{
  "best_metric": 1.0515674352645874,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.1869436201780414,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02373887240356083,
      "grad_norm": 1.5239546298980713,
      "learning_rate": 5e-05,
      "loss": 1.9376,
      "step": 1
    },
    {
      "epoch": 0.02373887240356083,
      "eval_loss": 3.6803083419799805,
      "eval_runtime": 3.8162,
      "eval_samples_per_second": 13.102,
      "eval_steps_per_second": 3.406,
      "step": 1
    },
    {
      "epoch": 0.04747774480712166,
      "grad_norm": 1.5886269807815552,
      "learning_rate": 0.0001,
      "loss": 2.2181,
      "step": 2
    },
    {
      "epoch": 0.0712166172106825,
      "grad_norm": 1.9380593299865723,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.2216,
      "step": 3
    },
    {
      "epoch": 0.09495548961424333,
      "grad_norm": 2.2847750186920166,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.321,
      "step": 4
    },
    {
      "epoch": 0.11869436201780416,
      "grad_norm": 1.8313699960708618,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.0965,
      "step": 5
    },
    {
      "epoch": 0.142433234421365,
      "grad_norm": 1.7363648414611816,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.1055,
      "step": 6
    },
    {
      "epoch": 0.1661721068249258,
      "grad_norm": 2.1500160694122314,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.3069,
      "step": 7
    },
    {
      "epoch": 0.18991097922848665,
      "grad_norm": 1.8061026334762573,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.3819,
      "step": 8
    },
    {
      "epoch": 0.21364985163204747,
      "grad_norm": 2.687041997909546,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.2735,
      "step": 9
    },
    {
      "epoch": 0.23738872403560832,
      "grad_norm": 2.061250925064087,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.4429,
      "step": 10
    },
    {
      "epoch": 0.26112759643916916,
      "grad_norm": 3.102854013442993,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.6455,
      "step": 11
    },
    {
      "epoch": 0.28486646884273,
      "grad_norm": 2.094451904296875,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.6517,
      "step": 12
    },
    {
      "epoch": 0.3086053412462908,
      "grad_norm": 1.6486390829086304,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.5262,
      "step": 13
    },
    {
      "epoch": 0.3323442136498516,
      "grad_norm": 1.2995418310165405,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.5157,
      "step": 14
    },
    {
      "epoch": 0.3560830860534125,
      "grad_norm": 1.1857811212539673,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.4002,
      "step": 15
    },
    {
      "epoch": 0.3798219584569733,
      "grad_norm": 1.467132806777954,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.5701,
      "step": 16
    },
    {
      "epoch": 0.4035608308605341,
      "grad_norm": 1.4040600061416626,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.5287,
      "step": 17
    },
    {
      "epoch": 0.42729970326409494,
      "grad_norm": 1.819309949874878,
      "learning_rate": 7.75e-05,
      "loss": 1.7185,
      "step": 18
    },
    {
      "epoch": 0.45103857566765576,
      "grad_norm": 1.787257194519043,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.7469,
      "step": 19
    },
    {
      "epoch": 0.47477744807121663,
      "grad_norm": 1.8518139123916626,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.8846,
      "step": 20
    },
    {
      "epoch": 0.49851632047477745,
      "grad_norm": 2.8248465061187744,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.9882,
      "step": 21
    },
    {
      "epoch": 0.5222551928783383,
      "grad_norm": 2.2027037143707275,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.1748,
      "step": 22
    },
    {
      "epoch": 0.5459940652818991,
      "grad_norm": 1.6065067052841187,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.1157,
      "step": 23
    },
    {
      "epoch": 0.56973293768546,
      "grad_norm": 1.5175880193710327,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.1018,
      "step": 24
    },
    {
      "epoch": 0.5934718100890207,
      "grad_norm": 1.377229928970337,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.1484,
      "step": 25
    },
    {
      "epoch": 0.5934718100890207,
      "eval_loss": 1.5251476764678955,
      "eval_runtime": 3.4747,
      "eval_samples_per_second": 14.39,
      "eval_steps_per_second": 3.741,
      "step": 25
    },
    {
      "epoch": 0.6172106824925816,
      "grad_norm": 1.4022682905197144,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.1673,
      "step": 26
    },
    {
      "epoch": 0.6409495548961425,
      "grad_norm": 1.360411286354065,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.2339,
      "step": 27
    },
    {
      "epoch": 0.6646884272997032,
      "grad_norm": 1.5245141983032227,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.2553,
      "step": 28
    },
    {
      "epoch": 0.6884272997032641,
      "grad_norm": 1.5429983139038086,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.3811,
      "step": 29
    },
    {
      "epoch": 0.712166172106825,
      "grad_norm": 1.6180874109268188,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.0528,
      "step": 30
    },
    {
      "epoch": 0.7359050445103857,
      "grad_norm": 2.2861862182617188,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.3014,
      "step": 31
    },
    {
      "epoch": 0.7596439169139466,
      "grad_norm": 2.1236374378204346,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.0626,
      "step": 32
    },
    {
      "epoch": 0.7833827893175074,
      "grad_norm": 1.7430927753448486,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.9247,
      "step": 33
    },
    {
      "epoch": 0.8071216617210683,
      "grad_norm": 1.372740387916565,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.959,
      "step": 34
    },
    {
      "epoch": 0.8308605341246291,
      "grad_norm": 1.3866841793060303,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.8239,
      "step": 35
    },
    {
      "epoch": 0.8545994065281899,
      "grad_norm": 1.8122707605361938,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.9378,
      "step": 36
    },
    {
      "epoch": 0.8783382789317508,
      "grad_norm": 1.5954991579055786,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.0473,
      "step": 37
    },
    {
      "epoch": 0.9020771513353115,
      "grad_norm": 1.5977816581726074,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.9681,
      "step": 38
    },
    {
      "epoch": 0.9258160237388724,
      "grad_norm": 1.6187400817871094,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.9797,
      "step": 39
    },
    {
      "epoch": 0.9495548961424333,
      "grad_norm": 1.8072162866592407,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.8826,
      "step": 40
    },
    {
      "epoch": 0.973293768545994,
      "grad_norm": 2.2397186756134033,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.0376,
      "step": 41
    },
    {
      "epoch": 0.9970326409495549,
      "grad_norm": 2.8178083896636963,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.2337,
      "step": 42
    },
    {
      "epoch": 1.0207715133531157,
      "grad_norm": 4.646073818206787,
      "learning_rate": 1.464072663102903e-05,
      "loss": 2.0149,
      "step": 43
    },
    {
      "epoch": 1.0445103857566767,
      "grad_norm": 1.2922364473342896,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.8055,
      "step": 44
    },
    {
      "epoch": 1.0682492581602374,
      "grad_norm": 1.1570236682891846,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.7687,
      "step": 45
    },
    {
      "epoch": 1.0919881305637982,
      "grad_norm": 1.2567687034606934,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.7373,
      "step": 46
    },
    {
      "epoch": 1.115727002967359,
      "grad_norm": 1.6276962757110596,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.8683,
      "step": 47
    },
    {
      "epoch": 1.13946587537092,
      "grad_norm": 1.4849191904067993,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.9161,
      "step": 48
    },
    {
      "epoch": 1.1632047477744807,
      "grad_norm": 1.447176456451416,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.8083,
      "step": 49
    },
    {
      "epoch": 1.1869436201780414,
      "grad_norm": 1.6718727350234985,
      "learning_rate": 1e-05,
      "loss": 0.9247,
      "step": 50
    },
    {
      "epoch": 1.1869436201780414,
      "eval_loss": 1.0515674352645874,
      "eval_runtime": 3.4991,
      "eval_samples_per_second": 14.29,
      "eval_steps_per_second": 3.715,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}