{
  "best_metric": 0.630431056022644,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.021073483236044084,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.214696647208817e-05,
      "eval_loss": 1.147399663925171,
      "eval_runtime": 871.891,
      "eval_samples_per_second": 11.458,
      "eval_steps_per_second": 2.865,
      "step": 1
    },
    {
      "epoch": 0.0004214696647208817,
      "grad_norm": 0.7626272439956665,
      "learning_rate": 4.34e-05,
      "loss": 1.0628,
      "step": 10
    },
    {
      "epoch": 0.0008429393294417634,
      "grad_norm": 0.4994406998157501,
      "learning_rate": 8.68e-05,
      "loss": 0.856,
      "step": 20
    },
    {
      "epoch": 0.001264408994162645,
      "grad_norm": 0.5089827179908752,
      "learning_rate": 0.0001302,
      "loss": 0.7376,
      "step": 30
    },
    {
      "epoch": 0.0016858786588835268,
      "grad_norm": 0.6126852035522461,
      "learning_rate": 0.0001736,
      "loss": 0.7691,
      "step": 40
    },
    {
      "epoch": 0.0021073483236044087,
      "grad_norm": 1.0332469940185547,
      "learning_rate": 0.000217,
      "loss": 0.7831,
      "step": 50
    },
    {
      "epoch": 0.0021073483236044087,
      "eval_loss": 0.7892972230911255,
      "eval_runtime": 872.9595,
      "eval_samples_per_second": 11.444,
      "eval_steps_per_second": 2.862,
      "step": 50
    },
    {
      "epoch": 0.00252881798832529,
      "grad_norm": 0.43384820222854614,
      "learning_rate": 0.00021673569945319091,
      "loss": 0.7715,
      "step": 60
    },
    {
      "epoch": 0.002950287653046172,
      "grad_norm": 0.4282907545566559,
      "learning_rate": 0.00021594408545846038,
      "loss": 0.6761,
      "step": 70
    },
    {
      "epoch": 0.0033717573177670535,
      "grad_norm": 0.4396986663341522,
      "learning_rate": 0.0002146290146796179,
      "loss": 0.6714,
      "step": 80
    },
    {
      "epoch": 0.0037932269824879354,
      "grad_norm": 0.5730768442153931,
      "learning_rate": 0.0002127968940093076,
      "loss": 0.7565,
      "step": 90
    },
    {
      "epoch": 0.004214696647208817,
      "grad_norm": 0.9540401697158813,
      "learning_rate": 0.00021045664935527106,
      "loss": 0.7393,
      "step": 100
    },
    {
      "epoch": 0.004214696647208817,
      "eval_loss": 0.7602397203445435,
      "eval_runtime": 872.7942,
      "eval_samples_per_second": 11.446,
      "eval_steps_per_second": 2.862,
      "step": 100
    },
    {
      "epoch": 0.004636166311929699,
      "grad_norm": 0.3995174765586853,
      "learning_rate": 0.00020761968215422217,
      "loss": 0.7404,
      "step": 110
    },
    {
      "epoch": 0.00505763597665058,
      "grad_norm": 0.4123441278934479,
      "learning_rate": 0.00020429981382519356,
      "loss": 0.6722,
      "step": 120
    },
    {
      "epoch": 0.005479105641371463,
      "grad_norm": 0.4265460968017578,
      "learning_rate": 0.00020051321843297219,
      "loss": 0.6447,
      "step": 130
    },
    {
      "epoch": 0.005900575306092344,
      "grad_norm": 0.5936018228530884,
      "learning_rate": 0.0001962783438896818,
      "loss": 0.7289,
      "step": 140
    },
    {
      "epoch": 0.006322044970813226,
      "grad_norm": 1.0116862058639526,
      "learning_rate": 0.0001916158220784091,
      "loss": 0.7043,
      "step": 150
    },
    {
      "epoch": 0.006322044970813226,
      "eval_loss": 0.7188068628311157,
      "eval_runtime": 872.6433,
      "eval_samples_per_second": 11.448,
      "eval_steps_per_second": 2.863,
      "step": 150
    },
    {
      "epoch": 0.006743514635534107,
      "grad_norm": 0.4303455054759979,
      "learning_rate": 0.00018654836833674362,
      "loss": 0.7164,
      "step": 160
    },
    {
      "epoch": 0.007164984300254989,
      "grad_norm": 0.42676424980163574,
      "learning_rate": 0.0001811006707899361,
      "loss": 0.6661,
      "step": 170
    },
    {
      "epoch": 0.007586453964975871,
      "grad_norm": 0.44973692297935486,
      "learning_rate": 0.0001752992700728339,
      "loss": 0.6661,
      "step": 180
    },
    {
      "epoch": 0.008007923629696753,
      "grad_norm": 0.48232847452163696,
      "learning_rate": 0.00016917243002657602,
      "loss": 0.6969,
      "step": 190
    },
    {
      "epoch": 0.008429393294417635,
      "grad_norm": 0.9322578310966492,
      "learning_rate": 0.00016275,
      "loss": 0.6935,
      "step": 200
    },
    {
      "epoch": 0.008429393294417635,
      "eval_loss": 0.7024884819984436,
      "eval_runtime": 872.9871,
      "eval_samples_per_second": 11.443,
      "eval_steps_per_second": 2.861,
      "step": 200
    },
    {
      "epoch": 0.008850862959138516,
      "grad_norm": 0.42416146397590637,
      "learning_rate": 0.0001560632694266149,
      "loss": 0.6823,
      "step": 210
    },
    {
      "epoch": 0.009272332623859398,
      "grad_norm": 0.394248902797699,
      "learning_rate": 0.00014914481538562646,
      "loss": 0.6591,
      "step": 220
    },
    {
      "epoch": 0.009693802288580279,
      "grad_norm": 0.40907424688339233,
      "learning_rate": 0.0001420283438896818,
      "loss": 0.6353,
      "step": 230
    },
    {
      "epoch": 0.01011527195330116,
      "grad_norm": 0.49951237440109253,
      "learning_rate": 0.00013474852567256393,
      "loss": 0.6632,
      "step": 240
    },
    {
      "epoch": 0.010536741618022042,
      "grad_norm": 1.0042486190795898,
      "learning_rate": 0.00012734082727686196,
      "loss": 0.6702,
      "step": 250
    },
    {
      "epoch": 0.010536741618022042,
      "eval_loss": 0.6787152290344238,
      "eval_runtime": 872.8552,
      "eval_samples_per_second": 11.445,
      "eval_steps_per_second": 2.862,
      "step": 250
    },
    {
      "epoch": 0.010958211282742925,
      "grad_norm": 0.4140114188194275,
      "learning_rate": 0.0001198413382645404,
      "loss": 0.6869,
      "step": 260
    },
    {
      "epoch": 0.011379680947463807,
      "grad_norm": 0.3980177640914917,
      "learning_rate": 0.00011228659539222137,
      "loss": 0.618,
      "step": 270
    },
    {
      "epoch": 0.011801150612184688,
      "grad_norm": 0.4262223243713379,
      "learning_rate": 0.00010471340460777866,
      "loss": 0.6145,
      "step": 280
    },
    {
      "epoch": 0.01222262027690557,
      "grad_norm": 0.5590672492980957,
      "learning_rate": 9.715866173545961e-05,
      "loss": 0.6731,
      "step": 290
    },
    {
      "epoch": 0.012644089941626451,
      "grad_norm": 0.9287014603614807,
      "learning_rate": 8.965917272313806e-05,
      "loss": 0.6508,
      "step": 300
    },
    {
      "epoch": 0.012644089941626451,
      "eval_loss": 0.6602598428726196,
      "eval_runtime": 873.3259,
      "eval_samples_per_second": 11.439,
      "eval_steps_per_second": 2.86,
      "step": 300
    },
    {
      "epoch": 0.013065559606347333,
      "grad_norm": 0.41679131984710693,
      "learning_rate": 8.225147432743606e-05,
      "loss": 0.658,
      "step": 310
    },
    {
      "epoch": 0.013487029271068214,
      "grad_norm": 0.4045983552932739,
      "learning_rate": 7.497165611031821e-05,
      "loss": 0.6414,
      "step": 320
    },
    {
      "epoch": 0.013908498935789097,
      "grad_norm": 0.4106775224208832,
      "learning_rate": 6.785518461437353e-05,
      "loss": 0.6159,
      "step": 330
    },
    {
      "epoch": 0.014329968600509979,
      "grad_norm": 0.5271579623222351,
      "learning_rate": 6.093673057338509e-05,
      "loss": 0.6481,
      "step": 340
    },
    {
      "epoch": 0.01475143826523086,
      "grad_norm": 0.8985204100608826,
      "learning_rate": 5.4250000000000024e-05,
      "loss": 0.6159,
      "step": 350
    },
    {
      "epoch": 0.01475143826523086,
      "eval_loss": 0.6442619562149048,
      "eval_runtime": 873.0849,
      "eval_samples_per_second": 11.442,
      "eval_steps_per_second": 2.861,
      "step": 350
    },
    {
      "epoch": 0.015172907929951742,
      "grad_norm": 0.41902175545692444,
      "learning_rate": 4.782756997342398e-05,
      "loss": 0.6228,
      "step": 360
    },
    {
      "epoch": 0.015594377594672623,
      "grad_norm": 0.3683434724807739,
      "learning_rate": 4.170072992716607e-05,
      "loss": 0.6158,
      "step": 370
    },
    {
      "epoch": 0.016015847259393506,
      "grad_norm": 0.4270426630973816,
      "learning_rate": 3.5899329210063916e-05,
      "loss": 0.6093,
      "step": 380
    },
    {
      "epoch": 0.016437316924114386,
      "grad_norm": 0.5241418480873108,
      "learning_rate": 3.045163166325637e-05,
      "loss": 0.662,
      "step": 390
    },
    {
      "epoch": 0.01685878658883527,
      "grad_norm": 0.7835712432861328,
      "learning_rate": 2.5384177921590895e-05,
      "loss": 0.6354,
      "step": 400
    },
    {
      "epoch": 0.01685878658883527,
      "eval_loss": 0.635778546333313,
      "eval_runtime": 873.4484,
      "eval_samples_per_second": 11.437,
      "eval_steps_per_second": 2.86,
      "step": 400
    },
    {
      "epoch": 0.01728025625355615,
      "grad_norm": 0.4076845645904541,
      "learning_rate": 2.0721656110318213e-05,
      "loss": 0.6454,
      "step": 410
    },
    {
      "epoch": 0.017701725918277032,
      "grad_norm": 0.4060816466808319,
      "learning_rate": 1.6486781567027783e-05,
      "loss": 0.6029,
      "step": 420
    },
    {
      "epoch": 0.018123195582997912,
      "grad_norm": 0.43102189898490906,
      "learning_rate": 1.2700186174806422e-05,
      "loss": 0.5974,
      "step": 430
    },
    {
      "epoch": 0.018544665247718795,
      "grad_norm": 0.515192985534668,
      "learning_rate": 9.380317845777794e-06,
      "loss": 0.6454,
      "step": 440
    },
    {
      "epoch": 0.01896613491243968,
      "grad_norm": 0.9731060266494751,
      "learning_rate": 6.543350644728947e-06,
      "loss": 0.6225,
      "step": 450
    },
    {
      "epoch": 0.01896613491243968,
      "eval_loss": 0.6311845779418945,
      "eval_runtime": 873.5871,
      "eval_samples_per_second": 11.436,
      "eval_steps_per_second": 2.859,
      "step": 450
    },
    {
      "epoch": 0.019387604577160558,
      "grad_norm": 0.38442152738571167,
      "learning_rate": 4.2031059906924e-06,
      "loss": 0.6438,
      "step": 460
    },
    {
      "epoch": 0.01980907424188144,
      "grad_norm": 0.38169050216674805,
      "learning_rate": 2.3709853203820825e-06,
      "loss": 0.6287,
      "step": 470
    },
    {
      "epoch": 0.02023054390660232,
      "grad_norm": 0.4052588641643524,
      "learning_rate": 1.0559145415396157e-06,
      "loss": 0.6131,
      "step": 480
    },
    {
      "epoch": 0.020652013571323204,
      "grad_norm": 0.47564056515693665,
      "learning_rate": 2.643005468090745e-07,
      "loss": 0.6782,
      "step": 490
    },
    {
      "epoch": 0.021073483236044084,
      "grad_norm": 0.9834715127944946,
      "learning_rate": 0.0,
      "loss": 0.6781,
      "step": 500
    },
    {
      "epoch": 0.021073483236044084,
      "eval_loss": 0.630431056022644,
      "eval_runtime": 874.2378,
      "eval_samples_per_second": 11.427,
      "eval_steps_per_second": 2.857,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 1.3554433904345088e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}