{
  "best_metric": 3.4573135375976562,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0008018410269979874,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6036820539959746e-05,
      "grad_norm": 2.014047145843506,
      "learning_rate": 0.0001,
      "loss": 3.9524,
      "step": 1
    },
    {
      "epoch": 1.6036820539959746e-05,
      "eval_loss": 5.2951202392578125,
      "eval_runtime": 7124.4274,
      "eval_samples_per_second": 3.685,
      "eval_steps_per_second": 1.843,
      "step": 1
    },
    {
      "epoch": 3.207364107991949e-05,
      "grad_norm": 2.957817792892456,
      "learning_rate": 0.0002,
      "loss": 4.7238,
      "step": 2
    },
    {
      "epoch": 4.811046161987924e-05,
      "grad_norm": 2.4472718238830566,
      "learning_rate": 0.00019978589232386035,
      "loss": 4.4611,
      "step": 3
    },
    {
      "epoch": 6.414728215983899e-05,
      "grad_norm": 2.3270387649536133,
      "learning_rate": 0.00019914448613738106,
      "loss": 4.0052,
      "step": 4
    },
    {
      "epoch": 8.018410269979874e-05,
      "grad_norm": 2.020864963531494,
      "learning_rate": 0.00019807852804032305,
      "loss": 4.2212,
      "step": 5
    },
    {
      "epoch": 9.622092323975848e-05,
      "grad_norm": 1.8430637121200562,
      "learning_rate": 0.00019659258262890683,
      "loss": 3.4336,
      "step": 6
    },
    {
      "epoch": 0.00011225774377971823,
      "grad_norm": 2.4499564170837402,
      "learning_rate": 0.0001946930129495106,
      "loss": 3.5644,
      "step": 7
    },
    {
      "epoch": 0.00012829456431967797,
      "grad_norm": 2.100043535232544,
      "learning_rate": 0.0001923879532511287,
      "loss": 3.4172,
      "step": 8
    },
    {
      "epoch": 0.00014433138485963774,
      "grad_norm": 1.809827446937561,
      "learning_rate": 0.00018968727415326884,
      "loss": 3.432,
      "step": 9
    },
    {
      "epoch": 0.00016036820539959748,
      "grad_norm": 2.047074794769287,
      "learning_rate": 0.00018660254037844388,
      "loss": 3.4664,
      "step": 10
    },
    {
      "epoch": 0.00017640502593955723,
      "grad_norm": 2.0685312747955322,
      "learning_rate": 0.00018314696123025454,
      "loss": 3.7947,
      "step": 11
    },
    {
      "epoch": 0.00019244184647951697,
      "grad_norm": 1.8843048810958862,
      "learning_rate": 0.00017933533402912354,
      "loss": 3.3569,
      "step": 12
    },
    {
      "epoch": 0.0002084786670194767,
      "grad_norm": 1.5609772205352783,
      "learning_rate": 0.00017518398074789775,
      "loss": 3.1331,
      "step": 13
    },
    {
      "epoch": 0.00022451548755943646,
      "grad_norm": 1.5881112813949585,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.1722,
      "step": 14
    },
    {
      "epoch": 0.00024055230809939623,
      "grad_norm": 1.5168817043304443,
      "learning_rate": 0.00016593458151000688,
      "loss": 3.1226,
      "step": 15
    },
    {
      "epoch": 0.00025658912863935594,
      "grad_norm": 1.7541691064834595,
      "learning_rate": 0.00016087614290087208,
      "loss": 3.1655,
      "step": 16
    },
    {
      "epoch": 0.0002726259491793157,
      "grad_norm": 1.376575231552124,
      "learning_rate": 0.00015555702330196023,
      "loss": 3.2914,
      "step": 17
    },
    {
      "epoch": 0.0002886627697192755,
      "grad_norm": 1.4468505382537842,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.1013,
      "step": 18
    },
    {
      "epoch": 0.0003046995902592352,
      "grad_norm": 1.3390285968780518,
      "learning_rate": 0.00014422886902190014,
      "loss": 3.0973,
      "step": 19
    },
    {
      "epoch": 0.00032073641079919497,
      "grad_norm": 1.3495227098464966,
      "learning_rate": 0.000138268343236509,
      "loss": 3.1966,
      "step": 20
    },
    {
      "epoch": 0.0003367732313391547,
      "grad_norm": 1.5788706541061401,
      "learning_rate": 0.00013214394653031616,
      "loss": 3.2838,
      "step": 21
    },
    {
      "epoch": 0.00035281005187911445,
      "grad_norm": 1.330959677696228,
      "learning_rate": 0.00012588190451025207,
      "loss": 3.4004,
      "step": 22
    },
    {
      "epoch": 0.0003688468724190742,
      "grad_norm": 1.814831018447876,
      "learning_rate": 0.00011950903220161285,
      "loss": 3.4603,
      "step": 23
    },
    {
      "epoch": 0.00038488369295903394,
      "grad_norm": 1.408077359199524,
      "learning_rate": 0.00011305261922200519,
      "loss": 3.1551,
      "step": 24
    },
    {
      "epoch": 0.0004009205134989937,
      "grad_norm": 1.7404779195785522,
      "learning_rate": 0.00010654031292301432,
      "loss": 3.4693,
      "step": 25
    },
    {
      "epoch": 0.0004009205134989937,
      "eval_loss": 3.4573135375976562,
      "eval_runtime": 7153.1181,
      "eval_samples_per_second": 3.671,
      "eval_steps_per_second": 1.835,
      "step": 25
    },
    {
      "epoch": 0.0004169573340389534,
      "grad_norm": 1.6844600439071655,
      "learning_rate": 0.0001,
      "loss": 3.7521,
      "step": 26
    },
    {
      "epoch": 0.00043299415457891317,
      "grad_norm": 1.4900075197219849,
      "learning_rate": 9.345968707698569e-05,
      "loss": 3.6154,
      "step": 27
    },
    {
      "epoch": 0.0004490309751188729,
      "grad_norm": 1.4075506925582886,
      "learning_rate": 8.694738077799488e-05,
      "loss": 3.3308,
      "step": 28
    },
    {
      "epoch": 0.00046506779565883265,
      "grad_norm": 1.423120379447937,
      "learning_rate": 8.049096779838719e-05,
      "loss": 3.4076,
      "step": 29
    },
    {
      "epoch": 0.00048110461619879245,
      "grad_norm": 1.6669692993164062,
      "learning_rate": 7.411809548974792e-05,
      "loss": 3.5694,
      "step": 30
    },
    {
      "epoch": 0.0004971414367387521,
      "grad_norm": 1.521008849143982,
      "learning_rate": 6.785605346968386e-05,
      "loss": 3.2869,
      "step": 31
    },
    {
      "epoch": 0.0005131782572787119,
      "grad_norm": 1.3426971435546875,
      "learning_rate": 6.173165676349103e-05,
      "loss": 3.0856,
      "step": 32
    },
    {
      "epoch": 0.0005292150778186716,
      "grad_norm": 1.8642768859863281,
      "learning_rate": 5.577113097809989e-05,
      "loss": 3.4737,
      "step": 33
    },
    {
      "epoch": 0.0005452518983586314,
      "grad_norm": 1.984915852546692,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.7566,
      "step": 34
    },
    {
      "epoch": 0.0005612887188985911,
      "grad_norm": 2.1844921112060547,
      "learning_rate": 4.444297669803981e-05,
      "loss": 3.6506,
      "step": 35
    },
    {
      "epoch": 0.000577325539438551,
      "grad_norm": 2.1441352367401123,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 3.8077,
      "step": 36
    },
    {
      "epoch": 0.0005933623599785107,
      "grad_norm": 1.569007158279419,
      "learning_rate": 3.406541848999312e-05,
      "loss": 3.5146,
      "step": 37
    },
    {
      "epoch": 0.0006093991805184704,
      "grad_norm": 1.796990990638733,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 3.8353,
      "step": 38
    },
    {
      "epoch": 0.0006254360010584302,
      "grad_norm": 2.0539660453796387,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 3.5431,
      "step": 39
    },
    {
      "epoch": 0.0006414728215983899,
      "grad_norm": 1.6848899126052856,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 3.2279,
      "step": 40
    },
    {
      "epoch": 0.0006575096421383497,
      "grad_norm": 1.9263161420822144,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 3.195,
      "step": 41
    },
    {
      "epoch": 0.0006735464626783094,
      "grad_norm": 1.6738039255142212,
      "learning_rate": 1.339745962155613e-05,
      "loss": 3.1865,
      "step": 42
    },
    {
      "epoch": 0.0006895832832182692,
      "grad_norm": 2.7173876762390137,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 3.215,
      "step": 43
    },
    {
      "epoch": 0.0007056201037582289,
      "grad_norm": 3.1960883140563965,
      "learning_rate": 7.612046748871327e-06,
      "loss": 3.9265,
      "step": 44
    },
    {
      "epoch": 0.0007216569242981886,
      "grad_norm": 4.025484085083008,
      "learning_rate": 5.306987050489442e-06,
      "loss": 3.6214,
      "step": 45
    },
    {
      "epoch": 0.0007376937448381484,
      "grad_norm": 3.7927160263061523,
      "learning_rate": 3.40741737109318e-06,
      "loss": 3.9951,
      "step": 46
    },
    {
      "epoch": 0.0007537305653781081,
      "grad_norm": 4.386187553405762,
      "learning_rate": 1.921471959676957e-06,
      "loss": 4.0177,
      "step": 47
    },
    {
      "epoch": 0.0007697673859180679,
      "grad_norm": 6.818923473358154,
      "learning_rate": 8.555138626189618e-07,
      "loss": 4.421,
      "step": 48
    },
    {
      "epoch": 0.0007858042064580276,
      "grad_norm": 6.9941935539245605,
      "learning_rate": 2.141076761396521e-07,
      "loss": 4.3937,
      "step": 49
    },
    {
      "epoch": 0.0008018410269979874,
      "grad_norm": 13.381073951721191,
      "learning_rate": 0.0,
      "loss": 5.6214,
      "step": 50
    },
    {
      "epoch": 0.0008018410269979874,
      "eval_loss": 3.993314266204834,
      "eval_runtime": 7155.1732,
      "eval_samples_per_second": 3.67,
      "eval_steps_per_second": 1.835,
      "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": 6.6109411688448e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}