{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 50000,
  "global_step": 928,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04310344827586207,
      "grad_norm": 5.7193193435668945,
      "learning_rate": 1.7857142857142859e-06,
      "loss": 0.7126,
      "step": 10
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 2.6962673664093018,
      "learning_rate": 3.5714285714285718e-06,
      "loss": 0.6662,
      "step": 20
    },
    {
      "epoch": 0.12931034482758622,
      "grad_norm": 1.6143770217895508,
      "learning_rate": 4.999939076763487e-06,
      "loss": 0.5303,
      "step": 30
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 1.3705445528030396,
      "learning_rate": 4.997807075247147e-06,
      "loss": 0.453,
      "step": 40
    },
    {
      "epoch": 0.21551724137931033,
      "grad_norm": 1.129184603691101,
      "learning_rate": 4.992631880567301e-06,
      "loss": 0.4192,
      "step": 50
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 1.3925697803497314,
      "learning_rate": 4.984419797901491e-06,
      "loss": 0.418,
      "step": 60
    },
    {
      "epoch": 0.3017241379310345,
      "grad_norm": 1.4394880533218384,
      "learning_rate": 4.973180832407471e-06,
      "loss": 0.4118,
      "step": 70
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 1.3788193464279175,
      "learning_rate": 4.958928677033465e-06,
      "loss": 0.4065,
      "step": 80
    },
    {
      "epoch": 0.3879310344827586,
      "grad_norm": 1.1382204294204712,
      "learning_rate": 4.9416806958354206e-06,
      "loss": 0.3819,
      "step": 90
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 1.081235647201538,
      "learning_rate": 4.921457902821578e-06,
      "loss": 0.399,
      "step": 100
    },
    {
      "epoch": 0.47413793103448276,
      "grad_norm": 1.21293044090271,
      "learning_rate": 4.898284936350144e-06,
      "loss": 0.3962,
      "step": 110
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 1.3453164100646973,
      "learning_rate": 4.8721900291112415e-06,
      "loss": 0.3818,
      "step": 120
    },
    {
      "epoch": 0.5603448275862069,
      "grad_norm": 1.2487531900405884,
      "learning_rate": 4.84320497372973e-06,
      "loss": 0.3901,
      "step": 130
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 1.1610265970230103,
      "learning_rate": 4.811365084030784e-06,
      "loss": 0.3867,
      "step": 140
    },
    {
      "epoch": 0.646551724137931,
      "grad_norm": 1.0656601190567017,
      "learning_rate": 4.776709152015443e-06,
      "loss": 0.3882,
      "step": 150
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 1.2680625915527344,
      "learning_rate": 4.7392794005985324e-06,
      "loss": 0.3739,
      "step": 160
    },
    {
      "epoch": 0.7327586206896551,
      "grad_norm": 1.3623387813568115,
      "learning_rate": 4.699121432166542e-06,
      "loss": 0.3733,
      "step": 170
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 1.096368432044983,
      "learning_rate": 4.656284173018144e-06,
      "loss": 0.3625,
      "step": 180
    },
    {
      "epoch": 0.8189655172413793,
      "grad_norm": 0.9958175420761108,
      "learning_rate": 4.610819813755038e-06,
      "loss": 0.3698,
      "step": 190
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 1.023909091949463,
      "learning_rate": 4.562783745695738e-06,
      "loss": 0.3471,
      "step": 200
    },
    {
      "epoch": 0.9051724137931034,
      "grad_norm": 1.061679482460022,
      "learning_rate": 4.512234493389785e-06,
      "loss": 0.3712,
      "step": 210
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 1.3929497003555298,
      "learning_rate": 4.4592336433146e-06,
      "loss": 0.3651,
      "step": 220
    },
    {
      "epoch": 0.9913793103448276,
      "grad_norm": 0.8806857466697693,
      "learning_rate": 4.403845768841842e-06,
      "loss": 0.3641,
      "step": 230
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 0.9649218916893005,
      "learning_rate": 4.346138351564711e-06,
      "loss": 0.3057,
      "step": 240
    },
    {
      "epoch": 1.0775862068965518,
      "grad_norm": 1.1328972578048706,
      "learning_rate": 4.286181699082008e-06,
      "loss": 0.3045,
      "step": 250
    },
    {
      "epoch": 1.1206896551724137,
      "grad_norm": 1.1146079301834106,
      "learning_rate": 4.224048859339175e-06,
      "loss": 0.301,
      "step": 260
    },
    {
      "epoch": 1.1637931034482758,
      "grad_norm": 1.1736148595809937,
      "learning_rate": 4.159815531630604e-06,
      "loss": 0.3236,
      "step": 270
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 1.1570653915405273,
      "learning_rate": 4.093559974371725e-06,
      "loss": 0.3078,
      "step": 280
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.335072636604309,
      "learning_rate": 4.02536290975317e-06,
      "loss": 0.3145,
      "step": 290
    },
    {
      "epoch": 1.293103448275862,
      "grad_norm": 1.0565122365951538,
      "learning_rate": 3.955307425393224e-06,
      "loss": 0.3018,
      "step": 300
    },
    {
      "epoch": 1.3362068965517242,
      "grad_norm": 1.3002219200134277,
      "learning_rate": 3.88347887310836e-06,
      "loss": 0.3215,
      "step": 310
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 1.0199170112609863,
      "learning_rate": 3.8099647649251984e-06,
      "loss": 0.2973,
      "step": 320
    },
    {
      "epoch": 1.4224137931034484,
      "grad_norm": 1.118922233581543,
      "learning_rate": 3.7348546664605777e-06,
      "loss": 0.3095,
      "step": 330
    },
    {
      "epoch": 1.4655172413793103,
      "grad_norm": 1.080239176750183,
      "learning_rate": 3.658240087799655e-06,
      "loss": 0.3172,
      "step": 340
    },
    {
      "epoch": 1.5086206896551724,
      "grad_norm": 0.9963559508323669,
      "learning_rate": 3.5802143720049565e-06,
      "loss": 0.2923,
      "step": 350
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 1.1155935525894165,
      "learning_rate": 3.5008725813922383e-06,
      "loss": 0.3032,
      "step": 360
    },
    {
      "epoch": 1.5948275862068966,
      "grad_norm": 1.4892568588256836,
      "learning_rate": 3.4203113817116955e-06,
      "loss": 0.3113,
      "step": 370
    },
    {
      "epoch": 1.6379310344827587,
      "grad_norm": 1.1873013973236084,
      "learning_rate": 3.338628924375638e-06,
      "loss": 0.3122,
      "step": 380
    },
    {
      "epoch": 1.6810344827586206,
      "grad_norm": 1.215104103088379,
      "learning_rate": 3.2559247268761117e-06,
      "loss": 0.2986,
      "step": 390
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 1.2356464862823486,
      "learning_rate": 3.1722995515381644e-06,
      "loss": 0.2969,
      "step": 400
    },
    {
      "epoch": 1.7672413793103448,
      "grad_norm": 1.217281699180603,
      "learning_rate": 3.087855282756475e-06,
      "loss": 0.294,
      "step": 410
    },
    {
      "epoch": 1.8103448275862069,
      "grad_norm": 1.3647332191467285,
      "learning_rate": 3.002694802864912e-06,
      "loss": 0.2987,
      "step": 420
    },
    {
      "epoch": 1.853448275862069,
      "grad_norm": 1.295482873916626,
      "learning_rate": 2.9169218667902562e-06,
      "loss": 0.3087,
      "step": 430
    },
    {
      "epoch": 1.896551724137931,
      "grad_norm": 1.1709827184677124,
      "learning_rate": 2.8306409756428067e-06,
      "loss": 0.2945,
      "step": 440
    },
    {
      "epoch": 1.9396551724137931,
      "grad_norm": 1.2571437358856201,
      "learning_rate": 2.743957249397874e-06,
      "loss": 0.3036,
      "step": 450
    },
    {
      "epoch": 1.9827586206896552,
      "grad_norm": 1.7302639484405518,
      "learning_rate": 2.6569762988232838e-06,
      "loss": 0.3119,
      "step": 460
    },
    {
      "epoch": 2.0258620689655173,
      "grad_norm": 0.9986317157745361,
      "learning_rate": 2.569804096808923e-06,
      "loss": 0.2789,
      "step": 470
    },
    {
      "epoch": 2.0689655172413794,
      "grad_norm": 1.130508303642273,
      "learning_rate": 2.482546849255096e-06,
      "loss": 0.2435,
      "step": 480
    },
    {
      "epoch": 2.1120689655172415,
      "grad_norm": 1.446877121925354,
      "learning_rate": 2.3953108656770018e-06,
      "loss": 0.2475,
      "step": 490
    },
    {
      "epoch": 2.1551724137931036,
      "grad_norm": 1.60965096950531,
      "learning_rate": 2.3082024296829538e-06,
      "loss": 0.2384,
      "step": 500
    },
    {
      "epoch": 2.1982758620689653,
      "grad_norm": 1.383519172668457,
      "learning_rate": 2.2213276694841866e-06,
      "loss": 0.2356,
      "step": 510
    },
    {
      "epoch": 2.2413793103448274,
      "grad_norm": 1.3211714029312134,
      "learning_rate": 2.134792428593971e-06,
      "loss": 0.2466,
      "step": 520
    },
    {
      "epoch": 2.2844827586206895,
      "grad_norm": 1.302563190460205,
      "learning_rate": 2.0487021368736002e-06,
      "loss": 0.2456,
      "step": 530
    },
    {
      "epoch": 2.3275862068965516,
      "grad_norm": 1.30355703830719,
      "learning_rate": 1.963161682082342e-06,
      "loss": 0.2406,
      "step": 540
    },
    {
      "epoch": 2.3706896551724137,
      "grad_norm": 1.1259819269180298,
      "learning_rate": 1.8782752820878636e-06,
      "loss": 0.2225,
      "step": 550
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 1.2397651672363281,
      "learning_rate": 1.7941463578928088e-06,
      "loss": 0.2312,
      "step": 560
    },
    {
      "epoch": 2.456896551724138,
      "grad_norm": 1.3761606216430664,
      "learning_rate": 1.7108774076322443e-06,
      "loss": 0.2415,
      "step": 570
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.3666378259658813,
      "learning_rate": 1.6285698816954626e-06,
      "loss": 0.2487,
      "step": 580
    },
    {
      "epoch": 2.543103448275862,
      "grad_norm": 1.183164119720459,
      "learning_rate": 1.547324059124315e-06,
      "loss": 0.2378,
      "step": 590
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 1.4499019384384155,
      "learning_rate": 1.467238925438646e-06,
      "loss": 0.2765,
      "step": 600
    },
    {
      "epoch": 2.6293103448275863,
      "grad_norm": 1.447636604309082,
      "learning_rate": 1.388412052037682e-06,
      "loss": 0.2584,
      "step": 610
    },
    {
      "epoch": 2.6724137931034484,
      "grad_norm": 1.449857473373413,
      "learning_rate": 1.3109394773243117e-06,
      "loss": 0.2323,
      "step": 620
    },
    {
      "epoch": 2.7155172413793105,
      "grad_norm": 1.3404827117919922,
      "learning_rate": 1.234915589697091e-06,
      "loss": 0.2384,
      "step": 630
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 1.3379237651824951,
      "learning_rate": 1.160433012552508e-06,
      "loss": 0.2382,
      "step": 640
    },
    {
      "epoch": 2.8017241379310347,
      "grad_norm": 1.4709217548370361,
      "learning_rate": 1.0875824914376555e-06,
      "loss": 0.2303,
      "step": 650
    },
    {
      "epoch": 2.844827586206897,
      "grad_norm": 1.3744317293167114,
      "learning_rate": 1.0164527834907468e-06,
      "loss": 0.2423,
      "step": 660
    },
    {
      "epoch": 2.887931034482759,
      "grad_norm": 1.7406655550003052,
      "learning_rate": 9.471305493042243e-07,
      "loss": 0.2426,
      "step": 670
    },
    {
      "epoch": 2.9310344827586206,
      "grad_norm": 1.6748679876327515,
      "learning_rate": 8.797002473421729e-07,
      "loss": 0.2494,
      "step": 680
    },
    {
      "epoch": 2.9741379310344827,
      "grad_norm": 1.5766329765319824,
      "learning_rate": 8.142440310406923e-07,
      "loss": 0.2407,
      "step": 690
    },
    {
      "epoch": 3.0172413793103448,
      "grad_norm": 1.2436530590057373,
      "learning_rate": 7.508416487165862e-07,
      "loss": 0.2254,
      "step": 700
    },
    {
      "epoch": 3.060344827586207,
      "grad_norm": 1.3559637069702148,
      "learning_rate": 6.895703464063319e-07,
      "loss": 0.2015,
      "step": 710
    },
    {
      "epoch": 3.103448275862069,
      "grad_norm": 1.3423281908035278,
      "learning_rate": 6.305047737536707e-07,
      "loss": 0.1952,
      "step": 720
    },
    {
      "epoch": 3.146551724137931,
      "grad_norm": 1.4924376010894775,
      "learning_rate": 5.737168930605272e-07,
      "loss": 0.1967,
      "step": 730
    },
    {
      "epoch": 3.189655172413793,
      "grad_norm": 1.4202907085418701,
      "learning_rate": 5.192758916120236e-07,
      "loss": 0.2128,
      "step": 740
    },
    {
      "epoch": 3.2327586206896552,
      "grad_norm": 1.252336025238037,
      "learning_rate": 4.672480973824312e-07,
      "loss": 0.1907,
      "step": 750
    },
    {
      "epoch": 3.2758620689655173,
      "grad_norm": 1.7021604776382446,
      "learning_rate": 4.1769689822475147e-07,
      "loss": 0.2046,
      "step": 760
    },
    {
      "epoch": 3.3189655172413794,
      "grad_norm": 1.637277364730835,
      "learning_rate": 3.7068266464238085e-07,
      "loss": 0.1973,
      "step": 770
    },
    {
      "epoch": 3.3620689655172415,
      "grad_norm": 1.2321523427963257,
      "learning_rate": 3.262626762369525e-07,
      "loss": 0.2107,
      "step": 780
    },
    {
      "epoch": 3.405172413793103,
      "grad_norm": 1.3565343618392944,
      "learning_rate": 2.844910519219632e-07,
      "loss": 0.2055,
      "step": 790
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 1.6926054954528809,
      "learning_rate": 2.454186839872158e-07,
      "loss": 0.2083,
      "step": 800
    },
    {
      "epoch": 3.4913793103448274,
      "grad_norm": 1.5500190258026123,
      "learning_rate": 2.0909317609440093e-07,
      "loss": 0.1973,
      "step": 810
    },
    {
      "epoch": 3.5344827586206895,
      "grad_norm": 1.4574564695358276,
      "learning_rate": 1.7555878527937164e-07,
      "loss": 0.2336,
      "step": 820
    },
    {
      "epoch": 3.5775862068965516,
      "grad_norm": 1.371783971786499,
      "learning_rate": 1.4485636803175828e-07,
      "loss": 0.2028,
      "step": 830
    },
    {
      "epoch": 3.6206896551724137,
      "grad_norm": 1.5117493867874146,
      "learning_rate": 1.1702333051763271e-07,
      "loss": 0.1897,
      "step": 840
    },
    {
      "epoch": 3.663793103448276,
      "grad_norm": 1.4221725463867188,
      "learning_rate": 9.209358300585474e-08,
      "loss": 0.2053,
      "step": 850
    },
    {
      "epoch": 3.706896551724138,
      "grad_norm": 1.3613110780715942,
      "learning_rate": 7.009749855363457e-08,
      "loss": 0.2019,
      "step": 860
    },
    {
      "epoch": 3.75,
      "grad_norm": 1.6522403955459595,
      "learning_rate": 5.106187600163987e-08,
      "loss": 0.2012,
      "step": 870
    },
    {
      "epoch": 3.793103448275862,
      "grad_norm": 1.1785835027694702,
      "learning_rate": 3.5009907323737826e-08,
      "loss": 0.2041,
      "step": 880
    },
    {
      "epoch": 3.836206896551724,
      "grad_norm": 1.3110618591308594,
      "learning_rate": 2.1961149371145795e-08,
      "loss": 0.2157,
      "step": 890
    },
    {
      "epoch": 3.8793103448275863,
      "grad_norm": 1.1076109409332275,
      "learning_rate": 1.193150004542204e-08,
      "loss": 0.2124,
      "step": 900
    },
    {
      "epoch": 3.9224137931034484,
      "grad_norm": 1.5730844736099243,
      "learning_rate": 4.933178929321103e-09,
      "loss": 0.2164,
      "step": 910
    },
    {
      "epoch": 3.9655172413793105,
      "grad_norm": 1.6986498832702637,
      "learning_rate": 9.747123991141193e-10,
      "loss": 0.209,
      "step": 920
    },
    {
      "epoch": 4.0,
      "step": 928,
      "total_flos": 1.573815416315904e+17,
      "train_loss": 0.29322911118125095,
      "train_runtime": 2500.7039,
      "train_samples_per_second": 5.936,
      "train_steps_per_second": 0.371
    }
  ],
  "logging_steps": 10,
  "max_steps": 928,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.573815416315904e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}