{
  "best_metric": 0.029691379517316818,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.8221993833504625,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01644398766700925,
      "grad_norm": 11.88234806060791,
      "learning_rate": 5e-05,
      "loss": 4.0707,
      "step": 1
    },
    {
      "epoch": 0.01644398766700925,
      "eval_loss": 4.141063690185547,
      "eval_runtime": 3.8298,
      "eval_samples_per_second": 107.055,
      "eval_steps_per_second": 13.578,
      "step": 1
    },
    {
      "epoch": 0.0328879753340185,
      "grad_norm": 11.51584243774414,
      "learning_rate": 0.0001,
      "loss": 4.088,
      "step": 2
    },
    {
      "epoch": 0.04933196300102775,
      "grad_norm": 10.898468971252441,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.8651,
      "step": 3
    },
    {
      "epoch": 0.065775950668037,
      "grad_norm": 8.73388385772705,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.614,
      "step": 4
    },
    {
      "epoch": 0.08221993833504625,
      "grad_norm": 6.254705905914307,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.633,
      "step": 5
    },
    {
      "epoch": 0.0986639260020555,
      "grad_norm": 4.807916641235352,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0216,
      "step": 6
    },
    {
      "epoch": 0.11510791366906475,
      "grad_norm": 3.9596571922302246,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.6494,
      "step": 7
    },
    {
      "epoch": 0.131551901336074,
      "grad_norm": 2.9272944927215576,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3476,
      "step": 8
    },
    {
      "epoch": 0.14799588900308325,
      "grad_norm": 2.2420060634613037,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.2218,
      "step": 9
    },
    {
      "epoch": 0.1644398766700925,
      "grad_norm": 1.8657557964324951,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1886,
      "step": 10
    },
    {
      "epoch": 0.18088386433710174,
      "grad_norm": 1.282920479774475,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1259,
      "step": 11
    },
    {
      "epoch": 0.197327852004111,
      "grad_norm": 1.5356467962265015,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1294,
      "step": 12
    },
    {
      "epoch": 0.21377183967112023,
      "grad_norm": 2.162227153778076,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.1533,
      "step": 13
    },
    {
      "epoch": 0.2302158273381295,
      "grad_norm": 1.1411077976226807,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0782,
      "step": 14
    },
    {
      "epoch": 0.24665981500513876,
      "grad_norm": 1.2007100582122803,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.1172,
      "step": 15
    },
    {
      "epoch": 0.263103802672148,
      "grad_norm": 0.6250143647193909,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0434,
      "step": 16
    },
    {
      "epoch": 0.2795477903391572,
      "grad_norm": 0.7979683876037598,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0707,
      "step": 17
    },
    {
      "epoch": 0.2959917780061665,
      "grad_norm": 0.5584985613822937,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0331,
      "step": 18
    },
    {
      "epoch": 0.31243576567317577,
      "grad_norm": 0.552579939365387,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0334,
      "step": 19
    },
    {
      "epoch": 0.328879753340185,
      "grad_norm": 0.6117237210273743,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0423,
      "step": 20
    },
    {
      "epoch": 0.34532374100719426,
      "grad_norm": 0.5110507011413574,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0319,
      "step": 21
    },
    {
      "epoch": 0.3617677286742035,
      "grad_norm": 0.4170028865337372,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0453,
      "step": 22
    },
    {
      "epoch": 0.37821171634121276,
      "grad_norm": 0.4100589156150818,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0414,
      "step": 23
    },
    {
      "epoch": 0.394655704008222,
      "grad_norm": 0.5163671970367432,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0337,
      "step": 24
    },
    {
      "epoch": 0.41109969167523125,
      "grad_norm": 0.48314791917800903,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0611,
      "step": 25
    },
    {
      "epoch": 0.41109969167523125,
      "eval_loss": 0.0325031504034996,
      "eval_runtime": 3.8224,
      "eval_samples_per_second": 107.262,
      "eval_steps_per_second": 13.604,
      "step": 25
    },
    {
      "epoch": 0.42754367934224047,
      "grad_norm": 0.4967133402824402,
      "learning_rate": 5e-05,
      "loss": 0.0747,
      "step": 26
    },
    {
      "epoch": 0.44398766700924974,
      "grad_norm": 0.6573581099510193,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.051,
      "step": 27
    },
    {
      "epoch": 0.460431654676259,
      "grad_norm": 0.7091865539550781,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0283,
      "step": 28
    },
    {
      "epoch": 0.47687564234326824,
      "grad_norm": 0.353059321641922,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0551,
      "step": 29
    },
    {
      "epoch": 0.4933196300102775,
      "grad_norm": 0.40428224205970764,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0467,
      "step": 30
    },
    {
      "epoch": 0.5097636176772867,
      "grad_norm": 0.38357752561569214,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0407,
      "step": 31
    },
    {
      "epoch": 0.526207605344296,
      "grad_norm": 0.4076400697231293,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0214,
      "step": 32
    },
    {
      "epoch": 0.5426515930113053,
      "grad_norm": 0.5312539935112,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0276,
      "step": 33
    },
    {
      "epoch": 0.5590955806783144,
      "grad_norm": 0.24239972233772278,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0114,
      "step": 34
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 0.21986766159534454,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0108,
      "step": 35
    },
    {
      "epoch": 0.591983556012333,
      "grad_norm": 0.43781280517578125,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0552,
      "step": 36
    },
    {
      "epoch": 0.6084275436793423,
      "grad_norm": 0.503707766532898,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.045,
      "step": 37
    },
    {
      "epoch": 0.6248715313463515,
      "grad_norm": 0.5236077308654785,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.027,
      "step": 38
    },
    {
      "epoch": 0.6413155190133607,
      "grad_norm": 0.5696163773536682,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0188,
      "step": 39
    },
    {
      "epoch": 0.65775950668037,
      "grad_norm": 0.5354735851287842,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0348,
      "step": 40
    },
    {
      "epoch": 0.6742034943473793,
      "grad_norm": 0.5729418396949768,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0507,
      "step": 41
    },
    {
      "epoch": 0.6906474820143885,
      "grad_norm": 0.29594871401786804,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0176,
      "step": 42
    },
    {
      "epoch": 0.7070914696813977,
      "grad_norm": 0.2777194678783417,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0149,
      "step": 43
    },
    {
      "epoch": 0.723535457348407,
      "grad_norm": 0.5910176634788513,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0334,
      "step": 44
    },
    {
      "epoch": 0.7399794450154162,
      "grad_norm": 0.47184309363365173,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0284,
      "step": 45
    },
    {
      "epoch": 0.7564234326824255,
      "grad_norm": 0.36582136154174805,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0392,
      "step": 46
    },
    {
      "epoch": 0.7728674203494348,
      "grad_norm": 0.3152853548526764,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0294,
      "step": 47
    },
    {
      "epoch": 0.789311408016444,
      "grad_norm": 0.25798124074935913,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.017,
      "step": 48
    },
    {
      "epoch": 0.8057553956834532,
      "grad_norm": 0.1165856271982193,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0048,
      "step": 49
    },
    {
      "epoch": 0.8221993833504625,
      "grad_norm": 0.3071959614753723,
      "learning_rate": 0.0,
      "loss": 0.0306,
      "step": 50
    },
    {
      "epoch": 0.8221993833504625,
      "eval_loss": 0.029691379517316818,
      "eval_runtime": 3.8208,
      "eval_samples_per_second": 107.309,
      "eval_steps_per_second": 13.61,
      "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": 8.336768348717056e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}