{
  "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": 0.9639704104941377,
      "learning_rate": 8e-06,
      "loss": 0.7439,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.8442173824916553,
      "learning_rate": 8e-06,
      "loss": 0.6913,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9135177104158955,
      "learning_rate": 8e-06,
      "loss": 0.6706,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.7447503678432672,
      "learning_rate": 8e-06,
      "loss": 0.6689,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.44266019319258165,
      "learning_rate": 8e-06,
      "loss": 0.6641,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.30998631234245,
      "learning_rate": 8e-06,
      "loss": 0.6461,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.3164751503953061,
      "learning_rate": 8e-06,
      "loss": 0.6459,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.3350368477653695,
      "learning_rate": 8e-06,
      "loss": 0.6508,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.3086185193667254,
      "learning_rate": 8e-06,
      "loss": 0.6363,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.33448171137595584,
      "learning_rate": 8e-06,
      "loss": 0.6379,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.3384106640783101,
      "learning_rate": 8e-06,
      "loss": 0.6294,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.30260557253018994,
      "learning_rate": 8e-06,
      "loss": 0.6376,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.33298272040177757,
      "learning_rate": 8e-06,
      "loss": 0.6387,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.31265997710460536,
      "learning_rate": 8e-06,
      "loss": 0.6408,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.31516199031803915,
      "learning_rate": 8e-06,
      "loss": 0.6333,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.31682011905006013,
      "learning_rate": 8e-06,
      "loss": 0.6386,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.3564513676586145,
      "learning_rate": 8e-06,
      "loss": 0.6303,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3306179870426032,
      "learning_rate": 8e-06,
      "loss": 0.6359,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.33474028648939197,
      "learning_rate": 8e-06,
      "loss": 0.6286,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.3206144090448144,
      "learning_rate": 8e-06,
      "loss": 0.6365,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.3177671154762098,
      "learning_rate": 8e-06,
      "loss": 0.6329,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.3021654059092019,
      "learning_rate": 8e-06,
      "loss": 0.6366,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.3290669088275951,
      "learning_rate": 8e-06,
      "loss": 0.6322,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.30424722815187283,
      "learning_rate": 8e-06,
      "loss": 0.628,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.3474823315395405,
      "learning_rate": 8e-06,
      "loss": 0.6329,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3168891366378092,
      "learning_rate": 8e-06,
      "loss": 0.6312,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.34553565431951916,
      "learning_rate": 8e-06,
      "loss": 0.6283,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.3332271782588716,
      "learning_rate": 8e-06,
      "loss": 0.6391,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3880170201690876,
      "learning_rate": 8e-06,
      "loss": 0.6278,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.3130673004887942,
      "learning_rate": 8e-06,
      "loss": 0.6258,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.3358637038063554,
      "learning_rate": 8e-06,
      "loss": 0.6257,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.3399489989506044,
      "learning_rate": 8e-06,
      "loss": 0.6263,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.38771766102214283,
      "learning_rate": 8e-06,
      "loss": 0.6229,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.3283255856874223,
      "learning_rate": 8e-06,
      "loss": 0.6286,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.3268975490281503,
      "learning_rate": 8e-06,
      "loss": 0.6357,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.32733368412799924,
      "learning_rate": 8e-06,
      "loss": 0.6276,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.3624716188998123,
      "learning_rate": 8e-06,
      "loss": 0.6212,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3061531887849296,
      "learning_rate": 8e-06,
      "loss": 0.6336,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.36678334857855494,
      "learning_rate": 8e-06,
      "loss": 0.6321,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.34292337617119184,
      "learning_rate": 8e-06,
      "loss": 0.6352,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.33405894563773253,
      "learning_rate": 8e-06,
      "loss": 0.6315,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.3164130023383584,
      "learning_rate": 8e-06,
      "loss": 0.6185,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.3977987648498147,
      "learning_rate": 8e-06,
      "loss": 0.6314,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6220688819885254,
      "eval_runtime": 442.3463,
      "eval_samples_per_second": 26.728,
      "eval_steps_per_second": 0.418,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.41535494548627566,
      "learning_rate": 8e-06,
      "loss": 0.6423,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.3735476403023979,
      "learning_rate": 8e-06,
      "loss": 0.5863,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.3183198999243994,
      "learning_rate": 8e-06,
      "loss": 0.5799,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.3175544461491631,
      "learning_rate": 8e-06,
      "loss": 0.5808,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.32855484029978815,
      "learning_rate": 8e-06,
      "loss": 0.5884,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.3222089893505811,
      "learning_rate": 8e-06,
      "loss": 0.5935,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.34758032863197696,
      "learning_rate": 8e-06,
      "loss": 0.5839,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.3196612744024533,
      "learning_rate": 8e-06,
      "loss": 0.5819,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.2975047803907781,
      "learning_rate": 8e-06,
      "loss": 0.5876,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.3241282573148342,
      "learning_rate": 8e-06,
      "loss": 0.5809,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.3304353844650285,
      "learning_rate": 8e-06,
      "loss": 0.5911,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.3216443108997831,
      "learning_rate": 8e-06,
      "loss": 0.5878,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.28632058626541573,
      "learning_rate": 8e-06,
      "loss": 0.5896,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.32577387421456516,
      "learning_rate": 8e-06,
      "loss": 0.5839,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.29722092652806653,
      "learning_rate": 8e-06,
      "loss": 0.5824,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.30497645231514076,
      "learning_rate": 8e-06,
      "loss": 0.5821,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.3356906043288017,
      "learning_rate": 8e-06,
      "loss": 0.5877,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.3197713793402043,
      "learning_rate": 8e-06,
      "loss": 0.5878,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.3184351238575717,
      "learning_rate": 8e-06,
      "loss": 0.5906,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.38972545692696076,
      "learning_rate": 8e-06,
      "loss": 0.5887,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.33229014658178607,
      "learning_rate": 8e-06,
      "loss": 0.5836,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.31309389506608065,
      "learning_rate": 8e-06,
      "loss": 0.5817,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.370537402842656,
      "learning_rate": 8e-06,
      "loss": 0.5814,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.3857314872058338,
      "learning_rate": 8e-06,
      "loss": 0.5889,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.2943021984178184,
      "learning_rate": 8e-06,
      "loss": 0.5778,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.33551835524618123,
      "learning_rate": 8e-06,
      "loss": 0.5816,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.3129729258150647,
      "learning_rate": 8e-06,
      "loss": 0.5971,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.3281106159791198,
      "learning_rate": 8e-06,
      "loss": 0.5844,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.30736214724993627,
      "learning_rate": 8e-06,
      "loss": 0.5889,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.31301654778685145,
      "learning_rate": 8e-06,
      "loss": 0.5822,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.3832408006580538,
      "learning_rate": 8e-06,
      "loss": 0.5834,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.2881229879737456,
      "learning_rate": 8e-06,
      "loss": 0.5809,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.33079937680811516,
      "learning_rate": 8e-06,
      "loss": 0.5846,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.3121300231001629,
      "learning_rate": 8e-06,
      "loss": 0.5812,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.32381306898398965,
      "learning_rate": 8e-06,
      "loss": 0.5884,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.3132261319703939,
      "learning_rate": 8e-06,
      "loss": 0.586,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.3109108661140414,
      "learning_rate": 8e-06,
      "loss": 0.5732,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.3378524689763439,
      "learning_rate": 8e-06,
      "loss": 0.5808,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.3682104905353802,
      "learning_rate": 8e-06,
      "loss": 0.5787,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.3166688390782565,
      "learning_rate": 8e-06,
      "loss": 0.5824,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.3390663411975044,
      "learning_rate": 8e-06,
      "loss": 0.5869,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.30499332586283723,
      "learning_rate": 8e-06,
      "loss": 0.5851,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.31339130972566714,
      "learning_rate": 8e-06,
      "loss": 0.5864,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.33397359259310516,
      "learning_rate": 8e-06,
      "loss": 0.5839,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6177216172218323,
      "eval_runtime": 442.0957,
      "eval_samples_per_second": 26.743,
      "eval_steps_per_second": 0.418,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.3942199397790381,
      "learning_rate": 8e-06,
      "loss": 0.5988,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.3622133382325446,
      "learning_rate": 8e-06,
      "loss": 0.529,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.3051101757043286,
      "learning_rate": 8e-06,
      "loss": 0.5431,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.31808930925704476,
      "learning_rate": 8e-06,
      "loss": 0.5415,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.3053872915751511,
      "learning_rate": 8e-06,
      "loss": 0.5444,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.30464054596272677,
      "learning_rate": 8e-06,
      "loss": 0.5431,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.3314113247332846,
      "learning_rate": 8e-06,
      "loss": 0.538,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.2925179652880053,
      "learning_rate": 8e-06,
      "loss": 0.5388,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.30911668605275777,
      "learning_rate": 8e-06,
      "loss": 0.544,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.3199475341742108,
      "learning_rate": 8e-06,
      "loss": 0.5438,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.32055573087102224,
      "learning_rate": 8e-06,
      "loss": 0.5341,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.3186808852851889,
      "learning_rate": 8e-06,
      "loss": 0.543,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.33549794419622847,
      "learning_rate": 8e-06,
      "loss": 0.5435,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.34091571131374626,
      "learning_rate": 8e-06,
      "loss": 0.541,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.3040233000106589,
      "learning_rate": 8e-06,
      "loss": 0.5441,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.32578198574988587,
      "learning_rate": 8e-06,
      "loss": 0.5454,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.30647179694911697,
      "learning_rate": 8e-06,
      "loss": 0.5438,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.3183190725429563,
      "learning_rate": 8e-06,
      "loss": 0.5431,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.3062188640144124,
      "learning_rate": 8e-06,
      "loss": 0.5512,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.3017755578758498,
      "learning_rate": 8e-06,
      "loss": 0.5539,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.33019353573088506,
      "learning_rate": 8e-06,
      "loss": 0.5494,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.2852464261424503,
      "learning_rate": 8e-06,
      "loss": 0.5476,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.3500005782241224,
      "learning_rate": 8e-06,
      "loss": 0.5535,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.35098221183935024,
      "learning_rate": 8e-06,
      "loss": 0.5477,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.30922704201508944,
      "learning_rate": 8e-06,
      "loss": 0.5458,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.3082574345947817,
      "learning_rate": 8e-06,
      "loss": 0.5455,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.33169661267365713,
      "learning_rate": 8e-06,
      "loss": 0.5452,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.315011239745189,
      "learning_rate": 8e-06,
      "loss": 0.5458,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.38634457368273284,
      "learning_rate": 8e-06,
      "loss": 0.547,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.308611576841766,
      "learning_rate": 8e-06,
      "loss": 0.5495,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.3061797999061911,
      "learning_rate": 8e-06,
      "loss": 0.5449,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.3626848717846874,
      "learning_rate": 8e-06,
      "loss": 0.5462,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.3447009825960258,
      "learning_rate": 8e-06,
      "loss": 0.5494,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.2897396756037604,
      "learning_rate": 8e-06,
      "loss": 0.5526,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.32027753437812284,
      "learning_rate": 8e-06,
      "loss": 0.543,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.32454406486781057,
      "learning_rate": 8e-06,
      "loss": 0.5415,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.3600363939988387,
      "learning_rate": 8e-06,
      "loss": 0.5559,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.30006980036728953,
      "learning_rate": 8e-06,
      "loss": 0.5525,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.3297390936565714,
      "learning_rate": 8e-06,
      "loss": 0.5499,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.35731426271290295,
      "learning_rate": 8e-06,
      "loss": 0.551,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.3324101899396559,
      "learning_rate": 8e-06,
      "loss": 0.5415,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.34191471108090155,
      "learning_rate": 8e-06,
      "loss": 0.5419,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.33614143212531566,
      "learning_rate": 8e-06,
      "loss": 0.543,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.31863479804372463,
      "learning_rate": 8e-06,
      "loss": 0.5523,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6223628520965576,
      "eval_runtime": 442.7522,
      "eval_samples_per_second": 26.703,
      "eval_steps_per_second": 0.418,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.5901586229216925,
      "train_runtime": 70551.5379,
      "train_samples_per_second": 9.551,
      "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
}