{
  "best_metric": 0.0934281200170517,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.004221635883905013,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.443271767810026e-05,
      "grad_norm": 36.238685607910156,
      "learning_rate": 0.0001,
      "loss": 8.6372,
      "step": 1
    },
    {
      "epoch": 8.443271767810026e-05,
      "eval_loss": 7.14997673034668,
      "eval_runtime": 1747.2511,
      "eval_samples_per_second": 2.854,
      "eval_steps_per_second": 1.427,
      "step": 1
    },
    {
      "epoch": 0.00016886543535620053,
      "grad_norm": 22.111175537109375,
      "learning_rate": 0.0002,
      "loss": 9.0008,
      "step": 2
    },
    {
      "epoch": 0.0002532981530343008,
      "grad_norm": 18.092870712280273,
      "learning_rate": 0.00019978589232386035,
      "loss": 5.7067,
      "step": 3
    },
    {
      "epoch": 0.00033773087071240106,
      "grad_norm": 13.40740966796875,
      "learning_rate": 0.00019914448613738106,
      "loss": 2.9529,
      "step": 4
    },
    {
      "epoch": 0.00042216358839050134,
      "grad_norm": 15.289527893066406,
      "learning_rate": 0.00019807852804032305,
      "loss": 2.0192,
      "step": 5
    },
    {
      "epoch": 0.0005065963060686016,
      "grad_norm": 8.689441680908203,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.9383,
      "step": 6
    },
    {
      "epoch": 0.0005910290237467018,
      "grad_norm": 5.27055549621582,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.2762,
      "step": 7
    },
    {
      "epoch": 0.0006754617414248021,
      "grad_norm": 8.563719749450684,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.3639,
      "step": 8
    },
    {
      "epoch": 0.0007598944591029024,
      "grad_norm": 13.948263168334961,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.4229,
      "step": 9
    },
    {
      "epoch": 0.0008443271767810027,
      "grad_norm": 9.877755165100098,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.5385,
      "step": 10
    },
    {
      "epoch": 0.000928759894459103,
      "grad_norm": 4.546455383300781,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.152,
      "step": 11
    },
    {
      "epoch": 0.0010131926121372031,
      "grad_norm": 5.590847015380859,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.3444,
      "step": 12
    },
    {
      "epoch": 0.0010976253298153034,
      "grad_norm": 4.4191508293151855,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.2935,
      "step": 13
    },
    {
      "epoch": 0.0011820580474934037,
      "grad_norm": 10.509808540344238,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6362,
      "step": 14
    },
    {
      "epoch": 0.001266490765171504,
      "grad_norm": 2.2120509147644043,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.1195,
      "step": 15
    },
    {
      "epoch": 0.0013509234828496042,
      "grad_norm": 8.435502052307129,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.3736,
      "step": 16
    },
    {
      "epoch": 0.0014353562005277045,
      "grad_norm": 2.322937250137329,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.043,
      "step": 17
    },
    {
      "epoch": 0.0015197889182058048,
      "grad_norm": 3.382920742034912,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1894,
      "step": 18
    },
    {
      "epoch": 0.001604221635883905,
      "grad_norm": 2.115218162536621,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.0963,
      "step": 19
    },
    {
      "epoch": 0.0016886543535620053,
      "grad_norm": 3.9554922580718994,
      "learning_rate": 0.000138268343236509,
      "loss": 0.1499,
      "step": 20
    },
    {
      "epoch": 0.0017730870712401056,
      "grad_norm": 2.485090732574463,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0795,
      "step": 21
    },
    {
      "epoch": 0.001857519788918206,
      "grad_norm": 1.8215144872665405,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0863,
      "step": 22
    },
    {
      "epoch": 0.001941952506596306,
      "grad_norm": 1.6672977209091187,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0254,
      "step": 23
    },
    {
      "epoch": 0.0020263852242744062,
      "grad_norm": 1.2854676246643066,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.0466,
      "step": 24
    },
    {
      "epoch": 0.0021108179419525065,
      "grad_norm": 3.5440475940704346,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.2324,
      "step": 25
    },
    {
      "epoch": 0.0021108179419525065,
      "eval_loss": 0.23284952342510223,
      "eval_runtime": 1757.7264,
      "eval_samples_per_second": 2.837,
      "eval_steps_per_second": 1.419,
      "step": 25
    },
    {
      "epoch": 0.002195250659630607,
      "grad_norm": 4.415905952453613,
      "learning_rate": 0.0001,
      "loss": 0.2306,
      "step": 26
    },
    {
      "epoch": 0.002279683377308707,
      "grad_norm": 2.082292318344116,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.0689,
      "step": 27
    },
    {
      "epoch": 0.0023641160949868074,
      "grad_norm": 0.1635982245206833,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.0034,
      "step": 28
    },
    {
      "epoch": 0.0024485488126649076,
      "grad_norm": 5.064727306365967,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.1768,
      "step": 29
    },
    {
      "epoch": 0.002532981530343008,
      "grad_norm": 1.381342887878418,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.0235,
      "step": 30
    },
    {
      "epoch": 0.002617414248021108,
      "grad_norm": 2.433394193649292,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.0458,
      "step": 31
    },
    {
      "epoch": 0.0027018469656992085,
      "grad_norm": 0.16443267464637756,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0031,
      "step": 32
    },
    {
      "epoch": 0.0027862796833773087,
      "grad_norm": 5.821410179138184,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.1666,
      "step": 33
    },
    {
      "epoch": 0.002870712401055409,
      "grad_norm": 0.13388852775096893,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0039,
      "step": 34
    },
    {
      "epoch": 0.0029551451187335093,
      "grad_norm": 3.2496159076690674,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.2075,
      "step": 35
    },
    {
      "epoch": 0.0030395778364116096,
      "grad_norm": 0.4470334053039551,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.0083,
      "step": 36
    },
    {
      "epoch": 0.00312401055408971,
      "grad_norm": 2.798367977142334,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.0599,
      "step": 37
    },
    {
      "epoch": 0.00320844327176781,
      "grad_norm": 0.4125634431838989,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0067,
      "step": 38
    },
    {
      "epoch": 0.0032928759894459104,
      "grad_norm": 5.9901323318481445,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.1536,
      "step": 39
    },
    {
      "epoch": 0.0033773087071240107,
      "grad_norm": 1.085100769996643,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.0135,
      "step": 40
    },
    {
      "epoch": 0.003461741424802111,
      "grad_norm": 8.561752319335938,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.2638,
      "step": 41
    },
    {
      "epoch": 0.0035461741424802113,
      "grad_norm": 5.0624847412109375,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.2491,
      "step": 42
    },
    {
      "epoch": 0.0036306068601583115,
      "grad_norm": 3.0588884353637695,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.0416,
      "step": 43
    },
    {
      "epoch": 0.003715039577836412,
      "grad_norm": 0.11724475026130676,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0022,
      "step": 44
    },
    {
      "epoch": 0.003799472295514512,
      "grad_norm": 0.7609636783599854,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.0195,
      "step": 45
    },
    {
      "epoch": 0.003883905013192612,
      "grad_norm": 0.0424778014421463,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.0007,
      "step": 46
    },
    {
      "epoch": 0.003968337730870713,
      "grad_norm": 0.03648586571216583,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.0007,
      "step": 47
    },
    {
      "epoch": 0.0040527704485488125,
      "grad_norm": 3.957385301589966,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.1444,
      "step": 48
    },
    {
      "epoch": 0.004137203166226913,
      "grad_norm": 1.900801420211792,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.0386,
      "step": 49
    },
    {
      "epoch": 0.004221635883905013,
      "grad_norm": 11.870166778564453,
      "learning_rate": 0.0,
      "loss": 0.8645,
      "step": 50
    },
    {
      "epoch": 0.004221635883905013,
      "eval_loss": 0.0934281200170517,
      "eval_runtime": 1757.9204,
      "eval_samples_per_second": 2.837,
      "eval_steps_per_second": 1.419,
      "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": 7.41887283560448e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}