{
  "best_metric": 2.2774572372436523,
  "best_model_checkpoint": "miner_id_24/checkpoint-600",
  "epoch": 0.07487131492746842,
  "eval_steps": 50,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012478552487911403,
      "eval_loss": 2.4755678176879883,
      "eval_runtime": 773.5103,
      "eval_samples_per_second": 17.449,
      "eval_steps_per_second": 4.363,
      "step": 1
    },
    {
      "epoch": 0.0012478552487911402,
      "grad_norm": 0.16583509743213654,
      "learning_rate": 0.0002,
      "loss": 2.3528,
      "step": 10
    },
    {
      "epoch": 0.0024957104975822804,
      "grad_norm": 0.25612133741378784,
      "learning_rate": 0.0001998582695676762,
      "loss": 2.4048,
      "step": 20
    },
    {
      "epoch": 0.003743565746373421,
      "grad_norm": 0.2528512477874756,
      "learning_rate": 0.00019943348002101371,
      "loss": 2.3608,
      "step": 30
    },
    {
      "epoch": 0.004991420995164561,
      "grad_norm": 0.28028661012649536,
      "learning_rate": 0.00019872683547213446,
      "loss": 2.3613,
      "step": 40
    },
    {
      "epoch": 0.006239276243955701,
      "grad_norm": 0.5793240666389465,
      "learning_rate": 0.00019774033898178667,
      "loss": 2.3264,
      "step": 50
    },
    {
      "epoch": 0.006239276243955701,
      "eval_loss": 2.371112585067749,
      "eval_runtime": 776.6819,
      "eval_samples_per_second": 17.378,
      "eval_steps_per_second": 4.345,
      "step": 50
    },
    {
      "epoch": 0.007487131492746842,
      "grad_norm": 0.12962862849235535,
      "learning_rate": 0.0001964767868814516,
      "loss": 2.3947,
      "step": 60
    },
    {
      "epoch": 0.008734986741537982,
      "grad_norm": 0.20106595754623413,
      "learning_rate": 0.00019493976084683813,
      "loss": 2.3285,
      "step": 70
    },
    {
      "epoch": 0.009982841990329122,
      "grad_norm": 0.21679773926734924,
      "learning_rate": 0.00019313361774523385,
      "loss": 2.3039,
      "step": 80
    },
    {
      "epoch": 0.011230697239120261,
      "grad_norm": 0.2606624662876129,
      "learning_rate": 0.00019106347728549135,
      "loss": 2.3043,
      "step": 90
    },
    {
      "epoch": 0.012478552487911403,
      "grad_norm": 0.5491822361946106,
      "learning_rate": 0.00018873520750565718,
      "loss": 2.3937,
      "step": 100
    },
    {
      "epoch": 0.012478552487911403,
      "eval_loss": 2.3474936485290527,
      "eval_runtime": 776.4812,
      "eval_samples_per_second": 17.382,
      "eval_steps_per_second": 4.347,
      "step": 100
    },
    {
      "epoch": 0.013726407736702542,
      "grad_norm": 0.14413654804229736,
      "learning_rate": 0.0001861554081393806,
      "loss": 2.3631,
      "step": 110
    },
    {
      "epoch": 0.014974262985493684,
      "grad_norm": 0.1816205084323883,
      "learning_rate": 0.0001833313919082515,
      "loss": 2.2978,
      "step": 120
    },
    {
      "epoch": 0.01622211823428482,
      "grad_norm": 0.2172219306230545,
      "learning_rate": 0.00018027116379309638,
      "loss": 2.3025,
      "step": 130
    },
    {
      "epoch": 0.017469973483075964,
      "grad_norm": 0.2570364475250244,
      "learning_rate": 0.00017698339834299061,
      "loss": 2.277,
      "step": 140
    },
    {
      "epoch": 0.018717828731867104,
      "grad_norm": 0.5790348649024963,
      "learning_rate": 0.00017347741508630672,
      "loss": 2.3765,
      "step": 150
    },
    {
      "epoch": 0.018717828731867104,
      "eval_loss": 2.32619309425354,
      "eval_runtime": 776.2554,
      "eval_samples_per_second": 17.387,
      "eval_steps_per_second": 4.348,
      "step": 150
    },
    {
      "epoch": 0.019965683980658244,
      "grad_norm": 0.12973032891750336,
      "learning_rate": 0.0001697631521134985,
      "loss": 2.3644,
      "step": 160
    },
    {
      "epoch": 0.021213539229449383,
      "grad_norm": 0.16801460087299347,
      "learning_rate": 0.00016585113790650388,
      "loss": 2.3234,
      "step": 170
    },
    {
      "epoch": 0.022461394478240523,
      "grad_norm": 0.21193420886993408,
      "learning_rate": 0.0001617524614946192,
      "loss": 2.2965,
      "step": 180
    },
    {
      "epoch": 0.023709249727031666,
      "grad_norm": 0.25452449917793274,
      "learning_rate": 0.0001574787410214407,
      "loss": 2.2585,
      "step": 190
    },
    {
      "epoch": 0.024957104975822805,
      "grad_norm": 0.6596676707267761,
      "learning_rate": 0.00015304209081197425,
      "loss": 2.2978,
      "step": 200
    },
    {
      "epoch": 0.024957104975822805,
      "eval_loss": 2.3140604496002197,
      "eval_runtime": 777.3893,
      "eval_samples_per_second": 17.362,
      "eval_steps_per_second": 4.341,
      "step": 200
    },
    {
      "epoch": 0.026204960224613945,
      "grad_norm": 0.13376474380493164,
      "learning_rate": 0.00014845508703326504,
      "loss": 2.3587,
      "step": 210
    },
    {
      "epoch": 0.027452815473405084,
      "grad_norm": 0.17478545010089874,
      "learning_rate": 0.00014373073204588556,
      "loss": 2.2949,
      "step": 220
    },
    {
      "epoch": 0.028700670722196224,
      "grad_norm": 0.216487318277359,
      "learning_rate": 0.00013888241754733208,
      "loss": 2.3117,
      "step": 230
    },
    {
      "epoch": 0.029948525970987367,
      "grad_norm": 0.256217896938324,
      "learning_rate": 0.00013392388661180303,
      "loss": 2.2552,
      "step": 240
    },
    {
      "epoch": 0.031196381219778507,
      "grad_norm": 1.1952381134033203,
      "learning_rate": 0.0001288691947339621,
      "loss": 2.3613,
      "step": 250
    },
    {
      "epoch": 0.031196381219778507,
      "eval_loss": 2.302210569381714,
      "eval_runtime": 776.8581,
      "eval_samples_per_second": 17.374,
      "eval_steps_per_second": 4.344,
      "step": 250
    },
    {
      "epoch": 0.03244423646856964,
      "grad_norm": 0.12836463749408722,
      "learning_rate": 0.0001237326699871115,
      "loss": 2.3424,
      "step": 260
    },
    {
      "epoch": 0.03369209171736079,
      "grad_norm": 0.1755310595035553,
      "learning_rate": 0.00011852887240871145,
      "loss": 2.3364,
      "step": 270
    },
    {
      "epoch": 0.03493994696615193,
      "grad_norm": 0.2055431306362152,
      "learning_rate": 0.00011327255272837221,
      "loss": 2.2775,
      "step": 280
    },
    {
      "epoch": 0.03618780221494307,
      "grad_norm": 0.25998595356941223,
      "learning_rate": 0.00010797861055530831,
      "loss": 2.2766,
      "step": 290
    },
    {
      "epoch": 0.03743565746373421,
      "grad_norm": 0.5140986442565918,
      "learning_rate": 0.00010266205214377748,
      "loss": 2.2792,
      "step": 300
    },
    {
      "epoch": 0.03743565746373421,
      "eval_loss": 2.2953712940216064,
      "eval_runtime": 777.8336,
      "eval_samples_per_second": 17.352,
      "eval_steps_per_second": 4.339,
      "step": 300
    },
    {
      "epoch": 0.03868351271252535,
      "grad_norm": 0.13169974088668823,
      "learning_rate": 9.733794785622253e-05,
      "loss": 2.3453,
      "step": 310
    },
    {
      "epoch": 0.03993136796131649,
      "grad_norm": 0.18538571894168854,
      "learning_rate": 9.202138944469168e-05,
      "loss": 2.3464,
      "step": 320
    },
    {
      "epoch": 0.04117922321010763,
      "grad_norm": 0.21668769419193268,
      "learning_rate": 8.672744727162781e-05,
      "loss": 2.2719,
      "step": 330
    },
    {
      "epoch": 0.042427078458898766,
      "grad_norm": 0.2757132351398468,
      "learning_rate": 8.147112759128859e-05,
      "loss": 2.2284,
      "step": 340
    },
    {
      "epoch": 0.043674933707689906,
      "grad_norm": 0.4823644757270813,
      "learning_rate": 7.626733001288851e-05,
      "loss": 2.3233,
      "step": 350
    },
    {
      "epoch": 0.043674933707689906,
      "eval_loss": 2.2893431186676025,
      "eval_runtime": 776.9389,
      "eval_samples_per_second": 17.372,
      "eval_steps_per_second": 4.344,
      "step": 350
    },
    {
      "epoch": 0.044922788956481045,
      "grad_norm": 0.12886932492256165,
      "learning_rate": 7.113080526603792e-05,
      "loss": 2.3833,
      "step": 360
    },
    {
      "epoch": 0.04617064420527219,
      "grad_norm": 0.19028502702713013,
      "learning_rate": 6.607611338819697e-05,
      "loss": 2.2903,
      "step": 370
    },
    {
      "epoch": 0.04741849945406333,
      "grad_norm": 0.21879573166370392,
      "learning_rate": 6.111758245266794e-05,
      "loss": 2.2499,
      "step": 380
    },
    {
      "epoch": 0.04866635470285447,
      "grad_norm": 0.2598637044429779,
      "learning_rate": 5.626926795411447e-05,
      "loss": 2.2238,
      "step": 390
    },
    {
      "epoch": 0.04991420995164561,
      "grad_norm": 0.5259443521499634,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 2.2736,
      "step": 400
    },
    {
      "epoch": 0.04991420995164561,
      "eval_loss": 2.2839443683624268,
      "eval_runtime": 776.7055,
      "eval_samples_per_second": 17.377,
      "eval_steps_per_second": 4.345,
      "step": 400
    },
    {
      "epoch": 0.05116206520043675,
      "grad_norm": 0.13961468636989594,
      "learning_rate": 4.695790918802576e-05,
      "loss": 2.3594,
      "step": 410
    },
    {
      "epoch": 0.05240992044922789,
      "grad_norm": 0.17360930144786835,
      "learning_rate": 4.252125897855932e-05,
      "loss": 2.2746,
      "step": 420
    },
    {
      "epoch": 0.05365777569801903,
      "grad_norm": 0.22088685631752014,
      "learning_rate": 3.824753850538082e-05,
      "loss": 2.2731,
      "step": 430
    },
    {
      "epoch": 0.05490563094681017,
      "grad_norm": 0.27481532096862793,
      "learning_rate": 3.414886209349615e-05,
      "loss": 2.2392,
      "step": 440
    },
    {
      "epoch": 0.05615348619560131,
      "grad_norm": 0.5030316710472107,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 2.2607,
      "step": 450
    },
    {
      "epoch": 0.05615348619560131,
      "eval_loss": 2.2802443504333496,
      "eval_runtime": 776.8326,
      "eval_samples_per_second": 17.374,
      "eval_steps_per_second": 4.345,
      "step": 450
    },
    {
      "epoch": 0.05740134144439245,
      "grad_norm": 0.13550977408885956,
      "learning_rate": 2.6522584913693294e-05,
      "loss": 2.3409,
      "step": 460
    },
    {
      "epoch": 0.05864919669318359,
      "grad_norm": 0.172842338681221,
      "learning_rate": 2.301660165700936e-05,
      "loss": 2.2541,
      "step": 470
    },
    {
      "epoch": 0.059897051941974734,
      "grad_norm": 0.21645210683345795,
      "learning_rate": 1.9728836206903656e-05,
      "loss": 2.2169,
      "step": 480
    },
    {
      "epoch": 0.061144907190765874,
      "grad_norm": 0.26775994896888733,
      "learning_rate": 1.6668608091748495e-05,
      "loss": 2.2397,
      "step": 490
    },
    {
      "epoch": 0.06239276243955701,
      "grad_norm": 0.6055644750595093,
      "learning_rate": 1.3844591860619383e-05,
      "loss": 2.2556,
      "step": 500
    },
    {
      "epoch": 0.06239276243955701,
      "eval_loss": 2.278071403503418,
      "eval_runtime": 777.8304,
      "eval_samples_per_second": 17.352,
      "eval_steps_per_second": 4.339,
      "step": 500
    },
    {
      "epoch": 0.06364061768834815,
      "grad_norm": 0.13105718791484833,
      "learning_rate": 1.1264792494342857e-05,
      "loss": 2.3481,
      "step": 510
    },
    {
      "epoch": 0.06488847293713929,
      "grad_norm": 0.18398968875408173,
      "learning_rate": 8.936522714508678e-06,
      "loss": 2.3156,
      "step": 520
    },
    {
      "epoch": 0.06613632818593043,
      "grad_norm": 0.2107171267271042,
      "learning_rate": 6.866382254766157e-06,
      "loss": 2.2551,
      "step": 530
    },
    {
      "epoch": 0.06738418343472158,
      "grad_norm": 0.2676718533039093,
      "learning_rate": 5.060239153161872e-06,
      "loss": 2.2416,
      "step": 540
    },
    {
      "epoch": 0.06863203868351271,
      "grad_norm": 0.5341309905052185,
      "learning_rate": 3.5232131185484076e-06,
      "loss": 2.2829,
      "step": 550
    },
    {
      "epoch": 0.06863203868351271,
      "eval_loss": 2.2774720191955566,
      "eval_runtime": 776.3638,
      "eval_samples_per_second": 17.385,
      "eval_steps_per_second": 4.347,
      "step": 550
    },
    {
      "epoch": 0.06987989393230386,
      "grad_norm": 0.12428457289934158,
      "learning_rate": 2.259661018213333e-06,
      "loss": 2.3326,
      "step": 560
    },
    {
      "epoch": 0.07112774918109499,
      "grad_norm": 0.1817050576210022,
      "learning_rate": 1.2731645278655445e-06,
      "loss": 2.2474,
      "step": 570
    },
    {
      "epoch": 0.07237560442988614,
      "grad_norm": 0.2181014120578766,
      "learning_rate": 5.665199789862907e-07,
      "loss": 2.2753,
      "step": 580
    },
    {
      "epoch": 0.07362345967867727,
      "grad_norm": 0.27867138385772705,
      "learning_rate": 1.4173043232380557e-07,
      "loss": 2.2633,
      "step": 590
    },
    {
      "epoch": 0.07487131492746842,
      "grad_norm": 0.5270544290542603,
      "learning_rate": 0.0,
      "loss": 2.2796,
      "step": 600
    },
    {
      "epoch": 0.07487131492746842,
      "eval_loss": 2.2774572372436523,
      "eval_runtime": 776.2331,
      "eval_samples_per_second": 17.388,
      "eval_steps_per_second": 4.348,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 4.112970510332068e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}