{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9971181556195967,
  "eval_steps": 500,
  "global_step": 780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03842459173871278,
      "grad_norm": 0.7461163997650146,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2598,
      "step": 10
    },
    {
      "epoch": 0.07684918347742556,
      "grad_norm": 0.25502100586891174,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.7563,
      "step": 20
    },
    {
      "epoch": 0.11527377521613832,
      "grad_norm": 0.14209185540676117,
      "learning_rate": 0.00019996891820008164,
      "loss": 0.63,
      "step": 30
    },
    {
      "epoch": 0.15369836695485112,
      "grad_norm": 0.10494557023048401,
      "learning_rate": 0.0001997790438338385,
      "loss": 0.5646,
      "step": 40
    },
    {
      "epoch": 0.19212295869356388,
      "grad_norm": 0.11090180277824402,
      "learning_rate": 0.0001994168902089112,
      "loss": 0.5158,
      "step": 50
    },
    {
      "epoch": 0.23054755043227665,
      "grad_norm": 0.09561982750892639,
      "learning_rate": 0.00019888308262251285,
      "loss": 0.5171,
      "step": 60
    },
    {
      "epoch": 0.2689721421709894,
      "grad_norm": 0.13890881836414337,
      "learning_rate": 0.0001981785427508966,
      "loss": 0.5013,
      "step": 70
    },
    {
      "epoch": 0.30739673390970224,
      "grad_norm": 0.09685279428958893,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.4803,
      "step": 80
    },
    {
      "epoch": 0.345821325648415,
      "grad_norm": 0.0978529155254364,
      "learning_rate": 0.0001962624246950012,
      "loss": 0.4824,
      "step": 90
    },
    {
      "epoch": 0.38424591738712777,
      "grad_norm": 0.09823426604270935,
      "learning_rate": 0.0001950541548947829,
      "loss": 0.4765,
      "step": 100
    },
    {
      "epoch": 0.42267050912584053,
      "grad_norm": 0.11479681730270386,
      "learning_rate": 0.0001936817638651871,
      "loss": 0.4804,
      "step": 110
    },
    {
      "epoch": 0.4610951008645533,
      "grad_norm": 0.1102244183421135,
      "learning_rate": 0.00019214762118704076,
      "loss": 0.4735,
      "step": 120
    },
    {
      "epoch": 0.49951969260326606,
      "grad_norm": 0.09442220628261566,
      "learning_rate": 0.00019045437572280194,
      "loss": 0.4654,
      "step": 130
    },
    {
      "epoch": 0.5379442843419788,
      "grad_norm": 0.0998912900686264,
      "learning_rate": 0.00018860495104301345,
      "loss": 0.4714,
      "step": 140
    },
    {
      "epoch": 0.5763688760806917,
      "grad_norm": 0.12593407928943634,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.4652,
      "step": 150
    },
    {
      "epoch": 0.6147934678194045,
      "grad_norm": 0.10841673612594604,
      "learning_rate": 0.0001844506011066308,
      "loss": 0.4633,
      "step": 160
    },
    {
      "epoch": 0.6532180595581172,
      "grad_norm": 0.09892784804105759,
      "learning_rate": 0.00018215284878234642,
      "loss": 0.461,
      "step": 170
    },
    {
      "epoch": 0.69164265129683,
      "grad_norm": 0.5387171506881714,
      "learning_rate": 0.00017971325072229226,
      "loss": 0.4591,
      "step": 180
    },
    {
      "epoch": 0.7300672430355427,
      "grad_norm": 0.11192867159843445,
      "learning_rate": 0.0001771360191551,
      "loss": 0.4592,
      "step": 190
    },
    {
      "epoch": 0.7684918347742555,
      "grad_norm": 0.10694364458322525,
      "learning_rate": 0.00017442560394846516,
      "loss": 0.4574,
      "step": 200
    },
    {
      "epoch": 0.8069164265129684,
      "grad_norm": 0.10873424261808395,
      "learning_rate": 0.00017158668492597186,
      "loss": 0.4492,
      "step": 210
    },
    {
      "epoch": 0.8453410182516811,
      "grad_norm": 0.11694315820932388,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.4467,
      "step": 220
    },
    {
      "epoch": 0.8837656099903939,
      "grad_norm": 0.10100408643484116,
      "learning_rate": 0.000165543155642781,
      "loss": 0.4488,
      "step": 230
    },
    {
      "epoch": 0.9221902017291066,
      "grad_norm": 0.10397649556398392,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.447,
      "step": 240
    },
    {
      "epoch": 0.9606147934678194,
      "grad_norm": 0.10007993876934052,
      "learning_rate": 0.00015904715250387498,
      "loss": 0.4428,
      "step": 250
    },
    {
      "epoch": 0.9990393852065321,
      "grad_norm": 0.10865867137908936,
      "learning_rate": 0.00015564337355766412,
      "loss": 0.4452,
      "step": 260
    },
    {
      "epoch": 1.037463976945245,
      "grad_norm": 0.10476306080818176,
      "learning_rate": 0.0001521435203379498,
      "loss": 0.4367,
      "step": 270
    },
    {
      "epoch": 1.0758885686839577,
      "grad_norm": 0.10958375781774521,
      "learning_rate": 0.00014855363571801523,
      "loss": 0.4336,
      "step": 280
    },
    {
      "epoch": 1.1143131604226706,
      "grad_norm": 0.11801016330718994,
      "learning_rate": 0.00014487991802004623,
      "loss": 0.4346,
      "step": 290
    },
    {
      "epoch": 1.1527377521613833,
      "grad_norm": 0.11526134610176086,
      "learning_rate": 0.00014112871031306119,
      "loss": 0.4221,
      "step": 300
    },
    {
      "epoch": 1.191162343900096,
      "grad_norm": 0.10705429315567017,
      "learning_rate": 0.0001373064894609194,
      "loss": 0.4363,
      "step": 310
    },
    {
      "epoch": 1.229586935638809,
      "grad_norm": 0.09906008094549179,
      "learning_rate": 0.00013341985493931877,
      "loss": 0.4359,
      "step": 320
    },
    {
      "epoch": 1.2680115273775217,
      "grad_norm": 0.11935935914516449,
      "learning_rate": 0.00012947551744109043,
      "loss": 0.429,
      "step": 330
    },
    {
      "epoch": 1.3064361191162344,
      "grad_norm": 0.11651390045881271,
      "learning_rate": 0.0001254802872894655,
      "loss": 0.4295,
      "step": 340
    },
    {
      "epoch": 1.344860710854947,
      "grad_norm": 0.13374051451683044,
      "learning_rate": 0.00012144106267931876,
      "loss": 0.43,
      "step": 350
    },
    {
      "epoch": 1.38328530259366,
      "grad_norm": 0.10709749907255173,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.4229,
      "step": 360
    },
    {
      "epoch": 1.4217098943323727,
      "grad_norm": 0.10747699439525604,
      "learning_rate": 0.00011325859062716795,
      "loss": 0.4255,
      "step": 370
    },
    {
      "epoch": 1.4601344860710854,
      "grad_norm": 0.1302700638771057,
      "learning_rate": 0.00010912947110386484,
      "loss": 0.4314,
      "step": 380
    },
    {
      "epoch": 1.4985590778097984,
      "grad_norm": 0.10743537545204163,
      "learning_rate": 0.00010498458856606972,
      "loss": 0.4242,
      "step": 390
    },
    {
      "epoch": 1.536983669548511,
      "grad_norm": 0.11519400030374527,
      "learning_rate": 0.00010083109959960973,
      "loss": 0.4216,
      "step": 400
    },
    {
      "epoch": 1.5754082612872238,
      "grad_norm": 0.11456304788589478,
      "learning_rate": 9.667617565023735e-05,
      "loss": 0.4315,
      "step": 410
    },
    {
      "epoch": 1.6138328530259365,
      "grad_norm": 0.10759314894676208,
      "learning_rate": 9.252699064135758e-05,
      "loss": 0.4199,
      "step": 420
    },
    {
      "epoch": 1.6522574447646494,
      "grad_norm": 0.1024770587682724,
      "learning_rate": 8.839070858747697e-05,
      "loss": 0.4272,
      "step": 430
    },
    {
      "epoch": 1.6906820365033621,
      "grad_norm": 0.10736548155546188,
      "learning_rate": 8.427447122476148e-05,
      "loss": 0.4232,
      "step": 440
    },
    {
      "epoch": 1.729106628242075,
      "grad_norm": 0.1060362458229065,
      "learning_rate": 8.018538568006027e-05,
      "loss": 0.4237,
      "step": 450
    },
    {
      "epoch": 1.7675312199807878,
      "grad_norm": 0.10463803261518478,
      "learning_rate": 7.613051219968623e-05,
      "loss": 0.4247,
      "step": 460
    },
    {
      "epoch": 1.8059558117195005,
      "grad_norm": 0.10327400267124176,
      "learning_rate": 7.211685195914097e-05,
      "loss": 0.4196,
      "step": 470
    },
    {
      "epoch": 1.8443804034582132,
      "grad_norm": 0.13895417749881744,
      "learning_rate": 6.815133497483157e-05,
      "loss": 0.4205,
      "step": 480
    },
    {
      "epoch": 1.882804995196926,
      "grad_norm": 0.10684759169816971,
      "learning_rate": 6.424080813865138e-05,
      "loss": 0.4224,
      "step": 490
    },
    {
      "epoch": 1.9212295869356388,
      "grad_norm": 0.13927388191223145,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.4196,
      "step": 500
    },
    {
      "epoch": 1.9596541786743515,
      "grad_norm": 0.10447521507740021,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.4225,
      "step": 510
    },
    {
      "epoch": 1.9980787704130645,
      "grad_norm": 0.10929688066244125,
      "learning_rate": 5.290614347797802e-05,
      "loss": 0.4254,
      "step": 520
    },
    {
      "epoch": 2.036503362151777,
      "grad_norm": 0.10282639414072037,
      "learning_rate": 4.92819734798441e-05,
      "loss": 0.4115,
      "step": 530
    },
    {
      "epoch": 2.07492795389049,
      "grad_norm": 0.10815539956092834,
      "learning_rate": 4.574537361342407e-05,
      "loss": 0.4162,
      "step": 540
    },
    {
      "epoch": 2.1133525456292026,
      "grad_norm": 0.1221628338098526,
      "learning_rate": 4.23024501990417e-05,
      "loss": 0.4056,
      "step": 550
    },
    {
      "epoch": 2.1517771373679153,
      "grad_norm": 0.1123044565320015,
      "learning_rate": 3.89591478145437e-05,
      "loss": 0.4089,
      "step": 560
    },
    {
      "epoch": 2.1902017291066285,
      "grad_norm": 0.11408425867557526,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.4113,
      "step": 570
    },
    {
      "epoch": 2.228626320845341,
      "grad_norm": 0.10744322091341019,
      "learning_rate": 3.259431444746846e-05,
      "loss": 0.4018,
      "step": 580
    },
    {
      "epoch": 2.267050912584054,
      "grad_norm": 0.11307461559772491,
      "learning_rate": 2.9583773034764826e-05,
      "loss": 0.405,
      "step": 590
    },
    {
      "epoch": 2.3054755043227666,
      "grad_norm": 0.11285313963890076,
      "learning_rate": 2.66948128170174e-05,
      "loss": 0.3995,
      "step": 600
    },
    {
      "epoch": 2.3439000960614793,
      "grad_norm": 0.15918630361557007,
      "learning_rate": 2.3932421894989167e-05,
      "loss": 0.4027,
      "step": 610
    },
    {
      "epoch": 2.382324687800192,
      "grad_norm": 0.11159035563468933,
      "learning_rate": 2.1301369833931117e-05,
      "loss": 0.4082,
      "step": 620
    },
    {
      "epoch": 2.4207492795389047,
      "grad_norm": 0.11359286308288574,
      "learning_rate": 1.880619942841435e-05,
      "loss": 0.4054,
      "step": 630
    },
    {
      "epoch": 2.459173871277618,
      "grad_norm": 0.11326448619365692,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.4064,
      "step": 640
    },
    {
      "epoch": 2.4975984630163306,
      "grad_norm": 0.11316490173339844,
      "learning_rate": 1.4240494252234049e-05,
      "loss": 0.4111,
      "step": 650
    },
    {
      "epoch": 2.5360230547550433,
      "grad_norm": 0.11959807574748993,
      "learning_rate": 1.2177842662977135e-05,
      "loss": 0.4078,
      "step": 660
    },
    {
      "epoch": 2.574447646493756,
      "grad_norm": 0.10980040580034256,
      "learning_rate": 1.0266825480913611e-05,
      "loss": 0.408,
      "step": 670
    },
    {
      "epoch": 2.6128722382324687,
      "grad_norm": 0.11757558584213257,
      "learning_rate": 8.510742282896544e-06,
      "loss": 0.4019,
      "step": 680
    },
    {
      "epoch": 2.6512968299711814,
      "grad_norm": 0.11953994631767273,
      "learning_rate": 6.9126251355795864e-06,
      "loss": 0.4037,
      "step": 690
    },
    {
      "epoch": 2.689721421709894,
      "grad_norm": 0.13467754423618317,
      "learning_rate": 5.475233360227527e-06,
      "loss": 0.404,
      "step": 700
    },
    {
      "epoch": 2.7281460134486073,
      "grad_norm": 0.11414311081171036,
      "learning_rate": 4.20104876845111e-06,
      "loss": 0.4043,
      "step": 710
    },
    {
      "epoch": 2.76657060518732,
      "grad_norm": 0.11653583496809006,
      "learning_rate": 3.092271377092215e-06,
      "loss": 0.4036,
      "step": 720
    },
    {
      "epoch": 2.8049951969260327,
      "grad_norm": 0.1183491125702858,
      "learning_rate": 2.150815609657875e-06,
      "loss": 0.4053,
      "step": 730
    },
    {
      "epoch": 2.8434197886647454,
      "grad_norm": 0.142572820186615,
      "learning_rate": 1.378306990862177e-06,
      "loss": 0.4037,
      "step": 740
    },
    {
      "epoch": 2.881844380403458,
      "grad_norm": 0.11191695928573608,
      "learning_rate": 7.760793399827937e-07,
      "loss": 0.4035,
      "step": 750
    },
    {
      "epoch": 2.920268972142171,
      "grad_norm": 0.11203925311565399,
      "learning_rate": 3.451724678784518e-07,
      "loss": 0.409,
      "step": 760
    },
    {
      "epoch": 2.9586935638808836,
      "grad_norm": 0.11161793023347855,
      "learning_rate": 8.633038164358454e-08,
      "loss": 0.3982,
      "step": 770
    },
    {
      "epoch": 2.9971181556195967,
      "grad_norm": 0.11390741169452667,
      "learning_rate": 0.0,
      "loss": 0.4073,
      "step": 780
    }
  ],
  "logging_steps": 10,
  "max_steps": 780,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5.794517495096279e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}