{
  "best_metric": 2.0915205478668213,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.35650623885918004,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0071301247771836,
      "grad_norm": 1.5173163414001465,
      "learning_rate": 2e-05,
      "loss": 2.8537,
      "step": 1
    },
    {
      "epoch": 0.0071301247771836,
      "eval_loss": 3.90462064743042,
      "eval_runtime": 1.5866,
      "eval_samples_per_second": 148.747,
      "eval_steps_per_second": 18.908,
      "step": 1
    },
    {
      "epoch": 0.0142602495543672,
      "grad_norm": 1.3383238315582275,
      "learning_rate": 4e-05,
      "loss": 2.8749,
      "step": 2
    },
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 1.6879465579986572,
      "learning_rate": 6e-05,
      "loss": 2.9998,
      "step": 3
    },
    {
      "epoch": 0.0285204991087344,
      "grad_norm": 1.7708063125610352,
      "learning_rate": 8e-05,
      "loss": 3.06,
      "step": 4
    },
    {
      "epoch": 0.035650623885918005,
      "grad_norm": 1.486020803451538,
      "learning_rate": 0.0001,
      "loss": 2.9697,
      "step": 5
    },
    {
      "epoch": 0.0427807486631016,
      "grad_norm": 1.6805022954940796,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.8983,
      "step": 6
    },
    {
      "epoch": 0.049910873440285206,
      "grad_norm": 1.4022825956344604,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.016,
      "step": 7
    },
    {
      "epoch": 0.0570409982174688,
      "grad_norm": 1.6186312437057495,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.8773,
      "step": 8
    },
    {
      "epoch": 0.06417112299465241,
      "grad_norm": 1.357567310333252,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.9339,
      "step": 9
    },
    {
      "epoch": 0.07130124777183601,
      "grad_norm": 1.825875997543335,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.0052,
      "step": 10
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 1.7561568021774292,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.8068,
      "step": 11
    },
    {
      "epoch": 0.0855614973262032,
      "grad_norm": 1.8440032005310059,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.0174,
      "step": 12
    },
    {
      "epoch": 0.09269162210338681,
      "grad_norm": 1.3899633884429932,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.9899,
      "step": 13
    },
    {
      "epoch": 0.09982174688057041,
      "grad_norm": 1.4993560314178467,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.8701,
      "step": 14
    },
    {
      "epoch": 0.10695187165775401,
      "grad_norm": 1.4138418436050415,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.6803,
      "step": 15
    },
    {
      "epoch": 0.1140819964349376,
      "grad_norm": 1.846754789352417,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.9407,
      "step": 16
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.996471881866455,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.2487,
      "step": 17
    },
    {
      "epoch": 0.12834224598930483,
      "grad_norm": 2.1197140216827393,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.1799,
      "step": 18
    },
    {
      "epoch": 0.1354723707664884,
      "grad_norm": 1.753442406654358,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.7721,
      "step": 19
    },
    {
      "epoch": 0.14260249554367202,
      "grad_norm": 1.6010884046554565,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.5523,
      "step": 20
    },
    {
      "epoch": 0.1497326203208556,
      "grad_norm": 1.6448290348052979,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.9927,
      "step": 21
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 1.990535020828247,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.6969,
      "step": 22
    },
    {
      "epoch": 0.16399286987522282,
      "grad_norm": 1.4850422143936157,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.6551,
      "step": 23
    },
    {
      "epoch": 0.1711229946524064,
      "grad_norm": 1.9399062395095825,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.0327,
      "step": 24
    },
    {
      "epoch": 0.17825311942959002,
      "grad_norm": 2.076749086380005,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.104,
      "step": 25
    },
    {
      "epoch": 0.17825311942959002,
      "eval_loss": 2.4427363872528076,
      "eval_runtime": 1.5836,
      "eval_samples_per_second": 149.028,
      "eval_steps_per_second": 18.944,
      "step": 25
    },
    {
      "epoch": 0.18538324420677363,
      "grad_norm": 1.5658035278320312,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.5442,
      "step": 26
    },
    {
      "epoch": 0.1925133689839572,
      "grad_norm": 1.6989140510559082,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.6993,
      "step": 27
    },
    {
      "epoch": 0.19964349376114082,
      "grad_norm": 2.7406604290008545,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.7101,
      "step": 28
    },
    {
      "epoch": 0.20677361853832443,
      "grad_norm": 2.6439878940582275,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.4467,
      "step": 29
    },
    {
      "epoch": 0.21390374331550802,
      "grad_norm": 3.644503593444824,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.9153,
      "step": 30
    },
    {
      "epoch": 0.22103386809269163,
      "grad_norm": 2.4745495319366455,
      "learning_rate": 3.790390522001662e-05,
      "loss": 3.6534,
      "step": 31
    },
    {
      "epoch": 0.2281639928698752,
      "grad_norm": 4.7882866859436035,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.7345,
      "step": 32
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 2.7473108768463135,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.8752,
      "step": 33
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 3.205869674682617,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.8759,
      "step": 34
    },
    {
      "epoch": 0.24955436720142601,
      "grad_norm": 3.5639467239379883,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.4342,
      "step": 35
    },
    {
      "epoch": 0.25668449197860965,
      "grad_norm": 2.509160041809082,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9873,
      "step": 36
    },
    {
      "epoch": 0.2638146167557932,
      "grad_norm": 2.184943914413452,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.9518,
      "step": 37
    },
    {
      "epoch": 0.2709447415329768,
      "grad_norm": 1.8048384189605713,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.8759,
      "step": 38
    },
    {
      "epoch": 0.27807486631016043,
      "grad_norm": 2.1149380207061768,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.8156,
      "step": 39
    },
    {
      "epoch": 0.28520499108734404,
      "grad_norm": 1.9589015245437622,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.7161,
      "step": 40
    },
    {
      "epoch": 0.29233511586452765,
      "grad_norm": 2.062096357345581,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4362,
      "step": 41
    },
    {
      "epoch": 0.2994652406417112,
      "grad_norm": 2.128787040710449,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.7625,
      "step": 42
    },
    {
      "epoch": 0.3065953654188948,
      "grad_norm": 2.045071840286255,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.68,
      "step": 43
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 1.7764232158660889,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.8457,
      "step": 44
    },
    {
      "epoch": 0.32085561497326204,
      "grad_norm": 1.7600865364074707,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.8762,
      "step": 45
    },
    {
      "epoch": 0.32798573975044565,
      "grad_norm": 1.417314887046814,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.478,
      "step": 46
    },
    {
      "epoch": 0.33511586452762926,
      "grad_norm": 2.077120065689087,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.0639,
      "step": 47
    },
    {
      "epoch": 0.3422459893048128,
      "grad_norm": 1.3124065399169922,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.8697,
      "step": 48
    },
    {
      "epoch": 0.3493761140819964,
      "grad_norm": 1.1877974271774292,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.7146,
      "step": 49
    },
    {
      "epoch": 0.35650623885918004,
      "grad_norm": 1.3717702627182007,
      "learning_rate": 0.0,
      "loss": 1.8756,
      "step": 50
    },
    {
      "epoch": 0.35650623885918004,
      "eval_loss": 2.0915205478668213,
      "eval_runtime": 1.5783,
      "eval_samples_per_second": 149.529,
      "eval_steps_per_second": 19.008,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 618044011315200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}