{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9955156950672643,
  "eval_steps": 500,
  "global_step": 1002,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029895366218236172,
      "grad_norm": 1.7227757373325907,
      "learning_rate": 5e-06,
      "loss": 0.7996,
      "step": 10
    },
    {
      "epoch": 0.059790732436472344,
      "grad_norm": 0.9611203507591377,
      "learning_rate": 5e-06,
      "loss": 0.7135,
      "step": 20
    },
    {
      "epoch": 0.08968609865470852,
      "grad_norm": 0.9725569590195154,
      "learning_rate": 5e-06,
      "loss": 0.6951,
      "step": 30
    },
    {
      "epoch": 0.11958146487294469,
      "grad_norm": 3.2811538218803395,
      "learning_rate": 5e-06,
      "loss": 0.6797,
      "step": 40
    },
    {
      "epoch": 0.14947683109118087,
      "grad_norm": 0.8573391570675103,
      "learning_rate": 5e-06,
      "loss": 0.6784,
      "step": 50
    },
    {
      "epoch": 0.17937219730941703,
      "grad_norm": 0.868925104854094,
      "learning_rate": 5e-06,
      "loss": 0.6581,
      "step": 60
    },
    {
      "epoch": 0.20926756352765322,
      "grad_norm": 0.8638395884318166,
      "learning_rate": 5e-06,
      "loss": 0.6555,
      "step": 70
    },
    {
      "epoch": 0.23916292974588937,
      "grad_norm": 0.8066338987622645,
      "learning_rate": 5e-06,
      "loss": 0.648,
      "step": 80
    },
    {
      "epoch": 0.26905829596412556,
      "grad_norm": 0.959241666467243,
      "learning_rate": 5e-06,
      "loss": 0.6408,
      "step": 90
    },
    {
      "epoch": 0.29895366218236175,
      "grad_norm": 0.9081144806308692,
      "learning_rate": 5e-06,
      "loss": 0.6316,
      "step": 100
    },
    {
      "epoch": 0.32884902840059793,
      "grad_norm": 0.527888295759615,
      "learning_rate": 5e-06,
      "loss": 0.6291,
      "step": 110
    },
    {
      "epoch": 0.35874439461883406,
      "grad_norm": 0.530904898441949,
      "learning_rate": 5e-06,
      "loss": 0.6306,
      "step": 120
    },
    {
      "epoch": 0.38863976083707025,
      "grad_norm": 1.340210203403077,
      "learning_rate": 5e-06,
      "loss": 0.6297,
      "step": 130
    },
    {
      "epoch": 0.41853512705530643,
      "grad_norm": 0.6798935279587197,
      "learning_rate": 5e-06,
      "loss": 0.6174,
      "step": 140
    },
    {
      "epoch": 0.4484304932735426,
      "grad_norm": 0.5563075616885166,
      "learning_rate": 5e-06,
      "loss": 0.6267,
      "step": 150
    },
    {
      "epoch": 0.47832585949177875,
      "grad_norm": 0.5882371698166489,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 160
    },
    {
      "epoch": 0.5082212257100149,
      "grad_norm": 0.8190976883281922,
      "learning_rate": 5e-06,
      "loss": 0.6291,
      "step": 170
    },
    {
      "epoch": 0.5381165919282511,
      "grad_norm": 1.1616952378221264,
      "learning_rate": 5e-06,
      "loss": 0.622,
      "step": 180
    },
    {
      "epoch": 0.5680119581464873,
      "grad_norm": 0.9342456317602823,
      "learning_rate": 5e-06,
      "loss": 0.6223,
      "step": 190
    },
    {
      "epoch": 0.5979073243647235,
      "grad_norm": 0.5634508480434365,
      "learning_rate": 5e-06,
      "loss": 0.6224,
      "step": 200
    },
    {
      "epoch": 0.6278026905829597,
      "grad_norm": 0.5687247783350089,
      "learning_rate": 5e-06,
      "loss": 0.6165,
      "step": 210
    },
    {
      "epoch": 0.6576980568011959,
      "grad_norm": 0.4883258194508368,
      "learning_rate": 5e-06,
      "loss": 0.6152,
      "step": 220
    },
    {
      "epoch": 0.6875934230194319,
      "grad_norm": 0.8486304132789366,
      "learning_rate": 5e-06,
      "loss": 0.6159,
      "step": 230
    },
    {
      "epoch": 0.7174887892376681,
      "grad_norm": 0.6238248908563286,
      "learning_rate": 5e-06,
      "loss": 0.6162,
      "step": 240
    },
    {
      "epoch": 0.7473841554559043,
      "grad_norm": 0.6044745525104007,
      "learning_rate": 5e-06,
      "loss": 0.6234,
      "step": 250
    },
    {
      "epoch": 0.7772795216741405,
      "grad_norm": 0.9451375549677865,
      "learning_rate": 5e-06,
      "loss": 0.6111,
      "step": 260
    },
    {
      "epoch": 0.8071748878923767,
      "grad_norm": 0.45825630250172444,
      "learning_rate": 5e-06,
      "loss": 0.6192,
      "step": 270
    },
    {
      "epoch": 0.8370702541106129,
      "grad_norm": 0.6319201283396348,
      "learning_rate": 5e-06,
      "loss": 0.6096,
      "step": 280
    },
    {
      "epoch": 0.866965620328849,
      "grad_norm": 0.7657293379708856,
      "learning_rate": 5e-06,
      "loss": 0.6141,
      "step": 290
    },
    {
      "epoch": 0.8968609865470852,
      "grad_norm": 0.9893263705993499,
      "learning_rate": 5e-06,
      "loss": 0.6089,
      "step": 300
    },
    {
      "epoch": 0.9267563527653214,
      "grad_norm": 0.7173372190639082,
      "learning_rate": 5e-06,
      "loss": 0.6111,
      "step": 310
    },
    {
      "epoch": 0.9566517189835575,
      "grad_norm": 0.9811853051168589,
      "learning_rate": 5e-06,
      "loss": 0.6102,
      "step": 320
    },
    {
      "epoch": 0.9865470852017937,
      "grad_norm": 0.7112900733743598,
      "learning_rate": 5e-06,
      "loss": 0.61,
      "step": 330
    },
    {
      "epoch": 0.9985052316890882,
      "eval_loss": 0.6036205291748047,
      "eval_runtime": 179.7257,
      "eval_samples_per_second": 50.143,
      "eval_steps_per_second": 0.395,
      "step": 334
    },
    {
      "epoch": 1.0164424514200299,
      "grad_norm": 0.798448788433312,
      "learning_rate": 5e-06,
      "loss": 0.5844,
      "step": 340
    },
    {
      "epoch": 1.046337817638266,
      "grad_norm": 0.4862066251039951,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 350
    },
    {
      "epoch": 1.0762331838565022,
      "grad_norm": 0.4993076971258802,
      "learning_rate": 5e-06,
      "loss": 0.5527,
      "step": 360
    },
    {
      "epoch": 1.1061285500747384,
      "grad_norm": 0.5150950615801339,
      "learning_rate": 5e-06,
      "loss": 0.5634,
      "step": 370
    },
    {
      "epoch": 1.1360239162929746,
      "grad_norm": 0.5048692828921545,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 380
    },
    {
      "epoch": 1.1659192825112108,
      "grad_norm": 0.6753247004760012,
      "learning_rate": 5e-06,
      "loss": 0.564,
      "step": 390
    },
    {
      "epoch": 1.195814648729447,
      "grad_norm": 0.6573750836477811,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 400
    },
    {
      "epoch": 1.2257100149476832,
      "grad_norm": 0.4776374496819678,
      "learning_rate": 5e-06,
      "loss": 0.5606,
      "step": 410
    },
    {
      "epoch": 1.2556053811659194,
      "grad_norm": 0.6972347006108826,
      "learning_rate": 5e-06,
      "loss": 0.5623,
      "step": 420
    },
    {
      "epoch": 1.2855007473841553,
      "grad_norm": 0.5751682932357886,
      "learning_rate": 5e-06,
      "loss": 0.5638,
      "step": 430
    },
    {
      "epoch": 1.3153961136023917,
      "grad_norm": 0.46990283221273976,
      "learning_rate": 5e-06,
      "loss": 0.5613,
      "step": 440
    },
    {
      "epoch": 1.3452914798206277,
      "grad_norm": 0.48832783516725714,
      "learning_rate": 5e-06,
      "loss": 0.5618,
      "step": 450
    },
    {
      "epoch": 1.375186846038864,
      "grad_norm": 0.577664523498894,
      "learning_rate": 5e-06,
      "loss": 0.5576,
      "step": 460
    },
    {
      "epoch": 1.4050822122571,
      "grad_norm": 1.1296329041134021,
      "learning_rate": 5e-06,
      "loss": 0.5669,
      "step": 470
    },
    {
      "epoch": 1.4349775784753362,
      "grad_norm": 0.5151995683265159,
      "learning_rate": 5e-06,
      "loss": 0.5574,
      "step": 480
    },
    {
      "epoch": 1.4648729446935724,
      "grad_norm": 0.5099370836269055,
      "learning_rate": 5e-06,
      "loss": 0.5595,
      "step": 490
    },
    {
      "epoch": 1.4947683109118086,
      "grad_norm": 1.9533464161877931,
      "learning_rate": 5e-06,
      "loss": 0.5537,
      "step": 500
    },
    {
      "epoch": 1.5246636771300448,
      "grad_norm": 0.48399021315551105,
      "learning_rate": 5e-06,
      "loss": 0.5495,
      "step": 510
    },
    {
      "epoch": 1.554559043348281,
      "grad_norm": 0.6214335190059805,
      "learning_rate": 5e-06,
      "loss": 0.5613,
      "step": 520
    },
    {
      "epoch": 1.5844544095665172,
      "grad_norm": 0.5861564517777224,
      "learning_rate": 5e-06,
      "loss": 0.5541,
      "step": 530
    },
    {
      "epoch": 1.6143497757847534,
      "grad_norm": 0.49297078946119194,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 540
    },
    {
      "epoch": 1.6442451420029895,
      "grad_norm": 0.5714533139717856,
      "learning_rate": 5e-06,
      "loss": 0.5593,
      "step": 550
    },
    {
      "epoch": 1.6741405082212257,
      "grad_norm": 0.5006114767351605,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 560
    },
    {
      "epoch": 1.704035874439462,
      "grad_norm": 0.46703065624186,
      "learning_rate": 5e-06,
      "loss": 0.5598,
      "step": 570
    },
    {
      "epoch": 1.733931240657698,
      "grad_norm": 0.7730998357221065,
      "learning_rate": 5e-06,
      "loss": 0.5634,
      "step": 580
    },
    {
      "epoch": 1.7638266068759343,
      "grad_norm": 0.49277366694442,
      "learning_rate": 5e-06,
      "loss": 0.5605,
      "step": 590
    },
    {
      "epoch": 1.7937219730941703,
      "grad_norm": 0.5504433736301172,
      "learning_rate": 5e-06,
      "loss": 0.5561,
      "step": 600
    },
    {
      "epoch": 1.8236173393124067,
      "grad_norm": 0.5967647274743713,
      "learning_rate": 5e-06,
      "loss": 0.566,
      "step": 610
    },
    {
      "epoch": 1.8535127055306426,
      "grad_norm": 0.48890667749726296,
      "learning_rate": 5e-06,
      "loss": 0.5605,
      "step": 620
    },
    {
      "epoch": 1.883408071748879,
      "grad_norm": 0.4629644980754441,
      "learning_rate": 5e-06,
      "loss": 0.5595,
      "step": 630
    },
    {
      "epoch": 1.913303437967115,
      "grad_norm": 0.6662601841176711,
      "learning_rate": 5e-06,
      "loss": 0.5558,
      "step": 640
    },
    {
      "epoch": 1.9431988041853514,
      "grad_norm": 0.49445892345223935,
      "learning_rate": 5e-06,
      "loss": 0.5656,
      "step": 650
    },
    {
      "epoch": 1.9730941704035874,
      "grad_norm": 0.49038356562054847,
      "learning_rate": 5e-06,
      "loss": 0.5516,
      "step": 660
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5952211022377014,
      "eval_runtime": 180.2664,
      "eval_samples_per_second": 49.993,
      "eval_steps_per_second": 0.394,
      "step": 669
    },
    {
      "epoch": 2.0029895366218238,
      "grad_norm": 0.8976719305214347,
      "learning_rate": 5e-06,
      "loss": 0.5594,
      "step": 670
    },
    {
      "epoch": 2.0328849028400597,
      "grad_norm": 0.5732430368808332,
      "learning_rate": 5e-06,
      "loss": 0.5126,
      "step": 680
    },
    {
      "epoch": 2.062780269058296,
      "grad_norm": 0.711257434778952,
      "learning_rate": 5e-06,
      "loss": 0.5066,
      "step": 690
    },
    {
      "epoch": 2.092675635276532,
      "grad_norm": 0.47578936442907804,
      "learning_rate": 5e-06,
      "loss": 0.5091,
      "step": 700
    },
    {
      "epoch": 2.1225710014947685,
      "grad_norm": 0.6502616890155823,
      "learning_rate": 5e-06,
      "loss": 0.502,
      "step": 710
    },
    {
      "epoch": 2.1524663677130045,
      "grad_norm": 0.5259070657358127,
      "learning_rate": 5e-06,
      "loss": 0.5098,
      "step": 720
    },
    {
      "epoch": 2.1823617339312404,
      "grad_norm": 0.48835956768596295,
      "learning_rate": 5e-06,
      "loss": 0.5056,
      "step": 730
    },
    {
      "epoch": 2.212257100149477,
      "grad_norm": 0.49943490023849413,
      "learning_rate": 5e-06,
      "loss": 0.5075,
      "step": 740
    },
    {
      "epoch": 2.242152466367713,
      "grad_norm": 0.5545099395398798,
      "learning_rate": 5e-06,
      "loss": 0.5119,
      "step": 750
    },
    {
      "epoch": 2.2720478325859492,
      "grad_norm": 0.49299741003621683,
      "learning_rate": 5e-06,
      "loss": 0.5117,
      "step": 760
    },
    {
      "epoch": 2.301943198804185,
      "grad_norm": 0.6118684934934306,
      "learning_rate": 5e-06,
      "loss": 0.5072,
      "step": 770
    },
    {
      "epoch": 2.3318385650224216,
      "grad_norm": 0.5626142080265026,
      "learning_rate": 5e-06,
      "loss": 0.51,
      "step": 780
    },
    {
      "epoch": 2.3617339312406576,
      "grad_norm": 0.6010691540792277,
      "learning_rate": 5e-06,
      "loss": 0.5161,
      "step": 790
    },
    {
      "epoch": 2.391629297458894,
      "grad_norm": 0.5047015995016646,
      "learning_rate": 5e-06,
      "loss": 0.5153,
      "step": 800
    },
    {
      "epoch": 2.42152466367713,
      "grad_norm": 0.6949616571712588,
      "learning_rate": 5e-06,
      "loss": 0.5149,
      "step": 810
    },
    {
      "epoch": 2.4514200298953663,
      "grad_norm": 0.5728721236291187,
      "learning_rate": 5e-06,
      "loss": 0.5152,
      "step": 820
    },
    {
      "epoch": 2.4813153961136023,
      "grad_norm": 0.6710964944926828,
      "learning_rate": 5e-06,
      "loss": 0.5101,
      "step": 830
    },
    {
      "epoch": 2.5112107623318387,
      "grad_norm": 0.5811240824837944,
      "learning_rate": 5e-06,
      "loss": 0.5178,
      "step": 840
    },
    {
      "epoch": 2.5411061285500747,
      "grad_norm": 0.4751656854800782,
      "learning_rate": 5e-06,
      "loss": 0.5093,
      "step": 850
    },
    {
      "epoch": 2.5710014947683106,
      "grad_norm": 0.5791534437598944,
      "learning_rate": 5e-06,
      "loss": 0.5172,
      "step": 860
    },
    {
      "epoch": 2.600896860986547,
      "grad_norm": 0.6285700826659869,
      "learning_rate": 5e-06,
      "loss": 0.5114,
      "step": 870
    },
    {
      "epoch": 2.6307922272047835,
      "grad_norm": 0.5891524124365762,
      "learning_rate": 5e-06,
      "loss": 0.5155,
      "step": 880
    },
    {
      "epoch": 2.6606875934230194,
      "grad_norm": 0.5554272805920556,
      "learning_rate": 5e-06,
      "loss": 0.5136,
      "step": 890
    },
    {
      "epoch": 2.6905829596412554,
      "grad_norm": 0.5212686694617318,
      "learning_rate": 5e-06,
      "loss": 0.5057,
      "step": 900
    },
    {
      "epoch": 2.720478325859492,
      "grad_norm": 0.5049518346407917,
      "learning_rate": 5e-06,
      "loss": 0.5124,
      "step": 910
    },
    {
      "epoch": 2.750373692077728,
      "grad_norm": 0.5199545471660975,
      "learning_rate": 5e-06,
      "loss": 0.511,
      "step": 920
    },
    {
      "epoch": 2.780269058295964,
      "grad_norm": 0.5504296104314776,
      "learning_rate": 5e-06,
      "loss": 0.5131,
      "step": 930
    },
    {
      "epoch": 2.8101644245142,
      "grad_norm": 0.6934304296183573,
      "learning_rate": 5e-06,
      "loss": 0.5141,
      "step": 940
    },
    {
      "epoch": 2.8400597907324365,
      "grad_norm": 0.5471886063573883,
      "learning_rate": 5e-06,
      "loss": 0.5085,
      "step": 950
    },
    {
      "epoch": 2.8699551569506725,
      "grad_norm": 0.5910070248229388,
      "learning_rate": 5e-06,
      "loss": 0.511,
      "step": 960
    },
    {
      "epoch": 2.899850523168909,
      "grad_norm": 0.7084764050035022,
      "learning_rate": 5e-06,
      "loss": 0.512,
      "step": 970
    },
    {
      "epoch": 2.929745889387145,
      "grad_norm": 0.4994611316507679,
      "learning_rate": 5e-06,
      "loss": 0.5083,
      "step": 980
    },
    {
      "epoch": 2.9596412556053813,
      "grad_norm": 0.5300263474194525,
      "learning_rate": 5e-06,
      "loss": 0.5077,
      "step": 990
    },
    {
      "epoch": 2.9895366218236172,
      "grad_norm": 0.4912770545978263,
      "learning_rate": 5e-06,
      "loss": 0.5082,
      "step": 1000
    },
    {
      "epoch": 2.9955156950672643,
      "eval_loss": 0.5980154871940613,
      "eval_runtime": 180.5721,
      "eval_samples_per_second": 49.908,
      "eval_steps_per_second": 0.393,
      "step": 1002
    },
    {
      "epoch": 2.9955156950672643,
      "step": 1002,
      "total_flos": 1677968560619520.0,
      "train_loss": 0.5696332816354291,
      "train_runtime": 30032.1545,
      "train_samples_per_second": 17.104,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 1002,
  "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": 1677968560619520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}