{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.053882939314339594,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000538829393143396,
      "grad_norm": 0.24569196999073029,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.125,
      "step": 1
    },
    {
      "epoch": 0.000538829393143396,
      "eval_loss": NaN,
      "eval_runtime": 123.4386,
      "eval_samples_per_second": 25.324,
      "eval_steps_per_second": 6.335,
      "step": 1
    },
    {
      "epoch": 0.001077658786286792,
      "grad_norm": NaN,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0016164881794301878,
      "grad_norm": NaN,
      "learning_rate": 1.5e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.002155317572573584,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00269414696571698,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0032329763588603757,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003771805752003772,
      "grad_norm": NaN,
      "learning_rate": 3.5e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.004310635145147168,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0048494645382905635,
      "grad_norm": NaN,
      "learning_rate": 4.5e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00538829393143396,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.005927123324577356,
      "grad_norm": NaN,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.006465952717720751,
      "grad_norm": NaN,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.007004782110864148,
      "grad_norm": NaN,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.007543611504007544,
      "grad_norm": NaN,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.00808244089715094,
      "grad_norm": NaN,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.008621270290294336,
      "grad_norm": NaN,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.009160099683437731,
      "grad_norm": NaN,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.009698929076581127,
      "grad_norm": NaN,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.010237758469724523,
      "grad_norm": NaN,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.01077658786286792,
      "grad_norm": NaN,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.011315417256011316,
      "grad_norm": NaN,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.011854246649154711,
      "grad_norm": NaN,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.012393076042298107,
      "grad_norm": NaN,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.012931905435441503,
      "grad_norm": NaN,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.013470734828584898,
      "grad_norm": NaN,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.014009564221728296,
      "grad_norm": NaN,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.014548393614871691,
      "grad_norm": NaN,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.015087223008015087,
      "grad_norm": NaN,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.015626052401158483,
      "grad_norm": NaN,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.01616488179430188,
      "grad_norm": NaN,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.016703711187445274,
      "grad_norm": NaN,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.01724254058058867,
      "grad_norm": NaN,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.017781369973732065,
      "grad_norm": NaN,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.018320199366875463,
      "grad_norm": NaN,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.01885902876001886,
      "grad_norm": NaN,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.019397858153162254,
      "grad_norm": NaN,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.01993668754630565,
      "grad_norm": NaN,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.020475516939449045,
      "grad_norm": NaN,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.021014346332592443,
      "grad_norm": NaN,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.02155317572573584,
      "grad_norm": NaN,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.022092005118879234,
      "grad_norm": NaN,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.02263083451202263,
      "grad_norm": NaN,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.023169663905166026,
      "grad_norm": NaN,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.023708493298309423,
      "grad_norm": NaN,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.02424732269145282,
      "grad_norm": NaN,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.024786152084596214,
      "grad_norm": NaN,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.02532498147773961,
      "grad_norm": NaN,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.025863810870883006,
      "grad_norm": NaN,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.026402640264026403,
      "grad_norm": NaN,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.026941469657169797,
      "grad_norm": NaN,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.026941469657169797,
      "eval_loss": NaN,
      "eval_runtime": 122.6027,
      "eval_samples_per_second": 25.497,
      "eval_steps_per_second": 6.378,
      "step": 50
    },
    {
      "epoch": 0.027480299050313194,
      "grad_norm": NaN,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.02801912844345659,
      "grad_norm": NaN,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.028557957836599986,
      "grad_norm": NaN,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.029096787229743383,
      "grad_norm": NaN,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.029635616622886777,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.030174446016030174,
      "grad_norm": NaN,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.03071327540917357,
      "grad_norm": NaN,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.031252104802316966,
      "grad_norm": NaN,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.03179093419546036,
      "grad_norm": NaN,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.03232976358860376,
      "grad_norm": NaN,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.03286859298174715,
      "grad_norm": NaN,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.03340742237489055,
      "grad_norm": NaN,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.033946251768033946,
      "grad_norm": NaN,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.03448508116117734,
      "grad_norm": NaN,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.03502391055432074,
      "grad_norm": NaN,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.03556273994746413,
      "grad_norm": NaN,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.03610156934060753,
      "grad_norm": NaN,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.036640398733750926,
      "grad_norm": NaN,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.03717922812689432,
      "grad_norm": NaN,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.03771805752003772,
      "grad_norm": NaN,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.03825688691318111,
      "grad_norm": NaN,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.03879571630632451,
      "grad_norm": NaN,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.039334545699467906,
      "grad_norm": NaN,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.0398733750926113,
      "grad_norm": NaN,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.0404122044857547,
      "grad_norm": NaN,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.04095103387889809,
      "grad_norm": NaN,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.04148986327204149,
      "grad_norm": NaN,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.042028692665184886,
      "grad_norm": NaN,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.04256752205832828,
      "grad_norm": NaN,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.04310635145147168,
      "grad_norm": NaN,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.04364518084461507,
      "grad_norm": NaN,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.04418401023775847,
      "grad_norm": NaN,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.044722839630901866,
      "grad_norm": NaN,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.04526166902404526,
      "grad_norm": NaN,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.04580049841718866,
      "grad_norm": NaN,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.04633932781033205,
      "grad_norm": NaN,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.04687815720347545,
      "grad_norm": NaN,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.047416986596618846,
      "grad_norm": NaN,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.04795581598976224,
      "grad_norm": NaN,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.04849464538290564,
      "grad_norm": NaN,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.04903347477604903,
      "grad_norm": NaN,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.04957230416919243,
      "grad_norm": NaN,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.050111133562335826,
      "grad_norm": NaN,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.05064996295547922,
      "grad_norm": NaN,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.05118879234862262,
      "grad_norm": NaN,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.05172762174176601,
      "grad_norm": NaN,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.05226645113490941,
      "grad_norm": NaN,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.052805280528052806,
      "grad_norm": NaN,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.0533441099211962,
      "grad_norm": NaN,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.053882939314339594,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.053882939314339594,
      "eval_loss": NaN,
      "eval_runtime": 122.5451,
      "eval_samples_per_second": 25.509,
      "eval_steps_per_second": 6.381,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 3.736608642485453e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}