{
  "best_metric": 0.314230740070343,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.33698399326032014,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003369839932603201,
      "grad_norm": 7.51057243347168,
      "learning_rate": 1e-05,
      "loss": 2.1494,
      "step": 1
    },
    {
      "epoch": 0.003369839932603201,
      "eval_loss": 0.8092716336250305,
      "eval_runtime": 120.282,
      "eval_samples_per_second": 4.157,
      "eval_steps_per_second": 1.039,
      "step": 1
    },
    {
      "epoch": 0.006739679865206402,
      "grad_norm": 9.15483570098877,
      "learning_rate": 2e-05,
      "loss": 2.7371,
      "step": 2
    },
    {
      "epoch": 0.010109519797809604,
      "grad_norm": 7.816402912139893,
      "learning_rate": 3e-05,
      "loss": 2.5099,
      "step": 3
    },
    {
      "epoch": 0.013479359730412805,
      "grad_norm": 5.4665608406066895,
      "learning_rate": 4e-05,
      "loss": 2.3463,
      "step": 4
    },
    {
      "epoch": 0.016849199663016005,
      "grad_norm": 5.093127727508545,
      "learning_rate": 5e-05,
      "loss": 2.1346,
      "step": 5
    },
    {
      "epoch": 0.020219039595619208,
      "grad_norm": 5.4731855392456055,
      "learning_rate": 6e-05,
      "loss": 2.2381,
      "step": 6
    },
    {
      "epoch": 0.02358887952822241,
      "grad_norm": 4.477018356323242,
      "learning_rate": 7e-05,
      "loss": 1.927,
      "step": 7
    },
    {
      "epoch": 0.02695871946082561,
      "grad_norm": 4.402273178100586,
      "learning_rate": 8e-05,
      "loss": 2.0187,
      "step": 8
    },
    {
      "epoch": 0.030328559393428812,
      "grad_norm": 3.9021198749542236,
      "learning_rate": 9e-05,
      "loss": 1.752,
      "step": 9
    },
    {
      "epoch": 0.03369839932603201,
      "grad_norm": 4.180506229400635,
      "learning_rate": 0.0001,
      "loss": 1.8939,
      "step": 10
    },
    {
      "epoch": 0.03706823925863521,
      "grad_norm": 3.6741297245025635,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.7022,
      "step": 11
    },
    {
      "epoch": 0.040438079191238416,
      "grad_norm": 3.5289134979248047,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.8531,
      "step": 12
    },
    {
      "epoch": 0.04380791912384162,
      "grad_norm": 4.152334690093994,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.85,
      "step": 13
    },
    {
      "epoch": 0.04717775905644482,
      "grad_norm": 3.1703765392303467,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6875,
      "step": 14
    },
    {
      "epoch": 0.05054759898904802,
      "grad_norm": 3.482504367828369,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8679,
      "step": 15
    },
    {
      "epoch": 0.05391743892165122,
      "grad_norm": 2.8432414531707764,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.777,
      "step": 16
    },
    {
      "epoch": 0.05728727885425442,
      "grad_norm": 3.414099931716919,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.6603,
      "step": 17
    },
    {
      "epoch": 0.060657118786857624,
      "grad_norm": 3.249868869781494,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7211,
      "step": 18
    },
    {
      "epoch": 0.06402695871946082,
      "grad_norm": 2.949674606323242,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6861,
      "step": 19
    },
    {
      "epoch": 0.06739679865206402,
      "grad_norm": 2.7226510047912598,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.6053,
      "step": 20
    },
    {
      "epoch": 0.07076663858466722,
      "grad_norm": 3.109335422515869,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.6572,
      "step": 21
    },
    {
      "epoch": 0.07413647851727043,
      "grad_norm": 3.3253257274627686,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.5954,
      "step": 22
    },
    {
      "epoch": 0.07750631844987363,
      "grad_norm": 3.090282917022705,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.6515,
      "step": 23
    },
    {
      "epoch": 0.08087615838247683,
      "grad_norm": 2.9994139671325684,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.7576,
      "step": 24
    },
    {
      "epoch": 0.08424599831508003,
      "grad_norm": 3.127659320831299,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.6768,
      "step": 25
    },
    {
      "epoch": 0.08761583824768324,
      "grad_norm": 3.3083384037017822,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.568,
      "step": 26
    },
    {
      "epoch": 0.09098567818028644,
      "grad_norm": 3.118006706237793,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.5629,
      "step": 27
    },
    {
      "epoch": 0.09435551811288964,
      "grad_norm": 3.579113245010376,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.5379,
      "step": 28
    },
    {
      "epoch": 0.09772535804549284,
      "grad_norm": 3.026153802871704,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4824,
      "step": 29
    },
    {
      "epoch": 0.10109519797809605,
      "grad_norm": 2.802640914916992,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.2536,
      "step": 30
    },
    {
      "epoch": 0.10446503791069923,
      "grad_norm": 3.0235989093780518,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3792,
      "step": 31
    },
    {
      "epoch": 0.10783487784330244,
      "grad_norm": 3.0789220333099365,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2263,
      "step": 32
    },
    {
      "epoch": 0.11120471777590564,
      "grad_norm": 2.703223943710327,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.1993,
      "step": 33
    },
    {
      "epoch": 0.11457455770850884,
      "grad_norm": 2.7497401237487793,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.4319,
      "step": 34
    },
    {
      "epoch": 0.11794439764111204,
      "grad_norm": 2.8858532905578613,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.549,
      "step": 35
    },
    {
      "epoch": 0.12131423757371525,
      "grad_norm": 2.815218925476074,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.5933,
      "step": 36
    },
    {
      "epoch": 0.12468407750631845,
      "grad_norm": 2.8283677101135254,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.599,
      "step": 37
    },
    {
      "epoch": 0.12805391743892164,
      "grad_norm": 2.8242433071136475,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.559,
      "step": 38
    },
    {
      "epoch": 0.13142375737152484,
      "grad_norm": 2.870215654373169,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.6841,
      "step": 39
    },
    {
      "epoch": 0.13479359730412804,
      "grad_norm": 2.8067023754119873,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.6646,
      "step": 40
    },
    {
      "epoch": 0.13816343723673125,
      "grad_norm": 2.9085981845855713,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.7161,
      "step": 41
    },
    {
      "epoch": 0.14153327716933445,
      "grad_norm": 2.7535951137542725,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.5564,
      "step": 42
    },
    {
      "epoch": 0.14490311710193765,
      "grad_norm": 2.7437710762023926,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5449,
      "step": 43
    },
    {
      "epoch": 0.14827295703454085,
      "grad_norm": 2.6580138206481934,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.4529,
      "step": 44
    },
    {
      "epoch": 0.15164279696714406,
      "grad_norm": 3.217501163482666,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.4437,
      "step": 45
    },
    {
      "epoch": 0.15501263689974726,
      "grad_norm": 4.156802177429199,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.5593,
      "step": 46
    },
    {
      "epoch": 0.15838247683235046,
      "grad_norm": 2.9678525924682617,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.4153,
      "step": 47
    },
    {
      "epoch": 0.16175231676495366,
      "grad_norm": 2.6032907962799072,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3261,
      "step": 48
    },
    {
      "epoch": 0.16512215669755687,
      "grad_norm": 2.3966689109802246,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.3488,
      "step": 49
    },
    {
      "epoch": 0.16849199663016007,
      "grad_norm": 3.1099071502685547,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5242,
      "step": 50
    },
    {
      "epoch": 0.16849199663016007,
      "eval_loss": 0.3645605444908142,
      "eval_runtime": 121.6366,
      "eval_samples_per_second": 4.111,
      "eval_steps_per_second": 1.028,
      "step": 50
    },
    {
      "epoch": 0.17186183656276327,
      "grad_norm": 2.536522388458252,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.5471,
      "step": 51
    },
    {
      "epoch": 0.17523167649536647,
      "grad_norm": 2.1130993366241455,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.5713,
      "step": 52
    },
    {
      "epoch": 0.17860151642796968,
      "grad_norm": 1.899036169052124,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.5713,
      "step": 53
    },
    {
      "epoch": 0.18197135636057288,
      "grad_norm": 2.3696439266204834,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.583,
      "step": 54
    },
    {
      "epoch": 0.18534119629317608,
      "grad_norm": 2.156263589859009,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4893,
      "step": 55
    },
    {
      "epoch": 0.18871103622577928,
      "grad_norm": 1.9296045303344727,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.4985,
      "step": 56
    },
    {
      "epoch": 0.19208087615838249,
      "grad_norm": 1.9608573913574219,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.4801,
      "step": 57
    },
    {
      "epoch": 0.1954507160909857,
      "grad_norm": 2.0413198471069336,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.4525,
      "step": 58
    },
    {
      "epoch": 0.1988205560235889,
      "grad_norm": 1.96634840965271,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.4184,
      "step": 59
    },
    {
      "epoch": 0.2021903959561921,
      "grad_norm": 1.993112325668335,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.342,
      "step": 60
    },
    {
      "epoch": 0.2055602358887953,
      "grad_norm": 1.9955614805221558,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.2742,
      "step": 61
    },
    {
      "epoch": 0.20893007582139847,
      "grad_norm": 1.9142816066741943,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.114,
      "step": 62
    },
    {
      "epoch": 0.21229991575400167,
      "grad_norm": 2.074475049972534,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3422,
      "step": 63
    },
    {
      "epoch": 0.21566975568660487,
      "grad_norm": 2.186030626296997,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.3134,
      "step": 64
    },
    {
      "epoch": 0.21903959561920808,
      "grad_norm": 2.226123571395874,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6073,
      "step": 65
    },
    {
      "epoch": 0.22240943555181128,
      "grad_norm": 2.3604118824005127,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.5057,
      "step": 66
    },
    {
      "epoch": 0.22577927548441448,
      "grad_norm": 2.158315896987915,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5419,
      "step": 67
    },
    {
      "epoch": 0.22914911541701768,
      "grad_norm": 2.1268155574798584,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.4379,
      "step": 68
    },
    {
      "epoch": 0.2325189553496209,
      "grad_norm": 2.069324254989624,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.3387,
      "step": 69
    },
    {
      "epoch": 0.2358887952822241,
      "grad_norm": 2.181563377380371,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.6706,
      "step": 70
    },
    {
      "epoch": 0.2392586352148273,
      "grad_norm": 2.1285486221313477,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2435,
      "step": 71
    },
    {
      "epoch": 0.2426284751474305,
      "grad_norm": 2.0617074966430664,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.2847,
      "step": 72
    },
    {
      "epoch": 0.2459983150800337,
      "grad_norm": 2.0489954948425293,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.3647,
      "step": 73
    },
    {
      "epoch": 0.2493681550126369,
      "grad_norm": 2.035676956176758,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.1035,
      "step": 74
    },
    {
      "epoch": 0.2527379949452401,
      "grad_norm": 1.9856700897216797,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0442,
      "step": 75
    },
    {
      "epoch": 0.2561078348778433,
      "grad_norm": 2.228813886642456,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.2683,
      "step": 76
    },
    {
      "epoch": 0.2594776748104465,
      "grad_norm": 2.338102340698242,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2413,
      "step": 77
    },
    {
      "epoch": 0.2628475147430497,
      "grad_norm": 2.1351075172424316,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0997,
      "step": 78
    },
    {
      "epoch": 0.2662173546756529,
      "grad_norm": 2.4263010025024414,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.1819,
      "step": 79
    },
    {
      "epoch": 0.2695871946082561,
      "grad_norm": 2.098903179168701,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0219,
      "step": 80
    },
    {
      "epoch": 0.2729570345408593,
      "grad_norm": 2.0994834899902344,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9817,
      "step": 81
    },
    {
      "epoch": 0.2763268744734625,
      "grad_norm": 2.0242087841033936,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8622,
      "step": 82
    },
    {
      "epoch": 0.2796967144060657,
      "grad_norm": 1.9342875480651855,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9491,
      "step": 83
    },
    {
      "epoch": 0.2830665543386689,
      "grad_norm": 2.0760669708251953,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.1232,
      "step": 84
    },
    {
      "epoch": 0.2864363942712721,
      "grad_norm": 2.1343932151794434,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.1115,
      "step": 85
    },
    {
      "epoch": 0.2898062342038753,
      "grad_norm": 2.311663866043091,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.325,
      "step": 86
    },
    {
      "epoch": 0.2931760741364785,
      "grad_norm": 2.1452784538269043,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.301,
      "step": 87
    },
    {
      "epoch": 0.2965459140690817,
      "grad_norm": 2.288419246673584,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.2846,
      "step": 88
    },
    {
      "epoch": 0.2999157540016849,
      "grad_norm": 2.253816604614258,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2931,
      "step": 89
    },
    {
      "epoch": 0.3032855939342881,
      "grad_norm": 2.3119921684265137,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.3536,
      "step": 90
    },
    {
      "epoch": 0.3066554338668913,
      "grad_norm": 2.3031837940216064,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.4333,
      "step": 91
    },
    {
      "epoch": 0.3100252737994945,
      "grad_norm": 2.3394315242767334,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.3935,
      "step": 92
    },
    {
      "epoch": 0.3133951137320977,
      "grad_norm": 2.75341534614563,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.351,
      "step": 93
    },
    {
      "epoch": 0.3167649536647009,
      "grad_norm": 2.6161062717437744,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3347,
      "step": 94
    },
    {
      "epoch": 0.3201347935973041,
      "grad_norm": 2.364361524581909,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9233,
      "step": 95
    },
    {
      "epoch": 0.3235046335299073,
      "grad_norm": 2.500354290008545,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.339,
      "step": 96
    },
    {
      "epoch": 0.32687447346251053,
      "grad_norm": 2.3215596675872803,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.2591,
      "step": 97
    },
    {
      "epoch": 0.33024431339511373,
      "grad_norm": 2.3461391925811768,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.2868,
      "step": 98
    },
    {
      "epoch": 0.33361415332771693,
      "grad_norm": 2.204437494277954,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0907,
      "step": 99
    },
    {
      "epoch": 0.33698399326032014,
      "grad_norm": 2.5249979496002197,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.2808,
      "step": 100
    },
    {
      "epoch": 0.33698399326032014,
      "eval_loss": 0.314230740070343,
      "eval_runtime": 121.707,
      "eval_samples_per_second": 4.108,
      "eval_steps_per_second": 1.027,
      "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": 2.836953552818012e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}