{ "config": { "model": "google/gemma-4-E4B-it", "revision": "ee0ef6023621cff504d758262d4e04895a5af4a2", "data": "/kaggle/working/star3.jsonl", "out_dir": "/kaggle/working/adapter", "epochs": 2, "lr": 0.0001, "batch_size": 4, "grad_accum": 4, "max_length": 1024, "rank": 16, "alpha": 32, "dropout": 0.05, "seed": 0 }, "dtype": "torch.float16", "grad_scaling": true, "target_modules": 342, "base_params": 7463013376, "adapter_params": 38666240, "total_params": 7501679616, "examples": 4073, "trained_examples": 4073, "dropped_too_long": 0, "dropped_misaligned": 0, "skipped_steps": 0, "seconds": 15551.6, "tokens_per_s": 317.6, "peak_memory_gb": [ 10.56, 6.99 ], "steps": [ { "step": 1, "epoch": 0, "loss": 0.19640883523944777, "lr": 0.0, "grad_norm": 0.4852641522884369, "skipped": false, "seconds": 29.4 }, { "step": 2, "epoch": 0, "loss": 0.2024406308274182, "lr": 6.666666666666667e-06, "grad_norm": 0.48907169699668884, "skipped": false, "seconds": 58.9 }, { "step": 3, "epoch": 0, "loss": 0.20496504929589732, "lr": 1.3333333333333333e-05, "grad_norm": 0.5109589695930481, "skipped": false, "seconds": 89.4 }, { "step": 4, "epoch": 0, "loss": 0.20524678683676226, "lr": 2e-05, "grad_norm": 0.5412611365318298, "skipped": false, "seconds": 120.8 }, { "step": 5, "epoch": 0, "loss": 0.16709267570479677, "lr": 2.6666666666666667e-05, "grad_norm": 0.5452609658241272, "skipped": false, "seconds": 151.0 }, { "step": 6, "epoch": 0, "loss": 0.15597860216284942, "lr": 3.3333333333333335e-05, "grad_norm": 0.4582180082798004, "skipped": false, "seconds": 180.9 }, { "step": 7, "epoch": 0, "loss": 0.14760536539304112, "lr": 4e-05, "grad_norm": 0.3433503210544586, "skipped": false, "seconds": 210.8 }, { "step": 8, "epoch": 0, "loss": 0.14063837973937082, "lr": 4.666666666666667e-05, "grad_norm": 0.304032564163208, "skipped": false, "seconds": 241.3 }, { "step": 9, "epoch": 0, "loss": 0.15517175885577025, "lr": 5.333333333333333e-05, "grad_norm": 0.2853395938873291, "skipped": false, "seconds": 271.0 }, { "step": 10, "epoch": 0, "loss": 0.12460355233487874, "lr": 6e-05, "grad_norm": 0.26190483570098877, "skipped": false, "seconds": 301.3 }, { "step": 11, "epoch": 0, "loss": 0.13429050899623296, "lr": 6.666666666666667e-05, "grad_norm": 0.2822328805923462, "skipped": false, "seconds": 332.0 }, { "step": 12, "epoch": 0, "loss": 0.10786084480626937, "lr": 7.333333333333333e-05, "grad_norm": 0.2527726888656616, "skipped": false, "seconds": 360.5 }, { "step": 13, "epoch": 0, "loss": 0.09978185194823579, "lr": 8e-05, "grad_norm": 0.23101957142353058, "skipped": false, "seconds": 391.4 }, { "step": 14, "epoch": 0, "loss": 0.10522525868517288, "lr": 8.666666666666667e-05, "grad_norm": 0.2543775737285614, "skipped": false, "seconds": 422.5 }, { "step": 15, "epoch": 0, "loss": 0.08935808227175758, "lr": 9.333333333333334e-05, "grad_norm": 0.24526648223400116, "skipped": false, "seconds": 452.1 }, { "step": 16, "epoch": 0, "loss": 0.10548639101148338, "lr": 0.0001, "grad_norm": 0.30216461420059204, "skipped": false, "seconds": 484.5 }, { "step": 17, "epoch": 0, "loss": 0.0861717793149071, "lr": 9.999899300364532e-05, "grad_norm": 0.26806312799453735, "skipped": false, "seconds": 515.7 }, { "step": 18, "epoch": 0, "loss": 0.08647315657249598, "lr": 9.999597205514297e-05, "grad_norm": 0.3897492587566376, "skipped": false, "seconds": 546.5 }, { "step": 19, "epoch": 0, "loss": 0.07331878050296768, "lr": 9.99909372761763e-05, "grad_norm": 0.2865033745765686, "skipped": false, "seconds": 575.8 }, { "step": 20, "epoch": 0, "loss": 0.0808455167275755, "lr": 9.998388886954547e-05, "grad_norm": 0.3762819170951843, "skipped": false, "seconds": 604.1 }, { "step": 21, "epoch": 0, "loss": 0.08293077495736136, "lr": 9.997482711915927e-05, "grad_norm": 0.3262479901313782, "skipped": false, "seconds": 635.3 }, { "step": 22, "epoch": 0, "loss": 0.0765426305353788, "lr": 9.996375239002369e-05, "grad_norm": 0.36088672280311584, "skipped": false, "seconds": 664.5 }, { "step": 23, "epoch": 0, "loss": 0.08666027548914276, "lr": 9.99506651282272e-05, "grad_norm": 0.5469640493392944, "skipped": false, "seconds": 695.4 }, { "step": 24, "epoch": 0, "loss": 0.08630259219662725, "lr": 9.993556586092281e-05, "grad_norm": 0.456892192363739, "skipped": false, "seconds": 728.2 }, { "step": 25, "epoch": 0, "loss": 0.0724076038978558, "lr": 9.991845519630678e-05, "grad_norm": 0.39262059330940247, "skipped": false, "seconds": 758.8 }, { "step": 26, "epoch": 0, "loss": 0.07770107819389818, "lr": 9.989933382359422e-05, "grad_norm": 0.4262242317199707, "skipped": false, "seconds": 791.2 }, { "step": 27, "epoch": 0, "loss": 0.06933413065568625, "lr": 9.987820251299122e-05, "grad_norm": 0.46644866466522217, "skipped": false, "seconds": 821.9 }, { "step": 28, "epoch": 0, "loss": 0.065214456355704, "lr": 9.985506211566388e-05, "grad_norm": 0.9025358557701111, "skipped": false, "seconds": 852.3 }, { "step": 29, "epoch": 0, "loss": 0.06811053849340527, "lr": 9.982991356370404e-05, "grad_norm": 0.4470258355140686, "skipped": false, "seconds": 881.8 }, { "step": 30, "epoch": 0, "loss": 0.053144117122032736, "lr": 9.98027578700917e-05, "grad_norm": 0.38273853063583374, "skipped": false, "seconds": 912.0 }, { "step": 31, "epoch": 0, "loss": 0.05634953098012355, "lr": 9.977359612865423e-05, "grad_norm": 0.4882364273071289, "skipped": false, "seconds": 941.3 }, { "step": 32, "epoch": 0, "loss": 0.055631592902682075, "lr": 9.974242951402235e-05, "grad_norm": 0.3918277621269226, "skipped": false, "seconds": 971.1 }, { "step": 33, "epoch": 0, "loss": 0.07527670451454374, "lr": 9.970925928158274e-05, "grad_norm": 0.5305290222167969, "skipped": false, "seconds": 1002.1 }, { "step": 34, "epoch": 0, "loss": 0.05458790223464191, "lr": 9.967408676742751e-05, "grad_norm": 0.4513584077358246, "skipped": false, "seconds": 1031.2 }, { "step": 35, "epoch": 0, "loss": 0.050869956201693954, "lr": 9.963691338830044e-05, "grad_norm": 0.36274057626724243, "skipped": false, "seconds": 1061.9 }, { "step": 36, "epoch": 0, "loss": 0.0570102071433521, "lr": 9.959774064153977e-05, "grad_norm": 0.42373621463775635, "skipped": false, "seconds": 1091.4 }, { "step": 37, "epoch": 0, "loss": 0.05033422113724285, "lr": 9.955657010501806e-05, "grad_norm": 0.46532633900642395, "skipped": false, "seconds": 1121.0 }, { "step": 38, "epoch": 0, "loss": 0.054250309157325254, "lr": 9.951340343707852e-05, "grad_norm": 0.5128265023231506, "skipped": false, "seconds": 1150.8 }, { "step": 39, "epoch": 0, "loss": 0.051204504607117715, "lr": 9.946824237646824e-05, "grad_norm": 0.3985678553581238, "skipped": false, "seconds": 1181.8 }, { "step": 40, "epoch": 0, "loss": 0.06049295101113949, "lr": 9.942108874226811e-05, "grad_norm": 0.525611400604248, "skipped": false, "seconds": 1212.5 }, { "step": 41, "epoch": 0, "loss": 0.05473621184691105, "lr": 9.937194443381972e-05, "grad_norm": 0.503436803817749, "skipped": false, "seconds": 1242.8 }, { "step": 42, "epoch": 0, "loss": 0.05886410636377241, "lr": 9.93208114306486e-05, "grad_norm": 0.47664114832878113, "skipped": false, "seconds": 1274.4 }, { "step": 43, "epoch": 0, "loss": 0.05740216232730541, "lr": 9.926769179238466e-05, "grad_norm": 0.994827389717102, "skipped": false, "seconds": 1304.9 }, { "step": 44, "epoch": 0, "loss": 0.05837026187973685, "lr": 9.921258765867919e-05, "grad_norm": 0.47819700837135315, "skipped": false, "seconds": 1335.1 }, { "step": 45, "epoch": 0, "loss": 0.048231410801350474, "lr": 9.915550124911866e-05, "grad_norm": 0.41990071535110474, "skipped": false, "seconds": 1366.3 }, { "step": 46, "epoch": 0, "loss": 0.04562145920400366, "lr": 9.909643486313533e-05, "grad_norm": 0.3867731988430023, "skipped": false, "seconds": 1396.0 }, { "step": 47, "epoch": 0, "loss": 0.04700247855921044, "lr": 9.903539087991462e-05, "grad_norm": 0.4377094805240631, "skipped": false, "seconds": 1427.3 }, { "step": 48, "epoch": 0, "loss": 0.04771211157444897, "lr": 9.897237175829926e-05, "grad_norm": 0.4685591757297516, "skipped": false, "seconds": 1457.2 }, { "step": 49, "epoch": 0, "loss": 0.0489195060784648, "lr": 9.890738003669029e-05, "grad_norm": 0.4277944564819336, "skipped": false, "seconds": 1487.9 }, { "step": 50, "epoch": 0, "loss": 0.05864074655654856, "lr": 9.884041833294476e-05, "grad_norm": 0.45892971754074097, "skipped": false, "seconds": 1519.0 }, { "step": 51, "epoch": 0, "loss": 0.04818263103261309, "lr": 9.877148934427037e-05, "grad_norm": 0.39819756150245667, "skipped": false, "seconds": 1552.3 }, { "step": 52, "epoch": 0, "loss": 0.05366593056003958, "lr": 9.870059584711668e-05, "grad_norm": 0.6030884385108948, "skipped": false, "seconds": 1581.7 }, { "step": 53, "epoch": 0, "loss": 0.043071207878591276, "lr": 9.862774069706346e-05, "grad_norm": 0.37357521057128906, "skipped": false, "seconds": 1614.2 }, { "step": 54, "epoch": 0, "loss": 0.04875012851107735, "lr": 9.855292682870551e-05, "grad_norm": 0.4176650047302246, "skipped": false, "seconds": 1645.7 }, { "step": 55, "epoch": 0, "loss": 0.05916158294450872, "lr": 9.847615725553456e-05, "grad_norm": 0.5978649258613586, "skipped": false, "seconds": 1675.6 }, { "step": 56, "epoch": 0, "loss": 0.058098166422967945, "lr": 9.839743506981782e-05, "grad_norm": 0.42823487520217896, "skipped": false, "seconds": 1706.4 }, { "step": 57, "epoch": 0, "loss": 0.045172476261220076, "lr": 9.831676344247342e-05, "grad_norm": 0.4181194603443146, "skipped": false, "seconds": 1737.6 }, { "step": 58, "epoch": 0, "loss": 0.05060952837004283, "lr": 9.82341456229428e-05, "grad_norm": 0.5255125761032104, "skipped": false, "seconds": 1765.9 }, { "step": 59, "epoch": 0, "loss": 0.05047130558174233, "lr": 9.814958493905963e-05, "grad_norm": 0.43823546171188354, "skipped": false, "seconds": 1797.2 }, { "step": 60, "epoch": 0, "loss": 0.0491023870761557, "lr": 9.806308479691595e-05, "grad_norm": 0.4243999719619751, "skipped": false, "seconds": 1828.1 }, { "step": 61, "epoch": 0, "loss": 0.043288892164662245, "lr": 9.797464868072488e-05, "grad_norm": 0.4273908734321594, "skipped": false, "seconds": 1857.9 }, { "step": 62, "epoch": 0, "loss": 0.04162379607413579, "lr": 9.788428015268027e-05, "grad_norm": 0.45563948154449463, "skipped": false, "seconds": 1887.6 }, { "step": 63, "epoch": 0, "loss": 0.046959113067771105, "lr": 9.779198285281325e-05, "grad_norm": 0.5101006031036377, "skipped": false, "seconds": 1919.9 }, { "step": 64, "epoch": 0, "loss": 0.04868613549499087, "lr": 9.769776049884563e-05, "grad_norm": 0.4730517864227295, "skipped": false, "seconds": 1951.2 }, { "step": 65, "epoch": 0, "loss": 0.052818452819319794, "lr": 9.760161688604008e-05, "grad_norm": 0.4125804007053375, "skipped": false, "seconds": 1982.8 }, { "step": 66, "epoch": 0, "loss": 0.04659271240234375, "lr": 9.750355588704727e-05, "grad_norm": 0.45149803161621094, "skipped": false, "seconds": 2013.5 }, { "step": 67, "epoch": 0, "loss": 0.04500601429651194, "lr": 9.740358145174998e-05, "grad_norm": 0.44188907742500305, "skipped": false, "seconds": 2045.2 }, { "step": 68, "epoch": 0, "loss": 0.046970408207588896, "lr": 9.730169760710386e-05, "grad_norm": 0.5863640904426575, "skipped": false, "seconds": 2076.5 }, { "step": 69, "epoch": 0, "loss": 0.044865242302458606, "lr": 9.719790845697533e-05, "grad_norm": 0.39309433102607727, "skipped": false, "seconds": 2108.1 }, { "step": 70, "epoch": 0, "loss": 0.04593456075913328, "lr": 9.709221818197624e-05, "grad_norm": 0.44956448674201965, "skipped": false, "seconds": 2139.3 }, { "step": 71, "epoch": 0, "loss": 0.045809862771893126, "lr": 9.698463103929542e-05, "grad_norm": 0.48698508739471436, "skipped": false, "seconds": 2170.5 }, { "step": 72, "epoch": 0, "loss": 0.044335218049706415, "lr": 9.687515136252731e-05, "grad_norm": 0.536542534828186, "skipped": false, "seconds": 2201.8 }, { "step": 73, "epoch": 0, "loss": 0.034864149286479816, "lr": 9.676378356149734e-05, "grad_norm": 0.36436447501182556, "skipped": false, "seconds": 2231.0 }, { "step": 74, "epoch": 0, "loss": 0.043896083493069775, "lr": 9.665053212208426e-05, "grad_norm": 0.4838595688343048, "skipped": false, "seconds": 2260.5 }, { "step": 75, "epoch": 0, "loss": 0.04309926780932544, "lr": 9.653540160603956e-05, "grad_norm": 0.4336928725242615, "skipped": false, "seconds": 2291.4 }, { "step": 76, "epoch": 0, "loss": 0.049297388306396996, "lr": 9.641839665080363e-05, "grad_norm": 0.4917004406452179, "skipped": false, "seconds": 2320.4 }, { "step": 77, "epoch": 0, "loss": 0.04662362143164262, "lr": 9.629952196931901e-05, "grad_norm": 0.7901037335395813, "skipped": false, "seconds": 2350.6 }, { "step": 78, "epoch": 0, "loss": 0.04559790509483134, "lr": 9.617878234984055e-05, "grad_norm": 0.48896324634552, "skipped": false, "seconds": 2381.8 }, { "step": 79, "epoch": 0, "loss": 0.041544652383531604, "lr": 9.60561826557425e-05, "grad_norm": 0.43355318903923035, "skipped": false, "seconds": 2411.3 }, { "step": 80, "epoch": 0, "loss": 0.04375480673779016, "lr": 9.593172782532268e-05, "grad_norm": 0.4469282031059265, "skipped": false, "seconds": 2442.5 }, { "step": 81, "epoch": 0, "loss": 0.043051442354047106, "lr": 9.580542287160348e-05, "grad_norm": 0.4262138903141022, "skipped": false, "seconds": 2474.1 }, { "step": 82, "epoch": 0, "loss": 0.05389878683908257, "lr": 9.567727288213005e-05, "grad_norm": 0.533173680305481, "skipped": false, "seconds": 2505.5 }, { "step": 83, "epoch": 0, "loss": 0.04077400034217979, "lr": 9.554728301876526e-05, "grad_norm": 0.4008263349533081, "skipped": false, "seconds": 2538.1 }, { "step": 84, "epoch": 0, "loss": 0.042045998732131294, "lr": 9.541545851748186e-05, "grad_norm": 0.4874799847602844, "skipped": false, "seconds": 2568.2 }, { "step": 85, "epoch": 0, "loss": 0.042924036080179126, "lr": 9.528180468815155e-05, "grad_norm": 0.4657498896121979, "skipped": false, "seconds": 2599.4 }, { "step": 86, "epoch": 0, "loss": 0.04021313511834994, "lr": 9.514632691433107e-05, "grad_norm": 0.4809572398662567, "skipped": false, "seconds": 2628.6 }, { "step": 87, "epoch": 0, "loss": 0.04092615930167263, "lr": 9.50090306530454e-05, "grad_norm": 0.48094093799591064, "skipped": false, "seconds": 2660.8 }, { "step": 88, "epoch": 0, "loss": 0.0385408574271613, "lr": 9.486992143456792e-05, "grad_norm": 0.47969570755958557, "skipped": false, "seconds": 2690.8 }, { "step": 89, "epoch": 0, "loss": 0.040967103461144676, "lr": 9.472900486219769e-05, "grad_norm": 0.4366934597492218, "skipped": false, "seconds": 2721.1 }, { "step": 90, "epoch": 0, "loss": 0.047251623422032964, "lr": 9.458628661203367e-05, "grad_norm": 0.48443788290023804, "skipped": false, "seconds": 2752.0 }, { "step": 91, "epoch": 0, "loss": 0.0382828146632823, "lr": 9.444177243274618e-05, "grad_norm": 0.4706588685512543, "skipped": false, "seconds": 2783.3 }, { "step": 92, "epoch": 0, "loss": 0.04608729774082383, "lr": 9.429546814534529e-05, "grad_norm": 0.44139933586120605, "skipped": false, "seconds": 2813.4 }, { "step": 93, "epoch": 0, "loss": 0.04839884853088036, "lr": 9.414737964294636e-05, "grad_norm": 0.4453069567680359, "skipped": false, "seconds": 2843.4 }, { "step": 94, "epoch": 0, "loss": 0.0385095516794599, "lr": 9.399751289053267e-05, "grad_norm": 0.42764177918434143, "skipped": false, "seconds": 2874.1 }, { "step": 95, "epoch": 0, "loss": 0.03839392269232086, "lr": 9.384587392471515e-05, "grad_norm": 0.4124580919742584, "skipped": false, "seconds": 2905.1 }, { "step": 96, "epoch": 0, "loss": 0.043852357471378486, "lr": 9.369246885348926e-05, "grad_norm": 0.47256457805633545, "skipped": false, "seconds": 2936.3 }, { "step": 97, "epoch": 0, "loss": 0.041886468532681916, "lr": 9.353730385598887e-05, "grad_norm": 0.4709848165512085, "skipped": false, "seconds": 2965.5 }, { "step": 98, "epoch": 0, "loss": 0.044607980541999256, "lr": 9.338038518223747e-05, "grad_norm": 0.42527738213539124, "skipped": false, "seconds": 2995.5 }, { "step": 99, "epoch": 0, "loss": 0.04058560680755121, "lr": 9.322171915289635e-05, "grad_norm": 0.41362443566322327, "skipped": false, "seconds": 3026.1 }, { "step": 100, "epoch": 0, "loss": 0.036925773563923486, "lr": 9.306131215901003e-05, "grad_norm": 0.39879411458969116, "skipped": false, "seconds": 3056.0 }, { "step": 101, "epoch": 0, "loss": 0.04319861298706494, "lr": 9.289917066174886e-05, "grad_norm": 0.45430848002433777, "skipped": false, "seconds": 3085.9 }, { "step": 102, "epoch": 0, "loss": 0.038103842340568954, "lr": 9.273530119214868e-05, "grad_norm": 1.6617456674575806, "skipped": false, "seconds": 3117.3 }, { "step": 103, "epoch": 0, "loss": 0.04705844420699579, "lr": 9.256971035084785e-05, "grad_norm": 0.5413803458213806, "skipped": false, "seconds": 3148.0 }, { "step": 104, "epoch": 0, "loss": 0.04588349056332997, "lr": 9.24024048078213e-05, "grad_norm": 0.48643723130226135, "skipped": false, "seconds": 3176.6 }, { "step": 105, "epoch": 0, "loss": 0.03868896050454584, "lr": 9.223339130211192e-05, "grad_norm": 0.4337347447872162, "skipped": false, "seconds": 3207.2 }, { "step": 106, "epoch": 0, "loss": 0.036370536171722645, "lr": 9.206267664155907e-05, "grad_norm": 0.41438397765159607, "skipped": false, "seconds": 3236.2 }, { "step": 107, "epoch": 0, "loss": 0.045510898442028866, "lr": 9.189026770252436e-05, "grad_norm": 0.4909036159515381, "skipped": false, "seconds": 3266.4 }, { "step": 108, "epoch": 0, "loss": 0.041277409169551436, "lr": 9.171617142961477e-05, "grad_norm": 0.506044864654541, "skipped": false, "seconds": 3295.5 }, { "step": 109, "epoch": 0, "loss": 0.048108986375681596, "lr": 9.154039483540273e-05, "grad_norm": 0.8060802221298218, "skipped": false, "seconds": 3325.8 }, { "step": 110, "epoch": 0, "loss": 0.04355858804628586, "lr": 9.136294500014386e-05, "grad_norm": 0.4543282687664032, "skipped": false, "seconds": 3356.2 }, { "step": 111, "epoch": 0, "loss": 0.038672522803189745, "lr": 9.118382907149165e-05, "grad_norm": 0.40678146481513977, "skipped": false, "seconds": 3387.2 }, { "step": 112, "epoch": 0, "loss": 0.042898832788448915, "lr": 9.100305426420956e-05, "grad_norm": 0.46925193071365356, "skipped": false, "seconds": 3415.2 }, { "step": 113, "epoch": 0, "loss": 0.044555553183160804, "lr": 9.082062785988049e-05, "grad_norm": 0.4316609501838684, "skipped": false, "seconds": 3445.5 }, { "step": 114, "epoch": 0, "loss": 0.05310061437274338, "lr": 9.06365572066134e-05, "grad_norm": 0.47825491428375244, "skipped": false, "seconds": 3476.2 }, { "step": 115, "epoch": 0, "loss": 0.039852327125268344, "lr": 9.045084971874738e-05, "grad_norm": 0.4318072199821472, "skipped": false, "seconds": 3507.8 }, { "step": 116, "epoch": 0, "loss": 0.04183180106903781, "lr": 9.026351287655294e-05, "grad_norm": 0.41331470012664795, "skipped": false, "seconds": 3540.0 }, { "step": 117, "epoch": 0, "loss": 0.03974040917733554, "lr": 9.007455422593077e-05, "grad_norm": 0.5103293657302856, "skipped": false, "seconds": 3570.9 }, { "step": 118, "epoch": 0, "loss": 0.044967052919180975, "lr": 8.988398137810777e-05, "grad_norm": 0.4268462359905243, "skipped": false, "seconds": 3602.0 }, { "step": 119, "epoch": 0, "loss": 0.036238125160800834, "lr": 8.969180200933047e-05, "grad_norm": 0.3959253132343292, "skipped": false, "seconds": 3634.4 }, { "step": 120, "epoch": 0, "loss": 0.03730900039784556, "lr": 8.949802386055581e-05, "grad_norm": 0.4061117172241211, "skipped": false, "seconds": 3665.0 }, { "step": 121, "epoch": 0, "loss": 0.04315282394073202, "lr": 8.930265473713938e-05, "grad_norm": 0.43387264013290405, "skipped": false, "seconds": 3695.2 }, { "step": 122, "epoch": 0, "loss": 0.04045547115192259, "lr": 8.910570250852097e-05, "grad_norm": 0.43794116377830505, "skipped": false, "seconds": 3725.1 }, { "step": 123, "epoch": 0, "loss": 0.039255543758994656, "lr": 8.890717510790763e-05, "grad_norm": 0.421598881483078, "skipped": false, "seconds": 3753.7 }, { "step": 124, "epoch": 0, "loss": 0.04119531671735658, "lr": 8.870708053195413e-05, "grad_norm": 0.41828998923301697, "skipped": false, "seconds": 3782.7 }, { "step": 125, "epoch": 0, "loss": 0.03619634128686488, "lr": 8.850542684044078e-05, "grad_norm": 0.3894548714160919, "skipped": false, "seconds": 3813.8 }, { "step": 126, "epoch": 0, "loss": 0.04429675767294329, "lr": 8.83022221559489e-05, "grad_norm": 0.4620448052883148, "skipped": false, "seconds": 3843.6 }, { "step": 127, "epoch": 0, "loss": 0.03996556843091452, "lr": 8.809747466353356e-05, "grad_norm": 0.4065825343132019, "skipped": false, "seconds": 3874.3 }, { "step": 128, "epoch": 0, "loss": 0.0439553558475418, "lr": 8.789119261039385e-05, "grad_norm": 0.4792153239250183, "skipped": false, "seconds": 3904.4 }, { "step": 129, "epoch": 0, "loss": 0.038623366088057345, "lr": 8.768338430554082e-05, "grad_norm": 0.38725003600120544, "skipped": false, "seconds": 3933.6 }, { "step": 130, "epoch": 0, "loss": 0.034875345331959726, "lr": 8.74740581194627e-05, "grad_norm": 0.46025949716567993, "skipped": false, "seconds": 3962.5 }, { "step": 131, "epoch": 0, "loss": 0.03991871696805529, "lr": 8.726322248378775e-05, "grad_norm": 0.5329133868217468, "skipped": false, "seconds": 3993.1 }, { "step": 132, "epoch": 0, "loss": 0.04528188935060945, "lr": 8.705088589094459e-05, "grad_norm": 0.6367639899253845, "skipped": false, "seconds": 4023.4 }, { "step": 133, "epoch": 0, "loss": 0.04366885924049116, "lr": 8.683705689382024e-05, "grad_norm": 0.8130128979682922, "skipped": false, "seconds": 4054.7 }, { "step": 134, "epoch": 0, "loss": 0.04263949807086629, "lr": 8.662174410541555e-05, "grad_norm": 0.47220155596733093, "skipped": false, "seconds": 4086.5 }, { "step": 135, "epoch": 0, "loss": 0.03748772638578097, "lr": 8.640495619849821e-05, "grad_norm": 0.7511334419250488, "skipped": false, "seconds": 4115.9 }, { "step": 136, "epoch": 0, "loss": 0.03817583855450704, "lr": 8.618670190525352e-05, "grad_norm": 0.45687562227249146, "skipped": false, "seconds": 4146.9 }, { "step": 137, "epoch": 0, "loss": 0.045329121330418734, "lr": 8.596699001693255e-05, "grad_norm": 0.5111539959907532, "skipped": false, "seconds": 4177.5 }, { "step": 138, "epoch": 0, "loss": 0.04316695398120789, "lr": 8.574582938349817e-05, "grad_norm": 0.47795966267585754, "skipped": false, "seconds": 4207.5 }, { "step": 139, "epoch": 0, "loss": 0.03760606574186284, "lr": 8.552322891326846e-05, "grad_norm": 0.4370393753051758, "skipped": false, "seconds": 4238.5 }, { "step": 140, "epoch": 0, "loss": 0.03411327835019874, "lr": 8.529919757255783e-05, "grad_norm": 0.5971311926841736, "skipped": false, "seconds": 4269.4 }, { "step": 141, "epoch": 0, "loss": 0.040823135821758484, "lr": 8.507374438531607e-05, "grad_norm": 0.4045528471469879, "skipped": false, "seconds": 4300.7 }, { "step": 142, "epoch": 0, "loss": 0.03689725307248674, "lr": 8.484687843276469e-05, "grad_norm": 0.503023624420166, "skipped": false, "seconds": 4330.5 }, { "step": 143, "epoch": 0, "loss": 0.04255549059662948, "lr": 8.461860885303114e-05, "grad_norm": 1.0986597537994385, "skipped": false, "seconds": 4362.6 }, { "step": 144, "epoch": 0, "loss": 0.03933713789797076, "lr": 8.438894484078086e-05, "grad_norm": 0.384954571723938, "skipped": false, "seconds": 4394.5 }, { "step": 145, "epoch": 0, "loss": 0.04379340127772898, "lr": 8.415789564684673e-05, "grad_norm": 0.42970529198646545, "skipped": false, "seconds": 4424.8 }, { "step": 146, "epoch": 0, "loss": 0.0348121738856441, "lr": 8.392547057785661e-05, "grad_norm": 0.3794669210910797, "skipped": false, "seconds": 4454.9 }, { "step": 147, "epoch": 0, "loss": 0.03421579952458653, "lr": 8.369167899585841e-05, "grad_norm": 0.3601197600364685, "skipped": false, "seconds": 4485.3 }, { "step": 148, "epoch": 0, "loss": 0.042821301594670964, "lr": 8.345653031794292e-05, "grad_norm": 0.4644930958747864, "skipped": false, "seconds": 4516.7 }, { "step": 149, "epoch": 0, "loss": 0.044358414786973915, "lr": 8.322003401586462e-05, "grad_norm": 0.4486781060695648, "skipped": false, "seconds": 4547.8 }, { "step": 150, "epoch": 0, "loss": 0.04154949754934255, "lr": 8.298219961566009e-05, "grad_norm": 0.4688260853290558, "skipped": false, "seconds": 4579.2 }, { "step": 151, "epoch": 0, "loss": 0.04206281148280588, "lr": 8.274303669726426e-05, "grad_norm": 0.4345685541629791, "skipped": false, "seconds": 4609.6 }, { "step": 152, "epoch": 0, "loss": 0.03806614825690483, "lr": 8.250255489412463e-05, "grad_norm": 0.41471055150032043, "skipped": false, "seconds": 4639.3 }, { "step": 153, "epoch": 0, "loss": 0.036419154975548464, "lr": 8.226076389281316e-05, "grad_norm": 0.39894402027130127, "skipped": false, "seconds": 4670.0 }, { "step": 154, "epoch": 0, "loss": 0.0412287198855671, "lr": 8.201767343263612e-05, "grad_norm": 0.5558825135231018, "skipped": false, "seconds": 4699.3 }, { "step": 155, "epoch": 0, "loss": 0.03543429750900332, "lr": 8.177329330524182e-05, "grad_norm": 0.3999188542366028, "skipped": false, "seconds": 4731.7 }, { "step": 156, "epoch": 0, "loss": 0.0313229477893021, "lr": 8.152763335422613e-05, "grad_norm": 0.36880818009376526, "skipped": false, "seconds": 4762.2 }, { "step": 157, "epoch": 0, "loss": 0.04267634258650647, "lr": 8.128070347473609e-05, "grad_norm": 0.476824015378952, "skipped": false, "seconds": 4793.5 }, { "step": 158, "epoch": 0, "loss": 0.036534420304552194, "lr": 8.103251361307119e-05, "grad_norm": 0.3953181505203247, "skipped": false, "seconds": 4824.2 }, { "step": 159, "epoch": 0, "loss": 0.04185770834502996, "lr": 8.07830737662829e-05, "grad_norm": 0.4075761139392853, "skipped": false, "seconds": 4854.8 }, { "step": 160, "epoch": 0, "loss": 0.03086744183635943, "lr": 8.053239398177191e-05, "grad_norm": 0.3988531529903412, "skipped": false, "seconds": 4885.7 }, { "step": 161, "epoch": 0, "loss": 0.030656032216276878, "lr": 8.028048435688333e-05, "grad_norm": 0.41813963651657104, "skipped": false, "seconds": 4915.8 }, { "step": 162, "epoch": 0, "loss": 0.03457538713973674, "lr": 8.002735503850016e-05, "grad_norm": 0.5292803049087524, "skipped": false, "seconds": 4946.6 }, { "step": 163, "epoch": 0, "loss": 0.04431626313934932, "lr": 7.97730162226344e-05, "grad_norm": 0.46250706911087036, "skipped": false, "seconds": 4977.1 }, { "step": 164, "epoch": 0, "loss": 0.03613297641050265, "lr": 7.95174781540165e-05, "grad_norm": 0.4473329484462738, "skipped": false, "seconds": 5006.5 }, { "step": 165, "epoch": 0, "loss": 0.04166648178634685, "lr": 7.926075112568259e-05, "grad_norm": 0.45099830627441406, "skipped": false, "seconds": 5039.0 }, { "step": 166, "epoch": 0, "loss": 0.0461718571295432, "lr": 7.900284547855991e-05, "grad_norm": 0.4615466594696045, "skipped": false, "seconds": 5070.3 }, { "step": 167, "epoch": 0, "loss": 0.03558595718876008, "lr": 7.874377160105036e-05, "grad_norm": 0.40478748083114624, "skipped": false, "seconds": 5101.0 }, { "step": 168, "epoch": 0, "loss": 0.03655152665563376, "lr": 7.848353992861195e-05, "grad_norm": 0.8066860437393188, "skipped": false, "seconds": 5131.0 }, { "step": 169, "epoch": 0, "loss": 0.04193836329213726, "lr": 7.822216094333847e-05, "grad_norm": 0.47176116704940796, "skipped": false, "seconds": 5161.5 }, { "step": 170, "epoch": 0, "loss": 0.04063318507788144, "lr": 7.795964517353735e-05, "grad_norm": 0.6494160294532776, "skipped": false, "seconds": 5190.9 }, { "step": 171, "epoch": 0, "loss": 0.031576382511724656, "lr": 7.769600319330552e-05, "grad_norm": 0.33635416626930237, "skipped": false, "seconds": 5222.1 }, { "step": 172, "epoch": 0, "loss": 0.03734357056854235, "lr": 7.74312456221035e-05, "grad_norm": 0.4150267243385315, "skipped": false, "seconds": 5253.9 }, { "step": 173, "epoch": 0, "loss": 0.032456102336556145, "lr": 7.716538312432766e-05, "grad_norm": 0.4122450649738312, "skipped": false, "seconds": 5285.7 }, { "step": 174, "epoch": 0, "loss": 0.04108603528774564, "lr": 7.689842640888063e-05, "grad_norm": 0.4406798183917999, "skipped": false, "seconds": 5316.2 }, { "step": 175, "epoch": 0, "loss": 0.034947429970073884, "lr": 7.663038622873999e-05, "grad_norm": 0.388076514005661, "skipped": false, "seconds": 5345.7 }, { "step": 176, "epoch": 0, "loss": 0.03984182050221951, "lr": 7.636127338052512e-05, "grad_norm": 0.4097675085067749, "skipped": false, "seconds": 5376.6 }, { "step": 177, "epoch": 0, "loss": 0.03554444531306821, "lr": 7.60910987040623e-05, "grad_norm": 0.4486690163612366, "skipped": false, "seconds": 5404.5 }, { "step": 178, "epoch": 0, "loss": 0.03406732369196045, "lr": 7.58198730819481e-05, "grad_norm": 0.36147722601890564, "skipped": false, "seconds": 5437.3 }, { "step": 179, "epoch": 0, "loss": 0.03996114220770357, "lr": 7.554760743911103e-05, "grad_norm": 0.6578200459480286, "skipped": false, "seconds": 5468.4 }, { "step": 180, "epoch": 0, "loss": 0.03974208406398927, "lr": 7.52743127423715e-05, "grad_norm": 0.5207664370536804, "skipped": false, "seconds": 5498.2 }, { "step": 181, "epoch": 0, "loss": 0.04600800008996591, "lr": 7.500000000000001e-05, "grad_norm": 0.5798813104629517, "skipped": false, "seconds": 5528.0 }, { "step": 182, "epoch": 0, "loss": 0.039908104562122335, "lr": 7.472468026127385e-05, "grad_norm": 0.4419390559196472, "skipped": false, "seconds": 5559.1 }, { "step": 183, "epoch": 0, "loss": 0.03292939452479223, "lr": 7.444836461603195e-05, "grad_norm": 0.3788493871688843, "skipped": false, "seconds": 5588.1 }, { "step": 184, "epoch": 0, "loss": 0.04538562315394896, "lr": 7.417106419422819e-05, "grad_norm": 0.48531362414360046, "skipped": false, "seconds": 5617.4 }, { "step": 185, "epoch": 0, "loss": 0.03726213373671817, "lr": 7.389279016548316e-05, "grad_norm": 0.4027515649795532, "skipped": false, "seconds": 5650.0 }, { "step": 186, "epoch": 0, "loss": 0.03393715986206677, "lr": 7.361355373863414e-05, "grad_norm": 0.3956986963748932, "skipped": false, "seconds": 5680.1 }, { "step": 187, "epoch": 0, "loss": 0.04360706535456188, "lr": 7.333336616128369e-05, "grad_norm": 0.4776063561439514, "skipped": false, "seconds": 5709.6 }, { "step": 188, "epoch": 0, "loss": 0.05108193350914854, "lr": 7.305223871934657e-05, "grad_norm": 0.4673639237880707, "skipped": false, "seconds": 5739.7 }, { "step": 189, "epoch": 0, "loss": 0.03513687010553615, "lr": 7.277018273659517e-05, "grad_norm": 0.3786344826221466, "skipped": false, "seconds": 5769.9 }, { "step": 190, "epoch": 0, "loss": 0.037264012151926776, "lr": 7.24872095742033e-05, "grad_norm": 0.4696302115917206, "skipped": false, "seconds": 5801.1 }, { "step": 191, "epoch": 0, "loss": 0.03839773619213788, "lr": 7.220333063028872e-05, "grad_norm": 1.4208773374557495, "skipped": false, "seconds": 5832.1 }, { "step": 192, "epoch": 0, "loss": 0.037638320253307794, "lr": 7.191855733945387e-05, "grad_norm": 0.4687727987766266, "skipped": false, "seconds": 5861.9 }, { "step": 193, "epoch": 0, "loss": 0.033059018984484906, "lr": 7.163290117232542e-05, "grad_norm": 0.46348440647125244, "skipped": false, "seconds": 5892.3 }, { "step": 194, "epoch": 0, "loss": 0.037771729388868955, "lr": 7.13463736350921e-05, "grad_norm": 0.39239150285720825, "skipped": false, "seconds": 5921.5 }, { "step": 195, "epoch": 0, "loss": 0.04014919540012298, "lr": 7.105898626904134e-05, "grad_norm": 0.4191938638687134, "skipped": false, "seconds": 5952.6 }, { "step": 196, "epoch": 0, "loss": 0.032287506898942726, "lr": 7.077075065009433e-05, "grad_norm": 0.3714689612388611, "skipped": false, "seconds": 5983.1 }, { "step": 197, "epoch": 0, "loss": 0.03435342616117841, "lr": 7.048167838833977e-05, "grad_norm": 0.43851959705352783, "skipped": false, "seconds": 6014.3 }, { "step": 198, "epoch": 0, "loss": 0.031339017286041354, "lr": 7.019178112756624e-05, "grad_norm": 1.0957211256027222, "skipped": false, "seconds": 6045.5 }, { "step": 199, "epoch": 0, "loss": 0.03213614967368697, "lr": 6.990107054479312e-05, "grad_norm": 0.4667567014694214, "skipped": false, "seconds": 6075.9 }, { "step": 200, "epoch": 0, "loss": 0.03776222146967406, "lr": 6.960955834980028e-05, "grad_norm": 0.49867287278175354, "skipped": false, "seconds": 6106.6 }, { "step": 201, "epoch": 0, "loss": 0.03299907082185107, "lr": 6.931725628465643e-05, "grad_norm": 0.4388504922389984, "skipped": false, "seconds": 6137.2 }, { "step": 202, "epoch": 0, "loss": 0.02845420716160882, "lr": 6.902417612324615e-05, "grad_norm": 0.4300897717475891, "skipped": false, "seconds": 6167.6 }, { "step": 203, "epoch": 0, "loss": 0.048140803469887264, "lr": 6.873032967079561e-05, "grad_norm": 0.4720727205276489, "skipped": false, "seconds": 6196.9 }, { "step": 204, "epoch": 0, "loss": 0.04197649929110564, "lr": 6.843572876339705e-05, "grad_norm": 0.5733126997947693, "skipped": false, "seconds": 6228.0 }, { "step": 205, "epoch": 0, "loss": 0.0407797022241052, "lr": 6.814038526753205e-05, "grad_norm": 0.4141710102558136, "skipped": false, "seconds": 6258.9 }, { "step": 206, "epoch": 0, "loss": 0.03560397631227188, "lr": 6.784431107959359e-05, "grad_norm": 0.4068869650363922, "skipped": false, "seconds": 6289.4 }, { "step": 207, "epoch": 0, "loss": 0.03401413873482035, "lr": 6.754751812540679e-05, "grad_norm": 0.3947623372077942, "skipped": false, "seconds": 6319.6 }, { "step": 208, "epoch": 0, "loss": 0.04135789566635663, "lr": 6.725001835974853e-05, "grad_norm": 0.4253414571285248, "skipped": false, "seconds": 6351.6 }, { "step": 209, "epoch": 0, "loss": 0.03787880008467034, "lr": 6.695182376586603e-05, "grad_norm": 0.4344177544116974, "skipped": false, "seconds": 6382.8 }, { "step": 210, "epoch": 0, "loss": 0.03571759499921796, "lr": 6.665294635499404e-05, "grad_norm": 0.3693549633026123, "skipped": false, "seconds": 6413.8 }, { "step": 211, "epoch": 0, "loss": 0.037497748775431376, "lr": 6.635339816587109e-05, "grad_norm": 0.4440297484397888, "skipped": false, "seconds": 6443.4 }, { "step": 212, "epoch": 0, "loss": 0.03740905688192839, "lr": 6.605319126425454e-05, "grad_norm": 0.4463842213153839, "skipped": false, "seconds": 6474.5 }, { "step": 213, "epoch": 0, "loss": 0.04070149968421992, "lr": 6.575233774243465e-05, "grad_norm": 0.6535020470619202, "skipped": false, "seconds": 6505.5 }, { "step": 214, "epoch": 0, "loss": 0.03551791987161815, "lr": 6.545084971874738e-05, "grad_norm": 0.4679766297340393, "skipped": false, "seconds": 6536.2 }, { "step": 215, "epoch": 0, "loss": 0.0383298000410759, "lr": 6.514873933708638e-05, "grad_norm": 0.3855707347393036, "skipped": false, "seconds": 6566.2 }, { "step": 216, "epoch": 0, "loss": 0.037831665922547046, "lr": 6.484601876641375e-05, "grad_norm": 1.139644742012024, "skipped": false, "seconds": 6595.9 }, { "step": 217, "epoch": 0, "loss": 0.03648110361960469, "lr": 6.454270020026995e-05, "grad_norm": 0.4173310101032257, "skipped": false, "seconds": 6626.4 }, { "step": 218, "epoch": 0, "loss": 0.033973121468026765, "lr": 6.423879585628261e-05, "grad_norm": 0.4316014349460602, "skipped": false, "seconds": 6655.2 }, { "step": 219, "epoch": 0, "loss": 0.04896280768634715, "lr": 6.39343179756744e-05, "grad_norm": 1.1312209367752075, "skipped": false, "seconds": 6685.7 }, { "step": 220, "epoch": 0, "loss": 0.03579341232938403, "lr": 6.36292788227699e-05, "grad_norm": 0.40495115518569946, "skipped": false, "seconds": 6716.8 }, { "step": 221, "epoch": 0, "loss": 0.05005555049648453, "lr": 6.332369068450174e-05, "grad_norm": 0.47920170426368713, "skipped": false, "seconds": 6749.8 }, { "step": 222, "epoch": 0, "loss": 0.03518659511842654, "lr": 6.30175658699156e-05, "grad_norm": 0.47350093722343445, "skipped": false, "seconds": 6780.5 }, { "step": 223, "epoch": 0, "loss": 0.03665763939553687, "lr": 6.271091670967436e-05, "grad_norm": 0.42811599373817444, "skipped": false, "seconds": 6810.9 }, { "step": 224, "epoch": 0, "loss": 0.07557717694559939, "lr": 6.240375555556145e-05, "grad_norm": 0.5362834930419922, "skipped": false, "seconds": 6841.8 }, { "step": 225, "epoch": 0, "loss": 0.034370320694503485, "lr": 6.209609477998338e-05, "grad_norm": 0.3875359296798706, "skipped": false, "seconds": 6873.3 }, { "step": 226, "epoch": 0, "loss": 0.03586724312368848, "lr": 6.178794677547137e-05, "grad_norm": 0.4375789761543274, "skipped": false, "seconds": 6903.7 }, { "step": 227, "epoch": 0, "loss": 0.03204754625441711, "lr": 6.147932395418205e-05, "grad_norm": 0.37311556935310364, "skipped": false, "seconds": 6934.6 }, { "step": 228, "epoch": 0, "loss": 0.029651823812095246, "lr": 6.117023874739772e-05, "grad_norm": 0.3873976469039917, "skipped": false, "seconds": 6965.5 }, { "step": 229, "epoch": 0, "loss": 0.03313081313206076, "lr": 6.0860703605025395e-05, "grad_norm": 0.40196579694747925, "skipped": false, "seconds": 6997.5 }, { "step": 230, "epoch": 0, "loss": 0.032857811465442976, "lr": 6.05507309950955e-05, "grad_norm": 0.3450320065021515, "skipped": false, "seconds": 7025.7 }, { "step": 231, "epoch": 0, "loss": 0.03128418165351189, "lr": 6.024033340325954e-05, "grad_norm": 0.33902105689048767, "skipped": false, "seconds": 7058.4 }, { "step": 232, "epoch": 0, "loss": 0.033792713284052735, "lr": 5.992952333228728e-05, "grad_norm": 0.3558861017227173, "skipped": false, "seconds": 7088.5 }, { "step": 233, "epoch": 0, "loss": 0.03406227171537694, "lr": 5.9618313301563055e-05, "grad_norm": 0.4204740524291992, "skipped": false, "seconds": 7120.3 }, { "step": 234, "epoch": 0, "loss": 0.03475309157182153, "lr": 5.9306715846581506e-05, "grad_norm": 0.38286036252975464, "skipped": false, "seconds": 7149.4 }, { "step": 235, "epoch": 0, "loss": 0.032176283458823195, "lr": 5.8994743518442694e-05, "grad_norm": 0.40629762411117554, "skipped": false, "seconds": 7180.5 }, { "step": 236, "epoch": 0, "loss": 0.031434473539711294, "lr": 5.868240888334653e-05, "grad_norm": 0.3440655469894409, "skipped": false, "seconds": 7211.0 }, { "step": 237, "epoch": 0, "loss": 0.036813643134599484, "lr": 5.836972452208654e-05, "grad_norm": 0.3786338269710541, "skipped": false, "seconds": 7242.7 }, { "step": 238, "epoch": 0, "loss": 0.028255267931254515, "lr": 5.805670302954321e-05, "grad_norm": 0.3729824125766754, "skipped": false, "seconds": 7274.4 }, { "step": 239, "epoch": 0, "loss": 0.041683754948011256, "lr": 5.7743357014176624e-05, "grad_norm": 0.475638210773468, "skipped": false, "seconds": 7306.1 }, { "step": 240, "epoch": 0, "loss": 0.03886621624397832, "lr": 5.7429699097518585e-05, "grad_norm": 0.44749245047569275, "skipped": false, "seconds": 7337.5 }, { "step": 241, "epoch": 0, "loss": 0.0370755632110252, "lr": 5.7115741913664264e-05, "grad_norm": 0.4899304211139679, "skipped": false, "seconds": 7368.2 }, { "step": 242, "epoch": 0, "loss": 0.032659575216887886, "lr": 5.680149810876322e-05, "grad_norm": 0.3824728727340698, "skipped": false, "seconds": 7398.7 }, { "step": 243, "epoch": 0, "loss": 0.041655277951663454, "lr": 5.6486980340510086e-05, "grad_norm": 0.5157487988471985, "skipped": false, "seconds": 7428.5 }, { "step": 244, "epoch": 0, "loss": 0.03493482644935842, "lr": 5.617220127763474e-05, "grad_norm": 0.8254408836364746, "skipped": false, "seconds": 7458.7 }, { "step": 245, "epoch": 0, "loss": 0.03271396995609642, "lr": 5.585717359939192e-05, "grad_norm": 0.4264238178730011, "skipped": false, "seconds": 7489.6 }, { "step": 246, "epoch": 0, "loss": 0.035557805931201635, "lr": 5.5541909995050554e-05, "grad_norm": 0.7259626388549805, "skipped": false, "seconds": 7520.5 }, { "step": 247, "epoch": 0, "loss": 0.03830919612537731, "lr": 5.522642316338268e-05, "grad_norm": 0.5846589803695679, "skipped": false, "seconds": 7550.8 }, { "step": 248, "epoch": 0, "loss": 0.030078849312401398, "lr": 5.4910725812151864e-05, "grad_norm": 0.3776968717575073, "skipped": false, "seconds": 7581.3 }, { "step": 249, "epoch": 0, "loss": 0.03155149267491511, "lr": 5.4594830657601384e-05, "grad_norm": 0.3725808262825012, "skipped": false, "seconds": 7610.1 }, { "step": 250, "epoch": 0, "loss": 0.028693306861097875, "lr": 5.427875042394199e-05, "grad_norm": 0.4124157130718231, "skipped": false, "seconds": 7642.6 }, { "step": 251, "epoch": 0, "loss": 0.03217434105471025, "lr": 5.396249784283942e-05, "grad_norm": 0.5312711000442505, "skipped": false, "seconds": 7673.0 }, { "step": 252, "epoch": 0, "loss": 0.03104523542030881, "lr": 5.364608565290155e-05, "grad_norm": 0.4328680634498596, "skipped": false, "seconds": 7704.1 }, { "step": 253, "epoch": 0, "loss": 0.038518297395887566, "lr": 5.3329526599165204e-05, "grad_norm": 0.4788975417613983, "skipped": false, "seconds": 7735.2 }, { "step": 254, "epoch": 0, "loss": 0.03644856197733275, "lr": 5.301283343258293e-05, "grad_norm": 0.3760280907154083, "skipped": false, "seconds": 7765.5 }, { "step": 255, "epoch": 0, "loss": 0.040502291837035805, "lr": 5.2696018909509306e-05, "grad_norm": 0.609524667263031, "skipped": false, "seconds": 7781.9 }, { "step": 256, "epoch": 1, "loss": 0.024327973316301866, "lr": 5.2379095791187124e-05, "grad_norm": 0.34370267391204834, "skipped": false, "seconds": 7813.3 }, { "step": 257, "epoch": 1, "loss": 0.023225568969183718, "lr": 5.2062076843233366e-05, "grad_norm": 0.2865596413612366, "skipped": false, "seconds": 7844.7 }, { "step": 258, "epoch": 1, "loss": 0.020964424002418502, "lr": 5.174497483512506e-05, "grad_norm": 0.29307377338409424, "skipped": false, "seconds": 7874.0 }, { "step": 259, "epoch": 1, "loss": 0.02225420688061004, "lr": 5.142780253968481e-05, "grad_norm": 0.25329098105430603, "skipped": false, "seconds": 7905.2 }, { "step": 260, "epoch": 1, "loss": 0.019704535258939154, "lr": 5.1110572732566475e-05, "grad_norm": 0.2547796964645386, "skipped": false, "seconds": 7936.0 }, { "step": 261, "epoch": 1, "loss": 0.029142963339943442, "lr": 5.0793298191740404e-05, "grad_norm": 0.457135945558548, "skipped": false, "seconds": 7966.4 }, { "step": 262, "epoch": 1, "loss": 0.024066689716361174, "lr": 5.047599169697884e-05, "grad_norm": 0.2987236976623535, "skipped": false, "seconds": 7998.0 }, { "step": 263, "epoch": 1, "loss": 0.021392749322089965, "lr": 5.015866602934112e-05, "grad_norm": 0.2809486985206604, "skipped": false, "seconds": 8028.5 }, { "step": 264, "epoch": 1, "loss": 0.018585208267671207, "lr": 4.984133397065889e-05, "grad_norm": 0.2966468930244446, "skipped": false, "seconds": 8060.1 }, { "step": 265, "epoch": 1, "loss": 0.023124013230306148, "lr": 4.952400830302117e-05, "grad_norm": 0.4006018340587616, "skipped": false, "seconds": 8091.2 }, { "step": 266, "epoch": 1, "loss": 0.019659400110981634, "lr": 4.92067018082596e-05, "grad_norm": 0.29323676228523254, "skipped": false, "seconds": 8120.9 }, { "step": 267, "epoch": 1, "loss": 0.024482026068742894, "lr": 4.888942726743353e-05, "grad_norm": 0.3428184390068054, "skipped": false, "seconds": 8151.8 }, { "step": 268, "epoch": 1, "loss": 0.02003022017938944, "lr": 4.85721974603152e-05, "grad_norm": 0.3119227886199951, "skipped": false, "seconds": 8182.3 }, { "step": 269, "epoch": 1, "loss": 0.026439435787854695, "lr": 4.825502516487497e-05, "grad_norm": 0.3782959580421448, "skipped": false, "seconds": 8212.2 }, { "step": 270, "epoch": 1, "loss": 0.014993694335972417, "lr": 4.7937923156766646e-05, "grad_norm": 0.23553837835788727, "skipped": false, "seconds": 8242.5 }, { "step": 271, "epoch": 1, "loss": 0.01803465460008746, "lr": 4.762090420881289e-05, "grad_norm": 0.2514285147190094, "skipped": false, "seconds": 8273.6 }, { "step": 272, "epoch": 1, "loss": 0.019902860205701138, "lr": 4.730398109049071e-05, "grad_norm": 0.2984468340873718, "skipped": false, "seconds": 8304.0 }, { "step": 273, "epoch": 1, "loss": 0.01947339402151121, "lr": 4.698716656741708e-05, "grad_norm": 0.2736494541168213, "skipped": false, "seconds": 8335.5 }, { "step": 274, "epoch": 1, "loss": 0.01885466807551386, "lr": 4.667047340083481e-05, "grad_norm": 0.25517645478248596, "skipped": false, "seconds": 8364.6 }, { "step": 275, "epoch": 1, "loss": 0.01877950233943932, "lr": 4.635391434709847e-05, "grad_norm": 0.2774704396724701, "skipped": false, "seconds": 8394.3 }, { "step": 276, "epoch": 1, "loss": 0.018360153023932645, "lr": 4.603750215716057e-05, "grad_norm": 0.32435178756713867, "skipped": false, "seconds": 8424.5 }, { "step": 277, "epoch": 1, "loss": 0.01531967046614941, "lr": 4.5721249576058027e-05, "grad_norm": 0.3591376543045044, "skipped": false, "seconds": 8456.0 }, { "step": 278, "epoch": 1, "loss": 0.016068661741435234, "lr": 4.5405169342398634e-05, "grad_norm": 0.32163316011428833, "skipped": false, "seconds": 8484.3 }, { "step": 279, "epoch": 1, "loss": 0.017871897473814482, "lr": 4.508927418784815e-05, "grad_norm": 0.2604014277458191, "skipped": false, "seconds": 8515.2 }, { "step": 280, "epoch": 1, "loss": 0.021977489380508728, "lr": 4.477357683661734e-05, "grad_norm": 0.3197914958000183, "skipped": false, "seconds": 8547.2 }, { "step": 281, "epoch": 1, "loss": 0.02219422790948942, "lr": 4.445809000494946e-05, "grad_norm": 0.36903974413871765, "skipped": false, "seconds": 8577.6 }, { "step": 282, "epoch": 1, "loss": 0.017691280488369144, "lr": 4.4142826400608086e-05, "grad_norm": 0.29918819665908813, "skipped": false, "seconds": 8607.6 }, { "step": 283, "epoch": 1, "loss": 0.016365259626193267, "lr": 4.3827798722365264e-05, "grad_norm": 0.34842997789382935, "skipped": false, "seconds": 8638.8 }, { "step": 284, "epoch": 1, "loss": 0.020046620939416723, "lr": 4.351301965948991e-05, "grad_norm": 0.2710837423801422, "skipped": false, "seconds": 8671.2 }, { "step": 285, "epoch": 1, "loss": 0.01676117178713448, "lr": 4.3198501891236804e-05, "grad_norm": 0.27728036046028137, "skipped": false, "seconds": 8700.4 }, { "step": 286, "epoch": 1, "loss": 0.017474436593507493, "lr": 4.288425808633575e-05, "grad_norm": 0.2791229486465454, "skipped": false, "seconds": 8731.9 }, { "step": 287, "epoch": 1, "loss": 0.01543151501258758, "lr": 4.2570300902481426e-05, "grad_norm": 0.25070998072624207, "skipped": false, "seconds": 8762.9 }, { "step": 288, "epoch": 1, "loss": 0.017339263243646895, "lr": 4.2256642985823395e-05, "grad_norm": 0.2656727433204651, "skipped": false, "seconds": 8793.3 }, { "step": 289, "epoch": 1, "loss": 0.022872012997628945, "lr": 4.19432969704568e-05, "grad_norm": 0.36633551120758057, "skipped": false, "seconds": 8823.6 }, { "step": 290, "epoch": 1, "loss": 0.020003974834431417, "lr": 4.163027547791347e-05, "grad_norm": 0.26786261796951294, "skipped": false, "seconds": 8853.5 }, { "step": 291, "epoch": 1, "loss": 0.016302781465769377, "lr": 4.131759111665349e-05, "grad_norm": 0.2734525501728058, "skipped": false, "seconds": 8884.3 }, { "step": 292, "epoch": 1, "loss": 0.01887829475529337, "lr": 4.100525648155731e-05, "grad_norm": 0.31800055503845215, "skipped": false, "seconds": 8913.4 }, { "step": 293, "epoch": 1, "loss": 0.020399836793905158, "lr": 4.06932841534185e-05, "grad_norm": 0.3321515619754791, "skipped": false, "seconds": 8946.0 }, { "step": 294, "epoch": 1, "loss": 0.021608482857536256, "lr": 4.038168669843697e-05, "grad_norm": 0.3299846351146698, "skipped": false, "seconds": 8976.4 }, { "step": 295, "epoch": 1, "loss": 0.015938243765422702, "lr": 4.007047666771274e-05, "grad_norm": 0.32036611437797546, "skipped": false, "seconds": 9007.7 }, { "step": 296, "epoch": 1, "loss": 0.016782717475817, "lr": 3.9759666596740476e-05, "grad_norm": 0.2806603014469147, "skipped": false, "seconds": 9039.7 }, { "step": 297, "epoch": 1, "loss": 0.014644961975055359, "lr": 3.944926900490452e-05, "grad_norm": 0.2742427885532379, "skipped": false, "seconds": 9071.9 }, { "step": 298, "epoch": 1, "loss": 0.016398670697453047, "lr": 3.913929639497462e-05, "grad_norm": 0.28872784972190857, "skipped": false, "seconds": 9104.5 }, { "step": 299, "epoch": 1, "loss": 0.017263746750174284, "lr": 3.882976125260229e-05, "grad_norm": 0.41232573986053467, "skipped": false, "seconds": 9133.6 }, { "step": 300, "epoch": 1, "loss": 0.019409321586866885, "lr": 3.852067604581794e-05, "grad_norm": 0.36655980348587036, "skipped": false, "seconds": 9165.4 }, { "step": 301, "epoch": 1, "loss": 0.013817376942734192, "lr": 3.821205322452863e-05, "grad_norm": 0.4269910156726837, "skipped": false, "seconds": 9197.3 }, { "step": 302, "epoch": 1, "loss": 0.02174159104628318, "lr": 3.790390522001662e-05, "grad_norm": 0.3511791229248047, "skipped": false, "seconds": 9226.2 }, { "step": 303, "epoch": 1, "loss": 0.016236488907425493, "lr": 3.759624444443858e-05, "grad_norm": 0.23098163306713104, "skipped": false, "seconds": 9255.1 }, { "step": 304, "epoch": 1, "loss": 0.017032122276003547, "lr": 3.728908329032567e-05, "grad_norm": 0.3353688716888428, "skipped": false, "seconds": 9285.3 }, { "step": 305, "epoch": 1, "loss": 0.01921281299615016, "lr": 3.69824341300844e-05, "grad_norm": 0.2812039256095886, "skipped": false, "seconds": 9317.4 }, { "step": 306, "epoch": 1, "loss": 0.016250054041544598, "lr": 3.6676309315498256e-05, "grad_norm": 0.28371351957321167, "skipped": false, "seconds": 9346.9 }, { "step": 307, "epoch": 1, "loss": 0.017268654154290946, "lr": 3.6370721177230116e-05, "grad_norm": 0.30808404088020325, "skipped": false, "seconds": 9377.3 }, { "step": 308, "epoch": 1, "loss": 0.018877130984260353, "lr": 3.606568202432562e-05, "grad_norm": 0.2958217263221741, "skipped": false, "seconds": 9408.6 }, { "step": 309, "epoch": 1, "loss": 0.018510348657640053, "lr": 3.5761204143717385e-05, "grad_norm": 0.2983313500881195, "skipped": false, "seconds": 9438.1 }, { "step": 310, "epoch": 1, "loss": 0.027753260579261186, "lr": 3.545729979973005e-05, "grad_norm": 0.49328893423080444, "skipped": false, "seconds": 9468.4 }, { "step": 311, "epoch": 1, "loss": 0.021194045424342375, "lr": 3.515398123358627e-05, "grad_norm": 0.29437315464019775, "skipped": false, "seconds": 9498.7 }, { "step": 312, "epoch": 1, "loss": 0.01686973282576468, "lr": 3.485126066291364e-05, "grad_norm": 0.24846428632736206, "skipped": false, "seconds": 9529.9 }, { "step": 313, "epoch": 1, "loss": 0.020775053623928477, "lr": 3.4549150281252636e-05, "grad_norm": 0.32179757952690125, "skipped": false, "seconds": 9561.7 }, { "step": 314, "epoch": 1, "loss": 0.01746008980630427, "lr": 3.424766225756537e-05, "grad_norm": 0.2708369493484497, "skipped": false, "seconds": 9592.7 }, { "step": 315, "epoch": 1, "loss": 0.02235273347283802, "lr": 3.394680873574546e-05, "grad_norm": 0.30049774050712585, "skipped": false, "seconds": 9623.0 }, { "step": 316, "epoch": 1, "loss": 0.020062926840855224, "lr": 3.364660183412892e-05, "grad_norm": 0.27229195833206177, "skipped": false, "seconds": 9654.1 }, { "step": 317, "epoch": 1, "loss": 0.017258836476076313, "lr": 3.334705364500596e-05, "grad_norm": 0.26787665486335754, "skipped": false, "seconds": 9684.8 }, { "step": 318, "epoch": 1, "loss": 0.01641855517474037, "lr": 3.304817623413397e-05, "grad_norm": 0.2533664405345917, "skipped": false, "seconds": 9715.7 }, { "step": 319, "epoch": 1, "loss": 0.019590947524596114, "lr": 3.274998164025148e-05, "grad_norm": 0.2662172317504883, "skipped": false, "seconds": 9746.9 }, { "step": 320, "epoch": 1, "loss": 0.015173372780071455, "lr": 3.2452481874593234e-05, "grad_norm": 0.2734486162662506, "skipped": false, "seconds": 9777.2 }, { "step": 321, "epoch": 1, "loss": 0.01690472215391683, "lr": 3.215568892040641e-05, "grad_norm": 0.2521533966064453, "skipped": false, "seconds": 9806.3 }, { "step": 322, "epoch": 1, "loss": 0.02087894162760005, "lr": 3.1859614732467954e-05, "grad_norm": 0.31441473960876465, "skipped": false, "seconds": 9836.5 }, { "step": 323, "epoch": 1, "loss": 0.013367866929058109, "lr": 3.156427123660297e-05, "grad_norm": 0.2140335887670517, "skipped": false, "seconds": 9867.4 }, { "step": 324, "epoch": 1, "loss": 0.014857198143227932, "lr": 3.12696703292044e-05, "grad_norm": 0.25735756754875183, "skipped": false, "seconds": 9898.8 }, { "step": 325, "epoch": 1, "loss": 0.017185792865311567, "lr": 3.097582387675385e-05, "grad_norm": 0.311068594455719, "skipped": false, "seconds": 9929.0 }, { "step": 326, "epoch": 1, "loss": 0.02158736824714009, "lr": 3.0682743715343564e-05, "grad_norm": 0.40494808554649353, "skipped": false, "seconds": 9960.3 }, { "step": 327, "epoch": 1, "loss": 0.017084697947514934, "lr": 3.0390441650199724e-05, "grad_norm": 0.40005937218666077, "skipped": false, "seconds": 9990.1 }, { "step": 328, "epoch": 1, "loss": 0.018331635892169955, "lr": 3.0098929455206904e-05, "grad_norm": 0.29285380244255066, "skipped": false, "seconds": 10020.1 }, { "step": 329, "epoch": 1, "loss": 0.01609054411061065, "lr": 2.9808218872433767e-05, "grad_norm": 0.3758953809738159, "skipped": false, "seconds": 10048.8 }, { "step": 330, "epoch": 1, "loss": 0.022970987022469896, "lr": 2.9518321611660237e-05, "grad_norm": 0.3137178421020508, "skipped": false, "seconds": 10079.0 }, { "step": 331, "epoch": 1, "loss": 0.017783200439661022, "lr": 2.9229249349905684e-05, "grad_norm": 0.29773151874542236, "skipped": false, "seconds": 10109.6 }, { "step": 332, "epoch": 1, "loss": 0.016127112212563518, "lr": 2.894101373095867e-05, "grad_norm": 0.2919289171695709, "skipped": false, "seconds": 10137.5 }, { "step": 333, "epoch": 1, "loss": 0.01922946286664721, "lr": 2.8653626364907917e-05, "grad_norm": 0.2525309920310974, "skipped": false, "seconds": 10168.2 }, { "step": 334, "epoch": 1, "loss": 0.013304160924842517, "lr": 2.8367098827674578e-05, "grad_norm": 0.23909994959831238, "skipped": false, "seconds": 10199.6 }, { "step": 335, "epoch": 1, "loss": 0.016354744904398068, "lr": 2.8081442660546125e-05, "grad_norm": 0.22283875942230225, "skipped": false, "seconds": 10228.6 }, { "step": 336, "epoch": 1, "loss": 0.015653531660566027, "lr": 2.7796669369711294e-05, "grad_norm": 0.2464396357536316, "skipped": false, "seconds": 10258.2 }, { "step": 337, "epoch": 1, "loss": 0.016884816086275165, "lr": 2.7512790425796718e-05, "grad_norm": 0.25359708070755005, "skipped": false, "seconds": 10288.8 }, { "step": 338, "epoch": 1, "loss": 0.02054701702025414, "lr": 2.7229817263404866e-05, "grad_norm": 0.22650858759880066, "skipped": false, "seconds": 10320.9 }, { "step": 339, "epoch": 1, "loss": 0.01796677281747861, "lr": 2.694776128065345e-05, "grad_norm": 0.3973900377750397, "skipped": false, "seconds": 10350.4 }, { "step": 340, "epoch": 1, "loss": 0.01574439181162856, "lr": 2.6666633838716314e-05, "grad_norm": 0.2303837239742279, "skipped": false, "seconds": 10380.1 }, { "step": 341, "epoch": 1, "loss": 0.013421567281087239, "lr": 2.638644626136587e-05, "grad_norm": 0.256214439868927, "skipped": false, "seconds": 10411.5 }, { "step": 342, "epoch": 1, "loss": 0.01560402047647239, "lr": 2.6107209834516854e-05, "grad_norm": 0.2719871401786804, "skipped": false, "seconds": 10444.1 }, { "step": 343, "epoch": 1, "loss": 0.02437654976241827, "lr": 2.5828935805771802e-05, "grad_norm": 0.5778554081916809, "skipped": false, "seconds": 10474.6 }, { "step": 344, "epoch": 1, "loss": 0.025893028253831666, "lr": 2.5551635383968065e-05, "grad_norm": 1.2740740776062012, "skipped": false, "seconds": 10505.2 }, { "step": 345, "epoch": 1, "loss": 0.01596813173179167, "lr": 2.5275319738726165e-05, "grad_norm": 0.3198592960834503, "skipped": false, "seconds": 10535.3 }, { "step": 346, "epoch": 1, "loss": 0.02277532178302144, "lr": 2.500000000000001e-05, "grad_norm": 0.36020344495773315, "skipped": false, "seconds": 10565.9 }, { "step": 347, "epoch": 1, "loss": 0.03668016211487209, "lr": 2.4725687257628534e-05, "grad_norm": 0.3347547948360443, "skipped": false, "seconds": 10596.5 }, { "step": 348, "epoch": 1, "loss": 0.018362691837820064, "lr": 2.4452392560888976e-05, "grad_norm": 0.5395991802215576, "skipped": false, "seconds": 10627.8 }, { "step": 349, "epoch": 1, "loss": 0.021723086045103975, "lr": 2.418012691805191e-05, "grad_norm": 0.30525851249694824, "skipped": false, "seconds": 10655.7 }, { "step": 350, "epoch": 1, "loss": 0.013355130647918101, "lr": 2.3908901295937713e-05, "grad_norm": 0.2056380659341812, "skipped": false, "seconds": 10687.6 }, { "step": 351, "epoch": 1, "loss": 0.01658166001536888, "lr": 2.363872661947488e-05, "grad_norm": 0.29792430996894836, "skipped": false, "seconds": 10717.7 }, { "step": 352, "epoch": 1, "loss": 0.01986786977065489, "lr": 2.336961377126001e-05, "grad_norm": 0.33303678035736084, "skipped": false, "seconds": 10749.8 }, { "step": 353, "epoch": 1, "loss": 0.019453472974544632, "lr": 2.310157359111938e-05, "grad_norm": 0.35702478885650635, "skipped": false, "seconds": 10779.0 }, { "step": 354, "epoch": 1, "loss": 0.015191067429245598, "lr": 2.283461687567236e-05, "grad_norm": 0.2647939622402191, "skipped": false, "seconds": 10808.7 }, { "step": 355, "epoch": 1, "loss": 0.015050849344550908, "lr": 2.2568754377896516e-05, "grad_norm": 0.2411239743232727, "skipped": false, "seconds": 10840.6 }, { "step": 356, "epoch": 1, "loss": 0.012920646420356383, "lr": 2.2303996806694488e-05, "grad_norm": 0.22789867222309113, "skipped": false, "seconds": 10871.0 }, { "step": 357, "epoch": 1, "loss": 0.014633365573149149, "lr": 2.2040354826462668e-05, "grad_norm": 0.2780497670173645, "skipped": false, "seconds": 10902.1 }, { "step": 358, "epoch": 1, "loss": 0.015241143214731, "lr": 2.1777839056661554e-05, "grad_norm": 0.2793889045715332, "skipped": false, "seconds": 10933.8 }, { "step": 359, "epoch": 1, "loss": 0.017730983503526435, "lr": 2.1516460071388062e-05, "grad_norm": 0.2675914466381073, "skipped": false, "seconds": 10964.3 }, { "step": 360, "epoch": 1, "loss": 0.02158524816624618, "lr": 2.125622839894964e-05, "grad_norm": 0.29603734612464905, "skipped": false, "seconds": 10995.1 }, { "step": 361, "epoch": 1, "loss": 0.016972364705656273, "lr": 2.09971545214401e-05, "grad_norm": 0.3738466203212738, "skipped": false, "seconds": 11026.7 }, { "step": 362, "epoch": 1, "loss": 0.021522874766122458, "lr": 2.073924887431744e-05, "grad_norm": 0.31328442692756653, "skipped": false, "seconds": 11058.1 }, { "step": 363, "epoch": 1, "loss": 0.017776748608779275, "lr": 2.048252184598352e-05, "grad_norm": 0.2673688232898712, "skipped": false, "seconds": 11089.1 }, { "step": 364, "epoch": 1, "loss": 0.020682575531182877, "lr": 2.0226983777365604e-05, "grad_norm": 0.3776637017726898, "skipped": false, "seconds": 11120.0 }, { "step": 365, "epoch": 1, "loss": 0.01417801892561934, "lr": 1.9972644961499854e-05, "grad_norm": 0.20646420121192932, "skipped": false, "seconds": 11150.7 }, { "step": 366, "epoch": 1, "loss": 0.019781235268653725, "lr": 1.9719515643116674e-05, "grad_norm": 0.31171584129333496, "skipped": false, "seconds": 11181.4 }, { "step": 367, "epoch": 1, "loss": 0.016028509728283503, "lr": 1.946760601822809e-05, "grad_norm": 0.271849662065506, "skipped": false, "seconds": 11211.2 }, { "step": 368, "epoch": 1, "loss": 0.01597410992545235, "lr": 1.9216926233717085e-05, "grad_norm": 0.26115888357162476, "skipped": false, "seconds": 11241.2 }, { "step": 369, "epoch": 1, "loss": 0.01464600051658741, "lr": 1.8967486386928817e-05, "grad_norm": 0.20717978477478027, "skipped": false, "seconds": 11271.8 }, { "step": 370, "epoch": 1, "loss": 0.014690513336154173, "lr": 1.8719296525263922e-05, "grad_norm": 0.2489292472600937, "skipped": false, "seconds": 11300.7 }, { "step": 371, "epoch": 1, "loss": 0.019532598908972135, "lr": 1.847236664577389e-05, "grad_norm": 0.2948475182056427, "skipped": false, "seconds": 11332.0 }, { "step": 372, "epoch": 1, "loss": 0.019013768308514138, "lr": 1.8226706694758195e-05, "grad_norm": 0.24077652394771576, "skipped": false, "seconds": 11363.0 }, { "step": 373, "epoch": 1, "loss": 0.015933554452930872, "lr": 1.7982326567363888e-05, "grad_norm": 0.287951797246933, "skipped": false, "seconds": 11394.9 }, { "step": 374, "epoch": 1, "loss": 0.01682713304488164, "lr": 1.773923610718686e-05, "grad_norm": 0.22983764111995697, "skipped": false, "seconds": 11424.4 }, { "step": 375, "epoch": 1, "loss": 0.017295656077654046, "lr": 1.7497445105875377e-05, "grad_norm": 0.2799907922744751, "skipped": false, "seconds": 11455.1 }, { "step": 376, "epoch": 1, "loss": 0.014463379727276486, "lr": 1.725696330273575e-05, "grad_norm": 0.2402082234621048, "skipped": false, "seconds": 11483.6 }, { "step": 377, "epoch": 1, "loss": 0.01813724382882879, "lr": 1.7017800384339928e-05, "grad_norm": 0.39935919642448425, "skipped": false, "seconds": 11513.5 }, { "step": 378, "epoch": 1, "loss": 0.02063750761723156, "lr": 1.6779965984135377e-05, "grad_norm": 0.26636335253715515, "skipped": false, "seconds": 11542.8 }, { "step": 379, "epoch": 1, "loss": 0.01720981912825147, "lr": 1.6543469682057106e-05, "grad_norm": 0.25584572553634644, "skipped": false, "seconds": 11573.4 }, { "step": 380, "epoch": 1, "loss": 0.016045881793675845, "lr": 1.6308321004141607e-05, "grad_norm": 0.24034883081912994, "skipped": false, "seconds": 11604.8 }, { "step": 381, "epoch": 1, "loss": 0.016837453895027516, "lr": 1.60745294221434e-05, "grad_norm": 0.27986347675323486, "skipped": false, "seconds": 11636.5 }, { "step": 382, "epoch": 1, "loss": 0.020221882823811536, "lr": 1.5842104353153287e-05, "grad_norm": 27.728328704833984, "skipped": false, "seconds": 11665.6 }, { "step": 383, "epoch": 1, "loss": 0.01467958791457942, "lr": 1.5611055159219152e-05, "grad_norm": 0.27296140789985657, "skipped": false, "seconds": 11696.4 }, { "step": 384, "epoch": 1, "loss": 0.014055224498078696, "lr": 1.5381391146968866e-05, "grad_norm": 0.22324781119823456, "skipped": false, "seconds": 11727.0 }, { "step": 385, "epoch": 1, "loss": 0.016929681425198358, "lr": 1.5153121567235335e-05, "grad_norm": 0.2702989876270294, "skipped": false, "seconds": 11757.3 }, { "step": 386, "epoch": 1, "loss": 0.015159464784758233, "lr": 1.4926255614683932e-05, "grad_norm": 0.2476302534341812, "skipped": false, "seconds": 11788.4 }, { "step": 387, "epoch": 1, "loss": 0.018204662800171433, "lr": 1.4700802427442179e-05, "grad_norm": 1.1057723760604858, "skipped": false, "seconds": 11819.5 }, { "step": 388, "epoch": 1, "loss": 0.01382485911035508, "lr": 1.4476771086731567e-05, "grad_norm": 0.2819043695926666, "skipped": false, "seconds": 11848.7 }, { "step": 389, "epoch": 1, "loss": 0.013176220352306017, "lr": 1.4254170616501827e-05, "grad_norm": 0.2870631217956543, "skipped": false, "seconds": 11879.2 }, { "step": 390, "epoch": 1, "loss": 0.015560504752145687, "lr": 1.4033009983067452e-05, "grad_norm": 0.2705937325954437, "skipped": false, "seconds": 11909.6 }, { "step": 391, "epoch": 1, "loss": 0.0172401643150863, "lr": 1.3813298094746491e-05, "grad_norm": 0.3437158465385437, "skipped": false, "seconds": 11940.3 }, { "step": 392, "epoch": 1, "loss": 0.021647427999498762, "lr": 1.3595043801501794e-05, "grad_norm": 0.2943425476551056, "skipped": false, "seconds": 11970.0 }, { "step": 393, "epoch": 1, "loss": 0.02094827180419021, "lr": 1.3378255894584463e-05, "grad_norm": 0.2669637203216553, "skipped": false, "seconds": 11999.7 }, { "step": 394, "epoch": 1, "loss": 0.016528638708385404, "lr": 1.3162943106179749e-05, "grad_norm": 0.29634103178977966, "skipped": false, "seconds": 12031.1 }, { "step": 395, "epoch": 1, "loss": 0.013307068416540571, "lr": 1.2949114109055415e-05, "grad_norm": 0.2215854972600937, "skipped": false, "seconds": 12060.2 }, { "step": 396, "epoch": 1, "loss": 0.015899094069978637, "lr": 1.2736777516212266e-05, "grad_norm": 0.2678273022174835, "skipped": false, "seconds": 12089.3 }, { "step": 397, "epoch": 1, "loss": 0.011314437034100134, "lr": 1.2525941880537307e-05, "grad_norm": 0.2707388997077942, "skipped": false, "seconds": 12119.0 }, { "step": 398, "epoch": 1, "loss": 0.01665331870056188, "lr": 1.2316615694459189e-05, "grad_norm": 0.4135851263999939, "skipped": false, "seconds": 12149.1 }, { "step": 399, "epoch": 1, "loss": 0.022952738952416948, "lr": 1.2108807389606158e-05, "grad_norm": 0.3070237338542938, "skipped": false, "seconds": 12179.5 }, { "step": 400, "epoch": 1, "loss": 0.017071752871094466, "lr": 1.1902525336466464e-05, "grad_norm": 0.23360101878643036, "skipped": false, "seconds": 12209.9 }, { "step": 401, "epoch": 1, "loss": 0.02012303668381288, "lr": 1.1697777844051105e-05, "grad_norm": 0.5425054430961609, "skipped": false, "seconds": 12240.2 }, { "step": 402, "epoch": 1, "loss": 0.013822645244752747, "lr": 1.1494573159559213e-05, "grad_norm": 0.24790161848068237, "skipped": false, "seconds": 12269.8 }, { "step": 403, "epoch": 1, "loss": 0.01809105012161628, "lr": 1.1292919468045877e-05, "grad_norm": 0.2774483263492584, "skipped": false, "seconds": 12299.4 }, { "step": 404, "epoch": 1, "loss": 0.014330840732265222, "lr": 1.1092824892092373e-05, "grad_norm": 0.30954477190971375, "skipped": false, "seconds": 12330.3 }, { "step": 405, "epoch": 1, "loss": 0.018357951065589642, "lr": 1.0894297491479045e-05, "grad_norm": 1.0409938097000122, "skipped": false, "seconds": 12360.4 }, { "step": 406, "epoch": 1, "loss": 0.016694805807263444, "lr": 1.0697345262860636e-05, "grad_norm": 0.3196686804294586, "skipped": false, "seconds": 12390.2 }, { "step": 407, "epoch": 1, "loss": 0.017687978299173884, "lr": 1.0501976139444191e-05, "grad_norm": 0.27741143107414246, "skipped": false, "seconds": 12420.6 }, { "step": 408, "epoch": 1, "loss": 0.02315771045021266, "lr": 1.0308197990669538e-05, "grad_norm": 0.33277827501296997, "skipped": false, "seconds": 12450.5 }, { "step": 409, "epoch": 1, "loss": 0.014765257162961296, "lr": 1.0116018621892237e-05, "grad_norm": 0.26430729031562805, "skipped": false, "seconds": 12481.0 }, { "step": 410, "epoch": 1, "loss": 0.021278894573238723, "lr": 9.92544577406923e-06, "grad_norm": 0.2686549127101898, "skipped": false, "seconds": 12511.7 }, { "step": 411, "epoch": 1, "loss": 0.014673768498664539, "lr": 9.73648712344707e-06, "grad_norm": 0.22932101786136627, "skipped": false, "seconds": 12540.4 }, { "step": 412, "epoch": 1, "loss": 0.012732859466220641, "lr": 9.549150281252633e-06, "grad_norm": 0.21991147100925446, "skipped": false, "seconds": 12571.3 }, { "step": 413, "epoch": 1, "loss": 0.01871246826772906, "lr": 9.363442793386606e-06, "grad_norm": 0.24232839047908783, "skipped": false, "seconds": 12603.8 }, { "step": 414, "epoch": 1, "loss": 0.013039972662259746, "lr": 9.179372140119525e-06, "grad_norm": 0.21381565928459167, "skipped": false, "seconds": 12636.0 }, { "step": 415, "epoch": 1, "loss": 0.01748069505959961, "lr": 8.996945735790447e-06, "grad_norm": 0.2568955421447754, "skipped": false, "seconds": 12664.7 }, { "step": 416, "epoch": 1, "loss": 0.014440955766563963, "lr": 8.816170928508365e-06, "grad_norm": 0.2171037197113037, "skipped": false, "seconds": 12695.5 }, { "step": 417, "epoch": 1, "loss": 0.013840633916014087, "lr": 8.637054999856148e-06, "grad_norm": 0.265576034784317, "skipped": false, "seconds": 12723.2 }, { "step": 418, "epoch": 1, "loss": 0.014396657270685956, "lr": 8.459605164597267e-06, "grad_norm": 0.26587891578674316, "skipped": false, "seconds": 12754.4 }, { "step": 419, "epoch": 1, "loss": 0.01791663248030866, "lr": 8.283828570385238e-06, "grad_norm": 0.3830026388168335, "skipped": false, "seconds": 12785.5 }, { "step": 420, "epoch": 1, "loss": 0.016166413976127142, "lr": 8.109732297475635e-06, "grad_norm": 0.26750504970550537, "skipped": false, "seconds": 12816.0 }, { "step": 421, "epoch": 1, "loss": 0.012980075526736159, "lr": 7.937323358440935e-06, "grad_norm": 0.23061294853687286, "skipped": false, "seconds": 12847.4 }, { "step": 422, "epoch": 1, "loss": 0.01326038453287219, "lr": 7.766608697888095e-06, "grad_norm": 0.2267688363790512, "skipped": false, "seconds": 12877.5 }, { "step": 423, "epoch": 1, "loss": 0.01464304382652022, "lr": 7.597595192178702e-06, "grad_norm": 0.26651710271835327, "skipped": false, "seconds": 12906.8 }, { "step": 424, "epoch": 1, "loss": 0.014991654364183522, "lr": 7.430289649152156e-06, "grad_norm": 3.3915822505950928, "skipped": false, "seconds": 12938.5 }, { "step": 425, "epoch": 1, "loss": 0.01039733584913624, "lr": 7.264698807851328e-06, "grad_norm": 0.1901535987854004, "skipped": false, "seconds": 12967.8 }, { "step": 426, "epoch": 1, "loss": 0.01814713527780788, "lr": 7.100829338251147e-06, "grad_norm": 0.3595639765262604, "skipped": false, "seconds": 12997.6 }, { "step": 427, "epoch": 1, "loss": 0.017600897006762102, "lr": 6.9386878409899715e-06, "grad_norm": 0.26794108748435974, "skipped": false, "seconds": 13028.5 }, { "step": 428, "epoch": 1, "loss": 0.013089698404604005, "lr": 6.778280847103669e-06, "grad_norm": 0.22527790069580078, "skipped": false, "seconds": 13058.3 }, { "step": 429, "epoch": 1, "loss": 0.014918052926552072, "lr": 6.619614817762537e-06, "grad_norm": 0.23448950052261353, "skipped": false, "seconds": 13090.1 }, { "step": 430, "epoch": 1, "loss": 0.01596330983663676, "lr": 6.462696144011149e-06, "grad_norm": 0.2590503692626953, "skipped": false, "seconds": 13121.9 }, { "step": 431, "epoch": 1, "loss": 0.0151835978799376, "lr": 6.3075311465107535e-06, "grad_norm": 0.20222195982933044, "skipped": false, "seconds": 13152.0 }, { "step": 432, "epoch": 1, "loss": 0.016157260446313156, "lr": 6.154126075284855e-06, "grad_norm": 0.26201319694519043, "skipped": false, "seconds": 13182.5 }, { "step": 433, "epoch": 1, "loss": 0.017083022302860837, "lr": 6.002487109467347e-06, "grad_norm": 0.3449777364730835, "skipped": false, "seconds": 13212.7 }, { "step": 434, "epoch": 1, "loss": 0.01500254542848523, "lr": 5.852620357053651e-06, "grad_norm": 0.2756975293159485, "skipped": false, "seconds": 13243.5 }, { "step": 435, "epoch": 1, "loss": 0.02222851620663891, "lr": 5.704531854654721e-06, "grad_norm": 0.3507115840911865, "skipped": false, "seconds": 13273.1 }, { "step": 436, "epoch": 1, "loss": 0.019562456892998556, "lr": 5.558227567253832e-06, "grad_norm": 0.49055540561676025, "skipped": false, "seconds": 13303.6 }, { "step": 437, "epoch": 1, "loss": 0.016707392397116234, "lr": 5.413713387966329e-06, "grad_norm": 0.30712446570396423, "skipped": false, "seconds": 13331.3 }, { "step": 438, "epoch": 1, "loss": 0.015860420129522206, "lr": 5.270995137802315e-06, "grad_norm": 0.2504942715167999, "skipped": false, "seconds": 13361.0 }, { "step": 439, "epoch": 1, "loss": 0.017581775125712695, "lr": 5.13007856543209e-06, "grad_norm": 0.24654711782932281, "skipped": false, "seconds": 13393.6 }, { "step": 440, "epoch": 1, "loss": 0.017193995594407954, "lr": 4.99096934695461e-06, "grad_norm": 0.2912333011627197, "skipped": false, "seconds": 13423.5 }, { "step": 441, "epoch": 1, "loss": 0.016572819199672965, "lr": 4.853673085668947e-06, "grad_norm": 0.24467350542545319, "skipped": false, "seconds": 13452.7 }, { "step": 442, "epoch": 1, "loss": 0.0161877468859019, "lr": 4.7181953118484556e-06, "grad_norm": 0.3681254982948303, "skipped": false, "seconds": 13482.4 }, { "step": 443, "epoch": 1, "loss": 0.017729474168756372, "lr": 4.58454148251814e-06, "grad_norm": 0.25886455178260803, "skipped": false, "seconds": 13513.4 }, { "step": 444, "epoch": 1, "loss": 0.017672039854985017, "lr": 4.452716981234744e-06, "grad_norm": 0.3544117510318756, "skipped": false, "seconds": 13543.3 }, { "step": 445, "epoch": 1, "loss": 0.014902976864204671, "lr": 4.322727117869951e-06, "grad_norm": 0.2283497452735901, "skipped": false, "seconds": 13573.1 }, { "step": 446, "epoch": 1, "loss": 0.017319539780133623, "lr": 4.19457712839652e-06, "grad_norm": 0.36809778213500977, "skipped": false, "seconds": 13602.4 }, { "step": 447, "epoch": 1, "loss": 0.021381757385359655, "lr": 4.068272174677335e-06, "grad_norm": 0.3147641718387604, "skipped": false, "seconds": 13632.3 }, { "step": 448, "epoch": 1, "loss": 0.01543112478605562, "lr": 3.9438173442575e-06, "grad_norm": 0.22462071478366852, "skipped": false, "seconds": 13662.9 }, { "step": 449, "epoch": 1, "loss": 0.01753268618065157, "lr": 3.821217650159453e-06, "grad_norm": 0.22539229691028595, "skipped": false, "seconds": 13694.8 }, { "step": 450, "epoch": 1, "loss": 0.01648473962055351, "lr": 3.700478030680987e-06, "grad_norm": 0.22293080389499664, "skipped": false, "seconds": 13725.2 }, { "step": 451, "epoch": 1, "loss": 0.01837570977896805, "lr": 3.581603349196372e-06, "grad_norm": 0.24224314093589783, "skipped": false, "seconds": 13755.3 }, { "step": 452, "epoch": 1, "loss": 0.011402834787101922, "lr": 3.4645983939604496e-06, "grad_norm": 0.21129898726940155, "skipped": false, "seconds": 13784.0 }, { "step": 453, "epoch": 1, "loss": 0.013870194191312664, "lr": 3.349467877915746e-06, "grad_norm": 0.21010389924049377, "skipped": false, "seconds": 13813.6 }, { "step": 454, "epoch": 1, "loss": 0.014568589164859322, "lr": 3.2362164385026706e-06, "grad_norm": 0.2321111261844635, "skipped": false, "seconds": 13845.4 }, { "step": 455, "epoch": 1, "loss": 0.015580425932430933, "lr": 3.1248486374726883e-06, "grad_norm": 0.2638421356678009, "skipped": false, "seconds": 13877.1 }, { "step": 456, "epoch": 1, "loss": 0.013652178491824374, "lr": 3.0153689607045845e-06, "grad_norm": 0.24279172718524933, "skipped": false, "seconds": 13907.7 }, { "step": 457, "epoch": 1, "loss": 0.01109541549945247, "lr": 2.9077818180237693e-06, "grad_norm": 0.22842855751514435, "skipped": false, "seconds": 13939.2 }, { "step": 458, "epoch": 1, "loss": 0.016054675009398334, "lr": 2.802091543024671e-06, "grad_norm": 0.3169231414794922, "skipped": false, "seconds": 13968.8 }, { "step": 459, "epoch": 1, "loss": 0.021520703001592777, "lr": 2.6983023928961404e-06, "grad_norm": 0.4069320857524872, "skipped": false, "seconds": 14000.2 }, { "step": 460, "epoch": 1, "loss": 0.013510759170049744, "lr": 2.596418548250029e-06, "grad_norm": 0.21013274788856506, "skipped": false, "seconds": 14031.5 }, { "step": 461, "epoch": 1, "loss": 0.013634231950015235, "lr": 2.496444112952734e-06, "grad_norm": 0.29028260707855225, "skipped": false, "seconds": 14063.1 }, { "step": 462, "epoch": 1, "loss": 0.01630439492373671, "lr": 2.3983831139599287e-06, "grad_norm": 0.23812183737754822, "skipped": false, "seconds": 14094.4 }, { "step": 463, "epoch": 1, "loss": 0.015388567299092912, "lr": 2.3022395011543686e-06, "grad_norm": 0.22293654084205627, "skipped": false, "seconds": 14123.4 }, { "step": 464, "epoch": 1, "loss": 0.015927969555081974, "lr": 2.208017147186736e-06, "grad_norm": 0.28787466883659363, "skipped": false, "seconds": 14154.5 }, { "step": 465, "epoch": 1, "loss": 0.014266629292836635, "lr": 2.1157198473197414e-06, "grad_norm": 0.23060643672943115, "skipped": false, "seconds": 14185.9 }, { "step": 466, "epoch": 1, "loss": 0.019002444870969852, "lr": 2.0253513192751373e-06, "grad_norm": 0.2352025806903839, "skipped": false, "seconds": 14216.0 }, { "step": 467, "epoch": 1, "loss": 0.016235436245141923, "lr": 1.9369152030840556e-06, "grad_norm": 0.3779015839099884, "skipped": false, "seconds": 14246.5 }, { "step": 468, "epoch": 1, "loss": 0.02078640302022298, "lr": 1.8504150609403858e-06, "grad_norm": 0.3310161232948303, "skipped": false, "seconds": 14277.5 }, { "step": 469, "epoch": 1, "loss": 0.012792520942559773, "lr": 1.7658543770572189e-06, "grad_norm": 0.21761828660964966, "skipped": false, "seconds": 14307.9 }, { "step": 470, "epoch": 1, "loss": 0.016218211290812422, "lr": 1.6832365575265741e-06, "grad_norm": 0.20596861839294434, "skipped": false, "seconds": 14338.0 }, { "step": 471, "epoch": 1, "loss": 0.019815962166179115, "lr": 1.6025649301821876e-06, "grad_norm": 0.28267160058021545, "skipped": false, "seconds": 14369.4 }, { "step": 472, "epoch": 1, "loss": 0.013912331480348034, "lr": 1.523842744465437e-06, "grad_norm": 0.23686163127422333, "skipped": false, "seconds": 14399.0 }, { "step": 473, "epoch": 1, "loss": 0.013959775194577858, "lr": 1.4470731712944884e-06, "grad_norm": 0.2434159815311432, "skipped": false, "seconds": 14429.9 }, { "step": 474, "epoch": 1, "loss": 0.01357290552109755, "lr": 1.372259302936546e-06, "grad_norm": 0.2746292054653168, "skipped": false, "seconds": 14461.3 }, { "step": 475, "epoch": 1, "loss": 0.014042890674668011, "lr": 1.2994041528833266e-06, "grad_norm": 0.2632994055747986, "skipped": false, "seconds": 14492.8 }, { "step": 476, "epoch": 1, "loss": 0.013474665587544012, "lr": 1.2285106557296477e-06, "grad_norm": 0.2416546642780304, "skipped": false, "seconds": 14523.3 }, { "step": 477, "epoch": 1, "loss": 0.01666516979245374, "lr": 1.1595816670552428e-06, "grad_norm": 0.23275969922542572, "skipped": false, "seconds": 14552.4 }, { "step": 478, "epoch": 1, "loss": 0.011933755860480118, "lr": 1.0926199633097157e-06, "grad_norm": 0.22021210193634033, "skipped": false, "seconds": 14582.8 }, { "step": 479, "epoch": 1, "loss": 0.01824787427528745, "lr": 1.02762824170074e-06, "grad_norm": 0.2591199576854706, "skipped": false, "seconds": 14612.6 }, { "step": 480, "epoch": 1, "loss": 0.01649331980774414, "lr": 9.646091200853802e-07, "grad_norm": 0.3194705545902252, "skipped": false, "seconds": 14645.0 }, { "step": 481, "epoch": 1, "loss": 0.02036778127466428, "lr": 9.035651368646648e-07, "grad_norm": 0.43635284900665283, "skipped": false, "seconds": 14675.4 }, { "step": 482, "epoch": 1, "loss": 0.016031105149885316, "lr": 8.444987508813451e-07, "grad_norm": 0.22120577096939087, "skipped": false, "seconds": 14706.1 }, { "step": 483, "epoch": 1, "loss": 0.015851634324078795, "lr": 7.874123413208145e-07, "grad_norm": 0.3351321816444397, "skipped": false, "seconds": 14737.7 }, { "step": 484, "epoch": 1, "loss": 0.017026997200027875, "lr": 7.323082076153509e-07, "grad_norm": 0.28247079253196716, "skipped": false, "seconds": 14768.3 }, { "step": 485, "epoch": 1, "loss": 0.021605440543634866, "lr": 6.791885693514133e-07, "grad_norm": 0.27851662039756775, "skipped": false, "seconds": 14799.0 }, { "step": 486, "epoch": 1, "loss": 0.017235946980944803, "lr": 6.280555661802856e-07, "grad_norm": 0.2936553657054901, "skipped": false, "seconds": 14829.3 }, { "step": 487, "epoch": 1, "loss": 0.01512704289275211, "lr": 5.78911257731879e-07, "grad_norm": 0.21169595420360565, "skipped": false, "seconds": 14860.4 }, { "step": 488, "epoch": 1, "loss": 0.016688139252046503, "lr": 5.317576235317756e-07, "grad_norm": 0.2827041745185852, "skipped": false, "seconds": 14891.6 }, { "step": 489, "epoch": 1, "loss": 0.014433720455782647, "lr": 4.865965629214819e-07, "grad_norm": 0.24454833567142487, "skipped": false, "seconds": 14922.8 }, { "step": 490, "epoch": 1, "loss": 0.01710877140949955, "lr": 4.434298949819449e-07, "grad_norm": 0.2576327621936798, "skipped": false, "seconds": 14954.1 }, { "step": 491, "epoch": 1, "loss": 0.024297605621693766, "lr": 4.02259358460233e-07, "grad_norm": 0.46404898166656494, "skipped": false, "seconds": 14983.7 }, { "step": 492, "epoch": 1, "loss": 0.01663580822664791, "lr": 3.630866116995757e-07, "grad_norm": 0.27184104919433594, "skipped": false, "seconds": 15014.6 }, { "step": 493, "epoch": 1, "loss": 0.020265022200381948, "lr": 3.2591323257248893e-07, "grad_norm": 0.24386714398860931, "skipped": false, "seconds": 15045.4 }, { "step": 494, "epoch": 1, "loss": 0.016951551928618313, "lr": 2.907407184172706e-07, "grad_norm": 0.27427002787590027, "skipped": false, "seconds": 15075.4 }, { "step": 495, "epoch": 1, "loss": 0.016049816498071592, "lr": 2.5757048597765396e-07, "grad_norm": 0.22172033786773682, "skipped": false, "seconds": 15106.9 }, { "step": 496, "epoch": 1, "loss": 0.01609070582001692, "lr": 2.2640387134577058e-07, "grad_norm": 0.2710008919239044, "skipped": false, "seconds": 15136.7 }, { "step": 497, "epoch": 1, "loss": 0.015595577054981822, "lr": 1.9724212990830938e-07, "grad_norm": 0.25194889307022095, "skipped": false, "seconds": 15166.6 }, { "step": 498, "epoch": 1, "loss": 0.011678507451703827, "lr": 1.7008643629596866e-07, "grad_norm": 2.243579626083374, "skipped": false, "seconds": 15197.3 }, { "step": 499, "epoch": 1, "loss": 0.014588745646268718, "lr": 1.449378843361271e-07, "grad_norm": 0.2866562604904175, "skipped": false, "seconds": 15228.6 }, { "step": 500, "epoch": 1, "loss": 0.013277890113232332, "lr": 1.2179748700879012e-07, "grad_norm": 0.2638900876045227, "skipped": false, "seconds": 15259.5 }, { "step": 501, "epoch": 1, "loss": 0.013807131787219783, "lr": 1.0066617640578368e-07, "grad_norm": 0.23005108535289764, "skipped": false, "seconds": 15290.9 }, { "step": 502, "epoch": 1, "loss": 0.02514329022550263, "lr": 8.15448036932176e-08, "grad_norm": 0.24505768716335297, "skipped": false, "seconds": 15323.3 }, { "step": 503, "epoch": 1, "loss": 0.019522010527541444, "lr": 6.443413907720186e-08, "grad_norm": 0.3740701973438263, "skipped": false, "seconds": 15353.2 }, { "step": 504, "epoch": 1, "loss": 0.015291050259849599, "lr": 4.933487177280482e-08, "grad_norm": 0.29071199893951416, "skipped": false, "seconds": 15383.7 }, { "step": 505, "epoch": 1, "loss": 0.014405335253931761, "lr": 3.624760997631982e-08, "grad_norm": 0.2308592051267624, "skipped": false, "seconds": 15414.3 }, { "step": 506, "epoch": 1, "loss": 0.012780588496198009, "lr": 2.5172880840745873e-08, "grad_norm": 0.25191834568977356, "skipped": false, "seconds": 15445.2 }, { "step": 507, "epoch": 1, "loss": 0.01951780338693646, "lr": 1.6111130454543598e-08, "grad_norm": 0.47091758251190186, "skipped": false, "seconds": 15474.9 }, { "step": 508, "epoch": 1, "loss": 0.014618728624938905, "lr": 9.06272382371065e-09, "grad_norm": 0.2414289265871048, "skipped": false, "seconds": 15506.0 }, { "step": 509, "epoch": 1, "loss": 0.014318742624718845, "lr": 4.0279448570323954e-09, "grad_norm": 0.24327567219734192, "skipped": false, "seconds": 15534.2 }, { "step": 510, "epoch": 1, "loss": 0.010492502323318565, "lr": 1.0069963546743832e-09, "grad_norm": 0.2578527629375458, "skipped": false, "seconds": 15551.6 } ] }