{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1180, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003395585738539898, "grad_norm": 7.1178366810389075, "learning_rate": 0.0, "loss": 0.5506677627563477, "step": 1 }, { "epoch": 0.006791171477079796, "grad_norm": 7.024814904097202, "learning_rate": 8.474576271186441e-07, "loss": 0.599281907081604, "step": 2 }, { "epoch": 0.010186757215619695, "grad_norm": 6.853107961612166, "learning_rate": 1.6949152542372882e-06, "loss": 0.5870709419250488, "step": 3 }, { "epoch": 0.013582342954159592, "grad_norm": 5.954984166055368, "learning_rate": 2.5423728813559323e-06, "loss": 0.5824997425079346, "step": 4 }, { "epoch": 0.01697792869269949, "grad_norm": 4.658838920956997, "learning_rate": 3.3898305084745763e-06, "loss": 0.585983157157898, "step": 5 }, { "epoch": 0.02037351443123939, "grad_norm": 3.2010849287722585, "learning_rate": 4.23728813559322e-06, "loss": 0.5429093241691589, "step": 6 }, { "epoch": 0.023769100169779286, "grad_norm": 2.9163250402862957, "learning_rate": 5.084745762711865e-06, "loss": 0.542880654335022, "step": 7 }, { "epoch": 0.027164685908319185, "grad_norm": 1.9185843677049557, "learning_rate": 5.932203389830509e-06, "loss": 0.5096145868301392, "step": 8 }, { "epoch": 0.030560271646859084, "grad_norm": 1.1982853083312783, "learning_rate": 6.779661016949153e-06, "loss": 0.41756781935691833, "step": 9 }, { "epoch": 0.03395585738539898, "grad_norm": 1.0596692131749834, "learning_rate": 7.627118644067798e-06, "loss": 0.46277719736099243, "step": 10 }, { "epoch": 0.03735144312393888, "grad_norm": 1.8214728018448225, "learning_rate": 8.47457627118644e-06, "loss": 0.4573628902435303, "step": 11 }, { "epoch": 0.04074702886247878, "grad_norm": 1.600210925717614, "learning_rate": 9.322033898305085e-06, "loss": 0.41718530654907227, "step": 12 }, { "epoch": 0.044142614601018676, "grad_norm": 1.4921367520201188, "learning_rate": 1.016949152542373e-05, "loss": 0.43204784393310547, "step": 13 }, { "epoch": 0.04753820033955857, "grad_norm": 1.0851179549374617, "learning_rate": 1.1016949152542374e-05, "loss": 0.40290939807891846, "step": 14 }, { "epoch": 0.050933786078098474, "grad_norm": 0.8551868034270019, "learning_rate": 1.1864406779661018e-05, "loss": 0.3809565305709839, "step": 15 }, { "epoch": 0.05432937181663837, "grad_norm": 0.6767693231830578, "learning_rate": 1.2711864406779661e-05, "loss": 0.36067473888397217, "step": 16 }, { "epoch": 0.057724957555178265, "grad_norm": 0.6494263513664725, "learning_rate": 1.3559322033898305e-05, "loss": 0.3391953408718109, "step": 17 }, { "epoch": 0.06112054329371817, "grad_norm": 0.6740114111548333, "learning_rate": 1.440677966101695e-05, "loss": 0.34520161151885986, "step": 18 }, { "epoch": 0.06451612903225806, "grad_norm": 0.6127236499049523, "learning_rate": 1.5254237288135596e-05, "loss": 0.3492334485054016, "step": 19 }, { "epoch": 0.06791171477079797, "grad_norm": 0.4757507185674207, "learning_rate": 1.6101694915254237e-05, "loss": 0.3266001343727112, "step": 20 }, { "epoch": 0.07130730050933787, "grad_norm": 0.4286168800029103, "learning_rate": 1.694915254237288e-05, "loss": 0.317482590675354, "step": 21 }, { "epoch": 0.07470288624787776, "grad_norm": 0.44220907165134377, "learning_rate": 1.7796610169491526e-05, "loss": 0.33983325958251953, "step": 22 }, { "epoch": 0.07809847198641766, "grad_norm": 0.4589148928047419, "learning_rate": 1.864406779661017e-05, "loss": 0.3188186585903168, "step": 23 }, { "epoch": 0.08149405772495756, "grad_norm": 0.43377805787378765, "learning_rate": 1.9491525423728814e-05, "loss": 0.3050963282585144, "step": 24 }, { "epoch": 0.08488964346349745, "grad_norm": 1.1868658781282868, "learning_rate": 2.033898305084746e-05, "loss": 0.28910261392593384, "step": 25 }, { "epoch": 0.08828522920203735, "grad_norm": 0.3695239848956912, "learning_rate": 2.1186440677966103e-05, "loss": 0.3009563684463501, "step": 26 }, { "epoch": 0.09168081494057725, "grad_norm": 0.3201270679717402, "learning_rate": 2.2033898305084748e-05, "loss": 0.31131142377853394, "step": 27 }, { "epoch": 0.09507640067911714, "grad_norm": 0.3388887999146668, "learning_rate": 2.2881355932203392e-05, "loss": 0.31799793243408203, "step": 28 }, { "epoch": 0.09847198641765705, "grad_norm": 0.3384355876435382, "learning_rate": 2.3728813559322036e-05, "loss": 0.30172300338745117, "step": 29 }, { "epoch": 0.10186757215619695, "grad_norm": 0.31769175010577233, "learning_rate": 2.457627118644068e-05, "loss": 0.29452279210090637, "step": 30 }, { "epoch": 0.10526315789473684, "grad_norm": 0.32085416879183465, "learning_rate": 2.5423728813559322e-05, "loss": 0.27935513854026794, "step": 31 }, { "epoch": 0.10865874363327674, "grad_norm": 0.32274117843801886, "learning_rate": 2.627118644067797e-05, "loss": 0.28016525506973267, "step": 32 }, { "epoch": 0.11205432937181664, "grad_norm": 0.3281125773660198, "learning_rate": 2.711864406779661e-05, "loss": 0.2676544487476349, "step": 33 }, { "epoch": 0.11544991511035653, "grad_norm": 0.3030091352312692, "learning_rate": 2.7966101694915255e-05, "loss": 0.28189581632614136, "step": 34 }, { "epoch": 0.11884550084889643, "grad_norm": 0.2861172077824191, "learning_rate": 2.88135593220339e-05, "loss": 0.2989804446697235, "step": 35 }, { "epoch": 0.12224108658743633, "grad_norm": 0.3094781303022246, "learning_rate": 2.9661016949152544e-05, "loss": 0.27032431960105896, "step": 36 }, { "epoch": 0.12563667232597622, "grad_norm": 0.3035094719118333, "learning_rate": 3.050847457627119e-05, "loss": 0.2800889015197754, "step": 37 }, { "epoch": 0.12903225806451613, "grad_norm": 0.2768573734011211, "learning_rate": 3.135593220338983e-05, "loss": 0.27580755949020386, "step": 38 }, { "epoch": 0.13242784380305603, "grad_norm": 0.32254876682126954, "learning_rate": 3.2203389830508473e-05, "loss": 0.27307555079460144, "step": 39 }, { "epoch": 0.13582342954159593, "grad_norm": 0.3098612684379937, "learning_rate": 3.305084745762712e-05, "loss": 0.2461966574192047, "step": 40 }, { "epoch": 0.13921901528013583, "grad_norm": 0.29052564904643446, "learning_rate": 3.389830508474576e-05, "loss": 0.24892249703407288, "step": 41 }, { "epoch": 0.14261460101867574, "grad_norm": 0.28391336911106557, "learning_rate": 3.474576271186441e-05, "loss": 0.25047633051872253, "step": 42 }, { "epoch": 0.1460101867572156, "grad_norm": 0.25316802440332303, "learning_rate": 3.559322033898305e-05, "loss": 0.26240214705467224, "step": 43 }, { "epoch": 0.1494057724957555, "grad_norm": 0.2606660335730921, "learning_rate": 3.644067796610169e-05, "loss": 0.25489258766174316, "step": 44 }, { "epoch": 0.15280135823429541, "grad_norm": 0.273095082924603, "learning_rate": 3.728813559322034e-05, "loss": 0.28270888328552246, "step": 45 }, { "epoch": 0.15619694397283532, "grad_norm": 0.26451824539645064, "learning_rate": 3.813559322033898e-05, "loss": 0.25881218910217285, "step": 46 }, { "epoch": 0.15959252971137522, "grad_norm": 0.293871306555325, "learning_rate": 3.898305084745763e-05, "loss": 0.2486695945262909, "step": 47 }, { "epoch": 0.16298811544991512, "grad_norm": 0.30033225058730173, "learning_rate": 3.983050847457627e-05, "loss": 0.24640750885009766, "step": 48 }, { "epoch": 0.166383701188455, "grad_norm": 0.28600917740236625, "learning_rate": 4.067796610169492e-05, "loss": 0.23367922008037567, "step": 49 }, { "epoch": 0.1697792869269949, "grad_norm": 0.31556646859153925, "learning_rate": 4.152542372881356e-05, "loss": 0.236191064119339, "step": 50 }, { "epoch": 0.1731748726655348, "grad_norm": 0.2694247944660879, "learning_rate": 4.2372881355932206e-05, "loss": 0.25406211614608765, "step": 51 }, { "epoch": 0.1765704584040747, "grad_norm": 0.27427710136743083, "learning_rate": 4.3220338983050854e-05, "loss": 0.2599134147167206, "step": 52 }, { "epoch": 0.1799660441426146, "grad_norm": 0.28998564145903943, "learning_rate": 4.4067796610169495e-05, "loss": 0.25581443309783936, "step": 53 }, { "epoch": 0.1833616298811545, "grad_norm": 0.29073845004571885, "learning_rate": 4.491525423728814e-05, "loss": 0.2514399588108063, "step": 54 }, { "epoch": 0.1867572156196944, "grad_norm": 0.279749696448169, "learning_rate": 4.5762711864406784e-05, "loss": 0.2396245300769806, "step": 55 }, { "epoch": 0.19015280135823429, "grad_norm": 0.286612476876764, "learning_rate": 4.6610169491525425e-05, "loss": 0.23107075691223145, "step": 56 }, { "epoch": 0.1935483870967742, "grad_norm": 0.316397661882123, "learning_rate": 4.745762711864407e-05, "loss": 0.22436249256134033, "step": 57 }, { "epoch": 0.1969439728353141, "grad_norm": 0.31927357094314146, "learning_rate": 4.8305084745762714e-05, "loss": 0.22618135809898376, "step": 58 }, { "epoch": 0.200339558573854, "grad_norm": 0.32277569146168633, "learning_rate": 4.915254237288136e-05, "loss": 0.24815194308757782, "step": 59 }, { "epoch": 0.2037351443123939, "grad_norm": 0.29044290617868845, "learning_rate": 5e-05, "loss": 0.2659604549407959, "step": 60 }, { "epoch": 0.2071307300509338, "grad_norm": 0.2732315941257702, "learning_rate": 5.0847457627118643e-05, "loss": 0.2433127462863922, "step": 61 }, { "epoch": 0.21052631578947367, "grad_norm": 0.27109103512353994, "learning_rate": 5.1694915254237284e-05, "loss": 0.24123245477676392, "step": 62 }, { "epoch": 0.21392190152801357, "grad_norm": 0.2807796635423633, "learning_rate": 5.254237288135594e-05, "loss": 0.2337493896484375, "step": 63 }, { "epoch": 0.21731748726655348, "grad_norm": 0.27828658255387806, "learning_rate": 5.338983050847458e-05, "loss": 0.2308078408241272, "step": 64 }, { "epoch": 0.22071307300509338, "grad_norm": 0.27935527944112337, "learning_rate": 5.423728813559322e-05, "loss": 0.2289617508649826, "step": 65 }, { "epoch": 0.22410865874363328, "grad_norm": 0.3119695204217176, "learning_rate": 5.508474576271186e-05, "loss": 0.22649109363555908, "step": 66 }, { "epoch": 0.22750424448217318, "grad_norm": 0.31484085007951523, "learning_rate": 5.593220338983051e-05, "loss": 0.23481115698814392, "step": 67 }, { "epoch": 0.23089983022071306, "grad_norm": 0.2596726287989604, "learning_rate": 5.677966101694916e-05, "loss": 0.24313673377037048, "step": 68 }, { "epoch": 0.23429541595925296, "grad_norm": 0.27070114894324776, "learning_rate": 5.76271186440678e-05, "loss": 0.23855337500572205, "step": 69 }, { "epoch": 0.23769100169779286, "grad_norm": 0.356513712097721, "learning_rate": 5.8474576271186446e-05, "loss": 0.24447250366210938, "step": 70 }, { "epoch": 0.24108658743633277, "grad_norm": 0.2774437946110805, "learning_rate": 5.932203389830509e-05, "loss": 0.229949951171875, "step": 71 }, { "epoch": 0.24448217317487267, "grad_norm": 0.28588562248639116, "learning_rate": 6.016949152542373e-05, "loss": 0.24441254138946533, "step": 72 }, { "epoch": 0.24787775891341257, "grad_norm": 0.31597911189734607, "learning_rate": 6.101694915254238e-05, "loss": 0.2335294485092163, "step": 73 }, { "epoch": 0.25127334465195245, "grad_norm": 0.31962528326744133, "learning_rate": 6.186440677966102e-05, "loss": 0.21792781352996826, "step": 74 }, { "epoch": 0.2546689303904924, "grad_norm": 0.3222528810526582, "learning_rate": 6.271186440677966e-05, "loss": 0.21460942924022675, "step": 75 }, { "epoch": 0.25806451612903225, "grad_norm": 0.3207048994425017, "learning_rate": 6.35593220338983e-05, "loss": 0.25418978929519653, "step": 76 }, { "epoch": 0.2614601018675722, "grad_norm": 0.31407468150310375, "learning_rate": 6.440677966101695e-05, "loss": 0.2527194917201996, "step": 77 }, { "epoch": 0.26485568760611206, "grad_norm": 0.25578633390107663, "learning_rate": 6.52542372881356e-05, "loss": 0.22875438630580902, "step": 78 }, { "epoch": 0.26825127334465193, "grad_norm": 0.30041532574885715, "learning_rate": 6.610169491525424e-05, "loss": 0.24634066224098206, "step": 79 }, { "epoch": 0.27164685908319186, "grad_norm": 0.28720163470796234, "learning_rate": 6.694915254237288e-05, "loss": 0.23561954498291016, "step": 80 }, { "epoch": 0.27504244482173174, "grad_norm": 0.2968580729572226, "learning_rate": 6.779661016949152e-05, "loss": 0.2398541420698166, "step": 81 }, { "epoch": 0.27843803056027167, "grad_norm": 0.301600585896161, "learning_rate": 6.864406779661017e-05, "loss": 0.21922165155410767, "step": 82 }, { "epoch": 0.28183361629881154, "grad_norm": 0.34942349472966594, "learning_rate": 6.949152542372882e-05, "loss": 0.2114916294813156, "step": 83 }, { "epoch": 0.28522920203735147, "grad_norm": 0.29357812401075967, "learning_rate": 7.033898305084746e-05, "loss": 0.24709288775920868, "step": 84 }, { "epoch": 0.28862478777589134, "grad_norm": 0.2792515328095172, "learning_rate": 7.11864406779661e-05, "loss": 0.24666891992092133, "step": 85 }, { "epoch": 0.2920203735144312, "grad_norm": 0.3093064457550283, "learning_rate": 7.203389830508474e-05, "loss": 0.24253448843955994, "step": 86 }, { "epoch": 0.29541595925297115, "grad_norm": 0.26746552284000313, "learning_rate": 7.288135593220338e-05, "loss": 0.22799479961395264, "step": 87 }, { "epoch": 0.298811544991511, "grad_norm": 0.32134448393955756, "learning_rate": 7.372881355932204e-05, "loss": 0.24200555682182312, "step": 88 }, { "epoch": 0.30220713073005095, "grad_norm": 0.30615974473522656, "learning_rate": 7.457627118644068e-05, "loss": 0.2582242488861084, "step": 89 }, { "epoch": 0.30560271646859083, "grad_norm": 0.2956997407518662, "learning_rate": 7.542372881355932e-05, "loss": 0.2349974364042282, "step": 90 }, { "epoch": 0.3089983022071307, "grad_norm": 0.3242077945910731, "learning_rate": 7.627118644067796e-05, "loss": 0.2243499457836151, "step": 91 }, { "epoch": 0.31239388794567063, "grad_norm": 0.2291267096943001, "learning_rate": 7.711864406779662e-05, "loss": 0.20744214951992035, "step": 92 }, { "epoch": 0.3157894736842105, "grad_norm": 0.25590320049675314, "learning_rate": 7.796610169491526e-05, "loss": 0.2435624599456787, "step": 93 }, { "epoch": 0.31918505942275044, "grad_norm": 0.24707015368979632, "learning_rate": 7.88135593220339e-05, "loss": 0.23833028972148895, "step": 94 }, { "epoch": 0.3225806451612903, "grad_norm": 0.2625160380202141, "learning_rate": 7.966101694915254e-05, "loss": 0.24096858501434326, "step": 95 }, { "epoch": 0.32597623089983024, "grad_norm": 0.2694747093274474, "learning_rate": 8.050847457627118e-05, "loss": 0.23922137916088104, "step": 96 }, { "epoch": 0.3293718166383701, "grad_norm": 0.2597742217407219, "learning_rate": 8.135593220338983e-05, "loss": 0.23311959207057953, "step": 97 }, { "epoch": 0.33276740237691, "grad_norm": 0.2735106779620377, "learning_rate": 8.220338983050848e-05, "loss": 0.23571442067623138, "step": 98 }, { "epoch": 0.3361629881154499, "grad_norm": 0.3016690403750513, "learning_rate": 8.305084745762712e-05, "loss": 0.21786992251873016, "step": 99 }, { "epoch": 0.3395585738539898, "grad_norm": 0.2951484956467193, "learning_rate": 8.389830508474577e-05, "loss": 0.2159511148929596, "step": 100 }, { "epoch": 0.34295415959252973, "grad_norm": 0.27308055347297105, "learning_rate": 8.474576271186441e-05, "loss": 0.24954597651958466, "step": 101 }, { "epoch": 0.3463497453310696, "grad_norm": 0.29559834594219103, "learning_rate": 8.559322033898305e-05, "loss": 0.23789939284324646, "step": 102 }, { "epoch": 0.34974533106960953, "grad_norm": 0.2662332814050448, "learning_rate": 8.644067796610171e-05, "loss": 0.2424975335597992, "step": 103 }, { "epoch": 0.3531409168081494, "grad_norm": 0.26894005975361857, "learning_rate": 8.728813559322035e-05, "loss": 0.22227713465690613, "step": 104 }, { "epoch": 0.3565365025466893, "grad_norm": 0.2878280691210002, "learning_rate": 8.813559322033899e-05, "loss": 0.2273646593093872, "step": 105 }, { "epoch": 0.3599320882852292, "grad_norm": 0.26630814801598224, "learning_rate": 8.898305084745763e-05, "loss": 0.22364693880081177, "step": 106 }, { "epoch": 0.3633276740237691, "grad_norm": 0.3239290678180081, "learning_rate": 8.983050847457629e-05, "loss": 0.23547998070716858, "step": 107 }, { "epoch": 0.366723259762309, "grad_norm": 0.3079831363362857, "learning_rate": 9.067796610169493e-05, "loss": 0.21374540030956268, "step": 108 }, { "epoch": 0.3701188455008489, "grad_norm": 0.28005875856276596, "learning_rate": 9.152542372881357e-05, "loss": 0.24590888619422913, "step": 109 }, { "epoch": 0.3735144312393888, "grad_norm": 0.24348555831706375, "learning_rate": 9.237288135593221e-05, "loss": 0.2446185052394867, "step": 110 }, { "epoch": 0.3769100169779287, "grad_norm": 0.2869203540357986, "learning_rate": 9.322033898305085e-05, "loss": 0.24687200784683228, "step": 111 }, { "epoch": 0.38030560271646857, "grad_norm": 0.270117618665772, "learning_rate": 9.40677966101695e-05, "loss": 0.23702184855937958, "step": 112 }, { "epoch": 0.3837011884550085, "grad_norm": 0.30519582405042517, "learning_rate": 9.491525423728815e-05, "loss": 0.2477806806564331, "step": 113 }, { "epoch": 0.3870967741935484, "grad_norm": 0.25676748233120766, "learning_rate": 9.576271186440679e-05, "loss": 0.2298315465450287, "step": 114 }, { "epoch": 0.3904923599320883, "grad_norm": 0.2532913495029346, "learning_rate": 9.661016949152543e-05, "loss": 0.23230913281440735, "step": 115 }, { "epoch": 0.3938879456706282, "grad_norm": 0.28288759260938, "learning_rate": 9.745762711864407e-05, "loss": 0.22428736090660095, "step": 116 }, { "epoch": 0.39728353140916806, "grad_norm": 0.2527417684235068, "learning_rate": 9.830508474576272e-05, "loss": 0.24214443564414978, "step": 117 }, { "epoch": 0.400679117147708, "grad_norm": 0.2205547994996794, "learning_rate": 9.915254237288136e-05, "loss": 0.23968636989593506, "step": 118 }, { "epoch": 0.40407470288624786, "grad_norm": 0.26864017651744315, "learning_rate": 0.0001, "loss": 0.2447093427181244, "step": 119 }, { "epoch": 0.4074702886247878, "grad_norm": 0.26668139212734876, "learning_rate": 9.999978122867161e-05, "loss": 0.23015892505645752, "step": 120 }, { "epoch": 0.41086587436332767, "grad_norm": 0.2605430941629103, "learning_rate": 9.999912491660088e-05, "loss": 0.2350776046514511, "step": 121 }, { "epoch": 0.4142614601018676, "grad_norm": 0.27256983855135675, "learning_rate": 9.99980310695311e-05, "loss": 0.23778581619262695, "step": 122 }, { "epoch": 0.41765704584040747, "grad_norm": 0.261499381758678, "learning_rate": 9.999649969703437e-05, "loss": 0.23488375544548035, "step": 123 }, { "epoch": 0.42105263157894735, "grad_norm": 0.25089308058112375, "learning_rate": 9.999453081251149e-05, "loss": 0.21894145011901855, "step": 124 }, { "epoch": 0.4244482173174873, "grad_norm": 0.28936844899089237, "learning_rate": 9.99921244331919e-05, "loss": 0.2228689193725586, "step": 125 }, { "epoch": 0.42784380305602715, "grad_norm": 0.2866460472139636, "learning_rate": 9.998928058013346e-05, "loss": 0.24738013744354248, "step": 126 }, { "epoch": 0.4312393887945671, "grad_norm": 0.27878129244896416, "learning_rate": 9.99859992782223e-05, "loss": 0.2421463429927826, "step": 127 }, { "epoch": 0.43463497453310695, "grad_norm": 0.28081462224652015, "learning_rate": 9.998228055617263e-05, "loss": 0.2364376038312912, "step": 128 }, { "epoch": 0.4380305602716469, "grad_norm": 0.26989498758835595, "learning_rate": 9.997812444652643e-05, "loss": 0.23303601145744324, "step": 129 }, { "epoch": 0.44142614601018676, "grad_norm": 0.24401601941837, "learning_rate": 9.997353098565322e-05, "loss": 0.21893653273582458, "step": 130 }, { "epoch": 0.44482173174872663, "grad_norm": 0.2739884490318145, "learning_rate": 9.996850021374968e-05, "loss": 0.22419391572475433, "step": 131 }, { "epoch": 0.44821731748726656, "grad_norm": 0.2776652345145256, "learning_rate": 9.996303217483938e-05, "loss": 0.23730161786079407, "step": 132 }, { "epoch": 0.45161290322580644, "grad_norm": 0.2904925384328224, "learning_rate": 9.99571269167723e-05, "loss": 0.2120521366596222, "step": 133 }, { "epoch": 0.45500848896434637, "grad_norm": 0.2409477512228426, "learning_rate": 9.995078449122451e-05, "loss": 0.23090839385986328, "step": 134 }, { "epoch": 0.45840407470288624, "grad_norm": 0.24163416430182227, "learning_rate": 9.99440049536976e-05, "loss": 0.2544405162334442, "step": 135 }, { "epoch": 0.4617996604414261, "grad_norm": 0.24681258800534392, "learning_rate": 9.993678836351836e-05, "loss": 0.23123544454574585, "step": 136 }, { "epoch": 0.46519524617996605, "grad_norm": 0.26560000913600756, "learning_rate": 9.99291347838381e-05, "loss": 0.22880616784095764, "step": 137 }, { "epoch": 0.4685908319185059, "grad_norm": 0.24965796902874066, "learning_rate": 9.992104428163216e-05, "loss": 0.23567315936088562, "step": 138 }, { "epoch": 0.47198641765704585, "grad_norm": 0.2462058407532618, "learning_rate": 9.991251692769932e-05, "loss": 0.22095608711242676, "step": 139 }, { "epoch": 0.47538200339558573, "grad_norm": 0.27903370011716255, "learning_rate": 9.990355279666124e-05, "loss": 0.21891427040100098, "step": 140 }, { "epoch": 0.47877758913412566, "grad_norm": 0.25636106850723833, "learning_rate": 9.98941519669617e-05, "loss": 0.22320841252803802, "step": 141 }, { "epoch": 0.48217317487266553, "grad_norm": 0.21145894117851521, "learning_rate": 9.988431452086596e-05, "loss": 0.19432592391967773, "step": 142 }, { "epoch": 0.4855687606112054, "grad_norm": 0.23515983413377808, "learning_rate": 9.987404054446008e-05, "loss": 0.24033010005950928, "step": 143 }, { "epoch": 0.48896434634974534, "grad_norm": 0.23745667306130833, "learning_rate": 9.986333012765013e-05, "loss": 0.2425290197134018, "step": 144 }, { "epoch": 0.4923599320882852, "grad_norm": 0.21442704179864383, "learning_rate": 9.985218336416138e-05, "loss": 0.2400854080915451, "step": 145 }, { "epoch": 0.49575551782682514, "grad_norm": 0.4019545064519207, "learning_rate": 9.98406003515375e-05, "loss": 0.2298232764005661, "step": 146 }, { "epoch": 0.499151103565365, "grad_norm": 0.23786718933107567, "learning_rate": 9.982858119113979e-05, "loss": 0.23393326997756958, "step": 147 }, { "epoch": 0.5025466893039049, "grad_norm": 0.24285589465748644, "learning_rate": 9.981612598814611e-05, "loss": 0.22845295071601868, "step": 148 }, { "epoch": 0.5059422750424448, "grad_norm": 0.24302634390278022, "learning_rate": 9.980323485155013e-05, "loss": 0.21047458052635193, "step": 149 }, { "epoch": 0.5093378607809848, "grad_norm": 0.25358128389692347, "learning_rate": 9.97899078941603e-05, "loss": 0.2082354873418808, "step": 150 }, { "epoch": 0.5127334465195246, "grad_norm": 0.23847873502310243, "learning_rate": 9.977614523259884e-05, "loss": 0.24798107147216797, "step": 151 }, { "epoch": 0.5161290322580645, "grad_norm": 0.23345850904212775, "learning_rate": 9.976194698730079e-05, "loss": 0.2375301569700241, "step": 152 }, { "epoch": 0.5195246179966044, "grad_norm": 0.2368422414277986, "learning_rate": 9.974731328251293e-05, "loss": 0.23879459500312805, "step": 153 }, { "epoch": 0.5229202037351444, "grad_norm": 4.994135695054419, "learning_rate": 9.973224424629265e-05, "loss": 0.24870698153972626, "step": 154 }, { "epoch": 0.5263157894736842, "grad_norm": 0.30514318964382864, "learning_rate": 9.971674001050686e-05, "loss": 0.22625446319580078, "step": 155 }, { "epoch": 0.5297113752122241, "grad_norm": 0.30519418195866216, "learning_rate": 9.970080071083086e-05, "loss": 0.23094254732131958, "step": 156 }, { "epoch": 0.533106960950764, "grad_norm": 0.289491616043026, "learning_rate": 9.968442648674713e-05, "loss": 0.2225530445575714, "step": 157 }, { "epoch": 0.5365025466893039, "grad_norm": 0.2523622184038582, "learning_rate": 9.966761748154408e-05, "loss": 0.21614186465740204, "step": 158 }, { "epoch": 0.5398981324278438, "grad_norm": 0.2508299294026511, "learning_rate": 9.965037384231488e-05, "loss": 0.23069505393505096, "step": 159 }, { "epoch": 0.5432937181663837, "grad_norm": 0.25000121023230865, "learning_rate": 9.963269571995604e-05, "loss": 0.24436424672603607, "step": 160 }, { "epoch": 0.5466893039049237, "grad_norm": 0.22989692708443416, "learning_rate": 9.961458326916624e-05, "loss": 0.2381608933210373, "step": 161 }, { "epoch": 0.5500848896434635, "grad_norm": 0.25164343786807386, "learning_rate": 9.959603664844486e-05, "loss": 0.23107120394706726, "step": 162 }, { "epoch": 0.5534804753820034, "grad_norm": 0.23564002438428963, "learning_rate": 9.957705602009068e-05, "loss": 0.2146880328655243, "step": 163 }, { "epoch": 0.5568760611205433, "grad_norm": 0.24989526466865708, "learning_rate": 9.955764155020037e-05, "loss": 0.21356713771820068, "step": 164 }, { "epoch": 0.5602716468590832, "grad_norm": 0.24304847818625214, "learning_rate": 9.95377934086671e-05, "loss": 0.2142661064863205, "step": 165 }, { "epoch": 0.5636672325976231, "grad_norm": 0.2438400077071865, "learning_rate": 9.951751176917907e-05, "loss": 0.20942895114421844, "step": 166 }, { "epoch": 0.567062818336163, "grad_norm": 0.24079855409285839, "learning_rate": 9.94967968092179e-05, "loss": 0.23409561812877655, "step": 167 }, { "epoch": 0.5704584040747029, "grad_norm": 0.21284832091287684, "learning_rate": 9.947564871005717e-05, "loss": 0.23351506888866425, "step": 168 }, { "epoch": 0.5738539898132428, "grad_norm": 0.2223868476827016, "learning_rate": 9.94540676567608e-05, "loss": 0.22570857405662537, "step": 169 }, { "epoch": 0.5772495755517827, "grad_norm": 0.2276866612162022, "learning_rate": 9.943205383818141e-05, "loss": 0.217237651348114, "step": 170 }, { "epoch": 0.5806451612903226, "grad_norm": 0.23276976082403275, "learning_rate": 9.940960744695868e-05, "loss": 0.22958600521087646, "step": 171 }, { "epoch": 0.5840407470288624, "grad_norm": 0.2668186678853451, "learning_rate": 9.938672867951773e-05, "loss": 0.2244614064693451, "step": 172 }, { "epoch": 0.5874363327674024, "grad_norm": 0.22664025108342212, "learning_rate": 9.936341773606723e-05, "loss": 0.21355020999908447, "step": 173 }, { "epoch": 0.5908319185059423, "grad_norm": 0.37743205692118836, "learning_rate": 9.933967482059787e-05, "loss": 0.2083015739917755, "step": 174 }, { "epoch": 0.5942275042444821, "grad_norm": 0.2593542036852034, "learning_rate": 9.931550014088039e-05, "loss": 0.19412027299404144, "step": 175 }, { "epoch": 0.597623089983022, "grad_norm": 0.937089907509418, "learning_rate": 9.929089390846387e-05, "loss": 0.2366977334022522, "step": 176 }, { "epoch": 0.601018675721562, "grad_norm": 0.24027124334830727, "learning_rate": 9.926585633867385e-05, "loss": 0.24104642868041992, "step": 177 }, { "epoch": 0.6044142614601019, "grad_norm": 0.28887539421272934, "learning_rate": 9.924038765061042e-05, "loss": 0.23962323367595673, "step": 178 }, { "epoch": 0.6078098471986417, "grad_norm": 0.2576543841282187, "learning_rate": 9.921448806714631e-05, "loss": 0.22236159443855286, "step": 179 }, { "epoch": 0.6112054329371817, "grad_norm": 0.26241795649632377, "learning_rate": 9.918815781492496e-05, "loss": 0.2328980416059494, "step": 180 }, { "epoch": 0.6146010186757216, "grad_norm": 0.2713558869213999, "learning_rate": 9.916139712435859e-05, "loss": 0.22485488653182983, "step": 181 }, { "epoch": 0.6179966044142614, "grad_norm": 0.24923721688373596, "learning_rate": 9.913420622962606e-05, "loss": 0.21858148276805878, "step": 182 }, { "epoch": 0.6213921901528013, "grad_norm": 0.2928533904192313, "learning_rate": 9.910658536867086e-05, "loss": 0.21802471578121185, "step": 183 }, { "epoch": 0.6247877758913413, "grad_norm": 0.25570059047914656, "learning_rate": 9.907853478319912e-05, "loss": 0.2524697780609131, "step": 184 }, { "epoch": 0.6281833616298812, "grad_norm": 0.26428073931896845, "learning_rate": 9.905005471867739e-05, "loss": 0.24499434232711792, "step": 185 }, { "epoch": 0.631578947368421, "grad_norm": 0.2571790196855782, "learning_rate": 9.902114542433051e-05, "loss": 0.23677490651607513, "step": 186 }, { "epoch": 0.634974533106961, "grad_norm": 0.24655161272441353, "learning_rate": 9.89918071531395e-05, "loss": 0.24191361665725708, "step": 187 }, { "epoch": 0.6383701188455009, "grad_norm": 0.21940759244496874, "learning_rate": 9.896204016183925e-05, "loss": 0.22591513395309448, "step": 188 }, { "epoch": 0.6417657045840407, "grad_norm": 0.26082527438281883, "learning_rate": 9.89318447109163e-05, "loss": 0.21840059757232666, "step": 189 }, { "epoch": 0.6451612903225806, "grad_norm": 0.23406534105627977, "learning_rate": 9.890122106460666e-05, "loss": 0.2169826477766037, "step": 190 }, { "epoch": 0.6485568760611206, "grad_norm": 0.27428907598331453, "learning_rate": 9.887016949089333e-05, "loss": 0.22284410893917084, "step": 191 }, { "epoch": 0.6519524617996605, "grad_norm": 0.21490156052971887, "learning_rate": 9.883869026150409e-05, "loss": 0.22144243121147156, "step": 192 }, { "epoch": 0.6553480475382003, "grad_norm": 0.22066212075505107, "learning_rate": 9.880678365190902e-05, "loss": 0.24004662036895752, "step": 193 }, { "epoch": 0.6587436332767402, "grad_norm": 0.18864383882840047, "learning_rate": 9.87744499413182e-05, "loss": 0.2288690060377121, "step": 194 }, { "epoch": 0.6621392190152802, "grad_norm": 0.24196563864650045, "learning_rate": 9.874168941267919e-05, "loss": 0.23588120937347412, "step": 195 }, { "epoch": 0.66553480475382, "grad_norm": 0.20460484523540667, "learning_rate": 9.870850235267453e-05, "loss": 0.2202383279800415, "step": 196 }, { "epoch": 0.6689303904923599, "grad_norm": 0.22516293707456805, "learning_rate": 9.867488905171933e-05, "loss": 0.21472087502479553, "step": 197 }, { "epoch": 0.6723259762308998, "grad_norm": 0.2469948742540965, "learning_rate": 9.864084980395867e-05, "loss": 0.21431753039360046, "step": 198 }, { "epoch": 0.6757215619694398, "grad_norm": 0.2276467117009385, "learning_rate": 9.860638490726497e-05, "loss": 0.2234257161617279, "step": 199 }, { "epoch": 0.6791171477079796, "grad_norm": 0.259052310914345, "learning_rate": 9.857149466323549e-05, "loss": 0.2075185477733612, "step": 200 }, { "epoch": 0.6825127334465195, "grad_norm": 0.21933265105604827, "learning_rate": 9.853617937718966e-05, "loss": 0.2294955551624298, "step": 201 }, { "epoch": 0.6859083191850595, "grad_norm": 0.25275605747765933, "learning_rate": 9.850043935816633e-05, "loss": 0.24128815531730652, "step": 202 }, { "epoch": 0.6893039049235993, "grad_norm": 0.23805874675739983, "learning_rate": 9.846427491892118e-05, "loss": 0.23756973445415497, "step": 203 }, { "epoch": 0.6926994906621392, "grad_norm": 0.25015537885215355, "learning_rate": 9.842768637592388e-05, "loss": 0.2260195016860962, "step": 204 }, { "epoch": 0.6960950764006791, "grad_norm": 0.2282910370617052, "learning_rate": 9.839067404935542e-05, "loss": 0.2113071084022522, "step": 205 }, { "epoch": 0.6994906621392191, "grad_norm": 0.2826530491569556, "learning_rate": 9.835323826310521e-05, "loss": 0.22311383485794067, "step": 206 }, { "epoch": 0.7028862478777589, "grad_norm": 0.23070174496730433, "learning_rate": 9.831537934476835e-05, "loss": 0.2145499438047409, "step": 207 }, { "epoch": 0.7062818336162988, "grad_norm": 0.2694973269236268, "learning_rate": 9.827709762564263e-05, "loss": 0.21655277907848358, "step": 208 }, { "epoch": 0.7096774193548387, "grad_norm": 0.19614155165837252, "learning_rate": 9.82383934407258e-05, "loss": 0.21204611659049988, "step": 209 }, { "epoch": 0.7130730050933786, "grad_norm": 0.23985509301390945, "learning_rate": 9.819926712871247e-05, "loss": 0.24427255988121033, "step": 210 }, { "epoch": 0.7164685908319185, "grad_norm": 0.2067050962676951, "learning_rate": 9.815971903199126e-05, "loss": 0.23202571272850037, "step": 211 }, { "epoch": 0.7198641765704584, "grad_norm": 0.22382982829123338, "learning_rate": 9.811974949664175e-05, "loss": 0.22098636627197266, "step": 212 }, { "epoch": 0.7232597623089984, "grad_norm": 0.21490302661522875, "learning_rate": 9.807935887243147e-05, "loss": 0.21789786219596863, "step": 213 }, { "epoch": 0.7266553480475382, "grad_norm": 0.23409646513230503, "learning_rate": 9.803854751281285e-05, "loss": 0.216179758310318, "step": 214 }, { "epoch": 0.7300509337860781, "grad_norm": 0.20964624933570156, "learning_rate": 9.79973157749201e-05, "loss": 0.21294806897640228, "step": 215 }, { "epoch": 0.733446519524618, "grad_norm": 0.23229538635579616, "learning_rate": 9.79556640195661e-05, "loss": 0.20469018816947937, "step": 216 }, { "epoch": 0.7368421052631579, "grad_norm": 0.2135001013869683, "learning_rate": 9.791359261123926e-05, "loss": 0.2233818769454956, "step": 217 }, { "epoch": 0.7402376910016978, "grad_norm": 0.2002811105518864, "learning_rate": 9.787110191810027e-05, "loss": 0.2394098937511444, "step": 218 }, { "epoch": 0.7436332767402377, "grad_norm": 0.22815238407474717, "learning_rate": 9.782819231197898e-05, "loss": 0.243118017911911, "step": 219 }, { "epoch": 0.7470288624787776, "grad_norm": 0.21605901692659363, "learning_rate": 9.7784864168371e-05, "loss": 0.2359468638896942, "step": 220 }, { "epoch": 0.7504244482173175, "grad_norm": 0.2116593286193831, "learning_rate": 9.77411178664346e-05, "loss": 0.21984606981277466, "step": 221 }, { "epoch": 0.7538200339558574, "grad_norm": 0.2018692843177458, "learning_rate": 9.769695378898722e-05, "loss": 0.21307775378227234, "step": 222 }, { "epoch": 0.7572156196943973, "grad_norm": 0.22120834695991848, "learning_rate": 9.765237232250222e-05, "loss": 0.19848167896270752, "step": 223 }, { "epoch": 0.7606112054329371, "grad_norm": 0.21947936601850218, "learning_rate": 9.760737385710547e-05, "loss": 0.1999792754650116, "step": 224 }, { "epoch": 0.7640067911714771, "grad_norm": 0.24536315067614115, "learning_rate": 9.756195878657192e-05, "loss": 0.20483741164207458, "step": 225 }, { "epoch": 0.767402376910017, "grad_norm": 0.23025021844151686, "learning_rate": 9.75161275083222e-05, "loss": 0.25475412607192993, "step": 226 }, { "epoch": 0.7707979626485568, "grad_norm": 0.23345597770727125, "learning_rate": 9.746988042341906e-05, "loss": 0.24407581984996796, "step": 227 }, { "epoch": 0.7741935483870968, "grad_norm": 0.2049966459545434, "learning_rate": 9.7423217936564e-05, "loss": 0.22000408172607422, "step": 228 }, { "epoch": 0.7775891341256367, "grad_norm": 0.21639276173326616, "learning_rate": 9.737614045609356e-05, "loss": 0.23386375606060028, "step": 229 }, { "epoch": 0.7809847198641766, "grad_norm": 0.21365526354578962, "learning_rate": 9.732864839397584e-05, "loss": 0.22645223140716553, "step": 230 }, { "epoch": 0.7843803056027164, "grad_norm": 0.2732144357585197, "learning_rate": 9.728074216580694e-05, "loss": 0.2220667600631714, "step": 231 }, { "epoch": 0.7877758913412564, "grad_norm": 0.2143091345894192, "learning_rate": 9.723242219080721e-05, "loss": 0.20215916633605957, "step": 232 }, { "epoch": 0.7911714770797963, "grad_norm": 0.22666682655303366, "learning_rate": 9.718368889181764e-05, "loss": 0.20549795031547546, "step": 233 }, { "epoch": 0.7945670628183361, "grad_norm": 0.2176639667132063, "learning_rate": 9.71345426952962e-05, "loss": 0.2441175878047943, "step": 234 }, { "epoch": 0.797962648556876, "grad_norm": 0.20258282549356804, "learning_rate": 9.708498403131401e-05, "loss": 0.2296900451183319, "step": 235 }, { "epoch": 0.801358234295416, "grad_norm": 0.21969989327477835, "learning_rate": 9.703501333355168e-05, "loss": 0.2238549292087555, "step": 236 }, { "epoch": 0.8047538200339559, "grad_norm": 0.23069241609289173, "learning_rate": 9.698463103929542e-05, "loss": 0.2226986140012741, "step": 237 }, { "epoch": 0.8081494057724957, "grad_norm": 0.6439618200720699, "learning_rate": 9.693383758943333e-05, "loss": 0.22474968433380127, "step": 238 }, { "epoch": 0.8115449915110357, "grad_norm": 0.3628558428615112, "learning_rate": 9.68826334284514e-05, "loss": 0.21470312774181366, "step": 239 }, { "epoch": 0.8149405772495756, "grad_norm": 0.26763666260984226, "learning_rate": 9.683101900442973e-05, "loss": 0.22060631215572357, "step": 240 }, { "epoch": 0.8183361629881154, "grad_norm": 0.24297945641759153, "learning_rate": 9.677899476903857e-05, "loss": 0.2042260617017746, "step": 241 }, { "epoch": 0.8217317487266553, "grad_norm": 0.2375665265328584, "learning_rate": 9.672656117753434e-05, "loss": 0.2103169858455658, "step": 242 }, { "epoch": 0.8251273344651953, "grad_norm": 0.21496291548970697, "learning_rate": 9.667371868875574e-05, "loss": 0.23855875432491302, "step": 243 }, { "epoch": 0.8285229202037352, "grad_norm": 0.21509347893390351, "learning_rate": 9.662046776511959e-05, "loss": 0.21938180923461914, "step": 244 }, { "epoch": 0.831918505942275, "grad_norm": 0.20014411456480394, "learning_rate": 9.656680887261693e-05, "loss": 0.22301563620567322, "step": 245 }, { "epoch": 0.8353140916808149, "grad_norm": 0.2072135960747425, "learning_rate": 9.651274248080882e-05, "loss": 0.2160690277814865, "step": 246 }, { "epoch": 0.8387096774193549, "grad_norm": 0.19805632635787146, "learning_rate": 9.645826906282233e-05, "loss": 0.2054440975189209, "step": 247 }, { "epoch": 0.8421052631578947, "grad_norm": 0.2167209645597022, "learning_rate": 9.640338909534636e-05, "loss": 0.20753411948680878, "step": 248 }, { "epoch": 0.8455008488964346, "grad_norm": 0.2080074211377332, "learning_rate": 9.634810305862741e-05, "loss": 0.20639455318450928, "step": 249 }, { "epoch": 0.8488964346349746, "grad_norm": 0.23663348399315012, "learning_rate": 9.62924114364655e-05, "loss": 0.20507106184959412, "step": 250 }, { "epoch": 0.8522920203735145, "grad_norm": 0.1889918578558979, "learning_rate": 9.62363147162098e-05, "loss": 0.22666499018669128, "step": 251 }, { "epoch": 0.8556876061120543, "grad_norm": 0.1949815965291924, "learning_rate": 9.617981338875448e-05, "loss": 0.2249736487865448, "step": 252 }, { "epoch": 0.8590831918505942, "grad_norm": 0.19956093525712537, "learning_rate": 9.612290794853439e-05, "loss": 0.2283181995153427, "step": 253 }, { "epoch": 0.8624787775891342, "grad_norm": 0.20212131833498942, "learning_rate": 9.606559889352064e-05, "loss": 0.22333121299743652, "step": 254 }, { "epoch": 0.865874363327674, "grad_norm": 0.2444086358960834, "learning_rate": 9.60078867252164e-05, "loss": 0.21846352517604828, "step": 255 }, { "epoch": 0.8692699490662139, "grad_norm": 0.20909707924589782, "learning_rate": 9.594977194865234e-05, "loss": 0.2146604061126709, "step": 256 }, { "epoch": 0.8726655348047538, "grad_norm": 0.2572707827585049, "learning_rate": 9.589125507238233e-05, "loss": 0.20799563825130463, "step": 257 }, { "epoch": 0.8760611205432938, "grad_norm": 0.2166071202742226, "learning_rate": 9.583233660847899e-05, "loss": 0.1953374594449997, "step": 258 }, { "epoch": 0.8794567062818336, "grad_norm": 0.21887463058885664, "learning_rate": 9.577301707252912e-05, "loss": 0.22548696398735046, "step": 259 }, { "epoch": 0.8828522920203735, "grad_norm": 0.18605324305501425, "learning_rate": 9.57132969836293e-05, "loss": 0.21879589557647705, "step": 260 }, { "epoch": 0.8862478777589134, "grad_norm": 0.24234467796174414, "learning_rate": 9.565317686438123e-05, "loss": 0.2384566068649292, "step": 261 }, { "epoch": 0.8896434634974533, "grad_norm": 0.19610615106953166, "learning_rate": 9.559265724088723e-05, "loss": 0.22203326225280762, "step": 262 }, { "epoch": 0.8930390492359932, "grad_norm": 0.21043294667279946, "learning_rate": 9.553173864274567e-05, "loss": 0.21503224968910217, "step": 263 }, { "epoch": 0.8964346349745331, "grad_norm": 0.2301954992674604, "learning_rate": 9.547042160304624e-05, "loss": 0.2197357416152954, "step": 264 }, { "epoch": 0.8998302207130731, "grad_norm": 0.2646454943330505, "learning_rate": 9.540870665836535e-05, "loss": 0.2099461555480957, "step": 265 }, { "epoch": 0.9032258064516129, "grad_norm": 0.22916765632853775, "learning_rate": 9.534659434876141e-05, "loss": 0.2035030573606491, "step": 266 }, { "epoch": 0.9066213921901528, "grad_norm": 0.20044888216109796, "learning_rate": 9.528408521777013e-05, "loss": 0.2143951654434204, "step": 267 }, { "epoch": 0.9100169779286927, "grad_norm": 0.19301009298451235, "learning_rate": 9.522117981239973e-05, "loss": 0.22913703322410583, "step": 268 }, { "epoch": 0.9134125636672326, "grad_norm": 0.20048858324184862, "learning_rate": 9.515787868312619e-05, "loss": 0.21478328108787537, "step": 269 }, { "epoch": 0.9168081494057725, "grad_norm": 0.2062783547856151, "learning_rate": 9.509418238388837e-05, "loss": 0.21238267421722412, "step": 270 }, { "epoch": 0.9202037351443124, "grad_norm": 0.20846281626763072, "learning_rate": 9.503009147208323e-05, "loss": 0.21635258197784424, "step": 271 }, { "epoch": 0.9235993208828522, "grad_norm": 0.2109019771556574, "learning_rate": 9.496560650856097e-05, "loss": 0.2180865854024887, "step": 272 }, { "epoch": 0.9269949066213922, "grad_norm": 0.19649788756387773, "learning_rate": 9.490072805761999e-05, "loss": 0.197824165225029, "step": 273 }, { "epoch": 0.9303904923599321, "grad_norm": 0.2053019341884595, "learning_rate": 9.48354566870021e-05, "loss": 0.19292232394218445, "step": 274 }, { "epoch": 0.933786078098472, "grad_norm": 0.2273589406667174, "learning_rate": 9.476979296788747e-05, "loss": 0.2040998339653015, "step": 275 }, { "epoch": 0.9371816638370118, "grad_norm": 0.19800513910506343, "learning_rate": 9.470373747488966e-05, "loss": 0.2347426414489746, "step": 276 }, { "epoch": 0.9405772495755518, "grad_norm": 0.1896743063740462, "learning_rate": 9.463729078605062e-05, "loss": 0.22722655534744263, "step": 277 }, { "epoch": 0.9439728353140917, "grad_norm": 0.1941259952363859, "learning_rate": 9.457045348283552e-05, "loss": 0.21831445395946503, "step": 278 }, { "epoch": 0.9473684210526315, "grad_norm": 0.19936923160310902, "learning_rate": 9.450322615012783e-05, "loss": 0.22684292495250702, "step": 279 }, { "epoch": 0.9507640067911715, "grad_norm": 0.20702489184730474, "learning_rate": 9.443560937622403e-05, "loss": 0.21297010779380798, "step": 280 }, { "epoch": 0.9541595925297114, "grad_norm": 0.19290541776416487, "learning_rate": 9.436760375282859e-05, "loss": 0.21467456221580505, "step": 281 }, { "epoch": 0.9575551782682513, "grad_norm": 0.20704612424478325, "learning_rate": 9.429920987504872e-05, "loss": 0.20584368705749512, "step": 282 }, { "epoch": 0.9609507640067911, "grad_norm": 0.26344294252348743, "learning_rate": 9.423042834138924e-05, "loss": 0.21096479892730713, "step": 283 }, { "epoch": 0.9643463497453311, "grad_norm": 0.20201659226714985, "learning_rate": 9.41612597537472e-05, "loss": 0.21519868075847626, "step": 284 }, { "epoch": 0.967741935483871, "grad_norm": 0.19479262162416716, "learning_rate": 9.40917047174068e-05, "loss": 0.22541747987270355, "step": 285 }, { "epoch": 0.9711375212224108, "grad_norm": 0.21871305630005558, "learning_rate": 9.402176384103391e-05, "loss": 0.22788241505622864, "step": 286 }, { "epoch": 0.9745331069609507, "grad_norm": 0.21325220105041445, "learning_rate": 9.395143773667088e-05, "loss": 0.21846871078014374, "step": 287 }, { "epoch": 0.9779286926994907, "grad_norm": 0.21257803875656317, "learning_rate": 9.388072701973112e-05, "loss": 0.2181614488363266, "step": 288 }, { "epoch": 0.9813242784380306, "grad_norm": 0.21492380221961657, "learning_rate": 9.380963230899371e-05, "loss": 0.20441970229148865, "step": 289 }, { "epoch": 0.9847198641765704, "grad_norm": 0.22232701000715308, "learning_rate": 9.373815422659806e-05, "loss": 0.20419475436210632, "step": 290 }, { "epoch": 0.9881154499151104, "grad_norm": 0.22471854913748254, "learning_rate": 9.366629339803836e-05, "loss": 0.20370034873485565, "step": 291 }, { "epoch": 0.9915110356536503, "grad_norm": 0.2182200087586731, "learning_rate": 9.359405045215816e-05, "loss": 0.22537897527217865, "step": 292 }, { "epoch": 0.9949066213921901, "grad_norm": 0.21277303782523274, "learning_rate": 9.352142602114486e-05, "loss": 0.21867594122886658, "step": 293 }, { "epoch": 0.99830220713073, "grad_norm": 0.22637719161065545, "learning_rate": 9.34484207405242e-05, "loss": 0.21650215983390808, "step": 294 }, { "epoch": 1.0, "grad_norm": 0.28058619046453315, "learning_rate": 9.337503524915468e-05, "loss": 0.18550601601600647, "step": 295 }, { "epoch": 1.00339558573854, "grad_norm": 0.23639443665656001, "learning_rate": 9.330127018922194e-05, "loss": 0.1868228167295456, "step": 296 }, { "epoch": 1.0067911714770799, "grad_norm": 0.22816538266976844, "learning_rate": 9.322712620623319e-05, "loss": 0.18762430548667908, "step": 297 }, { "epoch": 1.0101867572156198, "grad_norm": 0.24420119035702575, "learning_rate": 9.315260394901153e-05, "loss": 0.18745410442352295, "step": 298 }, { "epoch": 1.0135823429541595, "grad_norm": 0.25021615524039786, "learning_rate": 9.30777040696903e-05, "loss": 0.17205271124839783, "step": 299 }, { "epoch": 1.0169779286926994, "grad_norm": 0.23633599345350373, "learning_rate": 9.300242722370735e-05, "loss": 0.15902850031852722, "step": 300 }, { "epoch": 1.0203735144312394, "grad_norm": 0.24119731016839763, "learning_rate": 9.292677406979929e-05, "loss": 0.15773308277130127, "step": 301 }, { "epoch": 1.0237691001697793, "grad_norm": 0.23151537445122872, "learning_rate": 9.285074526999576e-05, "loss": 0.13681277632713318, "step": 302 }, { "epoch": 1.0271646859083192, "grad_norm": 0.27738569267536983, "learning_rate": 9.277434148961364e-05, "loss": 0.1409766674041748, "step": 303 }, { "epoch": 1.0305602716468591, "grad_norm": 0.30334263847950926, "learning_rate": 9.269756339725116e-05, "loss": 0.17550992965698242, "step": 304 }, { "epoch": 1.033955857385399, "grad_norm": 0.22711009522114184, "learning_rate": 9.262041166478214e-05, "loss": 0.1663069725036621, "step": 305 }, { "epoch": 1.0373514431239388, "grad_norm": 0.24431445899857623, "learning_rate": 9.254288696735007e-05, "loss": 0.18417814373970032, "step": 306 }, { "epoch": 1.0407470288624787, "grad_norm": 0.19985054623431828, "learning_rate": 9.246498998336219e-05, "loss": 0.1629078984260559, "step": 307 }, { "epoch": 1.0441426146010186, "grad_norm": 0.2161015945297243, "learning_rate": 9.238672139448354e-05, "loss": 0.15201131999492645, "step": 308 }, { "epoch": 1.0475382003395586, "grad_norm": 0.18955204144616244, "learning_rate": 9.230808188563109e-05, "loss": 0.13979549705982208, "step": 309 }, { "epoch": 1.0509337860780985, "grad_norm": 0.2292819098216901, "learning_rate": 9.222907214496763e-05, "loss": 0.1403750777244568, "step": 310 }, { "epoch": 1.0543293718166384, "grad_norm": 0.20993925748496248, "learning_rate": 9.214969286389576e-05, "loss": 0.1467626988887787, "step": 311 }, { "epoch": 1.0577249575551784, "grad_norm": 0.22613230470025902, "learning_rate": 9.206994473705192e-05, "loss": 0.1573966145515442, "step": 312 }, { "epoch": 1.061120543293718, "grad_norm": 0.20746124496919238, "learning_rate": 9.198982846230028e-05, "loss": 0.18230614066123962, "step": 313 }, { "epoch": 1.064516129032258, "grad_norm": 0.20019386012407803, "learning_rate": 9.190934474072658e-05, "loss": 0.17953181266784668, "step": 314 }, { "epoch": 1.067911714770798, "grad_norm": 0.20968950417583684, "learning_rate": 9.182849427663205e-05, "loss": 0.15756899118423462, "step": 315 }, { "epoch": 1.0713073005093379, "grad_norm": 0.2265429559757196, "learning_rate": 9.174727777752723e-05, "loss": 0.16961023211479187, "step": 316 }, { "epoch": 1.0747028862478778, "grad_norm": 0.19941995280442124, "learning_rate": 9.166569595412575e-05, "loss": 0.15267187356948853, "step": 317 }, { "epoch": 1.0780984719864177, "grad_norm": 0.20167959867434732, "learning_rate": 9.158374952033819e-05, "loss": 0.14712190628051758, "step": 318 }, { "epoch": 1.0814940577249577, "grad_norm": 0.20340656029227042, "learning_rate": 9.150143919326577e-05, "loss": 0.13596060872077942, "step": 319 }, { "epoch": 1.0848896434634974, "grad_norm": 0.2414393043852893, "learning_rate": 9.141876569319404e-05, "loss": 0.1422816663980484, "step": 320 }, { "epoch": 1.0882852292020373, "grad_norm": 0.29212780929936155, "learning_rate": 9.133572974358669e-05, "loss": 0.20048227906227112, "step": 321 }, { "epoch": 1.0916808149405772, "grad_norm": 0.20191800340310445, "learning_rate": 9.125233207107909e-05, "loss": 0.17392735183238983, "step": 322 }, { "epoch": 1.0950764006791172, "grad_norm": 0.20170250850562177, "learning_rate": 9.116857340547202e-05, "loss": 0.17555058002471924, "step": 323 }, { "epoch": 1.098471986417657, "grad_norm": 0.22452119118315, "learning_rate": 9.108445447972531e-05, "loss": 0.16190403699874878, "step": 324 }, { "epoch": 1.101867572156197, "grad_norm": 0.18873731711629102, "learning_rate": 9.099997602995128e-05, "loss": 0.1456845998764038, "step": 325 }, { "epoch": 1.1052631578947367, "grad_norm": 0.2158691310092312, "learning_rate": 9.091513879540845e-05, "loss": 0.14603030681610107, "step": 326 }, { "epoch": 1.1086587436332767, "grad_norm": 0.20474251175130814, "learning_rate": 9.0829943518495e-05, "loss": 0.1453815996646881, "step": 327 }, { "epoch": 1.1120543293718166, "grad_norm": 0.22591726148334335, "learning_rate": 9.07443909447423e-05, "loss": 0.1473894566297531, "step": 328 }, { "epoch": 1.1154499151103565, "grad_norm": 0.23025167891489134, "learning_rate": 9.065848182280833e-05, "loss": 0.17691753804683685, "step": 329 }, { "epoch": 1.1188455008488964, "grad_norm": 0.2044551765510098, "learning_rate": 9.057221690447124e-05, "loss": 0.19459426403045654, "step": 330 }, { "epoch": 1.1222410865874364, "grad_norm": 0.19986749041735527, "learning_rate": 9.048559694462262e-05, "loss": 0.1716732680797577, "step": 331 }, { "epoch": 1.1256366723259763, "grad_norm": 0.18779291017490157, "learning_rate": 9.039862270126102e-05, "loss": 0.1696777641773224, "step": 332 }, { "epoch": 1.129032258064516, "grad_norm": 0.1949105193776305, "learning_rate": 9.03112949354853e-05, "loss": 0.15999673306941986, "step": 333 }, { "epoch": 1.132427843803056, "grad_norm": 0.19263949754185097, "learning_rate": 9.02236144114879e-05, "loss": 0.15610679984092712, "step": 334 }, { "epoch": 1.1358234295415959, "grad_norm": 0.18540644191536584, "learning_rate": 9.013558189654819e-05, "loss": 0.15449127554893494, "step": 335 }, { "epoch": 1.1392190152801358, "grad_norm": 0.18176478958433234, "learning_rate": 9.00471981610258e-05, "loss": 0.13070036470890045, "step": 336 }, { "epoch": 1.1426146010186757, "grad_norm": 0.20460102538496885, "learning_rate": 8.99584639783538e-05, "loss": 0.1655994951725006, "step": 337 }, { "epoch": 1.1460101867572157, "grad_norm": 0.1992852343692147, "learning_rate": 8.986938012503203e-05, "loss": 0.1953735053539276, "step": 338 }, { "epoch": 1.1494057724957556, "grad_norm": 0.20430617083523767, "learning_rate": 8.977994738062017e-05, "loss": 0.18439728021621704, "step": 339 }, { "epoch": 1.1528013582342953, "grad_norm": 0.19064661457016643, "learning_rate": 8.969016652773103e-05, "loss": 0.16322055459022522, "step": 340 }, { "epoch": 1.1561969439728352, "grad_norm": 0.20279077307228588, "learning_rate": 8.96000383520237e-05, "loss": 0.15768763422966003, "step": 341 }, { "epoch": 1.1595925297113752, "grad_norm": 0.17293847779750832, "learning_rate": 8.950956364219658e-05, "loss": 0.1556030958890915, "step": 342 }, { "epoch": 1.162988115449915, "grad_norm": 0.2063029318229405, "learning_rate": 8.941874318998058e-05, "loss": 0.15308734774589539, "step": 343 }, { "epoch": 1.166383701188455, "grad_norm": 0.19078637540772903, "learning_rate": 8.932757779013214e-05, "loss": 0.13935653865337372, "step": 344 }, { "epoch": 1.169779286926995, "grad_norm": 0.20752554454230282, "learning_rate": 8.923606824042627e-05, "loss": 0.1464628428220749, "step": 345 }, { "epoch": 1.1731748726655349, "grad_norm": 0.19896272159334225, "learning_rate": 8.914421534164962e-05, "loss": 0.18659351766109467, "step": 346 }, { "epoch": 1.1765704584040746, "grad_norm": 0.191335249907775, "learning_rate": 8.905201989759341e-05, "loss": 0.17295019328594208, "step": 347 }, { "epoch": 1.1799660441426145, "grad_norm": 0.19703684228483856, "learning_rate": 8.895948271504642e-05, "loss": 0.16895386576652527, "step": 348 }, { "epoch": 1.1833616298811545, "grad_norm": 0.1809760741886333, "learning_rate": 8.886660460378797e-05, "loss": 0.1675156205892563, "step": 349 }, { "epoch": 1.1867572156196944, "grad_norm": 0.19345200216236544, "learning_rate": 8.877338637658075e-05, "loss": 0.16741690039634705, "step": 350 }, { "epoch": 1.1901528013582343, "grad_norm": 0.18729474756540548, "learning_rate": 8.867982884916376e-05, "loss": 0.15447917580604553, "step": 351 }, { "epoch": 1.1935483870967742, "grad_norm": 0.2025239786377195, "learning_rate": 8.858593284024523e-05, "loss": 0.14785239100456238, "step": 352 }, { "epoch": 1.1969439728353142, "grad_norm": 0.1839963102106056, "learning_rate": 8.849169917149531e-05, "loss": 0.14344629645347595, "step": 353 }, { "epoch": 1.2003395585738539, "grad_norm": 0.2012851211217905, "learning_rate": 8.839712866753901e-05, "loss": 0.1786291003227234, "step": 354 }, { "epoch": 1.2037351443123938, "grad_norm": 0.18192843966403632, "learning_rate": 8.83022221559489e-05, "loss": 0.16876618564128876, "step": 355 }, { "epoch": 1.2071307300509337, "grad_norm": 0.19514414300605581, "learning_rate": 8.820698046723796e-05, "loss": 0.17299698293209076, "step": 356 }, { "epoch": 1.2105263157894737, "grad_norm": 0.17660782941845454, "learning_rate": 8.811140443485217e-05, "loss": 0.16695550084114075, "step": 357 }, { "epoch": 1.2139219015280136, "grad_norm": 0.1898559829306152, "learning_rate": 8.801549489516341e-05, "loss": 0.15887045860290527, "step": 358 }, { "epoch": 1.2173174872665535, "grad_norm": 0.17960503848633516, "learning_rate": 8.791925268746193e-05, "loss": 0.15074649453163147, "step": 359 }, { "epoch": 1.2207130730050935, "grad_norm": 0.18452744570000343, "learning_rate": 8.782267865394917e-05, "loss": 0.14895610511302948, "step": 360 }, { "epoch": 1.2241086587436332, "grad_norm": 0.21157593417879816, "learning_rate": 8.772577363973033e-05, "loss": 0.1332865208387375, "step": 361 }, { "epoch": 1.227504244482173, "grad_norm": 0.1884908336162296, "learning_rate": 8.762853849280693e-05, "loss": 0.16228394210338593, "step": 362 }, { "epoch": 1.230899830220713, "grad_norm": 0.1882730673792506, "learning_rate": 8.753097406406949e-05, "loss": 0.20317047834396362, "step": 363 }, { "epoch": 1.234295415959253, "grad_norm": 0.18492900215007393, "learning_rate": 8.743308120728997e-05, "loss": 0.1679389923810959, "step": 364 }, { "epoch": 1.237691001697793, "grad_norm": 0.17484923535330463, "learning_rate": 8.73348607791144e-05, "loss": 0.16052062809467316, "step": 365 }, { "epoch": 1.2410865874363328, "grad_norm": 0.19327809581804048, "learning_rate": 8.723631363905531e-05, "loss": 0.17321988940238953, "step": 366 }, { "epoch": 1.2444821731748728, "grad_norm": 0.18892779281397767, "learning_rate": 8.713744064948426e-05, "loss": 0.16489598155021667, "step": 367 }, { "epoch": 1.2478777589134125, "grad_norm": 0.1982506465222332, "learning_rate": 8.703824267562425e-05, "loss": 0.13714341819286346, "step": 368 }, { "epoch": 1.2512733446519524, "grad_norm": 0.20356297733418954, "learning_rate": 8.69387205855422e-05, "loss": 0.13603711128234863, "step": 369 }, { "epoch": 1.2546689303904923, "grad_norm": 0.2033231525193697, "learning_rate": 8.683887525014127e-05, "loss": 0.13591307401657104, "step": 370 }, { "epoch": 1.2580645161290323, "grad_norm": 0.16414036874164306, "learning_rate": 8.673870754315336e-05, "loss": 0.16990725696086884, "step": 371 }, { "epoch": 1.2614601018675722, "grad_norm": 0.20045368003519234, "learning_rate": 8.663821834113135e-05, "loss": 0.17480716109275818, "step": 372 }, { "epoch": 1.2648556876061121, "grad_norm": 0.17606489932153216, "learning_rate": 8.65374085234415e-05, "loss": 0.18333372473716736, "step": 373 }, { "epoch": 1.268251273344652, "grad_norm": 0.21033061847941922, "learning_rate": 8.643627897225571e-05, "loss": 0.1716233193874359, "step": 374 }, { "epoch": 1.2716468590831917, "grad_norm": 0.19052742247741852, "learning_rate": 8.633483057254381e-05, "loss": 0.17103354632854462, "step": 375 }, { "epoch": 1.2750424448217317, "grad_norm": 0.20974673130426658, "learning_rate": 8.623306421206587e-05, "loss": 0.14799927175045013, "step": 376 }, { "epoch": 1.2784380305602716, "grad_norm": 0.19170166178945716, "learning_rate": 8.613098078136437e-05, "loss": 0.1382761299610138, "step": 377 }, { "epoch": 1.2818336162988115, "grad_norm": 0.2261581073875909, "learning_rate": 8.60285811737564e-05, "loss": 0.13463819026947021, "step": 378 }, { "epoch": 1.2852292020373515, "grad_norm": 0.24930596197381394, "learning_rate": 8.592586628532588e-05, "loss": 0.18594394624233246, "step": 379 }, { "epoch": 1.2886247877758914, "grad_norm": 0.17990657580712696, "learning_rate": 8.582283701491576e-05, "loss": 0.18147127330303192, "step": 380 }, { "epoch": 1.2920203735144313, "grad_norm": 0.2297335710615592, "learning_rate": 8.571949426412001e-05, "loss": 0.1802498996257782, "step": 381 }, { "epoch": 1.295415959252971, "grad_norm": 0.2033965636212164, "learning_rate": 8.561583893727588e-05, "loss": 0.1777149885892868, "step": 382 }, { "epoch": 1.298811544991511, "grad_norm": 0.20719780969047427, "learning_rate": 8.551187194145592e-05, "loss": 0.16453149914741516, "step": 383 }, { "epoch": 1.302207130730051, "grad_norm": 0.19702896435929873, "learning_rate": 8.540759418646002e-05, "loss": 0.1615734100341797, "step": 384 }, { "epoch": 1.3056027164685908, "grad_norm": 0.21278634305792055, "learning_rate": 8.530300658480752e-05, "loss": 0.14433573186397552, "step": 385 }, { "epoch": 1.3089983022071308, "grad_norm": 0.21408372526278108, "learning_rate": 8.519811005172916e-05, "loss": 0.14615730941295624, "step": 386 }, { "epoch": 1.3123938879456707, "grad_norm": 0.20907036787403266, "learning_rate": 8.509290550515907e-05, "loss": 0.15451252460479736, "step": 387 }, { "epoch": 1.3157894736842106, "grad_norm": 0.19793349685487946, "learning_rate": 8.498739386572682e-05, "loss": 0.1867610067129135, "step": 388 }, { "epoch": 1.3191850594227503, "grad_norm": 0.18992417104331566, "learning_rate": 8.488157605674925e-05, "loss": 0.1667109727859497, "step": 389 }, { "epoch": 1.3225806451612903, "grad_norm": 0.17804702151948434, "learning_rate": 8.477545300422246e-05, "loss": 0.16456694900989532, "step": 390 }, { "epoch": 1.3259762308998302, "grad_norm": 0.20046314707526044, "learning_rate": 8.466902563681372e-05, "loss": 0.15338124334812164, "step": 391 }, { "epoch": 1.3293718166383701, "grad_norm": 0.34276261105180983, "learning_rate": 8.456229488585328e-05, "loss": 0.15841363370418549, "step": 392 }, { "epoch": 1.33276740237691, "grad_norm": 0.1920215970749504, "learning_rate": 8.445526168532627e-05, "loss": 0.1561691164970398, "step": 393 }, { "epoch": 1.33616298811545, "grad_norm": 0.2033315271992584, "learning_rate": 8.434792697186449e-05, "loss": 0.1360742449760437, "step": 394 }, { "epoch": 1.33955857385399, "grad_norm": 0.4624416182392774, "learning_rate": 8.424029168473829e-05, "loss": 0.14669910073280334, "step": 395 }, { "epoch": 1.3429541595925296, "grad_norm": 0.2146579172597149, "learning_rate": 8.413235676584823e-05, "loss": 0.18494638800621033, "step": 396 }, { "epoch": 1.3463497453310695, "grad_norm": 0.2587822813202277, "learning_rate": 8.402412315971693e-05, "loss": 0.18528585135936737, "step": 397 }, { "epoch": 1.3497453310696095, "grad_norm": 0.19399440532321974, "learning_rate": 8.391559181348082e-05, "loss": 0.16230188310146332, "step": 398 }, { "epoch": 1.3531409168081494, "grad_norm": 0.1954037033964251, "learning_rate": 8.380676367688172e-05, "loss": 0.1674966812133789, "step": 399 }, { "epoch": 1.3565365025466893, "grad_norm": 0.18953434474561193, "learning_rate": 8.36976397022587e-05, "loss": 0.15261387825012207, "step": 400 }, { "epoch": 1.3599320882852293, "grad_norm": 0.19384811240334962, "learning_rate": 8.358822084453965e-05, "loss": 0.14915475249290466, "step": 401 }, { "epoch": 1.3633276740237692, "grad_norm": 0.19122076757364848, "learning_rate": 8.347850806123288e-05, "loss": 0.14487414062023163, "step": 402 }, { "epoch": 1.366723259762309, "grad_norm": 0.27723132532670824, "learning_rate": 8.336850231241888e-05, "loss": 0.13761776685714722, "step": 403 }, { "epoch": 1.3701188455008488, "grad_norm": 0.22753344740894346, "learning_rate": 8.325820456074181e-05, "loss": 0.1681349277496338, "step": 404 }, { "epoch": 1.3735144312393888, "grad_norm": 0.20052637534999823, "learning_rate": 8.314761577140105e-05, "loss": 0.1848275363445282, "step": 405 }, { "epoch": 1.3769100169779287, "grad_norm": 0.20593746180528957, "learning_rate": 8.303673691214289e-05, "loss": 0.17066769301891327, "step": 406 }, { "epoch": 1.3803056027164686, "grad_norm": 0.17720150000136614, "learning_rate": 8.292556895325194e-05, "loss": 0.15952184796333313, "step": 407 }, { "epoch": 1.3837011884550086, "grad_norm": 0.1926269693557234, "learning_rate": 8.281411286754266e-05, "loss": 0.15444013476371765, "step": 408 }, { "epoch": 1.3870967741935485, "grad_norm": 0.19944289270593688, "learning_rate": 8.270236963035091e-05, "loss": 0.14692428708076477, "step": 409 }, { "epoch": 1.3904923599320882, "grad_norm": 0.1885279573691433, "learning_rate": 8.259034021952537e-05, "loss": 0.14548589289188385, "step": 410 }, { "epoch": 1.3938879456706281, "grad_norm": 0.1822130456259423, "learning_rate": 8.24780256154189e-05, "loss": 0.1397281289100647, "step": 411 }, { "epoch": 1.397283531409168, "grad_norm": 0.18801876837981288, "learning_rate": 8.236542680088015e-05, "loss": 0.164806067943573, "step": 412 }, { "epoch": 1.400679117147708, "grad_norm": 0.19388015253385277, "learning_rate": 8.225254476124478e-05, "loss": 0.18502959609031677, "step": 413 }, { "epoch": 1.404074702886248, "grad_norm": 0.1815658849019605, "learning_rate": 8.213938048432697e-05, "loss": 0.17280147969722748, "step": 414 }, { "epoch": 1.4074702886247878, "grad_norm": 0.21037405084422955, "learning_rate": 8.202593496041066e-05, "loss": 0.164241224527359, "step": 415 }, { "epoch": 1.4108658743633278, "grad_norm": 0.20576306835089408, "learning_rate": 8.191220918224101e-05, "loss": 0.16376134753227234, "step": 416 }, { "epoch": 1.4142614601018675, "grad_norm": 0.1910518751219804, "learning_rate": 8.179820414501555e-05, "loss": 0.17270877957344055, "step": 417 }, { "epoch": 1.4176570458404074, "grad_norm": 0.199511985090208, "learning_rate": 8.168392084637566e-05, "loss": 0.15782058238983154, "step": 418 }, { "epoch": 1.4210526315789473, "grad_norm": 0.23616650894639055, "learning_rate": 8.156936028639767e-05, "loss": 0.14752981066703796, "step": 419 }, { "epoch": 1.4244482173174873, "grad_norm": 0.20651335467555787, "learning_rate": 8.145452346758426e-05, "loss": 0.1332433819770813, "step": 420 }, { "epoch": 1.4278438030560272, "grad_norm": 0.18416426523921145, "learning_rate": 8.133941139485551e-05, "loss": 0.18285462260246277, "step": 421 }, { "epoch": 1.4312393887945671, "grad_norm": 0.17157152472729922, "learning_rate": 8.12240250755403e-05, "loss": 0.16667722165584564, "step": 422 }, { "epoch": 1.434634974533107, "grad_norm": 0.20475160805074769, "learning_rate": 8.110836551936736e-05, "loss": 0.1660834550857544, "step": 423 }, { "epoch": 1.4380305602716468, "grad_norm": 0.1885050554293432, "learning_rate": 8.099243373845646e-05, "loss": 0.16956230998039246, "step": 424 }, { "epoch": 1.4414261460101867, "grad_norm": 0.198045246606077, "learning_rate": 8.08762307473096e-05, "loss": 0.15231752395629883, "step": 425 }, { "epoch": 1.4448217317487266, "grad_norm": 0.1927679119304936, "learning_rate": 8.07597575628021e-05, "loss": 0.14480434358119965, "step": 426 }, { "epoch": 1.4482173174872666, "grad_norm": 0.20165140468314588, "learning_rate": 8.064301520417367e-05, "loss": 0.14340506494045258, "step": 427 }, { "epoch": 1.4516129032258065, "grad_norm": 0.21191042843824154, "learning_rate": 8.052600469301958e-05, "loss": 0.1494779735803604, "step": 428 }, { "epoch": 1.4550084889643464, "grad_norm": 0.1815480014064838, "learning_rate": 8.04087270532816e-05, "loss": 0.1498197764158249, "step": 429 }, { "epoch": 1.4584040747028864, "grad_norm": 0.19099685031960859, "learning_rate": 8.029118331123912e-05, "loss": 0.20055601000785828, "step": 430 }, { "epoch": 1.461799660441426, "grad_norm": 0.18535092740803596, "learning_rate": 8.01733744955002e-05, "loss": 0.16613398492336273, "step": 431 }, { "epoch": 1.465195246179966, "grad_norm": 0.17838289803655005, "learning_rate": 8.005530163699246e-05, "loss": 0.1740640103816986, "step": 432 }, { "epoch": 1.468590831918506, "grad_norm": 0.18541460428519524, "learning_rate": 7.993696576895415e-05, "loss": 0.1666644662618637, "step": 433 }, { "epoch": 1.4719864176570459, "grad_norm": 0.1787660893964586, "learning_rate": 7.981836792692508e-05, "loss": 0.14891597628593445, "step": 434 }, { "epoch": 1.4753820033955858, "grad_norm": 0.18112525162894888, "learning_rate": 7.969950914873753e-05, "loss": 0.1337478756904602, "step": 435 }, { "epoch": 1.4787775891341257, "grad_norm": 0.18334382675980654, "learning_rate": 7.958039047450723e-05, "loss": 0.13875997066497803, "step": 436 }, { "epoch": 1.4821731748726656, "grad_norm": 0.2805766927693815, "learning_rate": 7.946101294662418e-05, "loss": 0.17074432969093323, "step": 437 }, { "epoch": 1.4855687606112054, "grad_norm": 0.18444715811046747, "learning_rate": 7.934137760974363e-05, "loss": 0.1938565969467163, "step": 438 }, { "epoch": 1.4889643463497453, "grad_norm": 0.1680469060772462, "learning_rate": 7.922148551077681e-05, "loss": 0.1765138804912567, "step": 439 }, { "epoch": 1.4923599320882852, "grad_norm": 0.18548511354464917, "learning_rate": 7.910133769888188e-05, "loss": 0.17844665050506592, "step": 440 }, { "epoch": 1.4957555178268251, "grad_norm": 0.18222069361931734, "learning_rate": 7.898093522545472e-05, "loss": 0.164535790681839, "step": 441 }, { "epoch": 1.499151103565365, "grad_norm": 0.17419796888893707, "learning_rate": 7.886027914411964e-05, "loss": 0.15411187708377838, "step": 442 }, { "epoch": 1.5025466893039048, "grad_norm": 0.1895453679916474, "learning_rate": 7.873937051072035e-05, "loss": 0.16676245629787445, "step": 443 }, { "epoch": 1.505942275042445, "grad_norm": 0.17765554622112073, "learning_rate": 7.86182103833105e-05, "loss": 0.12973670661449432, "step": 444 }, { "epoch": 1.5093378607809846, "grad_norm": 0.2181301823092417, "learning_rate": 7.849679982214458e-05, "loss": 0.14135943353176117, "step": 445 }, { "epoch": 1.5127334465195246, "grad_norm": 0.19590431506040082, "learning_rate": 7.83751398896686e-05, "loss": 0.18276870250701904, "step": 446 }, { "epoch": 1.5161290322580645, "grad_norm": 0.17693029197439575, "learning_rate": 7.825323165051073e-05, "loss": 0.17886696755886078, "step": 447 }, { "epoch": 1.5195246179966044, "grad_norm": 0.18251011390178956, "learning_rate": 7.813107617147209e-05, "loss": 0.1715458333492279, "step": 448 }, { "epoch": 1.5229202037351444, "grad_norm": 0.18258583052865335, "learning_rate": 7.80086745215173e-05, "loss": 0.16793230175971985, "step": 449 }, { "epoch": 1.526315789473684, "grad_norm": 0.1760590266381234, "learning_rate": 7.788602777176528e-05, "loss": 0.15847665071487427, "step": 450 }, { "epoch": 1.5297113752122242, "grad_norm": 0.20607399159580456, "learning_rate": 7.77631369954797e-05, "loss": 0.15323980152606964, "step": 451 }, { "epoch": 1.533106960950764, "grad_norm": 0.21222145215549423, "learning_rate": 7.764000326805967e-05, "loss": 0.15271389484405518, "step": 452 }, { "epoch": 1.5365025466893039, "grad_norm": 0.1771587751860222, "learning_rate": 7.751662766703038e-05, "loss": 0.13208144903182983, "step": 453 }, { "epoch": 1.5398981324278438, "grad_norm": 0.18962924747187754, "learning_rate": 7.73930112720336e-05, "loss": 0.17377114295959473, "step": 454 }, { "epoch": 1.5432937181663837, "grad_norm": 0.19370916147297393, "learning_rate": 7.726915516481824e-05, "loss": 0.19509372115135193, "step": 455 }, { "epoch": 1.5466893039049237, "grad_norm": 0.17806107422099998, "learning_rate": 7.714506042923091e-05, "loss": 0.17389468848705292, "step": 456 }, { "epoch": 1.5500848896434634, "grad_norm": 0.18174989294212107, "learning_rate": 7.702072815120638e-05, "loss": 0.16574130952358246, "step": 457 }, { "epoch": 1.5534804753820035, "grad_norm": 0.18805794288592984, "learning_rate": 7.68961594187582e-05, "loss": 0.14233970642089844, "step": 458 }, { "epoch": 1.5568760611205432, "grad_norm": 0.1838908977956497, "learning_rate": 7.677135532196905e-05, "loss": 0.15779675543308258, "step": 459 }, { "epoch": 1.5602716468590832, "grad_norm": 0.17493459686021195, "learning_rate": 7.66463169529812e-05, "loss": 0.14088116586208344, "step": 460 }, { "epoch": 1.563667232597623, "grad_norm": 0.19452565737085545, "learning_rate": 7.652104540598712e-05, "loss": 0.1416524052619934, "step": 461 }, { "epoch": 1.567062818336163, "grad_norm": 0.17609783143397675, "learning_rate": 7.63955417772197e-05, "loss": 0.16610148549079895, "step": 462 }, { "epoch": 1.570458404074703, "grad_norm": 0.20417473158442093, "learning_rate": 7.626980716494274e-05, "loss": 0.18159864842891693, "step": 463 }, { "epoch": 1.5738539898132426, "grad_norm": 0.17178967942387124, "learning_rate": 7.614384266944139e-05, "loss": 0.18010705709457397, "step": 464 }, { "epoch": 1.5772495755517828, "grad_norm": 0.19685673528804337, "learning_rate": 7.601764939301241e-05, "loss": 0.1828932762145996, "step": 465 }, { "epoch": 1.5806451612903225, "grad_norm": 0.1926284029427127, "learning_rate": 7.589122843995469e-05, "loss": 0.15791763365268707, "step": 466 }, { "epoch": 1.5840407470288624, "grad_norm": 0.18795701286041544, "learning_rate": 7.57645809165594e-05, "loss": 0.15532039105892181, "step": 467 }, { "epoch": 1.5874363327674024, "grad_norm": 0.19432395776884948, "learning_rate": 7.563770793110039e-05, "loss": 0.14827030897140503, "step": 468 }, { "epoch": 1.5908319185059423, "grad_norm": 0.1864425491035546, "learning_rate": 7.551061059382455e-05, "loss": 0.14112061262130737, "step": 469 }, { "epoch": 1.5942275042444822, "grad_norm": 0.19139355085903184, "learning_rate": 7.5383290016942e-05, "loss": 0.1409231722354889, "step": 470 }, { "epoch": 1.597623089983022, "grad_norm": 0.18683650156156306, "learning_rate": 7.525574731461642e-05, "loss": 0.18162474036216736, "step": 471 }, { "epoch": 1.601018675721562, "grad_norm": 0.1827589507517917, "learning_rate": 7.512798360295526e-05, "loss": 0.1765042543411255, "step": 472 }, { "epoch": 1.6044142614601018, "grad_norm": 0.1765646179256097, "learning_rate": 7.500000000000001e-05, "loss": 0.16432282328605652, "step": 473 }, { "epoch": 1.6078098471986417, "grad_norm": 0.19231823374854237, "learning_rate": 7.487179762571637e-05, "loss": 0.16433201730251312, "step": 474 }, { "epoch": 1.6112054329371817, "grad_norm": 0.1748324482032478, "learning_rate": 7.474337760198447e-05, "loss": 0.15398603677749634, "step": 475 }, { "epoch": 1.6146010186757216, "grad_norm": 0.17594317036592277, "learning_rate": 7.461474105258911e-05, "loss": 0.14779743552207947, "step": 476 }, { "epoch": 1.6179966044142615, "grad_norm": 0.1883851989573403, "learning_rate": 7.448588910320983e-05, "loss": 0.1409299075603485, "step": 477 }, { "epoch": 1.6213921901528012, "grad_norm": 0.20348892729725218, "learning_rate": 7.435682288141111e-05, "loss": 0.13723161816596985, "step": 478 }, { "epoch": 1.6247877758913414, "grad_norm": 0.17046536317869096, "learning_rate": 7.422754351663252e-05, "loss": 0.16870960593223572, "step": 479 }, { "epoch": 1.628183361629881, "grad_norm": 0.17757703654770882, "learning_rate": 7.409805214017877e-05, "loss": 0.173429936170578, "step": 480 }, { "epoch": 1.631578947368421, "grad_norm": 0.19665049689102712, "learning_rate": 7.396834988520988e-05, "loss": 0.17763277888298035, "step": 481 }, { "epoch": 1.634974533106961, "grad_norm": 0.18262351289817452, "learning_rate": 7.383843788673126e-05, "loss": 0.1751786768436432, "step": 482 }, { "epoch": 1.6383701188455009, "grad_norm": 0.1868977018442509, "learning_rate": 7.37083172815837e-05, "loss": 0.1577882170677185, "step": 483 }, { "epoch": 1.6417657045840408, "grad_norm": 0.174429377611626, "learning_rate": 7.357798920843354e-05, "loss": 0.1525232493877411, "step": 484 }, { "epoch": 1.6451612903225805, "grad_norm": 0.24757160066493733, "learning_rate": 7.344745480776257e-05, "loss": 0.13874512910842896, "step": 485 }, { "epoch": 1.6485568760611207, "grad_norm": 0.17642711380497708, "learning_rate": 7.331671522185817e-05, "loss": 0.12604987621307373, "step": 486 }, { "epoch": 1.6519524617996604, "grad_norm": 0.1894340463493715, "learning_rate": 7.318577159480327e-05, "loss": 0.15690191090106964, "step": 487 }, { "epoch": 1.6553480475382003, "grad_norm": 0.1919670561728794, "learning_rate": 7.30546250724663e-05, "loss": 0.17964285612106323, "step": 488 }, { "epoch": 1.6587436332767402, "grad_norm": 0.1956783704393679, "learning_rate": 7.292327680249123e-05, "loss": 0.1727060079574585, "step": 489 }, { "epoch": 1.6621392190152802, "grad_norm": 0.18563940359787887, "learning_rate": 7.279172793428747e-05, "loss": 0.16723820567131042, "step": 490 }, { "epoch": 1.66553480475382, "grad_norm": 0.18455840639152749, "learning_rate": 7.265997961901987e-05, "loss": 0.1723594069480896, "step": 491 }, { "epoch": 1.6689303904923598, "grad_norm": 0.1912171167211459, "learning_rate": 7.252803300959855e-05, "loss": 0.15880949795246124, "step": 492 }, { "epoch": 1.6723259762309, "grad_norm": 0.17859536040584828, "learning_rate": 7.239588926066894e-05, "loss": 0.1469959318637848, "step": 493 }, { "epoch": 1.6757215619694397, "grad_norm": 0.18385956445143017, "learning_rate": 7.226354952860157e-05, "loss": 0.13693295419216156, "step": 494 }, { "epoch": 1.6791171477079796, "grad_norm": 0.19572296127554295, "learning_rate": 7.2131014971482e-05, "loss": 0.14472414553165436, "step": 495 }, { "epoch": 1.6825127334465195, "grad_norm": 0.1657566928548163, "learning_rate": 7.199828674910067e-05, "loss": 0.1794150471687317, "step": 496 }, { "epoch": 1.6859083191850595, "grad_norm": 0.18296098683526374, "learning_rate": 7.186536602294278e-05, "loss": 0.17176096141338348, "step": 497 }, { "epoch": 1.6893039049235994, "grad_norm": 0.16985787159417765, "learning_rate": 7.173225395617805e-05, "loss": 0.17153851687908173, "step": 498 }, { "epoch": 1.692699490662139, "grad_norm": 0.18148868602238358, "learning_rate": 7.159895171365065e-05, "loss": 0.16729089617729187, "step": 499 }, { "epoch": 1.6960950764006792, "grad_norm": 0.18654321841753257, "learning_rate": 7.146546046186893e-05, "loss": 0.16425371170043945, "step": 500 }, { "epoch": 1.699490662139219, "grad_norm": 0.17827119328781035, "learning_rate": 7.133178136899522e-05, "loss": 0.15057818591594696, "step": 501 }, { "epoch": 1.7028862478777589, "grad_norm": 0.18169638140377276, "learning_rate": 7.119791560483562e-05, "loss": 0.13917642831802368, "step": 502 }, { "epoch": 1.7062818336162988, "grad_norm": 0.1833482749441268, "learning_rate": 7.106386434082979e-05, "loss": 0.1311974823474884, "step": 503 }, { "epoch": 1.7096774193548387, "grad_norm": 0.18543610656731152, "learning_rate": 7.092962875004065e-05, "loss": 0.16842401027679443, "step": 504 }, { "epoch": 1.7130730050933787, "grad_norm": 0.17232136569921291, "learning_rate": 7.079521000714414e-05, "loss": 0.17561206221580505, "step": 505 }, { "epoch": 1.7164685908319184, "grad_norm": 0.18695004925792763, "learning_rate": 7.066060928841892e-05, "loss": 0.15638267993927002, "step": 506 }, { "epoch": 1.7198641765704585, "grad_norm": 0.20777241762984353, "learning_rate": 7.052582777173613e-05, "loss": 0.17052212357521057, "step": 507 }, { "epoch": 1.7232597623089982, "grad_norm": 0.1879758875095606, "learning_rate": 7.039086663654903e-05, "loss": 0.15996943414211273, "step": 508 }, { "epoch": 1.7266553480475382, "grad_norm": 0.17941686106673527, "learning_rate": 7.025572706388268e-05, "loss": 0.1609647125005722, "step": 509 }, { "epoch": 1.730050933786078, "grad_norm": 0.18451004879957808, "learning_rate": 7.012041023632364e-05, "loss": 0.14662379026412964, "step": 510 }, { "epoch": 1.733446519524618, "grad_norm": 0.19699282722138145, "learning_rate": 6.99849173380096e-05, "loss": 0.13662013411521912, "step": 511 }, { "epoch": 1.736842105263158, "grad_norm": 0.17905368130444776, "learning_rate": 6.984924955461901e-05, "loss": 0.1432567685842514, "step": 512 }, { "epoch": 1.7402376910016977, "grad_norm": 0.17351308309706964, "learning_rate": 6.971340807336072e-05, "loss": 0.18336886167526245, "step": 513 }, { "epoch": 1.7436332767402378, "grad_norm": 0.18148169867993, "learning_rate": 6.957739408296357e-05, "loss": 0.18250811100006104, "step": 514 }, { "epoch": 1.7470288624787775, "grad_norm": 0.18036906910812636, "learning_rate": 6.944120877366604e-05, "loss": 0.16854140162467957, "step": 515 }, { "epoch": 1.7504244482173175, "grad_norm": 0.17610610733686125, "learning_rate": 6.930485333720573e-05, "loss": 0.14952275156974792, "step": 516 }, { "epoch": 1.7538200339558574, "grad_norm": 0.20771238433810985, "learning_rate": 6.916832896680909e-05, "loss": 0.1549406796693802, "step": 517 }, { "epoch": 1.7572156196943973, "grad_norm": 0.16751245365571632, "learning_rate": 6.90316368571808e-05, "loss": 0.1423039734363556, "step": 518 }, { "epoch": 1.7606112054329373, "grad_norm": 0.18087990775399046, "learning_rate": 6.889477820449342e-05, "loss": 0.14016366004943848, "step": 519 }, { "epoch": 1.764006791171477, "grad_norm": 0.1838162385444869, "learning_rate": 6.875775420637696e-05, "loss": 0.14294710755348206, "step": 520 }, { "epoch": 1.7674023769100171, "grad_norm": 0.16760604357011016, "learning_rate": 6.86205660619083e-05, "loss": 0.17810671031475067, "step": 521 }, { "epoch": 1.7707979626485568, "grad_norm": 0.17084078524922822, "learning_rate": 6.848321497160073e-05, "loss": 0.18097054958343506, "step": 522 }, { "epoch": 1.7741935483870968, "grad_norm": 0.1730247683788355, "learning_rate": 6.834570213739346e-05, "loss": 0.16516205668449402, "step": 523 }, { "epoch": 1.7775891341256367, "grad_norm": 0.17999870814714078, "learning_rate": 6.820802876264112e-05, "loss": 0.16350559890270233, "step": 524 }, { "epoch": 1.7809847198641766, "grad_norm": 0.1747303659237364, "learning_rate": 6.807019605210319e-05, "loss": 0.16167867183685303, "step": 525 }, { "epoch": 1.7843803056027165, "grad_norm": 0.18396730355056362, "learning_rate": 6.793220521193346e-05, "loss": 0.15808960795402527, "step": 526 }, { "epoch": 1.7877758913412563, "grad_norm": 0.1908440442227778, "learning_rate": 6.779405744966954e-05, "loss": 0.1370973438024521, "step": 527 }, { "epoch": 1.7911714770797964, "grad_norm": 0.18245812313202964, "learning_rate": 6.76557539742222e-05, "loss": 0.13153865933418274, "step": 528 }, { "epoch": 1.7945670628183361, "grad_norm": 0.15553007213648265, "learning_rate": 6.751729599586483e-05, "loss": 0.1596919447183609, "step": 529 }, { "epoch": 1.797962648556876, "grad_norm": 0.17222320703509325, "learning_rate": 6.737868472622287e-05, "loss": 0.1752602905035019, "step": 530 }, { "epoch": 1.801358234295416, "grad_norm": 0.15729557792159204, "learning_rate": 6.723992137826318e-05, "loss": 0.1719258427619934, "step": 531 }, { "epoch": 1.804753820033956, "grad_norm": 0.16691025576556376, "learning_rate": 6.710100716628344e-05, "loss": 0.16097165644168854, "step": 532 }, { "epoch": 1.8081494057724958, "grad_norm": 0.16854455732420842, "learning_rate": 6.696194330590151e-05, "loss": 0.1574283391237259, "step": 533 }, { "epoch": 1.8115449915110355, "grad_norm": 0.1675094850991689, "learning_rate": 6.682273101404482e-05, "loss": 0.14706020057201385, "step": 534 }, { "epoch": 1.8149405772495757, "grad_norm": 0.17746803149572632, "learning_rate": 6.668337150893971e-05, "loss": 0.15042737126350403, "step": 535 }, { "epoch": 1.8183361629881154, "grad_norm": 0.1710843144602704, "learning_rate": 6.65438660101007e-05, "loss": 0.13203056156635284, "step": 536 }, { "epoch": 1.8217317487266553, "grad_norm": 0.25095542909557406, "learning_rate": 6.640421573831995e-05, "loss": 0.1480444371700287, "step": 537 }, { "epoch": 1.8251273344651953, "grad_norm": 0.16106614334330768, "learning_rate": 6.626442191565645e-05, "loss": 0.17822377383708954, "step": 538 }, { "epoch": 1.8285229202037352, "grad_norm": 0.1610910381910114, "learning_rate": 6.612448576542545e-05, "loss": 0.18047180771827698, "step": 539 }, { "epoch": 1.8319185059422751, "grad_norm": 0.16399463639566766, "learning_rate": 6.598440851218763e-05, "loss": 0.16620728373527527, "step": 540 }, { "epoch": 1.8353140916808148, "grad_norm": 0.1663434232145509, "learning_rate": 6.584419138173845e-05, "loss": 0.1614074409008026, "step": 541 }, { "epoch": 1.838709677419355, "grad_norm": 0.1718688944122613, "learning_rate": 6.570383560109745e-05, "loss": 0.16087627410888672, "step": 542 }, { "epoch": 1.8421052631578947, "grad_norm": 0.1667463971198413, "learning_rate": 6.556334239849744e-05, "loss": 0.14770135283470154, "step": 543 }, { "epoch": 1.8455008488964346, "grad_norm": 0.17207788474574298, "learning_rate": 6.542271300337377e-05, "loss": 0.14125823974609375, "step": 544 }, { "epoch": 1.8488964346349746, "grad_norm": 0.17946394240452213, "learning_rate": 6.528194864635369e-05, "loss": 0.14081749320030212, "step": 545 }, { "epoch": 1.8522920203735145, "grad_norm": 0.18414131308643106, "learning_rate": 6.514105055924538e-05, "loss": 0.17963922023773193, "step": 546 }, { "epoch": 1.8556876061120544, "grad_norm": 0.14294714400381414, "learning_rate": 6.500001997502731e-05, "loss": 0.1649813950061798, "step": 547 }, { "epoch": 1.8590831918505941, "grad_norm": 0.16041654271254796, "learning_rate": 6.485885812783739e-05, "loss": 0.16963443160057068, "step": 548 }, { "epoch": 1.8624787775891343, "grad_norm": 0.17133298100923808, "learning_rate": 6.471756625296224e-05, "loss": 0.15729641914367676, "step": 549 }, { "epoch": 1.865874363327674, "grad_norm": 0.16118956983206778, "learning_rate": 6.45761455868263e-05, "loss": 0.14063751697540283, "step": 550 }, { "epoch": 1.869269949066214, "grad_norm": 0.15823112881345047, "learning_rate": 6.443459736698105e-05, "loss": 0.1441025733947754, "step": 551 }, { "epoch": 1.8726655348047538, "grad_norm": 0.17113358987244853, "learning_rate": 6.429292283209419e-05, "loss": 0.1459069699048996, "step": 552 }, { "epoch": 1.8760611205432938, "grad_norm": 0.17887450754428866, "learning_rate": 6.41511232219387e-05, "loss": 0.13121017813682556, "step": 553 }, { "epoch": 1.8794567062818337, "grad_norm": 0.16945899573336043, "learning_rate": 6.400919977738222e-05, "loss": 0.17336687445640564, "step": 554 }, { "epoch": 1.8828522920203734, "grad_norm": 0.17602884735785318, "learning_rate": 6.386715374037596e-05, "loss": 0.18841490149497986, "step": 555 }, { "epoch": 1.8862478777589136, "grad_norm": 0.1625966113100334, "learning_rate": 6.372498635394388e-05, "loss": 0.16863588988780975, "step": 556 }, { "epoch": 1.8896434634974533, "grad_norm": 0.17772394195437274, "learning_rate": 6.358269886217194e-05, "loss": 0.16711756587028503, "step": 557 }, { "epoch": 1.8930390492359932, "grad_norm": 0.16439059992506974, "learning_rate": 6.344029251019707e-05, "loss": 0.14478228986263275, "step": 558 }, { "epoch": 1.8964346349745331, "grad_norm": 0.16907471451987538, "learning_rate": 6.329776854419636e-05, "loss": 0.14453932642936707, "step": 559 }, { "epoch": 1.899830220713073, "grad_norm": 0.16651601303723276, "learning_rate": 6.315512821137606e-05, "loss": 0.14067892730236053, "step": 560 }, { "epoch": 1.903225806451613, "grad_norm": 0.16457933463747362, "learning_rate": 6.301237275996082e-05, "loss": 0.13354872167110443, "step": 561 }, { "epoch": 1.9066213921901527, "grad_norm": 0.1717783175473143, "learning_rate": 6.286950343918262e-05, "loss": 0.1650480479001999, "step": 562 }, { "epoch": 1.9100169779286928, "grad_norm": 0.17058362911491767, "learning_rate": 6.272652149926988e-05, "loss": 0.1925385445356369, "step": 563 }, { "epoch": 1.9134125636672326, "grad_norm": 0.1617299489951924, "learning_rate": 6.258342819143659e-05, "loss": 0.17114019393920898, "step": 564 }, { "epoch": 1.9168081494057725, "grad_norm": 0.16528746885276557, "learning_rate": 6.244022476787124e-05, "loss": 0.15518032014369965, "step": 565 }, { "epoch": 1.9202037351443124, "grad_norm": 0.16049404486239083, "learning_rate": 6.229691248172599e-05, "loss": 0.14632579684257507, "step": 566 }, { "epoch": 1.9235993208828521, "grad_norm": 0.16982478433267317, "learning_rate": 6.215349258710557e-05, "loss": 0.14713209867477417, "step": 567 }, { "epoch": 1.9269949066213923, "grad_norm": 0.16277335386367456, "learning_rate": 6.200996633905646e-05, "loss": 0.13397686183452606, "step": 568 }, { "epoch": 1.930390492359932, "grad_norm": 0.1813684126188406, "learning_rate": 6.186633499355576e-05, "loss": 0.1379556655883789, "step": 569 }, { "epoch": 1.9337860780984721, "grad_norm": 0.18737110524897457, "learning_rate": 6.172259980750023e-05, "loss": 0.1290856897830963, "step": 570 }, { "epoch": 1.9371816638370118, "grad_norm": 0.17545045115455518, "learning_rate": 6.157876203869546e-05, "loss": 0.1697261929512024, "step": 571 }, { "epoch": 1.9405772495755518, "grad_norm": 0.17420613006370353, "learning_rate": 6.143482294584459e-05, "loss": 0.173529252409935, "step": 572 }, { "epoch": 1.9439728353140917, "grad_norm": 0.16189742546033578, "learning_rate": 6.129078378853748e-05, "loss": 0.15620549023151398, "step": 573 }, { "epoch": 1.9473684210526314, "grad_norm": 0.18274767780499362, "learning_rate": 6.114664582723966e-05, "loss": 0.15449392795562744, "step": 574 }, { "epoch": 1.9507640067911716, "grad_norm": 0.17968465642204184, "learning_rate": 6.100241032328124e-05, "loss": 0.14221139252185822, "step": 575 }, { "epoch": 1.9541595925297113, "grad_norm": 0.18348111509278955, "learning_rate": 6.085807853884595e-05, "loss": 0.14858148992061615, "step": 576 }, { "epoch": 1.9575551782682514, "grad_norm": 0.18423695648825972, "learning_rate": 6.0713651736960034e-05, "loss": 0.13991549611091614, "step": 577 }, { "epoch": 1.9609507640067911, "grad_norm": 0.19348292156174063, "learning_rate": 6.056913118148122e-05, "loss": 0.13638564944267273, "step": 578 }, { "epoch": 1.964346349745331, "grad_norm": 0.1595069297891854, "learning_rate": 6.0424518137087674e-05, "loss": 0.16120140254497528, "step": 579 }, { "epoch": 1.967741935483871, "grad_norm": 0.1747748246936634, "learning_rate": 6.0279813869266885e-05, "loss": 0.1653626561164856, "step": 580 }, { "epoch": 1.9711375212224107, "grad_norm": 0.16726561813373925, "learning_rate": 6.013501964430468e-05, "loss": 0.15936613082885742, "step": 581 }, { "epoch": 1.9745331069609509, "grad_norm": 0.18519342809269737, "learning_rate": 5.999013672927405e-05, "loss": 0.16321642696857452, "step": 582 }, { "epoch": 1.9779286926994906, "grad_norm": 0.17726059180761713, "learning_rate": 5.9845166392024074e-05, "loss": 0.1529730260372162, "step": 583 }, { "epoch": 1.9813242784380307, "grad_norm": 0.17575880124078921, "learning_rate": 5.970010990116892e-05, "loss": 0.14697983860969543, "step": 584 }, { "epoch": 1.9847198641765704, "grad_norm": 0.17712999362024573, "learning_rate": 5.955496852607661e-05, "loss": 0.13811354339122772, "step": 585 }, { "epoch": 1.9881154499151104, "grad_norm": 0.17161091040045579, "learning_rate": 5.940974353685804e-05, "loss": 0.124301478266716, "step": 586 }, { "epoch": 1.9915110356536503, "grad_norm": 0.17721217375237114, "learning_rate": 5.9264436204355724e-05, "loss": 0.1549723744392395, "step": 587 }, { "epoch": 1.99490662139219, "grad_norm": 0.20432739133195404, "learning_rate": 5.911904780013279e-05, "loss": 0.18239590525627136, "step": 588 }, { "epoch": 1.9983022071307301, "grad_norm": 0.1908595742145265, "learning_rate": 5.8973579596461834e-05, "loss": 0.14180368185043335, "step": 589 }, { "epoch": 2.0, "grad_norm": 0.24009256919933536, "learning_rate": 5.882803286631372e-05, "loss": 0.13346514105796814, "step": 590 }, { "epoch": 2.0033955857385397, "grad_norm": 0.27930924094415494, "learning_rate": 5.868240888334653e-05, "loss": 0.12378250062465668, "step": 591 }, { "epoch": 2.00679117147708, "grad_norm": 0.2431470709056894, "learning_rate": 5.853670892189432e-05, "loss": 0.11407718062400818, "step": 592 }, { "epoch": 2.0101867572156196, "grad_norm": 0.19139004103023372, "learning_rate": 5.839093425695609e-05, "loss": 0.10127812623977661, "step": 593 }, { "epoch": 2.0135823429541597, "grad_norm": 0.3543558615632127, "learning_rate": 5.824508616418449e-05, "loss": 0.09497358649969101, "step": 594 }, { "epoch": 2.0169779286926994, "grad_norm": 0.18584851631888175, "learning_rate": 5.8099165919874784e-05, "loss": 0.08638568967580795, "step": 595 }, { "epoch": 2.0203735144312396, "grad_norm": 0.23296396312857756, "learning_rate": 5.7953174800953604e-05, "loss": 0.0777568519115448, "step": 596 }, { "epoch": 2.0237691001697793, "grad_norm": 0.21293501060125108, "learning_rate": 5.7807114084967775e-05, "loss": 0.0734458938241005, "step": 597 }, { "epoch": 2.027164685908319, "grad_norm": 0.19399823139300765, "learning_rate": 5.766098505007318e-05, "loss": 0.06987430155277252, "step": 598 }, { "epoch": 2.030560271646859, "grad_norm": 0.2174080213987067, "learning_rate": 5.751478897502352e-05, "loss": 0.1168893501162529, "step": 599 }, { "epoch": 2.033955857385399, "grad_norm": 0.2083555533855022, "learning_rate": 5.736852713915921e-05, "loss": 0.10817261785268784, "step": 600 }, { "epoch": 2.037351443123939, "grad_norm": 0.18988272943992718, "learning_rate": 5.7222200822396075e-05, "loss": 0.10592930018901825, "step": 601 }, { "epoch": 2.0407470288624787, "grad_norm": 0.1809405492467449, "learning_rate": 5.7075811305214245e-05, "loss": 0.10201668739318848, "step": 602 }, { "epoch": 2.044142614601019, "grad_norm": 0.17657128795757143, "learning_rate": 5.692935986864685e-05, "loss": 0.08910071849822998, "step": 603 }, { "epoch": 2.0475382003395586, "grad_norm": 0.18465104051439643, "learning_rate": 5.678284779426891e-05, "loss": 0.07963181287050247, "step": 604 }, { "epoch": 2.0509337860780983, "grad_norm": 0.17823215682991914, "learning_rate": 5.6636276364186105e-05, "loss": 0.07471688836812973, "step": 605 }, { "epoch": 2.0543293718166384, "grad_norm": 0.17445856214169989, "learning_rate": 5.648964686102346e-05, "loss": 0.06771814823150635, "step": 606 }, { "epoch": 2.057724957555178, "grad_norm": 0.19260533373582076, "learning_rate": 5.6342960567914235e-05, "loss": 0.0887187272310257, "step": 607 }, { "epoch": 2.0611205432937183, "grad_norm": 0.2019352859072592, "learning_rate": 5.619621876848864e-05, "loss": 0.11880266666412354, "step": 608 }, { "epoch": 2.064516129032258, "grad_norm": 0.19718654777144978, "learning_rate": 5.60494227468626e-05, "loss": 0.10265833139419556, "step": 609 }, { "epoch": 2.067911714770798, "grad_norm": 0.17748838822794688, "learning_rate": 5.5902573787626544e-05, "loss": 0.09355604648590088, "step": 610 }, { "epoch": 2.071307300509338, "grad_norm": 0.18165577016402445, "learning_rate": 5.5755673175834145e-05, "loss": 0.08513667434453964, "step": 611 }, { "epoch": 2.0747028862478776, "grad_norm": 0.1853864279720625, "learning_rate": 5.56087221969911e-05, "loss": 0.0788930207490921, "step": 612 }, { "epoch": 2.0780984719864177, "grad_norm": 0.18643941914482987, "learning_rate": 5.546172213704384e-05, "loss": 0.07431256771087646, "step": 613 }, { "epoch": 2.0814940577249574, "grad_norm": 0.17615669284547794, "learning_rate": 5.5314674282368275e-05, "loss": 0.06649843603372574, "step": 614 }, { "epoch": 2.0848896434634976, "grad_norm": 0.20568731102131993, "learning_rate": 5.5167579919758606e-05, "loss": 0.06795898079872131, "step": 615 }, { "epoch": 2.0882852292020373, "grad_norm": 0.1686277043303997, "learning_rate": 5.5020440336416e-05, "loss": 0.11328067630529404, "step": 616 }, { "epoch": 2.0916808149405774, "grad_norm": 0.21028850191438905, "learning_rate": 5.487325681993733e-05, "loss": 0.11785249412059784, "step": 617 }, { "epoch": 2.095076400679117, "grad_norm": 0.17925330353372043, "learning_rate": 5.472603065830393e-05, "loss": 0.10392972081899643, "step": 618 }, { "epoch": 2.098471986417657, "grad_norm": 0.17107375066442876, "learning_rate": 5.457876313987034e-05, "loss": 0.08784636110067368, "step": 619 }, { "epoch": 2.101867572156197, "grad_norm": 0.18232366531737457, "learning_rate": 5.443145555335296e-05, "loss": 0.0826864168047905, "step": 620 }, { "epoch": 2.1052631578947367, "grad_norm": 0.17990275680825715, "learning_rate": 5.4284109187818845e-05, "loss": 0.07586630433797836, "step": 621 }, { "epoch": 2.108658743633277, "grad_norm": 0.19728627180446331, "learning_rate": 5.4136725332674434e-05, "loss": 0.07594335079193115, "step": 622 }, { "epoch": 2.1120543293718166, "grad_norm": 0.189009348956481, "learning_rate": 5.3989305277654156e-05, "loss": 0.06875759363174438, "step": 623 }, { "epoch": 2.1154499151103567, "grad_norm": 0.2089721067233783, "learning_rate": 5.3841850312809295e-05, "loss": 0.1098216325044632, "step": 624 }, { "epoch": 2.1188455008488964, "grad_norm": 0.19227367424881855, "learning_rate": 5.369436172849657e-05, "loss": 0.12781623005867004, "step": 625 }, { "epoch": 2.122241086587436, "grad_norm": 0.19032963693236096, "learning_rate": 5.354684081536693e-05, "loss": 0.10976029932498932, "step": 626 }, { "epoch": 2.1256366723259763, "grad_norm": 0.1991147980109885, "learning_rate": 5.3399288864354225e-05, "loss": 0.09619562327861786, "step": 627 }, { "epoch": 2.129032258064516, "grad_norm": 0.17505944859431077, "learning_rate": 5.3251707166663886e-05, "loss": 0.08784763514995575, "step": 628 }, { "epoch": 2.132427843803056, "grad_norm": 0.17512616158688596, "learning_rate": 5.31040970137617e-05, "loss": 0.08227354288101196, "step": 629 }, { "epoch": 2.135823429541596, "grad_norm": 0.1858336071218847, "learning_rate": 5.295645969736244e-05, "loss": 0.07487807422876358, "step": 630 }, { "epoch": 2.139219015280136, "grad_norm": 0.18361401088465984, "learning_rate": 5.280879650941857e-05, "loss": 0.06451160460710526, "step": 631 }, { "epoch": 2.1426146010186757, "grad_norm": 0.15823519399635375, "learning_rate": 5.2661108742108935e-05, "loss": 0.08187909424304962, "step": 632 }, { "epoch": 2.1460101867572154, "grad_norm": 0.16594954608976964, "learning_rate": 5.251339768782754e-05, "loss": 0.11212148517370224, "step": 633 }, { "epoch": 2.1494057724957556, "grad_norm": 0.17833182815432058, "learning_rate": 5.23656646391721e-05, "loss": 0.11305718868970871, "step": 634 }, { "epoch": 2.1528013582342953, "grad_norm": 0.19532920280556404, "learning_rate": 5.221791088893282e-05, "loss": 0.10172098875045776, "step": 635 }, { "epoch": 2.1561969439728355, "grad_norm": 0.3013870719119221, "learning_rate": 5.207013773008111e-05, "loss": 0.08888505399227142, "step": 636 }, { "epoch": 2.159592529711375, "grad_norm": 0.17743907236187367, "learning_rate": 5.192234645575814e-05, "loss": 0.08181847631931305, "step": 637 }, { "epoch": 2.1629881154499153, "grad_norm": 0.18510033401963283, "learning_rate": 5.177453835926366e-05, "loss": 0.07848383486270905, "step": 638 }, { "epoch": 2.166383701188455, "grad_norm": 0.16964624611307097, "learning_rate": 5.162671473404461e-05, "loss": 0.06493636965751648, "step": 639 }, { "epoch": 2.1697792869269947, "grad_norm": 0.19165970932035326, "learning_rate": 5.147887687368384e-05, "loss": 0.0707256868481636, "step": 640 }, { "epoch": 2.173174872665535, "grad_norm": 0.1721563135872704, "learning_rate": 5.133102607188874e-05, "loss": 0.10899870097637177, "step": 641 }, { "epoch": 2.1765704584040746, "grad_norm": 0.1672334512723684, "learning_rate": 5.1183163622479966e-05, "loss": 0.10445180535316467, "step": 642 }, { "epoch": 2.1799660441426147, "grad_norm": 0.1806841956527768, "learning_rate": 5.10352908193801e-05, "loss": 0.09651540219783783, "step": 643 }, { "epoch": 2.1833616298811545, "grad_norm": 0.20196049010082395, "learning_rate": 5.088740895660231e-05, "loss": 0.09565379470586777, "step": 644 }, { "epoch": 2.1867572156196946, "grad_norm": 0.1842107489787402, "learning_rate": 5.073951932823907e-05, "loss": 0.08658355474472046, "step": 645 }, { "epoch": 2.1901528013582343, "grad_norm": 0.17928013643477353, "learning_rate": 5.0591623228450805e-05, "loss": 0.07876981794834137, "step": 646 }, { "epoch": 2.193548387096774, "grad_norm": 0.1808277804496368, "learning_rate": 5.044372195145455e-05, "loss": 0.07109809666872025, "step": 647 }, { "epoch": 2.196943972835314, "grad_norm": 0.18043295964503364, "learning_rate": 5.0295816791512686e-05, "loss": 0.06647136807441711, "step": 648 }, { "epoch": 2.200339558573854, "grad_norm": 0.17684796212193798, "learning_rate": 5.014790904292149e-05, "loss": 0.10662539303302765, "step": 649 }, { "epoch": 2.203735144312394, "grad_norm": 0.1740192185663839, "learning_rate": 5e-05, "loss": 0.11376029253005981, "step": 650 }, { "epoch": 2.2071307300509337, "grad_norm": 0.16848575217961903, "learning_rate": 4.9852090957078515e-05, "loss": 0.09893074631690979, "step": 651 }, { "epoch": 2.2105263157894735, "grad_norm": 0.23162501925535942, "learning_rate": 4.9704183208487325e-05, "loss": 0.09183754771947861, "step": 652 }, { "epoch": 2.2139219015280136, "grad_norm": 0.17993997700028208, "learning_rate": 4.955627804854545e-05, "loss": 0.08125372231006622, "step": 653 }, { "epoch": 2.2173174872665533, "grad_norm": 0.17195501476542396, "learning_rate": 4.94083767715492e-05, "loss": 0.0768633484840393, "step": 654 }, { "epoch": 2.2207130730050935, "grad_norm": 0.17866247054760723, "learning_rate": 4.9260480671760925e-05, "loss": 0.0722515806555748, "step": 655 }, { "epoch": 2.224108658743633, "grad_norm": 0.18271382977131898, "learning_rate": 4.911259104339771e-05, "loss": 0.0666186511516571, "step": 656 }, { "epoch": 2.2275042444821733, "grad_norm": 0.16897556521854257, "learning_rate": 4.8964709180619924e-05, "loss": 0.08462535589933395, "step": 657 }, { "epoch": 2.230899830220713, "grad_norm": 0.15762040290256057, "learning_rate": 4.881683637752005e-05, "loss": 0.11229859292507172, "step": 658 }, { "epoch": 2.234295415959253, "grad_norm": 0.16708909029439764, "learning_rate": 4.866897392811126e-05, "loss": 0.10317954421043396, "step": 659 }, { "epoch": 2.237691001697793, "grad_norm": 0.17515063411769377, "learning_rate": 4.852112312631616e-05, "loss": 0.10435949265956879, "step": 660 }, { "epoch": 2.2410865874363326, "grad_norm": 0.17305905597060908, "learning_rate": 4.8373285265955395e-05, "loss": 0.08963470160961151, "step": 661 }, { "epoch": 2.2444821731748728, "grad_norm": 0.17239857971902753, "learning_rate": 4.822546164073635e-05, "loss": 0.0814611166715622, "step": 662 }, { "epoch": 2.2478777589134125, "grad_norm": 0.18235984073725345, "learning_rate": 4.8077653544241864e-05, "loss": 0.0766005665063858, "step": 663 }, { "epoch": 2.2512733446519526, "grad_norm": 0.17902539027962736, "learning_rate": 4.792986226991889e-05, "loss": 0.06602571904659271, "step": 664 }, { "epoch": 2.2546689303904923, "grad_norm": 0.18558458445776474, "learning_rate": 4.7782089111067176e-05, "loss": 0.06730405986309052, "step": 665 }, { "epoch": 2.258064516129032, "grad_norm": 0.17648345278633168, "learning_rate": 4.7634335360827905e-05, "loss": 0.11872434616088867, "step": 666 }, { "epoch": 2.261460101867572, "grad_norm": 0.16548873214367543, "learning_rate": 4.748660231217249e-05, "loss": 0.11121334880590439, "step": 667 }, { "epoch": 2.264855687606112, "grad_norm": 0.1719660207499494, "learning_rate": 4.7338891257891084e-05, "loss": 0.0968489795923233, "step": 668 }, { "epoch": 2.268251273344652, "grad_norm": 0.1850134785513106, "learning_rate": 4.719120349058146e-05, "loss": 0.0888376459479332, "step": 669 }, { "epoch": 2.2716468590831917, "grad_norm": 0.18695635318200762, "learning_rate": 4.7043540302637575e-05, "loss": 0.07844914495944977, "step": 670 }, { "epoch": 2.275042444821732, "grad_norm": 0.16881341588855783, "learning_rate": 4.6895902986238304e-05, "loss": 0.07310467213392258, "step": 671 }, { "epoch": 2.2784380305602716, "grad_norm": 0.17466440656494808, "learning_rate": 4.6748292833336125e-05, "loss": 0.06666155159473419, "step": 672 }, { "epoch": 2.2818336162988118, "grad_norm": 0.18249219677718487, "learning_rate": 4.6600711135645793e-05, "loss": 0.06474683433771133, "step": 673 }, { "epoch": 2.2852292020373515, "grad_norm": 0.187570158625838, "learning_rate": 4.6453159184633076e-05, "loss": 0.11088087409734726, "step": 674 }, { "epoch": 2.288624787775891, "grad_norm": 0.1905691442362375, "learning_rate": 4.6305638271503445e-05, "loss": 0.1207934319972992, "step": 675 }, { "epoch": 2.2920203735144313, "grad_norm": 0.1751134361111324, "learning_rate": 4.615814968719071e-05, "loss": 0.10184189677238464, "step": 676 }, { "epoch": 2.295415959252971, "grad_norm": 0.18095887619806494, "learning_rate": 4.601069472234584e-05, "loss": 0.0956878662109375, "step": 677 }, { "epoch": 2.298811544991511, "grad_norm": 0.17497874461623475, "learning_rate": 4.586327466732557e-05, "loss": 0.0891914814710617, "step": 678 }, { "epoch": 2.302207130730051, "grad_norm": 0.17110452420981204, "learning_rate": 4.571589081218116e-05, "loss": 0.08255179971456528, "step": 679 }, { "epoch": 2.3056027164685906, "grad_norm": 0.16832860278058365, "learning_rate": 4.556854444664706e-05, "loss": 0.0698966458439827, "step": 680 }, { "epoch": 2.3089983022071308, "grad_norm": 0.1712961600216127, "learning_rate": 4.5421236860129686e-05, "loss": 0.06230298802256584, "step": 681 }, { "epoch": 2.3123938879456705, "grad_norm": 0.18217990482091656, "learning_rate": 4.527396934169609e-05, "loss": 0.10267043113708496, "step": 682 }, { "epoch": 2.3157894736842106, "grad_norm": 0.1805819950574741, "learning_rate": 4.512674318006268e-05, "loss": 0.1234576553106308, "step": 683 }, { "epoch": 2.3191850594227503, "grad_norm": 0.1789978555761233, "learning_rate": 4.4979559663584015e-05, "loss": 0.11386032402515411, "step": 684 }, { "epoch": 2.3225806451612905, "grad_norm": 0.18283568796004748, "learning_rate": 4.4832420080241406e-05, "loss": 0.09699396789073944, "step": 685 }, { "epoch": 2.32597623089983, "grad_norm": 0.18190864472107063, "learning_rate": 4.4685325717631736e-05, "loss": 0.09254609793424606, "step": 686 }, { "epoch": 2.3293718166383703, "grad_norm": 0.17613238622943872, "learning_rate": 4.453827786295617e-05, "loss": 0.08423325419425964, "step": 687 }, { "epoch": 2.33276740237691, "grad_norm": 0.1782428785677366, "learning_rate": 4.4391277803008905e-05, "loss": 0.07241242378950119, "step": 688 }, { "epoch": 2.3361629881154498, "grad_norm": 0.20714257959058618, "learning_rate": 4.424432682416585e-05, "loss": 0.07077805697917938, "step": 689 }, { "epoch": 2.33955857385399, "grad_norm": 0.1793930811678062, "learning_rate": 4.4097426212373474e-05, "loss": 0.06788688153028488, "step": 690 }, { "epoch": 2.3429541595925296, "grad_norm": 0.154567252554236, "learning_rate": 4.3950577253137425e-05, "loss": 0.10577817261219025, "step": 691 }, { "epoch": 2.3463497453310698, "grad_norm": 0.2195055844527067, "learning_rate": 4.380378123151139e-05, "loss": 0.12233912944793701, "step": 692 }, { "epoch": 2.3497453310696095, "grad_norm": 0.1852715377219104, "learning_rate": 4.3657039432085776e-05, "loss": 0.09445637464523315, "step": 693 }, { "epoch": 2.353140916808149, "grad_norm": 0.17548944262613003, "learning_rate": 4.351035313897655e-05, "loss": 0.08697226643562317, "step": 694 }, { "epoch": 2.3565365025466893, "grad_norm": 0.1641988589272713, "learning_rate": 4.336372363581391e-05, "loss": 0.07541926950216293, "step": 695 }, { "epoch": 2.359932088285229, "grad_norm": 0.17268500043782573, "learning_rate": 4.32171522057311e-05, "loss": 0.072224922478199, "step": 696 }, { "epoch": 2.363327674023769, "grad_norm": 0.17348572863176273, "learning_rate": 4.307064013135316e-05, "loss": 0.06982975453138351, "step": 697 }, { "epoch": 2.366723259762309, "grad_norm": 0.16692609280302698, "learning_rate": 4.2924188694785773e-05, "loss": 0.06516002118587494, "step": 698 }, { "epoch": 2.370118845500849, "grad_norm": 0.17908260558281336, "learning_rate": 4.277779917760393e-05, "loss": 0.11083652079105377, "step": 699 }, { "epoch": 2.3735144312393888, "grad_norm": 0.15157715757891146, "learning_rate": 4.263147286084078e-05, "loss": 0.11505262553691864, "step": 700 }, { "epoch": 2.376910016977929, "grad_norm": 0.16802827685730093, "learning_rate": 4.2485211024976496e-05, "loss": 0.09915955364704132, "step": 701 }, { "epoch": 2.3803056027164686, "grad_norm": 0.1797548051366379, "learning_rate": 4.2339014949926844e-05, "loss": 0.08792432397603989, "step": 702 }, { "epoch": 2.3837011884550083, "grad_norm": 0.16254054209655075, "learning_rate": 4.219288591503224e-05, "loss": 0.07736881822347641, "step": 703 }, { "epoch": 2.3870967741935485, "grad_norm": 0.1713514779564915, "learning_rate": 4.204682519904641e-05, "loss": 0.08164150267839432, "step": 704 }, { "epoch": 2.390492359932088, "grad_norm": 0.1726994731422147, "learning_rate": 4.190083408012522e-05, "loss": 0.07089899480342865, "step": 705 }, { "epoch": 2.3938879456706283, "grad_norm": 0.17339258003316832, "learning_rate": 4.175491383581552e-05, "loss": 0.0633159726858139, "step": 706 }, { "epoch": 2.397283531409168, "grad_norm": 0.17825029386502939, "learning_rate": 4.160906574304392e-05, "loss": 0.10916628688573837, "step": 707 }, { "epoch": 2.4006791171477078, "grad_norm": 0.16096357537242212, "learning_rate": 4.146329107810569e-05, "loss": 0.1283857822418213, "step": 708 }, { "epoch": 2.404074702886248, "grad_norm": 0.1567655927134746, "learning_rate": 4.131759111665349e-05, "loss": 0.10651916265487671, "step": 709 }, { "epoch": 2.4074702886247876, "grad_norm": 0.17257485951775256, "learning_rate": 4.117196713368629e-05, "loss": 0.10017132014036179, "step": 710 }, { "epoch": 2.4108658743633278, "grad_norm": 0.16940514862847636, "learning_rate": 4.102642040353817e-05, "loss": 0.09811308979988098, "step": 711 }, { "epoch": 2.4142614601018675, "grad_norm": 0.15729121905044205, "learning_rate": 4.088095219986721e-05, "loss": 0.08088087290525436, "step": 712 }, { "epoch": 2.4176570458404076, "grad_norm": 0.1684583395156756, "learning_rate": 4.0735563795644294e-05, "loss": 0.06843972951173782, "step": 713 }, { "epoch": 2.4210526315789473, "grad_norm": 0.17087428647972447, "learning_rate": 4.059025646314197e-05, "loss": 0.06300380825996399, "step": 714 }, { "epoch": 2.4244482173174875, "grad_norm": 0.1762199239526789, "learning_rate": 4.044503147392339e-05, "loss": 0.06428471207618713, "step": 715 }, { "epoch": 2.427843803056027, "grad_norm": 0.16750985155904444, "learning_rate": 4.0299890098831096e-05, "loss": 0.11279623210430145, "step": 716 }, { "epoch": 2.431239388794567, "grad_norm": 0.16330035195973525, "learning_rate": 4.015483360797593e-05, "loss": 0.10454337298870087, "step": 717 }, { "epoch": 2.434634974533107, "grad_norm": 0.16804821734575356, "learning_rate": 4.0009863270725964e-05, "loss": 0.09333685040473938, "step": 718 }, { "epoch": 2.4380305602716468, "grad_norm": 0.1952635525255714, "learning_rate": 3.986498035569532e-05, "loss": 0.08931829780340195, "step": 719 }, { "epoch": 2.441426146010187, "grad_norm": 0.1754030483793059, "learning_rate": 3.972018613073312e-05, "loss": 0.0783512145280838, "step": 720 }, { "epoch": 2.4448217317487266, "grad_norm": 0.15551206451480853, "learning_rate": 3.957548186291233e-05, "loss": 0.07081504911184311, "step": 721 }, { "epoch": 2.4482173174872663, "grad_norm": 0.16505062797057274, "learning_rate": 3.9430868818518784e-05, "loss": 0.06218322366476059, "step": 722 }, { "epoch": 2.4516129032258065, "grad_norm": 0.1868304275735769, "learning_rate": 3.928634826303997e-05, "loss": 0.059126876294612885, "step": 723 }, { "epoch": 2.455008488964346, "grad_norm": 0.1853578606671566, "learning_rate": 3.914192146115407e-05, "loss": 0.1022864505648613, "step": 724 }, { "epoch": 2.4584040747028864, "grad_norm": 0.16518970835907015, "learning_rate": 3.899758967671878e-05, "loss": 0.10612255334854126, "step": 725 }, { "epoch": 2.461799660441426, "grad_norm": 0.16935720320024328, "learning_rate": 3.885335417276037e-05, "loss": 0.0974433645606041, "step": 726 }, { "epoch": 2.465195246179966, "grad_norm": 0.20372195250990488, "learning_rate": 3.870921621146254e-05, "loss": 0.0931549072265625, "step": 727 }, { "epoch": 2.468590831918506, "grad_norm": 0.20694225574051262, "learning_rate": 3.856517705415543e-05, "loss": 0.0862373560667038, "step": 728 }, { "epoch": 2.471986417657046, "grad_norm": 0.17051084056651614, "learning_rate": 3.8421237961304555e-05, "loss": 0.08289209753274918, "step": 729 }, { "epoch": 2.475382003395586, "grad_norm": 0.17650047163769184, "learning_rate": 3.827740019249977e-05, "loss": 0.06609411537647247, "step": 730 }, { "epoch": 2.4787775891341255, "grad_norm": 0.18533837210545853, "learning_rate": 3.8133665006444255e-05, "loss": 0.0610504113137722, "step": 731 }, { "epoch": 2.4821731748726656, "grad_norm": 0.18569882645975314, "learning_rate": 3.799003366094354e-05, "loss": 0.09701117128133774, "step": 732 }, { "epoch": 2.4855687606112054, "grad_norm": 0.1788887074850881, "learning_rate": 3.784650741289442e-05, "loss": 0.12465445697307587, "step": 733 }, { "epoch": 2.4889643463497455, "grad_norm": 0.1656627797197923, "learning_rate": 3.7703087518274015e-05, "loss": 0.1012495756149292, "step": 734 }, { "epoch": 2.492359932088285, "grad_norm": 0.18600566640658012, "learning_rate": 3.755977523212877e-05, "loss": 0.0960812196135521, "step": 735 }, { "epoch": 2.495755517826825, "grad_norm": 0.1997151459112257, "learning_rate": 3.7416571808563426e-05, "loss": 0.09349378198385239, "step": 736 }, { "epoch": 2.499151103565365, "grad_norm": 0.18554025176257402, "learning_rate": 3.727347850073012e-05, "loss": 0.07903861999511719, "step": 737 }, { "epoch": 2.502546689303905, "grad_norm": 0.16604309048255483, "learning_rate": 3.71304965608174e-05, "loss": 0.07200177013874054, "step": 738 }, { "epoch": 2.505942275042445, "grad_norm": 0.1822825212049376, "learning_rate": 3.698762724003919e-05, "loss": 0.06303315609693527, "step": 739 }, { "epoch": 2.5093378607809846, "grad_norm": 0.18626351402704802, "learning_rate": 3.6844871788623945e-05, "loss": 0.06897502392530441, "step": 740 }, { "epoch": 2.5127334465195243, "grad_norm": 0.17633386916618624, "learning_rate": 3.670223145580366e-05, "loss": 0.1113574355840683, "step": 741 }, { "epoch": 2.5161290322580645, "grad_norm": 0.15171936037974573, "learning_rate": 3.655970748980293e-05, "loss": 0.10773645341396332, "step": 742 }, { "epoch": 2.5195246179966047, "grad_norm": 0.1532667623070388, "learning_rate": 3.641730113782807e-05, "loss": 0.0943991169333458, "step": 743 }, { "epoch": 2.5229202037351444, "grad_norm": 0.1782008980261668, "learning_rate": 3.6275013646056135e-05, "loss": 0.08693014085292816, "step": 744 }, { "epoch": 2.526315789473684, "grad_norm": 0.18789164395769786, "learning_rate": 3.6132846259624055e-05, "loss": 0.08198776096105576, "step": 745 }, { "epoch": 2.5297113752122242, "grad_norm": 0.16978827609932354, "learning_rate": 3.599080022261777e-05, "loss": 0.07230781763792038, "step": 746 }, { "epoch": 2.533106960950764, "grad_norm": 0.16317475874306614, "learning_rate": 3.58488767780613e-05, "loss": 0.06677805632352829, "step": 747 }, { "epoch": 2.536502546689304, "grad_norm": 0.1972967269758657, "learning_rate": 3.570707716790584e-05, "loss": 0.059502989053726196, "step": 748 }, { "epoch": 2.539898132427844, "grad_norm": 0.18434895103360113, "learning_rate": 3.556540263301896e-05, "loss": 0.1087162122130394, "step": 749 }, { "epoch": 2.5432937181663835, "grad_norm": 0.16936513819953788, "learning_rate": 3.5423854413173706e-05, "loss": 0.10882570594549179, "step": 750 }, { "epoch": 2.5466893039049237, "grad_norm": 0.18239729346131794, "learning_rate": 3.5282433747037757e-05, "loss": 0.1013280600309372, "step": 751 }, { "epoch": 2.5500848896434634, "grad_norm": 0.18452129783328533, "learning_rate": 3.514114187216261e-05, "loss": 0.09412064403295517, "step": 752 }, { "epoch": 2.5534804753820035, "grad_norm": 0.1788700370067982, "learning_rate": 3.49999800249727e-05, "loss": 0.0804615169763565, "step": 753 }, { "epoch": 2.556876061120543, "grad_norm": 0.17757962765643567, "learning_rate": 3.485894944075463e-05, "loss": 0.09246362745761871, "step": 754 }, { "epoch": 2.560271646859083, "grad_norm": 0.18044254385294772, "learning_rate": 3.47180513536463e-05, "loss": 0.07304270565509796, "step": 755 }, { "epoch": 2.563667232597623, "grad_norm": 0.17263121190425817, "learning_rate": 3.457728699662621e-05, "loss": 0.06096385046839714, "step": 756 }, { "epoch": 2.5670628183361632, "grad_norm": 0.17547187620561558, "learning_rate": 3.4436657601502576e-05, "loss": 0.08266765624284744, "step": 757 }, { "epoch": 2.570458404074703, "grad_norm": 0.1848341758349366, "learning_rate": 3.429616439890258e-05, "loss": 0.11557235568761826, "step": 758 }, { "epoch": 2.5738539898132426, "grad_norm": 0.18546744327548575, "learning_rate": 3.4155808618261563e-05, "loss": 0.10113745927810669, "step": 759 }, { "epoch": 2.577249575551783, "grad_norm": 0.18119312219678071, "learning_rate": 3.4015591487812395e-05, "loss": 0.09464039653539658, "step": 760 }, { "epoch": 2.5806451612903225, "grad_norm": 0.1802385713225429, "learning_rate": 3.3875514234574556e-05, "loss": 0.08910854160785675, "step": 761 }, { "epoch": 2.5840407470288627, "grad_norm": 0.1911053301847068, "learning_rate": 3.373557808434355e-05, "loss": 0.07500690221786499, "step": 762 }, { "epoch": 2.5874363327674024, "grad_norm": 0.18341057535713914, "learning_rate": 3.359578426168007e-05, "loss": 0.07360392063856125, "step": 763 }, { "epoch": 2.590831918505942, "grad_norm": 0.1940401226942174, "learning_rate": 3.345613398989932e-05, "loss": 0.06643348187208176, "step": 764 }, { "epoch": 2.5942275042444822, "grad_norm": 0.18484893020921123, "learning_rate": 3.33166284910603e-05, "loss": 0.0637667179107666, "step": 765 }, { "epoch": 2.597623089983022, "grad_norm": 0.15876245308103723, "learning_rate": 3.317726898595517e-05, "loss": 0.1025618463754654, "step": 766 }, { "epoch": 2.601018675721562, "grad_norm": 0.16451563871558816, "learning_rate": 3.303805669409848e-05, "loss": 0.10825486481189728, "step": 767 }, { "epoch": 2.604414261460102, "grad_norm": 0.19042057842199994, "learning_rate": 3.289899283371657e-05, "loss": 0.09530699253082275, "step": 768 }, { "epoch": 2.6078098471986415, "grad_norm": 0.1812550045429384, "learning_rate": 3.276007862173683e-05, "loss": 0.08641920983791351, "step": 769 }, { "epoch": 2.6112054329371817, "grad_norm": 0.17604834133006597, "learning_rate": 3.262131527377715e-05, "loss": 0.0829029381275177, "step": 770 }, { "epoch": 2.614601018675722, "grad_norm": 0.16701558790918755, "learning_rate": 3.248270400413518e-05, "loss": 0.06672143936157227, "step": 771 }, { "epoch": 2.6179966044142615, "grad_norm": 0.17001463446645657, "learning_rate": 3.23442460257778e-05, "loss": 0.0628892034292221, "step": 772 }, { "epoch": 2.6213921901528012, "grad_norm": 0.1728233046869325, "learning_rate": 3.2205942550330456e-05, "loss": 0.05917782709002495, "step": 773 }, { "epoch": 2.6247877758913414, "grad_norm": 0.17003408799823622, "learning_rate": 3.206779478806654e-05, "loss": 0.10056929290294647, "step": 774 }, { "epoch": 2.628183361629881, "grad_norm": 0.16073642367644125, "learning_rate": 3.192980394789682e-05, "loss": 0.10843627154827118, "step": 775 }, { "epoch": 2.6315789473684212, "grad_norm": 0.17153592098478565, "learning_rate": 3.179197123735889e-05, "loss": 0.09619466960430145, "step": 776 }, { "epoch": 2.634974533106961, "grad_norm": 0.18327794909489512, "learning_rate": 3.1654297862606554e-05, "loss": 0.09573782980442047, "step": 777 }, { "epoch": 2.6383701188455007, "grad_norm": 0.1839139251920574, "learning_rate": 3.151678502839929e-05, "loss": 0.08106369525194168, "step": 778 }, { "epoch": 2.641765704584041, "grad_norm": 0.17924254837245787, "learning_rate": 3.1379433938091696e-05, "loss": 0.07815179973840714, "step": 779 }, { "epoch": 2.6451612903225805, "grad_norm": 0.16622738025815964, "learning_rate": 3.124224579362305e-05, "loss": 0.06951127201318741, "step": 780 }, { "epoch": 2.6485568760611207, "grad_norm": 0.16469536825877137, "learning_rate": 3.1105221795506584e-05, "loss": 0.061446063220500946, "step": 781 }, { "epoch": 2.6519524617996604, "grad_norm": 0.1830436361999393, "learning_rate": 3.096836314281923e-05, "loss": 0.09685629606246948, "step": 782 }, { "epoch": 2.6553480475382, "grad_norm": 0.18178354905531777, "learning_rate": 3.083167103319093e-05, "loss": 0.12026413530111313, "step": 783 }, { "epoch": 2.6587436332767402, "grad_norm": 0.1638396717874821, "learning_rate": 3.069514666279427e-05, "loss": 0.10666602849960327, "step": 784 }, { "epoch": 2.6621392190152804, "grad_norm": 0.16452440760436854, "learning_rate": 3.055879122633397e-05, "loss": 0.09171438217163086, "step": 785 }, { "epoch": 2.66553480475382, "grad_norm": 0.17252134096468763, "learning_rate": 3.042260591703643e-05, "loss": 0.08265566825866699, "step": 786 }, { "epoch": 2.66893039049236, "grad_norm": 0.19590675896541593, "learning_rate": 3.0286591926639287e-05, "loss": 0.08365504443645477, "step": 787 }, { "epoch": 2.6723259762309, "grad_norm": 0.17346560006390419, "learning_rate": 3.0150750445380992e-05, "loss": 0.06742806732654572, "step": 788 }, { "epoch": 2.6757215619694397, "grad_norm": 0.16925796446238367, "learning_rate": 3.0015082661990395e-05, "loss": 0.06698235869407654, "step": 789 }, { "epoch": 2.67911714770798, "grad_norm": 0.190479550362414, "learning_rate": 2.9879589763676358e-05, "loss": 0.06469935178756714, "step": 790 }, { "epoch": 2.6825127334465195, "grad_norm": 0.16691042668923836, "learning_rate": 2.9744272936117323e-05, "loss": 0.10404828190803528, "step": 791 }, { "epoch": 2.6859083191850592, "grad_norm": 0.16047916543981608, "learning_rate": 2.960913336345099e-05, "loss": 0.09722572565078735, "step": 792 }, { "epoch": 2.6893039049235994, "grad_norm": 0.1628721484822222, "learning_rate": 2.9474172228263887e-05, "loss": 0.09782986342906952, "step": 793 }, { "epoch": 2.692699490662139, "grad_norm": 0.15854921437126837, "learning_rate": 2.9339390711581105e-05, "loss": 0.08399864286184311, "step": 794 }, { "epoch": 2.6960950764006792, "grad_norm": 0.17978144515954722, "learning_rate": 2.9204789992855885e-05, "loss": 0.08404549956321716, "step": 795 }, { "epoch": 2.699490662139219, "grad_norm": 0.17819716159463206, "learning_rate": 2.9070371249959378e-05, "loss": 0.07262590527534485, "step": 796 }, { "epoch": 2.7028862478777587, "grad_norm": 0.17511969511403835, "learning_rate": 2.8936135659170216e-05, "loss": 0.06601671874523163, "step": 797 }, { "epoch": 2.706281833616299, "grad_norm": 0.15900113834788712, "learning_rate": 2.8802084395164386e-05, "loss": 0.05793508142232895, "step": 798 }, { "epoch": 2.709677419354839, "grad_norm": 0.16006428175654816, "learning_rate": 2.866821863100479e-05, "loss": 0.0999666303396225, "step": 799 }, { "epoch": 2.7130730050933787, "grad_norm": 0.18102275252219002, "learning_rate": 2.8534539538131076e-05, "loss": 0.11513181775808334, "step": 800 }, { "epoch": 2.7164685908319184, "grad_norm": 0.18155450137579152, "learning_rate": 2.8401048286349353e-05, "loss": 0.09707678854465485, "step": 801 }, { "epoch": 2.7198641765704585, "grad_norm": 0.1672244650069254, "learning_rate": 2.826774604382195e-05, "loss": 0.08562149852514267, "step": 802 }, { "epoch": 2.7232597623089982, "grad_norm": 0.16230378264983186, "learning_rate": 2.8134633977057235e-05, "loss": 0.08084724843502045, "step": 803 }, { "epoch": 2.7266553480475384, "grad_norm": 0.1752760396700523, "learning_rate": 2.800171325089933e-05, "loss": 0.08049998432397842, "step": 804 }, { "epoch": 2.730050933786078, "grad_norm": 0.1849836789734473, "learning_rate": 2.7868985028518006e-05, "loss": 0.06668615341186523, "step": 805 }, { "epoch": 2.733446519524618, "grad_norm": 0.174292360388813, "learning_rate": 2.7736450471398434e-05, "loss": 0.0583345964550972, "step": 806 }, { "epoch": 2.736842105263158, "grad_norm": 0.19003105024236863, "learning_rate": 2.7604110739331068e-05, "loss": 0.09205623716115952, "step": 807 }, { "epoch": 2.7402376910016977, "grad_norm": 0.14663856124744207, "learning_rate": 2.747196699040146e-05, "loss": 0.1073693260550499, "step": 808 }, { "epoch": 2.743633276740238, "grad_norm": 0.1666902803621123, "learning_rate": 2.7340020380980146e-05, "loss": 0.09746035188436508, "step": 809 }, { "epoch": 2.7470288624787775, "grad_norm": 0.1886181453115624, "learning_rate": 2.7208272065712537e-05, "loss": 0.09663771092891693, "step": 810 }, { "epoch": 2.7504244482173172, "grad_norm": 0.18350264933235916, "learning_rate": 2.7076723197508768e-05, "loss": 0.08637096732854843, "step": 811 }, { "epoch": 2.7538200339558574, "grad_norm": 0.16461327004325288, "learning_rate": 2.69453749275337e-05, "loss": 0.07879146933555603, "step": 812 }, { "epoch": 2.7572156196943975, "grad_norm": 0.17001926297718395, "learning_rate": 2.6814228405196738e-05, "loss": 0.06773528456687927, "step": 813 }, { "epoch": 2.7606112054329373, "grad_norm": 0.1804307513427523, "learning_rate": 2.6683284778141852e-05, "loss": 0.06176406145095825, "step": 814 }, { "epoch": 2.764006791171477, "grad_norm": 0.19803411172590618, "learning_rate": 2.655254519223746e-05, "loss": 0.06123121827840805, "step": 815 }, { "epoch": 2.767402376910017, "grad_norm": 0.15330896400602023, "learning_rate": 2.6422010791566492e-05, "loss": 0.11360757797956467, "step": 816 }, { "epoch": 2.770797962648557, "grad_norm": 0.14141782882790915, "learning_rate": 2.62916827184163e-05, "loss": 0.10179056972265244, "step": 817 }, { "epoch": 2.774193548387097, "grad_norm": 0.18057811395750734, "learning_rate": 2.6161562113268745e-05, "loss": 0.09349533170461655, "step": 818 }, { "epoch": 2.7775891341256367, "grad_norm": 0.19735227538997324, "learning_rate": 2.603165011479012e-05, "loss": 0.09211376309394836, "step": 819 }, { "epoch": 2.7809847198641764, "grad_norm": 0.17608048305075696, "learning_rate": 2.590194785982124e-05, "loss": 0.07923342287540436, "step": 820 }, { "epoch": 2.7843803056027165, "grad_norm": 0.16916485307153226, "learning_rate": 2.5772456483367497e-05, "loss": 0.0678873360157013, "step": 821 }, { "epoch": 2.7877758913412563, "grad_norm": 0.17553323512525765, "learning_rate": 2.56431771185889e-05, "loss": 0.06374121457338333, "step": 822 }, { "epoch": 2.7911714770797964, "grad_norm": 0.18885599244828064, "learning_rate": 2.5514110896790184e-05, "loss": 0.05840972810983658, "step": 823 }, { "epoch": 2.794567062818336, "grad_norm": 0.17921444032442846, "learning_rate": 2.5385258947410906e-05, "loss": 0.09742407500743866, "step": 824 }, { "epoch": 2.797962648556876, "grad_norm": 0.1621403416235573, "learning_rate": 2.525662239801553e-05, "loss": 0.11257597804069519, "step": 825 }, { "epoch": 2.801358234295416, "grad_norm": 0.16442225055136717, "learning_rate": 2.512820237428366e-05, "loss": 0.09314374625682831, "step": 826 }, { "epoch": 2.804753820033956, "grad_norm": 0.2019224728559447, "learning_rate": 2.500000000000001e-05, "loss": 0.09272406995296478, "step": 827 }, { "epoch": 2.808149405772496, "grad_norm": 0.19180941295758036, "learning_rate": 2.487201639704475e-05, "loss": 0.08272761106491089, "step": 828 }, { "epoch": 2.8115449915110355, "grad_norm": 0.16521873437528256, "learning_rate": 2.4744252685383596e-05, "loss": 0.06996961683034897, "step": 829 }, { "epoch": 2.8149405772495757, "grad_norm": 0.1717581921146658, "learning_rate": 2.4616709983058018e-05, "loss": 0.05900315195322037, "step": 830 }, { "epoch": 2.8183361629881154, "grad_norm": 0.19109131158747336, "learning_rate": 2.4489389406175456e-05, "loss": 0.060013480484485626, "step": 831 }, { "epoch": 2.8217317487266556, "grad_norm": 0.18418385938874648, "learning_rate": 2.436229206889962e-05, "loss": 0.08422234654426575, "step": 832 }, { "epoch": 2.8251273344651953, "grad_norm": 0.16152025311107465, "learning_rate": 2.4235419083440613e-05, "loss": 0.1072617620229721, "step": 833 }, { "epoch": 2.828522920203735, "grad_norm": 0.1581850042352063, "learning_rate": 2.4108771560045313e-05, "loss": 0.10338770598173141, "step": 834 }, { "epoch": 2.831918505942275, "grad_norm": 0.18076553217527003, "learning_rate": 2.3982350606987587e-05, "loss": 0.0931280106306076, "step": 835 }, { "epoch": 2.835314091680815, "grad_norm": 0.199349416068342, "learning_rate": 2.3856157330558625e-05, "loss": 0.09144037961959839, "step": 836 }, { "epoch": 2.838709677419355, "grad_norm": 0.18176260212489623, "learning_rate": 2.373019283505727e-05, "loss": 0.07673408091068268, "step": 837 }, { "epoch": 2.8421052631578947, "grad_norm": 0.17076299841509504, "learning_rate": 2.3604458222780313e-05, "loss": 0.06917516887187958, "step": 838 }, { "epoch": 2.8455008488964344, "grad_norm": 0.17587802917477777, "learning_rate": 2.347895459401288e-05, "loss": 0.061953525990247726, "step": 839 }, { "epoch": 2.8488964346349746, "grad_norm": 0.1747281809202088, "learning_rate": 2.33536830470188e-05, "loss": 0.05924539268016815, "step": 840 }, { "epoch": 2.8522920203735147, "grad_norm": 0.18292235651777716, "learning_rate": 2.322864467803097e-05, "loss": 0.11621153354644775, "step": 841 }, { "epoch": 2.8556876061120544, "grad_norm": 0.1634126405611687, "learning_rate": 2.3103840581241808e-05, "loss": 0.10423731058835983, "step": 842 }, { "epoch": 2.859083191850594, "grad_norm": 0.22658741963119602, "learning_rate": 2.2979271848793633e-05, "loss": 0.10128917545080185, "step": 843 }, { "epoch": 2.8624787775891343, "grad_norm": 0.18216549955240002, "learning_rate": 2.2854939570769117e-05, "loss": 0.08610906451940536, "step": 844 }, { "epoch": 2.865874363327674, "grad_norm": 0.17733083133078023, "learning_rate": 2.2730844835181757e-05, "loss": 0.07469803839921951, "step": 845 }, { "epoch": 2.869269949066214, "grad_norm": 0.17137269698796562, "learning_rate": 2.2606988727966393e-05, "loss": 0.06642265617847443, "step": 846 }, { "epoch": 2.872665534804754, "grad_norm": 0.18062817393847994, "learning_rate": 2.248337233296961e-05, "loss": 0.06281661987304688, "step": 847 }, { "epoch": 2.8760611205432935, "grad_norm": 0.16898827482368367, "learning_rate": 2.235999673194035e-05, "loss": 0.05801626294851303, "step": 848 }, { "epoch": 2.8794567062818337, "grad_norm": 0.17620883924221767, "learning_rate": 2.2236863004520326e-05, "loss": 0.10372237861156464, "step": 849 }, { "epoch": 2.8828522920203734, "grad_norm": 0.16858832563264545, "learning_rate": 2.2113972228234737e-05, "loss": 0.10756620764732361, "step": 850 }, { "epoch": 2.8862478777589136, "grad_norm": 0.17128817714866634, "learning_rate": 2.1991325478482694e-05, "loss": 0.09228329360485077, "step": 851 }, { "epoch": 2.8896434634974533, "grad_norm": 0.18428709426585435, "learning_rate": 2.1868923828527933e-05, "loss": 0.08767873048782349, "step": 852 }, { "epoch": 2.893039049235993, "grad_norm": 0.18100073652620724, "learning_rate": 2.1746768349489283e-05, "loss": 0.08027926087379456, "step": 853 }, { "epoch": 2.896434634974533, "grad_norm": 0.17494008713542883, "learning_rate": 2.162486011033142e-05, "loss": 0.07026295363903046, "step": 854 }, { "epoch": 2.8998302207130733, "grad_norm": 0.18172015734223784, "learning_rate": 2.1503200177855426e-05, "loss": 0.06201394647359848, "step": 855 }, { "epoch": 2.903225806451613, "grad_norm": 0.16840073165368433, "learning_rate": 2.1381789616689512e-05, "loss": 0.05623271316289902, "step": 856 }, { "epoch": 2.9066213921901527, "grad_norm": 0.1514570768465516, "learning_rate": 2.126062948927966e-05, "loss": 0.0802827849984169, "step": 857 }, { "epoch": 2.910016977928693, "grad_norm": 0.14914162722812582, "learning_rate": 2.1139720855880357e-05, "loss": 0.10669051110744476, "step": 858 }, { "epoch": 2.9134125636672326, "grad_norm": 0.16979658503662895, "learning_rate": 2.1019064774545282e-05, "loss": 0.09754259884357452, "step": 859 }, { "epoch": 2.9168081494057727, "grad_norm": 0.17890661960964657, "learning_rate": 2.089866230111813e-05, "loss": 0.08932974934577942, "step": 860 }, { "epoch": 2.9202037351443124, "grad_norm": 0.18031604921205213, "learning_rate": 2.0778514489223204e-05, "loss": 0.08105964958667755, "step": 861 }, { "epoch": 2.923599320882852, "grad_norm": 0.15293685962586767, "learning_rate": 2.065862239025639e-05, "loss": 0.0701388269662857, "step": 862 }, { "epoch": 2.9269949066213923, "grad_norm": 0.1602421514778121, "learning_rate": 2.053898705337583e-05, "loss": 0.07826648652553558, "step": 863 }, { "epoch": 2.930390492359932, "grad_norm": 0.17295362203895506, "learning_rate": 2.0419609525492794e-05, "loss": 0.0596000961959362, "step": 864 }, { "epoch": 2.933786078098472, "grad_norm": 0.17603716664188065, "learning_rate": 2.030049085126247e-05, "loss": 0.05892246961593628, "step": 865 }, { "epoch": 2.937181663837012, "grad_norm": 0.18273492035506614, "learning_rate": 2.0181632073074926e-05, "loss": 0.10967177152633667, "step": 866 }, { "epoch": 2.9405772495755516, "grad_norm": 0.14316236955044886, "learning_rate": 2.0063034231045852e-05, "loss": 0.09500811994075775, "step": 867 }, { "epoch": 2.9439728353140917, "grad_norm": 0.16644737673516605, "learning_rate": 1.9944698363007547e-05, "loss": 0.09110953658819199, "step": 868 }, { "epoch": 2.9473684210526314, "grad_norm": 0.19260646627625758, "learning_rate": 1.9826625504499806e-05, "loss": 0.08384446799755096, "step": 869 }, { "epoch": 2.9507640067911716, "grad_norm": 0.1768321044438133, "learning_rate": 1.9708816688760884e-05, "loss": 0.06967946887016296, "step": 870 }, { "epoch": 2.9541595925297113, "grad_norm": 0.15653207349065149, "learning_rate": 1.9591272946718415e-05, "loss": 0.07182908058166504, "step": 871 }, { "epoch": 2.9575551782682514, "grad_norm": 0.15469157410838638, "learning_rate": 1.947399530698043e-05, "loss": 0.05983252078294754, "step": 872 }, { "epoch": 2.960950764006791, "grad_norm": 0.16439766926557692, "learning_rate": 1.9356984795826334e-05, "loss": 0.054759681224823, "step": 873 }, { "epoch": 2.9643463497453313, "grad_norm": 0.17692383944185688, "learning_rate": 1.9240242437197913e-05, "loss": 0.09463880956172943, "step": 874 }, { "epoch": 2.967741935483871, "grad_norm": 0.1745706988367255, "learning_rate": 1.912376925269041e-05, "loss": 0.11154663562774658, "step": 875 }, { "epoch": 2.9711375212224107, "grad_norm": 0.14213415668794782, "learning_rate": 1.9007566261543558e-05, "loss": 0.0895266979932785, "step": 876 }, { "epoch": 2.974533106960951, "grad_norm": 0.15611486978088643, "learning_rate": 1.8891634480632664e-05, "loss": 0.08388682454824448, "step": 877 }, { "epoch": 2.9779286926994906, "grad_norm": 0.1720876778060776, "learning_rate": 1.8775974924459717e-05, "loss": 0.0881383940577507, "step": 878 }, { "epoch": 2.9813242784380307, "grad_norm": 0.17484986338437197, "learning_rate": 1.8660588605144484e-05, "loss": 0.0678919181227684, "step": 879 }, { "epoch": 2.9847198641765704, "grad_norm": 0.16092428869283115, "learning_rate": 1.8545476532415744e-05, "loss": 0.0655856803059578, "step": 880 }, { "epoch": 2.98811544991511, "grad_norm": 0.15814653133003054, "learning_rate": 1.8430639713602316e-05, "loss": 0.05788996070623398, "step": 881 }, { "epoch": 2.9915110356536503, "grad_norm": 0.16003540190417415, "learning_rate": 1.8316079153624355e-05, "loss": 0.08516006171703339, "step": 882 }, { "epoch": 2.99490662139219, "grad_norm": 0.16552096039523276, "learning_rate": 1.820179585498446e-05, "loss": 0.09487900137901306, "step": 883 }, { "epoch": 2.99830220713073, "grad_norm": 0.1512330782478313, "learning_rate": 1.808779081775901e-05, "loss": 0.0681651160120964, "step": 884 }, { "epoch": 3.0, "grad_norm": 0.2023956716474506, "learning_rate": 1.7974065039589333e-05, "loss": 0.05562879145145416, "step": 885 }, { "epoch": 3.0033955857385397, "grad_norm": 0.2287065498286656, "learning_rate": 1.7860619515673033e-05, "loss": 0.0673580914735794, "step": 886 }, { "epoch": 3.00679117147708, "grad_norm": 0.19801683140891588, "learning_rate": 1.7747455238755223e-05, "loss": 0.054912835359573364, "step": 887 }, { "epoch": 3.0101867572156196, "grad_norm": 0.1804627719654919, "learning_rate": 1.7634573199119863e-05, "loss": 0.04442862793803215, "step": 888 }, { "epoch": 3.0135823429541597, "grad_norm": 0.1462685053942342, "learning_rate": 1.7521974384581115e-05, "loss": 0.03634992241859436, "step": 889 }, { "epoch": 3.0169779286926994, "grad_norm": 0.15212781603985104, "learning_rate": 1.740965978047465e-05, "loss": 0.03315172344446182, "step": 890 }, { "epoch": 3.0203735144312396, "grad_norm": 0.14612235534582096, "learning_rate": 1.729763036964909e-05, "loss": 0.02704174816608429, "step": 891 }, { "epoch": 3.0237691001697793, "grad_norm": 0.16708180698747183, "learning_rate": 1.718588713245734e-05, "loss": 0.023155605420470238, "step": 892 }, { "epoch": 3.027164685908319, "grad_norm": 0.17707977078785955, "learning_rate": 1.7074431046748075e-05, "loss": 0.022725418210029602, "step": 893 }, { "epoch": 3.030560271646859, "grad_norm": 0.24737355642448566, "learning_rate": 1.6963263087857123e-05, "loss": 0.05386361479759216, "step": 894 }, { "epoch": 3.033955857385399, "grad_norm": 0.25851001917652455, "learning_rate": 1.6852384228598967e-05, "loss": 0.06401611119508743, "step": 895 }, { "epoch": 3.037351443123939, "grad_norm": 0.16953838249276665, "learning_rate": 1.6741795439258218e-05, "loss": 0.04542354866862297, "step": 896 }, { "epoch": 3.0407470288624787, "grad_norm": 0.15680709701808324, "learning_rate": 1.6631497687581126e-05, "loss": 0.03876464068889618, "step": 897 }, { "epoch": 3.044142614601019, "grad_norm": 0.1621940288708138, "learning_rate": 1.652149193876713e-05, "loss": 0.035458002239465714, "step": 898 }, { "epoch": 3.0475382003395586, "grad_norm": 0.14683841762804328, "learning_rate": 1.641177915546036e-05, "loss": 0.029961001127958298, "step": 899 }, { "epoch": 3.0509337860780983, "grad_norm": 0.14211796748340072, "learning_rate": 1.63023602977413e-05, "loss": 0.026551615446805954, "step": 900 }, { "epoch": 3.0543293718166384, "grad_norm": 0.149015210236981, "learning_rate": 1.6193236323118283e-05, "loss": 0.022327136248350143, "step": 901 }, { "epoch": 3.057724957555178, "grad_norm": 0.15609661806446196, "learning_rate": 1.6084408186519196e-05, "loss": 0.042529694736003876, "step": 902 }, { "epoch": 3.0611205432937183, "grad_norm": 0.1620896759781662, "learning_rate": 1.5975876840283072e-05, "loss": 0.06388020515441895, "step": 903 }, { "epoch": 3.064516129032258, "grad_norm": 0.14592498810532067, "learning_rate": 1.586764323415178e-05, "loss": 0.04957219213247299, "step": 904 }, { "epoch": 3.067911714770798, "grad_norm": 0.14309527473877956, "learning_rate": 1.5759708315261722e-05, "loss": 0.0441456101834774, "step": 905 }, { "epoch": 3.071307300509338, "grad_norm": 0.15003916164280975, "learning_rate": 1.5652073028135512e-05, "loss": 0.036236342042684555, "step": 906 }, { "epoch": 3.0747028862478776, "grad_norm": 0.16449819690771467, "learning_rate": 1.5544738314673747e-05, "loss": 0.03265400975942612, "step": 907 }, { "epoch": 3.0780984719864177, "grad_norm": 0.1429571587195673, "learning_rate": 1.5437705114146733e-05, "loss": 0.026175139471888542, "step": 908 }, { "epoch": 3.0814940577249574, "grad_norm": 0.12972515361377904, "learning_rate": 1.533097436318629e-05, "loss": 0.021192245185375214, "step": 909 }, { "epoch": 3.0848896434634976, "grad_norm": 0.14840787839680314, "learning_rate": 1.5224546995777549e-05, "loss": 0.024942472577095032, "step": 910 }, { "epoch": 3.0882852292020373, "grad_norm": 0.17581008918751306, "learning_rate": 1.5118423943250771e-05, "loss": 0.05906528979539871, "step": 911 }, { "epoch": 3.0916808149405774, "grad_norm": 0.17116495728343437, "learning_rate": 1.5012606134273205e-05, "loss": 0.04865565896034241, "step": 912 }, { "epoch": 3.095076400679117, "grad_norm": 0.15065942549132996, "learning_rate": 1.4907094494840929e-05, "loss": 0.037569206207990646, "step": 913 }, { "epoch": 3.098471986417657, "grad_norm": 0.14214807516551503, "learning_rate": 1.4801889948270853e-05, "loss": 0.03742380440235138, "step": 914 }, { "epoch": 3.101867572156197, "grad_norm": 0.1351709361847205, "learning_rate": 1.4696993415192484e-05, "loss": 0.02953353524208069, "step": 915 }, { "epoch": 3.1052631578947367, "grad_norm": 0.13129711910200692, "learning_rate": 1.4592405813539994e-05, "loss": 0.025264710187911987, "step": 916 }, { "epoch": 3.108658743633277, "grad_norm": 0.13223314573246042, "learning_rate": 1.4488128058544098e-05, "loss": 0.02316337451338768, "step": 917 }, { "epoch": 3.1120543293718166, "grad_norm": 0.12265048431079878, "learning_rate": 1.4384161062724133e-05, "loss": 0.019381247460842133, "step": 918 }, { "epoch": 3.1154499151103567, "grad_norm": 0.1397371448078249, "learning_rate": 1.428050573587999e-05, "loss": 0.05059080570936203, "step": 919 }, { "epoch": 3.1188455008488964, "grad_norm": 0.1358877403164227, "learning_rate": 1.4177162985084242e-05, "loss": 0.051333390176296234, "step": 920 }, { "epoch": 3.122241086587436, "grad_norm": 0.1358772433009525, "learning_rate": 1.4074133714674115e-05, "loss": 0.04799500107765198, "step": 921 }, { "epoch": 3.1256366723259763, "grad_norm": 0.1443040636807733, "learning_rate": 1.397141882624361e-05, "loss": 0.040485985577106476, "step": 922 }, { "epoch": 3.129032258064516, "grad_norm": 0.13203923626535163, "learning_rate": 1.3869019218635642e-05, "loss": 0.03332916274666786, "step": 923 }, { "epoch": 3.132427843803056, "grad_norm": 0.12700180572450606, "learning_rate": 1.3766935787934138e-05, "loss": 0.04002326726913452, "step": 924 }, { "epoch": 3.135823429541596, "grad_norm": 0.12967867811755004, "learning_rate": 1.3665169427456203e-05, "loss": 0.02388843521475792, "step": 925 }, { "epoch": 3.139219015280136, "grad_norm": 0.12338238118295694, "learning_rate": 1.3563721027744308e-05, "loss": 0.021195849403738976, "step": 926 }, { "epoch": 3.1426146010186757, "grad_norm": 0.16027197859587844, "learning_rate": 1.3462591476558511e-05, "loss": 0.04306637868285179, "step": 927 }, { "epoch": 3.1460101867572154, "grad_norm": 0.14360457403226243, "learning_rate": 1.336178165886865e-05, "loss": 0.053870104253292084, "step": 928 }, { "epoch": 3.1494057724957556, "grad_norm": 0.1311026593349651, "learning_rate": 1.3261292456846647e-05, "loss": 0.04142114520072937, "step": 929 }, { "epoch": 3.1528013582342953, "grad_norm": 0.13679382977814183, "learning_rate": 1.3161124749858738e-05, "loss": 0.04224657267332077, "step": 930 }, { "epoch": 3.1561969439728355, "grad_norm": 0.1395144754999581, "learning_rate": 1.3061279414457823e-05, "loss": 0.03984564542770386, "step": 931 }, { "epoch": 3.159592529711375, "grad_norm": 0.12178551924012121, "learning_rate": 1.2961757324375767e-05, "loss": 0.02691613882780075, "step": 932 }, { "epoch": 3.1629881154499153, "grad_norm": 0.1231562597300068, "learning_rate": 1.2862559350515746e-05, "loss": 0.0235055573284626, "step": 933 }, { "epoch": 3.166383701188455, "grad_norm": 0.12803697239446835, "learning_rate": 1.27636863609447e-05, "loss": 0.02205159328877926, "step": 934 }, { "epoch": 3.1697792869269947, "grad_norm": 0.13838654960788713, "learning_rate": 1.2665139220885613e-05, "loss": 0.024279549717903137, "step": 935 }, { "epoch": 3.173174872665535, "grad_norm": 0.1338553286408259, "learning_rate": 1.2566918792710042e-05, "loss": 0.05706634745001793, "step": 936 }, { "epoch": 3.1765704584040746, "grad_norm": 0.13429355262448361, "learning_rate": 1.2469025935930523e-05, "loss": 0.049813997000455856, "step": 937 }, { "epoch": 3.1799660441426147, "grad_norm": 0.13391151766003662, "learning_rate": 1.2371461507193078e-05, "loss": 0.04218004643917084, "step": 938 }, { "epoch": 3.1833616298811545, "grad_norm": 0.1302496712699556, "learning_rate": 1.2274226360269687e-05, "loss": 0.03302651271224022, "step": 939 }, { "epoch": 3.1867572156196946, "grad_norm": 0.13411284848375005, "learning_rate": 1.2177321346050835e-05, "loss": 0.030225880444049835, "step": 940 }, { "epoch": 3.1901528013582343, "grad_norm": 0.12090778410730388, "learning_rate": 1.2080747312538083e-05, "loss": 0.023621803149580956, "step": 941 }, { "epoch": 3.193548387096774, "grad_norm": 0.12191916953108109, "learning_rate": 1.1984505104836608e-05, "loss": 0.02137250266969204, "step": 942 }, { "epoch": 3.196943972835314, "grad_norm": 0.12044582203569461, "learning_rate": 1.1888595565147836e-05, "loss": 0.019377615302801132, "step": 943 }, { "epoch": 3.200339558573854, "grad_norm": 0.13238834380027187, "learning_rate": 1.1793019532762056e-05, "loss": 0.05031951889395714, "step": 944 }, { "epoch": 3.203735144312394, "grad_norm": 0.13290375068005594, "learning_rate": 1.1697777844051105e-05, "loss": 0.05532939359545708, "step": 945 }, { "epoch": 3.2071307300509337, "grad_norm": 0.12575324429533835, "learning_rate": 1.1602871332461002e-05, "loss": 0.040702566504478455, "step": 946 }, { "epoch": 3.2105263157894735, "grad_norm": 0.13163786886014323, "learning_rate": 1.150830082850468e-05, "loss": 0.041564490646123886, "step": 947 }, { "epoch": 3.2139219015280136, "grad_norm": 0.13429807100273985, "learning_rate": 1.141406715975476e-05, "loss": 0.03210339695215225, "step": 948 }, { "epoch": 3.2173174872665533, "grad_norm": 0.12825741869075025, "learning_rate": 1.1320171150836228e-05, "loss": 0.028910160064697266, "step": 949 }, { "epoch": 3.2207130730050935, "grad_norm": 0.11583113320386382, "learning_rate": 1.1226613623419269e-05, "loss": 0.021669626235961914, "step": 950 }, { "epoch": 3.224108658743633, "grad_norm": 0.12325145469098292, "learning_rate": 1.1133395396212049e-05, "loss": 0.02199777215719223, "step": 951 }, { "epoch": 3.2275042444821733, "grad_norm": 0.11840404330072238, "learning_rate": 1.1040517284953595e-05, "loss": 0.03625570982694626, "step": 952 }, { "epoch": 3.230899830220713, "grad_norm": 0.14307664119726513, "learning_rate": 1.0947980102406596e-05, "loss": 0.061830319464206696, "step": 953 }, { "epoch": 3.234295415959253, "grad_norm": 0.1312695445643524, "learning_rate": 1.0855784658350388e-05, "loss": 0.044841524213552475, "step": 954 }, { "epoch": 3.237691001697793, "grad_norm": 0.1198362828943224, "learning_rate": 1.0763931759573736e-05, "loss": 0.03786482661962509, "step": 955 }, { "epoch": 3.2410865874363326, "grad_norm": 0.13118645874481558, "learning_rate": 1.0672422209867878e-05, "loss": 0.03329238295555115, "step": 956 }, { "epoch": 3.2444821731748728, "grad_norm": 0.11849860372189018, "learning_rate": 1.0581256810019435e-05, "loss": 0.02538839727640152, "step": 957 }, { "epoch": 3.2478777589134125, "grad_norm": 0.12286527056099193, "learning_rate": 1.0490436357803435e-05, "loss": 0.025109291076660156, "step": 958 }, { "epoch": 3.2512733446519526, "grad_norm": 0.12357068323490371, "learning_rate": 1.0399961647976314e-05, "loss": 0.021655848249793053, "step": 959 }, { "epoch": 3.2546689303904923, "grad_norm": 0.15652966783482694, "learning_rate": 1.0309833472268976e-05, "loss": 0.024202316999435425, "step": 960 }, { "epoch": 3.258064516129032, "grad_norm": 0.11508594625250927, "learning_rate": 1.0220052619379843e-05, "loss": 0.052302829921245575, "step": 961 }, { "epoch": 3.261460101867572, "grad_norm": 0.12670651189730398, "learning_rate": 1.0130619874967983e-05, "loss": 0.048711176961660385, "step": 962 }, { "epoch": 3.264855687606112, "grad_norm": 0.12775460939273364, "learning_rate": 1.0041536021646204e-05, "loss": 0.0423329696059227, "step": 963 }, { "epoch": 3.268251273344652, "grad_norm": 0.12612617238345966, "learning_rate": 9.952801838974213e-06, "loss": 0.03406022489070892, "step": 964 }, { "epoch": 3.2716468590831917, "grad_norm": 0.12438145630992371, "learning_rate": 9.864418103451828e-06, "loss": 0.029523154720664024, "step": 965 }, { "epoch": 3.275042444821732, "grad_norm": 0.12328410442355167, "learning_rate": 9.776385588512121e-06, "loss": 0.02632921002805233, "step": 966 }, { "epoch": 3.2784380305602716, "grad_norm": 0.12230539281907025, "learning_rate": 9.688705064514703e-06, "loss": 0.02133692428469658, "step": 967 }, { "epoch": 3.2818336162988118, "grad_norm": 0.12410610690728713, "learning_rate": 9.601377298738977e-06, "loss": 0.01997721940279007, "step": 968 }, { "epoch": 3.2852292020373515, "grad_norm": 0.14392976845115754, "learning_rate": 9.514403055377386e-06, "loss": 0.05067284032702446, "step": 969 }, { "epoch": 3.288624787775891, "grad_norm": 0.13594754613361928, "learning_rate": 9.427783095528769e-06, "loss": 0.05785913020372391, "step": 970 }, { "epoch": 3.2920203735144313, "grad_norm": 0.12834590778573052, "learning_rate": 9.34151817719166e-06, "loss": 0.04777633398771286, "step": 971 }, { "epoch": 3.295415959252971, "grad_norm": 0.12623944849599206, "learning_rate": 9.255609055257713e-06, "loss": 0.038534604012966156, "step": 972 }, { "epoch": 3.298811544991511, "grad_norm": 0.1259826025384117, "learning_rate": 9.170056481504996e-06, "loss": 0.03242049366235733, "step": 973 }, { "epoch": 3.302207130730051, "grad_norm": 0.1221700934965317, "learning_rate": 9.084861204591549e-06, "loss": 0.027944771572947502, "step": 974 }, { "epoch": 3.3056027164685906, "grad_norm": 0.11491942560681297, "learning_rate": 9.000023970048726e-06, "loss": 0.022624008357524872, "step": 975 }, { "epoch": 3.3089983022071308, "grad_norm": 0.12332549902865371, "learning_rate": 8.915545520274698e-06, "loss": 0.021190008148550987, "step": 976 }, { "epoch": 3.3123938879456705, "grad_norm": 0.13636166486606488, "learning_rate": 8.831426594527975e-06, "loss": 0.03924716264009476, "step": 977 }, { "epoch": 3.3157894736842106, "grad_norm": 0.138797664924497, "learning_rate": 8.747667928920927e-06, "loss": 0.0606057271361351, "step": 978 }, { "epoch": 3.3191850594227503, "grad_norm": 0.12461083880660333, "learning_rate": 8.664270256413332e-06, "loss": 0.04649470001459122, "step": 979 }, { "epoch": 3.3225806451612905, "grad_norm": 0.1329552982261501, "learning_rate": 8.581234306805969e-06, "loss": 0.048369601368904114, "step": 980 }, { "epoch": 3.32597623089983, "grad_norm": 0.1280609732216262, "learning_rate": 8.498560806734229e-06, "loss": 0.03547901660203934, "step": 981 }, { "epoch": 3.3293718166383703, "grad_norm": 0.1186110736793347, "learning_rate": 8.416250479661803e-06, "loss": 0.03008534386754036, "step": 982 }, { "epoch": 3.33276740237691, "grad_norm": 0.12004796273708981, "learning_rate": 8.334304045874247e-06, "loss": 0.02395748905837536, "step": 983 }, { "epoch": 3.3361629881154498, "grad_norm": 0.11289648473423446, "learning_rate": 8.252722222472792e-06, "loss": 0.020507005974650383, "step": 984 }, { "epoch": 3.33955857385399, "grad_norm": 0.12645272151847867, "learning_rate": 8.171505723367961e-06, "loss": 0.021873991936445236, "step": 985 }, { "epoch": 3.3429541595925296, "grad_norm": 0.1229970020521114, "learning_rate": 8.090655259273428e-06, "loss": 0.054312169551849365, "step": 986 }, { "epoch": 3.3463497453310698, "grad_norm": 0.12456309550037527, "learning_rate": 8.010171537699712e-06, "loss": 0.051031019538640976, "step": 987 }, { "epoch": 3.3497453310696095, "grad_norm": 0.12874216817605386, "learning_rate": 7.930055262948072e-06, "loss": 0.04110771045088768, "step": 988 }, { "epoch": 3.353140916808149, "grad_norm": 0.12183387715821775, "learning_rate": 7.850307136104247e-06, "loss": 0.03764788806438446, "step": 989 }, { "epoch": 3.3565365025466893, "grad_norm": 0.12394364871674748, "learning_rate": 7.770927855032378e-06, "loss": 0.029466327279806137, "step": 990 }, { "epoch": 3.359932088285229, "grad_norm": 0.11542801993611722, "learning_rate": 7.691918114368907e-06, "loss": 0.023005565628409386, "step": 991 }, { "epoch": 3.363327674023769, "grad_norm": 0.11914954702312376, "learning_rate": 7.613278605516455e-06, "loss": 0.022195864468812943, "step": 992 }, { "epoch": 3.366723259762309, "grad_norm": 0.11872845223975578, "learning_rate": 7.535010016637828e-06, "loss": 0.021608486771583557, "step": 993 }, { "epoch": 3.370118845500849, "grad_norm": 0.12579123531625508, "learning_rate": 7.457113032649943e-06, "loss": 0.0499873161315918, "step": 994 }, { "epoch": 3.3735144312393888, "grad_norm": 0.12301506714902506, "learning_rate": 7.379588335217874e-06, "loss": 0.05264587327837944, "step": 995 }, { "epoch": 3.376910016977929, "grad_norm": 0.1253271954708119, "learning_rate": 7.302436602748864e-06, "loss": 0.0403154194355011, "step": 996 }, { "epoch": 3.3803056027164686, "grad_norm": 0.12579321355529954, "learning_rate": 7.225658510386385e-06, "loss": 0.03427085652947426, "step": 997 }, { "epoch": 3.3837011884550083, "grad_norm": 0.12422955087022457, "learning_rate": 7.1492547300042455e-06, "loss": 0.03029695712029934, "step": 998 }, { "epoch": 3.3870967741935485, "grad_norm": 0.11958994199608736, "learning_rate": 7.073225930200722e-06, "loss": 0.025695830583572388, "step": 999 }, { "epoch": 3.390492359932088, "grad_norm": 0.11256893738827631, "learning_rate": 6.99757277629266e-06, "loss": 0.022229617461562157, "step": 1000 }, { "epoch": 3.3938879456706283, "grad_norm": 0.11933399286318758, "learning_rate": 6.922295930309691e-06, "loss": 0.01890420913696289, "step": 1001 }, { "epoch": 3.397283531409168, "grad_norm": 0.14075818340504395, "learning_rate": 6.847396050988469e-06, "loss": 0.042036961764097214, "step": 1002 }, { "epoch": 3.4006791171477078, "grad_norm": 0.13882620104279927, "learning_rate": 6.772873793766815e-06, "loss": 0.05907998979091644, "step": 1003 }, { "epoch": 3.404074702886248, "grad_norm": 0.12180948896211187, "learning_rate": 6.698729810778065e-06, "loss": 0.04251595586538315, "step": 1004 }, { "epoch": 3.4074702886247876, "grad_norm": 0.12841680715346554, "learning_rate": 6.624964750845325e-06, "loss": 0.037187762558460236, "step": 1005 }, { "epoch": 3.4108658743633278, "grad_norm": 0.12421524114555775, "learning_rate": 6.551579259475809e-06, "loss": 0.03140611574053764, "step": 1006 }, { "epoch": 3.4142614601018675, "grad_norm": 0.13023205267528695, "learning_rate": 6.478573978855146e-06, "loss": 0.026064341887831688, "step": 1007 }, { "epoch": 3.4176570458404076, "grad_norm": 0.11587019883038634, "learning_rate": 6.405949547841849e-06, "loss": 0.02195816859602928, "step": 1008 }, { "epoch": 3.4210526315789473, "grad_norm": 0.11305852845312694, "learning_rate": 6.333706601961642e-06, "loss": 0.018451834097504616, "step": 1009 }, { "epoch": 3.4244482173174875, "grad_norm": 0.12394852802561025, "learning_rate": 6.2618457734019364e-06, "loss": 0.021571999415755272, "step": 1010 }, { "epoch": 3.427843803056027, "grad_norm": 0.12422171528354305, "learning_rate": 6.190367691006288e-06, "loss": 0.05437242239713669, "step": 1011 }, { "epoch": 3.431239388794567, "grad_norm": 0.13277863812978483, "learning_rate": 6.119272980268897e-06, "loss": 0.05201639235019684, "step": 1012 }, { "epoch": 3.434634974533107, "grad_norm": 0.12034323718654945, "learning_rate": 6.048562263329138e-06, "loss": 0.03945009037852287, "step": 1013 }, { "epoch": 3.4380305602716468, "grad_norm": 0.11821264782256398, "learning_rate": 5.978236158966105e-06, "loss": 0.034029774367809296, "step": 1014 }, { "epoch": 3.441426146010187, "grad_norm": 0.1318913719285147, "learning_rate": 5.908295282593207e-06, "loss": 0.030163567513227463, "step": 1015 }, { "epoch": 3.4448217317487266, "grad_norm": 0.12103176990126512, "learning_rate": 5.838740246252794e-06, "loss": 0.025972014293074608, "step": 1016 }, { "epoch": 3.4482173174872663, "grad_norm": 0.11758154061366656, "learning_rate": 5.769571658610762e-06, "loss": 0.02163957618176937, "step": 1017 }, { "epoch": 3.4516129032258065, "grad_norm": 0.11320580344258656, "learning_rate": 5.700790124951283e-06, "loss": 0.017679382115602493, "step": 1018 }, { "epoch": 3.455008488964346, "grad_norm": 0.12636765690680088, "learning_rate": 5.6323962471714286e-06, "loss": 0.04990405589342117, "step": 1019 }, { "epoch": 3.4584040747028864, "grad_norm": 0.12253748224862382, "learning_rate": 5.564390623775995e-06, "loss": 0.05478016659617424, "step": 1020 }, { "epoch": 3.461799660441426, "grad_norm": 0.11741379227005212, "learning_rate": 5.496773849872183e-06, "loss": 0.04403357952833176, "step": 1021 }, { "epoch": 3.465195246179966, "grad_norm": 0.12462760394568805, "learning_rate": 5.429546517164486e-06, "loss": 0.03723139688372612, "step": 1022 }, { "epoch": 3.468590831918506, "grad_norm": 0.11889623953373125, "learning_rate": 5.362709213949396e-06, "loss": 0.03130408003926277, "step": 1023 }, { "epoch": 3.471986417657046, "grad_norm": 0.1165830127245237, "learning_rate": 5.296262525110346e-06, "loss": 0.025761296972632408, "step": 1024 }, { "epoch": 3.475382003395586, "grad_norm": 0.11933954874173557, "learning_rate": 5.23020703211255e-06, "loss": 0.024434616789221764, "step": 1025 }, { "epoch": 3.4787775891341255, "grad_norm": 0.12182070855215353, "learning_rate": 5.1645433129979215e-06, "loss": 0.02007797360420227, "step": 1026 }, { "epoch": 3.4821731748726656, "grad_norm": 0.13979685734616396, "learning_rate": 5.0992719423800236e-06, "loss": 0.041598979383707047, "step": 1027 }, { "epoch": 3.4855687606112054, "grad_norm": 0.12407163023629854, "learning_rate": 5.034393491439043e-06, "loss": 0.05767684429883957, "step": 1028 }, { "epoch": 3.4889643463497455, "grad_norm": 0.12420571483623782, "learning_rate": 4.969908527916766e-06, "loss": 0.04558452218770981, "step": 1029 }, { "epoch": 3.492359932088285, "grad_norm": 0.12127161903962408, "learning_rate": 4.905817616111641e-06, "loss": 0.040574293583631516, "step": 1030 }, { "epoch": 3.495755517826825, "grad_norm": 0.1257340537429782, "learning_rate": 4.842121316873821e-06, "loss": 0.033539630472660065, "step": 1031 }, { "epoch": 3.499151103565365, "grad_norm": 0.12458790628552394, "learning_rate": 4.778820187600275e-06, "loss": 0.026948917657136917, "step": 1032 }, { "epoch": 3.502546689303905, "grad_norm": 0.1175504061592978, "learning_rate": 4.71591478222988e-06, "loss": 0.0230097658932209, "step": 1033 }, { "epoch": 3.505942275042445, "grad_norm": 0.11685318302170783, "learning_rate": 4.653405651238607e-06, "loss": 0.019026953727006912, "step": 1034 }, { "epoch": 3.5093378607809846, "grad_norm": 0.128477854704914, "learning_rate": 4.591293341634661e-06, "loss": 0.02308005653321743, "step": 1035 }, { "epoch": 3.5127334465195243, "grad_norm": 0.11780690824100111, "learning_rate": 4.529578396953771e-06, "loss": 0.05882404372096062, "step": 1036 }, { "epoch": 3.5161290322580645, "grad_norm": 0.12890218598426142, "learning_rate": 4.468261357254339e-06, "loss": 0.049779534339904785, "step": 1037 }, { "epoch": 3.5195246179966047, "grad_norm": 0.11889542512731646, "learning_rate": 4.407342759112776e-06, "loss": 0.03601907566189766, "step": 1038 }, { "epoch": 3.5229202037351444, "grad_norm": 0.11650917944581349, "learning_rate": 4.346823135618788e-06, "loss": 0.03361005708575249, "step": 1039 }, { "epoch": 3.526315789473684, "grad_norm": 0.12301107714897029, "learning_rate": 4.286703016370719e-06, "loss": 0.029762055724859238, "step": 1040 }, { "epoch": 3.5297113752122242, "grad_norm": 0.12726738060722753, "learning_rate": 4.226982927470874e-06, "loss": 0.02579472027719021, "step": 1041 }, { "epoch": 3.533106960950764, "grad_norm": 0.12046993408334836, "learning_rate": 4.167663391521015e-06, "loss": 0.020228728652000427, "step": 1042 }, { "epoch": 3.536502546689304, "grad_norm": 0.12863831226505196, "learning_rate": 4.108744927617669e-06, "loss": 0.019604738801717758, "step": 1043 }, { "epoch": 3.539898132427844, "grad_norm": 0.12133107458973948, "learning_rate": 4.050228051347671e-06, "loss": 0.04686151444911957, "step": 1044 }, { "epoch": 3.5432937181663835, "grad_norm": 0.12428805894218747, "learning_rate": 3.99211327478361e-06, "loss": 0.0543304905295372, "step": 1045 }, { "epoch": 3.5466893039049237, "grad_norm": 0.1216084778191569, "learning_rate": 3.9344011064793516e-06, "loss": 0.04142393916845322, "step": 1046 }, { "epoch": 3.5500848896434634, "grad_norm": 0.1214602412938836, "learning_rate": 3.877092051465614e-06, "loss": 0.03393886238336563, "step": 1047 }, { "epoch": 3.5534804753820035, "grad_norm": 0.11791697265301797, "learning_rate": 3.8201866112455185e-06, "loss": 0.030113479122519493, "step": 1048 }, { "epoch": 3.556876061120543, "grad_norm": 0.11514449648738104, "learning_rate": 3.763685283790208e-06, "loss": 0.024684980511665344, "step": 1049 }, { "epoch": 3.560271646859083, "grad_norm": 0.11861405039273788, "learning_rate": 3.707588563534514e-06, "loss": 0.022464102134108543, "step": 1050 }, { "epoch": 3.563667232597623, "grad_norm": 0.11720193875426402, "learning_rate": 3.6518969413725903e-06, "loss": 0.017372405156493187, "step": 1051 }, { "epoch": 3.5670628183361632, "grad_norm": 0.15002543714927977, "learning_rate": 3.596610904653652e-06, "loss": 0.03922034800052643, "step": 1052 }, { "epoch": 3.570458404074703, "grad_norm": 0.12325872182269806, "learning_rate": 3.5417309371776675e-06, "loss": 0.05485820025205612, "step": 1053 }, { "epoch": 3.5738539898132426, "grad_norm": 0.12523315400110815, "learning_rate": 3.4872575191911895e-06, "loss": 0.04063337296247482, "step": 1054 }, { "epoch": 3.577249575551783, "grad_norm": 0.11878954410433114, "learning_rate": 3.4331911273830784e-06, "loss": 0.035744693130254745, "step": 1055 }, { "epoch": 3.5806451612903225, "grad_norm": 0.1213977935936, "learning_rate": 3.3795322348804114e-06, "loss": 0.0327204205095768, "step": 1056 }, { "epoch": 3.5840407470288627, "grad_norm": 0.11548969778292585, "learning_rate": 3.326281311244267e-06, "loss": 0.028406118974089622, "step": 1057 }, { "epoch": 3.5874363327674024, "grad_norm": 0.12368778426006656, "learning_rate": 3.2734388224656575e-06, "loss": 0.022378256544470787, "step": 1058 }, { "epoch": 3.590831918505942, "grad_norm": 0.11425562028012727, "learning_rate": 3.2210052309614437e-06, "loss": 0.01868167705833912, "step": 1059 }, { "epoch": 3.5942275042444822, "grad_norm": 0.12660248343160396, "learning_rate": 3.1689809955702754e-06, "loss": 0.023598134517669678, "step": 1060 }, { "epoch": 3.597623089983022, "grad_norm": 1.2571829260844976, "learning_rate": 3.117366571548608e-06, "loss": 0.05531495064496994, "step": 1061 }, { "epoch": 3.601018675721562, "grad_norm": 0.1256764519838915, "learning_rate": 3.066162410566681e-06, "loss": 0.04982135817408562, "step": 1062 }, { "epoch": 3.604414261460102, "grad_norm": 0.11598061576796644, "learning_rate": 3.0153689607045845e-06, "loss": 0.034899309277534485, "step": 1063 }, { "epoch": 3.6078098471986415, "grad_norm": 0.12349487692552429, "learning_rate": 2.9649866664483385e-06, "loss": 0.03358934819698334, "step": 1064 }, { "epoch": 3.6112054329371817, "grad_norm": 0.12432375629970736, "learning_rate": 2.915015968686002e-06, "loss": 0.028581634163856506, "step": 1065 }, { "epoch": 3.614601018675722, "grad_norm": 0.1195457682187301, "learning_rate": 2.865457304703817e-06, "loss": 0.02503875456750393, "step": 1066 }, { "epoch": 3.6179966044142615, "grad_norm": 0.11259288466297206, "learning_rate": 2.816311108182368e-06, "loss": 0.019195111468434334, "step": 1067 }, { "epoch": 3.6213921901528012, "grad_norm": 0.11934329519302062, "learning_rate": 2.767577809192806e-06, "loss": 0.017958905547857285, "step": 1068 }, { "epoch": 3.6247877758913414, "grad_norm": 0.11819251946821233, "learning_rate": 2.7192578341930618e-06, "loss": 0.045885052531957626, "step": 1069 }, { "epoch": 3.628183361629881, "grad_norm": 0.13626145452527538, "learning_rate": 2.6713516060241527e-06, "loss": 0.06239771097898483, "step": 1070 }, { "epoch": 3.6315789473684212, "grad_norm": 0.12101513885839696, "learning_rate": 2.6238595439064484e-06, "loss": 0.042742691934108734, "step": 1071 }, { "epoch": 3.634974533106961, "grad_norm": 0.12439151070871296, "learning_rate": 2.5767820634360008e-06, "loss": 0.03938419371843338, "step": 1072 }, { "epoch": 3.6383701188455007, "grad_norm": 0.12325651142188807, "learning_rate": 2.530119576580936e-06, "loss": 0.03136751428246498, "step": 1073 }, { "epoch": 3.641765704584041, "grad_norm": 0.11640013428729339, "learning_rate": 2.483872491677819e-06, "loss": 0.027267418801784515, "step": 1074 }, { "epoch": 3.6451612903225805, "grad_norm": 0.11644777240004063, "learning_rate": 2.4380412134280884e-06, "loss": 0.02183561585843563, "step": 1075 }, { "epoch": 3.6485568760611207, "grad_norm": 0.11045905631252374, "learning_rate": 2.3926261428945383e-06, "loss": 0.019022442400455475, "step": 1076 }, { "epoch": 3.6519524617996604, "grad_norm": 0.13542460116667632, "learning_rate": 2.347627677497788e-06, "loss": 0.040305063128471375, "step": 1077 }, { "epoch": 3.6553480475382, "grad_norm": 0.12461058265011736, "learning_rate": 2.303046211012783e-06, "loss": 0.05720077082514763, "step": 1078 }, { "epoch": 3.6587436332767402, "grad_norm": 0.12029995471106943, "learning_rate": 2.258882133565404e-06, "loss": 0.042141806334257126, "step": 1079 }, { "epoch": 3.6621392190152804, "grad_norm": 0.12196288904810622, "learning_rate": 2.2151358316290006e-06, "loss": 0.03805346414446831, "step": 1080 }, { "epoch": 3.66553480475382, "grad_norm": 0.12652976069251184, "learning_rate": 2.1718076880210327e-06, "loss": 0.028709007427096367, "step": 1081 }, { "epoch": 3.66893039049236, "grad_norm": 0.11917535258555677, "learning_rate": 2.1288980818997275e-06, "loss": 0.02676650509238243, "step": 1082 }, { "epoch": 3.6723259762309, "grad_norm": 0.11521174314624066, "learning_rate": 2.0864073887607416e-06, "loss": 0.021988656371831894, "step": 1083 }, { "epoch": 3.6757215619694397, "grad_norm": 0.10876110623427103, "learning_rate": 2.0443359804338923e-06, "loss": 0.017682846635580063, "step": 1084 }, { "epoch": 3.67911714770798, "grad_norm": 0.12894264325802585, "learning_rate": 2.0026842250799038e-06, "loss": 0.02302953228354454, "step": 1085 }, { "epoch": 3.6825127334465195, "grad_norm": 0.11746141927658608, "learning_rate": 1.9614524871871544e-06, "loss": 0.05681226775050163, "step": 1086 }, { "epoch": 3.6859083191850592, "grad_norm": 0.11995551977691109, "learning_rate": 1.92064112756854e-06, "loss": 0.0456516370177269, "step": 1087 }, { "epoch": 3.6893039049235994, "grad_norm": 0.11692173663987014, "learning_rate": 1.8802505033582608e-06, "loss": 0.03863770514726639, "step": 1088 }, { "epoch": 3.692699490662139, "grad_norm": 0.11837029712751351, "learning_rate": 1.8402809680087452e-06, "loss": 0.03486296162009239, "step": 1089 }, { "epoch": 3.6960950764006792, "grad_norm": 0.11937441312126953, "learning_rate": 1.8007328712875305e-06, "loss": 0.02674887701869011, "step": 1090 }, { "epoch": 3.699490662139219, "grad_norm": 0.11575112269014678, "learning_rate": 1.7616065592742038e-06, "loss": 0.022751905024051666, "step": 1091 }, { "epoch": 3.7028862478777587, "grad_norm": 0.11277104529976778, "learning_rate": 1.7229023743573657e-06, "loss": 0.023014364764094353, "step": 1092 }, { "epoch": 3.706281833616299, "grad_norm": 0.1162901056676442, "learning_rate": 1.6846206552316612e-06, "loss": 0.018410202115774155, "step": 1093 }, { "epoch": 3.709677419354839, "grad_norm": 0.12619695937616396, "learning_rate": 1.6467617368947918e-06, "loss": 0.05249921604990959, "step": 1094 }, { "epoch": 3.7130730050933787, "grad_norm": 0.12649403517172286, "learning_rate": 1.6093259506445913e-06, "loss": 0.05118681490421295, "step": 1095 }, { "epoch": 3.7164685908319184, "grad_norm": 0.1228822707555336, "learning_rate": 1.5723136240761271e-06, "loss": 0.04066997021436691, "step": 1096 }, { "epoch": 3.7198641765704585, "grad_norm": 0.12250051954952695, "learning_rate": 1.5357250810788314e-06, "loss": 0.03652298450469971, "step": 1097 }, { "epoch": 3.7232597623089982, "grad_norm": 0.11612374431874883, "learning_rate": 1.4995606418336694e-06, "loss": 0.02981790155172348, "step": 1098 }, { "epoch": 3.7266553480475384, "grad_norm": 0.1234081055270492, "learning_rate": 1.4638206228103413e-06, "loss": 0.02735557220876217, "step": 1099 }, { "epoch": 3.730050933786078, "grad_norm": 0.11780518710981902, "learning_rate": 1.4285053367645074e-06, "loss": 0.031158095225691795, "step": 1100 }, { "epoch": 3.733446519524618, "grad_norm": 0.10783535773913047, "learning_rate": 1.39361509273504e-06, "loss": 0.017439626157283783, "step": 1101 }, { "epoch": 3.736842105263158, "grad_norm": 0.13414590375691468, "learning_rate": 1.3591501960413422e-06, "loss": 0.041479066014289856, "step": 1102 }, { "epoch": 3.7402376910016977, "grad_norm": 0.12218321366487778, "learning_rate": 1.3251109482806666e-06, "loss": 0.05795469880104065, "step": 1103 }, { "epoch": 3.743633276740238, "grad_norm": 0.11767108019750067, "learning_rate": 1.2914976473254793e-06, "loss": 0.04435582086443901, "step": 1104 }, { "epoch": 3.7470288624787775, "grad_norm": 0.12349053656714071, "learning_rate": 1.2583105873208267e-06, "loss": 0.04039248079061508, "step": 1105 }, { "epoch": 3.7504244482173172, "grad_norm": 0.12860465722165068, "learning_rate": 1.2255500586818014e-06, "loss": 0.030748805031180382, "step": 1106 }, { "epoch": 3.7538200339558574, "grad_norm": 0.11888642683107663, "learning_rate": 1.1932163480909865e-06, "loss": 0.02776479534804821, "step": 1107 }, { "epoch": 3.7572156196943975, "grad_norm": 0.12224822062292823, "learning_rate": 1.1613097384959248e-06, "loss": 0.02215997874736786, "step": 1108 }, { "epoch": 3.7606112054329373, "grad_norm": 0.11428355963276188, "learning_rate": 1.1298305091066664e-06, "loss": 0.02009144052863121, "step": 1109 }, { "epoch": 3.764006791171477, "grad_norm": 0.12435215008514583, "learning_rate": 1.0987789353933408e-06, "loss": 0.022261163219809532, "step": 1110 }, { "epoch": 3.767402376910017, "grad_norm": 0.11795084302715504, "learning_rate": 1.0681552890836944e-06, "loss": 0.05920621007680893, "step": 1111 }, { "epoch": 3.770797962648557, "grad_norm": 0.12049029743831541, "learning_rate": 1.037959838160768e-06, "loss": 0.05087507888674736, "step": 1112 }, { "epoch": 3.774193548387097, "grad_norm": 0.11751710676145449, "learning_rate": 1.0081928468605118e-06, "loss": 0.0380292646586895, "step": 1113 }, { "epoch": 3.7775891341256367, "grad_norm": 0.12027014055763775, "learning_rate": 9.788545756694967e-07, "loss": 0.03403709456324577, "step": 1114 }, { "epoch": 3.7809847198641764, "grad_norm": 0.1220449946571117, "learning_rate": 9.499452813226284e-07, "loss": 0.029617829248309135, "step": 1115 }, { "epoch": 3.7843803056027165, "grad_norm": 0.1165749946719359, "learning_rate": 9.214652168008875e-07, "loss": 0.023012368008494377, "step": 1116 }, { "epoch": 3.7877758913412563, "grad_norm": 0.11729702440601822, "learning_rate": 8.934146313291425e-07, "loss": 0.020834699273109436, "step": 1117 }, { "epoch": 3.7911714770797964, "grad_norm": 0.11060301875684929, "learning_rate": 8.657937703739516e-07, "loss": 0.018864905461668968, "step": 1118 }, { "epoch": 3.794567062818336, "grad_norm": 0.12452208014366169, "learning_rate": 8.386028756414089e-07, "loss": 0.05394645780324936, "step": 1119 }, { "epoch": 3.797962648556876, "grad_norm": 0.11745829598880726, "learning_rate": 8.118421850750347e-07, "loss": 0.04872319847345352, "step": 1120 }, { "epoch": 3.801358234295416, "grad_norm": 0.12310129335004406, "learning_rate": 7.855119328537109e-07, "loss": 0.039736177772283554, "step": 1121 }, { "epoch": 3.804753820033956, "grad_norm": 0.11896843223067839, "learning_rate": 7.596123493895991e-07, "loss": 0.0368708074092865, "step": 1122 }, { "epoch": 3.808149405772496, "grad_norm": 0.11827883877964149, "learning_rate": 7.341436613261532e-07, "loss": 0.030284777283668518, "step": 1123 }, { "epoch": 3.8115449915110355, "grad_norm": 0.11396458316876396, "learning_rate": 7.091060915361269e-07, "loss": 0.024617334827780724, "step": 1124 }, { "epoch": 3.8149405772495757, "grad_norm": 0.10981675506521492, "learning_rate": 6.844998591196138e-07, "loss": 0.020244378596544266, "step": 1125 }, { "epoch": 3.8183361629881154, "grad_norm": 0.11488504545162433, "learning_rate": 6.603251794021381e-07, "loss": 0.019265562295913696, "step": 1126 }, { "epoch": 3.8217317487266556, "grad_norm": 0.12493743372227485, "learning_rate": 6.365822639327723e-07, "loss": 0.03398379683494568, "step": 1127 }, { "epoch": 3.8251273344651953, "grad_norm": 0.11356806317769211, "learning_rate": 6.132713204822838e-07, "loss": 0.05216260999441147, "step": 1128 }, { "epoch": 3.828522920203735, "grad_norm": 0.11970348895255666, "learning_rate": 5.903925530413135e-07, "loss": 0.04568401724100113, "step": 1129 }, { "epoch": 3.831918505942275, "grad_norm": 0.11796825587119072, "learning_rate": 5.679461618185944e-07, "loss": 0.038143813610076904, "step": 1130 }, { "epoch": 3.835314091680815, "grad_norm": 0.12460428108575632, "learning_rate": 5.459323432392083e-07, "loss": 0.033648695796728134, "step": 1131 }, { "epoch": 3.838709677419355, "grad_norm": 0.12179212767908745, "learning_rate": 5.243512899428316e-07, "loss": 0.02586100623011589, "step": 1132 }, { "epoch": 3.8421052631578947, "grad_norm": 0.11171416252754224, "learning_rate": 5.032031907821089e-07, "loss": 0.022495951503515244, "step": 1133 }, { "epoch": 3.8455008488964344, "grad_norm": 0.1156113995424611, "learning_rate": 4.824882308209433e-07, "loss": 0.019813761115074158, "step": 1134 }, { "epoch": 3.8488964346349746, "grad_norm": 0.11603376823598478, "learning_rate": 4.6220659133290325e-07, "loss": 0.020243462175130844, "step": 1135 }, { "epoch": 3.8522920203735147, "grad_norm": 0.10792824503840247, "learning_rate": 4.423584497996458e-07, "loss": 0.0512520894408226, "step": 1136 }, { "epoch": 3.8556876061120544, "grad_norm": 0.1321638026396283, "learning_rate": 4.2294397990932934e-07, "loss": 0.057612400501966476, "step": 1137 }, { "epoch": 3.859083191850594, "grad_norm": 0.11877373969390309, "learning_rate": 4.039633515551422e-07, "loss": 0.04319695755839348, "step": 1138 }, { "epoch": 3.8624787775891343, "grad_norm": 0.12083334451114072, "learning_rate": 3.854167308337708e-07, "loss": 0.030842553824186325, "step": 1139 }, { "epoch": 3.865874363327674, "grad_norm": 0.12009663704476248, "learning_rate": 3.67304280043973e-07, "loss": 0.027373939752578735, "step": 1140 }, { "epoch": 3.869269949066214, "grad_norm": 0.11754365061151577, "learning_rate": 3.4962615768513453e-07, "loss": 0.025088828057050705, "step": 1141 }, { "epoch": 3.872665534804754, "grad_norm": 0.1189051043181852, "learning_rate": 3.323825184559204e-07, "loss": 0.020571477711200714, "step": 1142 }, { "epoch": 3.8760611205432935, "grad_norm": 0.10633316956379629, "learning_rate": 3.1557351325287586e-07, "loss": 0.017123613506555557, "step": 1143 }, { "epoch": 3.8794567062818337, "grad_norm": 0.12695943153869224, "learning_rate": 2.9919928916913866e-07, "loss": 0.044827818870544434, "step": 1144 }, { "epoch": 3.8828522920203734, "grad_norm": 0.12312568794781234, "learning_rate": 2.8325998949314536e-07, "loss": 0.051978062838315964, "step": 1145 }, { "epoch": 3.8862478777589136, "grad_norm": 0.11514811593110687, "learning_rate": 2.677557537073605e-07, "loss": 0.03830812871456146, "step": 1146 }, { "epoch": 3.8896434634974533, "grad_norm": 0.12830524625470124, "learning_rate": 2.526867174870717e-07, "loss": 0.03800264373421669, "step": 1147 }, { "epoch": 3.893039049235993, "grad_norm": 0.1310621457305441, "learning_rate": 2.3805301269920755e-07, "loss": 0.029516471549868584, "step": 1148 }, { "epoch": 3.896434634974533, "grad_norm": 0.1257078646712887, "learning_rate": 2.238547674011715e-07, "loss": 0.03173277527093887, "step": 1149 }, { "epoch": 3.8998302207130733, "grad_norm": 0.11365695822165997, "learning_rate": 2.1009210583971539e-07, "loss": 0.022136522457003593, "step": 1150 }, { "epoch": 3.903225806451613, "grad_norm": 0.106486080824731, "learning_rate": 1.9676514844987337e-07, "loss": 0.01766270026564598, "step": 1151 }, { "epoch": 3.9066213921901527, "grad_norm": 0.11581309376518396, "learning_rate": 1.8387401185389064e-07, "loss": 0.03541246056556702, "step": 1152 }, { "epoch": 3.910016977928693, "grad_norm": 0.1237173604933984, "learning_rate": 1.714188088602131e-07, "loss": 0.058458708226680756, "step": 1153 }, { "epoch": 3.9134125636672326, "grad_norm": 0.12161312691926111, "learning_rate": 1.5939964846249378e-07, "loss": 0.043392978608608246, "step": 1154 }, { "epoch": 3.9168081494057727, "grad_norm": 0.1195607542721311, "learning_rate": 1.4781663583863793e-07, "loss": 0.03745763748884201, "step": 1155 }, { "epoch": 3.9202037351443124, "grad_norm": 0.11554843920603164, "learning_rate": 1.366698723498816e-07, "loss": 0.03112410008907318, "step": 1156 }, { "epoch": 3.923599320882852, "grad_norm": 0.12034239955507457, "learning_rate": 1.2595945553992573e-07, "loss": 0.027484580874443054, "step": 1157 }, { "epoch": 3.9269949066213923, "grad_norm": 0.10722658005467967, "learning_rate": 1.1568547913404782e-07, "loss": 0.020586207509040833, "step": 1158 }, { "epoch": 3.930390492359932, "grad_norm": 0.11565997714765128, "learning_rate": 1.0584803303831381e-07, "loss": 0.020107561722397804, "step": 1159 }, { "epoch": 3.933786078098472, "grad_norm": 0.11973547921538986, "learning_rate": 9.6447203338762e-08, "loss": 0.020272759720683098, "step": 1160 }, { "epoch": 3.937181663837012, "grad_norm": 0.1124841677843221, "learning_rate": 8.748307230067588e-08, "loss": 0.050097476691007614, "step": 1161 }, { "epoch": 3.9405772495755516, "grad_norm": 0.12313688318869252, "learning_rate": 7.895571836785131e-08, "loss": 0.05279211327433586, "step": 1162 }, { "epoch": 3.9439728353140917, "grad_norm": 0.12062704857249691, "learning_rate": 7.086521616190279e-08, "loss": 0.04177408665418625, "step": 1163 }, { "epoch": 3.9473684210526314, "grad_norm": 0.11404214323428699, "learning_rate": 6.321163648163597e-08, "loss": 0.03475956618785858, "step": 1164 }, { "epoch": 3.9507640067911716, "grad_norm": 0.11965181453458439, "learning_rate": 5.599504630239838e-08, "loss": 0.027550702914595604, "step": 1165 }, { "epoch": 3.9541595925297113, "grad_norm": 0.11386822633677939, "learning_rate": 4.921550877550751e-08, "loss": 0.023431910201907158, "step": 1166 }, { "epoch": 3.9575551782682514, "grad_norm": 0.1141237684029982, "learning_rate": 4.287308322770689e-08, "loss": 0.021631918847560883, "step": 1167 }, { "epoch": 3.960950764006791, "grad_norm": 0.11691459684510735, "learning_rate": 3.696782516062758e-08, "loss": 0.018438920378684998, "step": 1168 }, { "epoch": 3.9643463497453313, "grad_norm": 0.1179185116010346, "learning_rate": 3.149978625032191e-08, "loss": 0.05369807407259941, "step": 1169 }, { "epoch": 3.967741935483871, "grad_norm": 0.12442148338762984, "learning_rate": 2.646901434678606e-08, "loss": 0.05239899083971977, "step": 1170 }, { "epoch": 3.9711375212224107, "grad_norm": 0.12267264116999667, "learning_rate": 2.1875553473565956e-08, "loss": 0.038403525948524475, "step": 1171 }, { "epoch": 3.974533106960951, "grad_norm": 0.12258808226107891, "learning_rate": 1.7719443827368677e-08, "loss": 0.03488669916987419, "step": 1172 }, { "epoch": 3.9779286926994906, "grad_norm": 0.11301881094259209, "learning_rate": 1.400072177770162e-08, "loss": 0.026330342516303062, "step": 1173 }, { "epoch": 3.9813242784380307, "grad_norm": 0.12275303892897563, "learning_rate": 1.0719419866550561e-08, "loss": 0.02484235167503357, "step": 1174 }, { "epoch": 3.9847198641765704, "grad_norm": 0.11236573789078697, "learning_rate": 7.875566808107637e-09, "loss": 0.02031204104423523, "step": 1175 }, { "epoch": 3.98811544991511, "grad_norm": 0.10848813880245003, "learning_rate": 5.469187488510441e-09, "loss": 0.01755809783935547, "step": 1176 }, { "epoch": 3.9915110356536503, "grad_norm": 0.1419320766205256, "learning_rate": 3.500302965636637e-09, "loss": 0.0445953831076622, "step": 1177 }, { "epoch": 3.99490662139219, "grad_norm": 0.12024525693209581, "learning_rate": 1.9689304688985664e-09, "loss": 0.04040689021348953, "step": 1178 }, { "epoch": 3.99830220713073, "grad_norm": 0.11656840612292153, "learning_rate": 8.750833991155727e-10, "loss": 0.02543703280389309, "step": 1179 }, { "epoch": 4.0, "grad_norm": 0.16435114852171887, "learning_rate": 2.1877132838632463e-10, "loss": 0.020692113786935806, "step": 1180 }, { "epoch": 4.0, "step": 1180, "total_flos": 7.881538624284525e+18, "train_loss": 0.1321902611324469, "train_runtime": 266690.9372, "train_samples_per_second": 0.212, "train_steps_per_second": 0.004 } ], "logging_steps": 1, "max_steps": 1180, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7.881538624284525e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }