 1.0663,
      "step": 10
    },
    {
      "epoch": 0.01566951566951567,
      "grad_norm": 0.9192906618118286,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.1089,
      "step": 11
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.8807336688041687,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1222,
      "step": 12
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.9005780816078186,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.0595,
      "step": 13
    },
    {
      "epoch": 0.019943019943019943,
      "grad_norm": 0.8774030208587646,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1263,
      "step": 14
    },
    {
      "epoch": 0.021367521367521368,
      "grad_norm": 0.8597561717033386,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1282,
      "step": 15
    },
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 0.8737494945526123,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.085,
      "step": 16
    },
    {
      "epoch": 0.024216524216524215,
      "grad_norm": 0.9524723887443542,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.1558,
      "step": 17
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 1.0169023275375366,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.2095,
      "step": 18
    },
    {
      "epoch": 0.027065527065527065,
      "grad_norm": 0.9679225087165833,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0824,
      "step": 19
    },
    {
      "epoch": 0.02849002849002849,
      "grad_norm": 1.0456973314285278,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.1306,
      "step": 20
    },
    {
      "epoch": 0.029914529914529916,
      "grad_norm": 1.1445212364196777,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1833,
      "step": 21
    },
    {
      "epoch": 0.03133903133903134,
      "grad_norm": 1.1573503017425537,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1789,
      "step": 22
    },
    {
      "epoch": 0.03276353276353276,
      "grad_norm": 1.2056080102920532,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.1198,
      "step": 23
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 1.2797175645828247,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1591,
      "step": 24
    },
    {
      "epoch": 0.03561253561253561,
      "grad_norm": 1.4011354446411133,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.052,
      "step": 25
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.9526931047439575,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2072,
      "step": 26
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 2.649031400680542,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.2972,
      "step": 27
    },
    {
      "epoch": 0.039886039886039885,
      "grad_norm": 2.6092941761016846,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.2277,
      "step": 28
    },
    {
      "epoch": 0.04131054131054131,
      "grad_norm": 3.3454010486602783,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4816,
      "step": 29
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 3.7493395805358887,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.5207,
      "step": 30
    },
    {
      "epoch": 0.04415954415954416,
      "grad_norm": 3.1265792846679688,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2653,
      "step": 31
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 3.3090927600860596,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3105,
      "step": 32
    },
    {
      "epoch": 0.04700854700854701,
      "grad_norm": 3.3450868129730225,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.4618,
      "step": 33
    },
    {
      "epoch": 0.04843304843304843,
      "grad_norm": 2.2661399841308594,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.0056,
      "step": 34
    },
    {
      "epoch": 0.04985754985754986,
      "grad_norm": 2.910419464111328,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.4462,
      "step": 35
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 2.9667439460754395,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.1563,
      "step": 36
    },
    {
      "epoch": 0.05270655270655271,
      "grad_norm": 3.5099833011627197,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1158,
      "step": 37
    },
    {
      "epoch": 0.05413105413105413,
      "grad_norm": 3.4474451541900635,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.0648,
      "step": 38
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 4.265199184417725,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.4478,
      "step": 39
    },
    {
      "epoch": 0.05698005698005698,
      "grad_norm": 4.456178665161133,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.1621,
      "step": 40
    },
    {
      "epoch": 0.0584045584045584,
      "grad_norm": 3.706169366836548,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.0857,
      "step": 41
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 4.969032287597656,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.9443,
      "step": 42
    },
    {
      "epoch": 0.06125356125356125,
      "grad_norm": 5.319019794464111,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.2881,
      "step": 43
    },
    {
      "epoch": 0.06267806267806268,
      "grad_norm": 5.219686031341553,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.6457,
      "step": 44
    },
    {
      "epoch": 0.0641025641025641,
      "grad_norm": 4.730462074279785,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.6407,
      "step": 45
    },
    {
      "epoch": 0.06552706552706553,
      "grad_norm": 4.715185165405273,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.9509,
      "step": 46
    },
    {
      "epoch": 0.06695156695156695,
      "grad_norm": 5.63643217086792,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.1613,
      "step": 47
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 4.680100917816162,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9855,
      "step": 48
    },
    {
      "epoch": 0.0698005698005698,
      "grad_norm": 5.361738204956055,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.4161,
      "step": 49
    },
    {
      "epoch": 0.07122507122507123,
      "grad_norm": 6.914300918579102,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6899,
      "step": 50
    },
    {
      "epoch": 0.07122507122507123,
      "eval_loss": 1.6694526672363281,
      "eval_runtime": 52.7339,
      "eval_samples_per_second": 22.414,
      "eval_steps_per_second": 5.613,
      "step": 50
    },
    {
      "epoch": 0.07264957264957266,
      "grad_norm": 1.8794810771942139,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2168,
      "step": 51
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.151414632797241,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.4221,
      "step": 52
    },
    {
      "epoch": 0.0754985754985755,
      "grad_norm": 1.6555006504058838,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.3112,
      "step": 53
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.2223625183105469,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1976,
      "step": 54
    },
    {
      "epoch": 0.07834757834757834,
      "grad_norm": 1.0195894241333008,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2126,
      "step": 55
    },
    {
      "epoch": 0.07977207977207977,
      "grad_norm": 0.7386775612831116,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1169,
      "step": 56
    },
    {
      "epoch": 0.0811965811965812,
      "grad_norm": 0.6235164403915405,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.0829,
      "step": 57
    },
    {
      "epoch": 0.08262108262108261,
      "grad_norm": 0.6764860153198242,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1481,
      "step": 58
    },
    {
      "epoch": 0.08404558404558404,
      "grad_norm": 0.7909321188926697,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.1837,
      "step": 59
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.843760073184967,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2104,
      "step": 60
    },
    {
      "epoch": 0.0868945868945869,
      "grad_norm": 0.8562942147254944,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.1524,
      "step": 61
    },
    {
      "epoch": 0.08831908831908832,
      "grad_norm": 0.843786895275116,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.1703,
      "step": 62
    },
    {
      "epoch": 0.08974358974358974,
      "grad_norm": 0.7898869514465332,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1328,
      "step": 63
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.768024742603302,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.1505,
      "step": 64
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.7674038410186768,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.1166,
      "step": 65
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.7880211472511292,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0265,
      "step": 66
    },
    {
      "epoch": 0.09544159544159544,
      "grad_norm": 0.8146145939826965,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0635,
      "step": 67
    },
    {
      "epoch": 0.09686609686609686,
      "grad_norm": 0.8939031958580017,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.0924,
      "step": 68
    },
    {
      "epoch": 0.09829059829059829,
      "grad_norm": 0.9344921112060547,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.1032,
      "step": 69
    },
    {
      "epoch": 0.09971509971509972,
      "grad_norm": 1.0251350402832031,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.0943,
      "step": 70
    },
    {
      "epoch": 0.10113960113960115,
      "grad_norm": 1.0262216329574585,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0996,
      "step": 71
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 1.050524115562439,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.03,
      "step": 72
    },
    {
      "epoch": 0.10398860398860399,
      "grad_norm": 1.1450400352478027,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0246,
      "step": 73
    },
    {
      "epoch": 0.10541310541310542,
      "grad_norm": 1.1916637420654297,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9999,
      "step": 74
    },
    {
      "epoch": 0.10683760683760683,
      "grad_norm": 1.4077075719833374,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.1149,
      "step": 75
    },
    {
      "epoch": 0.10826210826210826,
      "grad_norm": 1.5274344682693481,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9944,
      "step": 76
    },
    {
      "epoch": 0.10968660968660969,
      "grad_norm": 2.256171464920044,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2873,
      "step": 77
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 2.207008123397827,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0648,
      "step": 78
    },
    {
      "epoch": 0.11253561253561253,
      "grad_norm": 3.2979633808135986,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.3021,
      "step": 79
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 2.376344919204712,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0125,
      "step": 80
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 2.4043941497802734,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9742,
      "step": 81
    },
    {
      "epoch": 0.1168091168091168,
      "grad_norm": 2.793799877166748,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.1254,
      "step": 82
    },
    {
      "epoch": 0.11823361823361823,
      "grad_norm": 2.7024142742156982,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2951,
      "step": 83
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 3.5849368572235107,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.5779,
      "step": 84
    },
    {
      "epoch": 0.12108262108262108,
      "grad_norm": 3.006340265274048,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.3645,
      "step": 85
    },
    {
      "epoch": 0.1225071225071225,
      "grad_norm": 2.277855157852173,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0624,
      "step": 86
    },
    {
      "epoch": 0.12393162393162394,
      "grad_norm": 2.4271788597106934,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.5051,
      "step": 87
    },
    {
      "epoch": 0.12535612535612536,
      "grad_norm": 2.7788116931915283,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.7977,
      "step": 88
    },
    {
      "epoch": 0.1267806267806268,
      "grad_norm": 3.2901506423950195,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.9937,
      "step": 89
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 3.284877061843872,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0343,
      "step": 90
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 3.519197702407837,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.2603,
      "step": 91
    },
    {
      "epoch": 0.13105413105413105,
      "grad_norm": 3.5070576667785645,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.1193,
      "step": 92
    },
    {
      "epoch": 0.13247863247863248,
      "grad_norm": 3.874929904937744,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.1551,
      "step": 93
    },
    {
      "epoch": 0.1339031339031339,
      "grad_norm": 4.789926052093506,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.4054,
      "step": 94
    },
    {
      "epoch": 0.13532763532763534,
      "grad_norm": 5.195937633514404,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.6756,
      "step": 95
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 4.467799663543701,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.3472,
      "step": 96
    },
    {
      "epoch": 0.13817663817663817,
      "grad_norm": 4.928045272827148,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.9974,
      "step": 97
    },
    {
      "epoch": 0.1396011396011396,
      "grad_norm": 5.623568058013916,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.399,
      "step": 98
    },
    {
      "epoch": 0.14102564102564102,
      "grad_norm": 5.925526142120361,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.9024,
      "step": 99
    },
    {
      "epoch": 0.14245014245014245,
      "grad_norm": 7.447940826416016,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.841,
      "step": 100
    },
    {
      "epoch": 0.14245014245014245,
      "eval_loss": 1.5963640213012695,
      "eval_runtime": 52.7393,
      "eval_samples_per_second": 22.412,
      "eval_steps_per_second": 5.613,
      "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": 4.154039461321114e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}