{
  "best_metric": 0.7339180707931519,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 70.61749267578125,
      "learning_rate": 5e-06,
      "loss": 33.8017,
      "step": 1
    },
    {
      "epoch": 0.047619047619047616,
      "eval_loss": 8.488510131835938,
      "eval_runtime": 1.5143,
      "eval_samples_per_second": 23.774,
      "eval_steps_per_second": 11.887,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 89.3288345336914,
      "learning_rate": 1e-05,
      "loss": 36.8574,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 80.17635345458984,
      "learning_rate": 1.5e-05,
      "loss": 37.14,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 75.35139465332031,
      "learning_rate": 2e-05,
      "loss": 35.5743,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 80.63961791992188,
      "learning_rate": 2.5e-05,
      "loss": 35.1564,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 75.4241943359375,
      "learning_rate": 3e-05,
      "loss": 30.6528,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 73.1867446899414,
      "learning_rate": 3.5e-05,
      "loss": 27.3585,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 66.09611511230469,
      "learning_rate": 4e-05,
      "loss": 20.9346,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 61.280120849609375,
      "learning_rate": 4.5e-05,
      "loss": 16.2169,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 44.32679748535156,
      "learning_rate": 5e-05,
      "loss": 12.3205,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 51.232906341552734,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.1753,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 53.598365783691406,
      "learning_rate": 6e-05,
      "loss": 9.5126,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 49.24958419799805,
      "learning_rate": 6.500000000000001e-05,
      "loss": 6.3121,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 36.19329833984375,
      "learning_rate": 7e-05,
      "loss": 4.8738,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 25.576393127441406,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.6295,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 39.14617919921875,
      "learning_rate": 8e-05,
      "loss": 3.8308,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 28.955108642578125,
      "learning_rate": 8.5e-05,
      "loss": 3.9269,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 33.5592155456543,
      "learning_rate": 9e-05,
      "loss": 4.2107,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 29.655385971069336,
      "learning_rate": 9.5e-05,
      "loss": 3.5708,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 26.0640811920166,
      "learning_rate": 0.0001,
      "loss": 3.4429,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 38.40494918823242,
      "learning_rate": 9.986661418317759e-05,
      "loss": 3.5586,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 14.375667572021484,
      "learning_rate": 9.946716840375551e-05,
      "loss": 3.3643,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 25.285995483398438,
      "learning_rate": 9.880379387779637e-05,
      "loss": 3.4791,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 11.269182205200195,
      "learning_rate": 9.78800299954203e-05,
      "loss": 2.9826,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 15.11327838897705,
      "learning_rate": 9.67008054366274e-05,
      "loss": 3.1094,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 16.692920684814453,
      "learning_rate": 9.527241187465734e-05,
      "loss": 2.9784,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 36.734500885009766,
      "learning_rate": 9.360247040719039e-05,
      "loss": 3.5783,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 14.008699417114258,
      "learning_rate": 9.16998908944939e-05,
      "loss": 2.9826,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 11.462227821350098,
      "learning_rate": 8.957482442146272e-05,
      "loss": 3.0921,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 13.71957015991211,
      "learning_rate": 8.72386091371891e-05,
      "loss": 3.3794,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 4.488590240478516,
      "learning_rate": 8.47037097610317e-05,
      "loss": 2.7482,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 9.806519508361816,
      "learning_rate": 8.198365107794457e-05,
      "loss": 2.7917,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 19.80751609802246,
      "learning_rate": 7.909294577789766e-05,
      "loss": 3.4169,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 14.619462966918945,
      "learning_rate": 7.604701702439651e-05,
      "loss": 3.326,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 16.35366439819336,
      "learning_rate": 7.286211616523193e-05,
      "loss": 3.2313,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 6.2724609375,
      "learning_rate": 6.95552360245078e-05,
      "loss": 2.8079,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 10.460845947265625,
      "learning_rate": 6.614402023857232e-05,
      "loss": 2.9459,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 9.461526870727539,
      "learning_rate": 6.264666911958404e-05,
      "loss": 2.9598,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 7.6167097091674805,
      "learning_rate": 5.908184254897182e-05,
      "loss": 2.9533,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 9.928021430969238,
      "learning_rate": 5.546856041889373e-05,
      "loss": 2.9279,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 5.470791339874268,
      "learning_rate": 5.182610115288295e-05,
      "loss": 2.9515,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.028589725494385,
      "learning_rate": 4.817389884711705e-05,
      "loss": 3.0166,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 5.838282585144043,
      "learning_rate": 4.4531439581106295e-05,
      "loss": 2.8832,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 7.127386093139648,
      "learning_rate": 4.0918157451028185e-05,
      "loss": 2.9343,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 5.750761985778809,
      "learning_rate": 3.735333088041596e-05,
      "loss": 2.8033,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 7.080549240112305,
      "learning_rate": 3.38559797614277e-05,
      "loss": 2.6489,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 3.680392265319824,
      "learning_rate": 3.0444763975492208e-05,
      "loss": 2.7227,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 4.481716632843018,
      "learning_rate": 2.7137883834768073e-05,
      "loss": 2.8145,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 10.20344352722168,
      "learning_rate": 2.3952982975603496e-05,
      "loss": 3.0544,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 6.239677906036377,
      "learning_rate": 2.090705422210237e-05,
      "loss": 2.8421,
      "step": 50
    },
    {
      "epoch": 2.380952380952381,
      "eval_loss": 0.7339180707931519,
      "eval_runtime": 1.53,
      "eval_samples_per_second": 23.53,
      "eval_steps_per_second": 11.765,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 5.302610874176025,
      "learning_rate": 1.801634892205545e-05,
      "loss": 2.907,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 3.535484790802002,
      "learning_rate": 1.5296290238968303e-05,
      "loss": 2.816,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 2.9045586585998535,
      "learning_rate": 1.2761390862810907e-05,
      "loss": 2.8551,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 5.55578088760376,
      "learning_rate": 1.0425175578537299e-05,
      "loss": 2.7582,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 7.579736232757568,
      "learning_rate": 8.30010910550611e-06,
      "loss": 2.8881,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 4.39998722076416,
      "learning_rate": 6.397529592809614e-06,
      "loss": 2.7402,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 8.276344299316406,
      "learning_rate": 4.727588125342669e-06,
      "loss": 2.7021,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 4.667769908905029,
      "learning_rate": 3.299194563372604e-06,
      "loss": 2.9088,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 4.007717132568359,
      "learning_rate": 2.1199700045797077e-06,
      "loss": 2.8541,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 6.375820636749268,
      "learning_rate": 1.196206122203647e-06,
      "loss": 2.864,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 4.68563175201416,
      "learning_rate": 5.328315962444874e-07,
      "loss": 2.8855,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 4.791390895843506,
      "learning_rate": 1.333858168224178e-07,
      "loss": 2.7794,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.031291484832764,
      "learning_rate": 0.0,
      "loss": 2.8601,
      "step": 63
    }
  ],
  "logging_steps": 1,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.673626526089216e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}