{
  "best_metric": 4.377738878247328e-05,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.04144218814753419,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008288437629506838,
      "grad_norm": 46.59734344482422,
      "learning_rate": 0.0001,
      "loss": 5.1604,
      "step": 1
    },
    {
      "epoch": 0.0008288437629506838,
      "eval_loss": 5.056265354156494,
      "eval_runtime": 176.791,
      "eval_samples_per_second": 2.873,
      "eval_steps_per_second": 1.437,
      "step": 1
    },
    {
      "epoch": 0.0016576875259013675,
      "grad_norm": 37.48451614379883,
      "learning_rate": 0.0002,
      "loss": 4.8102,
      "step": 2
    },
    {
      "epoch": 0.0024865312888520514,
      "grad_norm": 18.382753372192383,
      "learning_rate": 0.00019978589232386035,
      "loss": 2.7822,
      "step": 3
    },
    {
      "epoch": 0.003315375051802735,
      "grad_norm": 5.563159465789795,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.1321,
      "step": 4
    },
    {
      "epoch": 0.004144218814753419,
      "grad_norm": 22.373699188232422,
      "learning_rate": 0.00019807852804032305,
      "loss": 2.4183,
      "step": 5
    },
    {
      "epoch": 0.004973062577704103,
      "grad_norm": 88.56672668457031,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.6643,
      "step": 6
    },
    {
      "epoch": 0.005801906340654786,
      "grad_norm": 31.46352195739746,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.5551,
      "step": 7
    },
    {
      "epoch": 0.00663075010360547,
      "grad_norm": 13.473725318908691,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.2948,
      "step": 8
    },
    {
      "epoch": 0.0074595938665561546,
      "grad_norm": 15.799386978149414,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.1593,
      "step": 9
    },
    {
      "epoch": 0.008288437629506838,
      "grad_norm": 8.64849853515625,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0422,
      "step": 10
    },
    {
      "epoch": 0.009117281392457521,
      "grad_norm": 3.842252016067505,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.01,
      "step": 11
    },
    {
      "epoch": 0.009946125155408206,
      "grad_norm": 0.018445704132318497,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.0002,
      "step": 12
    },
    {
      "epoch": 0.01077496891835889,
      "grad_norm": 0.008284776471555233,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.0002,
      "step": 13
    },
    {
      "epoch": 0.011603812681309573,
      "grad_norm": 28.959819793701172,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0574,
      "step": 14
    },
    {
      "epoch": 0.012432656444260257,
      "grad_norm": 0.05831862986087799,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.0007,
      "step": 15
    },
    {
      "epoch": 0.01326150020721094,
      "grad_norm": 1.0814573764801025,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.004,
      "step": 16
    },
    {
      "epoch": 0.014090343970161625,
      "grad_norm": 0.014470446854829788,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.0001,
      "step": 17
    },
    {
      "epoch": 0.014919187733112309,
      "grad_norm": 0.007898575626313686,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0001,
      "step": 18
    },
    {
      "epoch": 0.015748031496062992,
      "grad_norm": 0.13030454516410828,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.0002,
      "step": 19
    },
    {
      "epoch": 0.016576875259013676,
      "grad_norm": 180.7052001953125,
      "learning_rate": 0.000138268343236509,
      "loss": 0.1543,
      "step": 20
    },
    {
      "epoch": 0.01740571902196436,
      "grad_norm": 0.005868172738701105,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0001,
      "step": 21
    },
    {
      "epoch": 0.018234562784915042,
      "grad_norm": 0.003525336505845189,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0001,
      "step": 22
    },
    {
      "epoch": 0.019063406547865726,
      "grad_norm": 0.0039000571705400944,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0001,
      "step": 23
    },
    {
      "epoch": 0.01989225031081641,
      "grad_norm": 0.004776377230882645,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.0001,
      "step": 24
    },
    {
      "epoch": 0.020721094073767096,
      "grad_norm": 0.0036495423410087824,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.0001,
      "step": 25
    },
    {
      "epoch": 0.020721094073767096,
      "eval_loss": 0.045247744768857956,
      "eval_runtime": 177.8269,
      "eval_samples_per_second": 2.857,
      "eval_steps_per_second": 1.428,
      "step": 25
    },
    {
      "epoch": 0.02154993783671778,
      "grad_norm": 0.0020936632063239813,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.02237878159966846,
      "grad_norm": 0.002664591884240508,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.0001,
      "step": 27
    },
    {
      "epoch": 0.023207625362619146,
      "grad_norm": 72.78241729736328,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.1995,
      "step": 28
    },
    {
      "epoch": 0.02403646912556983,
      "grad_norm": 0.0020621209405362606,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.024865312888520515,
      "grad_norm": 0.0009359201067127287,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0256941566514712,
      "grad_norm": 0.0020899970550090075,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.02652300041442188,
      "grad_norm": 0.0018738162470981479,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.027351844177372565,
      "grad_norm": 0.0023636827245354652,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.02818068794032325,
      "grad_norm": 0.0009740522946231067,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.029009531703273934,
      "grad_norm": 0.002191737527027726,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.029838375466224618,
      "grad_norm": 0.003524180967360735,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.0001,
      "step": 36
    },
    {
      "epoch": 0.0306672192291753,
      "grad_norm": 0.0019169780425727367,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.031496062992125984,
      "grad_norm": 0.004368058405816555,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0001,
      "step": 38
    },
    {
      "epoch": 0.03232490675507667,
      "grad_norm": 0.0032108398154377937,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.0001,
      "step": 39
    },
    {
      "epoch": 0.03315375051802735,
      "grad_norm": 0.0013856951845809817,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.03398259428097804,
      "grad_norm": 0.0030144485644996166,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.0001,
      "step": 41
    },
    {
      "epoch": 0.03481143804392872,
      "grad_norm": 0.010318023152649403,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0001,
      "step": 42
    },
    {
      "epoch": 0.035640281806879406,
      "grad_norm": 0.004577960353344679,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.0001,
      "step": 43
    },
    {
      "epoch": 0.036469125569830084,
      "grad_norm": 0.0027028091717511415,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.03729796933278077,
      "grad_norm": 0.006148059386759996,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.0001,
      "step": 45
    },
    {
      "epoch": 0.03812681309573145,
      "grad_norm": 0.0023762828204780817,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.03895565685868214,
      "grad_norm": 0.001622220384888351,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.03978450062163282,
      "grad_norm": 0.0023418988566845655,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.04061334438458351,
      "grad_norm": 0.0022706985473632812,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.04144218814753419,
      "grad_norm": 0.002968005370348692,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "step": 50
    },
    {
      "epoch": 0.04144218814753419,
      "eval_loss": 4.377738878247328e-05,
      "eval_runtime": 177.8228,
      "eval_samples_per_second": 2.857,
      "eval_steps_per_second": 1.428,
      "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": 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": 7.41887283560448e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}