{
  "best_metric": 0.7736261487007141,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.4184397163120568,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.42114007472991943,
      "learning_rate": 5e-05,
      "loss": 1.6702,
      "step": 1
    },
    {
      "epoch": 0.028368794326241134,
      "eval_loss": 1.899458646774292,
      "eval_runtime": 2.2302,
      "eval_samples_per_second": 106.718,
      "eval_steps_per_second": 13.452,
      "step": 1
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.5437279343605042,
      "learning_rate": 0.0001,
      "loss": 1.7848,
      "step": 2
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.6194532513618469,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.8052,
      "step": 3
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 0.641870379447937,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.814,
      "step": 4
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.7480588555335999,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.7444,
      "step": 5
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.7562574744224548,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.6621,
      "step": 6
    },
    {
      "epoch": 0.19858156028368795,
      "grad_norm": 0.8102620244026184,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.4714,
      "step": 7
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 0.9009529948234558,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.3401,
      "step": 8
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 0.5861480832099915,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.4203,
      "step": 9
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.43803441524505615,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.326,
      "step": 10
    },
    {
      "epoch": 0.3120567375886525,
      "grad_norm": 0.4437030553817749,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.2301,
      "step": 11
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.46572837233543396,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1578,
      "step": 12
    },
    {
      "epoch": 0.36879432624113473,
      "grad_norm": 0.46367964148521423,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.0983,
      "step": 13
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 0.464253306388855,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.996,
      "step": 14
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.4719739556312561,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8901,
      "step": 15
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 0.45740458369255066,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.7915,
      "step": 16
    },
    {
      "epoch": 0.48226950354609927,
      "grad_norm": 0.6639715433120728,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.744,
      "step": 17
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 0.6000366806983948,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1856,
      "step": 18
    },
    {
      "epoch": 0.5390070921985816,
      "grad_norm": 0.6243106126785278,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.1144,
      "step": 19
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.5368908047676086,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0406,
      "step": 20
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 0.4204038083553314,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.8979,
      "step": 21
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": 0.3659383952617645,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8461,
      "step": 22
    },
    {
      "epoch": 0.6524822695035462,
      "grad_norm": 0.3935062289237976,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7838,
      "step": 23
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 0.4676189422607422,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.6523,
      "step": 24
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 0.5195455551147461,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.6157,
      "step": 25
    },
    {
      "epoch": 0.7092198581560284,
      "eval_loss": 0.8397419452667236,
      "eval_runtime": 2.2201,
      "eval_samples_per_second": 107.2,
      "eval_steps_per_second": 13.513,
      "step": 25
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": 0.6546393036842346,
      "learning_rate": 5e-05,
      "loss": 0.6403,
      "step": 26
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 0.3804154098033905,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.0668,
      "step": 27
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": 0.3659527599811554,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.9944,
      "step": 28
    },
    {
      "epoch": 0.8226950354609929,
      "grad_norm": 0.30047330260276794,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.9064,
      "step": 29
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.2907089591026306,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8317,
      "step": 30
    },
    {
      "epoch": 0.8794326241134752,
      "grad_norm": 0.2471207082271576,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.7746,
      "step": 31
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": 0.2888796329498291,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6717,
      "step": 32
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 0.31053251028060913,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.6391,
      "step": 33
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": 0.3765886425971985,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.5467,
      "step": 34
    },
    {
      "epoch": 0.9929078014184397,
      "grad_norm": 0.8381665349006653,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.514,
      "step": 35
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 0.6498362421989441,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.7386,
      "step": 36
    },
    {
      "epoch": 1.049645390070922,
      "grad_norm": 0.4573185443878174,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.9685,
      "step": 37
    },
    {
      "epoch": 1.0780141843971631,
      "grad_norm": 0.35154661536216736,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8553,
      "step": 38
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": 0.33329135179519653,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.7982,
      "step": 39
    },
    {
      "epoch": 1.1347517730496455,
      "grad_norm": 0.3315684199333191,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.7198,
      "step": 40
    },
    {
      "epoch": 1.1631205673758864,
      "grad_norm": 0.3105354309082031,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.6575,
      "step": 41
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 0.34584712982177734,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6094,
      "step": 42
    },
    {
      "epoch": 1.2198581560283688,
      "grad_norm": 0.43531346321105957,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.55,
      "step": 43
    },
    {
      "epoch": 1.24822695035461,
      "grad_norm": 0.38908010721206665,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3067,
      "step": 44
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 0.6625954508781433,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.4526,
      "step": 45
    },
    {
      "epoch": 1.3049645390070923,
      "grad_norm": 0.4183286428451538,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.9189,
      "step": 46
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.34246036410331726,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.8448,
      "step": 47
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.3462507426738739,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.7784,
      "step": 48
    },
    {
      "epoch": 1.3900709219858156,
      "grad_norm": 0.29618310928344727,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7085,
      "step": 49
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 0.3255789279937744,
      "learning_rate": 0.0,
      "loss": 0.6715,
      "step": 50
    },
    {
      "epoch": 1.4184397163120568,
      "eval_loss": 0.7736261487007141,
      "eval_runtime": 2.2187,
      "eval_samples_per_second": 107.27,
      "eval_steps_per_second": 13.521,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 8.33416392081408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}