{
  "best_metric": 4.553748607635498,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.001937121050694458,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.874242101388916e-05,
      "grad_norm": 0.9535180330276489,
      "learning_rate": 0.0001,
      "loss": 4.9277,
      "step": 1
    },
    {
      "epoch": 3.874242101388916e-05,
      "eval_loss": 5.099274158477783,
      "eval_runtime": 786.19,
      "eval_samples_per_second": 13.825,
      "eval_steps_per_second": 6.913,
      "step": 1
    },
    {
      "epoch": 7.748484202777832e-05,
      "grad_norm": 1.9804755449295044,
      "learning_rate": 0.0002,
      "loss": 5.0741,
      "step": 2
    },
    {
      "epoch": 0.00011622726304166748,
      "grad_norm": 1.898642897605896,
      "learning_rate": 0.00019978589232386035,
      "loss": 5.2926,
      "step": 3
    },
    {
      "epoch": 0.00015496968405555664,
      "grad_norm": 2.076120138168335,
      "learning_rate": 0.00019914448613738106,
      "loss": 4.7884,
      "step": 4
    },
    {
      "epoch": 0.00019371210506944578,
      "grad_norm": 1.9280245304107666,
      "learning_rate": 0.00019807852804032305,
      "loss": 4.737,
      "step": 5
    },
    {
      "epoch": 0.00023245452608333496,
      "grad_norm": 2.3307619094848633,
      "learning_rate": 0.00019659258262890683,
      "loss": 4.7751,
      "step": 6
    },
    {
      "epoch": 0.00027119694709722413,
      "grad_norm": 2.1762661933898926,
      "learning_rate": 0.0001946930129495106,
      "loss": 4.8104,
      "step": 7
    },
    {
      "epoch": 0.0003099393681111133,
      "grad_norm": 2.5910465717315674,
      "learning_rate": 0.0001923879532511287,
      "loss": 4.8574,
      "step": 8
    },
    {
      "epoch": 0.0003486817891250024,
      "grad_norm": 2.188605785369873,
      "learning_rate": 0.00018968727415326884,
      "loss": 5.1751,
      "step": 9
    },
    {
      "epoch": 0.00038742421013889157,
      "grad_norm": 2.2746739387512207,
      "learning_rate": 0.00018660254037844388,
      "loss": 4.858,
      "step": 10
    },
    {
      "epoch": 0.0004261666311527807,
      "grad_norm": 3.552828311920166,
      "learning_rate": 0.00018314696123025454,
      "loss": 4.6637,
      "step": 11
    },
    {
      "epoch": 0.0004649090521666699,
      "grad_norm": 2.574284076690674,
      "learning_rate": 0.00017933533402912354,
      "loss": 4.8492,
      "step": 12
    },
    {
      "epoch": 0.000503651473180559,
      "grad_norm": 2.5389957427978516,
      "learning_rate": 0.00017518398074789775,
      "loss": 4.8532,
      "step": 13
    },
    {
      "epoch": 0.0005423938941944483,
      "grad_norm": 2.9380061626434326,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.7526,
      "step": 14
    },
    {
      "epoch": 0.0005811363152083374,
      "grad_norm": 2.7166178226470947,
      "learning_rate": 0.00016593458151000688,
      "loss": 4.6415,
      "step": 15
    },
    {
      "epoch": 0.0006198787362222266,
      "grad_norm": 3.4056546688079834,
      "learning_rate": 0.00016087614290087208,
      "loss": 4.1055,
      "step": 16
    },
    {
      "epoch": 0.0006586211572361157,
      "grad_norm": 3.259704828262329,
      "learning_rate": 0.00015555702330196023,
      "loss": 4.7605,
      "step": 17
    },
    {
      "epoch": 0.0006973635782500048,
      "grad_norm": 3.1635217666625977,
      "learning_rate": 0.00015000000000000001,
      "loss": 4.854,
      "step": 18
    },
    {
      "epoch": 0.000736105999263894,
      "grad_norm": 2.6696650981903076,
      "learning_rate": 0.00014422886902190014,
      "loss": 4.35,
      "step": 19
    },
    {
      "epoch": 0.0007748484202777831,
      "grad_norm": 2.378119945526123,
      "learning_rate": 0.000138268343236509,
      "loss": 4.6636,
      "step": 20
    },
    {
      "epoch": 0.0008135908412916723,
      "grad_norm": 2.725853204727173,
      "learning_rate": 0.00013214394653031616,
      "loss": 4.6707,
      "step": 21
    },
    {
      "epoch": 0.0008523332623055614,
      "grad_norm": 2.411433458328247,
      "learning_rate": 0.00012588190451025207,
      "loss": 4.2935,
      "step": 22
    },
    {
      "epoch": 0.0008910756833194507,
      "grad_norm": 2.6273648738861084,
      "learning_rate": 0.00011950903220161285,
      "loss": 4.7996,
      "step": 23
    },
    {
      "epoch": 0.0009298181043333398,
      "grad_norm": 2.6210319995880127,
      "learning_rate": 0.00011305261922200519,
      "loss": 4.3075,
      "step": 24
    },
    {
      "epoch": 0.000968560525347229,
      "grad_norm": 2.7826545238494873,
      "learning_rate": 0.00010654031292301432,
      "loss": 4.4635,
      "step": 25
    },
    {
      "epoch": 0.000968560525347229,
      "eval_loss": 4.555358409881592,
      "eval_runtime": 786.2891,
      "eval_samples_per_second": 13.823,
      "eval_steps_per_second": 6.912,
      "step": 25
    },
    {
      "epoch": 0.001007302946361118,
      "grad_norm": 2.687333106994629,
      "learning_rate": 0.0001,
      "loss": 4.5739,
      "step": 26
    },
    {
      "epoch": 0.0010460453673750074,
      "grad_norm": 2.5073037147521973,
      "learning_rate": 9.345968707698569e-05,
      "loss": 4.4323,
      "step": 27
    },
    {
      "epoch": 0.0010847877883888965,
      "grad_norm": 2.664353609085083,
      "learning_rate": 8.694738077799488e-05,
      "loss": 4.5893,
      "step": 28
    },
    {
      "epoch": 0.0011235302094027857,
      "grad_norm": 2.6029088497161865,
      "learning_rate": 8.049096779838719e-05,
      "loss": 4.6615,
      "step": 29
    },
    {
      "epoch": 0.0011622726304166748,
      "grad_norm": 3.3007209300994873,
      "learning_rate": 7.411809548974792e-05,
      "loss": 4.7523,
      "step": 30
    },
    {
      "epoch": 0.001201015051430564,
      "grad_norm": 2.7942981719970703,
      "learning_rate": 6.785605346968386e-05,
      "loss": 4.3917,
      "step": 31
    },
    {
      "epoch": 0.001239757472444453,
      "grad_norm": 3.0454206466674805,
      "learning_rate": 6.173165676349103e-05,
      "loss": 4.3167,
      "step": 32
    },
    {
      "epoch": 0.0012784998934583422,
      "grad_norm": 2.9008948802948,
      "learning_rate": 5.577113097809989e-05,
      "loss": 4.3143,
      "step": 33
    },
    {
      "epoch": 0.0013172423144722314,
      "grad_norm": 3.7876012325286865,
      "learning_rate": 5.000000000000002e-05,
      "loss": 4.3297,
      "step": 34
    },
    {
      "epoch": 0.0013559847354861205,
      "grad_norm": 3.052884578704834,
      "learning_rate": 4.444297669803981e-05,
      "loss": 4.1575,
      "step": 35
    },
    {
      "epoch": 0.0013947271565000097,
      "grad_norm": 2.787257671356201,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 4.2594,
      "step": 36
    },
    {
      "epoch": 0.0014334695775138988,
      "grad_norm": 2.676872491836548,
      "learning_rate": 3.406541848999312e-05,
      "loss": 4.3648,
      "step": 37
    },
    {
      "epoch": 0.001472211998527788,
      "grad_norm": 2.9098947048187256,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 4.5961,
      "step": 38
    },
    {
      "epoch": 0.0015109544195416771,
      "grad_norm": 3.4376516342163086,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 4.1247,
      "step": 39
    },
    {
      "epoch": 0.0015496968405555663,
      "grad_norm": 5.867218494415283,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 4.6896,
      "step": 40
    },
    {
      "epoch": 0.0015884392615694554,
      "grad_norm": 6.272927284240723,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 5.0576,
      "step": 41
    },
    {
      "epoch": 0.0016271816825833446,
      "grad_norm": 6.831395626068115,
      "learning_rate": 1.339745962155613e-05,
      "loss": 4.4817,
      "step": 42
    },
    {
      "epoch": 0.0016659241035972337,
      "grad_norm": 5.350028038024902,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 4.8619,
      "step": 43
    },
    {
      "epoch": 0.0017046665246111229,
      "grad_norm": 4.794693946838379,
      "learning_rate": 7.612046748871327e-06,
      "loss": 4.7648,
      "step": 44
    },
    {
      "epoch": 0.0017434089456250122,
      "grad_norm": 4.822254180908203,
      "learning_rate": 5.306987050489442e-06,
      "loss": 4.4828,
      "step": 45
    },
    {
      "epoch": 0.0017821513666389014,
      "grad_norm": 6.765193462371826,
      "learning_rate": 3.40741737109318e-06,
      "loss": 4.808,
      "step": 46
    },
    {
      "epoch": 0.0018208937876527905,
      "grad_norm": 7.79011344909668,
      "learning_rate": 1.921471959676957e-06,
      "loss": 4.6111,
      "step": 47
    },
    {
      "epoch": 0.0018596362086666797,
      "grad_norm": 4.777038097381592,
      "learning_rate": 8.555138626189618e-07,
      "loss": 4.5941,
      "step": 48
    },
    {
      "epoch": 0.0018983786296805688,
      "grad_norm": 5.957098484039307,
      "learning_rate": 2.141076761396521e-07,
      "loss": 4.7932,
      "step": 49
    },
    {
      "epoch": 0.001937121050694458,
      "grad_norm": 13.376540184020996,
      "learning_rate": 0.0,
      "loss": 4.6022,
      "step": 50
    },
    {
      "epoch": 0.001937121050694458,
      "eval_loss": 4.553748607635498,
      "eval_runtime": 786.8189,
      "eval_samples_per_second": 13.814,
      "eval_steps_per_second": 6.908,
      "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": 3604771504128000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}