{
  "best_metric": 3.5215563774108887,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.003514629645901063,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.029259291802126e-05,
      "grad_norm": 9.411466598510742,
      "learning_rate": 0.0001,
      "loss": 6.8067,
      "step": 1
    },
    {
      "epoch": 7.029259291802126e-05,
      "eval_loss": 7.7762651443481445,
      "eval_runtime": 4432.0766,
      "eval_samples_per_second": 1.352,
      "eval_steps_per_second": 0.676,
      "step": 1
    },
    {
      "epoch": 0.00014058518583604253,
      "grad_norm": 9.495089530944824,
      "learning_rate": 0.0002,
      "loss": 6.2361,
      "step": 2
    },
    {
      "epoch": 0.00021087777875406378,
      "grad_norm": 8.74798583984375,
      "learning_rate": 0.00019978589232386035,
      "loss": 5.1303,
      "step": 3
    },
    {
      "epoch": 0.00028117037167208506,
      "grad_norm": 4.712350845336914,
      "learning_rate": 0.00019914448613738106,
      "loss": 4.4543,
      "step": 4
    },
    {
      "epoch": 0.00035146296459010633,
      "grad_norm": 4.159116744995117,
      "learning_rate": 0.00019807852804032305,
      "loss": 4.0895,
      "step": 5
    },
    {
      "epoch": 0.00042175555750812756,
      "grad_norm": 3.948648691177368,
      "learning_rate": 0.00019659258262890683,
      "loss": 3.9215,
      "step": 6
    },
    {
      "epoch": 0.0004920481504261489,
      "grad_norm": 4.281744003295898,
      "learning_rate": 0.0001946930129495106,
      "loss": 4.1163,
      "step": 7
    },
    {
      "epoch": 0.0005623407433441701,
      "grad_norm": 4.81821346282959,
      "learning_rate": 0.0001923879532511287,
      "loss": 3.53,
      "step": 8
    },
    {
      "epoch": 0.0006326333362621913,
      "grad_norm": 4.640680313110352,
      "learning_rate": 0.00018968727415326884,
      "loss": 3.731,
      "step": 9
    },
    {
      "epoch": 0.0007029259291802127,
      "grad_norm": 4.920532703399658,
      "learning_rate": 0.00018660254037844388,
      "loss": 3.3617,
      "step": 10
    },
    {
      "epoch": 0.0007732185220982339,
      "grad_norm": 4.455087661743164,
      "learning_rate": 0.00018314696123025454,
      "loss": 3.7523,
      "step": 11
    },
    {
      "epoch": 0.0008435111150162551,
      "grad_norm": 3.681004285812378,
      "learning_rate": 0.00017933533402912354,
      "loss": 3.9495,
      "step": 12
    },
    {
      "epoch": 0.0009138037079342764,
      "grad_norm": 3.6873984336853027,
      "learning_rate": 0.00017518398074789775,
      "loss": 3.2534,
      "step": 13
    },
    {
      "epoch": 0.0009840963008522978,
      "grad_norm": 4.170083522796631,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.6071,
      "step": 14
    },
    {
      "epoch": 0.001054388893770319,
      "grad_norm": 3.7524523735046387,
      "learning_rate": 0.00016593458151000688,
      "loss": 3.2183,
      "step": 15
    },
    {
      "epoch": 0.0011246814866883402,
      "grad_norm": 3.95082426071167,
      "learning_rate": 0.00016087614290087208,
      "loss": 3.6198,
      "step": 16
    },
    {
      "epoch": 0.0011949740796063616,
      "grad_norm": 4.456296920776367,
      "learning_rate": 0.00015555702330196023,
      "loss": 3.3993,
      "step": 17
    },
    {
      "epoch": 0.0012652666725243827,
      "grad_norm": 4.209654808044434,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.1265,
      "step": 18
    },
    {
      "epoch": 0.001335559265442404,
      "grad_norm": 4.037990093231201,
      "learning_rate": 0.00014422886902190014,
      "loss": 3.7803,
      "step": 19
    },
    {
      "epoch": 0.0014058518583604253,
      "grad_norm": 4.132318496704102,
      "learning_rate": 0.000138268343236509,
      "loss": 3.8329,
      "step": 20
    },
    {
      "epoch": 0.0014761444512784464,
      "grad_norm": 4.986948490142822,
      "learning_rate": 0.00013214394653031616,
      "loss": 4.0136,
      "step": 21
    },
    {
      "epoch": 0.0015464370441964678,
      "grad_norm": 3.795536518096924,
      "learning_rate": 0.00012588190451025207,
      "loss": 3.6991,
      "step": 22
    },
    {
      "epoch": 0.0016167296371144891,
      "grad_norm": 4.052053451538086,
      "learning_rate": 0.00011950903220161285,
      "loss": 3.9433,
      "step": 23
    },
    {
      "epoch": 0.0016870222300325102,
      "grad_norm": 3.4409587383270264,
      "learning_rate": 0.00011305261922200519,
      "loss": 3.2573,
      "step": 24
    },
    {
      "epoch": 0.0017573148229505316,
      "grad_norm": 4.064533710479736,
      "learning_rate": 0.00010654031292301432,
      "loss": 3.4339,
      "step": 25
    },
    {
      "epoch": 0.0017573148229505316,
      "eval_loss": 3.6852939128875732,
      "eval_runtime": 4443.7138,
      "eval_samples_per_second": 1.348,
      "eval_steps_per_second": 0.674,
      "step": 25
    },
    {
      "epoch": 0.001827607415868553,
      "grad_norm": 4.198983192443848,
      "learning_rate": 0.0001,
      "loss": 3.808,
      "step": 26
    },
    {
      "epoch": 0.001897900008786574,
      "grad_norm": 4.138834476470947,
      "learning_rate": 9.345968707698569e-05,
      "loss": 3.1475,
      "step": 27
    },
    {
      "epoch": 0.0019681926017045956,
      "grad_norm": 4.510487079620361,
      "learning_rate": 8.694738077799488e-05,
      "loss": 3.5543,
      "step": 28
    },
    {
      "epoch": 0.0020384851946226167,
      "grad_norm": 4.65043830871582,
      "learning_rate": 8.049096779838719e-05,
      "loss": 4.5274,
      "step": 29
    },
    {
      "epoch": 0.002108777787540638,
      "grad_norm": 4.022218704223633,
      "learning_rate": 7.411809548974792e-05,
      "loss": 3.8214,
      "step": 30
    },
    {
      "epoch": 0.0021790703804586593,
      "grad_norm": 3.9271130561828613,
      "learning_rate": 6.785605346968386e-05,
      "loss": 3.8296,
      "step": 31
    },
    {
      "epoch": 0.0022493629733766804,
      "grad_norm": 4.240511417388916,
      "learning_rate": 6.173165676349103e-05,
      "loss": 3.8647,
      "step": 32
    },
    {
      "epoch": 0.0023196555662947016,
      "grad_norm": 3.677292585372925,
      "learning_rate": 5.577113097809989e-05,
      "loss": 3.6044,
      "step": 33
    },
    {
      "epoch": 0.002389948159212723,
      "grad_norm": 4.133325099945068,
      "learning_rate": 5.000000000000002e-05,
      "loss": 4.2386,
      "step": 34
    },
    {
      "epoch": 0.0024602407521307442,
      "grad_norm": 4.031435012817383,
      "learning_rate": 4.444297669803981e-05,
      "loss": 3.8542,
      "step": 35
    },
    {
      "epoch": 0.0025305333450487653,
      "grad_norm": 3.931450843811035,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 3.8882,
      "step": 36
    },
    {
      "epoch": 0.002600825937966787,
      "grad_norm": 4.674798488616943,
      "learning_rate": 3.406541848999312e-05,
      "loss": 4.5656,
      "step": 37
    },
    {
      "epoch": 0.002671118530884808,
      "grad_norm": 3.8759536743164062,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 3.3743,
      "step": 38
    },
    {
      "epoch": 0.002741411123802829,
      "grad_norm": 3.7546091079711914,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 3.6026,
      "step": 39
    },
    {
      "epoch": 0.0028117037167208507,
      "grad_norm": 4.065143585205078,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 3.7303,
      "step": 40
    },
    {
      "epoch": 0.002881996309638872,
      "grad_norm": 4.17460298538208,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 4.0344,
      "step": 41
    },
    {
      "epoch": 0.002952288902556893,
      "grad_norm": 4.61301851272583,
      "learning_rate": 1.339745962155613e-05,
      "loss": 3.849,
      "step": 42
    },
    {
      "epoch": 0.0030225814954749144,
      "grad_norm": 4.693392753601074,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 4.1393,
      "step": 43
    },
    {
      "epoch": 0.0030928740883929356,
      "grad_norm": 4.002664566040039,
      "learning_rate": 7.612046748871327e-06,
      "loss": 3.7645,
      "step": 44
    },
    {
      "epoch": 0.0031631666813109567,
      "grad_norm": 3.897087812423706,
      "learning_rate": 5.306987050489442e-06,
      "loss": 3.599,
      "step": 45
    },
    {
      "epoch": 0.0032334592742289782,
      "grad_norm": 4.300354957580566,
      "learning_rate": 3.40741737109318e-06,
      "loss": 4.1152,
      "step": 46
    },
    {
      "epoch": 0.0033037518671469993,
      "grad_norm": 4.223507404327393,
      "learning_rate": 1.921471959676957e-06,
      "loss": 3.5119,
      "step": 47
    },
    {
      "epoch": 0.0033740444600650205,
      "grad_norm": 4.682356834411621,
      "learning_rate": 8.555138626189618e-07,
      "loss": 4.2198,
      "step": 48
    },
    {
      "epoch": 0.003444337052983042,
      "grad_norm": 4.126323223114014,
      "learning_rate": 2.141076761396521e-07,
      "loss": 3.8349,
      "step": 49
    },
    {
      "epoch": 0.003514629645901063,
      "grad_norm": 5.588482856750488,
      "learning_rate": 0.0,
      "loss": 4.7042,
      "step": 50
    },
    {
      "epoch": 0.003514629645901063,
      "eval_loss": 3.5215563774108887,
      "eval_runtime": 4445.4742,
      "eval_samples_per_second": 1.347,
      "eval_steps_per_second": 0.674,
      "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": 8.23612542025728e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}