{
  "best_metric": 0.29707786440849304,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.437636761487965,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00087527352297593,
      "eval_loss": 0.5409302115440369,
      "eval_runtime": 47.9717,
      "eval_samples_per_second": 10.027,
      "eval_steps_per_second": 2.522,
      "step": 1
    },
    {
      "epoch": 0.0087527352297593,
      "grad_norm": 0.6175008416175842,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 1.102,
      "step": 10
    },
    {
      "epoch": 0.0175054704595186,
      "grad_norm": 0.5922743082046509,
      "learning_rate": 8.120000000000001e-05,
      "loss": 0.7527,
      "step": 20
    },
    {
      "epoch": 0.0262582056892779,
      "grad_norm": 0.18080410361289978,
      "learning_rate": 0.00012179999999999999,
      "loss": 0.2428,
      "step": 30
    },
    {
      "epoch": 0.0350109409190372,
      "grad_norm": 0.2408462017774582,
      "learning_rate": 0.00016240000000000002,
      "loss": 0.0084,
      "step": 40
    },
    {
      "epoch": 0.0437636761487965,
      "grad_norm": 0.16170749068260193,
      "learning_rate": 0.000203,
      "loss": 0.0081,
      "step": 50
    },
    {
      "epoch": 0.0437636761487965,
      "eval_loss": 0.41450178623199463,
      "eval_runtime": 48.0897,
      "eval_samples_per_second": 10.002,
      "eval_steps_per_second": 2.516,
      "step": 50
    },
    {
      "epoch": 0.0525164113785558,
      "grad_norm": 0.523928165435791,
      "learning_rate": 0.00020275275110137215,
      "loss": 0.6924,
      "step": 60
    },
    {
      "epoch": 0.061269146608315096,
      "grad_norm": 0.6150461435317993,
      "learning_rate": 0.00020201220897726938,
      "loss": 0.5178,
      "step": 70
    },
    {
      "epoch": 0.0700218818380744,
      "grad_norm": 0.3789159655570984,
      "learning_rate": 0.00020078198147448128,
      "loss": 0.2702,
      "step": 80
    },
    {
      "epoch": 0.0787746170678337,
      "grad_norm": 1.880570411682129,
      "learning_rate": 0.00019906806213773937,
      "loss": 0.0048,
      "step": 90
    },
    {
      "epoch": 0.087527352297593,
      "grad_norm": 0.6373544335365295,
      "learning_rate": 0.0001968788010097697,
      "loss": 0.0049,
      "step": 100
    },
    {
      "epoch": 0.087527352297593,
      "eval_loss": 0.3669174313545227,
      "eval_runtime": 48.1037,
      "eval_samples_per_second": 9.999,
      "eval_steps_per_second": 2.515,
      "step": 100
    },
    {
      "epoch": 0.0962800875273523,
      "grad_norm": 0.6095497608184814,
      "learning_rate": 0.00019422486395072398,
      "loss": 0.8385,
      "step": 110
    },
    {
      "epoch": 0.1050328227571116,
      "grad_norm": 0.44535937905311584,
      "learning_rate": 0.0001911191806751811,
      "loss": 0.5802,
      "step": 120
    },
    {
      "epoch": 0.1137855579868709,
      "grad_norm": 0.10592010617256165,
      "learning_rate": 0.00018757688175987723,
      "loss": 0.1586,
      "step": 130
    },
    {
      "epoch": 0.12253829321663019,
      "grad_norm": 0.025220032781362534,
      "learning_rate": 0.00018361522492905716,
      "loss": 0.0018,
      "step": 140
    },
    {
      "epoch": 0.13129102844638948,
      "grad_norm": 0.014781222678720951,
      "learning_rate": 0.00017925351097657625,
      "loss": 0.002,
      "step": 150
    },
    {
      "epoch": 0.13129102844638948,
      "eval_loss": 0.36381667852401733,
      "eval_runtime": 48.1198,
      "eval_samples_per_second": 9.996,
      "eval_steps_per_second": 2.515,
      "step": 150
    },
    {
      "epoch": 0.1400437636761488,
      "grad_norm": 0.5591445565223694,
      "learning_rate": 0.00017451298973437308,
      "loss": 0.9412,
      "step": 160
    },
    {
      "epoch": 0.1487964989059081,
      "grad_norm": 0.30725646018981934,
      "learning_rate": 0.0001694167565454241,
      "loss": 0.4974,
      "step": 170
    },
    {
      "epoch": 0.1575492341356674,
      "grad_norm": 0.11813530325889587,
      "learning_rate": 0.0001639896397455543,
      "loss": 0.0992,
      "step": 180
    },
    {
      "epoch": 0.16630196936542668,
      "grad_norm": 0.009045140817761421,
      "learning_rate": 0.0001582580797022808,
      "loss": 0.0109,
      "step": 190
    },
    {
      "epoch": 0.175054704595186,
      "grad_norm": 0.017792249098420143,
      "learning_rate": 0.00015225,
      "loss": 0.0007,
      "step": 200
    },
    {
      "epoch": 0.175054704595186,
      "eval_loss": 0.35675832629203796,
      "eval_runtime": 47.8961,
      "eval_samples_per_second": 10.043,
      "eval_steps_per_second": 2.526,
      "step": 200
    },
    {
      "epoch": 0.1838074398249453,
      "grad_norm": 0.5258771777153015,
      "learning_rate": 0.00014599467139909136,
      "loss": 0.7887,
      "step": 210
    },
    {
      "epoch": 0.1925601750547046,
      "grad_norm": 0.5954610109329224,
      "learning_rate": 0.0001395225692317151,
      "loss": 0.7499,
      "step": 220
    },
    {
      "epoch": 0.2013129102844639,
      "grad_norm": 0.0030906260944902897,
      "learning_rate": 0.00013286522492905717,
      "loss": 0.1606,
      "step": 230
    },
    {
      "epoch": 0.2100656455142232,
      "grad_norm": 0.0038282345049083233,
      "learning_rate": 0.00012605507240336626,
      "loss": 0.0009,
      "step": 240
    },
    {
      "epoch": 0.2188183807439825,
      "grad_norm": 0.01913132704794407,
      "learning_rate": 0.00011912529003319345,
      "loss": 0.0004,
      "step": 250
    },
    {
      "epoch": 0.2188183807439825,
      "eval_loss": 0.3523136377334595,
      "eval_runtime": 48.1668,
      "eval_samples_per_second": 9.986,
      "eval_steps_per_second": 2.512,
      "step": 250
    },
    {
      "epoch": 0.2275711159737418,
      "grad_norm": 0.5447108149528503,
      "learning_rate": 0.00011210963902166683,
      "loss": 0.8402,
      "step": 260
    },
    {
      "epoch": 0.2363238512035011,
      "grad_norm": 0.32077598571777344,
      "learning_rate": 0.00010504229891530386,
      "loss": 0.6314,
      "step": 270
    },
    {
      "epoch": 0.24507658643326038,
      "grad_norm": 0.22313565015792847,
      "learning_rate": 9.795770108469618e-05,
      "loss": 0.2108,
      "step": 280
    },
    {
      "epoch": 0.2538293216630197,
      "grad_norm": 0.03895167261362076,
      "learning_rate": 9.08903609783332e-05,
      "loss": 0.0013,
      "step": 290
    },
    {
      "epoch": 0.26258205689277897,
      "grad_norm": 0.004272861871868372,
      "learning_rate": 8.387470996680658e-05,
      "loss": 0.0024,
      "step": 300
    },
    {
      "epoch": 0.26258205689277897,
      "eval_loss": 0.3272861838340759,
      "eval_runtime": 47.9479,
      "eval_samples_per_second": 10.032,
      "eval_steps_per_second": 2.524,
      "step": 300
    },
    {
      "epoch": 0.2713347921225383,
      "grad_norm": 0.4647512137889862,
      "learning_rate": 7.694492759663374e-05,
      "loss": 0.7352,
      "step": 310
    },
    {
      "epoch": 0.2800875273522976,
      "grad_norm": 0.23608016967773438,
      "learning_rate": 7.013477507094284e-05,
      "loss": 0.5446,
      "step": 320
    },
    {
      "epoch": 0.2888402625820569,
      "grad_norm": 0.011121237650513649,
      "learning_rate": 6.347743076828492e-05,
      "loss": 0.1594,
      "step": 330
    },
    {
      "epoch": 0.2975929978118162,
      "grad_norm": 0.03790149837732315,
      "learning_rate": 5.700532860090863e-05,
      "loss": 0.0004,
      "step": 340
    },
    {
      "epoch": 0.3063457330415755,
      "grad_norm": 0.17843233048915863,
      "learning_rate": 5.075000000000002e-05,
      "loss": 0.0016,
      "step": 350
    },
    {
      "epoch": 0.3063457330415755,
      "eval_loss": 0.31218644976615906,
      "eval_runtime": 47.9567,
      "eval_samples_per_second": 10.03,
      "eval_steps_per_second": 2.523,
      "step": 350
    },
    {
      "epoch": 0.3150984682713348,
      "grad_norm": 0.3766857385635376,
      "learning_rate": 4.4741920297719214e-05,
      "loss": 0.6989,
      "step": 360
    },
    {
      "epoch": 0.3238512035010941,
      "grad_norm": 0.45434561371803284,
      "learning_rate": 3.901036025444568e-05,
      "loss": 0.6038,
      "step": 370
    },
    {
      "epoch": 0.33260393873085337,
      "grad_norm": 0.002181870862841606,
      "learning_rate": 3.358324345457592e-05,
      "loss": 0.1711,
      "step": 380
    },
    {
      "epoch": 0.3413566739606127,
      "grad_norm": 0.0015434159431606531,
      "learning_rate": 2.8487010265626928e-05,
      "loss": 0.0022,
      "step": 390
    },
    {
      "epoch": 0.350109409190372,
      "grad_norm": 0.07286681234836578,
      "learning_rate": 2.3746489023423744e-05,
      "loss": 0.0005,
      "step": 400
    },
    {
      "epoch": 0.350109409190372,
      "eval_loss": 0.3000512421131134,
      "eval_runtime": 47.9614,
      "eval_samples_per_second": 10.029,
      "eval_steps_per_second": 2.523,
      "step": 400
    },
    {
      "epoch": 0.3588621444201313,
      "grad_norm": 0.36653754115104675,
      "learning_rate": 1.9384775070942844e-05,
      "loss": 0.7181,
      "step": 410
    },
    {
      "epoch": 0.3676148796498906,
      "grad_norm": 0.229636549949646,
      "learning_rate": 1.5423118240122765e-05,
      "loss": 0.5265,
      "step": 420
    },
    {
      "epoch": 0.37636761487964987,
      "grad_norm": 0.2803157567977905,
      "learning_rate": 1.188081932481891e-05,
      "loss": 0.1247,
      "step": 430
    },
    {
      "epoch": 0.3851203501094092,
      "grad_norm": 0.01452224887907505,
      "learning_rate": 8.775136049276001e-06,
      "loss": 0.0002,
      "step": 440
    },
    {
      "epoch": 0.3938730853391685,
      "grad_norm": 0.00235812459141016,
      "learning_rate": 6.121198990230306e-06,
      "loss": 0.0002,
      "step": 450
    },
    {
      "epoch": 0.3938730853391685,
      "eval_loss": 0.29808175563812256,
      "eval_runtime": 47.9228,
      "eval_samples_per_second": 10.037,
      "eval_steps_per_second": 2.525,
      "step": 450
    },
    {
      "epoch": 0.4026258205689278,
      "grad_norm": 0.4591379463672638,
      "learning_rate": 3.931937862260632e-06,
      "loss": 0.6904,
      "step": 460
    },
    {
      "epoch": 0.4113785557986871,
      "grad_norm": 0.2666955292224884,
      "learning_rate": 2.2180185255187225e-06,
      "loss": 0.5246,
      "step": 470
    },
    {
      "epoch": 0.4201312910284464,
      "grad_norm": 0.004976064432412386,
      "learning_rate": 9.877910227306082e-07,
      "loss": 0.0667,
      "step": 480
    },
    {
      "epoch": 0.4288840262582057,
      "grad_norm": 0.0005102211725898087,
      "learning_rate": 2.472488986278439e-07,
      "loss": 0.0005,
      "step": 490
    },
    {
      "epoch": 0.437636761487965,
      "grad_norm": 0.05553697422146797,
      "learning_rate": 0.0,
      "loss": 0.0007,
      "step": 500
    },
    {
      "epoch": 0.437636761487965,
      "eval_loss": 0.29707786440849304,
      "eval_runtime": 47.9196,
      "eval_samples_per_second": 10.038,
      "eval_steps_per_second": 2.525,
      "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": 1.6342833077157888e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}