{
  "best_metric": 0.6291812658309937,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0069113873746231135,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013822774749246226,
      "grad_norm": 0.20899590849876404,
      "learning_rate": 5e-05,
      "loss": 0.275,
      "step": 1
    },
    {
      "epoch": 0.00013822774749246226,
      "eval_loss": 1.491836428642273,
      "eval_runtime": 929.094,
      "eval_samples_per_second": 52.458,
      "eval_steps_per_second": 6.558,
      "step": 1
    },
    {
      "epoch": 0.0002764554949849245,
      "grad_norm": 0.2894967794418335,
      "learning_rate": 0.0001,
      "loss": 0.4265,
      "step": 2
    },
    {
      "epoch": 0.0004146832424773868,
      "grad_norm": 0.8162183165550232,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.192,
      "step": 3
    },
    {
      "epoch": 0.000552910989969849,
      "grad_norm": 2.975461721420288,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.5909,
      "step": 4
    },
    {
      "epoch": 0.0006911387374623114,
      "grad_norm": 0.8152533769607544,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.4245,
      "step": 5
    },
    {
      "epoch": 0.0008293664849547736,
      "grad_norm": 1.018890142440796,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.4628,
      "step": 6
    },
    {
      "epoch": 0.0009675942324472358,
      "grad_norm": 0.49169057607650757,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.1237,
      "step": 7
    },
    {
      "epoch": 0.001105821979939698,
      "grad_norm": 0.49682843685150146,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0297,
      "step": 8
    },
    {
      "epoch": 0.0012440497274321604,
      "grad_norm": 0.5139557123184204,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.9949,
      "step": 9
    },
    {
      "epoch": 0.0013822774749246227,
      "grad_norm": 0.6239488124847412,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0787,
      "step": 10
    },
    {
      "epoch": 0.0015205052224170849,
      "grad_norm": 0.793647050857544,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.1657,
      "step": 11
    },
    {
      "epoch": 0.0016587329699095472,
      "grad_norm": 1.479775309562683,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.3309,
      "step": 12
    },
    {
      "epoch": 0.0017969607174020095,
      "grad_norm": 0.09675563126802444,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.1813,
      "step": 13
    },
    {
      "epoch": 0.0019351884648944717,
      "grad_norm": 0.4216521084308624,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5141,
      "step": 14
    },
    {
      "epoch": 0.0020734162123869342,
      "grad_norm": 0.45123061537742615,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.5555,
      "step": 15
    },
    {
      "epoch": 0.002211643959879396,
      "grad_norm": 1.912581443786621,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.0431,
      "step": 16
    },
    {
      "epoch": 0.0023498717073718585,
      "grad_norm": 2.2045648097991943,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.933,
      "step": 17
    },
    {
      "epoch": 0.002488099454864321,
      "grad_norm": 0.8404837250709534,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0533,
      "step": 18
    },
    {
      "epoch": 0.002626327202356783,
      "grad_norm": 0.6056650876998901,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8534,
      "step": 19
    },
    {
      "epoch": 0.0027645549498492455,
      "grad_norm": 0.6158767938613892,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8675,
      "step": 20
    },
    {
      "epoch": 0.002902782697341708,
      "grad_norm": 0.5176986455917358,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.8201,
      "step": 21
    },
    {
      "epoch": 0.0030410104448341697,
      "grad_norm": 0.46838340163230896,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8073,
      "step": 22
    },
    {
      "epoch": 0.003179238192326632,
      "grad_norm": 0.6454631686210632,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8695,
      "step": 23
    },
    {
      "epoch": 0.0033174659398190944,
      "grad_norm": 0.6822229027748108,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.7872,
      "step": 24
    },
    {
      "epoch": 0.0034556936873115568,
      "grad_norm": 1.2478026151657104,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.9731,
      "step": 25
    },
    {
      "epoch": 0.0034556936873115568,
      "eval_loss": 0.7331727147102356,
      "eval_runtime": 928.5421,
      "eval_samples_per_second": 52.489,
      "eval_steps_per_second": 6.562,
      "step": 25
    },
    {
      "epoch": 0.003593921434804019,
      "grad_norm": 0.10816100239753723,
      "learning_rate": 5e-05,
      "loss": 0.1576,
      "step": 26
    },
    {
      "epoch": 0.0037321491822964814,
      "grad_norm": 0.22579136490821838,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.3991,
      "step": 27
    },
    {
      "epoch": 0.0038703769297889433,
      "grad_norm": 0.9358543157577515,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.6752,
      "step": 28
    },
    {
      "epoch": 0.004008604677281406,
      "grad_norm": 1.8839869499206543,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.7437,
      "step": 29
    },
    {
      "epoch": 0.0041468324247738685,
      "grad_norm": 0.5732693076133728,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.5957,
      "step": 30
    },
    {
      "epoch": 0.00428506017226633,
      "grad_norm": 0.5838826894760132,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.8786,
      "step": 31
    },
    {
      "epoch": 0.004423287919758792,
      "grad_norm": 0.4363511800765991,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6971,
      "step": 32
    },
    {
      "epoch": 0.004561515667251255,
      "grad_norm": 0.4109190106391907,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.6447,
      "step": 33
    },
    {
      "epoch": 0.004699743414743717,
      "grad_norm": 0.41865962743759155,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.5883,
      "step": 34
    },
    {
      "epoch": 0.004837971162236179,
      "grad_norm": 0.43567973375320435,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.6431,
      "step": 35
    },
    {
      "epoch": 0.004976198909728642,
      "grad_norm": 0.6182336211204529,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.6286,
      "step": 36
    },
    {
      "epoch": 0.005114426657221104,
      "grad_norm": 0.8428115844726562,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.7439,
      "step": 37
    },
    {
      "epoch": 0.005252654404713566,
      "grad_norm": 0.08650384098291397,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.135,
      "step": 38
    },
    {
      "epoch": 0.005390882152206029,
      "grad_norm": 0.29149913787841797,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.3554,
      "step": 39
    },
    {
      "epoch": 0.005529109899698491,
      "grad_norm": 0.27593764662742615,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.5741,
      "step": 40
    },
    {
      "epoch": 0.005667337647190953,
      "grad_norm": 0.9634928703308105,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.6408,
      "step": 41
    },
    {
      "epoch": 0.005805565394683416,
      "grad_norm": 1.063530683517456,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6106,
      "step": 42
    },
    {
      "epoch": 0.005943793142175877,
      "grad_norm": 0.9429785013198853,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.8032,
      "step": 43
    },
    {
      "epoch": 0.0060820208896683395,
      "grad_norm": 0.33883610367774963,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7053,
      "step": 44
    },
    {
      "epoch": 0.006220248637160802,
      "grad_norm": 0.31152814626693726,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.6431,
      "step": 45
    },
    {
      "epoch": 0.006358476384653264,
      "grad_norm": 0.30629175901412964,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.6012,
      "step": 46
    },
    {
      "epoch": 0.0064967041321457265,
      "grad_norm": 0.3602805435657501,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.6242,
      "step": 47
    },
    {
      "epoch": 0.006634931879638189,
      "grad_norm": 0.5614189505577087,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.6288,
      "step": 48
    },
    {
      "epoch": 0.006773159627130651,
      "grad_norm": 0.49987950921058655,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.5502,
      "step": 49
    },
    {
      "epoch": 0.0069113873746231135,
      "grad_norm": 1.0807961225509644,
      "learning_rate": 0.0,
      "loss": 0.8658,
      "step": 50
    },
    {
      "epoch": 0.0069113873746231135,
      "eval_loss": 0.6291812658309937,
      "eval_runtime": 927.4307,
      "eval_samples_per_second": 52.552,
      "eval_steps_per_second": 6.57,
      "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": 2.2898601066129e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}