{
  "best_metric": 10.366877555847168,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 2.564102564102564,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.024028141051530838,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.3795,
      "step": 1
    },
    {
      "epoch": 0.03418803418803419,
      "eval_loss": 10.37679672241211,
      "eval_runtime": 0.1087,
      "eval_samples_per_second": 459.817,
      "eval_steps_per_second": 119.552,
      "step": 1
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.027240164577960968,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.379,
      "step": 2
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.027441630139946938,
      "learning_rate": 0.0001,
      "loss": 10.3783,
      "step": 3
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.02922813594341278,
      "learning_rate": 9.99571699711836e-05,
      "loss": 10.378,
      "step": 4
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.03131942078471184,
      "learning_rate": 9.982876141412856e-05,
      "loss": 10.3768,
      "step": 5
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.04379850625991821,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3738,
      "step": 6
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.0539846196770668,
      "learning_rate": 9.931634888554937e-05,
      "loss": 10.3747,
      "step": 7
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.02217571809887886,
      "learning_rate": 9.893332032039701e-05,
      "loss": 10.3786,
      "step": 8
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.02530466951429844,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3781,
      "step": 9
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.027638306841254234,
      "learning_rate": 9.791726278367022e-05,
      "loss": 10.3776,
      "step": 10
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.029069717973470688,
      "learning_rate": 9.728616793536588e-05,
      "loss": 10.3769,
      "step": 11
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.03112073801457882,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3757,
      "step": 12
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.03275328129529953,
      "learning_rate": 9.578385041664925e-05,
      "loss": 10.376,
      "step": 13
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.04708424210548401,
      "learning_rate": 9.491548749301997e-05,
      "loss": 10.3737,
      "step": 14
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.024200988933444023,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3772,
      "step": 15
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.025222577154636383,
      "learning_rate": 9.295261506157986e-05,
      "loss": 10.3776,
      "step": 16
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.029448403045535088,
      "learning_rate": 9.186184199300464e-05,
      "loss": 10.3763,
      "step": 17
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.03146638721227646,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3758,
      "step": 18
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.03456265106797218,
      "learning_rate": 8.947199994035401e-05,
      "loss": 10.375,
      "step": 19
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.03508660942316055,
      "learning_rate": 8.817748015645558e-05,
      "loss": 10.3738,
      "step": 20
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.05112173408269882,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3729,
      "step": 21
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.027508389204740524,
      "learning_rate": 8.540155934270471e-05,
      "loss": 10.3757,
      "step": 22
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.03241690620779991,
      "learning_rate": 8.392544243589427e-05,
      "loss": 10.3762,
      "step": 23
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.03374025970697403,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3759,
      "step": 24
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.03651708737015724,
      "learning_rate": 8.081093963579707e-05,
      "loss": 10.3749,
      "step": 25
    },
    {
      "epoch": 0.8547008547008547,
      "eval_loss": 10.37341022491455,
      "eval_runtime": 0.0998,
      "eval_samples_per_second": 500.815,
      "eval_steps_per_second": 130.212,
      "step": 25
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.03954649716615677,
      "learning_rate": 7.917848237560709e-05,
      "loss": 10.3741,
      "step": 26
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.04464032128453255,
      "learning_rate": 7.75e-05,
      "loss": 10.3713,
      "step": 27
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.059212006628513336,
      "learning_rate": 7.577868759557654e-05,
      "loss": 10.3721,
      "step": 28
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.0634295716881752,
      "learning_rate": 7.401782177833148e-05,
      "loss": 10.3694,
      "step": 29
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.06830056756734848,
      "learning_rate": 7.222075445642904e-05,
      "loss": 18.6043,
      "step": 30
    },
    {
      "epoch": 1.0598290598290598,
      "grad_norm": 0.038523830473423004,
      "learning_rate": 7.03909064496551e-05,
      "loss": 10.0611,
      "step": 31
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.04325374588370323,
      "learning_rate": 6.853176097769229e-05,
      "loss": 10.396,
      "step": 32
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.04963960871100426,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.5299,
      "step": 33
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.04767056554555893,
      "learning_rate": 6.473978262721463e-05,
      "loss": 10.4291,
      "step": 34
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 0.05898962542414665,
      "learning_rate": 6.281416799501188e-05,
      "loss": 10.5953,
      "step": 35
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.0721501037478447,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3811,
      "step": 36
    },
    {
      "epoch": 1.264957264957265,
      "grad_norm": 0.04224683344364166,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 9.4466,
      "step": 37
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.05125311017036438,
      "learning_rate": 5.696287243144013e-05,
      "loss": 10.8119,
      "step": 38
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.051614489406347275,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.4335,
      "step": 39
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.06009482964873314,
      "learning_rate": 5.303712756855988e-05,
      "loss": 10.5632,
      "step": 40
    },
    {
      "epoch": 1.4017094017094016,
      "grad_norm": 0.06151549890637398,
      "learning_rate": 5.107799157635538e-05,
      "loss": 10.3618,
      "step": 41
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.07110217213630676,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.5662,
      "step": 42
    },
    {
      "epoch": 1.4700854700854702,
      "grad_norm": 0.09137392044067383,
      "learning_rate": 4.718583200498814e-05,
      "loss": 10.3167,
      "step": 43
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.044047337025403976,
      "learning_rate": 4.526021737278538e-05,
      "loss": 8.1399,
      "step": 44
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.06453102082014084,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 12.2658,
      "step": 45
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.06560295820236206,
      "learning_rate": 4.146823902230772e-05,
      "loss": 10.2777,
      "step": 46
    },
    {
      "epoch": 1.606837606837607,
      "grad_norm": 0.06661686301231384,
      "learning_rate": 3.960909355034491e-05,
      "loss": 10.5795,
      "step": 47
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.0714309886097908,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.4365,
      "step": 48
    },
    {
      "epoch": 1.6752136752136753,
      "grad_norm": 0.0735783651471138,
      "learning_rate": 3.598217822166854e-05,
      "loss": 10.5224,
      "step": 49
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.0946367010474205,
      "learning_rate": 3.422131240442349e-05,
      "loss": 10.2449,
      "step": 50
    },
    {
      "epoch": 1.7094017094017095,
      "eval_loss": 10.369140625,
      "eval_runtime": 0.0971,
      "eval_samples_per_second": 515.162,
      "eval_steps_per_second": 133.942,
      "step": 50
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.04459521546959877,
      "learning_rate": 3.250000000000001e-05,
      "loss": 4.0781,
      "step": 51
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.09696029871702194,
      "learning_rate": 3.082151762439293e-05,
      "loss": 16.5477,
      "step": 52
    },
    {
      "epoch": 1.811965811965812,
      "grad_norm": 0.07526196539402008,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 10.3167,
      "step": 53
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.07211493700742722,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3497,
      "step": 54
    },
    {
      "epoch": 1.8803418803418803,
      "grad_norm": 0.0758114755153656,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 10.5534,
      "step": 55
    },
    {
      "epoch": 1.9145299145299144,
      "grad_norm": 0.08330105990171432,
      "learning_rate": 2.459844065729529e-05,
      "loss": 10.3561,
      "step": 56
    },
    {
      "epoch": 1.9487179487179487,
      "grad_norm": 0.1038593128323555,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.4654,
      "step": 57
    },
    {
      "epoch": 1.982905982905983,
      "grad_norm": 0.10510390996932983,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 10.8554,
      "step": 58
    },
    {
      "epoch": 2.017094017094017,
      "grad_norm": 0.12666811048984528,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 17.6932,
      "step": 59
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.07206396758556366,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.1238,
      "step": 60
    },
    {
      "epoch": 2.0854700854700856,
      "grad_norm": 0.08021845668554306,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 10.3257,
      "step": 61
    },
    {
      "epoch": 2.1196581196581197,
      "grad_norm": 0.0848311111330986,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 10.6517,
      "step": 62
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.08744092285633087,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.3375,
      "step": 63
    },
    {
      "epoch": 2.1880341880341883,
      "grad_norm": 0.09486929327249527,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 10.7017,
      "step": 64
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.11365848779678345,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 10.3117,
      "step": 65
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.0729779526591301,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 8.8041,
      "step": 66
    },
    {
      "epoch": 2.2905982905982905,
      "grad_norm": 0.08433752506971359,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 11.3562,
      "step": 67
    },
    {
      "epoch": 2.324786324786325,
      "grad_norm": 0.09108246862888336,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 10.4199,
      "step": 68
    },
    {
      "epoch": 2.358974358974359,
      "grad_norm": 0.0905907079577446,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.6594,
      "step": 69
    },
    {
      "epoch": 2.393162393162393,
      "grad_norm": 0.09025926142930984,
      "learning_rate": 1.1066679679603e-05,
      "loss": 10.3229,
      "step": 70
    },
    {
      "epoch": 2.427350427350427,
      "grad_norm": 0.09516981989145279,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 10.6938,
      "step": 71
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.11765694618225098,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.066,
      "step": 72
    },
    {
      "epoch": 2.4957264957264957,
      "grad_norm": 0.058387916535139084,
      "learning_rate": 1.017123858587145e-05,
      "loss": 5.3975,
      "step": 73
    },
    {
      "epoch": 2.52991452991453,
      "grad_norm": 0.10583050549030304,
      "learning_rate": 1.00428300288164e-05,
      "loss": 15.0466,
      "step": 74
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.0866541638970375,
      "learning_rate": 1e-05,
      "loss": 10.3698,
      "step": 75
    },
    {
      "epoch": 2.564102564102564,
      "eval_loss": 10.366877555847168,
      "eval_runtime": 0.101,
      "eval_samples_per_second": 495.053,
      "eval_steps_per_second": 128.714,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 64285739581440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}