{
  "best_metric": 0.10595488548278809,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.2720348204570185,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000544069640914037,
      "eval_loss": 0.3388690948486328,
      "eval_runtime": 65.8398,
      "eval_samples_per_second": 5.878,
      "eval_steps_per_second": 1.473,
      "step": 1
    },
    {
      "epoch": 0.00544069640914037,
      "grad_norm": 0.17145936191082,
      "learning_rate": 4.22e-05,
      "loss": 0.2495,
      "step": 10
    },
    {
      "epoch": 0.01088139281828074,
      "grad_norm": 0.27646932005882263,
      "learning_rate": 8.44e-05,
      "loss": 0.2263,
      "step": 20
    },
    {
      "epoch": 0.01632208922742111,
      "grad_norm": 0.2995341122150421,
      "learning_rate": 0.0001266,
      "loss": 0.1708,
      "step": 30
    },
    {
      "epoch": 0.02176278563656148,
      "grad_norm": 0.2981434166431427,
      "learning_rate": 0.0001688,
      "loss": 0.1959,
      "step": 40
    },
    {
      "epoch": 0.02720348204570185,
      "grad_norm": 0.16809503734111786,
      "learning_rate": 0.000211,
      "loss": 0.1967,
      "step": 50
    },
    {
      "epoch": 0.02720348204570185,
      "eval_loss": 0.14689071476459503,
      "eval_runtime": 66.1969,
      "eval_samples_per_second": 5.846,
      "eval_steps_per_second": 1.465,
      "step": 50
    },
    {
      "epoch": 0.03264417845484222,
      "grad_norm": 0.29836317896842957,
      "learning_rate": 0.00021074300730241147,
      "loss": 0.1934,
      "step": 60
    },
    {
      "epoch": 0.03808487486398259,
      "grad_norm": 0.5127425789833069,
      "learning_rate": 0.00020997328125223568,
      "loss": 0.2337,
      "step": 70
    },
    {
      "epoch": 0.04352557127312296,
      "grad_norm": 0.7148259878158569,
      "learning_rate": 0.0002086945718774165,
      "loss": 0.3728,
      "step": 80
    },
    {
      "epoch": 0.04896626768226333,
      "grad_norm": 0.7618590593338013,
      "learning_rate": 0.00020691310892149265,
      "loss": 0.4246,
      "step": 90
    },
    {
      "epoch": 0.0544069640914037,
      "grad_norm": 1.4085367918014526,
      "learning_rate": 0.00020463757149291335,
      "loss": 0.6418,
      "step": 100
    },
    {
      "epoch": 0.0544069640914037,
      "eval_loss": 0.18226467072963715,
      "eval_runtime": 66.1407,
      "eval_samples_per_second": 5.851,
      "eval_steps_per_second": 1.467,
      "step": 100
    },
    {
      "epoch": 0.05984766050054407,
      "grad_norm": 0.09314069151878357,
      "learning_rate": 0.0002018790457812944,
      "loss": 0.1106,
      "step": 110
    },
    {
      "epoch": 0.06528835690968444,
      "grad_norm": 0.19934406876564026,
      "learning_rate": 0.0001986509710466168,
      "loss": 0.1377,
      "step": 120
    },
    {
      "epoch": 0.07072905331882481,
      "grad_norm": 0.16686424612998962,
      "learning_rate": 0.00019496907414450293,
      "loss": 0.1762,
      "step": 130
    },
    {
      "epoch": 0.07616974972796518,
      "grad_norm": 0.1390169858932495,
      "learning_rate": 0.00019085129290655697,
      "loss": 0.1576,
      "step": 140
    },
    {
      "epoch": 0.08161044613710555,
      "grad_norm": 0.36551663279533386,
      "learning_rate": 0.00018631768874905217,
      "loss": 0.2147,
      "step": 150
    },
    {
      "epoch": 0.08161044613710555,
      "eval_loss": 0.1364036649465561,
      "eval_runtime": 66.6017,
      "eval_samples_per_second": 5.811,
      "eval_steps_per_second": 1.456,
      "step": 150
    },
    {
      "epoch": 0.08705114254624592,
      "grad_norm": 0.26904261112213135,
      "learning_rate": 0.0001813903489357277,
      "loss": 0.234,
      "step": 160
    },
    {
      "epoch": 0.09249183895538629,
      "grad_norm": 0.448312371969223,
      "learning_rate": 0.00017609327897085954,
      "loss": 0.2675,
      "step": 170
    },
    {
      "epoch": 0.09793253536452666,
      "grad_norm": 0.6152125000953674,
      "learning_rate": 0.00017045228564685694,
      "loss": 0.3036,
      "step": 180
    },
    {
      "epoch": 0.10337323177366703,
      "grad_norm": 0.39368465542793274,
      "learning_rate": 0.0001644948513161638,
      "loss": 0.3332,
      "step": 190
    },
    {
      "epoch": 0.1088139281828074,
      "grad_norm": 1.3323695659637451,
      "learning_rate": 0.00015825,
      "loss": 0.4591,
      "step": 200
    },
    {
      "epoch": 0.1088139281828074,
      "eval_loss": 0.14527782797813416,
      "eval_runtime": 66.1265,
      "eval_samples_per_second": 5.852,
      "eval_steps_per_second": 1.467,
      "step": 200
    },
    {
      "epoch": 0.11425462459194777,
      "grad_norm": 0.17673972249031067,
      "learning_rate": 0.00015174815598624768,
      "loss": 0.1101,
      "step": 210
    },
    {
      "epoch": 0.11969532100108814,
      "grad_norm": 0.18985572457313538,
      "learning_rate": 0.00014502099560537873,
      "loss": 0.1234,
      "step": 220
    },
    {
      "epoch": 0.1251360174102285,
      "grad_norm": 0.1908355951309204,
      "learning_rate": 0.00013810129290655696,
      "loss": 0.13,
      "step": 230
    },
    {
      "epoch": 0.1305767138193689,
      "grad_norm": 0.2177634984254837,
      "learning_rate": 0.00013102275998576495,
      "loss": 0.1802,
      "step": 240
    },
    {
      "epoch": 0.13601741022850924,
      "grad_norm": 0.18758904933929443,
      "learning_rate": 0.00012381988274386116,
      "loss": 0.1612,
      "step": 250
    },
    {
      "epoch": 0.13601741022850924,
      "eval_loss": 0.13536955416202545,
      "eval_runtime": 66.6366,
      "eval_samples_per_second": 5.808,
      "eval_steps_per_second": 1.456,
      "step": 250
    },
    {
      "epoch": 0.14145810663764963,
      "grad_norm": 0.5093297958374023,
      "learning_rate": 0.00011652775287473745,
      "loss": 0.1836,
      "step": 260
    },
    {
      "epoch": 0.14689880304678998,
      "grad_norm": 0.5727118849754333,
      "learning_rate": 0.00010918189690211387,
      "loss": 0.2044,
      "step": 270
    },
    {
      "epoch": 0.15233949945593037,
      "grad_norm": 0.4531668424606323,
      "learning_rate": 0.00010181810309788618,
      "loss": 0.2924,
      "step": 280
    },
    {
      "epoch": 0.15778019586507072,
      "grad_norm": 0.9934888482093811,
      "learning_rate": 9.447224712526258e-05,
      "loss": 0.3537,
      "step": 290
    },
    {
      "epoch": 0.1632208922742111,
      "grad_norm": 0.6647962927818298,
      "learning_rate": 8.718011725613886e-05,
      "loss": 0.4845,
      "step": 300
    },
    {
      "epoch": 0.1632208922742111,
      "eval_loss": 0.12240716814994812,
      "eval_runtime": 66.1711,
      "eval_samples_per_second": 5.848,
      "eval_steps_per_second": 1.466,
      "step": 300
    },
    {
      "epoch": 0.16866158868335146,
      "grad_norm": 0.062041934579610825,
      "learning_rate": 7.997724001423507e-05,
      "loss": 0.0804,
      "step": 310
    },
    {
      "epoch": 0.17410228509249184,
      "grad_norm": 0.2328738570213318,
      "learning_rate": 7.289870709344306e-05,
      "loss": 0.079,
      "step": 320
    },
    {
      "epoch": 0.1795429815016322,
      "grad_norm": 0.1590886265039444,
      "learning_rate": 6.597900439462128e-05,
      "loss": 0.1257,
      "step": 330
    },
    {
      "epoch": 0.18498367791077258,
      "grad_norm": 0.205345019698143,
      "learning_rate": 5.9251844013752326e-05,
      "loss": 0.1441,
      "step": 340
    },
    {
      "epoch": 0.19042437431991294,
      "grad_norm": 0.1600612848997116,
      "learning_rate": 5.275000000000002e-05,
      "loss": 0.1837,
      "step": 350
    },
    {
      "epoch": 0.19042437431991294,
      "eval_loss": 0.11754260957241058,
      "eval_runtime": 66.1447,
      "eval_samples_per_second": 5.851,
      "eval_steps_per_second": 1.466,
      "step": 350
    },
    {
      "epoch": 0.19586507072905332,
      "grad_norm": 0.26457643508911133,
      "learning_rate": 4.650514868383623e-05,
      "loss": 0.1924,
      "step": 360
    },
    {
      "epoch": 0.20130576713819368,
      "grad_norm": 0.36637988686561584,
      "learning_rate": 4.054771435314305e-05,
      "loss": 0.1966,
      "step": 370
    },
    {
      "epoch": 0.20674646354733406,
      "grad_norm": 0.4704027473926544,
      "learning_rate": 3.4906721029140495e-05,
      "loss": 0.2195,
      "step": 380
    },
    {
      "epoch": 0.21218715995647444,
      "grad_norm": 0.7301682829856873,
      "learning_rate": 2.9609651064272323e-05,
      "loss": 0.3013,
      "step": 390
    },
    {
      "epoch": 0.2176278563656148,
      "grad_norm": 1.4596174955368042,
      "learning_rate": 2.468231125094783e-05,
      "loss": 0.534,
      "step": 400
    },
    {
      "epoch": 0.2176278563656148,
      "eval_loss": 0.10635092109441757,
      "eval_runtime": 66.0037,
      "eval_samples_per_second": 5.863,
      "eval_steps_per_second": 1.47,
      "step": 400
    },
    {
      "epoch": 0.22306855277475518,
      "grad_norm": 0.08893619477748871,
      "learning_rate": 2.0148707093443057e-05,
      "loss": 0.0705,
      "step": 410
    },
    {
      "epoch": 0.22850924918389554,
      "grad_norm": 0.11107783019542694,
      "learning_rate": 1.603092585549706e-05,
      "loss": 0.0688,
      "step": 420
    },
    {
      "epoch": 0.23394994559303592,
      "grad_norm": 0.2446814477443695,
      "learning_rate": 1.2349028953383204e-05,
      "loss": 0.1321,
      "step": 430
    },
    {
      "epoch": 0.23939064200217627,
      "grad_norm": 0.1496814340353012,
      "learning_rate": 9.120954218705596e-06,
      "loss": 0.157,
      "step": 440
    },
    {
      "epoch": 0.24483133841131666,
      "grad_norm": 0.18574567139148712,
      "learning_rate": 6.362428507086673e-06,
      "loss": 0.1899,
      "step": 450
    },
    {
      "epoch": 0.24483133841131666,
      "eval_loss": 0.10692635923624039,
      "eval_runtime": 66.4273,
      "eval_samples_per_second": 5.826,
      "eval_steps_per_second": 1.46,
      "step": 450
    },
    {
      "epoch": 0.250272034820457,
      "grad_norm": 0.14279238879680634,
      "learning_rate": 4.0868910785073565e-06,
      "loss": 0.1664,
      "step": 460
    },
    {
      "epoch": 0.25571273122959737,
      "grad_norm": 0.6236724853515625,
      "learning_rate": 2.3054281225835e-06,
      "loss": 0.2752,
      "step": 470
    },
    {
      "epoch": 0.2611534276387378,
      "grad_norm": 0.802135169506073,
      "learning_rate": 1.026718747764327e-06,
      "loss": 0.2971,
      "step": 480
    },
    {
      "epoch": 0.26659412404787813,
      "grad_norm": 0.7756718993186951,
      "learning_rate": 2.5699269758854715e-07,
      "loss": 0.3215,
      "step": 490
    },
    {
      "epoch": 0.2720348204570185,
      "grad_norm": 0.9758143424987793,
      "learning_rate": 0.0,
      "loss": 0.4517,
      "step": 500
    },
    {
      "epoch": 0.2720348204570185,
      "eval_loss": 0.10595488548278809,
      "eval_runtime": 66.4878,
      "eval_samples_per_second": 5.821,
      "eval_steps_per_second": 1.459,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3049289243623424e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}