{
  "best_metric": 0.7181956171989441,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.816901408450704,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 26.567787170410156,
      "learning_rate": 5e-05,
      "loss": 17.9482,
      "step": 1
    },
    {
      "epoch": 0.056338028169014086,
      "eval_loss": 18.03241729736328,
      "eval_runtime": 2.1719,
      "eval_samples_per_second": 55.252,
      "eval_steps_per_second": 6.907,
      "step": 1
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 27.20028305053711,
      "learning_rate": 0.0001,
      "loss": 18.1536,
      "step": 2
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 25.63456916809082,
      "learning_rate": 9.989294616193017e-05,
      "loss": 17.3624,
      "step": 3
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 16.92221450805664,
      "learning_rate": 9.957224306869053e-05,
      "loss": 14.0564,
      "step": 4
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 11.986424446105957,
      "learning_rate": 9.903926402016153e-05,
      "loss": 12.4003,
      "step": 5
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 12.184904098510742,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.7638,
      "step": 6
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 13.910933494567871,
      "learning_rate": 9.73465064747553e-05,
      "loss": 9.4848,
      "step": 7
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 15.018721580505371,
      "learning_rate": 9.619397662556435e-05,
      "loss": 8.0346,
      "step": 8
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 12.815889358520508,
      "learning_rate": 9.484363707663442e-05,
      "loss": 6.8596,
      "step": 9
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 15.688509941101074,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.1236,
      "step": 10
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 20.215763092041016,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.8695,
      "step": 11
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 21.569995880126953,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.2979,
      "step": 12
    },
    {
      "epoch": 0.7323943661971831,
      "grad_norm": 8.532081604003906,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3443,
      "step": 13
    },
    {
      "epoch": 0.7887323943661971,
      "grad_norm": 4.722276210784912,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.0925,
      "step": 14
    },
    {
      "epoch": 0.8450704225352113,
      "grad_norm": 5.054727554321289,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.0463,
      "step": 15
    },
    {
      "epoch": 0.9014084507042254,
      "grad_norm": 3.567676544189453,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.893,
      "step": 16
    },
    {
      "epoch": 0.9577464788732394,
      "grad_norm": 1.9127579927444458,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.9702,
      "step": 17
    },
    {
      "epoch": 1.0140845070422535,
      "grad_norm": 1.7992066144943237,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0372,
      "step": 18
    },
    {
      "epoch": 1.0704225352112675,
      "grad_norm": 1.826777458190918,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.7833,
      "step": 19
    },
    {
      "epoch": 1.1267605633802817,
      "grad_norm": 2.6626498699188232,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.764,
      "step": 20
    },
    {
      "epoch": 1.1830985915492958,
      "grad_norm": 1.1777507066726685,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7185,
      "step": 21
    },
    {
      "epoch": 1.2394366197183098,
      "grad_norm": 2.1660730838775635,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8506,
      "step": 22
    },
    {
      "epoch": 1.295774647887324,
      "grad_norm": 2.1182351112365723,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8022,
      "step": 23
    },
    {
      "epoch": 1.352112676056338,
      "grad_norm": 1.7126965522766113,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.7865,
      "step": 24
    },
    {
      "epoch": 1.408450704225352,
      "grad_norm": 1.6322726011276245,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.774,
      "step": 25
    },
    {
      "epoch": 1.408450704225352,
      "eval_loss": 0.7551879286766052,
      "eval_runtime": 2.1696,
      "eval_samples_per_second": 55.311,
      "eval_steps_per_second": 6.914,
      "step": 25
    },
    {
      "epoch": 1.4647887323943662,
      "grad_norm": 1.9145314693450928,
      "learning_rate": 5e-05,
      "loss": 0.7969,
      "step": 26
    },
    {
      "epoch": 1.5211267605633803,
      "grad_norm": 1.4079281091690063,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.7581,
      "step": 27
    },
    {
      "epoch": 1.5774647887323945,
      "grad_norm": 1.2622559070587158,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.7662,
      "step": 28
    },
    {
      "epoch": 1.6338028169014085,
      "grad_norm": 1.7799396514892578,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.7775,
      "step": 29
    },
    {
      "epoch": 1.6901408450704225,
      "grad_norm": 0.8976244330406189,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7749,
      "step": 30
    },
    {
      "epoch": 1.7464788732394365,
      "grad_norm": 0.7658373713493347,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.7603,
      "step": 31
    },
    {
      "epoch": 1.8028169014084507,
      "grad_norm": 0.7728968858718872,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7317,
      "step": 32
    },
    {
      "epoch": 1.8591549295774648,
      "grad_norm": 1.6836856603622437,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.7531,
      "step": 33
    },
    {
      "epoch": 1.915492957746479,
      "grad_norm": 1.2422633171081543,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7713,
      "step": 34
    },
    {
      "epoch": 1.971830985915493,
      "grad_norm": 1.2235596179962158,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.795,
      "step": 35
    },
    {
      "epoch": 2.028169014084507,
      "grad_norm": 1.3551065921783447,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.84,
      "step": 36
    },
    {
      "epoch": 2.084507042253521,
      "grad_norm": 1.9961484670639038,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.7307,
      "step": 37
    },
    {
      "epoch": 2.140845070422535,
      "grad_norm": 1.0495152473449707,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7203,
      "step": 38
    },
    {
      "epoch": 2.1971830985915495,
      "grad_norm": 1.5394065380096436,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.7215,
      "step": 39
    },
    {
      "epoch": 2.2535211267605635,
      "grad_norm": 1.6117628812789917,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.7332,
      "step": 40
    },
    {
      "epoch": 2.3098591549295775,
      "grad_norm": 1.222669243812561,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.7391,
      "step": 41
    },
    {
      "epoch": 2.3661971830985915,
      "grad_norm": 1.240601658821106,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.7892,
      "step": 42
    },
    {
      "epoch": 2.4225352112676055,
      "grad_norm": 1.0177549123764038,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.7369,
      "step": 43
    },
    {
      "epoch": 2.4788732394366195,
      "grad_norm": 1.381874680519104,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7961,
      "step": 44
    },
    {
      "epoch": 2.535211267605634,
      "grad_norm": 1.1401207447052002,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.7321,
      "step": 45
    },
    {
      "epoch": 2.591549295774648,
      "grad_norm": 1.0625675916671753,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.7325,
      "step": 46
    },
    {
      "epoch": 2.647887323943662,
      "grad_norm": 1.2292084693908691,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.7367,
      "step": 47
    },
    {
      "epoch": 2.704225352112676,
      "grad_norm": 1.9565144777297974,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8171,
      "step": 48
    },
    {
      "epoch": 2.76056338028169,
      "grad_norm": 1.4623973369598389,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7085,
      "step": 49
    },
    {
      "epoch": 2.816901408450704,
      "grad_norm": 0.729285717010498,
      "learning_rate": 0.0,
      "loss": 0.7502,
      "step": 50
    },
    {
      "epoch": 2.816901408450704,
      "eval_loss": 0.7181956171989441,
      "eval_runtime": 2.1694,
      "eval_samples_per_second": 55.315,
      "eval_steps_per_second": 6.914,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 2.229252309123072e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}