{
  "best_metric": 10.301432609558105,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.01404908751176611,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.809817502353222e-05,
      "eval_loss": 10.378629684448242,
      "eval_runtime": 60.0386,
      "eval_samples_per_second": 249.589,
      "eval_steps_per_second": 62.41,
      "step": 1
    },
    {
      "epoch": 0.0002809817502353222,
      "grad_norm": 0.19126524031162262,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 20.7601,
      "step": 10
    },
    {
      "epoch": 0.0005619635004706444,
      "grad_norm": 0.1812351495027542,
      "learning_rate": 8.120000000000001e-05,
      "loss": 20.7579,
      "step": 20
    },
    {
      "epoch": 0.0008429452507059666,
      "grad_norm": 0.21598900854587555,
      "learning_rate": 0.00012179999999999999,
      "loss": 20.7557,
      "step": 30
    },
    {
      "epoch": 0.0011239270009412888,
      "grad_norm": 0.29655301570892334,
      "learning_rate": 0.00016240000000000002,
      "loss": 20.7436,
      "step": 40
    },
    {
      "epoch": 0.001404908751176611,
      "grad_norm": 0.3212806284427643,
      "learning_rate": 0.000203,
      "loss": 20.7365,
      "step": 50
    },
    {
      "epoch": 0.001404908751176611,
      "eval_loss": 10.362621307373047,
      "eval_runtime": 60.4081,
      "eval_samples_per_second": 248.063,
      "eval_steps_per_second": 62.028,
      "step": 50
    },
    {
      "epoch": 0.0016858905014119332,
      "grad_norm": 0.4301055669784546,
      "learning_rate": 0.00020275275110137215,
      "loss": 20.7188,
      "step": 60
    },
    {
      "epoch": 0.0019668722516472557,
      "grad_norm": 0.3765835165977478,
      "learning_rate": 0.00020201220897726938,
      "loss": 20.6809,
      "step": 70
    },
    {
      "epoch": 0.0022478540018825775,
      "grad_norm": 0.3050801157951355,
      "learning_rate": 0.00020078198147448128,
      "loss": 20.6434,
      "step": 80
    },
    {
      "epoch": 0.0025288357521178998,
      "grad_norm": 0.31923723220825195,
      "learning_rate": 0.00019906806213773937,
      "loss": 20.6134,
      "step": 90
    },
    {
      "epoch": 0.002809817502353222,
      "grad_norm": 0.3668956160545349,
      "learning_rate": 0.0001968788010097697,
      "loss": 20.6138,
      "step": 100
    },
    {
      "epoch": 0.002809817502353222,
      "eval_loss": 10.308439254760742,
      "eval_runtime": 59.3542,
      "eval_samples_per_second": 252.467,
      "eval_steps_per_second": 63.129,
      "step": 100
    },
    {
      "epoch": 0.0030907992525885442,
      "grad_norm": 0.20467126369476318,
      "learning_rate": 0.00019422486395072398,
      "loss": 20.6304,
      "step": 110
    },
    {
      "epoch": 0.0033717810028238665,
      "grad_norm": 0.2518371343612671,
      "learning_rate": 0.0001911191806751811,
      "loss": 20.6217,
      "step": 120
    },
    {
      "epoch": 0.0036527627530591887,
      "grad_norm": 0.1735089272260666,
      "learning_rate": 0.00018757688175987723,
      "loss": 20.6238,
      "step": 130
    },
    {
      "epoch": 0.003933744503294511,
      "grad_norm": 0.17584048211574554,
      "learning_rate": 0.00018361522492905716,
      "loss": 20.6006,
      "step": 140
    },
    {
      "epoch": 0.004214726253529834,
      "grad_norm": 0.20633459091186523,
      "learning_rate": 0.00017925351097657625,
      "loss": 20.6024,
      "step": 150
    },
    {
      "epoch": 0.004214726253529834,
      "eval_loss": 10.306268692016602,
      "eval_runtime": 59.8224,
      "eval_samples_per_second": 250.492,
      "eval_steps_per_second": 62.635,
      "step": 150
    },
    {
      "epoch": 0.004495708003765155,
      "grad_norm": 0.18568071722984314,
      "learning_rate": 0.00017451298973437308,
      "loss": 20.6288,
      "step": 160
    },
    {
      "epoch": 0.004776689754000477,
      "grad_norm": 0.2910362184047699,
      "learning_rate": 0.0001694167565454241,
      "loss": 20.611,
      "step": 170
    },
    {
      "epoch": 0.0050576715042357995,
      "grad_norm": 0.2217985987663269,
      "learning_rate": 0.0001639896397455543,
      "loss": 20.618,
      "step": 180
    },
    {
      "epoch": 0.005338653254471122,
      "grad_norm": 0.19911141693592072,
      "learning_rate": 0.0001582580797022808,
      "loss": 20.6091,
      "step": 190
    },
    {
      "epoch": 0.005619635004706444,
      "grad_norm": 0.28544291853904724,
      "learning_rate": 0.00015225,
      "loss": 20.6026,
      "step": 200
    },
    {
      "epoch": 0.005619635004706444,
      "eval_loss": 10.305092811584473,
      "eval_runtime": 60.5578,
      "eval_samples_per_second": 247.45,
      "eval_steps_per_second": 61.875,
      "step": 200
    },
    {
      "epoch": 0.005900616754941766,
      "grad_norm": 0.21859851479530334,
      "learning_rate": 0.00014599467139909136,
      "loss": 20.6277,
      "step": 210
    },
    {
      "epoch": 0.0061815985051770885,
      "grad_norm": 0.2270508110523224,
      "learning_rate": 0.0001395225692317151,
      "loss": 20.6168,
      "step": 220
    },
    {
      "epoch": 0.006462580255412411,
      "grad_norm": 0.17180295288562775,
      "learning_rate": 0.00013286522492905717,
      "loss": 20.6051,
      "step": 230
    },
    {
      "epoch": 0.006743562005647733,
      "grad_norm": 0.2308344542980194,
      "learning_rate": 0.00012605507240336626,
      "loss": 20.6047,
      "step": 240
    },
    {
      "epoch": 0.007024543755883055,
      "grad_norm": 0.2163165658712387,
      "learning_rate": 0.00011912529003319345,
      "loss": 20.5976,
      "step": 250
    },
    {
      "epoch": 0.007024543755883055,
      "eval_loss": 10.303328514099121,
      "eval_runtime": 60.606,
      "eval_samples_per_second": 247.253,
      "eval_steps_per_second": 61.826,
      "step": 250
    },
    {
      "epoch": 0.0073055255061183775,
      "grad_norm": 0.1643211990594864,
      "learning_rate": 0.00011210963902166683,
      "loss": 20.6166,
      "step": 260
    },
    {
      "epoch": 0.0075865072563537,
      "grad_norm": 0.13470244407653809,
      "learning_rate": 0.00010504229891530386,
      "loss": 20.6187,
      "step": 270
    },
    {
      "epoch": 0.007867489006589023,
      "grad_norm": 0.15561600029468536,
      "learning_rate": 9.795770108469618e-05,
      "loss": 20.5993,
      "step": 280
    },
    {
      "epoch": 0.008148470756824344,
      "grad_norm": 0.1637904942035675,
      "learning_rate": 9.08903609783332e-05,
      "loss": 20.6033,
      "step": 290
    },
    {
      "epoch": 0.008429452507059667,
      "grad_norm": 0.2457241415977478,
      "learning_rate": 8.387470996680658e-05,
      "loss": 20.581,
      "step": 300
    },
    {
      "epoch": 0.008429452507059667,
      "eval_loss": 10.302334785461426,
      "eval_runtime": 59.2759,
      "eval_samples_per_second": 252.801,
      "eval_steps_per_second": 63.213,
      "step": 300
    },
    {
      "epoch": 0.008710434257294989,
      "grad_norm": 0.1403207629919052,
      "learning_rate": 7.694492759663374e-05,
      "loss": 20.6175,
      "step": 310
    },
    {
      "epoch": 0.00899141600753031,
      "grad_norm": 0.1851751208305359,
      "learning_rate": 7.013477507094284e-05,
      "loss": 20.6056,
      "step": 320
    },
    {
      "epoch": 0.009272397757765633,
      "grad_norm": 0.23650233447551727,
      "learning_rate": 6.347743076828492e-05,
      "loss": 20.6097,
      "step": 330
    },
    {
      "epoch": 0.009553379508000955,
      "grad_norm": 0.2193847894668579,
      "learning_rate": 5.700532860090863e-05,
      "loss": 20.5948,
      "step": 340
    },
    {
      "epoch": 0.009834361258236278,
      "grad_norm": 0.2748495638370514,
      "learning_rate": 5.075000000000002e-05,
      "loss": 20.5916,
      "step": 350
    },
    {
      "epoch": 0.009834361258236278,
      "eval_loss": 10.30180835723877,
      "eval_runtime": 60.3366,
      "eval_samples_per_second": 248.357,
      "eval_steps_per_second": 62.102,
      "step": 350
    },
    {
      "epoch": 0.010115343008471599,
      "grad_norm": 0.2530926764011383,
      "learning_rate": 4.4741920297719214e-05,
      "loss": 20.6187,
      "step": 360
    },
    {
      "epoch": 0.010396324758706922,
      "grad_norm": 0.18327485024929047,
      "learning_rate": 3.901036025444568e-05,
      "loss": 20.6102,
      "step": 370
    },
    {
      "epoch": 0.010677306508942244,
      "grad_norm": 0.1382702887058258,
      "learning_rate": 3.358324345457592e-05,
      "loss": 20.6094,
      "step": 380
    },
    {
      "epoch": 0.010958288259177567,
      "grad_norm": 0.19693830609321594,
      "learning_rate": 2.8487010265626928e-05,
      "loss": 20.5886,
      "step": 390
    },
    {
      "epoch": 0.011239270009412888,
      "grad_norm": 0.26368966698646545,
      "learning_rate": 2.3746489023423744e-05,
      "loss": 20.5852,
      "step": 400
    },
    {
      "epoch": 0.011239270009412888,
      "eval_loss": 10.301532745361328,
      "eval_runtime": 59.6237,
      "eval_samples_per_second": 251.326,
      "eval_steps_per_second": 62.844,
      "step": 400
    },
    {
      "epoch": 0.011520251759648211,
      "grad_norm": 0.15768560767173767,
      "learning_rate": 1.9384775070942844e-05,
      "loss": 20.6082,
      "step": 410
    },
    {
      "epoch": 0.011801233509883532,
      "grad_norm": 0.19848321378231049,
      "learning_rate": 1.5423118240122765e-05,
      "loss": 20.5956,
      "step": 420
    },
    {
      "epoch": 0.012082215260118856,
      "grad_norm": 0.14942528307437897,
      "learning_rate": 1.188081932481891e-05,
      "loss": 20.6074,
      "step": 430
    },
    {
      "epoch": 0.012363197010354177,
      "grad_norm": 0.21457645297050476,
      "learning_rate": 8.775136049276001e-06,
      "loss": 20.5856,
      "step": 440
    },
    {
      "epoch": 0.0126441787605895,
      "grad_norm": 0.3364667296409607,
      "learning_rate": 6.121198990230306e-06,
      "loss": 20.5984,
      "step": 450
    },
    {
      "epoch": 0.0126441787605895,
      "eval_loss": 10.30145263671875,
      "eval_runtime": 60.1852,
      "eval_samples_per_second": 248.982,
      "eval_steps_per_second": 62.258,
      "step": 450
    },
    {
      "epoch": 0.012925160510824821,
      "grad_norm": 0.16703709959983826,
      "learning_rate": 3.931937862260632e-06,
      "loss": 20.6069,
      "step": 460
    },
    {
      "epoch": 0.013206142261060145,
      "grad_norm": 0.19127300381660461,
      "learning_rate": 2.2180185255187225e-06,
      "loss": 20.6087,
      "step": 470
    },
    {
      "epoch": 0.013487124011295466,
      "grad_norm": 0.19735532999038696,
      "learning_rate": 9.877910227306082e-07,
      "loss": 20.6209,
      "step": 480
    },
    {
      "epoch": 0.013768105761530789,
      "grad_norm": 0.1791822463274002,
      "learning_rate": 2.472488986278439e-07,
      "loss": 20.5952,
      "step": 490
    },
    {
      "epoch": 0.01404908751176611,
      "grad_norm": 0.20496730506420135,
      "learning_rate": 0.0,
      "loss": 20.5889,
      "step": 500
    },
    {
      "epoch": 0.01404908751176611,
      "eval_loss": 10.301432609558105,
      "eval_runtime": 60.1498,
      "eval_samples_per_second": 249.128,
      "eval_steps_per_second": 62.294,
      "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": 21494130278400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}