{
  "best_metric": 0.952971339225769,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.010930753675465924,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021861507350931847,
      "grad_norm": 16.034286499023438,
      "learning_rate": 2e-05,
      "loss": 7.5287,
      "step": 1
    },
    {
      "epoch": 0.00021861507350931847,
      "eval_loss": 2.686614751815796,
      "eval_runtime": 564.5723,
      "eval_samples_per_second": 13.646,
      "eval_steps_per_second": 1.706,
      "step": 1
    },
    {
      "epoch": 0.00043723014701863694,
      "grad_norm": 17.467485427856445,
      "learning_rate": 4e-05,
      "loss": 7.593,
      "step": 2
    },
    {
      "epoch": 0.0006558452205279554,
      "grad_norm": 12.28742504119873,
      "learning_rate": 6e-05,
      "loss": 7.3064,
      "step": 3
    },
    {
      "epoch": 0.0008744602940372739,
      "grad_norm": 12.63910961151123,
      "learning_rate": 8e-05,
      "loss": 6.673,
      "step": 4
    },
    {
      "epoch": 0.0010930753675465923,
      "grad_norm": 10.90099811553955,
      "learning_rate": 0.0001,
      "loss": 6.5356,
      "step": 5
    },
    {
      "epoch": 0.0013116904410559109,
      "grad_norm": 9.051518440246582,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.9956,
      "step": 6
    },
    {
      "epoch": 0.0015303055145652292,
      "grad_norm": 8.200225830078125,
      "learning_rate": 9.951340343707852e-05,
      "loss": 5.8258,
      "step": 7
    },
    {
      "epoch": 0.0017489205880745478,
      "grad_norm": 7.3150129318237305,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.6125,
      "step": 8
    },
    {
      "epoch": 0.001967535661583866,
      "grad_norm": 8.261173248291016,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.6928,
      "step": 9
    },
    {
      "epoch": 0.0021861507350931847,
      "grad_norm": 6.815949440002441,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.6628,
      "step": 10
    },
    {
      "epoch": 0.002404765808602503,
      "grad_norm": 5.879499912261963,
      "learning_rate": 9.567727288213005e-05,
      "loss": 5.3772,
      "step": 11
    },
    {
      "epoch": 0.0026233808821118218,
      "grad_norm": 6.805439472198486,
      "learning_rate": 9.414737964294636e-05,
      "loss": 5.6461,
      "step": 12
    },
    {
      "epoch": 0.00284199595562114,
      "grad_norm": 6.350963592529297,
      "learning_rate": 9.24024048078213e-05,
      "loss": 5.3482,
      "step": 13
    },
    {
      "epoch": 0.0030606110291304584,
      "grad_norm": 5.94356107711792,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.3435,
      "step": 14
    },
    {
      "epoch": 0.003279226102639777,
      "grad_norm": 6.665226936340332,
      "learning_rate": 8.83022221559489e-05,
      "loss": 5.2223,
      "step": 15
    },
    {
      "epoch": 0.0034978411761490955,
      "grad_norm": 6.398581027984619,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.9641,
      "step": 16
    },
    {
      "epoch": 0.003716456249658414,
      "grad_norm": 6.765588760375977,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.8446,
      "step": 17
    },
    {
      "epoch": 0.003935071323167732,
      "grad_norm": 6.2813262939453125,
      "learning_rate": 8.07830737662829e-05,
      "loss": 4.9401,
      "step": 18
    },
    {
      "epoch": 0.004153686396677051,
      "grad_norm": 6.1281328201293945,
      "learning_rate": 7.795964517353735e-05,
      "loss": 4.8324,
      "step": 19
    },
    {
      "epoch": 0.004372301470186369,
      "grad_norm": 6.242575168609619,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.9384,
      "step": 20
    },
    {
      "epoch": 0.004590916543695688,
      "grad_norm": 6.1271653175354,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.8325,
      "step": 21
    },
    {
      "epoch": 0.004809531617205006,
      "grad_norm": 5.907933712005615,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.8918,
      "step": 22
    },
    {
      "epoch": 0.005028146690714325,
      "grad_norm": 6.204776763916016,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.7693,
      "step": 23
    },
    {
      "epoch": 0.0052467617642236435,
      "grad_norm": 5.6883015632629395,
      "learning_rate": 6.209609477998338e-05,
      "loss": 4.8656,
      "step": 24
    },
    {
      "epoch": 0.005465376837732962,
      "grad_norm": 5.991116046905518,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.638,
      "step": 25
    },
    {
      "epoch": 0.005465376837732962,
      "eval_loss": 0.952971339225769,
      "eval_runtime": 569.0719,
      "eval_samples_per_second": 13.538,
      "eval_steps_per_second": 1.692,
      "step": 25
    },
    {
      "epoch": 0.00568399191124228,
      "grad_norm": 5.873587131500244,
      "learning_rate": 5.522642316338268e-05,
      "loss": 4.8957,
      "step": 26
    },
    {
      "epoch": 0.005902606984751598,
      "grad_norm": 5.590426921844482,
      "learning_rate": 5.174497483512506e-05,
      "loss": 4.7604,
      "step": 27
    },
    {
      "epoch": 0.006121222058260917,
      "grad_norm": 5.399012088775635,
      "learning_rate": 4.825502516487497e-05,
      "loss": 4.3861,
      "step": 28
    },
    {
      "epoch": 0.006339837131770235,
      "grad_norm": 5.434515953063965,
      "learning_rate": 4.477357683661734e-05,
      "loss": 4.939,
      "step": 29
    },
    {
      "epoch": 0.006558452205279554,
      "grad_norm": 5.8018999099731445,
      "learning_rate": 4.131759111665349e-05,
      "loss": 4.5712,
      "step": 30
    },
    {
      "epoch": 0.0067770672787888725,
      "grad_norm": 5.351323127746582,
      "learning_rate": 3.790390522001662e-05,
      "loss": 4.0597,
      "step": 31
    },
    {
      "epoch": 0.006995682352298191,
      "grad_norm": 6.120589733123779,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.3157,
      "step": 32
    },
    {
      "epoch": 0.00721429742580751,
      "grad_norm": 6.096648216247559,
      "learning_rate": 3.12696703292044e-05,
      "loss": 4.3606,
      "step": 33
    },
    {
      "epoch": 0.007432912499316828,
      "grad_norm": 6.251641750335693,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 4.1731,
      "step": 34
    },
    {
      "epoch": 0.007651527572826147,
      "grad_norm": 9.29775619506836,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.4783,
      "step": 35
    },
    {
      "epoch": 0.007870142646335464,
      "grad_norm": 11.230655670166016,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.1192,
      "step": 36
    },
    {
      "epoch": 0.008088757719844783,
      "grad_norm": 10.136025428771973,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0439,
      "step": 37
    },
    {
      "epoch": 0.008307372793354102,
      "grad_norm": 9.469839096069336,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.9625,
      "step": 38
    },
    {
      "epoch": 0.00852598786686342,
      "grad_norm": 8.718362808227539,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.0432,
      "step": 39
    },
    {
      "epoch": 0.008744602940372739,
      "grad_norm": 9.521910667419434,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.9762,
      "step": 40
    },
    {
      "epoch": 0.008963218013882057,
      "grad_norm": 9.352231979370117,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0075,
      "step": 41
    },
    {
      "epoch": 0.009181833087391376,
      "grad_norm": 7.3484673500061035,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.955,
      "step": 42
    },
    {
      "epoch": 0.009400448160900694,
      "grad_norm": 8.650862693786621,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.0644,
      "step": 43
    },
    {
      "epoch": 0.009619063234410013,
      "grad_norm": 10.559455871582031,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.07,
      "step": 44
    },
    {
      "epoch": 0.009837678307919331,
      "grad_norm": 11.691309928894043,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.9961,
      "step": 45
    },
    {
      "epoch": 0.01005629338142865,
      "grad_norm": 8.233396530151367,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.0817,
      "step": 46
    },
    {
      "epoch": 0.010274908454937969,
      "grad_norm": 6.722311973571777,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.8507,
      "step": 47
    },
    {
      "epoch": 0.010493523528447287,
      "grad_norm": 6.870611190795898,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.8651,
      "step": 48
    },
    {
      "epoch": 0.010712138601956606,
      "grad_norm": 10.630144119262695,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.8569,
      "step": 49
    },
    {
      "epoch": 0.010930753675465924,
      "grad_norm": 8.184146881103516,
      "learning_rate": 0.0,
      "loss": 0.8619,
      "step": 50
    },
    {
      "epoch": 0.010930753675465924,
      "eval_loss": 0.9873545169830322,
      "eval_runtime": 568.3541,
      "eval_samples_per_second": 13.555,
      "eval_steps_per_second": 1.694,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.11922310751191e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}