{
  "best_metric": 0.348781555891037,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.5151515151515151,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 42.65187454223633,
      "learning_rate": 5e-05,
      "loss": 40.5917,
      "step": 1
    },
    {
      "epoch": 0.030303030303030304,
      "eval_loss": 3.099010944366455,
      "eval_runtime": 1.7169,
      "eval_samples_per_second": 29.122,
      "eval_steps_per_second": 7.572,
      "step": 1
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 40.510066986083984,
      "learning_rate": 0.0001,
      "loss": 42.2134,
      "step": 2
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 35.972103118896484,
      "learning_rate": 9.990365154573717e-05,
      "loss": 42.4964,
      "step": 3
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 32.96562576293945,
      "learning_rate": 9.961501876182148e-05,
      "loss": 39.1957,
      "step": 4
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 26.64986801147461,
      "learning_rate": 9.913533761814537e-05,
      "loss": 34.6822,
      "step": 5
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 28.514524459838867,
      "learning_rate": 9.846666218300807e-05,
      "loss": 31.089,
      "step": 6
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 30.795284271240234,
      "learning_rate": 9.761185582727977e-05,
      "loss": 29.8746,
      "step": 7
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 26.673248291015625,
      "learning_rate": 9.657457896300791e-05,
      "loss": 33.1275,
      "step": 8
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 17.892269134521484,
      "learning_rate": 9.535927336897098e-05,
      "loss": 20.5216,
      "step": 9
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 18.253292083740234,
      "learning_rate": 9.397114317029975e-05,
      "loss": 19.7817,
      "step": 10
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 18.005361557006836,
      "learning_rate": 9.241613255361455e-05,
      "loss": 18.1535,
      "step": 11
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 17.88747787475586,
      "learning_rate": 9.070090031310558e-05,
      "loss": 16.7335,
      "step": 12
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 14.878911972045898,
      "learning_rate": 8.883279133655399e-05,
      "loss": 15.589,
      "step": 13
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 22.06363868713379,
      "learning_rate": 8.681980515339464e-05,
      "loss": 14.918,
      "step": 14
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 24.978647232055664,
      "learning_rate": 8.467056167950311e-05,
      "loss": 14.4283,
      "step": 15
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 21.225818634033203,
      "learning_rate": 8.239426430539243e-05,
      "loss": 15.9054,
      "step": 16
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 10.050722122192383,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.8822,
      "step": 17
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 10.84476089477539,
      "learning_rate": 7.75e-05,
      "loss": 10.6607,
      "step": 18
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 9.327929496765137,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.7404,
      "step": 19
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 8.07457160949707,
      "learning_rate": 7.222075445642904e-05,
      "loss": 9.6303,
      "step": 20
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 10.68208122253418,
      "learning_rate": 6.946477593864228e-05,
      "loss": 9.915,
      "step": 21
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 9.476519584655762,
      "learning_rate": 6.664685702961344e-05,
      "loss": 9.0757,
      "step": 22
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 10.420138359069824,
      "learning_rate": 6.377906449072578e-05,
      "loss": 8.6263,
      "step": 23
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 15.338788032531738,
      "learning_rate": 6.087367864990233e-05,
      "loss": 9.5048,
      "step": 24
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 11.519371032714844,
      "learning_rate": 5.794314081535644e-05,
      "loss": 7.3465,
      "step": 25
    },
    {
      "epoch": 0.7575757575757576,
      "eval_loss": 0.5398735404014587,
      "eval_runtime": 1.7452,
      "eval_samples_per_second": 28.65,
      "eval_steps_per_second": 7.449,
      "step": 25
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 8.93183422088623,
      "learning_rate": 5.500000000000001e-05,
      "loss": 7.1282,
      "step": 26
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 7.6780195236206055,
      "learning_rate": 5.205685918464356e-05,
      "loss": 7.2661,
      "step": 27
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 7.696419715881348,
      "learning_rate": 4.912632135009769e-05,
      "loss": 7.2112,
      "step": 28
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 7.388005256652832,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 6.579,
      "step": 29
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 8.553566932678223,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 6.682,
      "step": 30
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 9.785886764526367,
      "learning_rate": 4.053522406135775e-05,
      "loss": 7.1062,
      "step": 31
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 14.416071891784668,
      "learning_rate": 3.777924554357096e-05,
      "loss": 8.1055,
      "step": 32
    },
    {
      "epoch": 1.0,
      "grad_norm": 8.140599250793457,
      "learning_rate": 3.509700894014496e-05,
      "loss": 6.4307,
      "step": 33
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 11.224316596984863,
      "learning_rate": 3.250000000000001e-05,
      "loss": 5.541,
      "step": 34
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 7.196849822998047,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 5.2257,
      "step": 35
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 6.592137336730957,
      "learning_rate": 2.760573569460757e-05,
      "loss": 5.2948,
      "step": 36
    },
    {
      "epoch": 1.121212121212121,
      "grad_norm": 6.121169567108154,
      "learning_rate": 2.53294383204969e-05,
      "loss": 5.4573,
      "step": 37
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 7.207998752593994,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 5.3519,
      "step": 38
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 6.918445110321045,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 5.0212,
      "step": 39
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 7.768368721008301,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 5.1239,
      "step": 40
    },
    {
      "epoch": 1.2424242424242424,
      "grad_norm": 11.915384292602539,
      "learning_rate": 1.758386744638546e-05,
      "loss": 5.7944,
      "step": 41
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 6.817359924316406,
      "learning_rate": 1.602885682970026e-05,
      "loss": 4.724,
      "step": 42
    },
    {
      "epoch": 1.303030303030303,
      "grad_norm": 7.651495933532715,
      "learning_rate": 1.464072663102903e-05,
      "loss": 4.8022,
      "step": 43
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 5.93342399597168,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 4.7365,
      "step": 44
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 6.173413276672363,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 4.7833,
      "step": 45
    },
    {
      "epoch": 1.393939393939394,
      "grad_norm": 7.115561485290527,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 4.987,
      "step": 46
    },
    {
      "epoch": 1.4242424242424243,
      "grad_norm": 6.725718975067139,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 4.6219,
      "step": 47
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 8.670489311218262,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 4.9975,
      "step": 48
    },
    {
      "epoch": 1.4848484848484849,
      "grad_norm": 13.76158618927002,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 5.3094,
      "step": 49
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 5.179720878601074,
      "learning_rate": 1e-05,
      "loss": 4.1417,
      "step": 50
    },
    {
      "epoch": 1.5151515151515151,
      "eval_loss": 0.348781555891037,
      "eval_runtime": 1.7648,
      "eval_samples_per_second": 28.332,
      "eval_steps_per_second": 7.366,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.259156315439104e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}