{
  "best_metric": 5.311061859130859,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5076142131979695,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01015228426395939,
      "grad_norm": 0.46062880754470825,
      "learning_rate": 5e-06,
      "loss": 5.3841,
      "step": 1
    },
    {
      "epoch": 0.01015228426395939,
      "eval_loss": 5.5305962562561035,
      "eval_runtime": 8.7087,
      "eval_samples_per_second": 19.061,
      "eval_steps_per_second": 9.531,
      "step": 1
    },
    {
      "epoch": 0.02030456852791878,
      "grad_norm": 0.5978866815567017,
      "learning_rate": 1e-05,
      "loss": 5.4053,
      "step": 2
    },
    {
      "epoch": 0.030456852791878174,
      "grad_norm": 0.4448310434818268,
      "learning_rate": 1.5e-05,
      "loss": 5.3689,
      "step": 3
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 0.507191002368927,
      "learning_rate": 2e-05,
      "loss": 5.4424,
      "step": 4
    },
    {
      "epoch": 0.050761421319796954,
      "grad_norm": 0.4688023626804352,
      "learning_rate": 2.5e-05,
      "loss": 5.4252,
      "step": 5
    },
    {
      "epoch": 0.06091370558375635,
      "grad_norm": 0.4471573531627655,
      "learning_rate": 3e-05,
      "loss": 5.3927,
      "step": 6
    },
    {
      "epoch": 0.07106598984771574,
      "grad_norm": 0.45171481370925903,
      "learning_rate": 3.5e-05,
      "loss": 5.3751,
      "step": 7
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 0.6176170706748962,
      "learning_rate": 4e-05,
      "loss": 5.4215,
      "step": 8
    },
    {
      "epoch": 0.09137055837563451,
      "grad_norm": 0.5099933743476868,
      "learning_rate": 4.5e-05,
      "loss": 5.3422,
      "step": 9
    },
    {
      "epoch": 0.10152284263959391,
      "grad_norm": 0.48276761174201965,
      "learning_rate": 5e-05,
      "loss": 5.4263,
      "step": 10
    },
    {
      "epoch": 0.1116751269035533,
      "grad_norm": 0.5048362612724304,
      "learning_rate": 5.500000000000001e-05,
      "loss": 5.3427,
      "step": 11
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 0.5130631923675537,
      "learning_rate": 6e-05,
      "loss": 5.3817,
      "step": 12
    },
    {
      "epoch": 0.1319796954314721,
      "grad_norm": 0.5273154377937317,
      "learning_rate": 6.500000000000001e-05,
      "loss": 5.3019,
      "step": 13
    },
    {
      "epoch": 0.14213197969543148,
      "grad_norm": 0.523825466632843,
      "learning_rate": 7e-05,
      "loss": 5.2535,
      "step": 14
    },
    {
      "epoch": 0.15228426395939088,
      "grad_norm": 0.6113125681877136,
      "learning_rate": 7.500000000000001e-05,
      "loss": 5.3172,
      "step": 15
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 0.5640417337417603,
      "learning_rate": 8e-05,
      "loss": 5.2758,
      "step": 16
    },
    {
      "epoch": 0.17258883248730963,
      "grad_norm": 0.4186924397945404,
      "learning_rate": 8.5e-05,
      "loss": 5.2586,
      "step": 17
    },
    {
      "epoch": 0.18274111675126903,
      "grad_norm": 0.5193726420402527,
      "learning_rate": 9e-05,
      "loss": 5.2615,
      "step": 18
    },
    {
      "epoch": 0.19289340101522842,
      "grad_norm": 0.5647014379501343,
      "learning_rate": 9.5e-05,
      "loss": 5.2652,
      "step": 19
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 0.5719868540763855,
      "learning_rate": 0.0001,
      "loss": 5.1955,
      "step": 20
    },
    {
      "epoch": 0.2131979695431472,
      "grad_norm": 0.6991127133369446,
      "learning_rate": 9.999238475781957e-05,
      "loss": 5.1646,
      "step": 21
    },
    {
      "epoch": 0.2233502538071066,
      "grad_norm": 0.7082369327545166,
      "learning_rate": 9.99695413509548e-05,
      "loss": 5.1052,
      "step": 22
    },
    {
      "epoch": 0.233502538071066,
      "grad_norm": 0.7457136511802673,
      "learning_rate": 9.99314767377287e-05,
      "loss": 5.1863,
      "step": 23
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 1.6564850807189941,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.0987,
      "step": 24
    },
    {
      "epoch": 0.25380710659898476,
      "grad_norm": 5.510101318359375,
      "learning_rate": 9.980973490458728e-05,
      "loss": 5.5984,
      "step": 25
    },
    {
      "epoch": 0.2639593908629442,
      "grad_norm": 4.215838432312012,
      "learning_rate": 9.972609476841367e-05,
      "loss": 5.5124,
      "step": 26
    },
    {
      "epoch": 0.27411167512690354,
      "grad_norm": 1.8195075988769531,
      "learning_rate": 9.962730758206611e-05,
      "loss": 5.4004,
      "step": 27
    },
    {
      "epoch": 0.28426395939086296,
      "grad_norm": 1.5931973457336426,
      "learning_rate": 9.951340343707852e-05,
      "loss": 5.3794,
      "step": 28
    },
    {
      "epoch": 0.29441624365482233,
      "grad_norm": 0.6483675241470337,
      "learning_rate": 9.938441702975689e-05,
      "loss": 5.3566,
      "step": 29
    },
    {
      "epoch": 0.30456852791878175,
      "grad_norm": 0.3973766267299652,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.2972,
      "step": 30
    },
    {
      "epoch": 0.3147208121827411,
      "grad_norm": 0.3534790277481079,
      "learning_rate": 9.908135917238321e-05,
      "loss": 5.2902,
      "step": 31
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 0.3970736861228943,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.2949,
      "step": 32
    },
    {
      "epoch": 0.3350253807106599,
      "grad_norm": 0.37264251708984375,
      "learning_rate": 9.871850323926177e-05,
      "loss": 5.2944,
      "step": 33
    },
    {
      "epoch": 0.34517766497461927,
      "grad_norm": 0.3872509002685547,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.326,
      "step": 34
    },
    {
      "epoch": 0.3553299492385787,
      "grad_norm": 0.3853321969509125,
      "learning_rate": 9.829629131445342e-05,
      "loss": 5.2708,
      "step": 35
    },
    {
      "epoch": 0.36548223350253806,
      "grad_norm": 0.39588385820388794,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.3228,
      "step": 36
    },
    {
      "epoch": 0.3756345177664975,
      "grad_norm": 0.4093726575374603,
      "learning_rate": 9.781523779815179e-05,
      "loss": 5.2831,
      "step": 37
    },
    {
      "epoch": 0.38578680203045684,
      "grad_norm": 0.4420938491821289,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.2103,
      "step": 38
    },
    {
      "epoch": 0.39593908629441626,
      "grad_norm": 0.5512685775756836,
      "learning_rate": 9.727592877996585e-05,
      "loss": 5.1775,
      "step": 39
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 0.3994300067424774,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.2478,
      "step": 40
    },
    {
      "epoch": 0.41624365482233505,
      "grad_norm": 0.5147640705108643,
      "learning_rate": 9.667902132486009e-05,
      "loss": 5.1743,
      "step": 41
    },
    {
      "epoch": 0.4263959390862944,
      "grad_norm": 0.6237267851829529,
      "learning_rate": 9.635919272833938e-05,
      "loss": 5.2249,
      "step": 42
    },
    {
      "epoch": 0.4365482233502538,
      "grad_norm": 0.5305359363555908,
      "learning_rate": 9.602524267262203e-05,
      "loss": 5.2915,
      "step": 43
    },
    {
      "epoch": 0.4467005076142132,
      "grad_norm": 0.4987878203392029,
      "learning_rate": 9.567727288213005e-05,
      "loss": 5.253,
      "step": 44
    },
    {
      "epoch": 0.45685279187817257,
      "grad_norm": 0.6333546042442322,
      "learning_rate": 9.53153893518325e-05,
      "loss": 5.1612,
      "step": 45
    },
    {
      "epoch": 0.467005076142132,
      "grad_norm": 0.7043673396110535,
      "learning_rate": 9.493970231495835e-05,
      "loss": 5.1424,
      "step": 46
    },
    {
      "epoch": 0.47715736040609136,
      "grad_norm": 0.6457162499427795,
      "learning_rate": 9.45503262094184e-05,
      "loss": 5.1876,
      "step": 47
    },
    {
      "epoch": 0.4873096446700508,
      "grad_norm": 0.9820389151573181,
      "learning_rate": 9.414737964294636e-05,
      "loss": 5.0792,
      "step": 48
    },
    {
      "epoch": 0.49746192893401014,
      "grad_norm": 2.78731369972229,
      "learning_rate": 9.373098535696979e-05,
      "loss": 5.5062,
      "step": 49
    },
    {
      "epoch": 0.5076142131979695,
      "grad_norm": 2.0711777210235596,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.4469,
      "step": 50
    },
    {
      "epoch": 0.5076142131979695,
      "eval_loss": 5.311061859130859,
      "eval_runtime": 8.7447,
      "eval_samples_per_second": 18.983,
      "eval_steps_per_second": 9.491,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.84541717577728e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}