{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 491,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002036659877800407,
      "grad_norm": 42.73765709178892,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 4.2137,
      "step": 1
    },
    {
      "epoch": 0.010183299389002037,
      "grad_norm": 43.823126465212304,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 4.2378,
      "step": 5
    },
    {
      "epoch": 0.020366598778004074,
      "grad_norm": 42.78292182490666,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.1532,
      "step": 10
    },
    {
      "epoch": 0.03054989816700611,
      "grad_norm": 26.956865206535298,
      "learning_rate": 6e-06,
      "loss": 3.7244,
      "step": 15
    },
    {
      "epoch": 0.04073319755600815,
      "grad_norm": 12.021358068486181,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.0576,
      "step": 20
    },
    {
      "epoch": 0.05091649694501019,
      "grad_norm": 10.364947442111331,
      "learning_rate": 1e-05,
      "loss": 2.5815,
      "step": 25
    },
    {
      "epoch": 0.06109979633401222,
      "grad_norm": 4.530399924565578,
      "learning_rate": 1.2e-05,
      "loss": 2.2026,
      "step": 30
    },
    {
      "epoch": 0.07128309572301425,
      "grad_norm": 3.2260177605870783,
      "learning_rate": 1.4e-05,
      "loss": 1.9904,
      "step": 35
    },
    {
      "epoch": 0.0814663951120163,
      "grad_norm": 2.12005760250828,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.8236,
      "step": 40
    },
    {
      "epoch": 0.09164969450101833,
      "grad_norm": 1.8468068964995024,
      "learning_rate": 1.8e-05,
      "loss": 1.6897,
      "step": 45
    },
    {
      "epoch": 0.10183299389002037,
      "grad_norm": 1.5429747637898503,
      "learning_rate": 2e-05,
      "loss": 1.6026,
      "step": 50
    },
    {
      "epoch": 0.1120162932790224,
      "grad_norm": 1.1896025193659396,
      "learning_rate": 1.9993657117550972e-05,
      "loss": 1.5431,
      "step": 55
    },
    {
      "epoch": 0.12219959266802444,
      "grad_norm": 1.0406079144844387,
      "learning_rate": 1.9974636516635436e-05,
      "loss": 1.4948,
      "step": 60
    },
    {
      "epoch": 0.13238289205702647,
      "grad_norm": 0.9826731697259301,
      "learning_rate": 1.994296232634054e-05,
      "loss": 1.4551,
      "step": 65
    },
    {
      "epoch": 0.1425661914460285,
      "grad_norm": 0.8350404902447894,
      "learning_rate": 1.9898674727799418e-05,
      "loss": 1.4548,
      "step": 70
    },
    {
      "epoch": 0.15274949083503056,
      "grad_norm": 0.8022790771564833,
      "learning_rate": 1.9841829903218377e-05,
      "loss": 1.45,
      "step": 75
    },
    {
      "epoch": 0.1629327902240326,
      "grad_norm": 0.8137274794499317,
      "learning_rate": 1.977249996460544e-05,
      "loss": 1.4206,
      "step": 80
    },
    {
      "epoch": 0.17311608961303462,
      "grad_norm": 0.6702892273400702,
      "learning_rate": 1.969077286229078e-05,
      "loss": 1.4068,
      "step": 85
    },
    {
      "epoch": 0.18329938900203666,
      "grad_norm": 0.6712397854919697,
      "learning_rate": 1.959675227335497e-05,
      "loss": 1.4027,
      "step": 90
    },
    {
      "epoch": 0.1934826883910387,
      "grad_norm": 0.6017420494268232,
      "learning_rate": 1.949055747010669e-05,
      "loss": 1.4036,
      "step": 95
    },
    {
      "epoch": 0.20366598778004075,
      "grad_norm": 0.5946907262324206,
      "learning_rate": 1.937232316877668e-05,
      "loss": 1.4021,
      "step": 100
    },
    {
      "epoch": 0.21384928716904278,
      "grad_norm": 0.584049807273413,
      "learning_rate": 1.9242199358619897e-05,
      "loss": 1.3773,
      "step": 105
    },
    {
      "epoch": 0.2240325865580448,
      "grad_norm": 0.5468171068137498,
      "learning_rate": 1.9100351111642666e-05,
      "loss": 1.3824,
      "step": 110
    },
    {
      "epoch": 0.23421588594704684,
      "grad_norm": 0.5631810496676463,
      "learning_rate": 1.894695837319623e-05,
      "loss": 1.3716,
      "step": 115
    },
    {
      "epoch": 0.24439918533604887,
      "grad_norm": 0.5579171191759417,
      "learning_rate": 1.8782215733702286e-05,
      "loss": 1.3722,
      "step": 120
    },
    {
      "epoch": 0.2545824847250509,
      "grad_norm": 0.5126218869264142,
      "learning_rate": 1.8606332181800165e-05,
      "loss": 1.3523,
      "step": 125
    },
    {
      "epoch": 0.26476578411405294,
      "grad_norm": 0.5007973223598261,
      "learning_rate": 1.841953083922875e-05,
      "loss": 1.3451,
      "step": 130
    },
    {
      "epoch": 0.27494908350305497,
      "grad_norm": 0.5048172409656928,
      "learning_rate": 1.8222048677779495e-05,
      "loss": 1.3534,
      "step": 135
    },
    {
      "epoch": 0.285132382892057,
      "grad_norm": 0.4725169108639936,
      "learning_rate": 1.8014136218679566e-05,
      "loss": 1.3473,
      "step": 140
    },
    {
      "epoch": 0.2953156822810591,
      "grad_norm": 0.48611682020845765,
      "learning_rate": 1.779605721478652e-05,
      "loss": 1.3373,
      "step": 145
    },
    {
      "epoch": 0.3054989816700611,
      "grad_norm": 0.45300491076813515,
      "learning_rate": 1.756808831599762e-05,
      "loss": 1.3513,
      "step": 150
    },
    {
      "epoch": 0.31568228105906315,
      "grad_norm": 0.4382778646436873,
      "learning_rate": 1.7330518718298263e-05,
      "loss": 1.3342,
      "step": 155
    },
    {
      "epoch": 0.3258655804480652,
      "grad_norm": 0.4427941208449195,
      "learning_rate": 1.7083649796894798e-05,
      "loss": 1.3162,
      "step": 160
    },
    {
      "epoch": 0.3360488798370672,
      "grad_norm": 0.416296697128989,
      "learning_rate": 1.6827794723896968e-05,
      "loss": 1.3468,
      "step": 165
    },
    {
      "epoch": 0.34623217922606925,
      "grad_norm": 0.43327582549066207,
      "learning_rate": 1.6563278071035182e-05,
      "loss": 1.3413,
      "step": 170
    },
    {
      "epoch": 0.3564154786150713,
      "grad_norm": 0.39987863733708096,
      "learning_rate": 1.6290435397916426e-05,
      "loss": 1.3275,
      "step": 175
    },
    {
      "epoch": 0.3665987780040733,
      "grad_norm": 0.4107034128984309,
      "learning_rate": 1.6009612826341226e-05,
      "loss": 1.3165,
      "step": 180
    },
    {
      "epoch": 0.37678207739307534,
      "grad_norm": 0.39958981244827124,
      "learning_rate": 1.5721166601221697e-05,
      "loss": 1.3238,
      "step": 185
    },
    {
      "epoch": 0.3869653767820774,
      "grad_norm": 0.40620805351711664,
      "learning_rate": 1.5425462638657597e-05,
      "loss": 1.3265,
      "step": 190
    },
    {
      "epoch": 0.3971486761710794,
      "grad_norm": 0.3930588952515658,
      "learning_rate": 1.5122876061743772e-05,
      "loss": 1.3346,
      "step": 195
    },
    {
      "epoch": 0.4073319755600815,
      "grad_norm": 0.3455411843725847,
      "learning_rate": 1.4813790724697832e-05,
      "loss": 1.2996,
      "step": 200
    },
    {
      "epoch": 0.4073319755600815,
      "eval_loss": 1.3280781507492065,
      "eval_runtime": 58.3849,
      "eval_samples_per_second": 238.195,
      "eval_steps_per_second": 3.734,
      "step": 200
    },
    {
      "epoch": 0.4175152749490835,
      "grad_norm": 0.38779728978307215,
      "learning_rate": 1.4498598725911693e-05,
      "loss": 1.3155,
      "step": 205
    },
    {
      "epoch": 0.42769857433808556,
      "grad_norm": 0.34758190751014123,
      "learning_rate": 1.4177699910544793e-05,
      "loss": 1.3226,
      "step": 210
    },
    {
      "epoch": 0.4378818737270876,
      "grad_norm": 0.347052132116147,
      "learning_rate": 1.3851501363289907e-05,
      "loss": 1.3042,
      "step": 215
    },
    {
      "epoch": 0.4480651731160896,
      "grad_norm": 0.35329848914934636,
      "learning_rate": 1.3520416891955101e-05,
      "loss": 1.3198,
      "step": 220
    },
    {
      "epoch": 0.45824847250509165,
      "grad_norm": 0.3689489097870586,
      "learning_rate": 1.3184866502516846e-05,
      "loss": 1.3295,
      "step": 225
    },
    {
      "epoch": 0.4684317718940937,
      "grad_norm": 0.3591427089290735,
      "learning_rate": 1.2845275866310325e-05,
      "loss": 1.3026,
      "step": 230
    },
    {
      "epoch": 0.4786150712830957,
      "grad_norm": 0.33192490822778736,
      "learning_rate": 1.2502075780032792e-05,
      "loss": 1.3211,
      "step": 235
    },
    {
      "epoch": 0.48879837067209775,
      "grad_norm": 0.3314637232326215,
      "learning_rate": 1.2155701619244997e-05,
      "loss": 1.3146,
      "step": 240
    },
    {
      "epoch": 0.4989816700610998,
      "grad_norm": 0.33428121648270825,
      "learning_rate": 1.1806592786063991e-05,
      "loss": 1.2953,
      "step": 245
    },
    {
      "epoch": 0.5091649694501018,
      "grad_norm": 0.33140728066789105,
      "learning_rate": 1.1455192151747931e-05,
      "loss": 1.3083,
      "step": 250
    },
    {
      "epoch": 0.5193482688391039,
      "grad_norm": 0.34894619572153845,
      "learning_rate": 1.1101945494880013e-05,
      "loss": 1.3001,
      "step": 255
    },
    {
      "epoch": 0.5295315682281059,
      "grad_norm": 0.2936066479920224,
      "learning_rate": 1.0747300935864245e-05,
      "loss": 1.299,
      "step": 260
    },
    {
      "epoch": 0.539714867617108,
      "grad_norm": 0.34761064821495535,
      "learning_rate": 1.0391708368450429e-05,
      "loss": 1.2987,
      "step": 265
    },
    {
      "epoch": 0.5498981670061099,
      "grad_norm": 0.32443077572814916,
      "learning_rate": 1.0035618889009535e-05,
      "loss": 1.3154,
      "step": 270
    },
    {
      "epoch": 0.560081466395112,
      "grad_norm": 0.3573334196924316,
      "learning_rate": 9.67948422428345e-06,
      "loss": 1.3045,
      "step": 275
    },
    {
      "epoch": 0.570264765784114,
      "grad_norm": 0.2929859629265363,
      "learning_rate": 9.323756158335054e-06,
      "loss": 1.2995,
      "step": 280
    },
    {
      "epoch": 0.5804480651731161,
      "grad_norm": 0.3725484551984738,
      "learning_rate": 8.968885959425567e-06,
      "loss": 1.3006,
      "step": 285
    },
    {
      "epoch": 0.5906313645621182,
      "grad_norm": 0.2977272122499357,
      "learning_rate": 8.615323807546258e-06,
      "loss": 1.2785,
      "step": 290
    },
    {
      "epoch": 0.6008146639511202,
      "grad_norm": 0.2934843742212814,
      "learning_rate": 8.263518223330698e-06,
      "loss": 1.301,
      "step": 295
    },
    {
      "epoch": 0.6109979633401222,
      "grad_norm": 0.2851617487482263,
      "learning_rate": 7.913915499071994e-06,
      "loss": 1.2957,
      "step": 300
    },
    {
      "epoch": 0.6211812627291242,
      "grad_norm": 0.3280712460992494,
      "learning_rate": 7.566959132566914e-06,
      "loss": 1.3021,
      "step": 305
    },
    {
      "epoch": 0.6313645621181263,
      "grad_norm": 0.28660010388812523,
      "learning_rate": 7.223089264505001e-06,
      "loss": 1.2809,
      "step": 310
    },
    {
      "epoch": 0.6415478615071283,
      "grad_norm": 0.29055149959882093,
      "learning_rate": 6.882742120116419e-06,
      "loss": 1.2958,
      "step": 315
    },
    {
      "epoch": 0.6517311608961304,
      "grad_norm": 0.2868148780704892,
      "learning_rate": 6.546349455786926e-06,
      "loss": 1.2931,
      "step": 320
    },
    {
      "epoch": 0.6619144602851323,
      "grad_norm": 0.3021008995725944,
      "learning_rate": 6.214338011341825e-06,
      "loss": 1.2855,
      "step": 325
    },
    {
      "epoch": 0.6720977596741344,
      "grad_norm": 0.2840488188778215,
      "learning_rate": 5.887128968693887e-06,
      "loss": 1.3091,
      "step": 330
    },
    {
      "epoch": 0.6822810590631364,
      "grad_norm": 0.2978772611216691,
      "learning_rate": 5.565137417541866e-06,
      "loss": 1.2826,
      "step": 335
    },
    {
      "epoch": 0.6924643584521385,
      "grad_norm": 0.28796550430490037,
      "learning_rate": 5.248771828797474e-06,
      "loss": 1.3008,
      "step": 340
    },
    {
      "epoch": 0.7026476578411406,
      "grad_norm": 0.2791511099905026,
      "learning_rate": 4.938433536408771e-06,
      "loss": 1.2848,
      "step": 345
    },
    {
      "epoch": 0.7128309572301426,
      "grad_norm": 0.282696156100298,
      "learning_rate": 4.634516228237372e-06,
      "loss": 1.291,
      "step": 350
    },
    {
      "epoch": 0.7230142566191446,
      "grad_norm": 0.27007483942462107,
      "learning_rate": 4.337405446635264e-06,
      "loss": 1.2821,
      "step": 355
    },
    {
      "epoch": 0.7331975560081466,
      "grad_norm": 0.2885536779707833,
      "learning_rate": 4.047478099354857e-06,
      "loss": 1.3193,
      "step": 360
    },
    {
      "epoch": 0.7433808553971487,
      "grad_norm": 0.3194820894463116,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 1.2993,
      "step": 365
    },
    {
      "epoch": 0.7535641547861507,
      "grad_norm": 0.28463406586484574,
      "learning_rate": 3.4906353085131917e-06,
      "loss": 1.297,
      "step": 370
    },
    {
      "epoch": 0.7637474541751528,
      "grad_norm": 0.2887353591273086,
      "learning_rate": 3.224426262624908e-06,
      "loss": 1.2887,
      "step": 375
    },
    {
      "epoch": 0.7739307535641547,
      "grad_norm": 0.28334983310000655,
      "learning_rate": 2.9668125502848035e-06,
      "loss": 1.2951,
      "step": 380
    },
    {
      "epoch": 0.7841140529531568,
      "grad_norm": 0.25257521474138683,
      "learning_rate": 2.7181209741918093e-06,
      "loss": 1.2937,
      "step": 385
    },
    {
      "epoch": 0.7942973523421588,
      "grad_norm": 0.2871884940474984,
      "learning_rate": 2.478667018632562e-06,
      "loss": 1.2858,
      "step": 390
    },
    {
      "epoch": 0.8044806517311609,
      "grad_norm": 0.25758574412430923,
      "learning_rate": 2.2487544492654832e-06,
      "loss": 1.3027,
      "step": 395
    },
    {
      "epoch": 0.814663951120163,
      "grad_norm": 0.2840318008095242,
      "learning_rate": 2.0286749277707783e-06,
      "loss": 1.2961,
      "step": 400
    },
    {
      "epoch": 0.814663951120163,
      "eval_loss": 1.297537922859192,
      "eval_runtime": 58.3016,
      "eval_samples_per_second": 238.536,
      "eval_steps_per_second": 3.739,
      "step": 400
    },
    {
      "epoch": 0.824847250509165,
      "grad_norm": 0.3101944505956513,
      "learning_rate": 1.8187076418552974e-06,
      "loss": 1.3014,
      "step": 405
    },
    {
      "epoch": 0.835030549898167,
      "grad_norm": 0.2791695231780548,
      "learning_rate": 1.6191189510815942e-06,
      "loss": 1.2931,
      "step": 410
    },
    {
      "epoch": 0.845213849287169,
      "grad_norm": 0.28415893155261507,
      "learning_rate": 1.4301620489704072e-06,
      "loss": 1.2988,
      "step": 415
    },
    {
      "epoch": 0.8553971486761711,
      "grad_norm": 0.2822535369305096,
      "learning_rate": 1.2520766418053408e-06,
      "loss": 1.2905,
      "step": 420
    },
    {
      "epoch": 0.8655804480651731,
      "grad_norm": 0.28168468277135167,
      "learning_rate": 1.0850886445471055e-06,
      "loss": 1.2817,
      "step": 425
    },
    {
      "epoch": 0.8757637474541752,
      "grad_norm": 0.2655425105216882,
      "learning_rate": 9.294098942430996e-07,
      "loss": 1.2843,
      "step": 430
    },
    {
      "epoch": 0.8859470468431772,
      "grad_norm": 0.2741436677332839,
      "learning_rate": 7.852378812959227e-07,
      "loss": 1.2924,
      "step": 435
    },
    {
      "epoch": 0.8961303462321792,
      "grad_norm": 0.26895584158358093,
      "learning_rate": 6.527554989316898e-07,
      "loss": 1.2935,
      "step": 440
    },
    {
      "epoch": 0.9063136456211812,
      "grad_norm": 0.266002518787797,
      "learning_rate": 5.321308111859791e-07,
      "loss": 1.2857,
      "step": 445
    },
    {
      "epoch": 0.9164969450101833,
      "grad_norm": 0.2650609910106162,
      "learning_rate": 4.235168397017542e-07,
      "loss": 1.2664,
      "step": 450
    },
    {
      "epoch": 0.9266802443991853,
      "grad_norm": 0.2647562856371479,
      "learning_rate": 3.2705136960970554e-07,
      "loss": 1.2988,
      "step": 455
    },
    {
      "epoch": 0.9368635437881874,
      "grad_norm": 0.29894331322023837,
      "learning_rate": 2.4285677473727123e-07,
      "loss": 1.2744,
      "step": 460
    },
    {
      "epoch": 0.9470468431771895,
      "grad_norm": 0.2719080220558317,
      "learning_rate": 1.7103986236807312e-07,
      "loss": 1.2803,
      "step": 465
    },
    {
      "epoch": 0.9572301425661914,
      "grad_norm": 0.2791229463614563,
      "learning_rate": 1.1169173774871478e-07,
      "loss": 1.2906,
      "step": 470
    },
    {
      "epoch": 0.9674134419551935,
      "grad_norm": 0.2987546290973262,
      "learning_rate": 6.488768851480087e-08,
      "loss": 1.2884,
      "step": 475
    },
    {
      "epoch": 0.9775967413441955,
      "grad_norm": 0.30009885175708245,
      "learning_rate": 3.0687089182819264e-08,
      "loss": 1.3051,
      "step": 480
    },
    {
      "epoch": 0.9877800407331976,
      "grad_norm": 0.2873283513110056,
      "learning_rate": 9.13332582901716e-09,
      "loss": 1.286,
      "step": 485
    },
    {
      "epoch": 0.9979633401221996,
      "grad_norm": 0.272339006461075,
      "learning_rate": 2.5374105085518297e-10,
      "loss": 1.2873,
      "step": 490
    },
    {
      "epoch": 1.0,
      "step": 491,
      "total_flos": 154920007237632.0,
      "train_loss": 1.4646558688760047,
      "train_runtime": 2127.1747,
      "train_samples_per_second": 59.07,
      "train_steps_per_second": 0.231
    }
  ],
  "logging_steps": 5,
  "max_steps": 491,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 154920007237632.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}