{
  "best_metric": 1.5987274646759033,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.03712641544458883,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00037126415444588826,
      "grad_norm": 6.770651817321777,
      "learning_rate": 1e-05,
      "loss": 14.1005,
      "step": 1
    },
    {
      "epoch": 0.00037126415444588826,
      "eval_loss": 4.361657619476318,
      "eval_runtime": 561.9621,
      "eval_samples_per_second": 8.073,
      "eval_steps_per_second": 2.02,
      "step": 1
    },
    {
      "epoch": 0.0007425283088917765,
      "grad_norm": 8.687636375427246,
      "learning_rate": 2e-05,
      "loss": 17.8128,
      "step": 2
    },
    {
      "epoch": 0.0011137924633376648,
      "grad_norm": 8.961566925048828,
      "learning_rate": 3e-05,
      "loss": 18.9768,
      "step": 3
    },
    {
      "epoch": 0.001485056617783553,
      "grad_norm": 8.438793182373047,
      "learning_rate": 4e-05,
      "loss": 18.1473,
      "step": 4
    },
    {
      "epoch": 0.0018563207722294413,
      "grad_norm": 11.668978691101074,
      "learning_rate": 5e-05,
      "loss": 20.4785,
      "step": 5
    },
    {
      "epoch": 0.0022275849266753297,
      "grad_norm": 12.654362678527832,
      "learning_rate": 6e-05,
      "loss": 20.2845,
      "step": 6
    },
    {
      "epoch": 0.0025988490811212177,
      "grad_norm": 12.418852806091309,
      "learning_rate": 7e-05,
      "loss": 21.1342,
      "step": 7
    },
    {
      "epoch": 0.002970113235567106,
      "grad_norm": 11.714797973632812,
      "learning_rate": 8e-05,
      "loss": 20.2635,
      "step": 8
    },
    {
      "epoch": 0.003341377390012994,
      "grad_norm": 15.500533103942871,
      "learning_rate": 9e-05,
      "loss": 21.1619,
      "step": 9
    },
    {
      "epoch": 0.0037126415444588825,
      "grad_norm": 14.004990577697754,
      "learning_rate": 0.0001,
      "loss": 21.6419,
      "step": 10
    },
    {
      "epoch": 0.0040839056989047705,
      "grad_norm": 9.49889850616455,
      "learning_rate": 9.99695413509548e-05,
      "loss": 13.9394,
      "step": 11
    },
    {
      "epoch": 0.004455169853350659,
      "grad_norm": 9.78544807434082,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.7483,
      "step": 12
    },
    {
      "epoch": 0.004826434007796547,
      "grad_norm": 8.1702880859375,
      "learning_rate": 9.972609476841367e-05,
      "loss": 9.8475,
      "step": 13
    },
    {
      "epoch": 0.005197698162242435,
      "grad_norm": 7.895254611968994,
      "learning_rate": 9.951340343707852e-05,
      "loss": 9.6974,
      "step": 14
    },
    {
      "epoch": 0.005568962316688323,
      "grad_norm": 14.222855567932129,
      "learning_rate": 9.924038765061042e-05,
      "loss": 9.0982,
      "step": 15
    },
    {
      "epoch": 0.005940226471134212,
      "grad_norm": 15.02148723602295,
      "learning_rate": 9.890738003669029e-05,
      "loss": 7.7513,
      "step": 16
    },
    {
      "epoch": 0.0063114906255801,
      "grad_norm": 7.8985419273376465,
      "learning_rate": 9.851478631379982e-05,
      "loss": 8.2367,
      "step": 17
    },
    {
      "epoch": 0.006682754780025988,
      "grad_norm": 9.158758163452148,
      "learning_rate": 9.806308479691595e-05,
      "loss": 8.205,
      "step": 18
    },
    {
      "epoch": 0.007054018934471877,
      "grad_norm": 21.200363159179688,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.5559,
      "step": 19
    },
    {
      "epoch": 0.007425283088917765,
      "grad_norm": 6.861835479736328,
      "learning_rate": 9.698463103929542e-05,
      "loss": 6.508,
      "step": 20
    },
    {
      "epoch": 0.007796547243363653,
      "grad_norm": 4.614739418029785,
      "learning_rate": 9.635919272833938e-05,
      "loss": 7.8475,
      "step": 21
    },
    {
      "epoch": 0.008167811397809541,
      "grad_norm": 6.366387844085693,
      "learning_rate": 9.567727288213005e-05,
      "loss": 7.4751,
      "step": 22
    },
    {
      "epoch": 0.008539075552255429,
      "grad_norm": 6.066256999969482,
      "learning_rate": 9.493970231495835e-05,
      "loss": 7.2972,
      "step": 23
    },
    {
      "epoch": 0.008910339706701319,
      "grad_norm": 5.310906887054443,
      "learning_rate": 9.414737964294636e-05,
      "loss": 6.0529,
      "step": 24
    },
    {
      "epoch": 0.009281603861147207,
      "grad_norm": 5.21856164932251,
      "learning_rate": 9.330127018922194e-05,
      "loss": 6.9142,
      "step": 25
    },
    {
      "epoch": 0.009652868015593095,
      "grad_norm": 4.360562324523926,
      "learning_rate": 9.24024048078213e-05,
      "loss": 7.5712,
      "step": 26
    },
    {
      "epoch": 0.010024132170038983,
      "grad_norm": 5.237946510314941,
      "learning_rate": 9.145187862775209e-05,
      "loss": 7.2218,
      "step": 27
    },
    {
      "epoch": 0.01039539632448487,
      "grad_norm": 6.701196193695068,
      "learning_rate": 9.045084971874738e-05,
      "loss": 6.7606,
      "step": 28
    },
    {
      "epoch": 0.010766660478930759,
      "grad_norm": 5.245985507965088,
      "learning_rate": 8.940053768033609e-05,
      "loss": 6.9502,
      "step": 29
    },
    {
      "epoch": 0.011137924633376647,
      "grad_norm": 4.025079727172852,
      "learning_rate": 8.83022221559489e-05,
      "loss": 5.8071,
      "step": 30
    },
    {
      "epoch": 0.011509188787822536,
      "grad_norm": 5.323147773742676,
      "learning_rate": 8.715724127386972e-05,
      "loss": 6.8309,
      "step": 31
    },
    {
      "epoch": 0.011880452942268424,
      "grad_norm": 4.425078868865967,
      "learning_rate": 8.596699001693255e-05,
      "loss": 6.5695,
      "step": 32
    },
    {
      "epoch": 0.012251717096714312,
      "grad_norm": 4.665747165679932,
      "learning_rate": 8.473291852294987e-05,
      "loss": 6.1289,
      "step": 33
    },
    {
      "epoch": 0.0126229812511602,
      "grad_norm": 4.494863986968994,
      "learning_rate": 8.345653031794292e-05,
      "loss": 6.1595,
      "step": 34
    },
    {
      "epoch": 0.012994245405606088,
      "grad_norm": 4.774189472198486,
      "learning_rate": 8.213938048432697e-05,
      "loss": 6.2973,
      "step": 35
    },
    {
      "epoch": 0.013365509560051976,
      "grad_norm": 4.161970615386963,
      "learning_rate": 8.07830737662829e-05,
      "loss": 6.7843,
      "step": 36
    },
    {
      "epoch": 0.013736773714497864,
      "grad_norm": 4.1743292808532715,
      "learning_rate": 7.938926261462366e-05,
      "loss": 6.4967,
      "step": 37
    },
    {
      "epoch": 0.014108037868943754,
      "grad_norm": 4.199504375457764,
      "learning_rate": 7.795964517353735e-05,
      "loss": 6.5638,
      "step": 38
    },
    {
      "epoch": 0.014479302023389642,
      "grad_norm": 4.517217636108398,
      "learning_rate": 7.649596321166024e-05,
      "loss": 7.2976,
      "step": 39
    },
    {
      "epoch": 0.01485056617783553,
      "grad_norm": 4.099196910858154,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.5602,
      "step": 40
    },
    {
      "epoch": 0.015221830332281418,
      "grad_norm": 4.4114251136779785,
      "learning_rate": 7.347357813929454e-05,
      "loss": 6.7823,
      "step": 41
    },
    {
      "epoch": 0.015593094486727306,
      "grad_norm": 4.016313552856445,
      "learning_rate": 7.191855733945387e-05,
      "loss": 6.5018,
      "step": 42
    },
    {
      "epoch": 0.015964358641173196,
      "grad_norm": 4.02785587310791,
      "learning_rate": 7.033683215379002e-05,
      "loss": 6.4507,
      "step": 43
    },
    {
      "epoch": 0.016335622795619082,
      "grad_norm": 4.262504577636719,
      "learning_rate": 6.873032967079561e-05,
      "loss": 6.1423,
      "step": 44
    },
    {
      "epoch": 0.016706886950064972,
      "grad_norm": 3.9246904850006104,
      "learning_rate": 6.710100716628344e-05,
      "loss": 6.2621,
      "step": 45
    },
    {
      "epoch": 0.017078151104510858,
      "grad_norm": 4.26507568359375,
      "learning_rate": 6.545084971874738e-05,
      "loss": 7.6392,
      "step": 46
    },
    {
      "epoch": 0.017449415258956748,
      "grad_norm": 3.834524393081665,
      "learning_rate": 6.378186779084995e-05,
      "loss": 6.7854,
      "step": 47
    },
    {
      "epoch": 0.017820679413402638,
      "grad_norm": 5.054991722106934,
      "learning_rate": 6.209609477998338e-05,
      "loss": 6.0353,
      "step": 48
    },
    {
      "epoch": 0.018191943567848524,
      "grad_norm": 3.795661687850952,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 5.4362,
      "step": 49
    },
    {
      "epoch": 0.018563207722294413,
      "grad_norm": 4.460452556610107,
      "learning_rate": 5.868240888334653e-05,
      "loss": 6.807,
      "step": 50
    },
    {
      "epoch": 0.018563207722294413,
      "eval_loss": 1.7446192502975464,
      "eval_runtime": 566.7624,
      "eval_samples_per_second": 8.005,
      "eval_steps_per_second": 2.003,
      "step": 50
    },
    {
      "epoch": 0.0189344718767403,
      "grad_norm": 5.353964328765869,
      "learning_rate": 5.695865504800327e-05,
      "loss": 8.9486,
      "step": 51
    },
    {
      "epoch": 0.01930573603118619,
      "grad_norm": 6.079212188720703,
      "learning_rate": 5.522642316338268e-05,
      "loss": 9.9081,
      "step": 52
    },
    {
      "epoch": 0.019677000185632076,
      "grad_norm": 7.1975932121276855,
      "learning_rate": 5.348782368720626e-05,
      "loss": 8.2391,
      "step": 53
    },
    {
      "epoch": 0.020048264340077965,
      "grad_norm": 6.638981342315674,
      "learning_rate": 5.174497483512506e-05,
      "loss": 8.5821,
      "step": 54
    },
    {
      "epoch": 0.020419528494523855,
      "grad_norm": 9.038630485534668,
      "learning_rate": 5e-05,
      "loss": 9.6055,
      "step": 55
    },
    {
      "epoch": 0.02079079264896974,
      "grad_norm": 9.090941429138184,
      "learning_rate": 4.825502516487497e-05,
      "loss": 9.724,
      "step": 56
    },
    {
      "epoch": 0.02116205680341563,
      "grad_norm": 7.1579108238220215,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 7.7207,
      "step": 57
    },
    {
      "epoch": 0.021533320957861517,
      "grad_norm": 8.75041389465332,
      "learning_rate": 4.477357683661734e-05,
      "loss": 8.7275,
      "step": 58
    },
    {
      "epoch": 0.021904585112307407,
      "grad_norm": 6.073078155517578,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 7.8166,
      "step": 59
    },
    {
      "epoch": 0.022275849266753293,
      "grad_norm": 6.027640342712402,
      "learning_rate": 4.131759111665349e-05,
      "loss": 6.9793,
      "step": 60
    },
    {
      "epoch": 0.022647113421199183,
      "grad_norm": 6.702777862548828,
      "learning_rate": 3.960441545911204e-05,
      "loss": 7.5993,
      "step": 61
    },
    {
      "epoch": 0.023018377575645073,
      "grad_norm": 6.559276103973389,
      "learning_rate": 3.790390522001662e-05,
      "loss": 6.5231,
      "step": 62
    },
    {
      "epoch": 0.02338964173009096,
      "grad_norm": 6.18765926361084,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 6.9596,
      "step": 63
    },
    {
      "epoch": 0.02376090588453685,
      "grad_norm": 5.145318508148193,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 6.4935,
      "step": 64
    },
    {
      "epoch": 0.024132170038982735,
      "grad_norm": 4.60317850112915,
      "learning_rate": 3.289899283371657e-05,
      "loss": 6.1899,
      "step": 65
    },
    {
      "epoch": 0.024503434193428625,
      "grad_norm": 4.280679225921631,
      "learning_rate": 3.12696703292044e-05,
      "loss": 6.1858,
      "step": 66
    },
    {
      "epoch": 0.02487469834787451,
      "grad_norm": 4.138360023498535,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 6.1128,
      "step": 67
    },
    {
      "epoch": 0.0252459625023204,
      "grad_norm": 4.611503601074219,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 6.3028,
      "step": 68
    },
    {
      "epoch": 0.02561722665676629,
      "grad_norm": 4.154057502746582,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 5.5962,
      "step": 69
    },
    {
      "epoch": 0.025988490811212177,
      "grad_norm": 3.594250202178955,
      "learning_rate": 2.500000000000001e-05,
      "loss": 5.6007,
      "step": 70
    },
    {
      "epoch": 0.026359754965658067,
      "grad_norm": 4.3070454597473145,
      "learning_rate": 2.350403678833976e-05,
      "loss": 6.1225,
      "step": 71
    },
    {
      "epoch": 0.026731019120103953,
      "grad_norm": 4.306888580322266,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 6.8154,
      "step": 72
    },
    {
      "epoch": 0.027102283274549843,
      "grad_norm": 3.854240655899048,
      "learning_rate": 2.061073738537635e-05,
      "loss": 5.8671,
      "step": 73
    },
    {
      "epoch": 0.02747354742899573,
      "grad_norm": 3.8052146434783936,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 6.1667,
      "step": 74
    },
    {
      "epoch": 0.02784481158344162,
      "grad_norm": 3.809180974960327,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 5.8298,
      "step": 75
    },
    {
      "epoch": 0.028216075737887508,
      "grad_norm": 3.352525234222412,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 5.3726,
      "step": 76
    },
    {
      "epoch": 0.028587339892333394,
      "grad_norm": 3.5558321475982666,
      "learning_rate": 1.526708147705013e-05,
      "loss": 6.2531,
      "step": 77
    },
    {
      "epoch": 0.028958604046779284,
      "grad_norm": 3.92938494682312,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 5.5628,
      "step": 78
    },
    {
      "epoch": 0.02932986820122517,
      "grad_norm": 3.702071189880371,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 5.8864,
      "step": 79
    },
    {
      "epoch": 0.02970113235567106,
      "grad_norm": 4.398648262023926,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 6.06,
      "step": 80
    },
    {
      "epoch": 0.03007239651011695,
      "grad_norm": 3.4324252605438232,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 5.1271,
      "step": 81
    },
    {
      "epoch": 0.030443660664562836,
      "grad_norm": 3.377044439315796,
      "learning_rate": 9.549150281252633e-06,
      "loss": 5.4419,
      "step": 82
    },
    {
      "epoch": 0.030814924819008726,
      "grad_norm": 3.836601734161377,
      "learning_rate": 8.548121372247918e-06,
      "loss": 5.5232,
      "step": 83
    },
    {
      "epoch": 0.031186188973454612,
      "grad_norm": 4.520117282867432,
      "learning_rate": 7.597595192178702e-06,
      "loss": 6.1833,
      "step": 84
    },
    {
      "epoch": 0.0315574531279005,
      "grad_norm": 3.46451473236084,
      "learning_rate": 6.698729810778065e-06,
      "loss": 5.3309,
      "step": 85
    },
    {
      "epoch": 0.03192871728234639,
      "grad_norm": 4.2184157371521,
      "learning_rate": 5.852620357053651e-06,
      "loss": 5.6528,
      "step": 86
    },
    {
      "epoch": 0.032299981436792274,
      "grad_norm": 4.261045455932617,
      "learning_rate": 5.060297685041659e-06,
      "loss": 6.3858,
      "step": 87
    },
    {
      "epoch": 0.032671245591238164,
      "grad_norm": 3.678689479827881,
      "learning_rate": 4.322727117869951e-06,
      "loss": 5.5889,
      "step": 88
    },
    {
      "epoch": 0.033042509745684054,
      "grad_norm": 4.6800665855407715,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 6.5155,
      "step": 89
    },
    {
      "epoch": 0.033413773900129944,
      "grad_norm": 4.469486713409424,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 6.2689,
      "step": 90
    },
    {
      "epoch": 0.03378503805457583,
      "grad_norm": 3.791959762573242,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 6.4441,
      "step": 91
    },
    {
      "epoch": 0.034156302209021716,
      "grad_norm": 3.8623321056365967,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 6.4281,
      "step": 92
    },
    {
      "epoch": 0.034527566363467606,
      "grad_norm": 6.107036113739014,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 6.3856,
      "step": 93
    },
    {
      "epoch": 0.034898830517913496,
      "grad_norm": 3.526797294616699,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 5.6764,
      "step": 94
    },
    {
      "epoch": 0.035270094672359385,
      "grad_norm": 4.093867301940918,
      "learning_rate": 7.596123493895991e-07,
      "loss": 5.6925,
      "step": 95
    },
    {
      "epoch": 0.035641358826805275,
      "grad_norm": 3.6119606494903564,
      "learning_rate": 4.865965629214819e-07,
      "loss": 5.3956,
      "step": 96
    },
    {
      "epoch": 0.03601262298125116,
      "grad_norm": 4.349273681640625,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 6.1551,
      "step": 97
    },
    {
      "epoch": 0.03638388713569705,
      "grad_norm": 3.9628746509552,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 5.6607,
      "step": 98
    },
    {
      "epoch": 0.03675515129014294,
      "grad_norm": 4.282620906829834,
      "learning_rate": 3.04586490452119e-08,
      "loss": 6.0429,
      "step": 99
    },
    {
      "epoch": 0.03712641544458883,
      "grad_norm": 4.604611873626709,
      "learning_rate": 0.0,
      "loss": 6.4466,
      "step": 100
    },
    {
      "epoch": 0.03712641544458883,
      "eval_loss": 1.5987274646759033,
      "eval_runtime": 565.1895,
      "eval_samples_per_second": 8.027,
      "eval_steps_per_second": 2.008,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5777468946317312e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}