{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.996011396011396,
  "eval_steps": 500,
  "global_step": 1314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 15.125983078744758,
      "learning_rate": 3.787878787878788e-07,
      "loss": 0.8308,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 5.106211060706855,
      "learning_rate": 7.575757575757576e-07,
      "loss": 0.8107,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 1.6409244850292617,
      "learning_rate": 1.1363636363636364e-06,
      "loss": 0.7552,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 1.0049951242628896,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.7308,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.9157452499624658,
      "learning_rate": 1.8939393939393941e-06,
      "loss": 0.7158,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.8628839965574723,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.6902,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.7308412022540539,
      "learning_rate": 2.6515151515151514e-06,
      "loss": 0.6844,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.868821693248259,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.6843,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.7991099571783645,
      "learning_rate": 3.409090909090909e-06,
      "loss": 0.6651,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.8494515975438381,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 0.6616,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.6688481290670764,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.6479,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.5229831628334457,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.6519,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.37649939369854807,
      "learning_rate": 4.924242424242425e-06,
      "loss": 0.6501,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.3422897131579416,
      "learning_rate": 4.999446185282947e-06,
      "loss": 0.6506,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.3241007372983375,
      "learning_rate": 4.997196742099456e-06,
      "loss": 0.6424,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.32292063048607617,
      "learning_rate": 4.993218644771816e-06,
      "loss": 0.6469,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.3604169283465372,
      "learning_rate": 4.987514703353798e-06,
      "loss": 0.6383,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.31383488263493586,
      "learning_rate": 4.980088947003254e-06,
      "loss": 0.6435,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.30348082668380777,
      "learning_rate": 4.970946621135998e-06,
      "loss": 0.6357,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.3160900714261373,
      "learning_rate": 4.960094183720539e-06,
      "loss": 0.6436,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.3042936930583843,
      "learning_rate": 4.947539300716295e-06,
      "loss": 0.6396,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.3075635512158751,
      "learning_rate": 4.933290840658501e-06,
      "loss": 0.6432,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.38940758621282484,
      "learning_rate": 4.917358868393641e-06,
      "loss": 0.6387,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.2941815609309389,
      "learning_rate": 4.8997546379698304e-06,
      "loss": 0.6344,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.33217327438419464,
      "learning_rate": 4.880490584687161e-06,
      "loss": 0.6392,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.30544876573581253,
      "learning_rate": 4.8595803163136455e-06,
      "loss": 0.6372,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.31345899291427864,
      "learning_rate": 4.837038603472932e-06,
      "loss": 0.6343,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.31662570229165077,
      "learning_rate": 4.812881369210625e-06,
      "loss": 0.6449,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3224781690706616,
      "learning_rate": 4.787125677746528e-06,
      "loss": 0.6335,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2866537117310808,
      "learning_rate": 4.75978972242081e-06,
      "loss": 0.6314,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.29647749002081614,
      "learning_rate": 4.730892812842562e-06,
      "loss": 0.6312,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.3324269942634098,
      "learning_rate": 4.700455361249849e-06,
      "loss": 0.6317,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.29925598379381463,
      "learning_rate": 4.668498868090891e-06,
      "loss": 0.6283,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.3154305379821916,
      "learning_rate": 4.635045906836541e-06,
      "loss": 0.6341,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.3199649642865213,
      "learning_rate": 4.6001201080348096e-06,
      "loss": 0.6411,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.32037054661311365,
      "learning_rate": 4.563746142618686e-06,
      "loss": 0.6328,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.3318697710361171,
      "learning_rate": 4.525949704479052e-06,
      "loss": 0.6265,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3246050423002289,
      "learning_rate": 4.486757492314996e-06,
      "loss": 0.6387,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.30506469521512686,
      "learning_rate": 4.446197190774345e-06,
      "loss": 0.6372,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.3085994412780229,
      "learning_rate": 4.404297450897755e-06,
      "loss": 0.6404,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.2749956429354596,
      "learning_rate": 4.361087869880142e-06,
      "loss": 0.6366,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.2936678775920064,
      "learning_rate": 4.31659897016378e-06,
      "loss": 0.6234,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.3336527691105597,
      "learning_rate": 4.270862177877817e-06,
      "loss": 0.6365,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.627018392086029,
      "eval_runtime": 440.9493,
      "eval_samples_per_second": 26.813,
      "eval_steps_per_second": 0.42,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.3118348041353063,
      "learning_rate": 4.2239098006394365e-06,
      "loss": 0.6498,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.3256449525170415,
      "learning_rate": 4.175775004732371e-06,
      "loss": 0.6077,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.32702392722031254,
      "learning_rate": 4.1264917916788475e-06,
      "loss": 0.6013,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.28050319740758334,
      "learning_rate": 4.07609497422155e-06,
      "loss": 0.6023,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.3000718527011783,
      "learning_rate": 4.024620151732549e-06,
      "loss": 0.6098,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.308697561622843,
      "learning_rate": 3.972103685066567e-06,
      "loss": 0.6147,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.27367615993888206,
      "learning_rate": 3.9185826708763455e-06,
      "loss": 0.6045,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.3131261213067205,
      "learning_rate": 3.86409491540827e-06,
      "loss": 0.6023,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.3082714238602967,
      "learning_rate": 3.8086789077967335e-06,
      "loss": 0.6079,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.2896155404732298,
      "learning_rate": 3.7523737928761345e-06,
      "loss": 0.6009,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.2949864594007117,
      "learning_rate": 3.695219343529694e-06,
      "loss": 0.611,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.29341498947539596,
      "learning_rate": 3.637255932594635e-06,
      "loss": 0.6074,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.28661195720596744,
      "learning_rate": 3.578524504343561e-06,
      "loss": 0.609,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.3026330084600481,
      "learning_rate": 3.5190665455621842e-06,
      "loss": 0.6029,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2658709316204282,
      "learning_rate": 3.458924056243836e-06,
      "loss": 0.6012,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.2684949299976577,
      "learning_rate": 3.3981395199214567e-06,
      "loss": 0.6012,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.299097522611276,
      "learning_rate": 3.336755873658014e-06,
      "loss": 0.6066,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.3135014047131652,
      "learning_rate": 3.274816477716569e-06,
      "loss": 0.6066,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.2934151051131123,
      "learning_rate": 3.2123650849313897e-06,
      "loss": 0.6093,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.2830185953651649,
      "learning_rate": 3.149445809801768e-06,
      "loss": 0.607,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.29912134559967146,
      "learning_rate": 3.0861030973303573e-06,
      "loss": 0.6019,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.2935467188047777,
      "learning_rate": 3.0223816916280574e-06,
      "loss": 0.5996,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.27437783484675404,
      "learning_rate": 2.9583266043075992e-06,
      "loss": 0.5994,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.29614627246404845,
      "learning_rate": 2.893983082688191e-06,
      "loss": 0.607,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.26516288075680605,
      "learning_rate": 2.8293965778336474e-06,
      "loss": 0.5956,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.32640130516394655,
      "learning_rate": 2.7646127124466114e-06,
      "loss": 0.5994,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.28248568655010486,
      "learning_rate": 2.6996772486415277e-06,
      "loss": 0.6152,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.2898149513994004,
      "learning_rate": 2.6346360556191326e-06,
      "loss": 0.6022,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.28975370189373456,
      "learning_rate": 2.569535077265311e-06,
      "loss": 0.6065,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.2962120678740453,
      "learning_rate": 2.504420299697193e-06,
      "loss": 0.5996,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.2880350725196617,
      "learning_rate": 2.4393377187794146e-06,
      "loss": 0.6005,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.28966271136759913,
      "learning_rate": 2.3743333076334986e-06,
      "loss": 0.5978,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.283507079919438,
      "learning_rate": 2.309452984163299e-06,
      "loss": 0.6019,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.29529607918677664,
      "learning_rate": 2.2447425786194495e-06,
      "loss": 0.5985,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.28319448713724227,
      "learning_rate": 2.1802478012257296e-06,
      "loss": 0.6056,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.2726643263502109,
      "learning_rate": 2.1160142098902133e-06,
      "loss": 0.603,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.27617806287641067,
      "learning_rate": 2.052087178024016e-06,
      "loss": 0.5898,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.29198691591599185,
      "learning_rate": 1.9885118624903573e-06,
      "loss": 0.5976,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.27844261589599106,
      "learning_rate": 1.9253331717066014e-06,
      "loss": 0.5954,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.2738167375905431,
      "learning_rate": 1.8625957339217828e-06,
      "loss": 0.5992,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.2885459820853412,
      "learning_rate": 1.8003438656920464e-06,
      "loss": 0.6038,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.29048300848707215,
      "learning_rate": 1.73862154057626e-06,
      "loss": 0.6017,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.27617825592983636,
      "learning_rate": 1.6774723580739071e-06,
      "loss": 0.6029,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.3013766038530734,
      "learning_rate": 1.6169395128272203e-06,
      "loss": 0.6006,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6203941106796265,
      "eval_runtime": 445.3298,
      "eval_samples_per_second": 26.549,
      "eval_steps_per_second": 0.415,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.26563524661619237,
      "learning_rate": 1.5570657641092865e-06,
      "loss": 0.6231,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.2794923155415762,
      "learning_rate": 1.4978934056196946e-06,
      "loss": 0.5694,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.2851227269905178,
      "learning_rate": 1.4394642356090566e-06,
      "loss": 0.5852,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.28857955805833607,
      "learning_rate": 1.3818195273535004e-06,
      "loss": 0.5831,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.27216092884865906,
      "learning_rate": 1.3250000000000007e-06,
      "loss": 0.5862,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.27002519179009965,
      "learning_rate": 1.2690457898031274e-06,
      "loss": 0.5837,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.2818496425678644,
      "learning_rate": 1.2139964217735515e-06,
      "loss": 0.5784,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.2701221946191815,
      "learning_rate": 1.1598907817583052e-06,
      "loss": 0.5793,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.27574524946055073,
      "learning_rate": 1.1067670889725543e-06,
      "loss": 0.5842,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.28332150705773357,
      "learning_rate": 1.0546628690022486e-06,
      "loss": 0.583,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.28208882210607483,
      "learning_rate": 1.0036149272967555e-06,
      "loss": 0.5727,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.27609878433695273,
      "learning_rate": 9.536593231701712e-07,
      "loss": 0.5816,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.2723619847411987,
      "learning_rate": 9.048313443296946e-07,
      "loss": 0.5818,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.2783655922018766,
      "learning_rate": 8.571654819490528e-07,
      "loss": 0.5793,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.28395769221124467,
      "learning_rate": 8.106954063045759e-07,
      "loss": 0.5823,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.26619297702415606,
      "learning_rate": 7.654539429911393e-07,
      "loss": 0.5837,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.26007555166748264,
      "learning_rate": 7.21473049734782e-07,
      "loss": 0.5813,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.29062347852432735,
      "learning_rate": 6.787837938183603e-07,
      "loss": 0.5805,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.27001754809897044,
      "learning_rate": 6.374163301361986e-07,
      "loss": 0.5887,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.2641873787984356,
      "learning_rate": 5.973998798932351e-07,
      "loss": 0.5918,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.2678841619133812,
      "learning_rate": 5.587627099637106e-07,
      "loss": 0.5871,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.2640549717266149,
      "learning_rate": 5.215321129239688e-07,
      "loss": 0.5844,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.28491735406972796,
      "learning_rate": 4.857343877734967e-07,
      "loss": 0.5912,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.2642156408420045,
      "learning_rate": 4.5139482135779634e-07,
      "loss": 0.5842,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.26299866058202587,
      "learning_rate": 4.185376705062326e-07,
      "loss": 0.5824,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.27022994903364983,
      "learning_rate": 3.871861448974572e-07,
      "loss": 0.5816,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.26101508013637187,
      "learning_rate": 3.5736239066452864e-07,
      "loss": 0.5813,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.27121387507355627,
      "learning_rate": 3.290874747512937e-07,
      "loss": 0.5815,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.2738045404235721,
      "learning_rate": 3.023813700310924e-07,
      "loss": 0.5822,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.2721835115660428,
      "learning_rate": 2.772629411982938e-07,
      "loss": 0.5855,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.2622528907504856,
      "learning_rate": 2.5374993144262513e-07,
      "loss": 0.5806,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.2577523362544388,
      "learning_rate": 2.3185894991571576e-07,
      "loss": 0.5815,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.26363889309421545,
      "learning_rate": 2.1160545999870025e-07,
      "loss": 0.5846,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.2598425521048642,
      "learning_rate": 1.9300376837917695e-07,
      "loss": 0.5878,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.2609543392451375,
      "learning_rate": 1.7606701494522731e-07,
      "loss": 0.5776,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.254572723920624,
      "learning_rate": 1.6080716350364643e-07,
      "loss": 0.576,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.2606448147342431,
      "learning_rate": 1.472349933289327e-07,
      "loss": 0.591,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.2608934236555304,
      "learning_rate": 1.35360091549008e-07,
      "loss": 0.5879,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.26384395992199977,
      "learning_rate": 1.2519084637305096e-07,
      "loss": 0.5849,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.2665820989189118,
      "learning_rate": 1.1673444116622113e-07,
      "loss": 0.5859,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.2621212407779067,
      "learning_rate": 1.0999684937546469e-07,
      "loss": 0.576,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.2631271259876569,
      "learning_rate": 1.0498283030998208e-07,
      "loss": 0.5759,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.27152984911342587,
      "learning_rate": 1.0169592577934177e-07,
      "loss": 0.5773,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.26902594864871143,
      "learning_rate": 1.0013845759161108e-07,
      "loss": 0.5874,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6206473112106323,
      "eval_runtime": 443.5397,
      "eval_samples_per_second": 26.656,
      "eval_steps_per_second": 0.417,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.6148462799949007,
      "train_runtime": 70693.2258,
      "train_samples_per_second": 9.532,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1314,
  "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": 2755219238682624.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}