{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999438727782975,
  "eval_steps": 500,
  "global_step": 1002,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029934518241347054,
      "grad_norm": 1.33524144451092,
      "learning_rate": 5e-06,
      "loss": 0.7726,
      "step": 10
    },
    {
      "epoch": 0.05986903648269411,
      "grad_norm": 0.7879332647993313,
      "learning_rate": 5e-06,
      "loss": 0.6941,
      "step": 20
    },
    {
      "epoch": 0.08980355472404115,
      "grad_norm": 0.8279414479936676,
      "learning_rate": 5e-06,
      "loss": 0.669,
      "step": 30
    },
    {
      "epoch": 0.11973807296538821,
      "grad_norm": 0.6801830999347731,
      "learning_rate": 5e-06,
      "loss": 0.6651,
      "step": 40
    },
    {
      "epoch": 0.14967259120673526,
      "grad_norm": 0.825336157832171,
      "learning_rate": 5e-06,
      "loss": 0.6563,
      "step": 50
    },
    {
      "epoch": 0.1796071094480823,
      "grad_norm": 0.8041213132253388,
      "learning_rate": 5e-06,
      "loss": 0.6486,
      "step": 60
    },
    {
      "epoch": 0.20954162768942938,
      "grad_norm": 0.7685208697099756,
      "learning_rate": 5e-06,
      "loss": 0.6456,
      "step": 70
    },
    {
      "epoch": 0.23947614593077643,
      "grad_norm": 0.8272207752381818,
      "learning_rate": 5e-06,
      "loss": 0.647,
      "step": 80
    },
    {
      "epoch": 0.2694106641721235,
      "grad_norm": 0.9517995329423086,
      "learning_rate": 5e-06,
      "loss": 0.638,
      "step": 90
    },
    {
      "epoch": 0.2993451824134705,
      "grad_norm": 0.8751066383364019,
      "learning_rate": 5e-06,
      "loss": 0.6394,
      "step": 100
    },
    {
      "epoch": 0.3292797006548176,
      "grad_norm": 0.8030803646782766,
      "learning_rate": 5e-06,
      "loss": 0.635,
      "step": 110
    },
    {
      "epoch": 0.3592142188961646,
      "grad_norm": 0.8567743177602571,
      "learning_rate": 5e-06,
      "loss": 0.6341,
      "step": 120
    },
    {
      "epoch": 0.3891487371375117,
      "grad_norm": 0.7057301347531115,
      "learning_rate": 5e-06,
      "loss": 0.6341,
      "step": 130
    },
    {
      "epoch": 0.41908325537885877,
      "grad_norm": 0.7257500307005497,
      "learning_rate": 5e-06,
      "loss": 0.6279,
      "step": 140
    },
    {
      "epoch": 0.4490177736202058,
      "grad_norm": 0.6593297594688626,
      "learning_rate": 5e-06,
      "loss": 0.6296,
      "step": 150
    },
    {
      "epoch": 0.47895229186155286,
      "grad_norm": 0.6452429439980394,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 160
    },
    {
      "epoch": 0.5088868101028999,
      "grad_norm": 0.6606811551730326,
      "learning_rate": 5e-06,
      "loss": 0.6229,
      "step": 170
    },
    {
      "epoch": 0.538821328344247,
      "grad_norm": 0.6711513998175146,
      "learning_rate": 5e-06,
      "loss": 0.6242,
      "step": 180
    },
    {
      "epoch": 0.568755846585594,
      "grad_norm": 0.7104593525315798,
      "learning_rate": 5e-06,
      "loss": 0.6221,
      "step": 190
    },
    {
      "epoch": 0.598690364826941,
      "grad_norm": 0.7379619895502215,
      "learning_rate": 5e-06,
      "loss": 0.6299,
      "step": 200
    },
    {
      "epoch": 0.6286248830682881,
      "grad_norm": 0.7648666735753528,
      "learning_rate": 5e-06,
      "loss": 0.6239,
      "step": 210
    },
    {
      "epoch": 0.6585594013096352,
      "grad_norm": 0.9404311490485926,
      "learning_rate": 5e-06,
      "loss": 0.622,
      "step": 220
    },
    {
      "epoch": 0.6884939195509823,
      "grad_norm": 0.7620760335678477,
      "learning_rate": 5e-06,
      "loss": 0.6245,
      "step": 230
    },
    {
      "epoch": 0.7184284377923292,
      "grad_norm": 0.6801471879586377,
      "learning_rate": 5e-06,
      "loss": 0.6234,
      "step": 240
    },
    {
      "epoch": 0.7483629560336763,
      "grad_norm": 0.6188538344723454,
      "learning_rate": 5e-06,
      "loss": 0.62,
      "step": 250
    },
    {
      "epoch": 0.7782974742750234,
      "grad_norm": 0.6763082935968893,
      "learning_rate": 5e-06,
      "loss": 0.6188,
      "step": 260
    },
    {
      "epoch": 0.8082319925163705,
      "grad_norm": 0.7713471285203956,
      "learning_rate": 5e-06,
      "loss": 0.6262,
      "step": 270
    },
    {
      "epoch": 0.8381665107577175,
      "grad_norm": 0.6607536842874296,
      "learning_rate": 5e-06,
      "loss": 0.6163,
      "step": 280
    },
    {
      "epoch": 0.8681010289990645,
      "grad_norm": 0.7717078426208482,
      "learning_rate": 5e-06,
      "loss": 0.6131,
      "step": 290
    },
    {
      "epoch": 0.8980355472404116,
      "grad_norm": 0.7870617184265295,
      "learning_rate": 5e-06,
      "loss": 0.6144,
      "step": 300
    },
    {
      "epoch": 0.9279700654817586,
      "grad_norm": 0.7331877573172668,
      "learning_rate": 5e-06,
      "loss": 0.6132,
      "step": 310
    },
    {
      "epoch": 0.9579045837231057,
      "grad_norm": 0.6228025141259461,
      "learning_rate": 5e-06,
      "loss": 0.6153,
      "step": 320
    },
    {
      "epoch": 0.9878391019644528,
      "grad_norm": 0.8794877763061338,
      "learning_rate": 5e-06,
      "loss": 0.6082,
      "step": 330
    },
    {
      "epoch": 0.9998129092609915,
      "eval_loss": 0.6191971302032471,
      "eval_runtime": 513.8197,
      "eval_samples_per_second": 17.518,
      "eval_steps_per_second": 0.549,
      "step": 334
    },
    {
      "epoch": 1.0177736202057999,
      "grad_norm": 1.051149899458133,
      "learning_rate": 5e-06,
      "loss": 0.6383,
      "step": 340
    },
    {
      "epoch": 1.047708138447147,
      "grad_norm": 0.8863718972848443,
      "learning_rate": 5e-06,
      "loss": 0.5521,
      "step": 350
    },
    {
      "epoch": 1.077642656688494,
      "grad_norm": 0.7696809696204965,
      "learning_rate": 5e-06,
      "loss": 0.5476,
      "step": 360
    },
    {
      "epoch": 1.1075771749298409,
      "grad_norm": 0.7321339489037564,
      "learning_rate": 5e-06,
      "loss": 0.5479,
      "step": 370
    },
    {
      "epoch": 1.137511693171188,
      "grad_norm": 0.855411890940372,
      "learning_rate": 5e-06,
      "loss": 0.5482,
      "step": 380
    },
    {
      "epoch": 1.167446211412535,
      "grad_norm": 0.6867381703861567,
      "learning_rate": 5e-06,
      "loss": 0.5497,
      "step": 390
    },
    {
      "epoch": 1.197380729653882,
      "grad_norm": 0.706701550293977,
      "learning_rate": 5e-06,
      "loss": 0.5498,
      "step": 400
    },
    {
      "epoch": 1.2273152478952292,
      "grad_norm": 0.657606609450406,
      "learning_rate": 5e-06,
      "loss": 0.5522,
      "step": 410
    },
    {
      "epoch": 1.2572497661365762,
      "grad_norm": 0.734454355764663,
      "learning_rate": 5e-06,
      "loss": 0.5565,
      "step": 420
    },
    {
      "epoch": 1.2871842843779233,
      "grad_norm": 0.6920219090733138,
      "learning_rate": 5e-06,
      "loss": 0.5512,
      "step": 430
    },
    {
      "epoch": 1.3171188026192704,
      "grad_norm": 0.7050222180373579,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 440
    },
    {
      "epoch": 1.3470533208606175,
      "grad_norm": 0.6418787070653531,
      "learning_rate": 5e-06,
      "loss": 0.5472,
      "step": 450
    },
    {
      "epoch": 1.3769878391019645,
      "grad_norm": 0.7020770314834763,
      "learning_rate": 5e-06,
      "loss": 0.5579,
      "step": 460
    },
    {
      "epoch": 1.4069223573433116,
      "grad_norm": 0.7565925680769534,
      "learning_rate": 5e-06,
      "loss": 0.5572,
      "step": 470
    },
    {
      "epoch": 1.4368568755846587,
      "grad_norm": 0.7716194723504068,
      "learning_rate": 5e-06,
      "loss": 0.5592,
      "step": 480
    },
    {
      "epoch": 1.4667913938260055,
      "grad_norm": 0.6242085523944472,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 490
    },
    {
      "epoch": 1.4967259120673526,
      "grad_norm": 0.7940557302941157,
      "learning_rate": 5e-06,
      "loss": 0.5548,
      "step": 500
    },
    {
      "epoch": 1.5266604303086997,
      "grad_norm": 0.6525047117975198,
      "learning_rate": 5e-06,
      "loss": 0.5576,
      "step": 510
    },
    {
      "epoch": 1.5565949485500468,
      "grad_norm": 0.6628111195235525,
      "learning_rate": 5e-06,
      "loss": 0.5555,
      "step": 520
    },
    {
      "epoch": 1.5865294667913938,
      "grad_norm": 0.689008481637834,
      "learning_rate": 5e-06,
      "loss": 0.556,
      "step": 530
    },
    {
      "epoch": 1.616463985032741,
      "grad_norm": 0.673209395932296,
      "learning_rate": 5e-06,
      "loss": 0.5597,
      "step": 540
    },
    {
      "epoch": 1.646398503274088,
      "grad_norm": 0.6562180289450842,
      "learning_rate": 5e-06,
      "loss": 0.559,
      "step": 550
    },
    {
      "epoch": 1.6763330215154348,
      "grad_norm": 0.6536265227596837,
      "learning_rate": 5e-06,
      "loss": 0.5497,
      "step": 560
    },
    {
      "epoch": 1.706267539756782,
      "grad_norm": 0.8061423665741692,
      "learning_rate": 5e-06,
      "loss": 0.5515,
      "step": 570
    },
    {
      "epoch": 1.736202057998129,
      "grad_norm": 0.7527856563515462,
      "learning_rate": 5e-06,
      "loss": 0.5528,
      "step": 580
    },
    {
      "epoch": 1.766136576239476,
      "grad_norm": 0.6524204661014693,
      "learning_rate": 5e-06,
      "loss": 0.5557,
      "step": 590
    },
    {
      "epoch": 1.7960710944808231,
      "grad_norm": 0.7636496430663919,
      "learning_rate": 5e-06,
      "loss": 0.5563,
      "step": 600
    },
    {
      "epoch": 1.8260056127221702,
      "grad_norm": 0.6139102967035015,
      "learning_rate": 5e-06,
      "loss": 0.5542,
      "step": 610
    },
    {
      "epoch": 1.8559401309635173,
      "grad_norm": 0.6601750107356386,
      "learning_rate": 5e-06,
      "loss": 0.5522,
      "step": 620
    },
    {
      "epoch": 1.8858746492048644,
      "grad_norm": 0.6527473717177242,
      "learning_rate": 5e-06,
      "loss": 0.5541,
      "step": 630
    },
    {
      "epoch": 1.9158091674462114,
      "grad_norm": 0.7081463978731246,
      "learning_rate": 5e-06,
      "loss": 0.5555,
      "step": 640
    },
    {
      "epoch": 1.9457436856875585,
      "grad_norm": 0.6575694714276955,
      "learning_rate": 5e-06,
      "loss": 0.5538,
      "step": 650
    },
    {
      "epoch": 1.9756782039289056,
      "grad_norm": 0.742675067686587,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 660
    },
    {
      "epoch": 1.999625818521983,
      "eval_loss": 0.6157492399215698,
      "eval_runtime": 513.972,
      "eval_samples_per_second": 17.513,
      "eval_steps_per_second": 0.549,
      "step": 668
    },
    {
      "epoch": 2.0056127221702527,
      "grad_norm": 1.0969823662871345,
      "learning_rate": 5e-06,
      "loss": 0.6006,
      "step": 670
    },
    {
      "epoch": 2.0355472404115997,
      "grad_norm": 0.8811643475045893,
      "learning_rate": 5e-06,
      "loss": 0.4848,
      "step": 680
    },
    {
      "epoch": 2.065481758652947,
      "grad_norm": 0.6969691205957229,
      "learning_rate": 5e-06,
      "loss": 0.4807,
      "step": 690
    },
    {
      "epoch": 2.095416276894294,
      "grad_norm": 0.7414702187007401,
      "learning_rate": 5e-06,
      "loss": 0.4851,
      "step": 700
    },
    {
      "epoch": 2.125350795135641,
      "grad_norm": 0.7009292878212435,
      "learning_rate": 5e-06,
      "loss": 0.4854,
      "step": 710
    },
    {
      "epoch": 2.155285313376988,
      "grad_norm": 0.7842781168002291,
      "learning_rate": 5e-06,
      "loss": 0.4889,
      "step": 720
    },
    {
      "epoch": 2.185219831618335,
      "grad_norm": 0.7461009782048098,
      "learning_rate": 5e-06,
      "loss": 0.4889,
      "step": 730
    },
    {
      "epoch": 2.2151543498596817,
      "grad_norm": 0.8026481173007173,
      "learning_rate": 5e-06,
      "loss": 0.4897,
      "step": 740
    },
    {
      "epoch": 2.245088868101029,
      "grad_norm": 0.7282963208145856,
      "learning_rate": 5e-06,
      "loss": 0.492,
      "step": 750
    },
    {
      "epoch": 2.275023386342376,
      "grad_norm": 0.6937815645596959,
      "learning_rate": 5e-06,
      "loss": 0.4876,
      "step": 760
    },
    {
      "epoch": 2.304957904583723,
      "grad_norm": 0.7336679828664284,
      "learning_rate": 5e-06,
      "loss": 0.4927,
      "step": 770
    },
    {
      "epoch": 2.33489242282507,
      "grad_norm": 0.6876179706146903,
      "learning_rate": 5e-06,
      "loss": 0.4885,
      "step": 780
    },
    {
      "epoch": 2.364826941066417,
      "grad_norm": 0.6652815658554195,
      "learning_rate": 5e-06,
      "loss": 0.4902,
      "step": 790
    },
    {
      "epoch": 2.394761459307764,
      "grad_norm": 0.7377189200046532,
      "learning_rate": 5e-06,
      "loss": 0.493,
      "step": 800
    },
    {
      "epoch": 2.4246959775491113,
      "grad_norm": 0.7876150878263464,
      "learning_rate": 5e-06,
      "loss": 0.4997,
      "step": 810
    },
    {
      "epoch": 2.4546304957904583,
      "grad_norm": 0.7434727155031786,
      "learning_rate": 5e-06,
      "loss": 0.4969,
      "step": 820
    },
    {
      "epoch": 2.4845650140318054,
      "grad_norm": 0.8780260045950764,
      "learning_rate": 5e-06,
      "loss": 0.4966,
      "step": 830
    },
    {
      "epoch": 2.5144995322731525,
      "grad_norm": 0.675071719958174,
      "learning_rate": 5e-06,
      "loss": 0.4938,
      "step": 840
    },
    {
      "epoch": 2.5444340505144996,
      "grad_norm": 0.7396853414765119,
      "learning_rate": 5e-06,
      "loss": 0.4974,
      "step": 850
    },
    {
      "epoch": 2.5743685687558466,
      "grad_norm": 0.7508686496100224,
      "learning_rate": 5e-06,
      "loss": 0.4955,
      "step": 860
    },
    {
      "epoch": 2.6043030869971937,
      "grad_norm": 0.6736369182740793,
      "learning_rate": 5e-06,
      "loss": 0.4933,
      "step": 870
    },
    {
      "epoch": 2.634237605238541,
      "grad_norm": 1.0093672073573243,
      "learning_rate": 5e-06,
      "loss": 0.4914,
      "step": 880
    },
    {
      "epoch": 2.664172123479888,
      "grad_norm": 0.7192705570737601,
      "learning_rate": 5e-06,
      "loss": 0.4975,
      "step": 890
    },
    {
      "epoch": 2.694106641721235,
      "grad_norm": 0.6676469165153502,
      "learning_rate": 5e-06,
      "loss": 0.5002,
      "step": 900
    },
    {
      "epoch": 2.724041159962582,
      "grad_norm": 0.7021525478180678,
      "learning_rate": 5e-06,
      "loss": 0.4938,
      "step": 910
    },
    {
      "epoch": 2.753975678203929,
      "grad_norm": 0.6608364791732315,
      "learning_rate": 5e-06,
      "loss": 0.495,
      "step": 920
    },
    {
      "epoch": 2.7839101964452757,
      "grad_norm": 0.6911790879608518,
      "learning_rate": 5e-06,
      "loss": 0.5007,
      "step": 930
    },
    {
      "epoch": 2.8138447146866232,
      "grad_norm": 0.6768871726531243,
      "learning_rate": 5e-06,
      "loss": 0.4986,
      "step": 940
    },
    {
      "epoch": 2.84377923292797,
      "grad_norm": 0.7274416613317195,
      "learning_rate": 5e-06,
      "loss": 0.4981,
      "step": 950
    },
    {
      "epoch": 2.8737137511693174,
      "grad_norm": 0.875210919144357,
      "learning_rate": 5e-06,
      "loss": 0.5002,
      "step": 960
    },
    {
      "epoch": 2.903648269410664,
      "grad_norm": 0.7725107537562403,
      "learning_rate": 5e-06,
      "loss": 0.4956,
      "step": 970
    },
    {
      "epoch": 2.933582787652011,
      "grad_norm": 0.9023853617091222,
      "learning_rate": 5e-06,
      "loss": 0.5013,
      "step": 980
    },
    {
      "epoch": 2.963517305893358,
      "grad_norm": 0.7151716284570461,
      "learning_rate": 5e-06,
      "loss": 0.5029,
      "step": 990
    },
    {
      "epoch": 2.9934518241347052,
      "grad_norm": 0.7126618209321779,
      "learning_rate": 5e-06,
      "loss": 0.5039,
      "step": 1000
    },
    {
      "epoch": 2.999438727782975,
      "eval_loss": 0.6349337697029114,
      "eval_runtime": 512.9128,
      "eval_samples_per_second": 17.549,
      "eval_steps_per_second": 0.55,
      "step": 1002
    },
    {
      "epoch": 2.999438727782975,
      "step": 1002,
      "total_flos": 3818092983484416.0,
      "train_loss": 0.5625353066507214,
      "train_runtime": 90507.5636,
      "train_samples_per_second": 5.668,
      "train_steps_per_second": 0.011
    }
  ],
  "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": 3818092983484416.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}