{
  "best_metric": 1.470105528831482,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0285714285714285,
  "eval_steps": 50,
  "global_step": 53,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 7.248203277587891,
      "learning_rate": 1e-05,
      "loss": 2.647,
      "step": 1
    },
    {
      "epoch": 0.05714285714285714,
      "eval_loss": 3.8393256664276123,
      "eval_runtime": 0.5254,
      "eval_samples_per_second": 57.097,
      "eval_steps_per_second": 15.226,
      "step": 1
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 18.592464447021484,
      "learning_rate": 2e-05,
      "loss": 3.1974,
      "step": 2
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 52.620887756347656,
      "learning_rate": 3e-05,
      "loss": 5.3147,
      "step": 3
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 40.471134185791016,
      "learning_rate": 4e-05,
      "loss": 5.3507,
      "step": 4
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.791353940963745,
      "learning_rate": 5e-05,
      "loss": 2.3549,
      "step": 5
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 4.121531963348389,
      "learning_rate": 6e-05,
      "loss": 2.4909,
      "step": 6
    },
    {
      "epoch": 0.4,
      "grad_norm": 17.40095329284668,
      "learning_rate": 7e-05,
      "loss": 4.4181,
      "step": 7
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 18.52124786376953,
      "learning_rate": 8e-05,
      "loss": 4.5092,
      "step": 8
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 1.829758644104004,
      "learning_rate": 9e-05,
      "loss": 2.1481,
      "step": 9
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.442340850830078,
      "learning_rate": 0.0001,
      "loss": 2.1406,
      "step": 10
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 5.458558559417725,
      "learning_rate": 9.986661418317759e-05,
      "loss": 2.2616,
      "step": 11
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 11.321267127990723,
      "learning_rate": 9.946716840375551e-05,
      "loss": 3.0082,
      "step": 12
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 1.7342873811721802,
      "learning_rate": 9.880379387779637e-05,
      "loss": 1.8843,
      "step": 13
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.1906113624572754,
      "learning_rate": 9.78800299954203e-05,
      "loss": 1.8916,
      "step": 14
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 4.323538780212402,
      "learning_rate": 9.67008054366274e-05,
      "loss": 1.9801,
      "step": 15
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 5.735661029815674,
      "learning_rate": 9.527241187465734e-05,
      "loss": 1.729,
      "step": 16
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 2.082949638366699,
      "learning_rate": 9.360247040719039e-05,
      "loss": 1.8639,
      "step": 17
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 6.3943190574646,
      "learning_rate": 9.16998908944939e-05,
      "loss": 2.438,
      "step": 18
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 1.7607228755950928,
      "learning_rate": 8.957482442146272e-05,
      "loss": 1.6208,
      "step": 19
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 3.193545341491699,
      "learning_rate": 8.72386091371891e-05,
      "loss": 1.682,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.23166561126709,
      "learning_rate": 8.47037097610317e-05,
      "loss": 0.9162,
      "step": 21
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 3.0824878215789795,
      "learning_rate": 8.198365107794457e-05,
      "loss": 1.5992,
      "step": 22
    },
    {
      "epoch": 1.3142857142857143,
      "grad_norm": 1.696791172027588,
      "learning_rate": 7.909294577789766e-05,
      "loss": 1.4764,
      "step": 23
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 2.419218063354492,
      "learning_rate": 7.604701702439651e-05,
      "loss": 1.2588,
      "step": 24
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 3.271068572998047,
      "learning_rate": 7.286211616523193e-05,
      "loss": 0.8795,
      "step": 25
    },
    {
      "epoch": 1.4857142857142858,
      "grad_norm": 4.406923294067383,
      "learning_rate": 6.95552360245078e-05,
      "loss": 1.4232,
      "step": 26
    },
    {
      "epoch": 1.5428571428571427,
      "grad_norm": 1.7464239597320557,
      "learning_rate": 6.614402023857232e-05,
      "loss": 1.5745,
      "step": 27
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.5956149101257324,
      "learning_rate": 6.264666911958404e-05,
      "loss": 0.9325,
      "step": 28
    },
    {
      "epoch": 1.657142857142857,
      "grad_norm": 3.6733956336975098,
      "learning_rate": 5.908184254897182e-05,
      "loss": 1.0339,
      "step": 29
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 2.5009891986846924,
      "learning_rate": 5.546856041889373e-05,
      "loss": 1.455,
      "step": 30
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 1.8941113948822021,
      "learning_rate": 5.182610115288295e-05,
      "loss": 1.4617,
      "step": 31
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 2.875288248062134,
      "learning_rate": 4.817389884711705e-05,
      "loss": 1.3048,
      "step": 32
    },
    {
      "epoch": 1.8857142857142857,
      "grad_norm": 3.436675548553467,
      "learning_rate": 4.4531439581106295e-05,
      "loss": 1.0613,
      "step": 33
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 2.804304838180542,
      "learning_rate": 4.0918157451028185e-05,
      "loss": 1.7596,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.853079795837402,
      "learning_rate": 3.735333088041596e-05,
      "loss": 1.0828,
      "step": 35
    },
    {
      "epoch": 2.057142857142857,
      "grad_norm": 1.2410961389541626,
      "learning_rate": 3.38559797614277e-05,
      "loss": 1.448,
      "step": 36
    },
    {
      "epoch": 2.1142857142857143,
      "grad_norm": 1.4228153228759766,
      "learning_rate": 3.0444763975492208e-05,
      "loss": 1.1607,
      "step": 37
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 2.402080535888672,
      "learning_rate": 2.7137883834768073e-05,
      "loss": 1.0873,
      "step": 38
    },
    {
      "epoch": 2.2285714285714286,
      "grad_norm": 2.7407891750335693,
      "learning_rate": 2.3952982975603496e-05,
      "loss": 0.6478,
      "step": 39
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.181046962738037,
      "learning_rate": 2.090705422210237e-05,
      "loss": 1.4208,
      "step": 40
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 1.7889063358306885,
      "learning_rate": 1.801634892205545e-05,
      "loss": 1.1349,
      "step": 41
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.678232431411743,
      "learning_rate": 1.5296290238968303e-05,
      "loss": 0.665,
      "step": 42
    },
    {
      "epoch": 2.4571428571428573,
      "grad_norm": 4.582726955413818,
      "learning_rate": 1.2761390862810907e-05,
      "loss": 0.7553,
      "step": 43
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 1.157283067703247,
      "learning_rate": 1.0425175578537299e-05,
      "loss": 1.383,
      "step": 44
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 1.7080718278884888,
      "learning_rate": 8.30010910550611e-06,
      "loss": 1.1187,
      "step": 45
    },
    {
      "epoch": 2.6285714285714286,
      "grad_norm": 2.5248517990112305,
      "learning_rate": 6.397529592809614e-06,
      "loss": 0.8633,
      "step": 46
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 3.649900197982788,
      "learning_rate": 4.727588125342669e-06,
      "loss": 0.671,
      "step": 47
    },
    {
      "epoch": 2.742857142857143,
      "grad_norm": 1.1063644886016846,
      "learning_rate": 3.299194563372604e-06,
      "loss": 1.3111,
      "step": 48
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4684921503067017,
      "learning_rate": 2.1199700045797077e-06,
      "loss": 1.1218,
      "step": 49
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 2.0206542015075684,
      "learning_rate": 1.196206122203647e-06,
      "loss": 1.0019,
      "step": 50
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 1.470105528831482,
      "eval_runtime": 0.5267,
      "eval_samples_per_second": 56.963,
      "eval_steps_per_second": 15.19,
      "step": 50
    },
    {
      "epoch": 2.914285714285714,
      "grad_norm": 3.2814621925354004,
      "learning_rate": 5.328315962444874e-07,
      "loss": 0.8637,
      "step": 51
    },
    {
      "epoch": 2.9714285714285715,
      "grad_norm": 1.216376781463623,
      "learning_rate": 1.333858168224178e-07,
      "loss": 1.1248,
      "step": 52
    },
    {
      "epoch": 3.0285714285714285,
      "grad_norm": 4.243889331817627,
      "learning_rate": 0.0,
      "loss": 1.5185,
      "step": 53
    }
  ],
  "logging_steps": 1,
  "max_steps": 53,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3497938460344320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}