{
  "best_metric": 0.7533472180366516,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03759398496240601,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007518796992481203,
      "grad_norm": 0.3548731803894043,
      "learning_rate": 2e-05,
      "loss": 0.5525,
      "step": 1
    },
    {
      "epoch": 0.0007518796992481203,
      "eval_loss": 2.070512056350708,
      "eval_runtime": 34.145,
      "eval_samples_per_second": 65.603,
      "eval_steps_per_second": 8.2,
      "step": 1
    },
    {
      "epoch": 0.0015037593984962407,
      "grad_norm": 0.3535686731338501,
      "learning_rate": 4e-05,
      "loss": 0.5513,
      "step": 2
    },
    {
      "epoch": 0.002255639097744361,
      "grad_norm": 0.35291755199432373,
      "learning_rate": 6e-05,
      "loss": 0.5492,
      "step": 3
    },
    {
      "epoch": 0.0030075187969924814,
      "grad_norm": 0.3565158247947693,
      "learning_rate": 8e-05,
      "loss": 0.5347,
      "step": 4
    },
    {
      "epoch": 0.0037593984962406013,
      "grad_norm": 0.36980941891670227,
      "learning_rate": 0.0001,
      "loss": 0.4941,
      "step": 5
    },
    {
      "epoch": 0.004511278195488722,
      "grad_norm": 0.42150601744651794,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6675,
      "step": 6
    },
    {
      "epoch": 0.005263157894736842,
      "grad_norm": 1.628402829170227,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.119,
      "step": 7
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 1.3515894412994385,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.9593,
      "step": 8
    },
    {
      "epoch": 0.006766917293233083,
      "grad_norm": 1.3216582536697388,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7719,
      "step": 9
    },
    {
      "epoch": 0.007518796992481203,
      "grad_norm": 1.2489310503005981,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5205,
      "step": 10
    },
    {
      "epoch": 0.008270676691729323,
      "grad_norm": 1.1850577592849731,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.252,
      "step": 11
    },
    {
      "epoch": 0.009022556390977444,
      "grad_norm": 1.072489857673645,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.119,
      "step": 12
    },
    {
      "epoch": 0.009774436090225564,
      "grad_norm": 1.7142881155014038,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3362,
      "step": 13
    },
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 1.6948894262313843,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1528,
      "step": 14
    },
    {
      "epoch": 0.011278195488721804,
      "grad_norm": 1.498194932937622,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.931,
      "step": 15
    },
    {
      "epoch": 0.012030075187969926,
      "grad_norm": 1.4077833890914917,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.725,
      "step": 16
    },
    {
      "epoch": 0.012781954887218045,
      "grad_norm": 1.3366233110427856,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.5344,
      "step": 17
    },
    {
      "epoch": 0.013533834586466165,
      "grad_norm": 1.3127669095993042,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.967,
      "step": 18
    },
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 3.2889244556427,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.2376,
      "step": 19
    },
    {
      "epoch": 0.015037593984962405,
      "grad_norm": 2.7316462993621826,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0283,
      "step": 20
    },
    {
      "epoch": 0.015789473684210527,
      "grad_norm": 3.016934394836426,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.7866,
      "step": 21
    },
    {
      "epoch": 0.016541353383458645,
      "grad_norm": 5.15310001373291,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.5786,
      "step": 22
    },
    {
      "epoch": 0.017293233082706767,
      "grad_norm": 2.2359912395477295,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2965,
      "step": 23
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 2.186990737915039,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.0794,
      "step": 24
    },
    {
      "epoch": 0.018796992481203006,
      "grad_norm": 2.550881862640381,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8794,
      "step": 25
    },
    {
      "epoch": 0.018796992481203006,
      "eval_loss": 1.1675419807434082,
      "eval_runtime": 34.3584,
      "eval_samples_per_second": 65.195,
      "eval_steps_per_second": 8.149,
      "step": 25
    },
    {
      "epoch": 0.019548872180451128,
      "grad_norm": 1.9011552333831787,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6784,
      "step": 26
    },
    {
      "epoch": 0.02030075187969925,
      "grad_norm": 3.8109452724456787,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.562,
      "step": 27
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 1.5873984098434448,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.4223,
      "step": 28
    },
    {
      "epoch": 0.02180451127819549,
      "grad_norm": 3.5254461765289307,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.6989,
      "step": 29
    },
    {
      "epoch": 0.022556390977443608,
      "grad_norm": 4.889553546905518,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.1854,
      "step": 30
    },
    {
      "epoch": 0.02330827067669173,
      "grad_norm": 4.314491271972656,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.9502,
      "step": 31
    },
    {
      "epoch": 0.02406015037593985,
      "grad_norm": 3.777453660964966,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7344,
      "step": 32
    },
    {
      "epoch": 0.02481203007518797,
      "grad_norm": 3.119612216949463,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.4925,
      "step": 33
    },
    {
      "epoch": 0.02556390977443609,
      "grad_norm": 2.7758524417877197,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.3475,
      "step": 34
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 5.14910364151001,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1196,
      "step": 35
    },
    {
      "epoch": 0.02706766917293233,
      "grad_norm": 5.293793201446533,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.1161,
      "step": 36
    },
    {
      "epoch": 0.027819548872180452,
      "grad_norm": 5.0176005363464355,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.9794,
      "step": 37
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 4.633277416229248,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.822,
      "step": 38
    },
    {
      "epoch": 0.029323308270676692,
      "grad_norm": 4.289181232452393,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.6658,
      "step": 39
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 4.746151447296143,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.0781,
      "step": 40
    },
    {
      "epoch": 0.030827067669172932,
      "grad_norm": 6.860289096832275,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.3591,
      "step": 41
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 6.435369491577148,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.2769,
      "step": 42
    },
    {
      "epoch": 0.032330827067669175,
      "grad_norm": 5.896880626678467,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.1897,
      "step": 43
    },
    {
      "epoch": 0.03308270676691729,
      "grad_norm": 5.520768165588379,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.1196,
      "step": 44
    },
    {
      "epoch": 0.03383458646616541,
      "grad_norm": 4.645603179931641,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.9711,
      "step": 45
    },
    {
      "epoch": 0.03458646616541353,
      "grad_norm": 5.012884140014648,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.3534,
      "step": 46
    },
    {
      "epoch": 0.035338345864661655,
      "grad_norm": 4.994361877441406,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.3407,
      "step": 47
    },
    {
      "epoch": 0.03609022556390978,
      "grad_norm": 4.962730407714844,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.3288,
      "step": 48
    },
    {
      "epoch": 0.03684210526315789,
      "grad_norm": 4.913819313049316,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.3198,
      "step": 49
    },
    {
      "epoch": 0.03759398496240601,
      "grad_norm": 4.907815456390381,
      "learning_rate": 0.0,
      "loss": 1.3149,
      "step": 50
    },
    {
      "epoch": 0.03759398496240601,
      "eval_loss": 0.7533472180366516,
      "eval_runtime": 34.4566,
      "eval_samples_per_second": 65.009,
      "eval_steps_per_second": 8.126,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 8272600262246400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}