{
  "best_metric": 1.1298441886901855,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.16891891891891891,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033783783783783786,
      "grad_norm": 3.826683282852173,
      "learning_rate": 5e-06,
      "loss": 1.4948,
      "step": 1
    },
    {
      "epoch": 0.0033783783783783786,
      "eval_loss": 2.366645336151123,
      "eval_runtime": 45.2663,
      "eval_samples_per_second": 11.024,
      "eval_steps_per_second": 5.523,
      "step": 1
    },
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 4.3141398429870605,
      "learning_rate": 1e-05,
      "loss": 1.6839,
      "step": 2
    },
    {
      "epoch": 0.010135135135135136,
      "grad_norm": 4.097876071929932,
      "learning_rate": 1.5e-05,
      "loss": 1.5752,
      "step": 3
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 4.010673522949219,
      "learning_rate": 2e-05,
      "loss": 1.5405,
      "step": 4
    },
    {
      "epoch": 0.016891891891891893,
      "grad_norm": 3.4538493156433105,
      "learning_rate": 2.5e-05,
      "loss": 1.5342,
      "step": 5
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 2.8183417320251465,
      "learning_rate": 3e-05,
      "loss": 1.3748,
      "step": 6
    },
    {
      "epoch": 0.02364864864864865,
      "grad_norm": 2.11971378326416,
      "learning_rate": 3.5e-05,
      "loss": 1.2566,
      "step": 7
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.5489553213119507,
      "learning_rate": 4e-05,
      "loss": 1.2766,
      "step": 8
    },
    {
      "epoch": 0.030405405405405407,
      "grad_norm": 1.3374286890029907,
      "learning_rate": 4.5e-05,
      "loss": 1.1642,
      "step": 9
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 1.4814637899398804,
      "learning_rate": 5e-05,
      "loss": 1.1382,
      "step": 10
    },
    {
      "epoch": 0.037162162162162164,
      "grad_norm": 1.3145912885665894,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.0861,
      "step": 11
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.5343668460845947,
      "learning_rate": 6e-05,
      "loss": 1.1041,
      "step": 12
    },
    {
      "epoch": 0.04391891891891892,
      "grad_norm": 1.3800190687179565,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.0442,
      "step": 13
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 1.1731736660003662,
      "learning_rate": 7e-05,
      "loss": 1.025,
      "step": 14
    },
    {
      "epoch": 0.05067567567567568,
      "grad_norm": 1.0756690502166748,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.077,
      "step": 15
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.126670479774475,
      "learning_rate": 8e-05,
      "loss": 1.0699,
      "step": 16
    },
    {
      "epoch": 0.057432432432432436,
      "grad_norm": 1.2052531242370605,
      "learning_rate": 8.5e-05,
      "loss": 1.0481,
      "step": 17
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 1.0971605777740479,
      "learning_rate": 9e-05,
      "loss": 1.1747,
      "step": 18
    },
    {
      "epoch": 0.06418918918918919,
      "grad_norm": 1.2357207536697388,
      "learning_rate": 9.5e-05,
      "loss": 1.2298,
      "step": 19
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 1.0170912742614746,
      "learning_rate": 0.0001,
      "loss": 0.963,
      "step": 20
    },
    {
      "epoch": 0.07094594594594594,
      "grad_norm": 1.040585994720459,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.0414,
      "step": 21
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 1.0849173069000244,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.9838,
      "step": 22
    },
    {
      "epoch": 0.0777027027027027,
      "grad_norm": 1.2504794597625732,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.132,
      "step": 23
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.1654671430587769,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1147,
      "step": 24
    },
    {
      "epoch": 0.08445945945945946,
      "grad_norm": 1.2212613821029663,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.0757,
      "step": 25
    },
    {
      "epoch": 0.08783783783783784,
      "grad_norm": 1.6377768516540527,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1149,
      "step": 26
    },
    {
      "epoch": 0.09121621621621621,
      "grad_norm": 1.4654461145401,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.0161,
      "step": 27
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 1.5125370025634766,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.1866,
      "step": 28
    },
    {
      "epoch": 0.09797297297297297,
      "grad_norm": 1.3907262086868286,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.0566,
      "step": 29
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 1.5802035331726074,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2932,
      "step": 30
    },
    {
      "epoch": 0.10472972972972973,
      "grad_norm": 1.4079865217208862,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.1993,
      "step": 31
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.471291184425354,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.2195,
      "step": 32
    },
    {
      "epoch": 0.11148648648648649,
      "grad_norm": 1.8197413682937622,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.1169,
      "step": 33
    },
    {
      "epoch": 0.11486486486486487,
      "grad_norm": 1.589645504951477,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.2959,
      "step": 34
    },
    {
      "epoch": 0.11824324324324324,
      "grad_norm": 1.9382315874099731,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.1117,
      "step": 35
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.9313946962356567,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1987,
      "step": 36
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.8206257820129395,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.1417,
      "step": 37
    },
    {
      "epoch": 0.12837837837837837,
      "grad_norm": 1.890135645866394,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.094,
      "step": 38
    },
    {
      "epoch": 0.13175675675675674,
      "grad_norm": 2.088564872741699,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.2143,
      "step": 39
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.9415384531021118,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.197,
      "step": 40
    },
    {
      "epoch": 0.13851351351351351,
      "grad_norm": 1.7540833950042725,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.0637,
      "step": 41
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 1.8551878929138184,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.0685,
      "step": 42
    },
    {
      "epoch": 0.14527027027027026,
      "grad_norm": 1.9881539344787598,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.081,
      "step": 43
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 2.670828104019165,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2052,
      "step": 44
    },
    {
      "epoch": 0.15202702702702703,
      "grad_norm": 2.176063060760498,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.856,
      "step": 45
    },
    {
      "epoch": 0.1554054054054054,
      "grad_norm": 2.3070170879364014,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.9129,
      "step": 46
    },
    {
      "epoch": 0.15878378378378377,
      "grad_norm": 2.7001495361328125,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.9219,
      "step": 47
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 2.964418888092041,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9442,
      "step": 48
    },
    {
      "epoch": 0.16554054054054054,
      "grad_norm": 3.5293803215026855,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.1814,
      "step": 49
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 3.7675538063049316,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9654,
      "step": 50
    },
    {
      "epoch": 0.16891891891891891,
      "eval_loss": 1.1298441886901855,
      "eval_runtime": 46.0078,
      "eval_samples_per_second": 10.846,
      "eval_steps_per_second": 5.434,
      "step": 50
    }
  ],
  "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": 7.855493374122394e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}