{
  "best_metric": 1.2625093460083008,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 2.6079869600651997,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026079869600651995,
      "grad_norm": 0.6620760560035706,
      "learning_rate": 2.5e-05,
      "loss": 1.2501,
      "step": 1
    },
    {
      "epoch": 0.026079869600651995,
      "eval_loss": 1.6212151050567627,
      "eval_runtime": 0.4971,
      "eval_samples_per_second": 100.592,
      "eval_steps_per_second": 26.154,
      "step": 1
    },
    {
      "epoch": 0.05215973920130399,
      "grad_norm": 1.0186434984207153,
      "learning_rate": 5e-05,
      "loss": 1.4369,
      "step": 2
    },
    {
      "epoch": 0.07823960880195599,
      "grad_norm": 0.7852559089660645,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3094,
      "step": 3
    },
    {
      "epoch": 0.10431947840260798,
      "grad_norm": 0.6789484024047852,
      "learning_rate": 0.0001,
      "loss": 1.3378,
      "step": 4
    },
    {
      "epoch": 0.13039934800325997,
      "grad_norm": 0.5586358308792114,
      "learning_rate": 9.997590643643647e-05,
      "loss": 1.4974,
      "step": 5
    },
    {
      "epoch": 0.15647921760391198,
      "grad_norm": 0.3749651610851288,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.3339,
      "step": 6
    },
    {
      "epoch": 0.18255908720456399,
      "grad_norm": 0.42121371626853943,
      "learning_rate": 9.978331270024886e-05,
      "loss": 1.5307,
      "step": 7
    },
    {
      "epoch": 0.20863895680521596,
      "grad_norm": 2.6662514209747314,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.7291,
      "step": 8
    },
    {
      "epoch": 0.23471882640586797,
      "grad_norm": 0.906875491142273,
      "learning_rate": 9.939894994381957e-05,
      "loss": 1.7642,
      "step": 9
    },
    {
      "epoch": 0.26079869600651995,
      "grad_norm": 0.32841840386390686,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.1277,
      "step": 10
    },
    {
      "epoch": 0.28687856560717195,
      "grad_norm": 0.32854458689689636,
      "learning_rate": 9.882446406748002e-05,
      "loss": 1.2506,
      "step": 11
    },
    {
      "epoch": 0.31295843520782396,
      "grad_norm": 0.2924271523952484,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.3405,
      "step": 12
    },
    {
      "epoch": 0.33903830480847597,
      "grad_norm": 0.28709307312965393,
      "learning_rate": 9.80623151079494e-05,
      "loss": 1.276,
      "step": 13
    },
    {
      "epoch": 0.36511817440912797,
      "grad_norm": 0.26937562227249146,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.3337,
      "step": 14
    },
    {
      "epoch": 0.39119804400978,
      "grad_norm": 0.25019437074661255,
      "learning_rate": 9.711576670407965e-05,
      "loss": 1.3807,
      "step": 15
    },
    {
      "epoch": 0.4172779136104319,
      "grad_norm": 0.27004799246788025,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.3273,
      "step": 16
    },
    {
      "epoch": 0.44335778321108393,
      "grad_norm": 0.3201175034046173,
      "learning_rate": 9.598887212145291e-05,
      "loss": 1.5258,
      "step": 17
    },
    {
      "epoch": 0.46943765281173594,
      "grad_norm": 0.4178328216075897,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.6499,
      "step": 18
    },
    {
      "epoch": 0.49551752241238795,
      "grad_norm": 0.9188335537910461,
      "learning_rate": 9.468645689567598e-05,
      "loss": 1.846,
      "step": 19
    },
    {
      "epoch": 0.5215973920130399,
      "grad_norm": 0.2169221043586731,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.1765,
      "step": 20
    },
    {
      "epoch": 0.5476772616136919,
      "grad_norm": 0.2450340837240219,
      "learning_rate": 9.321409816869605e-05,
      "loss": 1.2586,
      "step": 21
    },
    {
      "epoch": 0.5737571312143439,
      "grad_norm": 0.2194407731294632,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.2651,
      "step": 22
    },
    {
      "epoch": 0.5998370008149959,
      "grad_norm": 0.216043621301651,
      "learning_rate": 9.157810080662269e-05,
      "loss": 1.2809,
      "step": 23
    },
    {
      "epoch": 0.6259168704156479,
      "grad_norm": 0.2400970458984375,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.3573,
      "step": 24
    },
    {
      "epoch": 0.6519967400162999,
      "grad_norm": 0.2485317438840866,
      "learning_rate": 8.978547040132317e-05,
      "loss": 1.2768,
      "step": 25
    },
    {
      "epoch": 0.6519967400162999,
      "eval_loss": 1.3168331384658813,
      "eval_runtime": 0.4947,
      "eval_samples_per_second": 101.078,
      "eval_steps_per_second": 26.28,
      "step": 25
    },
    {
      "epoch": 0.6780766096169519,
      "grad_norm": 0.858853280544281,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.4349,
      "step": 26
    },
    {
      "epoch": 0.7041564792176039,
      "grad_norm": 0.3207035958766937,
      "learning_rate": 8.78438832714026e-05,
      "loss": 1.5518,
      "step": 27
    },
    {
      "epoch": 0.7302363488182559,
      "grad_norm": 0.47130295634269714,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.5278,
      "step": 28
    },
    {
      "epoch": 0.756316218418908,
      "grad_norm": 0.18217793107032776,
      "learning_rate": 8.57616535910292e-05,
      "loss": 1.0693,
      "step": 29
    },
    {
      "epoch": 0.78239608801956,
      "grad_norm": 0.21631065011024475,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.3558,
      "step": 30
    },
    {
      "epoch": 0.8084759576202118,
      "grad_norm": 0.19864201545715332,
      "learning_rate": 8.354769778736406e-05,
      "loss": 1.3028,
      "step": 31
    },
    {
      "epoch": 0.8345558272208639,
      "grad_norm": 0.19812346994876862,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.3066,
      "step": 32
    },
    {
      "epoch": 0.8606356968215159,
      "grad_norm": 0.23884153366088867,
      "learning_rate": 8.12114963590511e-05,
      "loss": 1.3189,
      "step": 33
    },
    {
      "epoch": 0.8867155664221679,
      "grad_norm": 0.2092161476612091,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.273,
      "step": 34
    },
    {
      "epoch": 0.9127954360228199,
      "grad_norm": 0.26922526955604553,
      "learning_rate": 7.876305327926657e-05,
      "loss": 1.3761,
      "step": 35
    },
    {
      "epoch": 0.9388753056234719,
      "grad_norm": 0.2948414087295532,
      "learning_rate": 7.75e-05,
      "loss": 1.3617,
      "step": 36
    },
    {
      "epoch": 0.9649551752241239,
      "grad_norm": 0.44491636753082275,
      "learning_rate": 7.62128531571699e-05,
      "loss": 1.5529,
      "step": 37
    },
    {
      "epoch": 0.9910350448247759,
      "grad_norm": 0.7980100512504578,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.6605,
      "step": 38
    },
    {
      "epoch": 1.017114914425428,
      "grad_norm": 0.42900562286376953,
      "learning_rate": 7.357181634119777e-05,
      "loss": 1.9593,
      "step": 39
    },
    {
      "epoch": 1.0431947840260798,
      "grad_norm": 0.17168301343917847,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.1427,
      "step": 40
    },
    {
      "epoch": 1.069274653626732,
      "grad_norm": 0.18627986311912537,
      "learning_rate": 7.085125215645552e-05,
      "loss": 1.3079,
      "step": 41
    },
    {
      "epoch": 1.0953545232273838,
      "grad_norm": 0.19410377740859985,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.2263,
      "step": 42
    },
    {
      "epoch": 1.121434392828036,
      "grad_norm": 0.20103414356708527,
      "learning_rate": 6.80628104764508e-05,
      "loss": 1.29,
      "step": 43
    },
    {
      "epoch": 1.1475142624286878,
      "grad_norm": 0.229043647646904,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.2465,
      "step": 44
    },
    {
      "epoch": 1.17359413202934,
      "grad_norm": 1.0233486890792847,
      "learning_rate": 6.52184318365468e-05,
      "loss": 1.3942,
      "step": 45
    },
    {
      "epoch": 1.1996740016299918,
      "grad_norm": 0.29909205436706543,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.4629,
      "step": 46
    },
    {
      "epoch": 1.225753871230644,
      "grad_norm": 0.389396071434021,
      "learning_rate": 6.23302963027565e-05,
      "loss": 1.5736,
      "step": 47
    },
    {
      "epoch": 1.2518337408312958,
      "grad_norm": 0.2234639823436737,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.7327,
      "step": 48
    },
    {
      "epoch": 1.277913610431948,
      "grad_norm": 0.21025896072387695,
      "learning_rate": 5.941077131483025e-05,
      "loss": 1.5035,
      "step": 49
    },
    {
      "epoch": 1.3039934800325998,
      "grad_norm": 0.17033106088638306,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.1971,
      "step": 50
    },
    {
      "epoch": 1.3039934800325998,
      "eval_loss": 1.276837706565857,
      "eval_runtime": 0.4933,
      "eval_samples_per_second": 101.363,
      "eval_steps_per_second": 26.355,
      "step": 50
    },
    {
      "epoch": 1.3300733496332517,
      "grad_norm": 0.18216781318187714,
      "learning_rate": 5.6472358726979935e-05,
      "loss": 1.2561,
      "step": 51
    },
    {
      "epoch": 1.3561532192339039,
      "grad_norm": 0.19190214574337006,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.2373,
      "step": 52
    },
    {
      "epoch": 1.3822330888345558,
      "grad_norm": 0.20375579595565796,
      "learning_rate": 5.352764127302008e-05,
      "loss": 1.3094,
      "step": 53
    },
    {
      "epoch": 1.4083129584352079,
      "grad_norm": 0.22090604901313782,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.2524,
      "step": 54
    },
    {
      "epoch": 1.4343928280358598,
      "grad_norm": 0.2642119526863098,
      "learning_rate": 5.058922868516978e-05,
      "loss": 1.3616,
      "step": 55
    },
    {
      "epoch": 1.4604726976365119,
      "grad_norm": 0.34405508637428284,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.5443,
      "step": 56
    },
    {
      "epoch": 1.4865525672371638,
      "grad_norm": 0.5865151882171631,
      "learning_rate": 4.7669703697243516e-05,
      "loss": 1.7222,
      "step": 57
    },
    {
      "epoch": 1.5126324368378157,
      "grad_norm": 0.3257847726345062,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.0614,
      "step": 58
    },
    {
      "epoch": 1.5387123064384678,
      "grad_norm": 0.15625827014446259,
      "learning_rate": 4.478156816345321e-05,
      "loss": 1.1532,
      "step": 59
    },
    {
      "epoch": 1.56479217603912,
      "grad_norm": 0.17408806085586548,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.185,
      "step": 60
    },
    {
      "epoch": 1.5908720456397718,
      "grad_norm": 0.18832173943519592,
      "learning_rate": 4.19371895235492e-05,
      "loss": 1.1786,
      "step": 61
    },
    {
      "epoch": 1.6169519152404237,
      "grad_norm": 0.19872711598873138,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.2668,
      "step": 62
    },
    {
      "epoch": 1.6430317848410758,
      "grad_norm": 0.22072260081768036,
      "learning_rate": 3.9148747843544495e-05,
      "loss": 1.2622,
      "step": 63
    },
    {
      "epoch": 1.669111654441728,
      "grad_norm": 0.25179487466812134,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.3652,
      "step": 64
    },
    {
      "epoch": 1.6951915240423798,
      "grad_norm": 0.28402817249298096,
      "learning_rate": 3.642818365880224e-05,
      "loss": 1.4035,
      "step": 65
    },
    {
      "epoch": 1.7212713936430317,
      "grad_norm": 0.4112336337566376,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.5314,
      "step": 66
    },
    {
      "epoch": 1.7473512632436838,
      "grad_norm": 0.24410173296928406,
      "learning_rate": 3.378714684283011e-05,
      "loss": 0.8069,
      "step": 67
    },
    {
      "epoch": 1.7734311328443357,
      "grad_norm": 0.20584547519683838,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.4517,
      "step": 68
    },
    {
      "epoch": 1.7995110024449876,
      "grad_norm": 0.17557083070278168,
      "learning_rate": 3.123694672073344e-05,
      "loss": 1.216,
      "step": 69
    },
    {
      "epoch": 1.8255908720456397,
      "grad_norm": 0.18803009390830994,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.2143,
      "step": 70
    },
    {
      "epoch": 1.8516707416462919,
      "grad_norm": 0.19694343209266663,
      "learning_rate": 2.8788503640948912e-05,
      "loss": 1.2274,
      "step": 71
    },
    {
      "epoch": 1.8777506112469438,
      "grad_norm": 0.20662301778793335,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.2995,
      "step": 72
    },
    {
      "epoch": 1.9038304808475957,
      "grad_norm": 0.22804853320121765,
      "learning_rate": 2.645230221263596e-05,
      "loss": 1.2843,
      "step": 73
    },
    {
      "epoch": 1.9299103504482478,
      "grad_norm": 0.2707391679286957,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.2768,
      "step": 74
    },
    {
      "epoch": 1.9559902200488999,
      "grad_norm": 0.37075576186180115,
      "learning_rate": 2.423834640897079e-05,
      "loss": 1.5192,
      "step": 75
    },
    {
      "epoch": 1.9559902200488999,
      "eval_loss": 1.2681915760040283,
      "eval_runtime": 0.4943,
      "eval_samples_per_second": 101.15,
      "eval_steps_per_second": 26.299,
      "step": 75
    },
    {
      "epoch": 1.9820700896495518,
      "grad_norm": 0.6423049569129944,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.6123,
      "step": 76
    },
    {
      "epoch": 2.0081499592502037,
      "grad_norm": 0.43415480852127075,
      "learning_rate": 2.215611672859741e-05,
      "loss": 1.9664,
      "step": 77
    },
    {
      "epoch": 2.034229828850856,
      "grad_norm": 0.150677889585495,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.0656,
      "step": 78
    },
    {
      "epoch": 2.060309698451508,
      "grad_norm": 0.17479360103607178,
      "learning_rate": 2.0214529598676836e-05,
      "loss": 1.1818,
      "step": 79
    },
    {
      "epoch": 2.0863895680521596,
      "grad_norm": 0.18362055718898773,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.1829,
      "step": 80
    },
    {
      "epoch": 2.1124694376528117,
      "grad_norm": 0.20285598933696747,
      "learning_rate": 1.842189919337732e-05,
      "loss": 1.2863,
      "step": 81
    },
    {
      "epoch": 2.138549307253464,
      "grad_norm": 0.21474912762641907,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.3106,
      "step": 82
    },
    {
      "epoch": 2.164629176854116,
      "grad_norm": 0.24042028188705444,
      "learning_rate": 1.6785901831303956e-05,
      "loss": 1.2384,
      "step": 83
    },
    {
      "epoch": 2.1907090464547676,
      "grad_norm": 0.2615673243999481,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.328,
      "step": 84
    },
    {
      "epoch": 2.2167889160554197,
      "grad_norm": 0.377523273229599,
      "learning_rate": 1.531354310432403e-05,
      "loss": 1.5058,
      "step": 85
    },
    {
      "epoch": 2.242868785656072,
      "grad_norm": 0.32665538787841797,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.9337,
      "step": 86
    },
    {
      "epoch": 2.2689486552567235,
      "grad_norm": 0.20789040625095367,
      "learning_rate": 1.4011127878547087e-05,
      "loss": 1.4827,
      "step": 87
    },
    {
      "epoch": 2.2950285248573756,
      "grad_norm": 0.17642174661159515,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.2114,
      "step": 88
    },
    {
      "epoch": 2.3211083944580277,
      "grad_norm": 0.17508623003959656,
      "learning_rate": 1.2884233295920353e-05,
      "loss": 1.2065,
      "step": 89
    },
    {
      "epoch": 2.34718826405868,
      "grad_norm": 0.18353621661663055,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.2285,
      "step": 90
    },
    {
      "epoch": 2.3732681336593315,
      "grad_norm": 0.20404478907585144,
      "learning_rate": 1.1937684892050604e-05,
      "loss": 1.2864,
      "step": 91
    },
    {
      "epoch": 2.3993480032599837,
      "grad_norm": 0.22320792078971863,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.2372,
      "step": 92
    },
    {
      "epoch": 2.4254278728606358,
      "grad_norm": 0.25220105051994324,
      "learning_rate": 1.1175535932519987e-05,
      "loss": 1.3136,
      "step": 93
    },
    {
      "epoch": 2.451507742461288,
      "grad_norm": 0.3090400695800781,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.364,
      "step": 94
    },
    {
      "epoch": 2.4775876120619396,
      "grad_norm": 0.4767124056816101,
      "learning_rate": 1.0601050056180447e-05,
      "loss": 1.6821,
      "step": 95
    },
    {
      "epoch": 2.5036674816625917,
      "grad_norm": 0.4842507839202881,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.1292,
      "step": 96
    },
    {
      "epoch": 2.529747351263244,
      "grad_norm": 0.14696048200130463,
      "learning_rate": 1.0216687299751144e-05,
      "loss": 1.1158,
      "step": 97
    },
    {
      "epoch": 2.555827220863896,
      "grad_norm": 0.37997448444366455,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.2302,
      "step": 98
    },
    {
      "epoch": 2.5819070904645476,
      "grad_norm": 0.1806773990392685,
      "learning_rate": 1.0024093563563546e-05,
      "loss": 1.1778,
      "step": 99
    },
    {
      "epoch": 2.6079869600651997,
      "grad_norm": 0.20082679390907288,
      "learning_rate": 1e-05,
      "loss": 1.253,
      "step": 100
    },
    {
      "epoch": 2.6079869600651997,
      "eval_loss": 1.2625093460083008,
      "eval_runtime": 0.4948,
      "eval_samples_per_second": 101.042,
      "eval_steps_per_second": 26.271,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.08890810679296e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}