{
  "best_metric": 1.1002987623214722,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0009760144450137862,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9520288900275725e-05,
      "grad_norm": 10.334268569946289,
      "learning_rate": 0.0001,
      "loss": 4.7093,
      "step": 1
    },
    {
      "epoch": 1.9520288900275725e-05,
      "eval_loss": 1.3136714696884155,
      "eval_runtime": 6002.6747,
      "eval_samples_per_second": 3.593,
      "eval_steps_per_second": 1.797,
      "step": 1
    },
    {
      "epoch": 3.904057780055145e-05,
      "grad_norm": 12.176424980163574,
      "learning_rate": 0.0002,
      "loss": 5.0525,
      "step": 2
    },
    {
      "epoch": 5.856086670082717e-05,
      "grad_norm": 8.576818466186523,
      "learning_rate": 0.00019978589232386035,
      "loss": 4.7167,
      "step": 3
    },
    {
      "epoch": 7.80811556011029e-05,
      "grad_norm": 18.30161476135254,
      "learning_rate": 0.00019914448613738106,
      "loss": 5.2112,
      "step": 4
    },
    {
      "epoch": 9.760144450137862e-05,
      "grad_norm": 8.57841682434082,
      "learning_rate": 0.00019807852804032305,
      "loss": 4.479,
      "step": 5
    },
    {
      "epoch": 0.00011712173340165434,
      "grad_norm": 5.883150100708008,
      "learning_rate": 0.00019659258262890683,
      "loss": 4.0482,
      "step": 6
    },
    {
      "epoch": 0.00013664202230193008,
      "grad_norm": 6.208558082580566,
      "learning_rate": 0.0001946930129495106,
      "loss": 4.6876,
      "step": 7
    },
    {
      "epoch": 0.0001561623112022058,
      "grad_norm": 7.253965377807617,
      "learning_rate": 0.0001923879532511287,
      "loss": 4.4962,
      "step": 8
    },
    {
      "epoch": 0.00017568260010248152,
      "grad_norm": 7.173295497894287,
      "learning_rate": 0.00018968727415326884,
      "loss": 4.579,
      "step": 9
    },
    {
      "epoch": 0.00019520288900275724,
      "grad_norm": 6.47155237197876,
      "learning_rate": 0.00018660254037844388,
      "loss": 4.7364,
      "step": 10
    },
    {
      "epoch": 0.00021472317790303296,
      "grad_norm": 6.548929691314697,
      "learning_rate": 0.00018314696123025454,
      "loss": 4.2588,
      "step": 11
    },
    {
      "epoch": 0.00023424346680330868,
      "grad_norm": 6.918939113616943,
      "learning_rate": 0.00017933533402912354,
      "loss": 4.2177,
      "step": 12
    },
    {
      "epoch": 0.0002537637557035844,
      "grad_norm": 5.7343363761901855,
      "learning_rate": 0.00017518398074789775,
      "loss": 4.3725,
      "step": 13
    },
    {
      "epoch": 0.00027328404460386015,
      "grad_norm": 5.065625190734863,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.0603,
      "step": 14
    },
    {
      "epoch": 0.00029280433350413584,
      "grad_norm": 6.888638496398926,
      "learning_rate": 0.00016593458151000688,
      "loss": 4.4999,
      "step": 15
    },
    {
      "epoch": 0.0003123246224044116,
      "grad_norm": 6.872077465057373,
      "learning_rate": 0.00016087614290087208,
      "loss": 4.2474,
      "step": 16
    },
    {
      "epoch": 0.0003318449113046873,
      "grad_norm": 5.9835309982299805,
      "learning_rate": 0.00015555702330196023,
      "loss": 4.4801,
      "step": 17
    },
    {
      "epoch": 0.00035136520020496304,
      "grad_norm": 6.098293304443359,
      "learning_rate": 0.00015000000000000001,
      "loss": 4.1836,
      "step": 18
    },
    {
      "epoch": 0.0003708854891052388,
      "grad_norm": 5.965084075927734,
      "learning_rate": 0.00014422886902190014,
      "loss": 4.7496,
      "step": 19
    },
    {
      "epoch": 0.0003904057780055145,
      "grad_norm": 6.869338512420654,
      "learning_rate": 0.000138268343236509,
      "loss": 4.4003,
      "step": 20
    },
    {
      "epoch": 0.0004099260669057902,
      "grad_norm": 5.926541805267334,
      "learning_rate": 0.00013214394653031616,
      "loss": 4.0398,
      "step": 21
    },
    {
      "epoch": 0.0004294463558060659,
      "grad_norm": 6.244675636291504,
      "learning_rate": 0.00012588190451025207,
      "loss": 4.2699,
      "step": 22
    },
    {
      "epoch": 0.00044896664470634167,
      "grad_norm": 6.214200496673584,
      "learning_rate": 0.00011950903220161285,
      "loss": 4.465,
      "step": 23
    },
    {
      "epoch": 0.00046848693360661736,
      "grad_norm": 5.795085430145264,
      "learning_rate": 0.00011305261922200519,
      "loss": 4.281,
      "step": 24
    },
    {
      "epoch": 0.0004880072225068931,
      "grad_norm": 6.204129219055176,
      "learning_rate": 0.00010654031292301432,
      "loss": 4.0462,
      "step": 25
    },
    {
      "epoch": 0.0004880072225068931,
      "eval_loss": 1.1002987623214722,
      "eval_runtime": 6028.5222,
      "eval_samples_per_second": 3.578,
      "eval_steps_per_second": 1.789,
      "step": 25
    },
    {
      "epoch": 0.0005075275114071688,
      "grad_norm": 5.981378078460693,
      "learning_rate": 0.0001,
      "loss": 4.6663,
      "step": 26
    },
    {
      "epoch": 0.0005270478003074446,
      "grad_norm": 6.813650131225586,
      "learning_rate": 9.345968707698569e-05,
      "loss": 4.4858,
      "step": 27
    },
    {
      "epoch": 0.0005465680892077203,
      "grad_norm": 5.694484710693359,
      "learning_rate": 8.694738077799488e-05,
      "loss": 3.8496,
      "step": 28
    },
    {
      "epoch": 0.000566088378107996,
      "grad_norm": 5.858161449432373,
      "learning_rate": 8.049096779838719e-05,
      "loss": 4.4739,
      "step": 29
    },
    {
      "epoch": 0.0005856086670082717,
      "grad_norm": 6.250691890716553,
      "learning_rate": 7.411809548974792e-05,
      "loss": 4.0139,
      "step": 30
    },
    {
      "epoch": 0.0006051289559085474,
      "grad_norm": 5.8988752365112305,
      "learning_rate": 6.785605346968386e-05,
      "loss": 4.0186,
      "step": 31
    },
    {
      "epoch": 0.0006246492448088232,
      "grad_norm": 6.843201637268066,
      "learning_rate": 6.173165676349103e-05,
      "loss": 4.3718,
      "step": 32
    },
    {
      "epoch": 0.0006441695337090989,
      "grad_norm": 7.384850025177002,
      "learning_rate": 5.577113097809989e-05,
      "loss": 4.5045,
      "step": 33
    },
    {
      "epoch": 0.0006636898226093746,
      "grad_norm": 7.434286594390869,
      "learning_rate": 5.000000000000002e-05,
      "loss": 4.2881,
      "step": 34
    },
    {
      "epoch": 0.0006832101115096503,
      "grad_norm": 7.059499740600586,
      "learning_rate": 4.444297669803981e-05,
      "loss": 4.4589,
      "step": 35
    },
    {
      "epoch": 0.0007027304004099261,
      "grad_norm": 7.253593444824219,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 4.148,
      "step": 36
    },
    {
      "epoch": 0.0007222506893102018,
      "grad_norm": 7.907142639160156,
      "learning_rate": 3.406541848999312e-05,
      "loss": 4.2299,
      "step": 37
    },
    {
      "epoch": 0.0007417709782104776,
      "grad_norm": 7.825556755065918,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 4.2046,
      "step": 38
    },
    {
      "epoch": 0.0007612912671107532,
      "grad_norm": 7.069599628448486,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 3.8814,
      "step": 39
    },
    {
      "epoch": 0.000780811556011029,
      "grad_norm": 7.556497097015381,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 4.1689,
      "step": 40
    },
    {
      "epoch": 0.0008003318449113047,
      "grad_norm": 8.259849548339844,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 3.7389,
      "step": 41
    },
    {
      "epoch": 0.0008198521338115805,
      "grad_norm": 8.705476760864258,
      "learning_rate": 1.339745962155613e-05,
      "loss": 4.6672,
      "step": 42
    },
    {
      "epoch": 0.0008393724227118561,
      "grad_norm": 7.974400043487549,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 3.6511,
      "step": 43
    },
    {
      "epoch": 0.0008588927116121318,
      "grad_norm": 7.9710540771484375,
      "learning_rate": 7.612046748871327e-06,
      "loss": 3.8957,
      "step": 44
    },
    {
      "epoch": 0.0008784130005124076,
      "grad_norm": 9.321637153625488,
      "learning_rate": 5.306987050489442e-06,
      "loss": 3.827,
      "step": 45
    },
    {
      "epoch": 0.0008979332894126833,
      "grad_norm": 9.066277503967285,
      "learning_rate": 3.40741737109318e-06,
      "loss": 4.1383,
      "step": 46
    },
    {
      "epoch": 0.0009174535783129591,
      "grad_norm": 10.388931274414062,
      "learning_rate": 1.921471959676957e-06,
      "loss": 4.7694,
      "step": 47
    },
    {
      "epoch": 0.0009369738672132347,
      "grad_norm": 11.57152271270752,
      "learning_rate": 8.555138626189618e-07,
      "loss": 4.068,
      "step": 48
    },
    {
      "epoch": 0.0009564941561135105,
      "grad_norm": 10.462427139282227,
      "learning_rate": 2.141076761396521e-07,
      "loss": 4.6273,
      "step": 49
    },
    {
      "epoch": 0.0009760144450137862,
      "grad_norm": 12.40966510772705,
      "learning_rate": 0.0,
      "loss": 5.1242,
      "step": 50
    },
    {
      "epoch": 0.0009760144450137862,
      "eval_loss": 1.1065218448638916,
      "eval_runtime": 6027.0265,
      "eval_samples_per_second": 3.579,
      "eval_steps_per_second": 1.789,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.066459555076506e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}