{
  "best_metric": 0.1367991715669632,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.1764705882352942,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011764705882352941,
      "grad_norm": 172.13253784179688,
      "learning_rate": 1e-05,
      "loss": 12.8531,
      "step": 1
    },
    {
      "epoch": 0.011764705882352941,
      "eval_loss": 3.819585084915161,
      "eval_runtime": 10.017,
      "eval_samples_per_second": 14.276,
      "eval_steps_per_second": 3.594,
      "step": 1
    },
    {
      "epoch": 0.023529411764705882,
      "grad_norm": 235.67892456054688,
      "learning_rate": 2e-05,
      "loss": 16.4036,
      "step": 2
    },
    {
      "epoch": 0.03529411764705882,
      "grad_norm": 163.02357482910156,
      "learning_rate": 3e-05,
      "loss": 13.8009,
      "step": 3
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 89.59043884277344,
      "learning_rate": 4e-05,
      "loss": 11.6774,
      "step": 4
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 71.21575927734375,
      "learning_rate": 5e-05,
      "loss": 8.828,
      "step": 5
    },
    {
      "epoch": 0.07058823529411765,
      "grad_norm": 42.346920013427734,
      "learning_rate": 6e-05,
      "loss": 5.7373,
      "step": 6
    },
    {
      "epoch": 0.08235294117647059,
      "grad_norm": 33.6362190246582,
      "learning_rate": 7e-05,
      "loss": 4.772,
      "step": 7
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 27.008169174194336,
      "learning_rate": 8e-05,
      "loss": 3.1034,
      "step": 8
    },
    {
      "epoch": 0.10588235294117647,
      "grad_norm": 26.866989135742188,
      "learning_rate": 9e-05,
      "loss": 2.1755,
      "step": 9
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 12.166391372680664,
      "learning_rate": 0.0001,
      "loss": 0.9419,
      "step": 10
    },
    {
      "epoch": 0.12941176470588237,
      "grad_norm": 20.708179473876953,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8818,
      "step": 11
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 31.24081802368164,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.303,
      "step": 12
    },
    {
      "epoch": 0.15294117647058825,
      "grad_norm": 20.4725399017334,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7433,
      "step": 13
    },
    {
      "epoch": 0.16470588235294117,
      "grad_norm": 13.737116813659668,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.6282,
      "step": 14
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 10.137227058410645,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7848,
      "step": 15
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 12.233553886413574,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.5794,
      "step": 16
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.958011150360107,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2509,
      "step": 17
    },
    {
      "epoch": 0.21176470588235294,
      "grad_norm": 6.280331611633301,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.193,
      "step": 18
    },
    {
      "epoch": 0.2235294117647059,
      "grad_norm": 9.127641677856445,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1429,
      "step": 19
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 23.55068588256836,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.815,
      "step": 20
    },
    {
      "epoch": 0.24705882352941178,
      "grad_norm": 13.28919792175293,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.678,
      "step": 21
    },
    {
      "epoch": 0.25882352941176473,
      "grad_norm": 15.312559127807617,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.7833,
      "step": 22
    },
    {
      "epoch": 0.27058823529411763,
      "grad_norm": 14.847261428833008,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7155,
      "step": 23
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 10.071728706359863,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.2511,
      "step": 24
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 39.675540924072266,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6476,
      "step": 25
    },
    {
      "epoch": 0.3058823529411765,
      "grad_norm": 18.280935287475586,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5675,
      "step": 26
    },
    {
      "epoch": 0.3176470588235294,
      "grad_norm": 9.581499099731445,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7484,
      "step": 27
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 16.631563186645508,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8557,
      "step": 28
    },
    {
      "epoch": 0.3411764705882353,
      "grad_norm": 9.667623519897461,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.9532,
      "step": 29
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 11.223725318908691,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.2162,
      "step": 30
    },
    {
      "epoch": 0.36470588235294116,
      "grad_norm": 12.181304931640625,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.0404,
      "step": 31
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 7.326420307159424,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1361,
      "step": 32
    },
    {
      "epoch": 0.38823529411764707,
      "grad_norm": 9.077566146850586,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.9267,
      "step": 33
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.180811405181885,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2922,
      "step": 34
    },
    {
      "epoch": 0.4117647058823529,
      "grad_norm": 8.063867568969727,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2879,
      "step": 35
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 6.026397705078125,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7409,
      "step": 36
    },
    {
      "epoch": 0.43529411764705883,
      "grad_norm": 5.567332744598389,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6219,
      "step": 37
    },
    {
      "epoch": 0.4470588235294118,
      "grad_norm": 11.872861862182617,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2524,
      "step": 38
    },
    {
      "epoch": 0.4588235294117647,
      "grad_norm": 5.847661018371582,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.3725,
      "step": 39
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 8.535446166992188,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4886,
      "step": 40
    },
    {
      "epoch": 0.4823529411764706,
      "grad_norm": 3.4708619117736816,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.2828,
      "step": 41
    },
    {
      "epoch": 0.49411764705882355,
      "grad_norm": 6.165454387664795,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2493,
      "step": 42
    },
    {
      "epoch": 0.5058823529411764,
      "grad_norm": 16.55398178100586,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.7234,
      "step": 43
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 7.818714141845703,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.8453,
      "step": 44
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 10.525383949279785,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.8413,
      "step": 45
    },
    {
      "epoch": 0.5411764705882353,
      "grad_norm": 14.856411933898926,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.419,
      "step": 46
    },
    {
      "epoch": 0.5529411764705883,
      "grad_norm": 14.55447006225586,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.7946,
      "step": 47
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 8.109572410583496,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.8387,
      "step": 48
    },
    {
      "epoch": 0.5764705882352941,
      "grad_norm": 12.000244140625,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.1077,
      "step": 49
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 9.803535461425781,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7227,
      "step": 50
    },
    {
      "epoch": 0.5882352941176471,
      "eval_loss": 0.19544397294521332,
      "eval_runtime": 10.2993,
      "eval_samples_per_second": 13.884,
      "eval_steps_per_second": 3.495,
      "step": 50
    },
    {
      "epoch": 0.6,
      "grad_norm": 7.584646701812744,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.1064,
      "step": 51
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 10.298470497131348,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7911,
      "step": 52
    },
    {
      "epoch": 0.6235294117647059,
      "grad_norm": 6.717485427856445,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8214,
      "step": 53
    },
    {
      "epoch": 0.6352941176470588,
      "grad_norm": 7.507389068603516,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.6952,
      "step": 54
    },
    {
      "epoch": 0.6470588235294118,
      "grad_norm": 8.4017972946167,
      "learning_rate": 5e-05,
      "loss": 0.7036,
      "step": 55
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 3.5801243782043457,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3011,
      "step": 56
    },
    {
      "epoch": 0.6705882352941176,
      "grad_norm": 10.52881145477295,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.3615,
      "step": 57
    },
    {
      "epoch": 0.6823529411764706,
      "grad_norm": 12.233630180358887,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7692,
      "step": 58
    },
    {
      "epoch": 0.6941176470588235,
      "grad_norm": 9.595785140991211,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.4879,
      "step": 59
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 3.319401741027832,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.149,
      "step": 60
    },
    {
      "epoch": 0.7176470588235294,
      "grad_norm": 4.197874546051025,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.3863,
      "step": 61
    },
    {
      "epoch": 0.7294117647058823,
      "grad_norm": 8.175625801086426,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.8901,
      "step": 62
    },
    {
      "epoch": 0.7411764705882353,
      "grad_norm": 6.46556282043457,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1752,
      "step": 63
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 5.688372611999512,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9829,
      "step": 64
    },
    {
      "epoch": 0.7647058823529411,
      "grad_norm": 11.830146789550781,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.7664,
      "step": 65
    },
    {
      "epoch": 0.7764705882352941,
      "grad_norm": 6.605645656585693,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7277,
      "step": 66
    },
    {
      "epoch": 0.788235294117647,
      "grad_norm": 9.657796859741211,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4354,
      "step": 67
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.997437953948975,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.6186,
      "step": 68
    },
    {
      "epoch": 0.8117647058823529,
      "grad_norm": 9.167948722839355,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.7866,
      "step": 69
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 4.58889102935791,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4929,
      "step": 70
    },
    {
      "epoch": 0.8352941176470589,
      "grad_norm": 14.913512229919434,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.6052,
      "step": 71
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 9.060704231262207,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5963,
      "step": 72
    },
    {
      "epoch": 0.8588235294117647,
      "grad_norm": 5.501027584075928,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.652,
      "step": 73
    },
    {
      "epoch": 0.8705882352941177,
      "grad_norm": 6.683467388153076,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8559,
      "step": 74
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 5.693670749664307,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4063,
      "step": 75
    },
    {
      "epoch": 0.8941176470588236,
      "grad_norm": 4.536059379577637,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4056,
      "step": 76
    },
    {
      "epoch": 0.9058823529411765,
      "grad_norm": 10.254261016845703,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.6245,
      "step": 77
    },
    {
      "epoch": 0.9176470588235294,
      "grad_norm": 4.397399425506592,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.5528,
      "step": 78
    },
    {
      "epoch": 0.9294117647058824,
      "grad_norm": 4.43278694152832,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.434,
      "step": 79
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 4.597718715667725,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3085,
      "step": 80
    },
    {
      "epoch": 0.9529411764705882,
      "grad_norm": 3.2471067905426025,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1114,
      "step": 81
    },
    {
      "epoch": 0.9647058823529412,
      "grad_norm": 5.037919044494629,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1963,
      "step": 82
    },
    {
      "epoch": 0.9764705882352941,
      "grad_norm": 4.532823085784912,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2862,
      "step": 83
    },
    {
      "epoch": 0.9882352941176471,
      "grad_norm": 3.4642655849456787,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.213,
      "step": 84
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.7223033905029297,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2898,
      "step": 85
    },
    {
      "epoch": 1.011764705882353,
      "grad_norm": 5.067540645599365,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6626,
      "step": 86
    },
    {
      "epoch": 1.0235294117647058,
      "grad_norm": 4.71868896484375,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.4808,
      "step": 87
    },
    {
      "epoch": 1.035294117647059,
      "grad_norm": 5.0733747482299805,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.5184,
      "step": 88
    },
    {
      "epoch": 1.0470588235294118,
      "grad_norm": 4.773634910583496,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.7317,
      "step": 89
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 3.814397096633911,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.3467,
      "step": 90
    },
    {
      "epoch": 1.0705882352941176,
      "grad_norm": 2.942286491394043,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3476,
      "step": 91
    },
    {
      "epoch": 1.0823529411764705,
      "grad_norm": 3.1209030151367188,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.3037,
      "step": 92
    },
    {
      "epoch": 1.0941176470588236,
      "grad_norm": 3.3495614528656006,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.4087,
      "step": 93
    },
    {
      "epoch": 1.1058823529411765,
      "grad_norm": 10.110942840576172,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.6253,
      "step": 94
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 3.524946689605713,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.5602,
      "step": 95
    },
    {
      "epoch": 1.1294117647058823,
      "grad_norm": 2.1545052528381348,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2894,
      "step": 96
    },
    {
      "epoch": 1.1411764705882352,
      "grad_norm": 5.259888172149658,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.6811,
      "step": 97
    },
    {
      "epoch": 1.1529411764705881,
      "grad_norm": 2.7670738697052,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.3104,
      "step": 98
    },
    {
      "epoch": 1.1647058823529413,
      "grad_norm": 3.015961170196533,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.352,
      "step": 99
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 2.9505271911621094,
      "learning_rate": 0.0,
      "loss": 0.3282,
      "step": 100
    },
    {
      "epoch": 1.1764705882352942,
      "eval_loss": 0.1367991715669632,
      "eval_runtime": 10.285,
      "eval_samples_per_second": 13.904,
      "eval_steps_per_second": 3.5,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.4122951699857408e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}