{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8148820326678767,
  "eval_steps": 200,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009074410163339383,
      "grad_norm": 16.44035557329009,
      "learning_rate": 1.5105740181268883e-07,
      "loss": 0.5313,
      "step": 10
    },
    {
      "epoch": 0.018148820326678767,
      "grad_norm": 13.589346550315073,
      "learning_rate": 3.0211480362537766e-07,
      "loss": 0.5264,
      "step": 20
    },
    {
      "epoch": 0.02722323049001815,
      "grad_norm": 8.801723774276022,
      "learning_rate": 4.5317220543806647e-07,
      "loss": 0.4906,
      "step": 30
    },
    {
      "epoch": 0.036297640653357534,
      "grad_norm": 7.796737259339279,
      "learning_rate": 6.042296072507553e-07,
      "loss": 0.4562,
      "step": 40
    },
    {
      "epoch": 0.045372050816696916,
      "grad_norm": 5.619286758257839,
      "learning_rate": 7.552870090634441e-07,
      "loss": 0.4272,
      "step": 50
    },
    {
      "epoch": 0.0544464609800363,
      "grad_norm": 5.239247505609891,
      "learning_rate": 9.063444108761329e-07,
      "loss": 0.3991,
      "step": 60
    },
    {
      "epoch": 0.06352087114337568,
      "grad_norm": 6.059965957962629,
      "learning_rate": 1.0574018126888218e-06,
      "loss": 0.3875,
      "step": 70
    },
    {
      "epoch": 0.07259528130671507,
      "grad_norm": 5.72161696835824,
      "learning_rate": 1.2084592145015106e-06,
      "loss": 0.3669,
      "step": 80
    },
    {
      "epoch": 0.08166969147005444,
      "grad_norm": 5.98089466352634,
      "learning_rate": 1.3595166163141997e-06,
      "loss": 0.3685,
      "step": 90
    },
    {
      "epoch": 0.09074410163339383,
      "grad_norm": 4.228944584834963,
      "learning_rate": 1.5105740181268883e-06,
      "loss": 0.3382,
      "step": 100
    },
    {
      "epoch": 0.0998185117967332,
      "grad_norm": 3.9947731454266164,
      "learning_rate": 1.6616314199395773e-06,
      "loss": 0.3319,
      "step": 110
    },
    {
      "epoch": 0.1088929219600726,
      "grad_norm": 5.346476060332237,
      "learning_rate": 1.8126888217522659e-06,
      "loss": 0.3308,
      "step": 120
    },
    {
      "epoch": 0.11796733212341198,
      "grad_norm": 6.012358120483266,
      "learning_rate": 1.963746223564955e-06,
      "loss": 0.3168,
      "step": 130
    },
    {
      "epoch": 0.12704174228675136,
      "grad_norm": 7.80716722713242,
      "learning_rate": 2.1148036253776437e-06,
      "loss": 0.3097,
      "step": 140
    },
    {
      "epoch": 0.13611615245009073,
      "grad_norm": 4.495582663557092,
      "learning_rate": 2.2658610271903325e-06,
      "loss": 0.3003,
      "step": 150
    },
    {
      "epoch": 0.14519056261343014,
      "grad_norm": 6.589727731945333,
      "learning_rate": 2.4169184290030213e-06,
      "loss": 0.3037,
      "step": 160
    },
    {
      "epoch": 0.1542649727767695,
      "grad_norm": 5.12141742766216,
      "learning_rate": 2.5679758308157105e-06,
      "loss": 0.2961,
      "step": 170
    },
    {
      "epoch": 0.16333938294010888,
      "grad_norm": 4.48757591654561,
      "learning_rate": 2.7190332326283993e-06,
      "loss": 0.2959,
      "step": 180
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 5.331379922324464,
      "learning_rate": 2.8700906344410877e-06,
      "loss": 0.2913,
      "step": 190
    },
    {
      "epoch": 0.18148820326678766,
      "grad_norm": 4.049954556040219,
      "learning_rate": 3.0211480362537765e-06,
      "loss": 0.2822,
      "step": 200
    },
    {
      "epoch": 0.18148820326678766,
      "eval_loss": 0.2889096438884735,
      "eval_runtime": 1382.3397,
      "eval_samples_per_second": 11.337,
      "eval_steps_per_second": 1.417,
      "step": 200
    },
    {
      "epoch": 0.19056261343012704,
      "grad_norm": 5.380256604861625,
      "learning_rate": 3.1722054380664657e-06,
      "loss": 0.2987,
      "step": 210
    },
    {
      "epoch": 0.1996370235934664,
      "grad_norm": 4.695280309658713,
      "learning_rate": 3.3232628398791546e-06,
      "loss": 0.286,
      "step": 220
    },
    {
      "epoch": 0.20871143375680581,
      "grad_norm": 7.410021678600578,
      "learning_rate": 3.474320241691843e-06,
      "loss": 0.2808,
      "step": 230
    },
    {
      "epoch": 0.2177858439201452,
      "grad_norm": 4.227606956439697,
      "learning_rate": 3.6253776435045317e-06,
      "loss": 0.2817,
      "step": 240
    },
    {
      "epoch": 0.22686025408348456,
      "grad_norm": 3.335480667199127,
      "learning_rate": 3.776435045317221e-06,
      "loss": 0.2742,
      "step": 250
    },
    {
      "epoch": 0.23593466424682397,
      "grad_norm": 4.4170121242119516,
      "learning_rate": 3.92749244712991e-06,
      "loss": 0.2746,
      "step": 260
    },
    {
      "epoch": 0.24500907441016334,
      "grad_norm": 3.7352741920625614,
      "learning_rate": 4.078549848942598e-06,
      "loss": 0.2709,
      "step": 270
    },
    {
      "epoch": 0.2540834845735027,
      "grad_norm": 3.3946306143266307,
      "learning_rate": 4.229607250755287e-06,
      "loss": 0.2717,
      "step": 280
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 3.829907219559702,
      "learning_rate": 4.380664652567977e-06,
      "loss": 0.2691,
      "step": 290
    },
    {
      "epoch": 0.27223230490018147,
      "grad_norm": 4.69527808808518,
      "learning_rate": 4.531722054380665e-06,
      "loss": 0.2633,
      "step": 300
    },
    {
      "epoch": 0.2813067150635209,
      "grad_norm": 2.6580155881938485,
      "learning_rate": 4.682779456193353e-06,
      "loss": 0.2621,
      "step": 310
    },
    {
      "epoch": 0.29038112522686027,
      "grad_norm": 2.6935512708763025,
      "learning_rate": 4.833836858006043e-06,
      "loss": 0.2643,
      "step": 320
    },
    {
      "epoch": 0.29945553539019965,
      "grad_norm": 3.4095865195690505,
      "learning_rate": 4.984894259818732e-06,
      "loss": 0.2595,
      "step": 330
    },
    {
      "epoch": 0.308529945553539,
      "grad_norm": 3.1660619521990836,
      "learning_rate": 4.9998870938579155e-06,
      "loss": 0.2547,
      "step": 340
    },
    {
      "epoch": 0.3176043557168784,
      "grad_norm": 2.6734260791985953,
      "learning_rate": 4.999496814114059e-06,
      "loss": 0.2588,
      "step": 350
    },
    {
      "epoch": 0.32667876588021777,
      "grad_norm": 3.174757780905876,
      "learning_rate": 4.998827810375969e-06,
      "loss": 0.2635,
      "step": 360
    },
    {
      "epoch": 0.33575317604355714,
      "grad_norm": 3.285166158168479,
      "learning_rate": 4.997880157245622e-06,
      "loss": 0.2614,
      "step": 370
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 3.2985588417707508,
      "learning_rate": 4.99665396039775e-06,
      "loss": 0.2474,
      "step": 380
    },
    {
      "epoch": 0.35390199637023595,
      "grad_norm": 3.176235224524523,
      "learning_rate": 4.99514935656807e-06,
      "loss": 0.2505,
      "step": 390
    },
    {
      "epoch": 0.3629764065335753,
      "grad_norm": 2.7762353330962806,
      "learning_rate": 4.993366513538027e-06,
      "loss": 0.2613,
      "step": 400
    },
    {
      "epoch": 0.3629764065335753,
      "eval_loss": 0.25481727719306946,
      "eval_runtime": 1385.7465,
      "eval_samples_per_second": 11.309,
      "eval_steps_per_second": 1.414,
      "step": 400
    },
    {
      "epoch": 0.3720508166969147,
      "grad_norm": 3.284602872317128,
      "learning_rate": 4.991305630116089e-06,
      "loss": 0.2575,
      "step": 410
    },
    {
      "epoch": 0.3811252268602541,
      "grad_norm": 3.5420665129610014,
      "learning_rate": 4.988966936115574e-06,
      "loss": 0.2531,
      "step": 420
    },
    {
      "epoch": 0.39019963702359345,
      "grad_norm": 2.596405302358754,
      "learning_rate": 4.986350692329026e-06,
      "loss": 0.2428,
      "step": 430
    },
    {
      "epoch": 0.3992740471869328,
      "grad_norm": 3.0355466208388666,
      "learning_rate": 4.983457190499133e-06,
      "loss": 0.2521,
      "step": 440
    },
    {
      "epoch": 0.40834845735027225,
      "grad_norm": 2.3566033024089763,
      "learning_rate": 4.980286753286196e-06,
      "loss": 0.2392,
      "step": 450
    },
    {
      "epoch": 0.41742286751361163,
      "grad_norm": 4.02751047219257,
      "learning_rate": 4.976839734232137e-06,
      "loss": 0.2329,
      "step": 460
    },
    {
      "epoch": 0.426497277676951,
      "grad_norm": 2.9592917812573494,
      "learning_rate": 4.973116517721096e-06,
      "loss": 0.2606,
      "step": 470
    },
    {
      "epoch": 0.4355716878402904,
      "grad_norm": 3.0918754569573936,
      "learning_rate": 4.969117518936547e-06,
      "loss": 0.2367,
      "step": 480
    },
    {
      "epoch": 0.44464609800362975,
      "grad_norm": 2.678589145871871,
      "learning_rate": 4.9648431838150125e-06,
      "loss": 0.2445,
      "step": 490
    },
    {
      "epoch": 0.4537205081669691,
      "grad_norm": 2.1561463010278255,
      "learning_rate": 4.96029398899633e-06,
      "loss": 0.2285,
      "step": 500
    },
    {
      "epoch": 0.4627949183303085,
      "grad_norm": 2.161451988235388,
      "learning_rate": 4.9554704417705044e-06,
      "loss": 0.2324,
      "step": 510
    },
    {
      "epoch": 0.47186932849364793,
      "grad_norm": 2.6425923752703913,
      "learning_rate": 4.950373080021137e-06,
      "loss": 0.2395,
      "step": 520
    },
    {
      "epoch": 0.4809437386569873,
      "grad_norm": 3.305712508434671,
      "learning_rate": 4.945002472165447e-06,
      "loss": 0.2375,
      "step": 530
    },
    {
      "epoch": 0.4900181488203267,
      "grad_norm": 3.4513276852208157,
      "learning_rate": 4.939359217090885e-06,
      "loss": 0.2391,
      "step": 540
    },
    {
      "epoch": 0.49909255898366606,
      "grad_norm": 2.777165668498985,
      "learning_rate": 4.933443944088348e-06,
      "loss": 0.2417,
      "step": 550
    },
    {
      "epoch": 0.5081669691470054,
      "grad_norm": 2.273980183746595,
      "learning_rate": 4.927257312782009e-06,
      "loss": 0.2406,
      "step": 560
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 9.086214853943419,
      "learning_rate": 4.92080001305576e-06,
      "loss": 0.2391,
      "step": 570
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 2.147258342906181,
      "learning_rate": 4.914072764976279e-06,
      "loss": 0.24,
      "step": 580
    },
    {
      "epoch": 0.5353901996370236,
      "grad_norm": 1.9776299889509728,
      "learning_rate": 4.907076318712739e-06,
      "loss": 0.2395,
      "step": 590
    },
    {
      "epoch": 0.5444646098003629,
      "grad_norm": 2.4410336006371915,
      "learning_rate": 4.89981145445315e-06,
      "loss": 0.236,
      "step": 600
    },
    {
      "epoch": 0.5444646098003629,
      "eval_loss": 0.2328660637140274,
      "eval_runtime": 1392.8159,
      "eval_samples_per_second": 11.251,
      "eval_steps_per_second": 1.407,
      "step": 600
    },
    {
      "epoch": 0.5535390199637024,
      "grad_norm": 2.665043975658583,
      "learning_rate": 4.8922789823173645e-06,
      "loss": 0.2367,
      "step": 610
    },
    {
      "epoch": 0.5626134301270418,
      "grad_norm": 2.3260938839144667,
      "learning_rate": 4.884479742266731e-06,
      "loss": 0.2341,
      "step": 620
    },
    {
      "epoch": 0.5716878402903811,
      "grad_norm": 2.9249986255847777,
      "learning_rate": 4.876414604010435e-06,
      "loss": 0.2355,
      "step": 630
    },
    {
      "epoch": 0.5807622504537205,
      "grad_norm": 2.3284564104550887,
      "learning_rate": 4.868084466908515e-06,
      "loss": 0.2304,
      "step": 640
    },
    {
      "epoch": 0.5898366606170599,
      "grad_norm": 2.655514713362018,
      "learning_rate": 4.859490259871571e-06,
      "loss": 0.2214,
      "step": 650
    },
    {
      "epoch": 0.5989110707803993,
      "grad_norm": 2.172273396017733,
      "learning_rate": 4.850632941257181e-06,
      "loss": 0.2388,
      "step": 660
    },
    {
      "epoch": 0.6079854809437386,
      "grad_norm": 2.8142514255768725,
      "learning_rate": 4.841513498763032e-06,
      "loss": 0.2299,
      "step": 670
    },
    {
      "epoch": 0.617059891107078,
      "grad_norm": 2.26086176843519,
      "learning_rate": 4.832132949316779e-06,
      "loss": 0.2228,
      "step": 680
    },
    {
      "epoch": 0.6261343012704175,
      "grad_norm": 2.7355865634251093,
      "learning_rate": 4.82249233896265e-06,
      "loss": 0.2304,
      "step": 690
    },
    {
      "epoch": 0.6352087114337568,
      "grad_norm": 2.38859944984162,
      "learning_rate": 4.812592742744793e-06,
      "loss": 0.228,
      "step": 700
    },
    {
      "epoch": 0.6442831215970962,
      "grad_norm": 3.9725253297824596,
      "learning_rate": 4.802435264587399e-06,
      "loss": 0.2256,
      "step": 710
    },
    {
      "epoch": 0.6533575317604355,
      "grad_norm": 2.846384833674891,
      "learning_rate": 4.7920210371716e-06,
      "loss": 0.2191,
      "step": 720
    },
    {
      "epoch": 0.662431941923775,
      "grad_norm": 2.654802858386062,
      "learning_rate": 4.781351221809166e-06,
      "loss": 0.219,
      "step": 730
    },
    {
      "epoch": 0.6715063520871143,
      "grad_norm": 2.46474267971609,
      "learning_rate": 4.770427008312995e-06,
      "loss": 0.2257,
      "step": 740
    },
    {
      "epoch": 0.6805807622504537,
      "grad_norm": 2.289413277605694,
      "learning_rate": 4.7592496148644444e-06,
      "loss": 0.2163,
      "step": 750
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 2.4384097969774072,
      "learning_rate": 4.747820287877485e-06,
      "loss": 0.2183,
      "step": 760
    },
    {
      "epoch": 0.6987295825771325,
      "grad_norm": 2.158160700782267,
      "learning_rate": 4.7361403018597095e-06,
      "loss": 0.2298,
      "step": 770
    },
    {
      "epoch": 0.7078039927404719,
      "grad_norm": 2.8309530601299686,
      "learning_rate": 4.724210959270212e-06,
      "loss": 0.2194,
      "step": 780
    },
    {
      "epoch": 0.7168784029038112,
      "grad_norm": 2.054056319721668,
      "learning_rate": 4.712033590374346e-06,
      "loss": 0.2209,
      "step": 790
    },
    {
      "epoch": 0.7259528130671506,
      "grad_norm": 1.8755126726314235,
      "learning_rate": 4.699609553095388e-06,
      "loss": 0.2316,
      "step": 800
    },
    {
      "epoch": 0.7259528130671506,
      "eval_loss": 0.21832555532455444,
      "eval_runtime": 1395.7972,
      "eval_samples_per_second": 11.227,
      "eval_steps_per_second": 1.403,
      "step": 800
    },
    {
      "epoch": 0.73502722323049,
      "grad_norm": 2.2175534974713558,
      "learning_rate": 4.686940232863104e-06,
      "loss": 0.2149,
      "step": 810
    },
    {
      "epoch": 0.7441016333938294,
      "grad_norm": 2.6199865645252087,
      "learning_rate": 4.67402704245927e-06,
      "loss": 0.2234,
      "step": 820
    },
    {
      "epoch": 0.7531760435571688,
      "grad_norm": 2.2120699099337746,
      "learning_rate": 4.660871421860117e-06,
      "loss": 0.2189,
      "step": 830
    },
    {
      "epoch": 0.7622504537205081,
      "grad_norm": 2.2524164578978194,
      "learning_rate": 4.647474838075765e-06,
      "loss": 0.2173,
      "step": 840
    },
    {
      "epoch": 0.7713248638838476,
      "grad_norm": 2.3499119638658583,
      "learning_rate": 4.63383878498663e-06,
      "loss": 0.2164,
      "step": 850
    },
    {
      "epoch": 0.7803992740471869,
      "grad_norm": 2.4962059632051017,
      "learning_rate": 4.619964783176842e-06,
      "loss": 0.2107,
      "step": 860
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 2.3768798330761967,
      "learning_rate": 4.605854379764673e-06,
      "loss": 0.2302,
      "step": 870
    },
    {
      "epoch": 0.7985480943738656,
      "grad_norm": 1.955343852648314,
      "learning_rate": 4.591509148230028e-06,
      "loss": 0.2238,
      "step": 880
    },
    {
      "epoch": 0.8076225045372051,
      "grad_norm": 2.6863720488743836,
      "learning_rate": 4.576930688238966e-06,
      "loss": 0.2251,
      "step": 890
    },
    {
      "epoch": 0.8166969147005445,
      "grad_norm": 2.827469079448433,
      "learning_rate": 4.5621206254653375e-06,
      "loss": 0.2153,
      "step": 900
    },
    {
      "epoch": 0.8257713248638838,
      "grad_norm": 2.7372391457936867,
      "learning_rate": 4.5470806114094855e-06,
      "loss": 0.2143,
      "step": 910
    },
    {
      "epoch": 0.8348457350272233,
      "grad_norm": 1.945206405296837,
      "learning_rate": 4.531812323214092e-06,
      "loss": 0.2265,
      "step": 920
    },
    {
      "epoch": 0.8439201451905626,
      "grad_norm": 2.8127205202853607,
      "learning_rate": 4.5163174634771555e-06,
      "loss": 0.2074,
      "step": 930
    },
    {
      "epoch": 0.852994555353902,
      "grad_norm": 2.217157904602061,
      "learning_rate": 4.500597760062128e-06,
      "loss": 0.222,
      "step": 940
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 2.380125212830743,
      "learning_rate": 4.4846549659052415e-06,
      "loss": 0.2137,
      "step": 950
    },
    {
      "epoch": 0.8711433756805808,
      "grad_norm": 1.9726123641599649,
      "learning_rate": 4.4684908588200305e-06,
      "loss": 0.2096,
      "step": 960
    },
    {
      "epoch": 0.8802177858439202,
      "grad_norm": 2.236951819316835,
      "learning_rate": 4.452107241299086e-06,
      "loss": 0.2068,
      "step": 970
    },
    {
      "epoch": 0.8892921960072595,
      "grad_norm": 1.9126809671927136,
      "learning_rate": 4.435505940313056e-06,
      "loss": 0.2103,
      "step": 980
    },
    {
      "epoch": 0.8983666061705989,
      "grad_norm": 2.2771294569890674,
      "learning_rate": 4.418688807106919e-06,
      "loss": 0.2133,
      "step": 990
    },
    {
      "epoch": 0.9074410163339383,
      "grad_norm": 2.318214669072201,
      "learning_rate": 4.40165771699354e-06,
      "loss": 0.2174,
      "step": 1000
    },
    {
      "epoch": 0.9074410163339383,
      "eval_loss": 0.21023514866828918,
      "eval_runtime": 1389.95,
      "eval_samples_per_second": 11.275,
      "eval_steps_per_second": 1.409,
      "step": 1000
    },
    {
      "epoch": 0.9165154264972777,
      "grad_norm": 1.9024376437747152,
      "learning_rate": 4.384414569144562e-06,
      "loss": 0.2215,
      "step": 1010
    },
    {
      "epoch": 0.925589836660617,
      "grad_norm": 2.602572238899701,
      "learning_rate": 4.366961286378611e-06,
      "loss": 0.2137,
      "step": 1020
    },
    {
      "epoch": 0.9346642468239564,
      "grad_norm": 2.386566082789539,
      "learning_rate": 4.349299814946897e-06,
      "loss": 0.2164,
      "step": 1030
    },
    {
      "epoch": 0.9437386569872959,
      "grad_norm": 2.470792431536072,
      "learning_rate": 4.3314321243161625e-06,
      "loss": 0.2089,
      "step": 1040
    },
    {
      "epoch": 0.9528130671506352,
      "grad_norm": 2.208078410049245,
      "learning_rate": 4.313360206949083e-06,
      "loss": 0.2013,
      "step": 1050
    },
    {
      "epoch": 0.9618874773139746,
      "grad_norm": 2.610990495763538,
      "learning_rate": 4.295086078082069e-06,
      "loss": 0.2129,
      "step": 1060
    },
    {
      "epoch": 0.9709618874773139,
      "grad_norm": 2.294970828246581,
      "learning_rate": 4.276611775500551e-06,
      "loss": 0.2182,
      "step": 1070
    },
    {
      "epoch": 0.9800362976406534,
      "grad_norm": 2.4650509566661074,
      "learning_rate": 4.257939359311737e-06,
      "loss": 0.2085,
      "step": 1080
    },
    {
      "epoch": 0.9891107078039928,
      "grad_norm": 2.7720539484155573,
      "learning_rate": 4.23907091171489e-06,
      "loss": 0.2031,
      "step": 1090
    },
    {
      "epoch": 0.9981851179673321,
      "grad_norm": 1.9761376034470355,
      "learning_rate": 4.220008536769135e-06,
      "loss": 0.2064,
      "step": 1100
    },
    {
      "epoch": 1.0072595281306715,
      "grad_norm": 2.8661775908744587,
      "learning_rate": 4.20075436015883e-06,
      "loss": 0.1754,
      "step": 1110
    },
    {
      "epoch": 1.0163339382940109,
      "grad_norm": 3.0571703056604718,
      "learning_rate": 4.181310528956532e-06,
      "loss": 0.1811,
      "step": 1120
    },
    {
      "epoch": 1.0254083484573502,
      "grad_norm": 2.2036266328488856,
      "learning_rate": 4.161679211383565e-06,
      "loss": 0.1773,
      "step": 1130
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 2.1184036505991943,
      "learning_rate": 4.1418625965682434e-06,
      "loss": 0.1685,
      "step": 1140
    },
    {
      "epoch": 1.043557168784029,
      "grad_norm": 2.98432394525953,
      "learning_rate": 4.121862894301754e-06,
      "loss": 0.1652,
      "step": 1150
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 4.127281890786837,
      "learning_rate": 4.1016823347917426e-06,
      "loss": 0.1722,
      "step": 1160
    },
    {
      "epoch": 1.061705989110708,
      "grad_norm": 2.7072627116449777,
      "learning_rate": 4.081323168413611e-06,
      "loss": 0.1641,
      "step": 1170
    },
    {
      "epoch": 1.0707803992740472,
      "grad_norm": 2.983336972856654,
      "learning_rate": 4.0607876654595795e-06,
      "loss": 0.1627,
      "step": 1180
    },
    {
      "epoch": 1.0798548094373865,
      "grad_norm": 2.291332244128816,
      "learning_rate": 4.040078115885521e-06,
      "loss": 0.1558,
      "step": 1190
    },
    {
      "epoch": 1.0889292196007259,
      "grad_norm": 2.942836478618513,
      "learning_rate": 4.019196829055602e-06,
      "loss": 0.1674,
      "step": 1200
    },
    {
      "epoch": 1.0889292196007259,
      "eval_loss": 0.22207966446876526,
      "eval_runtime": 1386.9829,
      "eval_samples_per_second": 11.299,
      "eval_steps_per_second": 1.412,
      "step": 1200
    },
    {
      "epoch": 1.0980036297640654,
      "grad_norm": 2.2047904283245914,
      "learning_rate": 3.998146133484759e-06,
      "loss": 0.1773,
      "step": 1210
    },
    {
      "epoch": 1.1070780399274047,
      "grad_norm": 2.549289996227374,
      "learning_rate": 3.976928376579048e-06,
      "loss": 0.1719,
      "step": 1220
    },
    {
      "epoch": 1.116152450090744,
      "grad_norm": 2.582934191127174,
      "learning_rate": 3.95554592437387e-06,
      "loss": 0.1705,
      "step": 1230
    },
    {
      "epoch": 1.1252268602540836,
      "grad_norm": 2.591599338279486,
      "learning_rate": 3.934001161270139e-06,
      "loss": 0.168,
      "step": 1240
    },
    {
      "epoch": 1.134301270417423,
      "grad_norm": 2.238977254673354,
      "learning_rate": 3.912296489768387e-06,
      "loss": 0.1733,
      "step": 1250
    },
    {
      "epoch": 1.1433756805807622,
      "grad_norm": 2.5460412991064874,
      "learning_rate": 3.890434330200859e-06,
      "loss": 0.165,
      "step": 1260
    },
    {
      "epoch": 1.1524500907441015,
      "grad_norm": 2.3394047910221434,
      "learning_rate": 3.868417120461616e-06,
      "loss": 0.1577,
      "step": 1270
    },
    {
      "epoch": 1.161524500907441,
      "grad_norm": 2.3581800863995617,
      "learning_rate": 3.846247315734678e-06,
      "loss": 0.1667,
      "step": 1280
    },
    {
      "epoch": 1.1705989110707804,
      "grad_norm": 2.406584332811748,
      "learning_rate": 3.823927388220248e-06,
      "loss": 0.173,
      "step": 1290
    },
    {
      "epoch": 1.1796733212341197,
      "grad_norm": 3.430801570890468,
      "learning_rate": 3.801459826859022e-06,
      "loss": 0.1635,
      "step": 1300
    },
    {
      "epoch": 1.1887477313974593,
      "grad_norm": 2.3679072240217782,
      "learning_rate": 3.7788471370546526e-06,
      "loss": 0.1719,
      "step": 1310
    },
    {
      "epoch": 1.1978221415607986,
      "grad_norm": 2.543912214782469,
      "learning_rate": 3.75609184039436e-06,
      "loss": 0.1681,
      "step": 1320
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 2.581428370171461,
      "learning_rate": 3.733196474367745e-06,
      "loss": 0.1666,
      "step": 1330
    },
    {
      "epoch": 1.2159709618874772,
      "grad_norm": 2.6902942803231813,
      "learning_rate": 3.71016359208383e-06,
      "loss": 0.1744,
      "step": 1340
    },
    {
      "epoch": 1.2250453720508168,
      "grad_norm": 3.01590815670282,
      "learning_rate": 3.6869957619863574e-06,
      "loss": 0.1633,
      "step": 1350
    },
    {
      "epoch": 1.234119782214156,
      "grad_norm": 2.3928777627538276,
      "learning_rate": 3.6636955675673747e-06,
      "loss": 0.1702,
      "step": 1360
    },
    {
      "epoch": 1.2431941923774954,
      "grad_norm": 2.4673548071164952,
      "learning_rate": 3.6402656070791455e-06,
      "loss": 0.169,
      "step": 1370
    },
    {
      "epoch": 1.252268602540835,
      "grad_norm": 2.916016475398333,
      "learning_rate": 3.616708493244411e-06,
      "loss": 0.1697,
      "step": 1380
    },
    {
      "epoch": 1.2613430127041743,
      "grad_norm": 2.3481470816747905,
      "learning_rate": 3.593026852965045e-06,
      "loss": 0.1706,
      "step": 1390
    },
    {
      "epoch": 1.2704174228675136,
      "grad_norm": 2.447622337661765,
      "learning_rate": 3.569223327029119e-06,
      "loss": 0.1656,
      "step": 1400
    },
    {
      "epoch": 1.2704174228675136,
      "eval_loss": 0.20881019532680511,
      "eval_runtime": 1390.5666,
      "eval_samples_per_second": 11.27,
      "eval_steps_per_second": 1.409,
      "step": 1400
    },
    {
      "epoch": 1.279491833030853,
      "grad_norm": 2.4302745225854223,
      "learning_rate": 3.545300569816419e-06,
      "loss": 0.1586,
      "step": 1410
    },
    {
      "epoch": 1.2885662431941924,
      "grad_norm": 2.8375607962764864,
      "learning_rate": 3.521261249002459e-06,
      "loss": 0.1657,
      "step": 1420
    },
    {
      "epoch": 1.2976406533575318,
      "grad_norm": 2.6797627074099353,
      "learning_rate": 3.4971080452609956e-06,
      "loss": 0.1616,
      "step": 1430
    },
    {
      "epoch": 1.306715063520871,
      "grad_norm": 2.246400126865409,
      "learning_rate": 3.472843651965104e-06,
      "loss": 0.1614,
      "step": 1440
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 3.10139379925332,
      "learning_rate": 3.448470774886833e-06,
      "loss": 0.158,
      "step": 1450
    },
    {
      "epoch": 1.32486388384755,
      "grad_norm": 2.9084460027040944,
      "learning_rate": 3.4239921318954812e-06,
      "loss": 0.1656,
      "step": 1460
    },
    {
      "epoch": 1.3339382940108893,
      "grad_norm": 2.5322999915231237,
      "learning_rate": 3.399410452654518e-06,
      "loss": 0.1638,
      "step": 1470
    },
    {
      "epoch": 1.3430127041742286,
      "grad_norm": 3.086032752130754,
      "learning_rate": 3.3747284783171963e-06,
      "loss": 0.1621,
      "step": 1480
    },
    {
      "epoch": 1.3520871143375681,
      "grad_norm": 2.6171253135143253,
      "learning_rate": 3.349948961220881e-06,
      "loss": 0.1677,
      "step": 1490
    },
    {
      "epoch": 1.3611615245009074,
      "grad_norm": 2.9456731239876843,
      "learning_rate": 3.325074664580129e-06,
      "loss": 0.1625,
      "step": 1500
    },
    {
      "epoch": 1.3702359346642468,
      "grad_norm": 2.2822738831120577,
      "learning_rate": 3.300108362178556e-06,
      "loss": 0.1612,
      "step": 1510
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 3.1233765779322393,
      "learning_rate": 3.2750528380595286e-06,
      "loss": 0.1603,
      "step": 1520
    },
    {
      "epoch": 1.3883847549909256,
      "grad_norm": 3.555763231043894,
      "learning_rate": 3.2499108862157104e-06,
      "loss": 0.1567,
      "step": 1530
    },
    {
      "epoch": 1.397459165154265,
      "grad_norm": 3.012507172479019,
      "learning_rate": 3.2246853102774982e-06,
      "loss": 0.159,
      "step": 1540
    },
    {
      "epoch": 1.4065335753176043,
      "grad_norm": 2.7884800272917336,
      "learning_rate": 3.1993789232003785e-06,
      "loss": 0.1568,
      "step": 1550
    },
    {
      "epoch": 1.4156079854809438,
      "grad_norm": 2.6522156479780734,
      "learning_rate": 3.173994546951257e-06,
      "loss": 0.1535,
      "step": 1560
    },
    {
      "epoch": 1.4246823956442831,
      "grad_norm": 2.690880618436342,
      "learning_rate": 3.1485350121937676e-06,
      "loss": 0.1642,
      "step": 1570
    },
    {
      "epoch": 1.4337568058076224,
      "grad_norm": 2.416955137134592,
      "learning_rate": 3.1230031579726254e-06,
      "loss": 0.156,
      "step": 1580
    },
    {
      "epoch": 1.442831215970962,
      "grad_norm": 2.3363176935386334,
      "learning_rate": 3.0974018313970367e-06,
      "loss": 0.1541,
      "step": 1590
    },
    {
      "epoch": 1.4519056261343013,
      "grad_norm": 2.990621526192577,
      "learning_rate": 3.0717338873232104e-06,
      "loss": 0.1565,
      "step": 1600
    },
    {
      "epoch": 1.4519056261343013,
      "eval_loss": 0.21768733859062195,
      "eval_runtime": 1388.7776,
      "eval_samples_per_second": 11.284,
      "eval_steps_per_second": 1.411,
      "step": 1600
    },
    {
      "epoch": 1.4609800362976406,
      "grad_norm": 2.5330079610413128,
      "learning_rate": 3.0460021880360104e-06,
      "loss": 0.162,
      "step": 1610
    },
    {
      "epoch": 1.47005444646098,
      "grad_norm": 2.7470540614501644,
      "learning_rate": 3.0202096029297718e-06,
      "loss": 0.1606,
      "step": 1620
    },
    {
      "epoch": 1.4791288566243195,
      "grad_norm": 2.700430477341895,
      "learning_rate": 2.994359008188335e-06,
      "loss": 0.157,
      "step": 1630
    },
    {
      "epoch": 1.4882032667876588,
      "grad_norm": 2.939527090716072,
      "learning_rate": 2.9684532864643123e-06,
      "loss": 0.1558,
      "step": 1640
    },
    {
      "epoch": 1.4972776769509981,
      "grad_norm": 2.561733051361771,
      "learning_rate": 2.942495326557636e-06,
      "loss": 0.161,
      "step": 1650
    },
    {
      "epoch": 1.5063520871143377,
      "grad_norm": 2.3927416251094913,
      "learning_rate": 2.9164880230934297e-06,
      "loss": 0.1623,
      "step": 1660
    },
    {
      "epoch": 1.515426497277677,
      "grad_norm": 2.7403691913319483,
      "learning_rate": 2.890434276199212e-06,
      "loss": 0.1524,
      "step": 1670
    },
    {
      "epoch": 1.5245009074410163,
      "grad_norm": 3.047303621944233,
      "learning_rate": 2.8643369911815084e-06,
      "loss": 0.1603,
      "step": 1680
    },
    {
      "epoch": 1.5335753176043556,
      "grad_norm": 2.709018147731808,
      "learning_rate": 2.8381990782018666e-06,
      "loss": 0.157,
      "step": 1690
    },
    {
      "epoch": 1.542649727767695,
      "grad_norm": 2.1829283333409912,
      "learning_rate": 2.812023451952342e-06,
      "loss": 0.163,
      "step": 1700
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 2.173423423571578,
      "learning_rate": 2.7858130313304733e-06,
      "loss": 0.1642,
      "step": 1710
    },
    {
      "epoch": 1.560798548094374,
      "grad_norm": 3.196586296071348,
      "learning_rate": 2.759570739113791e-06,
      "loss": 0.1609,
      "step": 1720
    },
    {
      "epoch": 1.5698729582577133,
      "grad_norm": 2.692405751944479,
      "learning_rate": 2.7332995016338936e-06,
      "loss": 0.1643,
      "step": 1730
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 3.222257019461879,
      "learning_rate": 2.707002248450123e-06,
      "loss": 0.1643,
      "step": 1740
    },
    {
      "epoch": 1.588021778584392,
      "grad_norm": 2.5952908077601182,
      "learning_rate": 2.680681912022886e-06,
      "loss": 0.1566,
      "step": 1750
    },
    {
      "epoch": 1.5970961887477313,
      "grad_norm": 2.5445336452362985,
      "learning_rate": 2.6543414273866495e-06,
      "loss": 0.1471,
      "step": 1760
    },
    {
      "epoch": 1.6061705989110708,
      "grad_norm": 2.9956462377938635,
      "learning_rate": 2.627983731822648e-06,
      "loss": 0.1542,
      "step": 1770
    },
    {
      "epoch": 1.6152450090744102,
      "grad_norm": 2.84414987744975,
      "learning_rate": 2.601611764531342e-06,
      "loss": 0.1464,
      "step": 1780
    },
    {
      "epoch": 1.6243194192377497,
      "grad_norm": 2.935442040913498,
      "learning_rate": 2.5752284663046604e-06,
      "loss": 0.1496,
      "step": 1790
    },
    {
      "epoch": 1.633393829401089,
      "grad_norm": 2.683961628638721,
      "learning_rate": 2.54883677919807e-06,
      "loss": 0.1611,
      "step": 1800
    },
    {
      "epoch": 1.633393829401089,
      "eval_loss": 0.19924426078796387,
      "eval_runtime": 1394.3787,
      "eval_samples_per_second": 11.239,
      "eval_steps_per_second": 1.405,
      "step": 1800
    },
    {
      "epoch": 1.6424682395644283,
      "grad_norm": 2.4486598859213538,
      "learning_rate": 2.522439646202495e-06,
      "loss": 0.1531,
      "step": 1810
    },
    {
      "epoch": 1.6515426497277677,
      "grad_norm": 2.816495954486452,
      "learning_rate": 2.496040010916147e-06,
      "loss": 0.1488,
      "step": 1820
    },
    {
      "epoch": 1.660617059891107,
      "grad_norm": 2.474284705036608,
      "learning_rate": 2.469640817216267e-06,
      "loss": 0.1472,
      "step": 1830
    },
    {
      "epoch": 1.6696914700544465,
      "grad_norm": 2.593780413603297,
      "learning_rate": 2.44324500893086e-06,
      "loss": 0.1487,
      "step": 1840
    },
    {
      "epoch": 1.6787658802177858,
      "grad_norm": 2.643998749679691,
      "learning_rate": 2.4168555295104128e-06,
      "loss": 0.162,
      "step": 1850
    },
    {
      "epoch": 1.6878402903811254,
      "grad_norm": 2.4339674398087765,
      "learning_rate": 2.390475321699668e-06,
      "loss": 0.1599,
      "step": 1860
    },
    {
      "epoch": 1.6969147005444647,
      "grad_norm": 2.7798518325679633,
      "learning_rate": 2.364107327209472e-06,
      "loss": 0.1642,
      "step": 1870
    },
    {
      "epoch": 1.705989110707804,
      "grad_norm": 2.3526604013511196,
      "learning_rate": 2.3377544863887413e-06,
      "loss": 0.1553,
      "step": 1880
    },
    {
      "epoch": 1.7150635208711433,
      "grad_norm": 2.5803366400982277,
      "learning_rate": 2.3114197378965707e-06,
      "loss": 0.1567,
      "step": 1890
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 2.884427313714114,
      "learning_rate": 2.2851060183745486e-06,
      "loss": 0.1582,
      "step": 1900
    },
    {
      "epoch": 1.7332123411978222,
      "grad_norm": 2.6892436838324913,
      "learning_rate": 2.2588162621192743e-06,
      "loss": 0.1615,
      "step": 1910
    },
    {
      "epoch": 1.7422867513611615,
      "grad_norm": 3.0409417649516906,
      "learning_rate": 2.2325534007551595e-06,
      "loss": 0.1559,
      "step": 1920
    },
    {
      "epoch": 1.751361161524501,
      "grad_norm": 2.5542741876541553,
      "learning_rate": 2.2063203629075064e-06,
      "loss": 0.1513,
      "step": 1930
    },
    {
      "epoch": 1.7604355716878404,
      "grad_norm": 2.4789943094684475,
      "learning_rate": 2.1801200738759405e-06,
      "loss": 0.1578,
      "step": 1940
    },
    {
      "epoch": 1.7695099818511797,
      "grad_norm": 2.3940496089558065,
      "learning_rate": 2.153955455308199e-06,
      "loss": 0.145,
      "step": 1950
    },
    {
      "epoch": 1.778584392014519,
      "grad_norm": 2.632221247717038,
      "learning_rate": 2.1278294248743296e-06,
      "loss": 0.1503,
      "step": 1960
    },
    {
      "epoch": 1.7876588021778583,
      "grad_norm": 3.159625330396048,
      "learning_rate": 2.1017448959413425e-06,
      "loss": 0.1526,
      "step": 1970
    },
    {
      "epoch": 1.7967332123411979,
      "grad_norm": 3.2645258981697665,
      "learning_rate": 2.0757047772483278e-06,
      "loss": 0.158,
      "step": 1980
    },
    {
      "epoch": 1.8058076225045372,
      "grad_norm": 2.7180474599627917,
      "learning_rate": 2.0497119725821012e-06,
      "loss": 0.1529,
      "step": 1990
    },
    {
      "epoch": 1.8148820326678767,
      "grad_norm": 2.9380433118432907,
      "learning_rate": 2.0237693804533938e-06,
      "loss": 0.161,
      "step": 2000
    },
    {
      "epoch": 1.8148820326678767,
      "eval_loss": 0.19724711775779724,
      "eval_runtime": 1389.1913,
      "eval_samples_per_second": 11.281,
      "eval_steps_per_second": 1.41,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3306,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1441911735844864.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}