{
  "best_metric": 0.8184752464294434,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.006735367414292449,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000134707348285849,
      "grad_norm": 0.3989875316619873,
      "learning_rate": 0.0001,
      "loss": 0.7305,
      "step": 1
    },
    {
      "epoch": 0.000134707348285849,
      "eval_loss": 0.9963889718055725,
      "eval_runtime": 1031.6757,
      "eval_samples_per_second": 3.03,
      "eval_steps_per_second": 1.515,
      "step": 1
    },
    {
      "epoch": 0.000269414696571698,
      "grad_norm": 0.266128271818161,
      "learning_rate": 0.0002,
      "loss": 0.6551,
      "step": 2
    },
    {
      "epoch": 0.00040412204485754696,
      "grad_norm": 0.3431636691093445,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.8567,
      "step": 3
    },
    {
      "epoch": 0.000538829393143396,
      "grad_norm": 0.35163378715515137,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.7488,
      "step": 4
    },
    {
      "epoch": 0.000673536741429245,
      "grad_norm": 0.27742981910705566,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.8172,
      "step": 5
    },
    {
      "epoch": 0.0008082440897150939,
      "grad_norm": 0.3320028781890869,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.718,
      "step": 6
    },
    {
      "epoch": 0.000942951438000943,
      "grad_norm": 0.535649299621582,
      "learning_rate": 0.0001946930129495106,
      "loss": 1.1064,
      "step": 7
    },
    {
      "epoch": 0.001077658786286792,
      "grad_norm": 0.27847981452941895,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.6898,
      "step": 8
    },
    {
      "epoch": 0.0012123661345726409,
      "grad_norm": 0.2542046308517456,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.8986,
      "step": 9
    },
    {
      "epoch": 0.00134707348285849,
      "grad_norm": 0.21672561764717102,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.7935,
      "step": 10
    },
    {
      "epoch": 0.001481780831144339,
      "grad_norm": 0.24396611750125885,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.8474,
      "step": 11
    },
    {
      "epoch": 0.0016164881794301878,
      "grad_norm": 0.22496944665908813,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.7853,
      "step": 12
    },
    {
      "epoch": 0.001751195527716037,
      "grad_norm": 0.30784857273101807,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.8631,
      "step": 13
    },
    {
      "epoch": 0.001885902876001886,
      "grad_norm": 0.2579905390739441,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.0081,
      "step": 14
    },
    {
      "epoch": 0.002020610224287735,
      "grad_norm": 0.231899231672287,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.8478,
      "step": 15
    },
    {
      "epoch": 0.002155317572573584,
      "grad_norm": 0.20303134620189667,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.8958,
      "step": 16
    },
    {
      "epoch": 0.002290024920859433,
      "grad_norm": 0.2198290228843689,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.9197,
      "step": 17
    },
    {
      "epoch": 0.0024247322691452818,
      "grad_norm": 0.2266380339860916,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.733,
      "step": 18
    },
    {
      "epoch": 0.0025594396174311307,
      "grad_norm": 0.213175430893898,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.7844,
      "step": 19
    },
    {
      "epoch": 0.00269414696571698,
      "grad_norm": 0.25168150663375854,
      "learning_rate": 0.000138268343236509,
      "loss": 0.7973,
      "step": 20
    },
    {
      "epoch": 0.002828854314002829,
      "grad_norm": 0.2322896122932434,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.6787,
      "step": 21
    },
    {
      "epoch": 0.002963561662288678,
      "grad_norm": 0.2419241964817047,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.8474,
      "step": 22
    },
    {
      "epoch": 0.0030982690105745268,
      "grad_norm": 0.2670826315879822,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.8448,
      "step": 23
    },
    {
      "epoch": 0.0032329763588603757,
      "grad_norm": 0.22268517315387726,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.8543,
      "step": 24
    },
    {
      "epoch": 0.0033676837071462246,
      "grad_norm": 0.22278288006782532,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.7067,
      "step": 25
    },
    {
      "epoch": 0.0033676837071462246,
      "eval_loss": 0.8295209407806396,
      "eval_runtime": 1038.2542,
      "eval_samples_per_second": 3.011,
      "eval_steps_per_second": 1.505,
      "step": 25
    },
    {
      "epoch": 0.003502391055432074,
      "grad_norm": 0.21760126948356628,
      "learning_rate": 0.0001,
      "loss": 0.7503,
      "step": 26
    },
    {
      "epoch": 0.003637098403717923,
      "grad_norm": 0.2235322743654251,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.7927,
      "step": 27
    },
    {
      "epoch": 0.003771805752003772,
      "grad_norm": 0.22535647451877594,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.8245,
      "step": 28
    },
    {
      "epoch": 0.003906513100289621,
      "grad_norm": 0.2814962565898895,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.9863,
      "step": 29
    },
    {
      "epoch": 0.00404122044857547,
      "grad_norm": 0.24935074150562286,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.9404,
      "step": 30
    },
    {
      "epoch": 0.0041759277968613185,
      "grad_norm": 0.2589765191078186,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.797,
      "step": 31
    },
    {
      "epoch": 0.004310635145147168,
      "grad_norm": 0.2682248651981354,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.7075,
      "step": 32
    },
    {
      "epoch": 0.004445342493433016,
      "grad_norm": 0.2292226403951645,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.7168,
      "step": 33
    },
    {
      "epoch": 0.004580049841718866,
      "grad_norm": 0.3114967942237854,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.934,
      "step": 34
    },
    {
      "epoch": 0.004714757190004715,
      "grad_norm": 0.26063475012779236,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.6765,
      "step": 35
    },
    {
      "epoch": 0.0048494645382905635,
      "grad_norm": 0.2700875699520111,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.8336,
      "step": 36
    },
    {
      "epoch": 0.004984171886576413,
      "grad_norm": 0.3182436525821686,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.9314,
      "step": 37
    },
    {
      "epoch": 0.005118879234862261,
      "grad_norm": 0.3367193639278412,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.9114,
      "step": 38
    },
    {
      "epoch": 0.005253586583148111,
      "grad_norm": 0.3540671169757843,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.9422,
      "step": 39
    },
    {
      "epoch": 0.00538829393143396,
      "grad_norm": 0.36494025588035583,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.9221,
      "step": 40
    },
    {
      "epoch": 0.0055230012797198086,
      "grad_norm": 0.35188528895378113,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.8136,
      "step": 41
    },
    {
      "epoch": 0.005657708628005658,
      "grad_norm": 0.38938695192337036,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.7914,
      "step": 42
    },
    {
      "epoch": 0.005792415976291506,
      "grad_norm": 0.45242178440093994,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.9588,
      "step": 43
    },
    {
      "epoch": 0.005927123324577356,
      "grad_norm": 0.4056650996208191,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.8246,
      "step": 44
    },
    {
      "epoch": 0.006061830672863205,
      "grad_norm": 0.4734395444393158,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.9447,
      "step": 45
    },
    {
      "epoch": 0.0061965380211490536,
      "grad_norm": 0.4617159962654114,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.7806,
      "step": 46
    },
    {
      "epoch": 0.006331245369434903,
      "grad_norm": 0.5809133648872375,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.9423,
      "step": 47
    },
    {
      "epoch": 0.006465952717720751,
      "grad_norm": 0.606318473815918,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.9536,
      "step": 48
    },
    {
      "epoch": 0.006600660066006601,
      "grad_norm": 0.6376668214797974,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.7261,
      "step": 49
    },
    {
      "epoch": 0.006735367414292449,
      "grad_norm": 0.9981294870376587,
      "learning_rate": 0.0,
      "loss": 0.7886,
      "step": 50
    },
    {
      "epoch": 0.006735367414292449,
      "eval_loss": 0.8184752464294434,
      "eval_runtime": 1039.4306,
      "eval_samples_per_second": 3.007,
      "eval_steps_per_second": 1.504,
      "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": 8.420420668411085e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}