{
  "best_metric": 1.0719058513641357,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.34916201117318435,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006983240223463687,
      "eval_loss": 1.370945930480957,
      "eval_runtime": 52.3088,
      "eval_samples_per_second": 11.528,
      "eval_steps_per_second": 2.887,
      "step": 1
    },
    {
      "epoch": 0.006983240223463687,
      "grad_norm": 0.8107507228851318,
      "learning_rate": 4.22e-05,
      "loss": 1.0747,
      "step": 10
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 0.5126632452011108,
      "learning_rate": 8.44e-05,
      "loss": 0.9055,
      "step": 20
    },
    {
      "epoch": 0.02094972067039106,
      "grad_norm": 0.6242287158966064,
      "learning_rate": 0.0001266,
      "loss": 0.9136,
      "step": 30
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 0.6027160882949829,
      "learning_rate": 0.0001688,
      "loss": 0.8772,
      "step": 40
    },
    {
      "epoch": 0.034916201117318434,
      "grad_norm": 1.1633682250976562,
      "learning_rate": 0.000211,
      "loss": 2.2737,
      "step": 50
    },
    {
      "epoch": 0.034916201117318434,
      "eval_loss": 1.2990323305130005,
      "eval_runtime": 52.3291,
      "eval_samples_per_second": 11.523,
      "eval_steps_per_second": 2.886,
      "step": 50
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 0.47972574830055237,
      "learning_rate": 0.00021074300730241147,
      "loss": 0.9318,
      "step": 60
    },
    {
      "epoch": 0.04888268156424581,
      "grad_norm": 0.447611004114151,
      "learning_rate": 0.00020997328125223568,
      "loss": 0.8635,
      "step": 70
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 0.48597830533981323,
      "learning_rate": 0.0002086945718774165,
      "loss": 0.9055,
      "step": 80
    },
    {
      "epoch": 0.06284916201117319,
      "grad_norm": 0.6027791500091553,
      "learning_rate": 0.00020691310892149265,
      "loss": 0.9913,
      "step": 90
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 1.350448489189148,
      "learning_rate": 0.00020463757149291335,
      "loss": 2.3175,
      "step": 100
    },
    {
      "epoch": 0.06983240223463687,
      "eval_loss": 1.2746367454528809,
      "eval_runtime": 52.113,
      "eval_samples_per_second": 11.571,
      "eval_steps_per_second": 2.898,
      "step": 100
    },
    {
      "epoch": 0.07681564245810056,
      "grad_norm": 0.5767949223518372,
      "learning_rate": 0.0002018790457812944,
      "loss": 0.9637,
      "step": 110
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 0.4701750576496124,
      "learning_rate": 0.0001986509710466168,
      "loss": 0.945,
      "step": 120
    },
    {
      "epoch": 0.09078212290502793,
      "grad_norm": 0.5360428690910339,
      "learning_rate": 0.00019496907414450293,
      "loss": 0.867,
      "step": 130
    },
    {
      "epoch": 0.09776536312849161,
      "grad_norm": 0.5477281212806702,
      "learning_rate": 0.00019085129290655697,
      "loss": 0.848,
      "step": 140
    },
    {
      "epoch": 0.10474860335195531,
      "grad_norm": 1.3646817207336426,
      "learning_rate": 0.00018631768874905217,
      "loss": 2.1608,
      "step": 150
    },
    {
      "epoch": 0.10474860335195531,
      "eval_loss": 1.219596028327942,
      "eval_runtime": 52.3452,
      "eval_samples_per_second": 11.52,
      "eval_steps_per_second": 2.885,
      "step": 150
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 0.4920892119407654,
      "learning_rate": 0.0001813903489357277,
      "loss": 0.9284,
      "step": 160
    },
    {
      "epoch": 0.11871508379888268,
      "grad_norm": 0.45749855041503906,
      "learning_rate": 0.00017609327897085954,
      "loss": 0.8539,
      "step": 170
    },
    {
      "epoch": 0.12569832402234637,
      "grad_norm": 0.4445869028568268,
      "learning_rate": 0.00017045228564685694,
      "loss": 0.8592,
      "step": 180
    },
    {
      "epoch": 0.13268156424581007,
      "grad_norm": 0.5051153302192688,
      "learning_rate": 0.0001644948513161638,
      "loss": 0.7785,
      "step": 190
    },
    {
      "epoch": 0.13966480446927373,
      "grad_norm": 1.2540266513824463,
      "learning_rate": 0.00015825,
      "loss": 1.9825,
      "step": 200
    },
    {
      "epoch": 0.13966480446927373,
      "eval_loss": 1.1976240873336792,
      "eval_runtime": 52.2387,
      "eval_samples_per_second": 11.543,
      "eval_steps_per_second": 2.891,
      "step": 200
    },
    {
      "epoch": 0.14664804469273743,
      "grad_norm": 0.44770610332489014,
      "learning_rate": 0.00015174815598624768,
      "loss": 0.91,
      "step": 210
    },
    {
      "epoch": 0.15363128491620112,
      "grad_norm": 0.4289681613445282,
      "learning_rate": 0.00014502099560537873,
      "loss": 0.9587,
      "step": 220
    },
    {
      "epoch": 0.16061452513966482,
      "grad_norm": 0.4543539583683014,
      "learning_rate": 0.00013810129290655696,
      "loss": 0.7476,
      "step": 230
    },
    {
      "epoch": 0.16759776536312848,
      "grad_norm": 0.6141102313995361,
      "learning_rate": 0.00013102275998576495,
      "loss": 0.9607,
      "step": 240
    },
    {
      "epoch": 0.17458100558659218,
      "grad_norm": 1.0941569805145264,
      "learning_rate": 0.00012381988274386116,
      "loss": 2.2834,
      "step": 250
    },
    {
      "epoch": 0.17458100558659218,
      "eval_loss": 1.150519847869873,
      "eval_runtime": 52.3046,
      "eval_samples_per_second": 11.529,
      "eval_steps_per_second": 2.887,
      "step": 250
    },
    {
      "epoch": 0.18156424581005587,
      "grad_norm": 0.5020606517791748,
      "learning_rate": 0.00011652775287473745,
      "loss": 0.9043,
      "step": 260
    },
    {
      "epoch": 0.18854748603351956,
      "grad_norm": 0.4165470004081726,
      "learning_rate": 0.00010918189690211387,
      "loss": 1.2468,
      "step": 270
    },
    {
      "epoch": 0.19553072625698323,
      "grad_norm": 0.4466763138771057,
      "learning_rate": 0.00010181810309788618,
      "loss": 0.772,
      "step": 280
    },
    {
      "epoch": 0.20251396648044692,
      "grad_norm": 0.5462682247161865,
      "learning_rate": 9.447224712526258e-05,
      "loss": 0.8108,
      "step": 290
    },
    {
      "epoch": 0.20949720670391062,
      "grad_norm": 1.6482914686203003,
      "learning_rate": 8.718011725613886e-05,
      "loss": 1.9559,
      "step": 300
    },
    {
      "epoch": 0.20949720670391062,
      "eval_loss": 1.1186692714691162,
      "eval_runtime": 52.2511,
      "eval_samples_per_second": 11.54,
      "eval_steps_per_second": 2.89,
      "step": 300
    },
    {
      "epoch": 0.2164804469273743,
      "grad_norm": 0.42285749316215515,
      "learning_rate": 7.997724001423507e-05,
      "loss": 0.9125,
      "step": 310
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.4134489595890045,
      "learning_rate": 7.289870709344306e-05,
      "loss": 0.8194,
      "step": 320
    },
    {
      "epoch": 0.23044692737430167,
      "grad_norm": 0.463888943195343,
      "learning_rate": 6.597900439462128e-05,
      "loss": 0.8107,
      "step": 330
    },
    {
      "epoch": 0.23743016759776536,
      "grad_norm": 0.48735177516937256,
      "learning_rate": 5.9251844013752326e-05,
      "loss": 0.802,
      "step": 340
    },
    {
      "epoch": 0.24441340782122906,
      "grad_norm": 1.3572193384170532,
      "learning_rate": 5.275000000000002e-05,
      "loss": 2.2902,
      "step": 350
    },
    {
      "epoch": 0.24441340782122906,
      "eval_loss": 1.097469449043274,
      "eval_runtime": 52.3157,
      "eval_samples_per_second": 11.526,
      "eval_steps_per_second": 2.886,
      "step": 350
    },
    {
      "epoch": 0.25139664804469275,
      "grad_norm": 0.40139132738113403,
      "learning_rate": 4.650514868383623e-05,
      "loss": 0.8447,
      "step": 360
    },
    {
      "epoch": 0.25837988826815644,
      "grad_norm": 0.39753517508506775,
      "learning_rate": 4.054771435314305e-05,
      "loss": 0.8506,
      "step": 370
    },
    {
      "epoch": 0.26536312849162014,
      "grad_norm": 0.46532756090164185,
      "learning_rate": 3.4906721029140495e-05,
      "loss": 0.7683,
      "step": 380
    },
    {
      "epoch": 0.2723463687150838,
      "grad_norm": 0.4958690106868744,
      "learning_rate": 2.9609651064272323e-05,
      "loss": 0.9185,
      "step": 390
    },
    {
      "epoch": 0.27932960893854747,
      "grad_norm": 1.153603434562683,
      "learning_rate": 2.468231125094783e-05,
      "loss": 2.3402,
      "step": 400
    },
    {
      "epoch": 0.27932960893854747,
      "eval_loss": 1.0796676874160767,
      "eval_runtime": 51.9898,
      "eval_samples_per_second": 11.598,
      "eval_steps_per_second": 2.904,
      "step": 400
    },
    {
      "epoch": 0.28631284916201116,
      "grad_norm": 0.40567949414253235,
      "learning_rate": 2.0148707093443057e-05,
      "loss": 0.8683,
      "step": 410
    },
    {
      "epoch": 0.29329608938547486,
      "grad_norm": 0.3860771656036377,
      "learning_rate": 1.603092585549706e-05,
      "loss": 0.7976,
      "step": 420
    },
    {
      "epoch": 0.30027932960893855,
      "grad_norm": 0.4146096408367157,
      "learning_rate": 1.2349028953383204e-05,
      "loss": 0.7469,
      "step": 430
    },
    {
      "epoch": 0.30726256983240224,
      "grad_norm": 0.5146927237510681,
      "learning_rate": 9.120954218705596e-06,
      "loss": 0.8733,
      "step": 440
    },
    {
      "epoch": 0.31424581005586594,
      "grad_norm": 1.1636193990707397,
      "learning_rate": 6.362428507086673e-06,
      "loss": 2.3676,
      "step": 450
    },
    {
      "epoch": 0.31424581005586594,
      "eval_loss": 1.0726971626281738,
      "eval_runtime": 52.9212,
      "eval_samples_per_second": 11.394,
      "eval_steps_per_second": 2.853,
      "step": 450
    },
    {
      "epoch": 0.32122905027932963,
      "grad_norm": 0.39169561862945557,
      "learning_rate": 4.0868910785073565e-06,
      "loss": 0.8389,
      "step": 460
    },
    {
      "epoch": 0.32821229050279327,
      "grad_norm": 0.38382428884506226,
      "learning_rate": 2.3054281225835e-06,
      "loss": 0.7781,
      "step": 470
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 0.4115770161151886,
      "learning_rate": 1.026718747764327e-06,
      "loss": 0.7531,
      "step": 480
    },
    {
      "epoch": 0.34217877094972066,
      "grad_norm": 0.47876521944999695,
      "learning_rate": 2.5699269758854715e-07,
      "loss": 0.8186,
      "step": 490
    },
    {
      "epoch": 0.34916201117318435,
      "grad_norm": 1.236006259918213,
      "learning_rate": 0.0,
      "loss": 2.1411,
      "step": 500
    },
    {
      "epoch": 0.34916201117318435,
      "eval_loss": 1.0719058513641357,
      "eval_runtime": 52.6183,
      "eval_samples_per_second": 11.46,
      "eval_steps_per_second": 2.87,
      "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": 1.408558478917632e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}