{
  "best_global_step": 383,
  "best_metric": 0.37941670417785645,
  "best_model_checkpoint": "./lora_qwen7b_cpp_adiff_v1/checkpoint-383",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1149,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02611818478615736,
      "grad_norm": 0.3439924716949463,
      "learning_rate": 2.347826086956522e-06,
      "loss": 0.9253,
      "step": 10
    },
    {
      "epoch": 0.05223636957231472,
      "grad_norm": 0.37593239545822144,
      "learning_rate": 4.956521739130435e-06,
      "loss": 0.8942,
      "step": 20
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.4532669186592102,
      "learning_rate": 7.5652173913043475e-06,
      "loss": 0.9621,
      "step": 30
    },
    {
      "epoch": 0.10447273914462944,
      "grad_norm": 0.30326446890830994,
      "learning_rate": 1.017391304347826e-05,
      "loss": 0.8363,
      "step": 40
    },
    {
      "epoch": 0.1305909239307868,
      "grad_norm": 0.4317711591720581,
      "learning_rate": 1.2782608695652173e-05,
      "loss": 0.7811,
      "step": 50
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.3774474263191223,
      "learning_rate": 1.5391304347826088e-05,
      "loss": 0.5888,
      "step": 60
    },
    {
      "epoch": 0.18282729350310153,
      "grad_norm": 0.1916833221912384,
      "learning_rate": 1.8e-05,
      "loss": 0.4563,
      "step": 70
    },
    {
      "epoch": 0.20894547828925888,
      "grad_norm": 0.13702069222927094,
      "learning_rate": 2.0608695652173913e-05,
      "loss": 0.4354,
      "step": 80
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.10257239639759064,
      "learning_rate": 2.3217391304347826e-05,
      "loss": 0.408,
      "step": 90
    },
    {
      "epoch": 0.2611818478615736,
      "grad_norm": 0.15386034548282623,
      "learning_rate": 2.582608695652174e-05,
      "loss": 0.3986,
      "step": 100
    },
    {
      "epoch": 0.28730003264773096,
      "grad_norm": 0.12275378406047821,
      "learning_rate": 2.8434782608695652e-05,
      "loss": 0.3773,
      "step": 110
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.13668131828308105,
      "learning_rate": 2.988394584139265e-05,
      "loss": 0.3579,
      "step": 120
    },
    {
      "epoch": 0.3395364022200457,
      "grad_norm": 0.11877596378326416,
      "learning_rate": 2.9593810444874276e-05,
      "loss": 0.3622,
      "step": 130
    },
    {
      "epoch": 0.36565458700620307,
      "grad_norm": 0.15862952172756195,
      "learning_rate": 2.93036750483559e-05,
      "loss": 0.352,
      "step": 140
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 0.14640262722969055,
      "learning_rate": 2.9013539651837528e-05,
      "loss": 0.3597,
      "step": 150
    },
    {
      "epoch": 0.41789095657851777,
      "grad_norm": 0.11437654495239258,
      "learning_rate": 2.872340425531915e-05,
      "loss": 0.3456,
      "step": 160
    },
    {
      "epoch": 0.4440091413646752,
      "grad_norm": 0.1443624049425125,
      "learning_rate": 2.8433268858800773e-05,
      "loss": 0.3513,
      "step": 170
    },
    {
      "epoch": 0.4701273261508325,
      "grad_norm": 0.11668717861175537,
      "learning_rate": 2.81431334622824e-05,
      "loss": 0.3246,
      "step": 180
    },
    {
      "epoch": 0.4962455109369899,
      "grad_norm": 0.1281779706478119,
      "learning_rate": 2.785299806576402e-05,
      "loss": 0.3504,
      "step": 190
    },
    {
      "epoch": 0.5223636957231472,
      "grad_norm": 0.130177304148674,
      "learning_rate": 2.7562862669245647e-05,
      "loss": 0.3487,
      "step": 200
    },
    {
      "epoch": 0.5484818805093046,
      "grad_norm": 0.1486888825893402,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.3305,
      "step": 210
    },
    {
      "epoch": 0.5746000652954619,
      "grad_norm": 0.12134828418493271,
      "learning_rate": 2.69825918762089e-05,
      "loss": 0.3451,
      "step": 220
    },
    {
      "epoch": 0.6007182500816193,
      "grad_norm": 0.12231825292110443,
      "learning_rate": 2.669245647969052e-05,
      "loss": 0.3233,
      "step": 230
    },
    {
      "epoch": 0.6268364348677767,
      "grad_norm": 0.13645341992378235,
      "learning_rate": 2.6402321083172148e-05,
      "loss": 0.3365,
      "step": 240
    },
    {
      "epoch": 0.6529546196539341,
      "grad_norm": 0.14500953257083893,
      "learning_rate": 2.6112185686653773e-05,
      "loss": 0.3329,
      "step": 250
    },
    {
      "epoch": 0.6790728044400914,
      "grad_norm": 0.16711661219596863,
      "learning_rate": 2.5822050290135396e-05,
      "loss": 0.3305,
      "step": 260
    },
    {
      "epoch": 0.7051909892262488,
      "grad_norm": 0.14286471903324127,
      "learning_rate": 2.5531914893617022e-05,
      "loss": 0.3159,
      "step": 270
    },
    {
      "epoch": 0.7313091740124061,
      "grad_norm": 0.17056842148303986,
      "learning_rate": 2.5241779497098648e-05,
      "loss": 0.335,
      "step": 280
    },
    {
      "epoch": 0.7574273587985635,
      "grad_norm": 0.16313998401165009,
      "learning_rate": 2.495164410058027e-05,
      "loss": 0.318,
      "step": 290
    },
    {
      "epoch": 0.7835455435847208,
      "grad_norm": 0.16147395968437195,
      "learning_rate": 2.4661508704061896e-05,
      "loss": 0.2996,
      "step": 300
    },
    {
      "epoch": 0.8096637283708782,
      "grad_norm": 0.1918044090270996,
      "learning_rate": 2.4371373307543522e-05,
      "loss": 0.3172,
      "step": 310
    },
    {
      "epoch": 0.8357819131570355,
      "grad_norm": 0.15215300023555756,
      "learning_rate": 2.408123791102515e-05,
      "loss": 0.3258,
      "step": 320
    },
    {
      "epoch": 0.861900097943193,
      "grad_norm": 0.15154816210269928,
      "learning_rate": 2.379110251450677e-05,
      "loss": 0.3206,
      "step": 330
    },
    {
      "epoch": 0.8880182827293504,
      "grad_norm": 0.19857144355773926,
      "learning_rate": 2.3500967117988397e-05,
      "loss": 0.3038,
      "step": 340
    },
    {
      "epoch": 0.9141364675155077,
      "grad_norm": 0.1814548224210739,
      "learning_rate": 2.321083172147002e-05,
      "loss": 0.3157,
      "step": 350
    },
    {
      "epoch": 0.940254652301665,
      "grad_norm": 0.17991890013217926,
      "learning_rate": 2.2920696324951642e-05,
      "loss": 0.3044,
      "step": 360
    },
    {
      "epoch": 0.9663728370878224,
      "grad_norm": 0.17508666217327118,
      "learning_rate": 2.2630560928433268e-05,
      "loss": 0.3081,
      "step": 370
    },
    {
      "epoch": 0.9924910218739798,
      "grad_norm": 0.17764495313167572,
      "learning_rate": 2.2340425531914894e-05,
      "loss": 0.2957,
      "step": 380
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.37941670417785645,
      "eval_runtime": 41.5299,
      "eval_samples_per_second": 22.105,
      "eval_steps_per_second": 11.052,
      "step": 383
    },
    {
      "epoch": 1.01828272935031,
      "grad_norm": 0.2144664078950882,
      "learning_rate": 2.2050290135396516e-05,
      "loss": 0.3094,
      "step": 390
    },
    {
      "epoch": 1.0444009141364674,
      "grad_norm": 0.2546301484107971,
      "learning_rate": 2.1760154738878142e-05,
      "loss": 0.2887,
      "step": 400
    },
    {
      "epoch": 1.070519098922625,
      "grad_norm": 0.2032032310962677,
      "learning_rate": 2.1470019342359768e-05,
      "loss": 0.3005,
      "step": 410
    },
    {
      "epoch": 1.0966372837087823,
      "grad_norm": 0.2284616231918335,
      "learning_rate": 2.1179883945841394e-05,
      "loss": 0.2854,
      "step": 420
    },
    {
      "epoch": 1.1227554684949397,
      "grad_norm": 0.21598398685455322,
      "learning_rate": 2.0889748549323017e-05,
      "loss": 0.3021,
      "step": 430
    },
    {
      "epoch": 1.148873653281097,
      "grad_norm": 0.2569762170314789,
      "learning_rate": 2.0599613152804643e-05,
      "loss": 0.2976,
      "step": 440
    },
    {
      "epoch": 1.1749918380672544,
      "grad_norm": 0.18876290321350098,
      "learning_rate": 2.030947775628627e-05,
      "loss": 0.2977,
      "step": 450
    },
    {
      "epoch": 1.2011100228534117,
      "grad_norm": 0.26530972123146057,
      "learning_rate": 2.001934235976789e-05,
      "loss": 0.2802,
      "step": 460
    },
    {
      "epoch": 1.227228207639569,
      "grad_norm": 0.2499823421239853,
      "learning_rate": 1.9729206963249517e-05,
      "loss": 0.278,
      "step": 470
    },
    {
      "epoch": 1.2533463924257264,
      "grad_norm": 0.2791983485221863,
      "learning_rate": 1.9439071566731143e-05,
      "loss": 0.2783,
      "step": 480
    },
    {
      "epoch": 1.2794645772118838,
      "grad_norm": 0.25514301657676697,
      "learning_rate": 1.914893617021277e-05,
      "loss": 0.2586,
      "step": 490
    },
    {
      "epoch": 1.3055827619980411,
      "grad_norm": 0.24786071479320526,
      "learning_rate": 1.885880077369439e-05,
      "loss": 0.2941,
      "step": 500
    },
    {
      "epoch": 1.3317009467841985,
      "grad_norm": 0.26750949025154114,
      "learning_rate": 1.8568665377176018e-05,
      "loss": 0.2784,
      "step": 510
    },
    {
      "epoch": 1.3578191315703558,
      "grad_norm": 0.2794158458709717,
      "learning_rate": 1.8278529980657643e-05,
      "loss": 0.2621,
      "step": 520
    },
    {
      "epoch": 1.3839373163565132,
      "grad_norm": 0.33961278200149536,
      "learning_rate": 1.7988394584139263e-05,
      "loss": 0.2657,
      "step": 530
    },
    {
      "epoch": 1.4100555011426705,
      "grad_norm": 0.2683992385864258,
      "learning_rate": 1.769825918762089e-05,
      "loss": 0.2734,
      "step": 540
    },
    {
      "epoch": 1.4361736859288279,
      "grad_norm": 0.2562316954135895,
      "learning_rate": 1.7408123791102515e-05,
      "loss": 0.2737,
      "step": 550
    },
    {
      "epoch": 1.4622918707149852,
      "grad_norm": 0.26707911491394043,
      "learning_rate": 1.7117988394584137e-05,
      "loss": 0.2534,
      "step": 560
    },
    {
      "epoch": 1.4884100555011428,
      "grad_norm": 0.28213635087013245,
      "learning_rate": 1.6827852998065763e-05,
      "loss": 0.2488,
      "step": 570
    },
    {
      "epoch": 1.5145282402873002,
      "grad_norm": 0.33098509907722473,
      "learning_rate": 1.653771760154739e-05,
      "loss": 0.2443,
      "step": 580
    },
    {
      "epoch": 1.5406464250734575,
      "grad_norm": 0.3213947117328644,
      "learning_rate": 1.6247582205029015e-05,
      "loss": 0.2335,
      "step": 590
    },
    {
      "epoch": 1.5667646098596149,
      "grad_norm": 0.3447439968585968,
      "learning_rate": 1.5957446808510637e-05,
      "loss": 0.2383,
      "step": 600
    },
    {
      "epoch": 1.5928827946457722,
      "grad_norm": 0.2642297148704529,
      "learning_rate": 1.5667311411992263e-05,
      "loss": 0.2724,
      "step": 610
    },
    {
      "epoch": 1.6190009794319296,
      "grad_norm": 0.3450152277946472,
      "learning_rate": 1.537717601547389e-05,
      "loss": 0.2408,
      "step": 620
    },
    {
      "epoch": 1.645119164218087,
      "grad_norm": 0.2866501212120056,
      "learning_rate": 1.5087040618955514e-05,
      "loss": 0.2717,
      "step": 630
    },
    {
      "epoch": 1.6712373490042443,
      "grad_norm": 0.3320681154727936,
      "learning_rate": 1.4796905222437138e-05,
      "loss": 0.2503,
      "step": 640
    },
    {
      "epoch": 1.6973555337904016,
      "grad_norm": 0.3560684025287628,
      "learning_rate": 1.4506769825918764e-05,
      "loss": 0.2716,
      "step": 650
    },
    {
      "epoch": 1.723473718576559,
      "grad_norm": 0.2683473825454712,
      "learning_rate": 1.4216634429400386e-05,
      "loss": 0.2351,
      "step": 660
    },
    {
      "epoch": 1.7495919033627163,
      "grad_norm": 0.34936392307281494,
      "learning_rate": 1.392649903288201e-05,
      "loss": 0.247,
      "step": 670
    },
    {
      "epoch": 1.7757100881488737,
      "grad_norm": 0.3231319487094879,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.2475,
      "step": 680
    },
    {
      "epoch": 1.801828272935031,
      "grad_norm": 0.3338012397289276,
      "learning_rate": 1.334622823984526e-05,
      "loss": 0.2429,
      "step": 690
    },
    {
      "epoch": 1.8279464577211884,
      "grad_norm": 0.4151914715766907,
      "learning_rate": 1.3056092843326887e-05,
      "loss": 0.246,
      "step": 700
    },
    {
      "epoch": 1.8540646425073457,
      "grad_norm": 0.323006808757782,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 0.2448,
      "step": 710
    },
    {
      "epoch": 1.880182827293503,
      "grad_norm": 0.3615120053291321,
      "learning_rate": 1.2475822050290135e-05,
      "loss": 0.2474,
      "step": 720
    },
    {
      "epoch": 1.9063010120796604,
      "grad_norm": 0.3660333752632141,
      "learning_rate": 1.2185686653771761e-05,
      "loss": 0.2297,
      "step": 730
    },
    {
      "epoch": 1.9324191968658178,
      "grad_norm": 0.3408561944961548,
      "learning_rate": 1.1895551257253385e-05,
      "loss": 0.2408,
      "step": 740
    },
    {
      "epoch": 1.958537381651975,
      "grad_norm": 0.3295958340167999,
      "learning_rate": 1.160541586073501e-05,
      "loss": 0.2329,
      "step": 750
    },
    {
      "epoch": 1.9846555664381325,
      "grad_norm": 0.30748242139816284,
      "learning_rate": 1.1315280464216634e-05,
      "loss": 0.2148,
      "step": 760
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3934667110443115,
      "eval_runtime": 41.1021,
      "eval_samples_per_second": 22.335,
      "eval_steps_per_second": 11.167,
      "step": 766
    },
    {
      "epoch": 2.0104472739144628,
      "grad_norm": 0.3356146812438965,
      "learning_rate": 1.1025145067698258e-05,
      "loss": 0.2499,
      "step": 770
    },
    {
      "epoch": 2.03656545870062,
      "grad_norm": 0.3222728967666626,
      "learning_rate": 1.0735009671179884e-05,
      "loss": 0.227,
      "step": 780
    },
    {
      "epoch": 2.0626836434867775,
      "grad_norm": 0.39890971779823303,
      "learning_rate": 1.0444874274661508e-05,
      "loss": 0.2218,
      "step": 790
    },
    {
      "epoch": 2.088801828272935,
      "grad_norm": 0.408120334148407,
      "learning_rate": 1.0154738878143134e-05,
      "loss": 0.2078,
      "step": 800
    },
    {
      "epoch": 2.1149200130590926,
      "grad_norm": 0.3901541233062744,
      "learning_rate": 9.864603481624759e-06,
      "loss": 0.2011,
      "step": 810
    },
    {
      "epoch": 2.14103819784525,
      "grad_norm": 0.3886492848396301,
      "learning_rate": 9.574468085106385e-06,
      "loss": 0.2151,
      "step": 820
    },
    {
      "epoch": 2.1671563826314073,
      "grad_norm": 0.39214348793029785,
      "learning_rate": 9.284332688588009e-06,
      "loss": 0.2441,
      "step": 830
    },
    {
      "epoch": 2.1932745674175647,
      "grad_norm": 0.3570252060890198,
      "learning_rate": 8.994197292069631e-06,
      "loss": 0.2163,
      "step": 840
    },
    {
      "epoch": 2.219392752203722,
      "grad_norm": 0.4596511423587799,
      "learning_rate": 8.704061895551257e-06,
      "loss": 0.2331,
      "step": 850
    },
    {
      "epoch": 2.2455109369898794,
      "grad_norm": 0.48779523372650146,
      "learning_rate": 8.413926499032882e-06,
      "loss": 0.2199,
      "step": 860
    },
    {
      "epoch": 2.2716291217760367,
      "grad_norm": 0.3428640365600586,
      "learning_rate": 8.123791102514507e-06,
      "loss": 0.2304,
      "step": 870
    },
    {
      "epoch": 2.297747306562194,
      "grad_norm": 0.39498019218444824,
      "learning_rate": 7.833655705996132e-06,
      "loss": 0.2148,
      "step": 880
    },
    {
      "epoch": 2.3238654913483514,
      "grad_norm": 0.39781302213668823,
      "learning_rate": 7.543520309477757e-06,
      "loss": 0.2401,
      "step": 890
    },
    {
      "epoch": 2.3499836761345088,
      "grad_norm": 0.43393346667289734,
      "learning_rate": 7.253384912959382e-06,
      "loss": 0.2184,
      "step": 900
    },
    {
      "epoch": 2.376101860920666,
      "grad_norm": 0.4301745593547821,
      "learning_rate": 6.963249516441005e-06,
      "loss": 0.2057,
      "step": 910
    },
    {
      "epoch": 2.4022200457068235,
      "grad_norm": 0.43270638585090637,
      "learning_rate": 6.67311411992263e-06,
      "loss": 0.2198,
      "step": 920
    },
    {
      "epoch": 2.428338230492981,
      "grad_norm": 0.4313347637653351,
      "learning_rate": 6.3829787234042555e-06,
      "loss": 0.2205,
      "step": 930
    },
    {
      "epoch": 2.454456415279138,
      "grad_norm": 0.4315342903137207,
      "learning_rate": 6.092843326885881e-06,
      "loss": 0.2168,
      "step": 940
    },
    {
      "epoch": 2.4805746000652955,
      "grad_norm": 0.4480975568294525,
      "learning_rate": 5.802707930367505e-06,
      "loss": 0.2189,
      "step": 950
    },
    {
      "epoch": 2.506692784851453,
      "grad_norm": 0.4834122955799103,
      "learning_rate": 5.512572533849129e-06,
      "loss": 0.2193,
      "step": 960
    },
    {
      "epoch": 2.53281096963761,
      "grad_norm": 0.4037538766860962,
      "learning_rate": 5.222437137330754e-06,
      "loss": 0.2139,
      "step": 970
    },
    {
      "epoch": 2.5589291544237676,
      "grad_norm": 0.3561624586582184,
      "learning_rate": 4.932301740812379e-06,
      "loss": 0.1906,
      "step": 980
    },
    {
      "epoch": 2.585047339209925,
      "grad_norm": 0.4143367409706116,
      "learning_rate": 4.642166344294004e-06,
      "loss": 0.2063,
      "step": 990
    },
    {
      "epoch": 2.6111655239960823,
      "grad_norm": 0.4470951557159424,
      "learning_rate": 4.352030947775629e-06,
      "loss": 0.2194,
      "step": 1000
    },
    {
      "epoch": 2.6372837087822396,
      "grad_norm": 0.4563806354999542,
      "learning_rate": 4.061895551257254e-06,
      "loss": 0.2084,
      "step": 1010
    },
    {
      "epoch": 2.663401893568397,
      "grad_norm": 0.4672696888446808,
      "learning_rate": 3.7717601547388784e-06,
      "loss": 0.2263,
      "step": 1020
    },
    {
      "epoch": 2.6895200783545543,
      "grad_norm": 0.4474937617778778,
      "learning_rate": 3.4816247582205027e-06,
      "loss": 0.2032,
      "step": 1030
    },
    {
      "epoch": 2.7156382631407117,
      "grad_norm": 0.5139485597610474,
      "learning_rate": 3.1914893617021277e-06,
      "loss": 0.1976,
      "step": 1040
    },
    {
      "epoch": 2.741756447926869,
      "grad_norm": 0.3937891721725464,
      "learning_rate": 2.9013539651837524e-06,
      "loss": 0.2145,
      "step": 1050
    },
    {
      "epoch": 2.7678746327130264,
      "grad_norm": 0.461599200963974,
      "learning_rate": 2.611218568665377e-06,
      "loss": 0.199,
      "step": 1060
    },
    {
      "epoch": 2.7939928174991837,
      "grad_norm": 0.28981783986091614,
      "learning_rate": 2.321083172147002e-06,
      "loss": 0.2192,
      "step": 1070
    },
    {
      "epoch": 2.820111002285341,
      "grad_norm": 0.48235049843788147,
      "learning_rate": 2.030947775628627e-06,
      "loss": 0.227,
      "step": 1080
    },
    {
      "epoch": 2.8462291870714984,
      "grad_norm": 0.5751634240150452,
      "learning_rate": 1.7408123791102513e-06,
      "loss": 0.2183,
      "step": 1090
    },
    {
      "epoch": 2.8723473718576558,
      "grad_norm": 0.3712913691997528,
      "learning_rate": 1.4506769825918762e-06,
      "loss": 0.1961,
      "step": 1100
    },
    {
      "epoch": 2.898465556643813,
      "grad_norm": 0.3893302381038666,
      "learning_rate": 1.160541586073501e-06,
      "loss": 0.2109,
      "step": 1110
    },
    {
      "epoch": 2.9245837414299705,
      "grad_norm": 0.5103141665458679,
      "learning_rate": 8.704061895551257e-07,
      "loss": 0.212,
      "step": 1120
    },
    {
      "epoch": 2.950701926216128,
      "grad_norm": 0.4350573718547821,
      "learning_rate": 5.802707930367505e-07,
      "loss": 0.2258,
      "step": 1130
    },
    {
      "epoch": 2.9768201110022856,
      "grad_norm": 0.4930060803890228,
      "learning_rate": 2.901353965183753e-07,
      "loss": 0.2049,
      "step": 1140
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.4022391736507416,
      "eval_runtime": 41.3609,
      "eval_samples_per_second": 22.195,
      "eval_steps_per_second": 11.097,
      "step": 1149
    }
  ],
  "logging_steps": 10,
  "max_steps": 1149,
  "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": 9.264298705040548e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}