{
  "best_metric": 0.7202689051628113,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.06827802813054759,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013655605626109517,
      "eval_loss": 0.9949688911437988,
      "eval_runtime": 302.7429,
      "eval_samples_per_second": 10.187,
      "eval_steps_per_second": 2.547,
      "step": 1
    },
    {
      "epoch": 0.0013655605626109518,
      "grad_norm": 0.2990376055240631,
      "learning_rate": 4.22e-05,
      "loss": 0.8081,
      "step": 10
    },
    {
      "epoch": 0.0027311211252219036,
      "grad_norm": 0.18796958029270172,
      "learning_rate": 8.44e-05,
      "loss": 0.7504,
      "step": 20
    },
    {
      "epoch": 0.004096681687832855,
      "grad_norm": 0.2915318012237549,
      "learning_rate": 0.0001266,
      "loss": 0.7859,
      "step": 30
    },
    {
      "epoch": 0.005462242250443807,
      "grad_norm": 0.4626297354698181,
      "learning_rate": 0.0001688,
      "loss": 0.946,
      "step": 40
    },
    {
      "epoch": 0.006827802813054759,
      "grad_norm": 0.713054895401001,
      "learning_rate": 0.000211,
      "loss": 0.9734,
      "step": 50
    },
    {
      "epoch": 0.006827802813054759,
      "eval_loss": 0.8493964076042175,
      "eval_runtime": 302.6927,
      "eval_samples_per_second": 10.189,
      "eval_steps_per_second": 2.547,
      "step": 50
    },
    {
      "epoch": 0.00819336337566571,
      "grad_norm": 0.2116241157054901,
      "learning_rate": 0.00021074300730241147,
      "loss": 0.7354,
      "step": 60
    },
    {
      "epoch": 0.009558923938276663,
      "grad_norm": 0.18535198271274567,
      "learning_rate": 0.00020997328125223568,
      "loss": 0.7021,
      "step": 70
    },
    {
      "epoch": 0.010924484500887614,
      "grad_norm": 0.2994266748428345,
      "learning_rate": 0.0002086945718774165,
      "loss": 0.697,
      "step": 80
    },
    {
      "epoch": 0.012290045063498567,
      "grad_norm": 0.5045783519744873,
      "learning_rate": 0.00020691310892149265,
      "loss": 0.83,
      "step": 90
    },
    {
      "epoch": 0.013655605626109518,
      "grad_norm": 1.0774104595184326,
      "learning_rate": 0.00020463757149291335,
      "loss": 0.9565,
      "step": 100
    },
    {
      "epoch": 0.013655605626109518,
      "eval_loss": 0.8299235105514526,
      "eval_runtime": 303.4517,
      "eval_samples_per_second": 10.163,
      "eval_steps_per_second": 2.541,
      "step": 100
    },
    {
      "epoch": 0.01502116618872047,
      "grad_norm": 0.1881781816482544,
      "learning_rate": 0.0002018790457812944,
      "loss": 0.7155,
      "step": 110
    },
    {
      "epoch": 0.01638672675133142,
      "grad_norm": 0.17206980288028717,
      "learning_rate": 0.0001986509710466168,
      "loss": 0.6885,
      "step": 120
    },
    {
      "epoch": 0.017752287313942374,
      "grad_norm": 0.2561348080635071,
      "learning_rate": 0.00019496907414450293,
      "loss": 0.7351,
      "step": 130
    },
    {
      "epoch": 0.019117847876553327,
      "grad_norm": 0.5087417364120483,
      "learning_rate": 0.00019085129290655697,
      "loss": 0.751,
      "step": 140
    },
    {
      "epoch": 0.020483408439164276,
      "grad_norm": 0.7206597924232483,
      "learning_rate": 0.00018631768874905217,
      "loss": 1.0318,
      "step": 150
    },
    {
      "epoch": 0.020483408439164276,
      "eval_loss": 0.8001604676246643,
      "eval_runtime": 303.0845,
      "eval_samples_per_second": 10.175,
      "eval_steps_per_second": 2.544,
      "step": 150
    },
    {
      "epoch": 0.02184896900177523,
      "grad_norm": 0.23315006494522095,
      "learning_rate": 0.0001813903489357277,
      "loss": 0.6814,
      "step": 160
    },
    {
      "epoch": 0.02321452956438618,
      "grad_norm": 0.21046818792819977,
      "learning_rate": 0.00017609327897085954,
      "loss": 0.6699,
      "step": 170
    },
    {
      "epoch": 0.024580090126997134,
      "grad_norm": 0.31327730417251587,
      "learning_rate": 0.00017045228564685694,
      "loss": 0.6939,
      "step": 180
    },
    {
      "epoch": 0.025945650689608083,
      "grad_norm": 0.6563451290130615,
      "learning_rate": 0.0001644948513161638,
      "loss": 0.7772,
      "step": 190
    },
    {
      "epoch": 0.027311211252219036,
      "grad_norm": 5.301021575927734,
      "learning_rate": 0.00015825,
      "loss": 0.8194,
      "step": 200
    },
    {
      "epoch": 0.027311211252219036,
      "eval_loss": 0.7733496427536011,
      "eval_runtime": 302.7702,
      "eval_samples_per_second": 10.186,
      "eval_steps_per_second": 2.546,
      "step": 200
    },
    {
      "epoch": 0.02867677181482999,
      "grad_norm": 0.20063194632530212,
      "learning_rate": 0.00015174815598624768,
      "loss": 0.6995,
      "step": 210
    },
    {
      "epoch": 0.03004233237744094,
      "grad_norm": 0.16673311591148376,
      "learning_rate": 0.00014502099560537873,
      "loss": 0.6325,
      "step": 220
    },
    {
      "epoch": 0.03140789294005189,
      "grad_norm": 0.2341037541627884,
      "learning_rate": 0.00013810129290655696,
      "loss": 0.6814,
      "step": 230
    },
    {
      "epoch": 0.03277345350266284,
      "grad_norm": 0.29294663667678833,
      "learning_rate": 0.00013102275998576495,
      "loss": 0.73,
      "step": 240
    },
    {
      "epoch": 0.034139014065273796,
      "grad_norm": 0.6317477226257324,
      "learning_rate": 0.00012381988274386116,
      "loss": 1.0111,
      "step": 250
    },
    {
      "epoch": 0.034139014065273796,
      "eval_loss": 0.7544133067131042,
      "eval_runtime": 302.7432,
      "eval_samples_per_second": 10.187,
      "eval_steps_per_second": 2.547,
      "step": 250
    },
    {
      "epoch": 0.03550457462788475,
      "grad_norm": 0.20855742692947388,
      "learning_rate": 0.00011652775287473745,
      "loss": 0.6858,
      "step": 260
    },
    {
      "epoch": 0.0368701351904957,
      "grad_norm": 0.2107452005147934,
      "learning_rate": 0.00010918189690211387,
      "loss": 0.7005,
      "step": 270
    },
    {
      "epoch": 0.038235695753106654,
      "grad_norm": 0.26034247875213623,
      "learning_rate": 0.00010181810309788618,
      "loss": 0.6453,
      "step": 280
    },
    {
      "epoch": 0.0396012563157176,
      "grad_norm": 0.3944404125213623,
      "learning_rate": 9.447224712526258e-05,
      "loss": 0.7761,
      "step": 290
    },
    {
      "epoch": 0.04096681687832855,
      "grad_norm": 0.8833209276199341,
      "learning_rate": 8.718011725613886e-05,
      "loss": 0.8044,
      "step": 300
    },
    {
      "epoch": 0.04096681687832855,
      "eval_loss": 0.740537703037262,
      "eval_runtime": 302.8602,
      "eval_samples_per_second": 10.183,
      "eval_steps_per_second": 2.546,
      "step": 300
    },
    {
      "epoch": 0.042332377440939505,
      "grad_norm": 0.17050737142562866,
      "learning_rate": 7.997724001423507e-05,
      "loss": 0.6244,
      "step": 310
    },
    {
      "epoch": 0.04369793800355046,
      "grad_norm": 0.21495510637760162,
      "learning_rate": 7.289870709344306e-05,
      "loss": 0.6406,
      "step": 320
    },
    {
      "epoch": 0.04506349856616141,
      "grad_norm": 0.23069900274276733,
      "learning_rate": 6.597900439462128e-05,
      "loss": 0.7098,
      "step": 330
    },
    {
      "epoch": 0.04642905912877236,
      "grad_norm": 0.5239390134811401,
      "learning_rate": 5.9251844013752326e-05,
      "loss": 0.7881,
      "step": 340
    },
    {
      "epoch": 0.047794619691383315,
      "grad_norm": 0.8861454725265503,
      "learning_rate": 5.275000000000002e-05,
      "loss": 0.9388,
      "step": 350
    },
    {
      "epoch": 0.047794619691383315,
      "eval_loss": 0.7316343784332275,
      "eval_runtime": 303.1651,
      "eval_samples_per_second": 10.173,
      "eval_steps_per_second": 2.543,
      "step": 350
    },
    {
      "epoch": 0.04916018025399427,
      "grad_norm": 0.18755333125591278,
      "learning_rate": 4.650514868383623e-05,
      "loss": 0.6713,
      "step": 360
    },
    {
      "epoch": 0.050525740816605214,
      "grad_norm": 0.20082293450832367,
      "learning_rate": 4.054771435314305e-05,
      "loss": 0.618,
      "step": 370
    },
    {
      "epoch": 0.051891301379216166,
      "grad_norm": 0.2751503586769104,
      "learning_rate": 3.4906721029140495e-05,
      "loss": 0.6994,
      "step": 380
    },
    {
      "epoch": 0.05325686194182712,
      "grad_norm": 0.8389333486557007,
      "learning_rate": 2.9609651064272323e-05,
      "loss": 0.819,
      "step": 390
    },
    {
      "epoch": 0.05462242250443807,
      "grad_norm": 0.7859941720962524,
      "learning_rate": 2.468231125094783e-05,
      "loss": 0.8555,
      "step": 400
    },
    {
      "epoch": 0.05462242250443807,
      "eval_loss": 0.7245707511901855,
      "eval_runtime": 303.0447,
      "eval_samples_per_second": 10.177,
      "eval_steps_per_second": 2.544,
      "step": 400
    },
    {
      "epoch": 0.055987983067049024,
      "grad_norm": 0.19546158611774445,
      "learning_rate": 2.0148707093443057e-05,
      "loss": 0.626,
      "step": 410
    },
    {
      "epoch": 0.05735354362965998,
      "grad_norm": 0.21460984647274017,
      "learning_rate": 1.603092585549706e-05,
      "loss": 0.6617,
      "step": 420
    },
    {
      "epoch": 0.05871910419227093,
      "grad_norm": 0.23666520416736603,
      "learning_rate": 1.2349028953383204e-05,
      "loss": 0.646,
      "step": 430
    },
    {
      "epoch": 0.06008466475488188,
      "grad_norm": 0.4160224497318268,
      "learning_rate": 9.120954218705596e-06,
      "loss": 0.7236,
      "step": 440
    },
    {
      "epoch": 0.06145022531749283,
      "grad_norm": 0.5936741232872009,
      "learning_rate": 6.362428507086673e-06,
      "loss": 0.8672,
      "step": 450
    },
    {
      "epoch": 0.06145022531749283,
      "eval_loss": 0.7202689051628113,
      "eval_runtime": 303.8246,
      "eval_samples_per_second": 10.151,
      "eval_steps_per_second": 2.538,
      "step": 450
    },
    {
      "epoch": 0.06281578588010378,
      "grad_norm": 0.1634497493505478,
      "learning_rate": 4.0868910785073565e-06,
      "loss": 0.6793,
      "step": 460
    },
    {
      "epoch": 0.06418134644271474,
      "grad_norm": 0.20016777515411377,
      "learning_rate": 2.3054281225835e-06,
      "loss": 0.6925,
      "step": 470
    },
    {
      "epoch": 0.06554690700532569,
      "grad_norm": 0.2985592782497406,
      "learning_rate": 1.026718747764327e-06,
      "loss": 0.6575,
      "step": 480
    },
    {
      "epoch": 0.06691246756793663,
      "grad_norm": 0.4534226059913635,
      "learning_rate": 2.5699269758854715e-07,
      "loss": 0.7295,
      "step": 490
    },
    {
      "epoch": 0.06827802813054759,
      "grad_norm": 0.5993149876594543,
      "learning_rate": 0.0,
      "loss": 0.8247,
      "step": 500
    },
    {
      "epoch": 0.06827802813054759,
      "eval_loss": 0.7215211987495422,
      "eval_runtime": 304.1302,
      "eval_samples_per_second": 10.14,
      "eval_steps_per_second": 2.535,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5642309924225024e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}