{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 833,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012004801920768308,
      "grad_norm": 0.3538109064102173,
      "learning_rate": 9.879951980792317e-05,
      "loss": 2.3075,
      "step": 10
    },
    {
      "epoch": 0.024009603841536616,
      "grad_norm": 0.3431814908981323,
      "learning_rate": 9.759903961584634e-05,
      "loss": 2.1468,
      "step": 20
    },
    {
      "epoch": 0.03601440576230492,
      "grad_norm": 0.6265680193901062,
      "learning_rate": 9.639855942376951e-05,
      "loss": 2.0353,
      "step": 30
    },
    {
      "epoch": 0.04801920768307323,
      "grad_norm": 0.3244292736053467,
      "learning_rate": 9.519807923169268e-05,
      "loss": 2.0219,
      "step": 40
    },
    {
      "epoch": 0.060024009603841535,
      "grad_norm": 0.6210302114486694,
      "learning_rate": 9.399759903961585e-05,
      "loss": 1.9809,
      "step": 50
    },
    {
      "epoch": 0.07202881152460984,
      "grad_norm": 0.4695661962032318,
      "learning_rate": 9.279711884753903e-05,
      "loss": 1.9376,
      "step": 60
    },
    {
      "epoch": 0.08403361344537816,
      "grad_norm": 0.27379557490348816,
      "learning_rate": 9.159663865546218e-05,
      "loss": 1.923,
      "step": 70
    },
    {
      "epoch": 0.09603841536614646,
      "grad_norm": 0.4497829079627991,
      "learning_rate": 9.039615846338536e-05,
      "loss": 1.9875,
      "step": 80
    },
    {
      "epoch": 0.10804321728691477,
      "grad_norm": 0.3675350844860077,
      "learning_rate": 8.919567827130852e-05,
      "loss": 1.953,
      "step": 90
    },
    {
      "epoch": 0.12004801920768307,
      "grad_norm": 0.293821781873703,
      "learning_rate": 8.79951980792317e-05,
      "loss": 1.8549,
      "step": 100
    },
    {
      "epoch": 0.12004801920768307,
      "eval_loss": 1.889587640762329,
      "eval_runtime": 39.6181,
      "eval_samples_per_second": 25.241,
      "eval_steps_per_second": 4.215,
      "step": 100
    },
    {
      "epoch": 0.13205282112845138,
      "grad_norm": 0.25892049074172974,
      "learning_rate": 8.679471788715487e-05,
      "loss": 1.8372,
      "step": 110
    },
    {
      "epoch": 0.14405762304921968,
      "grad_norm": 0.33091431856155396,
      "learning_rate": 8.559423769507804e-05,
      "loss": 1.9107,
      "step": 120
    },
    {
      "epoch": 0.15606242496998798,
      "grad_norm": 0.3052417039871216,
      "learning_rate": 8.43937575030012e-05,
      "loss": 1.8123,
      "step": 130
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 0.3017849028110504,
      "learning_rate": 8.319327731092437e-05,
      "loss": 1.8966,
      "step": 140
    },
    {
      "epoch": 0.18007202881152462,
      "grad_norm": 0.28657111525535583,
      "learning_rate": 8.199279711884754e-05,
      "loss": 1.8395,
      "step": 150
    },
    {
      "epoch": 0.19207683073229292,
      "grad_norm": 0.3324660062789917,
      "learning_rate": 8.079231692677071e-05,
      "loss": 1.8841,
      "step": 160
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.28194233775138855,
      "learning_rate": 7.959183673469388e-05,
      "loss": 1.8627,
      "step": 170
    },
    {
      "epoch": 0.21608643457382953,
      "grad_norm": 0.45277833938598633,
      "learning_rate": 7.839135654261706e-05,
      "loss": 1.8989,
      "step": 180
    },
    {
      "epoch": 0.22809123649459784,
      "grad_norm": 0.3656202256679535,
      "learning_rate": 7.719087635054022e-05,
      "loss": 1.911,
      "step": 190
    },
    {
      "epoch": 0.24009603841536614,
      "grad_norm": 0.33644187450408936,
      "learning_rate": 7.599039615846338e-05,
      "loss": 1.7805,
      "step": 200
    },
    {
      "epoch": 0.24009603841536614,
      "eval_loss": 1.8699440956115723,
      "eval_runtime": 39.0269,
      "eval_samples_per_second": 25.623,
      "eval_steps_per_second": 4.279,
      "step": 200
    },
    {
      "epoch": 0.25210084033613445,
      "grad_norm": 0.24649439752101898,
      "learning_rate": 7.478991596638657e-05,
      "loss": 1.841,
      "step": 210
    },
    {
      "epoch": 0.26410564225690275,
      "grad_norm": 0.30980348587036133,
      "learning_rate": 7.358943577430972e-05,
      "loss": 1.9065,
      "step": 220
    },
    {
      "epoch": 0.27611044417767105,
      "grad_norm": 0.2731610834598541,
      "learning_rate": 7.23889555822329e-05,
      "loss": 1.8713,
      "step": 230
    },
    {
      "epoch": 0.28811524609843936,
      "grad_norm": 0.3211459517478943,
      "learning_rate": 7.118847539015606e-05,
      "loss": 1.8719,
      "step": 240
    },
    {
      "epoch": 0.30012004801920766,
      "grad_norm": 0.3356248736381531,
      "learning_rate": 6.998799519807924e-05,
      "loss": 1.8211,
      "step": 250
    },
    {
      "epoch": 0.31212484993997597,
      "grad_norm": 0.35724079608917236,
      "learning_rate": 6.878751500600241e-05,
      "loss": 1.8773,
      "step": 260
    },
    {
      "epoch": 0.3241296518607443,
      "grad_norm": 0.5718697905540466,
      "learning_rate": 6.758703481392558e-05,
      "loss": 1.8231,
      "step": 270
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.32961568236351013,
      "learning_rate": 6.638655462184874e-05,
      "loss": 1.9494,
      "step": 280
    },
    {
      "epoch": 0.34813925570228094,
      "grad_norm": 0.3693414628505707,
      "learning_rate": 6.518607442977191e-05,
      "loss": 1.835,
      "step": 290
    },
    {
      "epoch": 0.36014405762304924,
      "grad_norm": 0.4198884665966034,
      "learning_rate": 6.398559423769508e-05,
      "loss": 1.8722,
      "step": 300
    },
    {
      "epoch": 0.36014405762304924,
      "eval_loss": 1.8641259670257568,
      "eval_runtime": 39.2717,
      "eval_samples_per_second": 25.464,
      "eval_steps_per_second": 4.252,
      "step": 300
    },
    {
      "epoch": 0.37214885954381755,
      "grad_norm": 0.3070141077041626,
      "learning_rate": 6.278511404561825e-05,
      "loss": 1.8771,
      "step": 310
    },
    {
      "epoch": 0.38415366146458585,
      "grad_norm": 0.43982160091400146,
      "learning_rate": 6.158463385354142e-05,
      "loss": 1.8954,
      "step": 320
    },
    {
      "epoch": 0.39615846338535415,
      "grad_norm": 0.2642657458782196,
      "learning_rate": 6.038415366146459e-05,
      "loss": 1.8977,
      "step": 330
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.25595635175704956,
      "learning_rate": 5.918367346938776e-05,
      "loss": 1.8949,
      "step": 340
    },
    {
      "epoch": 0.42016806722689076,
      "grad_norm": 0.27742770314216614,
      "learning_rate": 5.7983193277310935e-05,
      "loss": 1.8223,
      "step": 350
    },
    {
      "epoch": 0.43217286914765907,
      "grad_norm": 0.2831798791885376,
      "learning_rate": 5.6782713085234096e-05,
      "loss": 1.8477,
      "step": 360
    },
    {
      "epoch": 0.44417767106842737,
      "grad_norm": 0.3077690005302429,
      "learning_rate": 5.558223289315727e-05,
      "loss": 1.9376,
      "step": 370
    },
    {
      "epoch": 0.4561824729891957,
      "grad_norm": 0.5014916658401489,
      "learning_rate": 5.438175270108043e-05,
      "loss": 1.9241,
      "step": 380
    },
    {
      "epoch": 0.468187274909964,
      "grad_norm": 0.7313567399978638,
      "learning_rate": 5.31812725090036e-05,
      "loss": 1.8995,
      "step": 390
    },
    {
      "epoch": 0.4801920768307323,
      "grad_norm": 0.26589518785476685,
      "learning_rate": 5.1980792316926776e-05,
      "loss": 1.95,
      "step": 400
    },
    {
      "epoch": 0.4801920768307323,
      "eval_loss": 1.8611316680908203,
      "eval_runtime": 39.4525,
      "eval_samples_per_second": 25.347,
      "eval_steps_per_second": 4.233,
      "step": 400
    },
    {
      "epoch": 0.4921968787515006,
      "grad_norm": 0.293312668800354,
      "learning_rate": 5.078031212484994e-05,
      "loss": 1.8592,
      "step": 410
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 0.35831350088119507,
      "learning_rate": 4.957983193277311e-05,
      "loss": 1.9295,
      "step": 420
    },
    {
      "epoch": 0.5162064825930373,
      "grad_norm": 0.33949533104896545,
      "learning_rate": 4.837935174069628e-05,
      "loss": 1.8581,
      "step": 430
    },
    {
      "epoch": 0.5282112845138055,
      "grad_norm": 0.5358735918998718,
      "learning_rate": 4.717887154861945e-05,
      "loss": 1.8824,
      "step": 440
    },
    {
      "epoch": 0.5402160864345739,
      "grad_norm": 0.3915724456310272,
      "learning_rate": 4.5978391356542624e-05,
      "loss": 1.8699,
      "step": 450
    },
    {
      "epoch": 0.5522208883553421,
      "grad_norm": 0.3336695730686188,
      "learning_rate": 4.477791116446579e-05,
      "loss": 1.9749,
      "step": 460
    },
    {
      "epoch": 0.5642256902761105,
      "grad_norm": 0.3887428641319275,
      "learning_rate": 4.3577430972388954e-05,
      "loss": 1.8134,
      "step": 470
    },
    {
      "epoch": 0.5762304921968787,
      "grad_norm": 0.26423540711402893,
      "learning_rate": 4.237695078031212e-05,
      "loss": 1.8495,
      "step": 480
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.30970582365989685,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.8386,
      "step": 490
    },
    {
      "epoch": 0.6002400960384153,
      "grad_norm": 0.38180047273635864,
      "learning_rate": 3.9975990396158466e-05,
      "loss": 1.8729,
      "step": 500
    },
    {
      "epoch": 0.6002400960384153,
      "eval_loss": 1.8590781688690186,
      "eval_runtime": 39.0438,
      "eval_samples_per_second": 25.612,
      "eval_steps_per_second": 4.277,
      "step": 500
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 0.4111509621143341,
      "learning_rate": 3.8775510204081634e-05,
      "loss": 1.833,
      "step": 510
    },
    {
      "epoch": 0.6242496998799519,
      "grad_norm": 0.515201210975647,
      "learning_rate": 3.75750300120048e-05,
      "loss": 1.8744,
      "step": 520
    },
    {
      "epoch": 0.6362545018007203,
      "grad_norm": 0.2900288701057434,
      "learning_rate": 3.637454981992797e-05,
      "loss": 1.8364,
      "step": 530
    },
    {
      "epoch": 0.6482593037214885,
      "grad_norm": 0.2963515520095825,
      "learning_rate": 3.517406962785114e-05,
      "loss": 1.8469,
      "step": 540
    },
    {
      "epoch": 0.6602641056422569,
      "grad_norm": 0.41035813093185425,
      "learning_rate": 3.3973589435774314e-05,
      "loss": 1.9474,
      "step": 550
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.246292382478714,
      "learning_rate": 3.277310924369748e-05,
      "loss": 1.8128,
      "step": 560
    },
    {
      "epoch": 0.6842737094837935,
      "grad_norm": 0.3911287188529968,
      "learning_rate": 3.157262905162065e-05,
      "loss": 1.8663,
      "step": 570
    },
    {
      "epoch": 0.6962785114045619,
      "grad_norm": 0.3035126328468323,
      "learning_rate": 3.037214885954382e-05,
      "loss": 1.8921,
      "step": 580
    },
    {
      "epoch": 0.7082833133253301,
      "grad_norm": 0.2977759540081024,
      "learning_rate": 2.917166866746699e-05,
      "loss": 1.8288,
      "step": 590
    },
    {
      "epoch": 0.7202881152460985,
      "grad_norm": 0.3059289753437042,
      "learning_rate": 2.797118847539016e-05,
      "loss": 1.8482,
      "step": 600
    },
    {
      "epoch": 0.7202881152460985,
      "eval_loss": 1.8568615913391113,
      "eval_runtime": 39.5808,
      "eval_samples_per_second": 25.265,
      "eval_steps_per_second": 4.219,
      "step": 600
    },
    {
      "epoch": 0.7322929171668667,
      "grad_norm": 0.36612552404403687,
      "learning_rate": 2.6770708283313327e-05,
      "loss": 1.8577,
      "step": 610
    },
    {
      "epoch": 0.7442977190876351,
      "grad_norm": 0.2968533933162689,
      "learning_rate": 2.5570228091236498e-05,
      "loss": 1.8295,
      "step": 620
    },
    {
      "epoch": 0.7563025210084033,
      "grad_norm": 0.40536123514175415,
      "learning_rate": 2.4369747899159663e-05,
      "loss": 1.9242,
      "step": 630
    },
    {
      "epoch": 0.7683073229291717,
      "grad_norm": 0.3592563271522522,
      "learning_rate": 2.3169267707082835e-05,
      "loss": 1.8677,
      "step": 640
    },
    {
      "epoch": 0.78031212484994,
      "grad_norm": 0.3828364908695221,
      "learning_rate": 2.1968787515006003e-05,
      "loss": 1.9055,
      "step": 650
    },
    {
      "epoch": 0.7923169267707083,
      "grad_norm": 0.26257479190826416,
      "learning_rate": 2.076830732292917e-05,
      "loss": 1.9383,
      "step": 660
    },
    {
      "epoch": 0.8043217286914766,
      "grad_norm": 0.3253800570964813,
      "learning_rate": 1.9567827130852343e-05,
      "loss": 1.8142,
      "step": 670
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.3129618167877197,
      "learning_rate": 1.836734693877551e-05,
      "loss": 1.8447,
      "step": 680
    },
    {
      "epoch": 0.8283313325330132,
      "grad_norm": 0.32753467559814453,
      "learning_rate": 1.7166866746698683e-05,
      "loss": 1.8617,
      "step": 690
    },
    {
      "epoch": 0.8403361344537815,
      "grad_norm": 0.28356197476387024,
      "learning_rate": 1.5966386554621848e-05,
      "loss": 1.768,
      "step": 700
    },
    {
      "epoch": 0.8403361344537815,
      "eval_loss": 1.8553369045257568,
      "eval_runtime": 39.3665,
      "eval_samples_per_second": 25.402,
      "eval_steps_per_second": 4.242,
      "step": 700
    },
    {
      "epoch": 0.8523409363745498,
      "grad_norm": 0.42871856689453125,
      "learning_rate": 1.4765906362545018e-05,
      "loss": 1.8756,
      "step": 710
    },
    {
      "epoch": 0.8643457382953181,
      "grad_norm": 0.32104918360710144,
      "learning_rate": 1.3565426170468188e-05,
      "loss": 1.8396,
      "step": 720
    },
    {
      "epoch": 0.8763505402160864,
      "grad_norm": 0.3462695777416229,
      "learning_rate": 1.2364945978391356e-05,
      "loss": 1.8499,
      "step": 730
    },
    {
      "epoch": 0.8883553421368547,
      "grad_norm": 0.38381311297416687,
      "learning_rate": 1.1164465786314526e-05,
      "loss": 1.8353,
      "step": 740
    },
    {
      "epoch": 0.9003601440576231,
      "grad_norm": 0.48733091354370117,
      "learning_rate": 9.963985594237696e-06,
      "loss": 1.8566,
      "step": 750
    },
    {
      "epoch": 0.9123649459783914,
      "grad_norm": 0.35725510120391846,
      "learning_rate": 8.763505402160866e-06,
      "loss": 1.9016,
      "step": 760
    },
    {
      "epoch": 0.9243697478991597,
      "grad_norm": 0.2945646047592163,
      "learning_rate": 7.563025210084033e-06,
      "loss": 1.7727,
      "step": 770
    },
    {
      "epoch": 0.936374549819928,
      "grad_norm": 0.2922873795032501,
      "learning_rate": 6.362545018007203e-06,
      "loss": 1.8482,
      "step": 780
    },
    {
      "epoch": 0.9483793517406963,
      "grad_norm": 0.29431605339050293,
      "learning_rate": 5.162064825930372e-06,
      "loss": 1.8867,
      "step": 790
    },
    {
      "epoch": 0.9603841536614646,
      "grad_norm": 0.32220232486724854,
      "learning_rate": 3.9615846338535415e-06,
      "loss": 1.8904,
      "step": 800
    },
    {
      "epoch": 0.9603841536614646,
      "eval_loss": 1.854928970336914,
      "eval_runtime": 39.3819,
      "eval_samples_per_second": 25.392,
      "eval_steps_per_second": 4.241,
      "step": 800
    },
    {
      "epoch": 0.9723889555822329,
      "grad_norm": 0.2991810142993927,
      "learning_rate": 2.7611044417767106e-06,
      "loss": 1.8523,
      "step": 810
    },
    {
      "epoch": 0.9843937575030012,
      "grad_norm": 0.3944421112537384,
      "learning_rate": 1.56062424969988e-06,
      "loss": 1.8502,
      "step": 820
    },
    {
      "epoch": 0.9963985594237695,
      "grad_norm": 0.3155655264854431,
      "learning_rate": 3.601440576230492e-07,
      "loss": 1.9278,
      "step": 830
    }
  ],
  "logging_steps": 10,
  "max_steps": 833,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3760243809940275e+17,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}