{
  "best_metric": 0.9280461072921753,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5486968449931413,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 3.444253444671631,
      "learning_rate": 5e-05,
      "loss": 0.826,
      "step": 1
    },
    {
      "epoch": 0.010973936899862825,
      "eval_loss": 1.112309217453003,
      "eval_runtime": 60.1556,
      "eval_samples_per_second": 10.207,
      "eval_steps_per_second": 1.28,
      "step": 1
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 4.6327738761901855,
      "learning_rate": 0.0001,
      "loss": 0.905,
      "step": 2
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 4.319215297698975,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.9635,
      "step": 3
    },
    {
      "epoch": 0.0438957475994513,
      "grad_norm": 3.2993555068969727,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9953,
      "step": 4
    },
    {
      "epoch": 0.05486968449931413,
      "grad_norm": 2.6787290573120117,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9803,
      "step": 5
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 2.8237721920013428,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9666,
      "step": 6
    },
    {
      "epoch": 0.07681755829903979,
      "grad_norm": 3.397477626800537,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.0171,
      "step": 7
    },
    {
      "epoch": 0.0877914951989026,
      "grad_norm": 3.8774361610412598,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0147,
      "step": 8
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 2.831848621368408,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.0475,
      "step": 9
    },
    {
      "epoch": 0.10973936899862825,
      "grad_norm": 2.5278875827789307,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0487,
      "step": 10
    },
    {
      "epoch": 0.12071330589849108,
      "grad_norm": 2.676313877105713,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0425,
      "step": 11
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 4.963010311126709,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1167,
      "step": 12
    },
    {
      "epoch": 0.14266117969821673,
      "grad_norm": 5.277713775634766,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.0289,
      "step": 13
    },
    {
      "epoch": 0.15363511659807957,
      "grad_norm": 2.81939435005188,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8572,
      "step": 14
    },
    {
      "epoch": 0.1646090534979424,
      "grad_norm": 2.634293556213379,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8958,
      "step": 15
    },
    {
      "epoch": 0.1755829903978052,
      "grad_norm": 2.2317168712615967,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.9254,
      "step": 16
    },
    {
      "epoch": 0.18655692729766804,
      "grad_norm": 1.6640803813934326,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.9189,
      "step": 17
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.710531234741211,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9389,
      "step": 18
    },
    {
      "epoch": 0.2085048010973937,
      "grad_norm": 1.6166858673095703,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.9409,
      "step": 19
    },
    {
      "epoch": 0.2194787379972565,
      "grad_norm": 1.7352503538131714,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9577,
      "step": 20
    },
    {
      "epoch": 0.23045267489711935,
      "grad_norm": 1.9068537950515747,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.9812,
      "step": 21
    },
    {
      "epoch": 0.24142661179698216,
      "grad_norm": 2.3723080158233643,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.9997,
      "step": 22
    },
    {
      "epoch": 0.252400548696845,
      "grad_norm": 2.2920339107513428,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.986,
      "step": 23
    },
    {
      "epoch": 0.26337448559670784,
      "grad_norm": 3.8264620304107666,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0162,
      "step": 24
    },
    {
      "epoch": 0.27434842249657065,
      "grad_norm": 7.093075275421143,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.123,
      "step": 25
    },
    {
      "epoch": 0.27434842249657065,
      "eval_loss": 0.9366830587387085,
      "eval_runtime": 60.1392,
      "eval_samples_per_second": 10.21,
      "eval_steps_per_second": 1.28,
      "step": 25
    },
    {
      "epoch": 0.28532235939643347,
      "grad_norm": 2.419912338256836,
      "learning_rate": 5e-05,
      "loss": 0.7928,
      "step": 26
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.7259137630462646,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.8779,
      "step": 27
    },
    {
      "epoch": 0.30727023319615915,
      "grad_norm": 1.8197636604309082,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.8595,
      "step": 28
    },
    {
      "epoch": 0.31824417009602196,
      "grad_norm": 1.6042948961257935,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.892,
      "step": 29
    },
    {
      "epoch": 0.3292181069958848,
      "grad_norm": 1.546321153640747,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8862,
      "step": 30
    },
    {
      "epoch": 0.3401920438957476,
      "grad_norm": 1.2811124324798584,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.9036,
      "step": 31
    },
    {
      "epoch": 0.3511659807956104,
      "grad_norm": 1.3372602462768555,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9272,
      "step": 32
    },
    {
      "epoch": 0.36213991769547327,
      "grad_norm": 1.331268072128296,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.9367,
      "step": 33
    },
    {
      "epoch": 0.3731138545953361,
      "grad_norm": 1.6882885694503784,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.9741,
      "step": 34
    },
    {
      "epoch": 0.3840877914951989,
      "grad_norm": 1.8296782970428467,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.9216,
      "step": 35
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 2.422697067260742,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.9616,
      "step": 36
    },
    {
      "epoch": 0.4060356652949246,
      "grad_norm": 5.263638019561768,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.0788,
      "step": 37
    },
    {
      "epoch": 0.4170096021947874,
      "grad_norm": 4.142805099487305,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.9168,
      "step": 38
    },
    {
      "epoch": 0.4279835390946502,
      "grad_norm": 1.098343014717102,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.8683,
      "step": 39
    },
    {
      "epoch": 0.438957475994513,
      "grad_norm": 1.2079895734786987,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.8289,
      "step": 40
    },
    {
      "epoch": 0.4499314128943759,
      "grad_norm": 1.21189546585083,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.8602,
      "step": 41
    },
    {
      "epoch": 0.4609053497942387,
      "grad_norm": 1.1260839700698853,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8711,
      "step": 42
    },
    {
      "epoch": 0.4718792866941015,
      "grad_norm": 1.2705676555633545,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.8977,
      "step": 43
    },
    {
      "epoch": 0.4828532235939643,
      "grad_norm": 1.2326122522354126,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.905,
      "step": 44
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 1.3834530115127563,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.9292,
      "step": 45
    },
    {
      "epoch": 0.50480109739369,
      "grad_norm": 1.5778294801712036,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.9167,
      "step": 46
    },
    {
      "epoch": 0.5157750342935528,
      "grad_norm": 1.755370855331421,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.9525,
      "step": 47
    },
    {
      "epoch": 0.5267489711934157,
      "grad_norm": 2.129711389541626,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.979,
      "step": 48
    },
    {
      "epoch": 0.5377229080932785,
      "grad_norm": 2.775024652481079,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.986,
      "step": 49
    },
    {
      "epoch": 0.5486968449931413,
      "grad_norm": 6.473246097564697,
      "learning_rate": 0.0,
      "loss": 1.086,
      "step": 50
    },
    {
      "epoch": 0.5486968449931413,
      "eval_loss": 0.9280461072921753,
      "eval_runtime": 58.974,
      "eval_samples_per_second": 10.411,
      "eval_steps_per_second": 1.306,
      "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": 3.0459522160420454e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}