{
  "best_metric": 1.2717281579971313,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.28810141169691733,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005762028233938346,
      "eval_loss": 2.759286642074585,
      "eval_runtime": 44.2859,
      "eval_samples_per_second": 16.506,
      "eval_steps_per_second": 4.132,
      "step": 1
    },
    {
      "epoch": 0.005762028233938346,
      "grad_norm": 0.6934571266174316,
      "learning_rate": 4.3e-05,
      "loss": 2.2019,
      "step": 10
    },
    {
      "epoch": 0.011524056467876692,
      "grad_norm": 1.1018927097320557,
      "learning_rate": 8.6e-05,
      "loss": 2.072,
      "step": 20
    },
    {
      "epoch": 0.01728608470181504,
      "grad_norm": 1.6100819110870361,
      "learning_rate": 0.000129,
      "loss": 1.4799,
      "step": 30
    },
    {
      "epoch": 0.023048112935753384,
      "grad_norm": 1.5464179515838623,
      "learning_rate": 0.000172,
      "loss": 1.2626,
      "step": 40
    },
    {
      "epoch": 0.02881014116969173,
      "grad_norm": 1.7817376852035522,
      "learning_rate": 0.000215,
      "loss": 1.0018,
      "step": 50
    },
    {
      "epoch": 0.02881014116969173,
      "eval_loss": 1.4174914360046387,
      "eval_runtime": 44.7179,
      "eval_samples_per_second": 16.347,
      "eval_steps_per_second": 4.092,
      "step": 50
    },
    {
      "epoch": 0.03457216940363008,
      "grad_norm": 0.6755384802818298,
      "learning_rate": 0.0002147381354029311,
      "loss": 1.8599,
      "step": 60
    },
    {
      "epoch": 0.040334197637568424,
      "grad_norm": 0.9027474522590637,
      "learning_rate": 0.0002139538173897188,
      "loss": 1.5252,
      "step": 70
    },
    {
      "epoch": 0.04609622587150677,
      "grad_norm": 1.0059105157852173,
      "learning_rate": 0.0002126508670788841,
      "loss": 1.2772,
      "step": 80
    },
    {
      "epoch": 0.05185825410544512,
      "grad_norm": 0.9736582636833191,
      "learning_rate": 0.00021083563231336926,
      "loss": 1.0586,
      "step": 90
    },
    {
      "epoch": 0.05762028233938346,
      "grad_norm": 1.0923612117767334,
      "learning_rate": 0.00020851695673448515,
      "loss": 0.7892,
      "step": 100
    },
    {
      "epoch": 0.05762028233938346,
      "eval_loss": 1.486754298210144,
      "eval_runtime": 44.9804,
      "eval_samples_per_second": 16.252,
      "eval_steps_per_second": 4.068,
      "step": 100
    },
    {
      "epoch": 0.0633823105733218,
      "grad_norm": 0.610034704208374,
      "learning_rate": 0.00020570613669657956,
      "loss": 1.7989,
      "step": 110
    },
    {
      "epoch": 0.06914433880726016,
      "grad_norm": 0.7986786365509033,
      "learning_rate": 0.00020241686623233464,
      "loss": 1.5293,
      "step": 120
    },
    {
      "epoch": 0.0749063670411985,
      "grad_norm": 0.9212441444396973,
      "learning_rate": 0.00019866517033681577,
      "loss": 1.2778,
      "step": 130
    },
    {
      "epoch": 0.08066839527513685,
      "grad_norm": 0.9731055498123169,
      "learning_rate": 0.00019446932689530684,
      "loss": 1.0822,
      "step": 140
    },
    {
      "epoch": 0.08643042350907519,
      "grad_norm": 1.488525390625,
      "learning_rate": 0.0001898497776352901,
      "loss": 0.8345,
      "step": 150
    },
    {
      "epoch": 0.08643042350907519,
      "eval_loss": 1.5110596418380737,
      "eval_runtime": 45.1761,
      "eval_samples_per_second": 16.181,
      "eval_steps_per_second": 4.051,
      "step": 150
    },
    {
      "epoch": 0.09219245174301353,
      "grad_norm": 0.5915709733963013,
      "learning_rate": 0.000184829028536405,
      "loss": 1.8188,
      "step": 160
    },
    {
      "epoch": 0.09795447997695189,
      "grad_norm": 0.8901687860488892,
      "learning_rate": 0.00017943154018357726,
      "loss": 1.5977,
      "step": 170
    },
    {
      "epoch": 0.10371650821089023,
      "grad_norm": 1.0244994163513184,
      "learning_rate": 0.00017368360859750824,
      "loss": 1.3397,
      "step": 180
    },
    {
      "epoch": 0.10947853644482858,
      "grad_norm": 1.4333339929580688,
      "learning_rate": 0.00016761323712310527,
      "loss": 1.184,
      "step": 190
    },
    {
      "epoch": 0.11524056467876692,
      "grad_norm": 1.4265000820159912,
      "learning_rate": 0.00016125,
      "loss": 0.7475,
      "step": 200
    },
    {
      "epoch": 0.11524056467876692,
      "eval_loss": 1.3707703351974487,
      "eval_runtime": 44.8927,
      "eval_samples_per_second": 16.283,
      "eval_steps_per_second": 4.076,
      "step": 200
    },
    {
      "epoch": 0.12100259291270528,
      "grad_norm": 0.5921943783760071,
      "learning_rate": 0.0001546248982798258,
      "loss": 1.7297,
      "step": 210
    },
    {
      "epoch": 0.1267646211466436,
      "grad_norm": 0.6880895495414734,
      "learning_rate": 0.00014777020879221055,
      "loss": 1.5429,
      "step": 220
    },
    {
      "epoch": 0.13252664938058195,
      "grad_norm": 1.1970090866088867,
      "learning_rate": 0.00014071932689530684,
      "loss": 1.3795,
      "step": 230
    },
    {
      "epoch": 0.13828867761452032,
      "grad_norm": 1.1682662963867188,
      "learning_rate": 0.00013350660377696428,
      "loss": 1.113,
      "step": 240
    },
    {
      "epoch": 0.14405070584845867,
      "grad_norm": 1.2679342031478882,
      "learning_rate": 0.00012616717909919503,
      "loss": 0.7694,
      "step": 250
    },
    {
      "epoch": 0.14405070584845867,
      "eval_loss": 1.3522343635559082,
      "eval_runtime": 44.9013,
      "eval_samples_per_second": 16.28,
      "eval_steps_per_second": 4.076,
      "step": 250
    },
    {
      "epoch": 0.149812734082397,
      "grad_norm": 0.5863513350486755,
      "learning_rate": 0.00011873680980127275,
      "loss": 1.7156,
      "step": 260
    },
    {
      "epoch": 0.15557476231633535,
      "grad_norm": 0.697924792766571,
      "learning_rate": 0.00011125169589551887,
      "loss": 1.5295,
      "step": 270
    },
    {
      "epoch": 0.1613367905502737,
      "grad_norm": 0.7577078342437744,
      "learning_rate": 0.00010374830410448118,
      "loss": 1.3598,
      "step": 280
    },
    {
      "epoch": 0.16709881878421204,
      "grad_norm": 1.2936521768569946,
      "learning_rate": 9.626319019872726e-05,
      "loss": 1.1964,
      "step": 290
    },
    {
      "epoch": 0.17286084701815038,
      "grad_norm": 1.469357967376709,
      "learning_rate": 8.883282090080499e-05,
      "loss": 0.7995,
      "step": 300
    },
    {
      "epoch": 0.17286084701815038,
      "eval_loss": 1.2939176559448242,
      "eval_runtime": 45.0244,
      "eval_samples_per_second": 16.236,
      "eval_steps_per_second": 4.064,
      "step": 300
    },
    {
      "epoch": 0.17862287525208873,
      "grad_norm": 0.6379753947257996,
      "learning_rate": 8.149339622303573e-05,
      "loss": 1.7099,
      "step": 310
    },
    {
      "epoch": 0.18438490348602707,
      "grad_norm": 0.7869443893432617,
      "learning_rate": 7.428067310469316e-05,
      "loss": 1.5069,
      "step": 320
    },
    {
      "epoch": 0.19014693171996544,
      "grad_norm": 0.8459405899047852,
      "learning_rate": 6.722979120778945e-05,
      "loss": 1.3902,
      "step": 330
    },
    {
      "epoch": 0.19590895995390378,
      "grad_norm": 0.9072573781013489,
      "learning_rate": 6.0375101720174165e-05,
      "loss": 1.1384,
      "step": 340
    },
    {
      "epoch": 0.20167098818784213,
      "grad_norm": 1.5639623403549194,
      "learning_rate": 5.3750000000000026e-05,
      "loss": 0.7331,
      "step": 350
    },
    {
      "epoch": 0.20167098818784213,
      "eval_loss": 1.2823299169540405,
      "eval_runtime": 44.7714,
      "eval_samples_per_second": 16.327,
      "eval_steps_per_second": 4.087,
      "step": 350
    },
    {
      "epoch": 0.20743301642178047,
      "grad_norm": 0.6709028482437134,
      "learning_rate": 4.738676287689473e-05,
      "loss": 1.701,
      "step": 360
    },
    {
      "epoch": 0.2131950446557188,
      "grad_norm": 0.6328491568565369,
      "learning_rate": 4.131639140249173e-05,
      "loss": 1.524,
      "step": 370
    },
    {
      "epoch": 0.21895707288965716,
      "grad_norm": 0.835404634475708,
      "learning_rate": 3.5568459816422774e-05,
      "loss": 1.2396,
      "step": 380
    },
    {
      "epoch": 0.2247191011235955,
      "grad_norm": 0.9026359915733337,
      "learning_rate": 3.017097146359502e-05,
      "loss": 0.96,
      "step": 390
    },
    {
      "epoch": 0.23048112935753384,
      "grad_norm": 1.3837984800338745,
      "learning_rate": 2.5150222364709875e-05,
      "loss": 0.7806,
      "step": 400
    },
    {
      "epoch": 0.23048112935753384,
      "eval_loss": 1.2757760286331177,
      "eval_runtime": 44.9117,
      "eval_samples_per_second": 16.276,
      "eval_steps_per_second": 4.075,
      "step": 400
    },
    {
      "epoch": 0.23624315759147219,
      "grad_norm": 0.691465437412262,
      "learning_rate": 2.053067310469316e-05,
      "loss": 1.7634,
      "step": 410
    },
    {
      "epoch": 0.24200518582541056,
      "grad_norm": 0.6821807026863098,
      "learning_rate": 1.633482966318421e-05,
      "loss": 1.3809,
      "step": 420
    },
    {
      "epoch": 0.2477672140593489,
      "grad_norm": 0.761147141456604,
      "learning_rate": 1.2583133767665349e-05,
      "loss": 1.3838,
      "step": 430
    },
    {
      "epoch": 0.2535292422932872,
      "grad_norm": 0.964479923248291,
      "learning_rate": 9.293863303420395e-06,
      "loss": 1.1305,
      "step": 440
    },
    {
      "epoch": 0.25929127052722556,
      "grad_norm": 1.2261676788330078,
      "learning_rate": 6.483043265514856e-06,
      "loss": 0.7941,
      "step": 450
    },
    {
      "epoch": 0.25929127052722556,
      "eval_loss": 1.2717281579971313,
      "eval_runtime": 44.7154,
      "eval_samples_per_second": 16.348,
      "eval_steps_per_second": 4.093,
      "step": 450
    },
    {
      "epoch": 0.2650532987611639,
      "grad_norm": 0.5627772808074951,
      "learning_rate": 4.164367686630719e-06,
      "loss": 1.6535,
      "step": 460
    },
    {
      "epoch": 0.2708153269951023,
      "grad_norm": 0.6691345572471619,
      "learning_rate": 2.3491329211158885e-06,
      "loss": 1.3014,
      "step": 470
    },
    {
      "epoch": 0.27657735522904064,
      "grad_norm": 0.8095937371253967,
      "learning_rate": 1.046182610281186e-06,
      "loss": 1.2333,
      "step": 480
    },
    {
      "epoch": 0.282339383462979,
      "grad_norm": 1.0728657245635986,
      "learning_rate": 2.6186459706889876e-07,
      "loss": 1.0591,
      "step": 490
    },
    {
      "epoch": 0.28810141169691733,
      "grad_norm": 2.1311142444610596,
      "learning_rate": 0.0,
      "loss": 0.7293,
      "step": 500
    },
    {
      "epoch": 0.28810141169691733,
      "eval_loss": 1.2725006341934204,
      "eval_runtime": 45.1255,
      "eval_samples_per_second": 16.199,
      "eval_steps_per_second": 4.055,
      "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": 9.070027045915853e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}