nthakur's picture
Model save
cb8e87f verified
raw
history blame
29.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 200,
"global_step": 789,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012674271229404308,
"grad_norm": 0.8615043469450224,
"learning_rate": 2.531645569620253e-06,
"loss": 0.479,
"step": 1
},
{
"epoch": 0.0063371356147021544,
"grad_norm": 1.2064683000577734,
"learning_rate": 1.2658227848101267e-05,
"loss": 0.5395,
"step": 5
},
{
"epoch": 0.012674271229404309,
"grad_norm": 1.0410453983480228,
"learning_rate": 2.5316455696202533e-05,
"loss": 0.6061,
"step": 10
},
{
"epoch": 0.019011406844106463,
"grad_norm": 0.6487558463156515,
"learning_rate": 3.79746835443038e-05,
"loss": 0.5462,
"step": 15
},
{
"epoch": 0.025348542458808618,
"grad_norm": 0.5370587969238408,
"learning_rate": 5.0632911392405066e-05,
"loss": 0.4583,
"step": 20
},
{
"epoch": 0.031685678073510776,
"grad_norm": 0.5034416625324662,
"learning_rate": 6.329113924050633e-05,
"loss": 0.4883,
"step": 25
},
{
"epoch": 0.03802281368821293,
"grad_norm": 0.39983399371170963,
"learning_rate": 7.59493670886076e-05,
"loss": 0.3405,
"step": 30
},
{
"epoch": 0.044359949302915085,
"grad_norm": 0.43348705894690165,
"learning_rate": 8.860759493670887e-05,
"loss": 0.4164,
"step": 35
},
{
"epoch": 0.050697084917617236,
"grad_norm": 0.38455150629020124,
"learning_rate": 0.00010126582278481013,
"loss": 0.3655,
"step": 40
},
{
"epoch": 0.057034220532319393,
"grad_norm": 0.4620346635793738,
"learning_rate": 0.0001139240506329114,
"loss": 0.321,
"step": 45
},
{
"epoch": 0.06337135614702155,
"grad_norm": 0.5487179791839946,
"learning_rate": 0.00012658227848101267,
"loss": 0.3917,
"step": 50
},
{
"epoch": 0.0697084917617237,
"grad_norm": 0.4322988318215336,
"learning_rate": 0.00013924050632911395,
"loss": 0.2954,
"step": 55
},
{
"epoch": 0.07604562737642585,
"grad_norm": 0.45659465975830865,
"learning_rate": 0.0001518987341772152,
"loss": 0.3362,
"step": 60
},
{
"epoch": 0.08238276299112801,
"grad_norm": 0.5012029391973714,
"learning_rate": 0.00016455696202531648,
"loss": 0.3201,
"step": 65
},
{
"epoch": 0.08871989860583017,
"grad_norm": 0.4257121777036391,
"learning_rate": 0.00017721518987341773,
"loss": 0.3103,
"step": 70
},
{
"epoch": 0.09505703422053231,
"grad_norm": 0.49930786967179713,
"learning_rate": 0.00018987341772151899,
"loss": 0.3895,
"step": 75
},
{
"epoch": 0.10139416983523447,
"grad_norm": 0.3987283812690162,
"learning_rate": 0.00019999902106840922,
"loss": 0.2607,
"step": 80
},
{
"epoch": 0.10773130544993663,
"grad_norm": 0.4941124105408692,
"learning_rate": 0.00019996476047513454,
"loss": 0.3509,
"step": 85
},
{
"epoch": 0.11406844106463879,
"grad_norm": 0.35089312674321954,
"learning_rate": 0.00019988157246677513,
"loss": 0.323,
"step": 90
},
{
"epoch": 0.12040557667934093,
"grad_norm": 0.4238705680350401,
"learning_rate": 0.00019974949775942134,
"loss": 0.2834,
"step": 95
},
{
"epoch": 0.1267427122940431,
"grad_norm": 0.45602469539148643,
"learning_rate": 0.00019956860099659346,
"loss": 0.3492,
"step": 100
},
{
"epoch": 0.13307984790874525,
"grad_norm": 0.40420721250262537,
"learning_rate": 0.00019933897071760235,
"loss": 0.2865,
"step": 105
},
{
"epoch": 0.1394169835234474,
"grad_norm": 0.47242229343887376,
"learning_rate": 0.00019906071931421413,
"loss": 0.3047,
"step": 110
},
{
"epoch": 0.14575411913814956,
"grad_norm": 0.3662230634874705,
"learning_rate": 0.00019873398297564037,
"loss": 0.3183,
"step": 115
},
{
"epoch": 0.1520912547528517,
"grad_norm": 0.3786550636833906,
"learning_rate": 0.00019835892162188066,
"loss": 0.2903,
"step": 120
},
{
"epoch": 0.15842839036755388,
"grad_norm": 0.42556611928998644,
"learning_rate": 0.00019793571882545047,
"loss": 0.3298,
"step": 125
},
{
"epoch": 0.16476552598225602,
"grad_norm": 0.3477579859642712,
"learning_rate": 0.0001974645817215322,
"loss": 0.2811,
"step": 130
},
{
"epoch": 0.17110266159695817,
"grad_norm": 0.338149840344514,
"learning_rate": 0.0001969457409065933,
"loss": 0.3218,
"step": 135
},
{
"epoch": 0.17743979721166034,
"grad_norm": 0.31604418234996284,
"learning_rate": 0.0001963794503255219,
"loss": 0.3181,
"step": 140
},
{
"epoch": 0.18377693282636248,
"grad_norm": 0.37941148877648684,
"learning_rate": 0.00019576598714733431,
"loss": 0.2708,
"step": 145
},
{
"epoch": 0.19011406844106463,
"grad_norm": 0.41662892297732984,
"learning_rate": 0.00019510565162951537,
"loss": 0.3133,
"step": 150
},
{
"epoch": 0.1964512040557668,
"grad_norm": 0.33440472234808516,
"learning_rate": 0.0001943987669710586,
"loss": 0.3027,
"step": 155
},
{
"epoch": 0.20278833967046894,
"grad_norm": 0.3858834779514916,
"learning_rate": 0.0001936456791542776,
"loss": 0.3148,
"step": 160
},
{
"epoch": 0.20912547528517111,
"grad_norm": 0.3588666651678752,
"learning_rate": 0.000192846756775466,
"loss": 0.3038,
"step": 165
},
{
"epoch": 0.21546261089987326,
"grad_norm": 0.3923595420574365,
"learning_rate": 0.00019200239086448933,
"loss": 0.251,
"step": 170
},
{
"epoch": 0.2217997465145754,
"grad_norm": 0.3720411933468231,
"learning_rate": 0.0001911129946933968,
"loss": 0.3066,
"step": 175
},
{
"epoch": 0.22813688212927757,
"grad_norm": 0.32287305381502635,
"learning_rate": 0.00019017900357414669,
"loss": 0.3021,
"step": 180
},
{
"epoch": 0.23447401774397972,
"grad_norm": 0.3574163723783811,
"learning_rate": 0.00018920087464554427,
"loss": 0.3156,
"step": 185
},
{
"epoch": 0.24081115335868186,
"grad_norm": 0.4152681195493882,
"learning_rate": 0.0001881790866494969,
"loss": 0.2839,
"step": 190
},
{
"epoch": 0.24714828897338403,
"grad_norm": 0.36834582922377895,
"learning_rate": 0.00018711413969669526,
"loss": 0.2945,
"step": 195
},
{
"epoch": 0.2534854245880862,
"grad_norm": 0.39981519235640095,
"learning_rate": 0.00018600655502183612,
"loss": 0.3189,
"step": 200
},
{
"epoch": 0.2534854245880862,
"eval_loss": 0.28277337551116943,
"eval_runtime": 1084.4496,
"eval_samples_per_second": 3.689,
"eval_steps_per_second": 0.115,
"step": 200
},
{
"epoch": 0.2598225602027883,
"grad_norm": 0.31219177577589374,
"learning_rate": 0.0001848568747285054,
"loss": 0.2299,
"step": 205
},
{
"epoch": 0.2661596958174905,
"grad_norm": 0.37017559919032633,
"learning_rate": 0.00018366566152384773,
"loss": 0.2753,
"step": 210
},
{
"epoch": 0.27249683143219267,
"grad_norm": 0.29894743373031823,
"learning_rate": 0.00018243349844315117,
"loss": 0.2734,
"step": 215
},
{
"epoch": 0.2788339670468948,
"grad_norm": 0.3227139696142255,
"learning_rate": 0.00018116098856448253,
"loss": 0.2595,
"step": 220
},
{
"epoch": 0.28517110266159695,
"grad_norm": 0.3780707564332847,
"learning_rate": 0.00017984875471351302,
"loss": 0.3107,
"step": 225
},
{
"epoch": 0.2915082382762991,
"grad_norm": 0.31519655631233245,
"learning_rate": 0.00017849743915867807,
"loss": 0.2336,
"step": 230
},
{
"epoch": 0.29784537389100124,
"grad_norm": 0.35840275346083816,
"learning_rate": 0.00017710770329682144,
"loss": 0.2939,
"step": 235
},
{
"epoch": 0.3041825095057034,
"grad_norm": 0.2971942370747859,
"learning_rate": 0.0001756802273294766,
"loss": 0.2959,
"step": 240
},
{
"epoch": 0.3105196451204056,
"grad_norm": 0.3247193570102783,
"learning_rate": 0.0001742157099299445,
"loss": 0.2373,
"step": 245
},
{
"epoch": 0.31685678073510776,
"grad_norm": 0.38491700907647547,
"learning_rate": 0.00017271486790133023,
"loss": 0.3272,
"step": 250
},
{
"epoch": 0.3231939163498099,
"grad_norm": 0.3075011053275653,
"learning_rate": 0.00017117843582570608,
"loss": 0.2377,
"step": 255
},
{
"epoch": 0.32953105196451205,
"grad_norm": 0.31453423737207853,
"learning_rate": 0.00016960716570457292,
"loss": 0.2842,
"step": 260
},
{
"epoch": 0.3358681875792142,
"grad_norm": 0.24817557882025235,
"learning_rate": 0.00016800182659079568,
"loss": 0.2721,
"step": 265
},
{
"epoch": 0.34220532319391633,
"grad_norm": 0.3377039172873109,
"learning_rate": 0.00016636320421219278,
"loss": 0.2463,
"step": 270
},
{
"epoch": 0.3485424588086185,
"grad_norm": 0.3661471684768712,
"learning_rate": 0.00016469210058696446,
"loss": 0.3025,
"step": 275
},
{
"epoch": 0.3548795944233207,
"grad_norm": 0.27351558488185734,
"learning_rate": 0.0001629893336311477,
"loss": 0.2335,
"step": 280
},
{
"epoch": 0.3612167300380228,
"grad_norm": 0.4358770290773004,
"learning_rate": 0.00016125573675828983,
"loss": 0.279,
"step": 285
},
{
"epoch": 0.36755386565272496,
"grad_norm": 0.2774172437400498,
"learning_rate": 0.00015949215847153717,
"loss": 0.2581,
"step": 290
},
{
"epoch": 0.37389100126742714,
"grad_norm": 0.28991353506835355,
"learning_rate": 0.00015769946194833817,
"loss": 0.2314,
"step": 295
},
{
"epoch": 0.38022813688212925,
"grad_norm": 0.4117767724226869,
"learning_rate": 0.00015587852461796376,
"loss": 0.3218,
"step": 300
},
{
"epoch": 0.3865652724968314,
"grad_norm": 0.31038917537934363,
"learning_rate": 0.00015403023773205286,
"loss": 0.2315,
"step": 305
},
{
"epoch": 0.3929024081115336,
"grad_norm": 0.3358971163136089,
"learning_rate": 0.00015215550592839218,
"loss": 0.302,
"step": 310
},
{
"epoch": 0.39923954372623577,
"grad_norm": 0.24064351622215968,
"learning_rate": 0.00015025524678814427,
"loss": 0.2795,
"step": 315
},
{
"epoch": 0.4055766793409379,
"grad_norm": 0.32648334764287845,
"learning_rate": 0.00014833039038674047,
"loss": 0.2398,
"step": 320
},
{
"epoch": 0.41191381495564006,
"grad_norm": 0.4100611479861272,
"learning_rate": 0.0001463818788386588,
"loss": 0.2849,
"step": 325
},
{
"epoch": 0.41825095057034223,
"grad_norm": 0.333871597957756,
"learning_rate": 0.00014441066583630906,
"loss": 0.2297,
"step": 330
},
{
"epoch": 0.42458808618504434,
"grad_norm": 0.34174204454819196,
"learning_rate": 0.00014241771618325123,
"loss": 0.2704,
"step": 335
},
{
"epoch": 0.4309252217997465,
"grad_norm": 0.2539128471983557,
"learning_rate": 0.00014040400532197583,
"loss": 0.2579,
"step": 340
},
{
"epoch": 0.4372623574144487,
"grad_norm": 0.29762852904975656,
"learning_rate": 0.0001383705188564767,
"loss": 0.255,
"step": 345
},
{
"epoch": 0.4435994930291508,
"grad_norm": 0.3477101390224288,
"learning_rate": 0.00013631825206985063,
"loss": 0.2841,
"step": 350
},
{
"epoch": 0.449936628643853,
"grad_norm": 0.2807172517529508,
"learning_rate": 0.0001342482094371591,
"loss": 0.2112,
"step": 355
},
{
"epoch": 0.45627376425855515,
"grad_norm": 0.3838095185531826,
"learning_rate": 0.00013216140413379167,
"loss": 0.282,
"step": 360
},
{
"epoch": 0.46261089987325726,
"grad_norm": 0.2421625693621495,
"learning_rate": 0.00013005885753957048,
"loss": 0.2473,
"step": 365
},
{
"epoch": 0.46894803548795944,
"grad_norm": 0.32700829134754156,
"learning_rate": 0.0001279415987388395,
"loss": 0.2174,
"step": 370
},
{
"epoch": 0.4752851711026616,
"grad_norm": 0.3713274528328548,
"learning_rate": 0.0001258106640167826,
"loss": 0.283,
"step": 375
},
{
"epoch": 0.4816223067173637,
"grad_norm": 0.27730345855582755,
"learning_rate": 0.0001236670963522172,
"loss": 0.2021,
"step": 380
},
{
"epoch": 0.4879594423320659,
"grad_norm": 0.34446917830376517,
"learning_rate": 0.00012151194490711178,
"loss": 0.2561,
"step": 385
},
{
"epoch": 0.49429657794676807,
"grad_norm": 0.2522933072667094,
"learning_rate": 0.00011934626451307726,
"loss": 0.2433,
"step": 390
},
{
"epoch": 0.5006337135614702,
"grad_norm": 0.3469006061112617,
"learning_rate": 0.00011717111515508319,
"loss": 0.2266,
"step": 395
},
{
"epoch": 0.5069708491761724,
"grad_norm": 0.3778944814729631,
"learning_rate": 0.00011498756145265144,
"loss": 0.2906,
"step": 400
},
{
"epoch": 0.5069708491761724,
"eval_loss": 0.2465018332004547,
"eval_runtime": 1086.0248,
"eval_samples_per_second": 3.683,
"eval_steps_per_second": 0.115,
"step": 400
},
{
"epoch": 0.5133079847908745,
"grad_norm": 0.2906640770941992,
"learning_rate": 0.00011279667213878205,
"loss": 0.2329,
"step": 405
},
{
"epoch": 0.5196451204055766,
"grad_norm": 0.3562675808467966,
"learning_rate": 0.00011059951953686535,
"loss": 0.2727,
"step": 410
},
{
"epoch": 0.5259822560202788,
"grad_norm": 0.23100289329465973,
"learning_rate": 0.00010839717903583684,
"loss": 0.2559,
"step": 415
},
{
"epoch": 0.532319391634981,
"grad_norm": 0.31979110117969145,
"learning_rate": 0.00010619072856383181,
"loss": 0.2413,
"step": 420
},
{
"epoch": 0.5386565272496832,
"grad_norm": 0.3131449805956835,
"learning_rate": 0.00010398124806059701,
"loss": 0.2807,
"step": 425
},
{
"epoch": 0.5449936628643853,
"grad_norm": 0.30855801225213353,
"learning_rate": 0.00010176981894891768,
"loss": 0.1961,
"step": 430
},
{
"epoch": 0.5513307984790875,
"grad_norm": 0.3422494582211193,
"learning_rate": 9.955752360531896e-05,
"loss": 0.2805,
"step": 435
},
{
"epoch": 0.5576679340937896,
"grad_norm": 0.26688868743798966,
"learning_rate": 9.734544483030026e-05,
"loss": 0.2597,
"step": 440
},
{
"epoch": 0.5640050697084917,
"grad_norm": 0.3161252521303147,
"learning_rate": 9.513466531836221e-05,
"loss": 0.2166,
"step": 445
},
{
"epoch": 0.5703422053231939,
"grad_norm": 0.3401785018630494,
"learning_rate": 9.292626712808556e-05,
"loss": 0.2827,
"step": 450
},
{
"epoch": 0.5766793409378961,
"grad_norm": 0.3036061299387351,
"learning_rate": 9.072133115252112e-05,
"loss": 0.2254,
"step": 455
},
{
"epoch": 0.5830164765525983,
"grad_norm": 0.35415945685790207,
"learning_rate": 8.85209365901505e-05,
"loss": 0.2692,
"step": 460
},
{
"epoch": 0.5893536121673004,
"grad_norm": 0.25401069755470806,
"learning_rate": 8.632616041667577e-05,
"loss": 0.2539,
"step": 465
},
{
"epoch": 0.5956907477820025,
"grad_norm": 0.31003086790259704,
"learning_rate": 8.41380768578976e-05,
"loss": 0.2271,
"step": 470
},
{
"epoch": 0.6020278833967047,
"grad_norm": 0.3237135373224526,
"learning_rate": 8.195775686393897e-05,
"loss": 0.2792,
"step": 475
},
{
"epoch": 0.6083650190114068,
"grad_norm": 0.2952913468902984,
"learning_rate": 7.978626758507217e-05,
"loss": 0.2033,
"step": 480
},
{
"epoch": 0.614702154626109,
"grad_norm": 0.32514176968318775,
"learning_rate": 7.762467184940574e-05,
"loss": 0.2632,
"step": 485
},
{
"epoch": 0.6210392902408112,
"grad_norm": 0.2704128994845209,
"learning_rate": 7.547402764268689e-05,
"loss": 0.2657,
"step": 490
},
{
"epoch": 0.6273764258555133,
"grad_norm": 0.3419677722251191,
"learning_rate": 7.333538759047389e-05,
"loss": 0.2432,
"step": 495
},
{
"epoch": 0.6337135614702155,
"grad_norm": 0.3336718483492428,
"learning_rate": 7.120979844293201e-05,
"loss": 0.2789,
"step": 500
},
{
"epoch": 0.6400506970849176,
"grad_norm": 0.28861366582406006,
"learning_rate": 6.909830056250527e-05,
"loss": 0.2185,
"step": 505
},
{
"epoch": 0.6463878326996197,
"grad_norm": 0.3292639675337998,
"learning_rate": 6.700192741471447e-05,
"loss": 0.2622,
"step": 510
},
{
"epoch": 0.6527249683143219,
"grad_norm": 0.2539285743910528,
"learning_rate": 6.4921705062331e-05,
"loss": 0.2442,
"step": 515
},
{
"epoch": 0.6590621039290241,
"grad_norm": 0.3067269034698268,
"learning_rate": 6.285865166317386e-05,
"loss": 0.2143,
"step": 520
},
{
"epoch": 0.6653992395437263,
"grad_norm": 0.3245132022152399,
"learning_rate": 6.081377697177576e-05,
"loss": 0.2719,
"step": 525
},
{
"epoch": 0.6717363751584284,
"grad_norm": 0.27285602978719187,
"learning_rate": 5.8788081845162246e-05,
"loss": 0.205,
"step": 530
},
{
"epoch": 0.6780735107731305,
"grad_norm": 0.33017438859174614,
"learning_rate": 5.678255775298542e-05,
"loss": 0.2595,
"step": 535
},
{
"epoch": 0.6844106463878327,
"grad_norm": 0.22042843479196494,
"learning_rate": 5.479818629225259e-05,
"loss": 0.2508,
"step": 540
},
{
"epoch": 0.6907477820025348,
"grad_norm": 0.3262775579247169,
"learning_rate": 5.2835938706886966e-05,
"loss": 0.2252,
"step": 545
},
{
"epoch": 0.697084917617237,
"grad_norm": 0.3604718135367501,
"learning_rate": 5.0896775412355434e-05,
"loss": 0.2703,
"step": 550
},
{
"epoch": 0.7034220532319392,
"grad_norm": 0.2849330234510489,
"learning_rate": 4.89816455255966e-05,
"loss": 0.1977,
"step": 555
},
{
"epoch": 0.7097591888466414,
"grad_norm": 0.2992590502661103,
"learning_rate": 4.7091486400478604e-05,
"loss": 0.252,
"step": 560
},
{
"epoch": 0.7160963244613435,
"grad_norm": 0.2424976560859796,
"learning_rate": 4.5227223169014456e-05,
"loss": 0.2465,
"step": 565
},
{
"epoch": 0.7224334600760456,
"grad_norm": 0.35965307208087977,
"learning_rate": 4.338976828855939e-05,
"loss": 0.2249,
"step": 570
},
{
"epoch": 0.7287705956907478,
"grad_norm": 0.3741830397170476,
"learning_rate": 4.1580021095211486e-05,
"loss": 0.284,
"step": 575
},
{
"epoch": 0.7351077313054499,
"grad_norm": 0.2903803822883755,
"learning_rate": 3.9798867363634814e-05,
"loss": 0.2123,
"step": 580
},
{
"epoch": 0.7414448669201521,
"grad_norm": 0.31710020807356026,
"learning_rate": 3.804717887351991e-05,
"loss": 0.2605,
"step": 585
},
{
"epoch": 0.7477820025348543,
"grad_norm": 0.24733722916292933,
"learning_rate": 3.632581298289427e-05,
"loss": 0.2289,
"step": 590
},
{
"epoch": 0.7541191381495564,
"grad_norm": 0.3001878742603873,
"learning_rate": 3.4635612208491194e-05,
"loss": 0.2322,
"step": 595
},
{
"epoch": 0.7604562737642585,
"grad_norm": 0.3250883573895976,
"learning_rate": 3.2977403813382926e-05,
"loss": 0.2525,
"step": 600
},
{
"epoch": 0.7604562737642585,
"eval_loss": 0.2325838953256607,
"eval_runtime": 1086.1174,
"eval_samples_per_second": 3.683,
"eval_steps_per_second": 0.115,
"step": 600
},
{
"epoch": 0.7667934093789607,
"grad_norm": 0.3246331902911399,
"learning_rate": 3.135199940207947e-05,
"loss": 0.2206,
"step": 605
},
{
"epoch": 0.7731305449936628,
"grad_norm": 0.3364965552008111,
"learning_rate": 2.976019452329153e-05,
"loss": 0.2566,
"step": 610
},
{
"epoch": 0.779467680608365,
"grad_norm": 0.22924356326780843,
"learning_rate": 2.8202768280551894e-05,
"loss": 0.2448,
"step": 615
},
{
"epoch": 0.7858048162230672,
"grad_norm": 0.3207071242715804,
"learning_rate": 2.6680482950885777e-05,
"loss": 0.2269,
"step": 620
},
{
"epoch": 0.7921419518377694,
"grad_norm": 0.37606836614121164,
"learning_rate": 2.5194083611716935e-05,
"loss": 0.27,
"step": 625
},
{
"epoch": 0.7984790874524715,
"grad_norm": 0.2830616844795413,
"learning_rate": 2.374429777619205e-05,
"loss": 0.1848,
"step": 630
},
{
"epoch": 0.8048162230671736,
"grad_norm": 0.3123281734582231,
"learning_rate": 2.2331835037101823e-05,
"loss": 0.2562,
"step": 635
},
{
"epoch": 0.8111533586818758,
"grad_norm": 0.27281906149266577,
"learning_rate": 2.0957386719573224e-05,
"loss": 0.2417,
"step": 640
},
{
"epoch": 0.8174904942965779,
"grad_norm": 0.3463842809980822,
"learning_rate": 1.962162554270267e-05,
"loss": 0.2108,
"step": 645
},
{
"epoch": 0.8238276299112801,
"grad_norm": 0.35511851586585724,
"learning_rate": 1.83252052902961e-05,
"loss": 0.2789,
"step": 650
},
{
"epoch": 0.8301647655259823,
"grad_norm": 0.2720460231999165,
"learning_rate": 1.7068760490876422e-05,
"loss": 0.1886,
"step": 655
},
{
"epoch": 0.8365019011406845,
"grad_norm": 0.323785370919597,
"learning_rate": 1.5852906107115893e-05,
"loss": 0.2617,
"step": 660
},
{
"epoch": 0.8428390367553865,
"grad_norm": 0.23954436901187928,
"learning_rate": 1.4678237234844649e-05,
"loss": 0.2501,
"step": 665
},
{
"epoch": 0.8491761723700887,
"grad_norm": 0.3169133202131331,
"learning_rate": 1.354532881178301e-05,
"loss": 0.1988,
"step": 670
},
{
"epoch": 0.8555133079847909,
"grad_norm": 0.3516256902668012,
"learning_rate": 1.2454735336140167e-05,
"loss": 0.2765,
"step": 675
},
{
"epoch": 0.861850443599493,
"grad_norm": 0.2923347791144997,
"learning_rate": 1.1406990595216971e-05,
"loss": 0.2065,
"step": 680
},
{
"epoch": 0.8681875792141952,
"grad_norm": 0.30823497046755327,
"learning_rate": 1.0402607404145449e-05,
"loss": 0.2623,
"step": 685
},
{
"epoch": 0.8745247148288974,
"grad_norm": 0.25292131222665615,
"learning_rate": 9.442077354893198e-06,
"loss": 0.2461,
"step": 690
},
{
"epoch": 0.8808618504435995,
"grad_norm": 0.32414756933713984,
"learning_rate": 8.525870575655392e-06,
"loss": 0.217,
"step": 695
},
{
"epoch": 0.8871989860583016,
"grad_norm": 0.3423100582401461,
"learning_rate": 7.654435500752055e-06,
"loss": 0.2675,
"step": 700
},
{
"epoch": 0.8935361216730038,
"grad_norm": 0.29544160874192754,
"learning_rate": 6.828198651143425e-06,
"loss": 0.1927,
"step": 705
},
{
"epoch": 0.899873257287706,
"grad_norm": 0.32477510117980407,
"learning_rate": 6.047564425670749e-06,
"loss": 0.2613,
"step": 710
},
{
"epoch": 0.9062103929024081,
"grad_norm": 0.23676655623304554,
"learning_rate": 5.312914903124566e-06,
"loss": 0.2414,
"step": 715
},
{
"epoch": 0.9125475285171103,
"grad_norm": 0.2967989522178623,
"learning_rate": 4.624609655237544e-06,
"loss": 0.2002,
"step": 720
},
{
"epoch": 0.9188846641318125,
"grad_norm": 0.340334151463555,
"learning_rate": 3.982985570693354e-06,
"loss": 0.2764,
"step": 725
},
{
"epoch": 0.9252217997465145,
"grad_norm": 0.2776495387493925,
"learning_rate": 3.388356690237582e-06,
"loss": 0.1859,
"step": 730
},
{
"epoch": 0.9315589353612167,
"grad_norm": 0.37073108669893173,
"learning_rate": 2.84101405297158e-06,
"loss": 0.2378,
"step": 735
},
{
"epoch": 0.9378960709759189,
"grad_norm": 0.2570912693772944,
"learning_rate": 2.341225553904336e-06,
"loss": 0.2398,
"step": 740
},
{
"epoch": 0.944233206590621,
"grad_norm": 0.3306131510091784,
"learning_rate": 1.8892358128322018e-06,
"loss": 0.2092,
"step": 745
},
{
"epoch": 0.9505703422053232,
"grad_norm": 0.33888565708232804,
"learning_rate": 1.4852660546105234e-06,
"loss": 0.2873,
"step": 750
},
{
"epoch": 0.9569074778200254,
"grad_norm": 0.2906867586955816,
"learning_rate": 1.1295140008758864e-06,
"loss": 0.2079,
"step": 755
},
{
"epoch": 0.9632446134347274,
"grad_norm": 0.34402820600782946,
"learning_rate": 8.221537732719275e-07,
"loss": 0.2648,
"step": 760
},
{
"epoch": 0.9695817490494296,
"grad_norm": 0.26017431588284967,
"learning_rate": 5.633358082260954e-07,
"loss": 0.2481,
"step": 765
},
{
"epoch": 0.9759188846641318,
"grad_norm": 0.3339069885340444,
"learning_rate": 3.5318678331904833e-07,
"loss": 0.2237,
"step": 770
},
{
"epoch": 0.982256020278834,
"grad_norm": 0.34754105161997045,
"learning_rate": 1.9180955528270706e-07,
"loss": 0.27,
"step": 775
},
{
"epoch": 0.9885931558935361,
"grad_norm": 0.3246226295094946,
"learning_rate": 7.928310965742425e-08,
"loss": 0.2226,
"step": 780
},
{
"epoch": 0.9949302915082383,
"grad_norm": 0.31594487456225406,
"learning_rate": 1.5662522132742218e-08,
"loss": 0.2444,
"step": 785
},
{
"epoch": 1.0,
"step": 789,
"total_flos": 1.0371979095834624e+16,
"train_loss": 0.2726454405050314,
"train_runtime": 20804.2809,
"train_samples_per_second": 1.213,
"train_steps_per_second": 0.038
}
],
"logging_steps": 5,
"max_steps": 789,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.0371979095834624e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}