{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1892, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004228329809725159, "grad_norm": 6.6071672439575195, "learning_rate": 1.0526315789473685e-07, "loss": 1.8237226009368896, "step": 2 }, { "epoch": 0.008456659619450317, "grad_norm": 0.988720178604126, "learning_rate": 3.1578947368421055e-07, "loss": 2.1770057678222656, "step": 4 }, { "epoch": 0.012684989429175475, "grad_norm": 4.981032848358154, "learning_rate": 5.263157894736843e-07, "loss": 2.149057149887085, "step": 6 }, { "epoch": 0.016913319238900635, "grad_norm": 1.0069395303726196, "learning_rate": 7.368421052631579e-07, "loss": 1.9537242650985718, "step": 8 }, { "epoch": 0.021141649048625793, "grad_norm": 3.4668326377868652, "learning_rate": 9.473684210526317e-07, "loss": 2.0054521560668945, "step": 10 }, { "epoch": 0.02536997885835095, "grad_norm": 2.841759204864502, "learning_rate": 1.1578947368421053e-06, "loss": 1.6671046018600464, "step": 12 }, { "epoch": 0.02959830866807611, "grad_norm": 0.9642605185508728, "learning_rate": 1.3684210526315791e-06, "loss": 1.6186693906784058, "step": 14 }, { "epoch": 0.03382663847780127, "grad_norm": 1.1857709884643555, "learning_rate": 1.5789473684210526e-06, "loss": 1.7450484037399292, "step": 16 }, { "epoch": 0.03805496828752643, "grad_norm": 0.9702156782150269, "learning_rate": 1.7894736842105265e-06, "loss": 1.7557533979415894, "step": 18 }, { "epoch": 0.042283298097251586, "grad_norm": 2.14196515083313, "learning_rate": 2.0000000000000003e-06, "loss": 1.673680067062378, "step": 20 }, { "epoch": 0.046511627906976744, "grad_norm": 2.615105390548706, "learning_rate": 2.2105263157894738e-06, "loss": 1.4959195852279663, "step": 22 }, { "epoch": 0.0507399577167019, "grad_norm": 1.2625185251235962, "learning_rate": 2.4210526315789477e-06, "loss": 1.739831805229187, "step": 24 }, { "epoch": 0.05496828752642706, "grad_norm": 1.3486806154251099, "learning_rate": 2.631578947368421e-06, "loss": 1.3543747663497925, "step": 26 }, { "epoch": 0.05919661733615222, "grad_norm": 0.6488559246063232, "learning_rate": 2.842105263157895e-06, "loss": 1.6242082118988037, "step": 28 }, { "epoch": 0.06342494714587738, "grad_norm": 0.8200469017028809, "learning_rate": 3.052631578947369e-06, "loss": 1.2556012868881226, "step": 30 }, { "epoch": 0.06765327695560254, "grad_norm": 1.9508771896362305, "learning_rate": 3.2631578947368423e-06, "loss": 1.0250747203826904, "step": 32 }, { "epoch": 0.07188160676532769, "grad_norm": 2.1149778366088867, "learning_rate": 3.473684210526316e-06, "loss": 1.174399971961975, "step": 34 }, { "epoch": 0.07610993657505286, "grad_norm": 1.0890921354293823, "learning_rate": 3.6842105263157896e-06, "loss": 1.3459112644195557, "step": 36 }, { "epoch": 0.080338266384778, "grad_norm": 1.6121841669082642, "learning_rate": 3.894736842105263e-06, "loss": 1.2610503435134888, "step": 38 }, { "epoch": 0.08456659619450317, "grad_norm": 4.550328254699707, "learning_rate": 4.105263157894737e-06, "loss": 1.2262604236602783, "step": 40 }, { "epoch": 0.08879492600422834, "grad_norm": 1.313605546951294, "learning_rate": 4.315789473684211e-06, "loss": 1.6488430500030518, "step": 42 }, { "epoch": 0.09302325581395349, "grad_norm": 7.475367546081543, "learning_rate": 4.526315789473685e-06, "loss": 1.6110299825668335, "step": 44 }, { "epoch": 0.09725158562367865, "grad_norm": 0.7760991454124451, "learning_rate": 4.736842105263158e-06, "loss": 1.2666505575180054, "step": 46 }, { "epoch": 0.1014799154334038, "grad_norm": 0.7113277316093445, "learning_rate": 4.947368421052632e-06, "loss": 1.486632227897644, "step": 48 }, { "epoch": 0.10570824524312897, "grad_norm": 3.1856606006622314, "learning_rate": 5.157894736842106e-06, "loss": 1.486079454421997, "step": 50 }, { "epoch": 0.10993657505285412, "grad_norm": 2.580359697341919, "learning_rate": 5.36842105263158e-06, "loss": 0.6992756724357605, "step": 52 }, { "epoch": 0.11416490486257928, "grad_norm": 0.4834706485271454, "learning_rate": 5.578947368421052e-06, "loss": 1.056563138961792, "step": 54 }, { "epoch": 0.11839323467230443, "grad_norm": 1.032867193222046, "learning_rate": 5.789473684210527e-06, "loss": 1.3563868999481201, "step": 56 }, { "epoch": 0.1226215644820296, "grad_norm": 1.7154631614685059, "learning_rate": 6e-06, "loss": 1.3807646036148071, "step": 58 }, { "epoch": 0.12684989429175475, "grad_norm": 1.122086524963379, "learning_rate": 6.2105263157894745e-06, "loss": 1.3972307443618774, "step": 60 }, { "epoch": 0.13107822410147993, "grad_norm": 37.866905212402344, "learning_rate": 6.421052631578948e-06, "loss": 0.76498943567276, "step": 62 }, { "epoch": 0.13530655391120508, "grad_norm": 3.026092290878296, "learning_rate": 6.631578947368421e-06, "loss": 1.0148589611053467, "step": 64 }, { "epoch": 0.13953488372093023, "grad_norm": 0.762069046497345, "learning_rate": 6.842105263157896e-06, "loss": 1.3238638639450073, "step": 66 }, { "epoch": 0.14376321353065538, "grad_norm": 0.6277386546134949, "learning_rate": 7.052631578947369e-06, "loss": 1.3656563758850098, "step": 68 }, { "epoch": 0.14799154334038056, "grad_norm": 1.604831576347351, "learning_rate": 7.263157894736843e-06, "loss": 1.3539881706237793, "step": 70 }, { "epoch": 0.1522198731501057, "grad_norm": 0.648463249206543, "learning_rate": 7.473684210526316e-06, "loss": 1.3393738269805908, "step": 72 }, { "epoch": 0.15644820295983086, "grad_norm": 1.6237311363220215, "learning_rate": 7.68421052631579e-06, "loss": 0.9382629990577698, "step": 74 }, { "epoch": 0.160676532769556, "grad_norm": 0.990922749042511, "learning_rate": 7.894736842105265e-06, "loss": 0.8267001509666443, "step": 76 }, { "epoch": 0.1649048625792812, "grad_norm": 1.1128501892089844, "learning_rate": 8.105263157894736e-06, "loss": 1.2879154682159424, "step": 78 }, { "epoch": 0.16913319238900634, "grad_norm": 1.4431954622268677, "learning_rate": 8.315789473684212e-06, "loss": 1.0560591220855713, "step": 80 }, { "epoch": 0.1733615221987315, "grad_norm": 1.8278834819793701, "learning_rate": 8.526315789473685e-06, "loss": 1.0919139385223389, "step": 82 }, { "epoch": 0.17758985200845667, "grad_norm": 0.5909755825996399, "learning_rate": 8.736842105263158e-06, "loss": 0.8356268405914307, "step": 84 }, { "epoch": 0.18181818181818182, "grad_norm": 1.4228099584579468, "learning_rate": 8.947368421052632e-06, "loss": 1.7170177698135376, "step": 86 }, { "epoch": 0.18604651162790697, "grad_norm": 0.7354671955108643, "learning_rate": 9.157894736842105e-06, "loss": 1.2821717262268066, "step": 88 }, { "epoch": 0.19027484143763213, "grad_norm": 1.4013428688049316, "learning_rate": 9.36842105263158e-06, "loss": 1.0005549192428589, "step": 90 }, { "epoch": 0.1945031712473573, "grad_norm": 0.6270893812179565, "learning_rate": 9.578947368421054e-06, "loss": 1.3096117973327637, "step": 92 }, { "epoch": 0.19873150105708245, "grad_norm": 0.7756372094154358, "learning_rate": 9.789473684210527e-06, "loss": 0.9912471175193787, "step": 94 }, { "epoch": 0.2029598308668076, "grad_norm": 1.439513087272644, "learning_rate": 1e-05, "loss": 1.2891972064971924, "step": 96 }, { "epoch": 0.20718816067653276, "grad_norm": 2.38813853263855, "learning_rate": 9.999972492846047e-06, "loss": 1.3875130414962769, "step": 98 }, { "epoch": 0.21141649048625794, "grad_norm": 0.5498270392417908, "learning_rate": 9.999889971720468e-06, "loss": 1.3755178451538086, "step": 100 }, { "epoch": 0.2156448202959831, "grad_norm": 0.4167301654815674, "learning_rate": 9.999752437632121e-06, "loss": 1.2443665266036987, "step": 102 }, { "epoch": 0.21987315010570824, "grad_norm": 0.6303926706314087, "learning_rate": 9.999559892262412e-06, "loss": 1.3059874773025513, "step": 104 }, { "epoch": 0.22410147991543342, "grad_norm": 0.78045254945755, "learning_rate": 9.999312337965291e-06, "loss": 1.2922918796539307, "step": 106 }, { "epoch": 0.22832980972515857, "grad_norm": 1.0676648616790771, "learning_rate": 9.999009777767202e-06, "loss": 1.0399408340454102, "step": 108 }, { "epoch": 0.23255813953488372, "grad_norm": 0.830178439617157, "learning_rate": 9.99865221536707e-06, "loss": 1.2790594100952148, "step": 110 }, { "epoch": 0.23678646934460887, "grad_norm": 1.840660572052002, "learning_rate": 9.998239655136237e-06, "loss": 1.3637686967849731, "step": 112 }, { "epoch": 0.24101479915433405, "grad_norm": 0.5590378642082214, "learning_rate": 9.997772102118417e-06, "loss": 1.4808354377746582, "step": 114 }, { "epoch": 0.2452431289640592, "grad_norm": 1.009464144706726, "learning_rate": 9.997249562029637e-06, "loss": 1.332289695739746, "step": 116 }, { "epoch": 0.24947145877378435, "grad_norm": 1.323447585105896, "learning_rate": 9.996672041258154e-06, "loss": 1.338663935661316, "step": 118 }, { "epoch": 0.2536997885835095, "grad_norm": 1.1783710718154907, "learning_rate": 9.996039546864395e-06, "loss": 0.8129961490631104, "step": 120 }, { "epoch": 0.25792811839323465, "grad_norm": 0.6953306198120117, "learning_rate": 9.995352086580858e-06, "loss": 1.308255672454834, "step": 122 }, { "epoch": 0.26215644820295986, "grad_norm": 1.0921456813812256, "learning_rate": 9.994609668812022e-06, "loss": 1.1392494440078735, "step": 124 }, { "epoch": 0.266384778012685, "grad_norm": 1.8229342699050903, "learning_rate": 9.993812302634237e-06, "loss": 1.344388484954834, "step": 126 }, { "epoch": 0.27061310782241016, "grad_norm": 0.7680500149726868, "learning_rate": 9.99295999779563e-06, "loss": 0.9698686003684998, "step": 128 }, { "epoch": 0.2748414376321353, "grad_norm": 2.1851563453674316, "learning_rate": 9.99205276471597e-06, "loss": 0.9688682556152344, "step": 130 }, { "epoch": 0.27906976744186046, "grad_norm": 4.1189165115356445, "learning_rate": 9.991090614486546e-06, "loss": 1.2912046909332275, "step": 132 }, { "epoch": 0.2832980972515856, "grad_norm": 6.534398555755615, "learning_rate": 9.990073558870028e-06, "loss": 0.9575721025466919, "step": 134 }, { "epoch": 0.28752642706131076, "grad_norm": 1.5636370182037354, "learning_rate": 9.989001610300333e-06, "loss": 1.1275583505630493, "step": 136 }, { "epoch": 0.2917547568710359, "grad_norm": 1.2046842575073242, "learning_rate": 9.987874781882461e-06, "loss": 1.4454268217086792, "step": 138 }, { "epoch": 0.2959830866807611, "grad_norm": 1.3628989458084106, "learning_rate": 9.986693087392341e-06, "loss": 0.9149445295333862, "step": 140 }, { "epoch": 0.30021141649048627, "grad_norm": 0.7739085555076599, "learning_rate": 9.985456541276667e-06, "loss": 1.557478427886963, "step": 142 }, { "epoch": 0.3044397463002114, "grad_norm": 3.675485372543335, "learning_rate": 9.984165158652708e-06, "loss": 1.1246814727783203, "step": 144 }, { "epoch": 0.3086680761099366, "grad_norm": 0.8598083853721619, "learning_rate": 9.982818955308135e-06, "loss": 0.6895565390586853, "step": 146 }, { "epoch": 0.3128964059196617, "grad_norm": 1.1081278324127197, "learning_rate": 9.98141794770083e-06, "loss": 1.2444963455200195, "step": 148 }, { "epoch": 0.3171247357293869, "grad_norm": 0.4688684344291687, "learning_rate": 9.979962152958669e-06, "loss": 1.264260172843933, "step": 150 }, { "epoch": 0.321353065539112, "grad_norm": 0.5702924728393555, "learning_rate": 9.97845158887933e-06, "loss": 1.1961681842803955, "step": 152 }, { "epoch": 0.32558139534883723, "grad_norm": 1.5303266048431396, "learning_rate": 9.976886273930063e-06, "loss": 0.7738041877746582, "step": 154 }, { "epoch": 0.3298097251585624, "grad_norm": 0.6874333024024963, "learning_rate": 9.975266227247474e-06, "loss": 1.242485761642456, "step": 156 }, { "epoch": 0.33403805496828753, "grad_norm": 0.5659751296043396, "learning_rate": 9.973591468637286e-06, "loss": 1.270439624786377, "step": 158 }, { "epoch": 0.3382663847780127, "grad_norm": 0.6031907200813293, "learning_rate": 9.971862018574094e-06, "loss": 1.257002353668213, "step": 160 }, { "epoch": 0.34249471458773784, "grad_norm": 99.46913146972656, "learning_rate": 9.97007789820112e-06, "loss": 1.0921249389648438, "step": 162 }, { "epoch": 0.346723044397463, "grad_norm": 1.832014799118042, "learning_rate": 9.968239129329953e-06, "loss": 1.0248026847839355, "step": 164 }, { "epoch": 0.35095137420718814, "grad_norm": 0.8903549313545227, "learning_rate": 9.96634573444028e-06, "loss": 0.8892332315444946, "step": 166 }, { "epoch": 0.35517970401691334, "grad_norm": 0.718556821346283, "learning_rate": 9.964397736679615e-06, "loss": 1.1840183734893799, "step": 168 }, { "epoch": 0.3594080338266385, "grad_norm": 0.8867468237876892, "learning_rate": 9.962395159863014e-06, "loss": 1.2032510042190552, "step": 170 }, { "epoch": 0.36363636363636365, "grad_norm": 0.8973855376243591, "learning_rate": 9.960338028472781e-06, "loss": 1.0378704071044922, "step": 172 }, { "epoch": 0.3678646934460888, "grad_norm": 1.8450329303741455, "learning_rate": 9.958226367658176e-06, "loss": 1.3578194379806519, "step": 174 }, { "epoch": 0.37209302325581395, "grad_norm": 0.6784747242927551, "learning_rate": 9.9560602032351e-06, "loss": 1.0692775249481201, "step": 176 }, { "epoch": 0.3763213530655391, "grad_norm": 1.240138053894043, "learning_rate": 9.953839561685783e-06, "loss": 0.9274802207946777, "step": 178 }, { "epoch": 0.38054968287526425, "grad_norm": 0.37568116188049316, "learning_rate": 9.95156447015846e-06, "loss": 1.281457543373108, "step": 180 }, { "epoch": 0.38477801268498946, "grad_norm": 2.2039291858673096, "learning_rate": 9.94923495646704e-06, "loss": 1.5479613542556763, "step": 182 }, { "epoch": 0.3890063424947146, "grad_norm": 0.6686821579933167, "learning_rate": 9.946851049090764e-06, "loss": 1.3353830575942993, "step": 184 }, { "epoch": 0.39323467230443976, "grad_norm": 0.9058509469032288, "learning_rate": 9.944412777173854e-06, "loss": 1.1112406253814697, "step": 186 }, { "epoch": 0.3974630021141649, "grad_norm": 0.9436449408531189, "learning_rate": 9.941920170525168e-06, "loss": 0.9898382425308228, "step": 188 }, { "epoch": 0.40169133192389006, "grad_norm": 0.7498824000358582, "learning_rate": 9.939373259617822e-06, "loss": 0.9978891015052795, "step": 190 }, { "epoch": 0.4059196617336152, "grad_norm": 0.6851239800453186, "learning_rate": 9.936772075588825e-06, "loss": 1.295215368270874, "step": 192 }, { "epoch": 0.41014799154334036, "grad_norm": 0.2729327976703644, "learning_rate": 9.934116650238697e-06, "loss": 1.0182896852493286, "step": 194 }, { "epoch": 0.4143763213530655, "grad_norm": 0.7153222560882568, "learning_rate": 9.931407016031078e-06, "loss": 1.2881966829299927, "step": 196 }, { "epoch": 0.4186046511627907, "grad_norm": 1.0345572233200073, "learning_rate": 9.928643206092338e-06, "loss": 1.0612722635269165, "step": 198 }, { "epoch": 0.42283298097251587, "grad_norm": 0.43884575366973877, "learning_rate": 9.925825254211161e-06, "loss": 1.1737587451934814, "step": 200 }, { "epoch": 0.427061310782241, "grad_norm": 0.6989097595214844, "learning_rate": 9.922953194838143e-06, "loss": 0.5533363223075867, "step": 202 }, { "epoch": 0.4312896405919662, "grad_norm": 0.4158462882041931, "learning_rate": 9.920027063085363e-06, "loss": 1.2349354028701782, "step": 204 }, { "epoch": 0.4355179704016913, "grad_norm": 1.3961560726165771, "learning_rate": 9.917046894725957e-06, "loss": 1.3056493997573853, "step": 206 }, { "epoch": 0.4397463002114165, "grad_norm": 1.4015706777572632, "learning_rate": 9.91401272619368e-06, "loss": 0.787306010723114, "step": 208 }, { "epoch": 0.4439746300211416, "grad_norm": 0.5242287516593933, "learning_rate": 9.910924594582463e-06, "loss": 1.2907884120941162, "step": 210 }, { "epoch": 0.44820295983086683, "grad_norm": 0.5075401067733765, "learning_rate": 9.907782537645955e-06, "loss": 1.2753466367721558, "step": 212 }, { "epoch": 0.452431289640592, "grad_norm": 0.625218391418457, "learning_rate": 9.904586593797062e-06, "loss": 1.423142671585083, "step": 214 }, { "epoch": 0.45665961945031713, "grad_norm": 0.9167463779449463, "learning_rate": 9.901336802107485e-06, "loss": 0.6377100944519043, "step": 216 }, { "epoch": 0.4608879492600423, "grad_norm": 9.440084457397461, "learning_rate": 9.89803320230723e-06, "loss": 1.0045851469039917, "step": 218 }, { "epoch": 0.46511627906976744, "grad_norm": 0.766928493976593, "learning_rate": 9.894675834784136e-06, "loss": 1.2836695909500122, "step": 220 }, { "epoch": 0.4693446088794926, "grad_norm": 0.6827864646911621, "learning_rate": 9.891264740583367e-06, "loss": 1.237319827079773, "step": 222 }, { "epoch": 0.47357293868921774, "grad_norm": 0.9213079810142517, "learning_rate": 9.88779996140692e-06, "loss": 1.3421708345413208, "step": 224 }, { "epoch": 0.47780126849894294, "grad_norm": 0.5526377558708191, "learning_rate": 9.884281539613109e-06, "loss": 1.2499641180038452, "step": 226 }, { "epoch": 0.4820295983086681, "grad_norm": 1.432809591293335, "learning_rate": 9.880709518216061e-06, "loss": 1.245672583580017, "step": 228 }, { "epoch": 0.48625792811839325, "grad_norm": 0.4195214807987213, "learning_rate": 9.87708394088517e-06, "loss": 0.912977933883667, "step": 230 }, { "epoch": 0.4904862579281184, "grad_norm": 0.9615507125854492, "learning_rate": 9.873404851944573e-06, "loss": 1.2550969123840332, "step": 232 }, { "epoch": 0.49471458773784355, "grad_norm": 1.5864757299423218, "learning_rate": 9.869672296372611e-06, "loss": 0.9538388252258301, "step": 234 }, { "epoch": 0.4989429175475687, "grad_norm": 11.490452766418457, "learning_rate": 9.86588631980128e-06, "loss": 0.893232524394989, "step": 236 }, { "epoch": 0.5031712473572939, "grad_norm": 0.5910314917564392, "learning_rate": 9.86204696851566e-06, "loss": 0.8335579037666321, "step": 238 }, { "epoch": 0.507399577167019, "grad_norm": 0.8332681655883789, "learning_rate": 9.858154289453363e-06, "loss": 0.9030176997184753, "step": 240 }, { "epoch": 0.5116279069767442, "grad_norm": 0.7972539067268372, "learning_rate": 9.854208330203958e-06, "loss": 1.3126472234725952, "step": 242 }, { "epoch": 0.5158562367864693, "grad_norm": 1.3224173784255981, "learning_rate": 9.850209139008377e-06, "loss": 1.3536946773529053, "step": 244 }, { "epoch": 0.5200845665961945, "grad_norm": 1.1537795066833496, "learning_rate": 9.846156764758344e-06, "loss": 1.2858892679214478, "step": 246 }, { "epoch": 0.5243128964059197, "grad_norm": 0.6034507155418396, "learning_rate": 9.842051256995759e-06, "loss": 1.2412294149398804, "step": 248 }, { "epoch": 0.5285412262156448, "grad_norm": 3.123863697052002, "learning_rate": 9.837892665912105e-06, "loss": 1.1638362407684326, "step": 250 }, { "epoch": 0.53276955602537, "grad_norm": 3.6595218181610107, "learning_rate": 9.833681042347827e-06, "loss": 1.1129153966903687, "step": 252 }, { "epoch": 0.5369978858350951, "grad_norm": 0.8875865936279297, "learning_rate": 9.829416437791721e-06, "loss": 1.739338755607605, "step": 254 }, { "epoch": 0.5412262156448203, "grad_norm": 1.6488114595413208, "learning_rate": 9.825098904380284e-06, "loss": 1.2122129201889038, "step": 256 }, { "epoch": 0.5454545454545454, "grad_norm": 0.775840163230896, "learning_rate": 9.820728494897101e-06, "loss": 1.390175461769104, "step": 258 }, { "epoch": 0.5496828752642706, "grad_norm": 0.8227750658988953, "learning_rate": 9.816305262772182e-06, "loss": 1.0023421049118042, "step": 260 }, { "epoch": 0.5539112050739958, "grad_norm": 0.3920390009880066, "learning_rate": 9.811829262081315e-06, "loss": 1.197433590888977, "step": 262 }, { "epoch": 0.5581395348837209, "grad_norm": 0.8079970479011536, "learning_rate": 9.807300547545411e-06, "loss": 1.0697219371795654, "step": 264 }, { "epoch": 0.5623678646934461, "grad_norm": 0.7303589582443237, "learning_rate": 9.802719174529821e-06, "loss": 1.4988322257995605, "step": 266 }, { "epoch": 0.5665961945031712, "grad_norm": 3.1829843521118164, "learning_rate": 9.798085199043672e-06, "loss": 0.5641506910324097, "step": 268 }, { "epoch": 0.5708245243128964, "grad_norm": 1.5518643856048584, "learning_rate": 9.793398677739177e-06, "loss": 1.0542882680892944, "step": 270 }, { "epoch": 0.5750528541226215, "grad_norm": 12.813671112060547, "learning_rate": 9.788659667910942e-06, "loss": 1.1971925497055054, "step": 272 }, { "epoch": 0.5792811839323467, "grad_norm": 0.5287565588951111, "learning_rate": 9.783868227495262e-06, "loss": 0.9647678136825562, "step": 274 }, { "epoch": 0.5835095137420718, "grad_norm": 0.6110808849334717, "learning_rate": 9.779024415069427e-06, "loss": 0.9410707354545593, "step": 276 }, { "epoch": 0.587737843551797, "grad_norm": 0.3076048195362091, "learning_rate": 9.774128289850987e-06, "loss": 0.8640779852867126, "step": 278 }, { "epoch": 0.5919661733615222, "grad_norm": 0.6991233825683594, "learning_rate": 9.769179911697037e-06, "loss": 1.2267416715621948, "step": 280 }, { "epoch": 0.5961945031712473, "grad_norm": 0.7445630431175232, "learning_rate": 9.764179341103493e-06, "loss": 1.4532619714736938, "step": 282 }, { "epoch": 0.6004228329809725, "grad_norm": 0.17136923968791962, "learning_rate": 9.759126639204337e-06, "loss": 0.9280106425285339, "step": 284 }, { "epoch": 0.6046511627906976, "grad_norm": 0.5797514915466309, "learning_rate": 9.75402186777088e-06, "loss": 1.2762196063995361, "step": 286 }, { "epoch": 0.6088794926004228, "grad_norm": 0.7654552459716797, "learning_rate": 9.748865089211004e-06, "loss": 0.4129101634025574, "step": 288 }, { "epoch": 0.6131078224101479, "grad_norm": 1.7628523111343384, "learning_rate": 9.743656366568398e-06, "loss": 0.950832724571228, "step": 290 }, { "epoch": 0.6173361522198731, "grad_norm": 0.9539992213249207, "learning_rate": 9.738395763521792e-06, "loss": 0.8715356588363647, "step": 292 }, { "epoch": 0.6215644820295984, "grad_norm": 2.035680055618286, "learning_rate": 9.733083344384164e-06, "loss": 0.7256388664245605, "step": 294 }, { "epoch": 0.6257928118393234, "grad_norm": 3.409623384475708, "learning_rate": 9.727719174101981e-06, "loss": 0.7242799997329712, "step": 296 }, { "epoch": 0.6300211416490487, "grad_norm": 8.412034034729004, "learning_rate": 9.722303318254376e-06, "loss": 1.2908053398132324, "step": 298 }, { "epoch": 0.6342494714587738, "grad_norm": 2.2030303478240967, "learning_rate": 9.71683584305236e-06, "loss": 1.2399578094482422, "step": 300 }, { "epoch": 0.638477801268499, "grad_norm": 0.8988723158836365, "learning_rate": 9.71131681533802e-06, "loss": 0.7232897281646729, "step": 302 }, { "epoch": 0.642706131078224, "grad_norm": 0.830430269241333, "learning_rate": 9.705746302583682e-06, "loss": 0.8298974633216858, "step": 304 }, { "epoch": 0.6469344608879493, "grad_norm": 0.6206780076026917, "learning_rate": 9.700124372891104e-06, "loss": 0.9437882304191589, "step": 306 }, { "epoch": 0.6511627906976745, "grad_norm": 0.6085275411605835, "learning_rate": 9.694451094990636e-06, "loss": 1.230157494544983, "step": 308 }, { "epoch": 0.6553911205073996, "grad_norm": 1.2720834016799927, "learning_rate": 9.68872653824038e-06, "loss": 1.2132585048675537, "step": 310 }, { "epoch": 0.6596194503171248, "grad_norm": 0.6404009461402893, "learning_rate": 9.68295077262534e-06, "loss": 1.2104586362838745, "step": 312 }, { "epoch": 0.6638477801268499, "grad_norm": 0.5056244730949402, "learning_rate": 9.677123868756573e-06, "loss": 1.2310963869094849, "step": 314 }, { "epoch": 0.6680761099365751, "grad_norm": 0.4363325536251068, "learning_rate": 9.671245897870318e-06, "loss": 1.0772475004196167, "step": 316 }, { "epoch": 0.6723044397463002, "grad_norm": 3.0738465785980225, "learning_rate": 9.665316931827131e-06, "loss": 0.766052782535553, "step": 318 }, { "epoch": 0.6765327695560254, "grad_norm": 1.3529200553894043, "learning_rate": 9.659337043111006e-06, "loss": 1.2447305917739868, "step": 320 }, { "epoch": 0.6807610993657506, "grad_norm": 0.6388787627220154, "learning_rate": 9.653306304828483e-06, "loss": 1.3061776161193848, "step": 322 }, { "epoch": 0.6849894291754757, "grad_norm": 0.6954697370529175, "learning_rate": 9.647224790707762e-06, "loss": 1.0812194347381592, "step": 324 }, { "epoch": 0.6892177589852009, "grad_norm": 0.5801727771759033, "learning_rate": 9.641092575097795e-06, "loss": 1.2603461742401123, "step": 326 }, { "epoch": 0.693446088794926, "grad_norm": 1.7575656175613403, "learning_rate": 9.63490973296738e-06, "loss": 1.1890894174575806, "step": 328 }, { "epoch": 0.6976744186046512, "grad_norm": 15.703152656555176, "learning_rate": 9.62867633990425e-06, "loss": 0.8521145582199097, "step": 330 }, { "epoch": 0.7019027484143763, "grad_norm": 0.5467159152030945, "learning_rate": 9.622392472114136e-06, "loss": 1.2329680919647217, "step": 332 }, { "epoch": 0.7061310782241015, "grad_norm": 1.9533107280731201, "learning_rate": 9.61605820641985e-06, "loss": 1.2092995643615723, "step": 334 }, { "epoch": 0.7103594080338267, "grad_norm": 0.7030382752418518, "learning_rate": 9.60967362026033e-06, "loss": 1.2133989334106445, "step": 336 }, { "epoch": 0.7145877378435518, "grad_norm": 1.9070769548416138, "learning_rate": 9.60323879168971e-06, "loss": 1.3549447059631348, "step": 338 }, { "epoch": 0.718816067653277, "grad_norm": 1.6813571453094482, "learning_rate": 9.596753799376355e-06, "loss": 1.256995677947998, "step": 340 }, { "epoch": 0.7230443974630021, "grad_norm": 2.5749850273132324, "learning_rate": 9.5902187226019e-06, "loss": 1.1191085577011108, "step": 342 }, { "epoch": 0.7272727272727273, "grad_norm": 0.9855456948280334, "learning_rate": 9.583633641260285e-06, "loss": 0.913692831993103, "step": 344 }, { "epoch": 0.7315010570824524, "grad_norm": 10.514382362365723, "learning_rate": 9.576998635856774e-06, "loss": 0.8488363027572632, "step": 346 }, { "epoch": 0.7357293868921776, "grad_norm": 3.243300676345825, "learning_rate": 9.570313787506974e-06, "loss": 0.971068263053894, "step": 348 }, { "epoch": 0.7399577167019028, "grad_norm": 0.5629742741584778, "learning_rate": 9.563579177935844e-06, "loss": 1.298537015914917, "step": 350 }, { "epoch": 0.7441860465116279, "grad_norm": 1.5626896619796753, "learning_rate": 9.556794889476687e-06, "loss": 1.1531531810760498, "step": 352 }, { "epoch": 0.7484143763213531, "grad_norm": 1.946495532989502, "learning_rate": 9.549961005070161e-06, "loss": 0.6979737281799316, "step": 354 }, { "epoch": 0.7526427061310782, "grad_norm": 1.4085379838943481, "learning_rate": 9.543077608263245e-06, "loss": 1.0255022048950195, "step": 356 }, { "epoch": 0.7568710359408034, "grad_norm": 0.5378590226173401, "learning_rate": 9.536144783208229e-06, "loss": 1.2088229656219482, "step": 358 }, { "epoch": 0.7610993657505285, "grad_norm": 3.1184542179107666, "learning_rate": 9.529162614661687e-06, "loss": 0.7745996713638306, "step": 360 }, { "epoch": 0.7653276955602537, "grad_norm": 0.9173505306243896, "learning_rate": 9.522131187983433e-06, "loss": 1.0746722221374512, "step": 362 }, { "epoch": 0.7695560253699789, "grad_norm": 1.1630723476409912, "learning_rate": 9.515050589135485e-06, "loss": 1.0714057683944702, "step": 364 }, { "epoch": 0.773784355179704, "grad_norm": 0.9946353435516357, "learning_rate": 9.507920904681006e-06, "loss": 1.2642713785171509, "step": 366 }, { "epoch": 0.7780126849894292, "grad_norm": 0.6960881948471069, "learning_rate": 9.500742221783257e-06, "loss": 1.2090951204299927, "step": 368 }, { "epoch": 0.7822410147991543, "grad_norm": 1.4127271175384521, "learning_rate": 9.493514628204516e-06, "loss": 0.8742026090621948, "step": 370 }, { "epoch": 0.7864693446088795, "grad_norm": 1.0301803350448608, "learning_rate": 9.48623821230502e-06, "loss": 1.1914252042770386, "step": 372 }, { "epoch": 0.7906976744186046, "grad_norm": 1.0120967626571655, "learning_rate": 9.478913063041878e-06, "loss": 1.2108261585235596, "step": 374 }, { "epoch": 0.7949260042283298, "grad_norm": 0.8601047396659851, "learning_rate": 9.471539269967982e-06, "loss": 1.2950687408447266, "step": 376 }, { "epoch": 0.7991543340380549, "grad_norm": 0.9893262386322021, "learning_rate": 9.464116923230913e-06, "loss": 0.9722433686256409, "step": 378 }, { "epoch": 0.8033826638477801, "grad_norm": 1.28228759765625, "learning_rate": 9.456646113571844e-06, "loss": 1.3107208013534546, "step": 380 }, { "epoch": 0.8076109936575053, "grad_norm": 1.0441747903823853, "learning_rate": 9.449126932324424e-06, "loss": 1.1706490516662598, "step": 382 }, { "epoch": 0.8118393234672304, "grad_norm": 1.4109338521957397, "learning_rate": 9.441559471413665e-06, "loss": 0.9594972729682922, "step": 384 }, { "epoch": 0.8160676532769556, "grad_norm": 0.7071629762649536, "learning_rate": 9.433943823354816e-06, "loss": 0.9540708661079407, "step": 386 }, { "epoch": 0.8202959830866807, "grad_norm": 0.6447687149047852, "learning_rate": 9.426280081252232e-06, "loss": 1.47337806224823, "step": 388 }, { "epoch": 0.8245243128964059, "grad_norm": 1.4983271360397339, "learning_rate": 9.418568338798245e-06, "loss": 1.1582156419754028, "step": 390 }, { "epoch": 0.828752642706131, "grad_norm": 1.804780125617981, "learning_rate": 9.410808690271999e-06, "loss": 0.9358462691307068, "step": 392 }, { "epoch": 0.8329809725158562, "grad_norm": 0.6076309680938721, "learning_rate": 9.40300123053832e-06, "loss": 1.24779212474823, "step": 394 }, { "epoch": 0.8372093023255814, "grad_norm": 0.28070423007011414, "learning_rate": 9.395146055046535e-06, "loss": 0.7603135108947754, "step": 396 }, { "epoch": 0.8414376321353065, "grad_norm": 0.504742443561554, "learning_rate": 9.387243259829323e-06, "loss": 0.6789602041244507, "step": 398 }, { "epoch": 0.8456659619450317, "grad_norm": 1.1221299171447754, "learning_rate": 9.37929294150153e-06, "loss": 1.1268844604492188, "step": 400 }, { "epoch": 0.8498942917547568, "grad_norm": 0.9061374664306641, "learning_rate": 9.371295197258992e-06, "loss": 0.9392963647842407, "step": 402 }, { "epoch": 0.854122621564482, "grad_norm": 0.7222527265548706, "learning_rate": 9.363250124877345e-06, "loss": 0.8021476864814758, "step": 404 }, { "epoch": 0.8583509513742071, "grad_norm": 23.535512924194336, "learning_rate": 9.35515782271083e-06, "loss": 0.9895179867744446, "step": 406 }, { "epoch": 0.8625792811839323, "grad_norm": 0.7281707525253296, "learning_rate": 9.347018389691093e-06, "loss": 0.9979851841926575, "step": 408 }, { "epoch": 0.8668076109936576, "grad_norm": 1.874540090560913, "learning_rate": 9.338831925325974e-06, "loss": 0.9071183800697327, "step": 410 }, { "epoch": 0.8710359408033826, "grad_norm": 1.2659622430801392, "learning_rate": 9.330598529698287e-06, "loss": 1.1477982997894287, "step": 412 }, { "epoch": 0.8752642706131079, "grad_norm": 1.1179678440093994, "learning_rate": 9.322318303464603e-06, "loss": 1.0028682947158813, "step": 414 }, { "epoch": 0.879492600422833, "grad_norm": 1.088289499282837, "learning_rate": 9.313991347854015e-06, "loss": 1.096925973892212, "step": 416 }, { "epoch": 0.8837209302325582, "grad_norm": 0.6234061121940613, "learning_rate": 9.305617764666897e-06, "loss": 1.2145588397979736, "step": 418 }, { "epoch": 0.8879492600422833, "grad_norm": 1.29591703414917, "learning_rate": 9.297197656273672e-06, "loss": 1.156320333480835, "step": 420 }, { "epoch": 0.8921775898520085, "grad_norm": 1.4481463432312012, "learning_rate": 9.288731125613544e-06, "loss": 0.9453005790710449, "step": 422 }, { "epoch": 0.8964059196617337, "grad_norm": 0.7826648950576782, "learning_rate": 9.280218276193255e-06, "loss": 1.2269973754882812, "step": 424 }, { "epoch": 0.9006342494714588, "grad_norm": 0.6516926288604736, "learning_rate": 9.271659212085807e-06, "loss": 1.058658242225647, "step": 426 }, { "epoch": 0.904862579281184, "grad_norm": 0.8274529576301575, "learning_rate": 9.263054037929199e-06, "loss": 0.8633009791374207, "step": 428 }, { "epoch": 0.9090909090909091, "grad_norm": 0.9198406934738159, "learning_rate": 9.254402858925142e-06, "loss": 1.0801507234573364, "step": 430 }, { "epoch": 0.9133192389006343, "grad_norm": 1.1555202007293701, "learning_rate": 9.245705780837774e-06, "loss": 1.2459765672683716, "step": 432 }, { "epoch": 0.9175475687103594, "grad_norm": 1.5631474256515503, "learning_rate": 9.236962909992368e-06, "loss": 0.5561278462409973, "step": 434 }, { "epoch": 0.9217758985200846, "grad_norm": 2.41259503364563, "learning_rate": 9.228174353274037e-06, "loss": 0.39306020736694336, "step": 436 }, { "epoch": 0.9260042283298098, "grad_norm": 0.8015442490577698, "learning_rate": 9.219340218126413e-06, "loss": 0.9175229668617249, "step": 438 }, { "epoch": 0.9302325581395349, "grad_norm": 0.7356842160224915, "learning_rate": 9.210460612550348e-06, "loss": 1.1449198722839355, "step": 440 }, { "epoch": 0.9344608879492601, "grad_norm": 1.1924517154693604, "learning_rate": 9.20153564510259e-06, "loss": 0.7226524353027344, "step": 442 }, { "epoch": 0.9386892177589852, "grad_norm": 0.9468952417373657, "learning_rate": 9.19256542489445e-06, "loss": 1.2537710666656494, "step": 444 }, { "epoch": 0.9429175475687104, "grad_norm": 1.3517422676086426, "learning_rate": 9.183550061590476e-06, "loss": 1.0967553853988647, "step": 446 }, { "epoch": 0.9471458773784355, "grad_norm": 3.633507013320923, "learning_rate": 9.174489665407103e-06, "loss": 1.180832862854004, "step": 448 }, { "epoch": 0.9513742071881607, "grad_norm": 8.533449172973633, "learning_rate": 9.165384347111317e-06, "loss": 0.7824639081954956, "step": 450 }, { "epoch": 0.9556025369978859, "grad_norm": 0.5860720872879028, "learning_rate": 9.156234218019291e-06, "loss": 0.9444847702980042, "step": 452 }, { "epoch": 0.959830866807611, "grad_norm": 1.1931580305099487, "learning_rate": 9.147039389995029e-06, "loss": 1.320864200592041, "step": 454 }, { "epoch": 0.9640591966173362, "grad_norm": 1.0810269117355347, "learning_rate": 9.137799975448998e-06, "loss": 0.6557315587997437, "step": 456 }, { "epoch": 0.9682875264270613, "grad_norm": 1.8171831369400024, "learning_rate": 9.128516087336755e-06, "loss": 0.8884165287017822, "step": 458 }, { "epoch": 0.9725158562367865, "grad_norm": 0.8831843733787537, "learning_rate": 9.119187839157559e-06, "loss": 1.2318710088729858, "step": 460 }, { "epoch": 0.9767441860465116, "grad_norm": 2.8324692249298096, "learning_rate": 9.109815344952995e-06, "loss": 1.2145814895629883, "step": 462 }, { "epoch": 0.9809725158562368, "grad_norm": 1.251635193824768, "learning_rate": 9.100398719305566e-06, "loss": 0.7142945528030396, "step": 464 }, { "epoch": 0.985200845665962, "grad_norm": 0.7984769940376282, "learning_rate": 9.090938077337305e-06, "loss": 1.2117208242416382, "step": 466 }, { "epoch": 0.9894291754756871, "grad_norm": 1.7162734270095825, "learning_rate": 9.081433534708363e-06, "loss": 0.9912998676300049, "step": 468 }, { "epoch": 0.9936575052854123, "grad_norm": 0.8476374745368958, "learning_rate": 9.071885207615591e-06, "loss": 1.2481656074523926, "step": 470 }, { "epoch": 0.9978858350951374, "grad_norm": 1.907009482383728, "learning_rate": 9.062293212791123e-06, "loss": 1.247841238975525, "step": 472 }, { "epoch": 1.0021141649048626, "grad_norm": 1.6060584783554077, "learning_rate": 9.052657667500951e-06, "loss": 0.9835132956504822, "step": 474 }, { "epoch": 1.0063424947145878, "grad_norm": 0.7279644012451172, "learning_rate": 9.042978689543487e-06, "loss": 1.1604242324829102, "step": 476 }, { "epoch": 1.0105708245243128, "grad_norm": 3.146939992904663, "learning_rate": 9.033256397248124e-06, "loss": 0.4403705894947052, "step": 478 }, { "epoch": 1.014799154334038, "grad_norm": 2.115751028060913, "learning_rate": 9.02349090947379e-06, "loss": 0.7868874073028564, "step": 480 }, { "epoch": 1.0190274841437632, "grad_norm": 1.1618353128433228, "learning_rate": 9.013682345607502e-06, "loss": 0.6736200451850891, "step": 482 }, { "epoch": 1.0232558139534884, "grad_norm": 0.7894169092178345, "learning_rate": 9.003830825562887e-06, "loss": 1.0246351957321167, "step": 484 }, { "epoch": 1.0274841437632136, "grad_norm": 2.281885862350464, "learning_rate": 8.99393646977874e-06, "loss": 1.0766233205795288, "step": 486 }, { "epoch": 1.0317124735729386, "grad_norm": 4.022132873535156, "learning_rate": 8.983999399217536e-06, "loss": 0.9054970741271973, "step": 488 }, { "epoch": 1.0359408033826638, "grad_norm": 1.8047136068344116, "learning_rate": 8.974019735363952e-06, "loss": 0.8942304849624634, "step": 490 }, { "epoch": 1.040169133192389, "grad_norm": 3.0607986450195312, "learning_rate": 8.963997600223387e-06, "loss": 0.7784489989280701, "step": 492 }, { "epoch": 1.0443974630021142, "grad_norm": 1.7200645208358765, "learning_rate": 8.953933116320474e-06, "loss": 1.1436198949813843, "step": 494 }, { "epoch": 1.0486257928118394, "grad_norm": 0.8405398726463318, "learning_rate": 8.943826406697569e-06, "loss": 0.9646798968315125, "step": 496 }, { "epoch": 1.0528541226215644, "grad_norm": 0.7459695339202881, "learning_rate": 8.93367759491326e-06, "loss": 0.8522624969482422, "step": 498 }, { "epoch": 1.0570824524312896, "grad_norm": 0.7076525092124939, "learning_rate": 8.923486805040845e-06, "loss": 0.8505243062973022, "step": 500 }, { "epoch": 1.0613107822410148, "grad_norm": 0.6507482528686523, "learning_rate": 8.913254161666828e-06, "loss": 1.1239882707595825, "step": 502 }, { "epoch": 1.06553911205074, "grad_norm": 1.9743882417678833, "learning_rate": 8.902979789889382e-06, "loss": 1.118302345275879, "step": 504 }, { "epoch": 1.069767441860465, "grad_norm": 0.939518392086029, "learning_rate": 8.892663815316833e-06, "loss": 0.8027561902999878, "step": 506 }, { "epoch": 1.0739957716701902, "grad_norm": 0.8137811422348022, "learning_rate": 8.882306364066114e-06, "loss": 0.771781325340271, "step": 508 }, { "epoch": 1.0782241014799154, "grad_norm": 8.003303527832031, "learning_rate": 8.871907562761226e-06, "loss": 0.9428013563156128, "step": 510 }, { "epoch": 1.0824524312896406, "grad_norm": 0.8237425684928894, "learning_rate": 8.861467538531692e-06, "loss": 1.044594407081604, "step": 512 }, { "epoch": 1.0866807610993658, "grad_norm": 1.1039520502090454, "learning_rate": 8.850986419011006e-06, "loss": 1.1451327800750732, "step": 514 }, { "epoch": 1.0909090909090908, "grad_norm": 0.9447864890098572, "learning_rate": 8.840464332335062e-06, "loss": 0.8437500596046448, "step": 516 }, { "epoch": 1.095137420718816, "grad_norm": 1.1295294761657715, "learning_rate": 8.829901407140599e-06, "loss": 0.8714098930358887, "step": 518 }, { "epoch": 1.0993657505285412, "grad_norm": 1.4012198448181152, "learning_rate": 8.81929777256362e-06, "loss": 0.6220742464065552, "step": 520 }, { "epoch": 1.1035940803382664, "grad_norm": 1.0783562660217285, "learning_rate": 8.808653558237818e-06, "loss": 1.254813313484192, "step": 522 }, { "epoch": 1.1078224101479917, "grad_norm": 1.3354991674423218, "learning_rate": 8.797968894292992e-06, "loss": 0.7741164565086365, "step": 524 }, { "epoch": 1.1120507399577166, "grad_norm": 0.9223580360412598, "learning_rate": 8.787243911353447e-06, "loss": 1.333195686340332, "step": 526 }, { "epoch": 1.1162790697674418, "grad_norm": 0.6381306648254395, "learning_rate": 8.776478740536409e-06, "loss": 0.8335105180740356, "step": 528 }, { "epoch": 1.120507399577167, "grad_norm": 1.2061214447021484, "learning_rate": 8.76567351345042e-06, "loss": 0.49696025252342224, "step": 530 }, { "epoch": 1.1247357293868923, "grad_norm": 1.018559217453003, "learning_rate": 8.754828362193719e-06, "loss": 0.9994657039642334, "step": 532 }, { "epoch": 1.1289640591966172, "grad_norm": 0.9211387634277344, "learning_rate": 8.743943419352638e-06, "loss": 0.8971555829048157, "step": 534 }, { "epoch": 1.1331923890063424, "grad_norm": 0.47905275225639343, "learning_rate": 8.733018817999977e-06, "loss": 0.8626320958137512, "step": 536 }, { "epoch": 1.1374207188160677, "grad_norm": 1.0224030017852783, "learning_rate": 8.722054691693374e-06, "loss": 0.7981321215629578, "step": 538 }, { "epoch": 1.1416490486257929, "grad_norm": 1.224251627922058, "learning_rate": 8.711051174473682e-06, "loss": 0.7100337147712708, "step": 540 }, { "epoch": 1.145877378435518, "grad_norm": 0.8156324028968811, "learning_rate": 8.700008400863316e-06, "loss": 1.0931334495544434, "step": 542 }, { "epoch": 1.150105708245243, "grad_norm": 4.605739116668701, "learning_rate": 8.688926505864624e-06, "loss": 0.7602072358131409, "step": 544 }, { "epoch": 1.1543340380549683, "grad_norm": 0.6760260462760925, "learning_rate": 8.67780562495822e-06, "loss": 1.1434330940246582, "step": 546 }, { "epoch": 1.1585623678646935, "grad_norm": 1.7282962799072266, "learning_rate": 8.666645894101346e-06, "loss": 1.365561604499817, "step": 548 }, { "epoch": 1.1627906976744187, "grad_norm": 1.0927338600158691, "learning_rate": 8.655447449726189e-06, "loss": 0.7638922929763794, "step": 550 }, { "epoch": 1.1670190274841437, "grad_norm": 2.514376163482666, "learning_rate": 8.644210428738237e-06, "loss": 1.0670771598815918, "step": 552 }, { "epoch": 1.1712473572938689, "grad_norm": 1.0463567972183228, "learning_rate": 8.632934968514582e-06, "loss": 1.1643266677856445, "step": 554 }, { "epoch": 1.175475687103594, "grad_norm": 1.195021152496338, "learning_rate": 8.621621206902256e-06, "loss": 1.051544427871704, "step": 556 }, { "epoch": 1.1797040169133193, "grad_norm": 0.6516265273094177, "learning_rate": 8.61026928221654e-06, "loss": 1.0537703037261963, "step": 558 }, { "epoch": 1.1839323467230445, "grad_norm": 1.209865689277649, "learning_rate": 8.598879333239274e-06, "loss": 0.9948523044586182, "step": 560 }, { "epoch": 1.1881606765327695, "grad_norm": 1.2186599969863892, "learning_rate": 8.587451499217161e-06, "loss": 0.7878570556640625, "step": 562 }, { "epoch": 1.1923890063424947, "grad_norm": 0.8391376733779907, "learning_rate": 8.575985919860065e-06, "loss": 1.0550987720489502, "step": 564 }, { "epoch": 1.1966173361522199, "grad_norm": 1.5875688791275024, "learning_rate": 8.564482735339296e-06, "loss": 0.8893521428108215, "step": 566 }, { "epoch": 1.200845665961945, "grad_norm": 2.573927640914917, "learning_rate": 8.552942086285909e-06, "loss": 1.211724042892456, "step": 568 }, { "epoch": 1.20507399577167, "grad_norm": 2.2146034240722656, "learning_rate": 8.541364113788974e-06, "loss": 1.151242971420288, "step": 570 }, { "epoch": 1.2093023255813953, "grad_norm": 1.2212947607040405, "learning_rate": 8.529748959393855e-06, "loss": 1.0029034614562988, "step": 572 }, { "epoch": 1.2135306553911205, "grad_norm": 0.5558222532272339, "learning_rate": 8.518096765100485e-06, "loss": 0.7854599356651306, "step": 574 }, { "epoch": 1.2177589852008457, "grad_norm": 1.7243967056274414, "learning_rate": 8.50640767336162e-06, "loss": 0.773718535900116, "step": 576 }, { "epoch": 1.221987315010571, "grad_norm": 0.7746381759643555, "learning_rate": 8.494681827081096e-06, "loss": 0.918204128742218, "step": 578 }, { "epoch": 1.226215644820296, "grad_norm": 1.1792914867401123, "learning_rate": 8.482919369612103e-06, "loss": 0.8192765712738037, "step": 580 }, { "epoch": 1.230443974630021, "grad_norm": 1.1007940769195557, "learning_rate": 8.471120444755405e-06, "loss": 1.0946714878082275, "step": 582 }, { "epoch": 1.2346723044397463, "grad_norm": 1.213613748550415, "learning_rate": 8.4592851967576e-06, "loss": 0.8407611846923828, "step": 584 }, { "epoch": 1.2389006342494715, "grad_norm": 2.601245641708374, "learning_rate": 8.447413770309349e-06, "loss": 0.8317906260490417, "step": 586 }, { "epoch": 1.2431289640591967, "grad_norm": 2.1182992458343506, "learning_rate": 8.435506310543607e-06, "loss": 0.8845577239990234, "step": 588 }, { "epoch": 1.2473572938689217, "grad_norm": 0.3484657108783722, "learning_rate": 8.42356296303386e-06, "loss": 0.6100149750709534, "step": 590 }, { "epoch": 1.251585623678647, "grad_norm": 0.383044570684433, "learning_rate": 8.411583873792325e-06, "loss": 0.9404579997062683, "step": 592 }, { "epoch": 1.255813953488372, "grad_norm": 2.4902472496032715, "learning_rate": 8.399569189268182e-06, "loss": 1.1017520427703857, "step": 594 }, { "epoch": 1.2600422832980973, "grad_norm": 0.7992575168609619, "learning_rate": 8.387519056345778e-06, "loss": 0.7367591857910156, "step": 596 }, { "epoch": 1.2642706131078225, "grad_norm": 1.1948211193084717, "learning_rate": 8.375433622342824e-06, "loss": 1.0909743309020996, "step": 598 }, { "epoch": 1.2684989429175475, "grad_norm": 1.5478065013885498, "learning_rate": 8.363313035008613e-06, "loss": 1.285573959350586, "step": 600 }, { "epoch": 1.2727272727272727, "grad_norm": 0.5360077619552612, "learning_rate": 8.351157442522187e-06, "loss": 0.9145334959030151, "step": 602 }, { "epoch": 1.276955602536998, "grad_norm": 1.883304476737976, "learning_rate": 8.338966993490554e-06, "loss": 1.0761122703552246, "step": 604 }, { "epoch": 1.2811839323467231, "grad_norm": 1.591342568397522, "learning_rate": 8.326741836946852e-06, "loss": 0.7882466316223145, "step": 606 }, { "epoch": 1.285412262156448, "grad_norm": 0.8462498188018799, "learning_rate": 8.314482122348523e-06, "loss": 1.1010057926177979, "step": 608 }, { "epoch": 1.2896405919661733, "grad_norm": 0.7714747190475464, "learning_rate": 8.30218799957551e-06, "loss": 0.7261500358581543, "step": 610 }, { "epoch": 1.2938689217758985, "grad_norm": 1.234446406364441, "learning_rate": 8.289859618928404e-06, "loss": 0.6313963532447815, "step": 612 }, { "epoch": 1.2980972515856237, "grad_norm": 0.8163169026374817, "learning_rate": 8.277497131126608e-06, "loss": 0.8454522490501404, "step": 614 }, { "epoch": 1.302325581395349, "grad_norm": 1.0129764080047607, "learning_rate": 8.265100687306503e-06, "loss": 0.5041049122810364, "step": 616 }, { "epoch": 1.306553911205074, "grad_norm": 5.104666233062744, "learning_rate": 8.252670439019595e-06, "loss": 0.8745758533477783, "step": 618 }, { "epoch": 1.3107822410147991, "grad_norm": 0.8068632483482361, "learning_rate": 8.240206538230663e-06, "loss": 1.1073535680770874, "step": 620 }, { "epoch": 1.3150105708245243, "grad_norm": 0.5171518921852112, "learning_rate": 8.227709137315905e-06, "loss": 1.0346919298171997, "step": 622 }, { "epoch": 1.3192389006342495, "grad_norm": 1.478652000427246, "learning_rate": 8.215178389061064e-06, "loss": 0.658608615398407, "step": 624 }, { "epoch": 1.3234672304439745, "grad_norm": 0.7360924482345581, "learning_rate": 8.202614446659572e-06, "loss": 1.1715048551559448, "step": 626 }, { "epoch": 1.3276955602536997, "grad_norm": 1.6009150743484497, "learning_rate": 8.190017463710675e-06, "loss": 1.2271811962127686, "step": 628 }, { "epoch": 1.331923890063425, "grad_norm": 2.7243692874908447, "learning_rate": 8.177387594217548e-06, "loss": 0.969451904296875, "step": 630 }, { "epoch": 1.3361522198731501, "grad_norm": 0.7724528312683105, "learning_rate": 8.164724992585421e-06, "loss": 0.5695827007293701, "step": 632 }, { "epoch": 1.3403805496828753, "grad_norm": 0.8863224387168884, "learning_rate": 8.152029813619685e-06, "loss": 0.6862818002700806, "step": 634 }, { "epoch": 1.3446088794926006, "grad_norm": 0.5899203419685364, "learning_rate": 8.139302212524006e-06, "loss": 0.724890410900116, "step": 636 }, { "epoch": 1.3488372093023255, "grad_norm": 1.5803217887878418, "learning_rate": 8.126542344898419e-06, "loss": 1.0172871351242065, "step": 638 }, { "epoch": 1.3530655391120507, "grad_norm": 0.46476396918296814, "learning_rate": 8.113750366737431e-06, "loss": 0.7037006616592407, "step": 640 }, { "epoch": 1.357293868921776, "grad_norm": 0.6399050951004028, "learning_rate": 8.100926434428116e-06, "loss": 1.1906646490097046, "step": 642 }, { "epoch": 1.361522198731501, "grad_norm": 0.757767379283905, "learning_rate": 8.0880707047482e-06, "loss": 1.0581393241882324, "step": 644 }, { "epoch": 1.3657505285412261, "grad_norm": 1.6296606063842773, "learning_rate": 8.075183334864139e-06, "loss": 0.7375378012657166, "step": 646 }, { "epoch": 1.3699788583509513, "grad_norm": 2.3918702602386475, "learning_rate": 8.062264482329209e-06, "loss": 0.6977914571762085, "step": 648 }, { "epoch": 1.3742071881606766, "grad_norm": 7.050395488739014, "learning_rate": 8.049314305081575e-06, "loss": 0.7684383392333984, "step": 650 }, { "epoch": 1.3784355179704018, "grad_norm": 0.6664375066757202, "learning_rate": 8.036332961442355e-06, "loss": 0.7362555861473083, "step": 652 }, { "epoch": 1.382663847780127, "grad_norm": 1.0791950225830078, "learning_rate": 8.023320610113691e-06, "loss": 1.1517345905303955, "step": 654 }, { "epoch": 1.386892177589852, "grad_norm": 1.2541245222091675, "learning_rate": 8.010277410176801e-06, "loss": 1.0144686698913574, "step": 656 }, { "epoch": 1.3911205073995772, "grad_norm": 1.6852085590362549, "learning_rate": 7.997203521090053e-06, "loss": 0.8008504509925842, "step": 658 }, { "epoch": 1.3953488372093024, "grad_norm": 0.8540728688240051, "learning_rate": 7.984099102686986e-06, "loss": 0.9210661053657532, "step": 660 }, { "epoch": 1.3995771670190273, "grad_norm": 0.7518090009689331, "learning_rate": 7.970964315174384e-06, "loss": 1.0895636081695557, "step": 662 }, { "epoch": 1.4038054968287526, "grad_norm": 0.3041980266571045, "learning_rate": 7.9577993191303e-06, "loss": 0.9177976250648499, "step": 664 }, { "epoch": 1.4080338266384778, "grad_norm": 0.9373999238014221, "learning_rate": 7.944604275502102e-06, "loss": 1.272640347480774, "step": 666 }, { "epoch": 1.412262156448203, "grad_norm": 0.6827905178070068, "learning_rate": 7.931379345604495e-06, "loss": 1.0844895839691162, "step": 668 }, { "epoch": 1.4164904862579282, "grad_norm": 0.5546096563339233, "learning_rate": 7.918124691117563e-06, "loss": 0.6584613919258118, "step": 670 }, { "epoch": 1.4207188160676534, "grad_norm": 0.549161434173584, "learning_rate": 7.904840474084783e-06, "loss": 1.0463613271713257, "step": 672 }, { "epoch": 1.4249471458773784, "grad_norm": 0.7908539772033691, "learning_rate": 7.891526856911046e-06, "loss": 0.5788865685462952, "step": 674 }, { "epoch": 1.4291754756871036, "grad_norm": 1.6930519342422485, "learning_rate": 7.878184002360664e-06, "loss": 0.7770503163337708, "step": 676 }, { "epoch": 1.4334038054968288, "grad_norm": 0.754484236240387, "learning_rate": 7.864812073555402e-06, "loss": 1.2981189489364624, "step": 678 }, { "epoch": 1.437632135306554, "grad_norm": 1.2011444568634033, "learning_rate": 7.851411233972461e-06, "loss": 1.1564751863479614, "step": 680 }, { "epoch": 1.441860465116279, "grad_norm": 1.7061071395874023, "learning_rate": 7.837981647442486e-06, "loss": 1.1295804977416992, "step": 682 }, { "epoch": 1.4460887949260042, "grad_norm": 0.684702455997467, "learning_rate": 7.82452347814757e-06, "loss": 1.0844454765319824, "step": 684 }, { "epoch": 1.4503171247357294, "grad_norm": 1.4343141317367554, "learning_rate": 7.811036890619239e-06, "loss": 1.4134005308151245, "step": 686 }, { "epoch": 1.4545454545454546, "grad_norm": 0.7010160684585571, "learning_rate": 7.797522049736441e-06, "loss": 1.004253625869751, "step": 688 }, { "epoch": 1.4587737843551798, "grad_norm": 2.5509250164031982, "learning_rate": 7.78397912072354e-06, "loss": 0.397754967212677, "step": 690 }, { "epoch": 1.463002114164905, "grad_norm": 0.5985687375068665, "learning_rate": 7.770408269148281e-06, "loss": 1.1248722076416016, "step": 692 }, { "epoch": 1.46723044397463, "grad_norm": 4.1934099197387695, "learning_rate": 7.756809660919778e-06, "loss": 0.5213649868965149, "step": 694 }, { "epoch": 1.4714587737843552, "grad_norm": 1.830042839050293, "learning_rate": 7.74318346228648e-06, "loss": 1.062088966369629, "step": 696 }, { "epoch": 1.4756871035940804, "grad_norm": 0.543576717376709, "learning_rate": 7.72952983983414e-06, "loss": 1.1115893125534058, "step": 698 }, { "epoch": 1.4799154334038054, "grad_norm": 0.6739907264709473, "learning_rate": 7.715848960483776e-06, "loss": 0.8902627825737, "step": 700 }, { "epoch": 1.4841437632135306, "grad_norm": 0.5407891869544983, "learning_rate": 7.702140991489637e-06, "loss": 1.0512503385543823, "step": 702 }, { "epoch": 1.4883720930232558, "grad_norm": 0.7547590136528015, "learning_rate": 7.688406100437149e-06, "loss": 0.9831693768501282, "step": 704 }, { "epoch": 1.492600422832981, "grad_norm": 1.1633201837539673, "learning_rate": 7.674644455240878e-06, "loss": 0.7335575222969055, "step": 706 }, { "epoch": 1.4968287526427062, "grad_norm": 0.6175774335861206, "learning_rate": 7.660856224142456e-06, "loss": 0.23118150234222412, "step": 708 }, { "epoch": 1.5010570824524314, "grad_norm": 0.885739266872406, "learning_rate": 7.647041575708555e-06, "loss": 0.6682457327842712, "step": 710 }, { "epoch": 1.5052854122621564, "grad_norm": 2.0240211486816406, "learning_rate": 7.633200678828804e-06, "loss": 0.5503491163253784, "step": 712 }, { "epoch": 1.5095137420718816, "grad_norm": 0.7582908272743225, "learning_rate": 7.6193337027137215e-06, "loss": 0.9636995792388916, "step": 714 }, { "epoch": 1.5137420718816068, "grad_norm": 0.6742231845855713, "learning_rate": 7.605440816892667e-06, "loss": 1.064170479774475, "step": 716 }, { "epoch": 1.5179704016913318, "grad_norm": 0.7157659530639648, "learning_rate": 7.591522191211746e-06, "loss": 0.9279001951217651, "step": 718 }, { "epoch": 1.522198731501057, "grad_norm": 0.28072383999824524, "learning_rate": 7.577577995831755e-06, "loss": 0.8852240443229675, "step": 720 }, { "epoch": 1.5264270613107822, "grad_norm": 7.226950168609619, "learning_rate": 7.563608401226081e-06, "loss": 0.8385710716247559, "step": 722 }, { "epoch": 1.5306553911205074, "grad_norm": 1.0841549634933472, "learning_rate": 7.549613578178632e-06, "loss": 0.8861169815063477, "step": 724 }, { "epoch": 1.5348837209302326, "grad_norm": 1.0169841051101685, "learning_rate": 7.535593697781741e-06, "loss": 0.8674405217170715, "step": 726 }, { "epoch": 1.5391120507399578, "grad_norm": 1.079416275024414, "learning_rate": 7.52154893143408e-06, "loss": 0.5989157557487488, "step": 728 }, { "epoch": 1.543340380549683, "grad_norm": 1.846366047859192, "learning_rate": 7.50747945083856e-06, "loss": 0.8259937167167664, "step": 730 }, { "epoch": 1.547568710359408, "grad_norm": 0.5139471292495728, "learning_rate": 7.493385428000234e-06, "loss": 1.036810278892517, "step": 732 }, { "epoch": 1.5517970401691332, "grad_norm": 0.7547844052314758, "learning_rate": 7.479267035224191e-06, "loss": 0.22945381700992584, "step": 734 }, { "epoch": 1.5560253699788582, "grad_norm": 0.6049753427505493, "learning_rate": 7.465124445113459e-06, "loss": 0.9986231327056885, "step": 736 }, { "epoch": 1.5602536997885834, "grad_norm": 0.3699362874031067, "learning_rate": 7.450957830566878e-06, "loss": 0.7463698983192444, "step": 738 }, { "epoch": 1.5644820295983086, "grad_norm": 0.943959653377533, "learning_rate": 7.436767364777009e-06, "loss": 1.114400863647461, "step": 740 }, { "epoch": 1.5687103594080338, "grad_norm": 4.1429443359375, "learning_rate": 7.422553221227993e-06, "loss": 0.7858623266220093, "step": 742 }, { "epoch": 1.572938689217759, "grad_norm": 1.3906772136688232, "learning_rate": 7.4083155736934484e-06, "loss": 1.0840264558792114, "step": 744 }, { "epoch": 1.5771670190274842, "grad_norm": 1.1453956365585327, "learning_rate": 7.394054596234336e-06, "loss": 1.167376160621643, "step": 746 }, { "epoch": 1.5813953488372094, "grad_norm": 0.8556895852088928, "learning_rate": 7.379770463196831e-06, "loss": 0.8940363526344299, "step": 748 }, { "epoch": 1.5856236786469344, "grad_norm": 0.28730180859565735, "learning_rate": 7.365463349210203e-06, "loss": 0.07522695511579514, "step": 750 }, { "epoch": 1.5898520084566596, "grad_norm": 1.8237755298614502, "learning_rate": 7.351133429184666e-06, "loss": 0.8569766283035278, "step": 752 }, { "epoch": 1.5940803382663846, "grad_norm": 0.894396960735321, "learning_rate": 7.336780878309251e-06, "loss": 1.1304800510406494, "step": 754 }, { "epoch": 1.5983086680761098, "grad_norm": 1.0380446910858154, "learning_rate": 7.322405872049657e-06, "loss": 1.1127440929412842, "step": 756 }, { "epoch": 1.602536997885835, "grad_norm": 0.640801191329956, "learning_rate": 7.308008586146111e-06, "loss": 1.1162619590759277, "step": 758 }, { "epoch": 1.6067653276955602, "grad_norm": 1.282494068145752, "learning_rate": 7.293589196611221e-06, "loss": 1.1233618259429932, "step": 760 }, { "epoch": 1.6109936575052854, "grad_norm": 1.0078004598617554, "learning_rate": 7.279147879727811e-06, "loss": 1.1028566360473633, "step": 762 }, { "epoch": 1.6152219873150107, "grad_norm": 2.1717910766601562, "learning_rate": 7.264684812046787e-06, "loss": 1.1296380758285522, "step": 764 }, { "epoch": 1.6194503171247359, "grad_norm": 1.7443034648895264, "learning_rate": 7.250200170384961e-06, "loss": 0.8061440587043762, "step": 766 }, { "epoch": 1.6236786469344608, "grad_norm": 0.897519052028656, "learning_rate": 7.235694131822894e-06, "loss": 1.1120456457138062, "step": 768 }, { "epoch": 1.627906976744186, "grad_norm": 1.3329594135284424, "learning_rate": 7.221166873702738e-06, "loss": 1.0576757192611694, "step": 770 }, { "epoch": 1.6321353065539113, "grad_norm": 0.49017030000686646, "learning_rate": 7.206618573626058e-06, "loss": 1.1173020601272583, "step": 772 }, { "epoch": 1.6363636363636362, "grad_norm": 1.794071078300476, "learning_rate": 7.19204940945167e-06, "loss": 0.7875913977622986, "step": 774 }, { "epoch": 1.6405919661733614, "grad_norm": 0.8205191493034363, "learning_rate": 7.177459559293456e-06, "loss": 1.0946446657180786, "step": 776 }, { "epoch": 1.6448202959830867, "grad_norm": 1.4755090475082397, "learning_rate": 7.162849201518198e-06, "loss": 0.6944856643676758, "step": 778 }, { "epoch": 1.6490486257928119, "grad_norm": 0.7227916121482849, "learning_rate": 7.1482185147433905e-06, "loss": 1.0544497966766357, "step": 780 }, { "epoch": 1.653276955602537, "grad_norm": 0.5240799784660339, "learning_rate": 7.133567677835055e-06, "loss": 0.8035492300987244, "step": 782 }, { "epoch": 1.6575052854122623, "grad_norm": 0.6655469536781311, "learning_rate": 7.11889686990556e-06, "loss": 1.1894352436065674, "step": 784 }, { "epoch": 1.6617336152219875, "grad_norm": 1.3654241561889648, "learning_rate": 7.104206270311423e-06, "loss": 0.49121612310409546, "step": 786 }, { "epoch": 1.6659619450317125, "grad_norm": 1.331206202507019, "learning_rate": 7.089496058651133e-06, "loss": 1.1029548645019531, "step": 788 }, { "epoch": 1.6701902748414377, "grad_norm": 0.6633784174919128, "learning_rate": 7.0747664147629335e-06, "loss": 0.743760347366333, "step": 790 }, { "epoch": 1.6744186046511627, "grad_norm": 0.7696189880371094, "learning_rate": 7.060017518722637e-06, "loss": 0.428589403629303, "step": 792 }, { "epoch": 1.6786469344608879, "grad_norm": 0.5027663111686707, "learning_rate": 7.0452495508414276e-06, "loss": 1.063642978668213, "step": 794 }, { "epoch": 1.682875264270613, "grad_norm": 0.5724061727523804, "learning_rate": 7.030462691663641e-06, "loss": 0.6203397512435913, "step": 796 }, { "epoch": 1.6871035940803383, "grad_norm": 0.576188862323761, "learning_rate": 7.015657121964575e-06, "loss": 1.1779401302337646, "step": 798 }, { "epoch": 1.6913319238900635, "grad_norm": 0.4546792209148407, "learning_rate": 7.000833022748267e-06, "loss": 1.087310552597046, "step": 800 }, { "epoch": 1.6955602536997887, "grad_norm": 2.540952682495117, "learning_rate": 6.985990575245283e-06, "loss": 0.6117699146270752, "step": 802 }, { "epoch": 1.699788583509514, "grad_norm": 0.41943123936653137, "learning_rate": 6.97112996091051e-06, "loss": 1.0537569522857666, "step": 804 }, { "epoch": 1.7040169133192389, "grad_norm": 3.9632315635681152, "learning_rate": 6.956251361420926e-06, "loss": 0.7865187525749207, "step": 806 }, { "epoch": 1.708245243128964, "grad_norm": 8.233223915100098, "learning_rate": 6.94135495867339e-06, "loss": 0.7174930572509766, "step": 808 }, { "epoch": 1.712473572938689, "grad_norm": 0.7673368453979492, "learning_rate": 6.926440934782407e-06, "loss": 1.0891451835632324, "step": 810 }, { "epoch": 1.7167019027484143, "grad_norm": 1.7779408693313599, "learning_rate": 6.9115094720779155e-06, "loss": 1.307787537574768, "step": 812 }, { "epoch": 1.7209302325581395, "grad_norm": 0.8004451990127563, "learning_rate": 6.896560753103041e-06, "loss": 1.075011134147644, "step": 814 }, { "epoch": 1.7251585623678647, "grad_norm": 0.6611381769180298, "learning_rate": 6.881594960611881e-06, "loss": 1.134852647781372, "step": 816 }, { "epoch": 1.72938689217759, "grad_norm": 0.623605489730835, "learning_rate": 6.866612277567261e-06, "loss": 0.9129635095596313, "step": 818 }, { "epoch": 1.733615221987315, "grad_norm": 28.886743545532227, "learning_rate": 6.851612887138501e-06, "loss": 0.9819934964179993, "step": 820 }, { "epoch": 1.7378435517970403, "grad_norm": 1.1009865999221802, "learning_rate": 6.836596972699175e-06, "loss": 0.6983782649040222, "step": 822 }, { "epoch": 1.7420718816067653, "grad_norm": 0.317523330450058, "learning_rate": 6.82156471782487e-06, "loss": 0.649151623249054, "step": 824 }, { "epoch": 1.7463002114164905, "grad_norm": 6.080481052398682, "learning_rate": 6.806516306290942e-06, "loss": 0.9291117787361145, "step": 826 }, { "epoch": 1.7505285412262155, "grad_norm": 2.209254026412964, "learning_rate": 6.791451922070265e-06, "loss": 0.924919605255127, "step": 828 }, { "epoch": 1.7547568710359407, "grad_norm": 2.6113362312316895, "learning_rate": 6.77637174933099e-06, "loss": 0.7574297785758972, "step": 830 }, { "epoch": 1.758985200845666, "grad_norm": 0.8396579027175903, "learning_rate": 6.7612759724342895e-06, "loss": 1.164949893951416, "step": 832 }, { "epoch": 1.763213530655391, "grad_norm": 3.376640796661377, "learning_rate": 6.746164775932096e-06, "loss": 0.8233012557029724, "step": 834 }, { "epoch": 1.7674418604651163, "grad_norm": 0.5275226831436157, "learning_rate": 6.731038344564862e-06, "loss": 0.8249943256378174, "step": 836 }, { "epoch": 1.7716701902748415, "grad_norm": 0.8565027713775635, "learning_rate": 6.715896863259286e-06, "loss": 1.115562915802002, "step": 838 }, { "epoch": 1.7758985200845667, "grad_norm": 1.2589657306671143, "learning_rate": 6.700740517126061e-06, "loss": 0.8493784070014954, "step": 840 }, { "epoch": 1.7801268498942917, "grad_norm": 17.748231887817383, "learning_rate": 6.685569491457608e-06, "loss": 0.43042904138565063, "step": 842 }, { "epoch": 1.784355179704017, "grad_norm": 0.5341081023216248, "learning_rate": 6.670383971725809e-06, "loss": 0.6800081729888916, "step": 844 }, { "epoch": 1.7885835095137421, "grad_norm": 143.87908935546875, "learning_rate": 6.655184143579746e-06, "loss": 0.9978957772254944, "step": 846 }, { "epoch": 1.792811839323467, "grad_norm": 2.049363613128662, "learning_rate": 6.639970192843423e-06, "loss": 0.7387880086898804, "step": 848 }, { "epoch": 1.7970401691331923, "grad_norm": 1.0592776536941528, "learning_rate": 6.624742305513502e-06, "loss": 0.739241361618042, "step": 850 }, { "epoch": 1.8012684989429175, "grad_norm": 1.0896174907684326, "learning_rate": 6.609500667757022e-06, "loss": 0.9684228301048279, "step": 852 }, { "epoch": 1.8054968287526427, "grad_norm": 0.6536556482315063, "learning_rate": 6.594245465909127e-06, "loss": 0.7564343214035034, "step": 854 }, { "epoch": 1.809725158562368, "grad_norm": 0.5762327909469604, "learning_rate": 6.578976886470791e-06, "loss": 1.0506725311279297, "step": 856 }, { "epoch": 1.8139534883720931, "grad_norm": 0.7170271873474121, "learning_rate": 6.56369511610653e-06, "loss": 0.6205048561096191, "step": 858 }, { "epoch": 1.8181818181818183, "grad_norm": 1.69498872756958, "learning_rate": 6.548400341642128e-06, "loss": 1.014474868774414, "step": 860 }, { "epoch": 1.8224101479915433, "grad_norm": 0.5585842728614807, "learning_rate": 6.533092750062345e-06, "loss": 1.0422030687332153, "step": 862 }, { "epoch": 1.8266384778012685, "grad_norm": 0.5881413221359253, "learning_rate": 6.5177725285086416e-06, "loss": 0.5181625485420227, "step": 864 }, { "epoch": 1.8308668076109935, "grad_norm": 0.6261947751045227, "learning_rate": 6.5024398642768785e-06, "loss": 0.7503539323806763, "step": 866 }, { "epoch": 1.8350951374207187, "grad_norm": 0.4591817259788513, "learning_rate": 6.487094944815036e-06, "loss": 1.108430027961731, "step": 868 }, { "epoch": 1.839323467230444, "grad_norm": 0.876591682434082, "learning_rate": 6.47173795772092e-06, "loss": 1.0922421216964722, "step": 870 }, { "epoch": 1.8435517970401691, "grad_norm": 0.2909030020236969, "learning_rate": 6.456369090739869e-06, "loss": 0.7862840294837952, "step": 872 }, { "epoch": 1.8477801268498943, "grad_norm": 0.5919494032859802, "learning_rate": 6.440988531762454e-06, "loss": 1.0677984952926636, "step": 874 }, { "epoch": 1.8520084566596196, "grad_norm": 2.1568503379821777, "learning_rate": 6.42559646882219e-06, "loss": 0.9604772329330444, "step": 876 }, { "epoch": 1.8562367864693448, "grad_norm": 2.1942670345306396, "learning_rate": 6.410193090093227e-06, "loss": 0.30209189653396606, "step": 878 }, { "epoch": 1.8604651162790697, "grad_norm": 11.936202049255371, "learning_rate": 6.394778583888064e-06, "loss": 0.7097612023353577, "step": 880 }, { "epoch": 1.864693446088795, "grad_norm": 0.9149773120880127, "learning_rate": 6.379353138655227e-06, "loss": 1.0813405513763428, "step": 882 }, { "epoch": 1.86892177589852, "grad_norm": 0.5244007706642151, "learning_rate": 6.3639169429769805e-06, "loss": 0.7407552003860474, "step": 884 }, { "epoch": 1.8731501057082451, "grad_norm": 1.650093674659729, "learning_rate": 6.348470185567025e-06, "loss": 1.060293197631836, "step": 886 }, { "epoch": 1.8773784355179703, "grad_norm": 0.5465551614761353, "learning_rate": 6.333013055268169e-06, "loss": 1.1210304498672485, "step": 888 }, { "epoch": 1.8816067653276956, "grad_norm": 2.338768720626831, "learning_rate": 6.317545741050044e-06, "loss": 0.5387392044067383, "step": 890 }, { "epoch": 1.8858350951374208, "grad_norm": 2.000124454498291, "learning_rate": 6.3020684320067805e-06, "loss": 0.8054291009902954, "step": 892 }, { "epoch": 1.890063424947146, "grad_norm": 1.3637001514434814, "learning_rate": 6.2865813173546976e-06, "loss": 1.0544297695159912, "step": 894 }, { "epoch": 1.8942917547568712, "grad_norm": 0.9053227305412292, "learning_rate": 6.271084586429994e-06, "loss": 1.3180975914001465, "step": 896 }, { "epoch": 1.8985200845665962, "grad_norm": 0.6029000282287598, "learning_rate": 6.255578428686433e-06, "loss": 1.0015649795532227, "step": 898 }, { "epoch": 1.9027484143763214, "grad_norm": 0.6916961073875427, "learning_rate": 6.240063033693023e-06, "loss": 0.5087056159973145, "step": 900 }, { "epoch": 1.9069767441860463, "grad_norm": 0.6165688633918762, "learning_rate": 6.2245385911316994e-06, "loss": 1.0615694522857666, "step": 902 }, { "epoch": 1.9112050739957716, "grad_norm": 0.8279294371604919, "learning_rate": 6.2090052907950096e-06, "loss": 0.5493743419647217, "step": 904 }, { "epoch": 1.9154334038054968, "grad_norm": 0.6662288904190063, "learning_rate": 6.193463322583792e-06, "loss": 0.8905397653579712, "step": 906 }, { "epoch": 1.919661733615222, "grad_norm": 3.1187756061553955, "learning_rate": 6.177912876504851e-06, "loss": 1.18208909034729, "step": 908 }, { "epoch": 1.9238900634249472, "grad_norm": 2.945279598236084, "learning_rate": 6.16235414266864e-06, "loss": 0.7958618998527527, "step": 910 }, { "epoch": 1.9281183932346724, "grad_norm": 0.8455015420913696, "learning_rate": 6.146787311286927e-06, "loss": 1.1226367950439453, "step": 912 }, { "epoch": 1.9323467230443976, "grad_norm": 1.1459468603134155, "learning_rate": 6.131212572670483e-06, "loss": 0.6789748668670654, "step": 914 }, { "epoch": 1.9365750528541226, "grad_norm": 0.9291977286338806, "learning_rate": 6.115630117226741e-06, "loss": 1.101250410079956, "step": 916 }, { "epoch": 1.9408033826638478, "grad_norm": 0.6466909646987915, "learning_rate": 6.1000401354574855e-06, "loss": 0.6696260571479797, "step": 918 }, { "epoch": 1.945031712473573, "grad_norm": 3.4001340866088867, "learning_rate": 6.084442817956502e-06, "loss": 0.8927789330482483, "step": 920 }, { "epoch": 1.949260042283298, "grad_norm": 0.9555128812789917, "learning_rate": 6.0688383554072625e-06, "loss": 0.9435282945632935, "step": 922 }, { "epoch": 1.9534883720930232, "grad_norm": 0.5828202366828918, "learning_rate": 6.053226938580596e-06, "loss": 0.9868360161781311, "step": 924 }, { "epoch": 1.9577167019027484, "grad_norm": 0.23289379477500916, "learning_rate": 6.03760875833234e-06, "loss": 0.8844956159591675, "step": 926 }, { "epoch": 1.9619450317124736, "grad_norm": 0.8725548982620239, "learning_rate": 6.021984005601027e-06, "loss": 1.1722898483276367, "step": 928 }, { "epoch": 1.9661733615221988, "grad_norm": 1.3734270334243774, "learning_rate": 6.006352871405534e-06, "loss": 0.7536570429801941, "step": 930 }, { "epoch": 1.970401691331924, "grad_norm": 2.0888586044311523, "learning_rate": 5.990715546842755e-06, "loss": 1.2211147546768188, "step": 932 }, { "epoch": 1.9746300211416492, "grad_norm": 6.971341133117676, "learning_rate": 5.9750722230852694e-06, "loss": 0.8670483827590942, "step": 934 }, { "epoch": 1.9788583509513742, "grad_norm": 1.0185168981552124, "learning_rate": 5.959423091378992e-06, "loss": 0.6950554847717285, "step": 936 }, { "epoch": 1.9830866807610994, "grad_norm": 2.392500400543213, "learning_rate": 5.943768343040845e-06, "loss": 0.8060028553009033, "step": 938 }, { "epoch": 1.9873150105708244, "grad_norm": 0.8435702919960022, "learning_rate": 5.928108169456419e-06, "loss": 1.0431312322616577, "step": 940 }, { "epoch": 1.9915433403805496, "grad_norm": 0.6279540657997131, "learning_rate": 5.912442762077624e-06, "loss": 1.0776671171188354, "step": 942 }, { "epoch": 1.9957716701902748, "grad_norm": 0.7132748961448669, "learning_rate": 5.89677231242036e-06, "loss": 1.0668655633926392, "step": 944 }, { "epoch": 2.0, "grad_norm": 0.680631160736084, "learning_rate": 5.8810970120621714e-06, "loss": 0.4238647222518921, "step": 946 }, { "epoch": 2.004228329809725, "grad_norm": 2.1835405826568604, "learning_rate": 5.8654170526399014e-06, "loss": 0.7834351062774658, "step": 948 }, { "epoch": 2.0084566596194504, "grad_norm": 0.39423826336860657, "learning_rate": 5.849732625847354e-06, "loss": 0.9458348751068115, "step": 950 }, { "epoch": 2.0126849894291756, "grad_norm": 1.1566969156265259, "learning_rate": 5.834043923432947e-06, "loss": 0.83138108253479, "step": 952 }, { "epoch": 2.016913319238901, "grad_norm": 1.1080431938171387, "learning_rate": 5.818351137197373e-06, "loss": 1.103463053703308, "step": 954 }, { "epoch": 2.0211416490486256, "grad_norm": 1.2764878273010254, "learning_rate": 5.802654458991245e-06, "loss": 0.9882860779762268, "step": 956 }, { "epoch": 2.025369978858351, "grad_norm": 0.9656870365142822, "learning_rate": 5.786954080712763e-06, "loss": 0.7164374589920044, "step": 958 }, { "epoch": 2.029598308668076, "grad_norm": 1.9419013261795044, "learning_rate": 5.7712501943053576e-06, "loss": 0.9245442748069763, "step": 960 }, { "epoch": 2.033826638477801, "grad_norm": 14.90627384185791, "learning_rate": 5.755542991755352e-06, "loss": 0.9674210548400879, "step": 962 }, { "epoch": 2.0380549682875264, "grad_norm": 1.3510829210281372, "learning_rate": 5.739832665089604e-06, "loss": 0.7509015798568726, "step": 964 }, { "epoch": 2.0422832980972516, "grad_norm": 1.0945179462432861, "learning_rate": 5.724119406373171e-06, "loss": 0.7203839421272278, "step": 966 }, { "epoch": 2.046511627906977, "grad_norm": 2.9433858394622803, "learning_rate": 5.708403407706954e-06, "loss": 0.7549036741256714, "step": 968 }, { "epoch": 2.050739957716702, "grad_norm": 0.9213945865631104, "learning_rate": 5.692684861225349e-06, "loss": 1.001625657081604, "step": 970 }, { "epoch": 2.0549682875264272, "grad_norm": 5.510413646697998, "learning_rate": 5.676963959093904e-06, "loss": 0.4923773407936096, "step": 972 }, { "epoch": 2.059196617336152, "grad_norm": 0.7776215076446533, "learning_rate": 5.66124089350696e-06, "loss": 0.9227845668792725, "step": 974 }, { "epoch": 2.063424947145877, "grad_norm": 1.1960901021957397, "learning_rate": 5.645515856685316e-06, "loss": 0.9395514130592346, "step": 976 }, { "epoch": 2.0676532769556024, "grad_norm": 1.0001575946807861, "learning_rate": 5.629789040873862e-06, "loss": 0.9782544374465942, "step": 978 }, { "epoch": 2.0718816067653276, "grad_norm": 1.5085265636444092, "learning_rate": 5.614060638339238e-06, "loss": 0.6675861477851868, "step": 980 }, { "epoch": 2.076109936575053, "grad_norm": 2.796776056289673, "learning_rate": 5.598330841367487e-06, "loss": 0.6468226313591003, "step": 982 }, { "epoch": 2.080338266384778, "grad_norm": 0.6039304137229919, "learning_rate": 5.582599842261693e-06, "loss": 0.6757178902626038, "step": 984 }, { "epoch": 2.0845665961945032, "grad_norm": 2.612698554992676, "learning_rate": 5.566867833339644e-06, "loss": 0.8011523485183716, "step": 986 }, { "epoch": 2.0887949260042284, "grad_norm": 0.8382197618484497, "learning_rate": 5.551135006931467e-06, "loss": 0.9978527426719666, "step": 988 }, { "epoch": 2.0930232558139537, "grad_norm": 0.8249222636222839, "learning_rate": 5.535401555377287e-06, "loss": 0.8725526332855225, "step": 990 }, { "epoch": 2.097251585623679, "grad_norm": 3.3896560668945312, "learning_rate": 5.51966767102487e-06, "loss": 0.5478113293647766, "step": 992 }, { "epoch": 2.1014799154334036, "grad_norm": 3.3347837924957275, "learning_rate": 5.503933546227273e-06, "loss": 0.6797852516174316, "step": 994 }, { "epoch": 2.105708245243129, "grad_norm": 0.6727854609489441, "learning_rate": 5.4881993733404916e-06, "loss": 0.6836646199226379, "step": 996 }, { "epoch": 2.109936575052854, "grad_norm": 1.5045756101608276, "learning_rate": 5.472465344721113e-06, "loss": 0.8988355398178101, "step": 998 }, { "epoch": 2.1141649048625792, "grad_norm": 0.5710520148277283, "learning_rate": 5.456731652723959e-06, "loss": 0.9049930572509766, "step": 1000 }, { "epoch": 2.1183932346723044, "grad_norm": 0.3591303527355194, "learning_rate": 5.440998489699731e-06, "loss": 0.24542683362960815, "step": 1002 }, { "epoch": 2.1226215644820297, "grad_norm": 13.33676815032959, "learning_rate": 5.425266047992672e-06, "loss": 0.6531831622123718, "step": 1004 }, { "epoch": 2.126849894291755, "grad_norm": 0.7260448336601257, "learning_rate": 5.4095345199382e-06, "loss": 0.9343101382255554, "step": 1006 }, { "epoch": 2.13107822410148, "grad_norm": 1.9126611948013306, "learning_rate": 5.393804097860568e-06, "loss": 0.8683708906173706, "step": 1008 }, { "epoch": 2.1353065539112053, "grad_norm": 0.5570077896118164, "learning_rate": 5.3780749740705065e-06, "loss": 0.6270161867141724, "step": 1010 }, { "epoch": 2.13953488372093, "grad_norm": 0.7498522400856018, "learning_rate": 5.362347340862869e-06, "loss": 0.532853364944458, "step": 1012 }, { "epoch": 2.1437632135306552, "grad_norm": 0.7481929659843445, "learning_rate": 5.3466213905142935e-06, "loss": 0.5881395936012268, "step": 1014 }, { "epoch": 2.1479915433403804, "grad_norm": 0.7402887940406799, "learning_rate": 5.3308973152808395e-06, "loss": 0.7791345119476318, "step": 1016 }, { "epoch": 2.1522198731501057, "grad_norm": 0.9727804660797119, "learning_rate": 5.315175307395644e-06, "loss": 0.8897024989128113, "step": 1018 }, { "epoch": 2.156448202959831, "grad_norm": 2.347020387649536, "learning_rate": 5.299455559066571e-06, "loss": 0.7533575892448425, "step": 1020 }, { "epoch": 2.160676532769556, "grad_norm": 0.7883897423744202, "learning_rate": 5.283738262473859e-06, "loss": 0.6416608095169067, "step": 1022 }, { "epoch": 2.1649048625792813, "grad_norm": 0.8335028290748596, "learning_rate": 5.268023609767772e-06, "loss": 0.8805380463600159, "step": 1024 }, { "epoch": 2.1691331923890065, "grad_norm": 1.1651896238327026, "learning_rate": 5.2523117930662545e-06, "loss": 0.9464039206504822, "step": 1026 }, { "epoch": 2.1733615221987317, "grad_norm": 0.6849421858787537, "learning_rate": 5.2366030044525785e-06, "loss": 0.9600998759269714, "step": 1028 }, { "epoch": 2.177589852008457, "grad_norm": 0.5264531970024109, "learning_rate": 5.220897435972992e-06, "loss": 0.8875144720077515, "step": 1030 }, { "epoch": 2.1818181818181817, "grad_norm": 1.4176231622695923, "learning_rate": 5.205195279634385e-06, "loss": 0.9397720694541931, "step": 1032 }, { "epoch": 2.186046511627907, "grad_norm": 0.683865487575531, "learning_rate": 5.1894967274019245e-06, "loss": 1.108823299407959, "step": 1034 }, { "epoch": 2.190274841437632, "grad_norm": 0.7279227375984192, "learning_rate": 5.173801971196716e-06, "loss": 0.6587095260620117, "step": 1036 }, { "epoch": 2.1945031712473573, "grad_norm": 2.5986928939819336, "learning_rate": 5.158111202893464e-06, "loss": 0.39327144622802734, "step": 1038 }, { "epoch": 2.1987315010570825, "grad_norm": 0.8085549473762512, "learning_rate": 5.142424614318112e-06, "loss": 0.999077320098877, "step": 1040 }, { "epoch": 2.2029598308668077, "grad_norm": 2.0629513263702393, "learning_rate": 5.12674239724551e-06, "loss": 0.2888462543487549, "step": 1042 }, { "epoch": 2.207188160676533, "grad_norm": 0.5791046023368835, "learning_rate": 5.111064743397061e-06, "loss": 0.9783722162246704, "step": 1044 }, { "epoch": 2.211416490486258, "grad_norm": 0.6748907566070557, "learning_rate": 5.09539184443838e-06, "loss": 0.5095124244689941, "step": 1046 }, { "epoch": 2.2156448202959833, "grad_norm": 3.5107486248016357, "learning_rate": 5.079723891976956e-06, "loss": 0.8193997740745544, "step": 1048 }, { "epoch": 2.219873150105708, "grad_norm": 1.5522041320800781, "learning_rate": 5.064061077559803e-06, "loss": 0.5703198313713074, "step": 1050 }, { "epoch": 2.2241014799154333, "grad_norm": 0.8167155385017395, "learning_rate": 5.048403592671116e-06, "loss": 0.8021005988121033, "step": 1052 }, { "epoch": 2.2283298097251585, "grad_norm": 1.0883783102035522, "learning_rate": 5.032751628729943e-06, "loss": 0.975560188293457, "step": 1054 }, { "epoch": 2.2325581395348837, "grad_norm": 0.6755709648132324, "learning_rate": 5.017105377087829e-06, "loss": 0.9605676531791687, "step": 1056 }, { "epoch": 2.236786469344609, "grad_norm": 0.1840316504240036, "learning_rate": 5.0014650290264854e-06, "loss": 0.6622487902641296, "step": 1058 }, { "epoch": 2.241014799154334, "grad_norm": 2.420767307281494, "learning_rate": 4.9858307757554536e-06, "loss": 0.7697721719741821, "step": 1060 }, { "epoch": 2.2452431289640593, "grad_norm": 0.6482284665107727, "learning_rate": 4.97020280840976e-06, "loss": 0.9350615739822388, "step": 1062 }, { "epoch": 2.2494714587737845, "grad_norm": 0.8519812226295471, "learning_rate": 4.954581318047582e-06, "loss": 0.829891562461853, "step": 1064 }, { "epoch": 2.2536997885835097, "grad_norm": 1.7311917543411255, "learning_rate": 4.938966495647918e-06, "loss": 0.5028548836708069, "step": 1066 }, { "epoch": 2.2579281183932345, "grad_norm": 0.9015049934387207, "learning_rate": 4.923358532108244e-06, "loss": 0.8317457437515259, "step": 1068 }, { "epoch": 2.2621564482029597, "grad_norm": 1.5393600463867188, "learning_rate": 4.907757618242186e-06, "loss": 0.7896000146865845, "step": 1070 }, { "epoch": 2.266384778012685, "grad_norm": 0.8489202260971069, "learning_rate": 4.892163944777181e-06, "loss": 0.9926992654800415, "step": 1072 }, { "epoch": 2.27061310782241, "grad_norm": 1.0018798112869263, "learning_rate": 4.876577702352155e-06, "loss": 0.6268654465675354, "step": 1074 }, { "epoch": 2.2748414376321353, "grad_norm": 2.0593972206115723, "learning_rate": 4.860999081515183e-06, "loss": 0.7380053400993347, "step": 1076 }, { "epoch": 2.2790697674418605, "grad_norm": 1.253178596496582, "learning_rate": 4.845428272721161e-06, "loss": 0.192246213555336, "step": 1078 }, { "epoch": 2.2832980972515857, "grad_norm": 0.40064191818237305, "learning_rate": 4.8298654663294865e-06, "loss": 0.11899541318416595, "step": 1080 }, { "epoch": 2.287526427061311, "grad_norm": 0.2380247712135315, "learning_rate": 4.814310852601717e-06, "loss": 0.527076244354248, "step": 1082 }, { "epoch": 2.291754756871036, "grad_norm": 0.8007681965827942, "learning_rate": 4.7987646216992545e-06, "loss": 0.31804460287094116, "step": 1084 }, { "epoch": 2.295983086680761, "grad_norm": 0.6500993371009827, "learning_rate": 4.783226963681018e-06, "loss": 0.17850759625434875, "step": 1086 }, { "epoch": 2.300211416490486, "grad_norm": 9.290656089782715, "learning_rate": 4.76769806850112e-06, "loss": 0.6848217844963074, "step": 1088 }, { "epoch": 2.3044397463002113, "grad_norm": 0.5741628408432007, "learning_rate": 4.752178126006544e-06, "loss": 0.8869965076446533, "step": 1090 }, { "epoch": 2.3086680761099365, "grad_norm": 1.0271395444869995, "learning_rate": 4.736667325934819e-06, "loss": 0.629706859588623, "step": 1092 }, { "epoch": 2.3128964059196617, "grad_norm": 2.969717025756836, "learning_rate": 4.721165857911709e-06, "loss": 0.9150331020355225, "step": 1094 }, { "epoch": 2.317124735729387, "grad_norm": 0.6088107228279114, "learning_rate": 4.705673911448891e-06, "loss": 0.8772293925285339, "step": 1096 }, { "epoch": 2.321353065539112, "grad_norm": 0.7216980457305908, "learning_rate": 4.690191675941631e-06, "loss": 0.8810322284698486, "step": 1098 }, { "epoch": 2.3255813953488373, "grad_norm": 2.758298397064209, "learning_rate": 4.674719340666477e-06, "loss": 0.515298068523407, "step": 1100 }, { "epoch": 2.3298097251585626, "grad_norm": 0.7899646162986755, "learning_rate": 4.659257094778949e-06, "loss": 0.6127548217773438, "step": 1102 }, { "epoch": 2.3340380549682873, "grad_norm": 0.7029310464859009, "learning_rate": 4.643805127311212e-06, "loss": 0.9605186581611633, "step": 1104 }, { "epoch": 2.3382663847780125, "grad_norm": 0.7269206643104553, "learning_rate": 4.628363627169774e-06, "loss": 0.865380585193634, "step": 1106 }, { "epoch": 2.3424947145877377, "grad_norm": 0.9437695145606995, "learning_rate": 4.612932783133182e-06, "loss": 0.8871389031410217, "step": 1108 }, { "epoch": 2.346723044397463, "grad_norm": 10.804369926452637, "learning_rate": 4.5975127838497036e-06, "loss": 1.0122722387313843, "step": 1110 }, { "epoch": 2.350951374207188, "grad_norm": 0.24916067719459534, "learning_rate": 4.582103817835021e-06, "loss": 0.6240617036819458, "step": 1112 }, { "epoch": 2.3551797040169133, "grad_norm": 2.1334190368652344, "learning_rate": 4.566706073469938e-06, "loss": 0.8519321084022522, "step": 1114 }, { "epoch": 2.3594080338266386, "grad_norm": 0.7196120023727417, "learning_rate": 4.551319738998067e-06, "loss": 0.5866379141807556, "step": 1116 }, { "epoch": 2.3636363636363638, "grad_norm": 2.90144944190979, "learning_rate": 4.535945002523524e-06, "loss": 1.0403051376342773, "step": 1118 }, { "epoch": 2.367864693446089, "grad_norm": 0.6107671856880188, "learning_rate": 4.5205820520086415e-06, "loss": 0.9220075607299805, "step": 1120 }, { "epoch": 2.3720930232558137, "grad_norm": 1.3362375497817993, "learning_rate": 4.505231075271662e-06, "loss": 0.7784076929092407, "step": 1122 }, { "epoch": 2.376321353065539, "grad_norm": 0.6976295709609985, "learning_rate": 4.489892259984446e-06, "loss": 0.6905590295791626, "step": 1124 }, { "epoch": 2.380549682875264, "grad_norm": 6.246830940246582, "learning_rate": 4.474565793670167e-06, "loss": 0.7386388182640076, "step": 1126 }, { "epoch": 2.3847780126849893, "grad_norm": 2.571895122528076, "learning_rate": 4.459251863701038e-06, "loss": 0.6182255148887634, "step": 1128 }, { "epoch": 2.3890063424947146, "grad_norm": 1.6516543626785278, "learning_rate": 4.443950657296004e-06, "loss": 0.7557469606399536, "step": 1130 }, { "epoch": 2.3932346723044398, "grad_norm": 1.7424417734146118, "learning_rate": 4.4286623615184585e-06, "loss": 0.6463727951049805, "step": 1132 }, { "epoch": 2.397463002114165, "grad_norm": 1.1122921705245972, "learning_rate": 4.413387163273964e-06, "loss": 0.9473005533218384, "step": 1134 }, { "epoch": 2.40169133192389, "grad_norm": 1.3916555643081665, "learning_rate": 4.3981252493079506e-06, "loss": 0.6342065334320068, "step": 1136 }, { "epoch": 2.4059196617336154, "grad_norm": 1.8466628789901733, "learning_rate": 4.382876806203453e-06, "loss": 0.8434392213821411, "step": 1138 }, { "epoch": 2.41014799154334, "grad_norm": 0.720771849155426, "learning_rate": 4.3676420203788125e-06, "loss": 0.9179185032844543, "step": 1140 }, { "epoch": 2.4143763213530653, "grad_norm": 0.5521956086158752, "learning_rate": 4.352421078085405e-06, "loss": 0.9824479818344116, "step": 1142 }, { "epoch": 2.4186046511627906, "grad_norm": 1.1330708265304565, "learning_rate": 4.337214165405368e-06, "loss": 0.5630440711975098, "step": 1144 }, { "epoch": 2.4228329809725158, "grad_norm": 10.163344383239746, "learning_rate": 4.322021468249316e-06, "loss": 0.6985925436019897, "step": 1146 }, { "epoch": 2.427061310782241, "grad_norm": 0.778333306312561, "learning_rate": 4.306843172354076e-06, "loss": 0.6835106015205383, "step": 1148 }, { "epoch": 2.431289640591966, "grad_norm": 8.041601181030273, "learning_rate": 4.291679463280416e-06, "loss": 0.6271865367889404, "step": 1150 }, { "epoch": 2.4355179704016914, "grad_norm": 0.8931507468223572, "learning_rate": 4.276530526410768e-06, "loss": 0.5872765183448792, "step": 1152 }, { "epoch": 2.4397463002114166, "grad_norm": 0.6369198560714722, "learning_rate": 4.261396546946972e-06, "loss": 0.5028990507125854, "step": 1154 }, { "epoch": 2.443974630021142, "grad_norm": 0.6633052825927734, "learning_rate": 4.246277709908009e-06, "loss": 0.8032389879226685, "step": 1156 }, { "epoch": 2.448202959830867, "grad_norm": 0.5728570222854614, "learning_rate": 4.231174200127736e-06, "loss": 0.5324134230613708, "step": 1158 }, { "epoch": 2.452431289640592, "grad_norm": 0.6011850833892822, "learning_rate": 4.216086202252624e-06, "loss": 0.9477571249008179, "step": 1160 }, { "epoch": 2.456659619450317, "grad_norm": 0.8468151688575745, "learning_rate": 4.201013900739513e-06, "loss": 0.9242187142372131, "step": 1162 }, { "epoch": 2.460887949260042, "grad_norm": 0.5794147253036499, "learning_rate": 4.185957479853344e-06, "loss": 0.7302073240280151, "step": 1164 }, { "epoch": 2.4651162790697674, "grad_norm": 2.686353921890259, "learning_rate": 4.1709171236649096e-06, "loss": 1.1554944515228271, "step": 1166 }, { "epoch": 2.4693446088794926, "grad_norm": 1.0153250694274902, "learning_rate": 4.155893016048607e-06, "loss": 1.011820673942566, "step": 1168 }, { "epoch": 2.473572938689218, "grad_norm": 0.7952589392662048, "learning_rate": 4.140885340680189e-06, "loss": 0.7875487208366394, "step": 1170 }, { "epoch": 2.477801268498943, "grad_norm": 1.0109285116195679, "learning_rate": 4.125894281034517e-06, "loss": 0.8428477048873901, "step": 1172 }, { "epoch": 2.482029598308668, "grad_norm": 0.4454251527786255, "learning_rate": 4.110920020383316e-06, "loss": 0.7750532031059265, "step": 1174 }, { "epoch": 2.4862579281183934, "grad_norm": 0.6352078914642334, "learning_rate": 4.0959627417929386e-06, "loss": 0.6622282862663269, "step": 1176 }, { "epoch": 2.4904862579281186, "grad_norm": 1.9413386583328247, "learning_rate": 4.081022628122127e-06, "loss": 0.7515383958816528, "step": 1178 }, { "epoch": 2.4947145877378434, "grad_norm": 2.948779821395874, "learning_rate": 4.06609986201977e-06, "loss": 0.6136088967323303, "step": 1180 }, { "epoch": 2.4989429175475686, "grad_norm": 0.3935765027999878, "learning_rate": 4.051194625922681e-06, "loss": 0.44041118025779724, "step": 1182 }, { "epoch": 2.503171247357294, "grad_norm": 0.5345903635025024, "learning_rate": 4.036307102053359e-06, "loss": 0.1272549331188202, "step": 1184 }, { "epoch": 2.507399577167019, "grad_norm": 0.6290346384048462, "learning_rate": 4.021437472417763e-06, "loss": 0.8757612109184265, "step": 1186 }, { "epoch": 2.511627906976744, "grad_norm": 0.9762037992477417, "learning_rate": 4.006585918803091e-06, "loss": 0.7674428224563599, "step": 1188 }, { "epoch": 2.5158562367864694, "grad_norm": 3.9735844135284424, "learning_rate": 3.991752622775551e-06, "loss": 0.6173699498176575, "step": 1190 }, { "epoch": 2.5200845665961946, "grad_norm": 0.7253290414810181, "learning_rate": 3.97693776567815e-06, "loss": 0.8811478018760681, "step": 1192 }, { "epoch": 2.52431289640592, "grad_norm": 1.2412395477294922, "learning_rate": 3.962141528628465e-06, "loss": 0.5862326622009277, "step": 1194 }, { "epoch": 2.528541226215645, "grad_norm": 1.7458057403564453, "learning_rate": 3.947364092516437e-06, "loss": 0.8179827332496643, "step": 1196 }, { "epoch": 2.53276955602537, "grad_norm": 0.5777556300163269, "learning_rate": 3.932605638002163e-06, "loss": 0.9067537784576416, "step": 1198 }, { "epoch": 2.536997885835095, "grad_norm": 1.37425696849823, "learning_rate": 3.917866345513677e-06, "loss": 0.7321706414222717, "step": 1200 }, { "epoch": 2.54122621564482, "grad_norm": 0.9027764797210693, "learning_rate": 3.903146395244749e-06, "loss": 0.8918856978416443, "step": 1202 }, { "epoch": 2.5454545454545454, "grad_norm": 3.044384479522705, "learning_rate": 3.888445967152691e-06, "loss": 0.343666672706604, "step": 1204 }, { "epoch": 2.5496828752642706, "grad_norm": 5.199758529663086, "learning_rate": 3.873765240956138e-06, "loss": 1.0180174112319946, "step": 1206 }, { "epoch": 2.553911205073996, "grad_norm": 1.1066762208938599, "learning_rate": 3.859104396132863e-06, "loss": 0.9772629737854004, "step": 1208 }, { "epoch": 2.558139534883721, "grad_norm": 0.5610095262527466, "learning_rate": 3.84446361191759e-06, "loss": 0.9399202466011047, "step": 1210 }, { "epoch": 2.5623678646934462, "grad_norm": 1.3396538496017456, "learning_rate": 3.829843067299788e-06, "loss": 0.6574129462242126, "step": 1212 }, { "epoch": 2.5665961945031714, "grad_norm": 0.7421737909317017, "learning_rate": 3.8152429410214834e-06, "loss": 0.9064651727676392, "step": 1214 }, { "epoch": 2.570824524312896, "grad_norm": 1.3635436296463013, "learning_rate": 3.8006634115750886e-06, "loss": 0.6137216091156006, "step": 1216 }, { "epoch": 2.5750528541226214, "grad_norm": 0.9585432410240173, "learning_rate": 3.7861046572012105e-06, "loss": 0.6055303812026978, "step": 1218 }, { "epoch": 2.5792811839323466, "grad_norm": 2.2378289699554443, "learning_rate": 3.771566855886467e-06, "loss": 0.3955214321613312, "step": 1220 }, { "epoch": 2.583509513742072, "grad_norm": 2.5122313499450684, "learning_rate": 3.7570501853613227e-06, "loss": 0.520164966583252, "step": 1222 }, { "epoch": 2.587737843551797, "grad_norm": 3.1283109188079834, "learning_rate": 3.742554823097905e-06, "loss": 0.6785550713539124, "step": 1224 }, { "epoch": 2.5919661733615222, "grad_norm": 0.5118480920791626, "learning_rate": 3.7280809463078436e-06, "loss": 0.45351743698120117, "step": 1226 }, { "epoch": 2.5961945031712474, "grad_norm": 0.7750012278556824, "learning_rate": 3.7136287319400944e-06, "loss": 0.7336353063583374, "step": 1228 }, { "epoch": 2.6004228329809727, "grad_norm": 7.361147403717041, "learning_rate": 3.6991983566787847e-06, "loss": 0.7941614389419556, "step": 1230 }, { "epoch": 2.604651162790698, "grad_norm": 3.152771234512329, "learning_rate": 3.6847899969410515e-06, "loss": 0.5934794545173645, "step": 1232 }, { "epoch": 2.6088794926004226, "grad_norm": 3.012972354888916, "learning_rate": 3.6704038288748812e-06, "loss": 0.6661195755004883, "step": 1234 }, { "epoch": 2.613107822410148, "grad_norm": 1.5397342443466187, "learning_rate": 3.6560400283569543e-06, "loss": 0.8153946399688721, "step": 1236 }, { "epoch": 2.617336152219873, "grad_norm": 0.8656942248344421, "learning_rate": 3.641698770990507e-06, "loss": 0.8203715085983276, "step": 1238 }, { "epoch": 2.6215644820295982, "grad_norm": 1.0518449544906616, "learning_rate": 3.6273802321031738e-06, "loss": 0.674680769443512, "step": 1240 }, { "epoch": 2.6257928118393234, "grad_norm": 0.8664630055427551, "learning_rate": 3.6130845867448384e-06, "loss": 0.9432058334350586, "step": 1242 }, { "epoch": 2.6300211416490487, "grad_norm": 2.2329657077789307, "learning_rate": 3.598812009685514e-06, "loss": 0.9975607395172119, "step": 1244 }, { "epoch": 2.634249471458774, "grad_norm": 1.2762430906295776, "learning_rate": 3.584562675413189e-06, "loss": 0.6189113259315491, "step": 1246 }, { "epoch": 2.638477801268499, "grad_norm": 16.140363693237305, "learning_rate": 3.5703367581316985e-06, "loss": 0.5188018083572388, "step": 1248 }, { "epoch": 2.6427061310782243, "grad_norm": 0.5964422225952148, "learning_rate": 3.5561344317585957e-06, "loss": 0.9297536611557007, "step": 1250 }, { "epoch": 2.646934460887949, "grad_norm": 2.1867239475250244, "learning_rate": 3.5419558699230305e-06, "loss": 0.5405316352844238, "step": 1252 }, { "epoch": 2.6511627906976747, "grad_norm": 2.427215337753296, "learning_rate": 3.52780124596361e-06, "loss": 0.5897989273071289, "step": 1254 }, { "epoch": 2.6553911205073994, "grad_norm": 0.6648092269897461, "learning_rate": 3.5136707329263055e-06, "loss": 0.9447919726371765, "step": 1256 }, { "epoch": 2.6596194503171247, "grad_norm": 2.3099887371063232, "learning_rate": 3.499564503562315e-06, "loss": 0.2671961486339569, "step": 1258 }, { "epoch": 2.66384778012685, "grad_norm": 0.32390835881233215, "learning_rate": 3.4854827303259575e-06, "loss": 0.49519264698028564, "step": 1260 }, { "epoch": 2.668076109936575, "grad_norm": 3.469106674194336, "learning_rate": 3.47142558537257e-06, "loss": 0.6422495245933533, "step": 1262 }, { "epoch": 2.6723044397463003, "grad_norm": 4.621847629547119, "learning_rate": 3.4573932405563966e-06, "loss": 0.6686447858810425, "step": 1264 }, { "epoch": 2.6765327695560255, "grad_norm": 1.7567352056503296, "learning_rate": 3.4433858674284894e-06, "loss": 0.32132387161254883, "step": 1266 }, { "epoch": 2.6807610993657507, "grad_norm": 0.7601593732833862, "learning_rate": 3.429403637234614e-06, "loss": 0.6836571097373962, "step": 1268 }, { "epoch": 2.6849894291754755, "grad_norm": 0.7645792961120605, "learning_rate": 3.4154467209131515e-06, "loss": 0.9374161958694458, "step": 1270 }, { "epoch": 2.689217758985201, "grad_norm": 2.304508686065674, "learning_rate": 3.401515289093011e-06, "loss": 0.6606026291847229, "step": 1272 }, { "epoch": 2.693446088794926, "grad_norm": 1.2845077514648438, "learning_rate": 3.3876095120915433e-06, "loss": 0.4217822849750519, "step": 1274 }, { "epoch": 2.697674418604651, "grad_norm": 3.335594654083252, "learning_rate": 3.3737295599124592e-06, "loss": 0.4819757342338562, "step": 1276 }, { "epoch": 2.7019027484143763, "grad_norm": 0.9198805093765259, "learning_rate": 3.3598756022437507e-06, "loss": 0.9792485237121582, "step": 1278 }, { "epoch": 2.7061310782241015, "grad_norm": 3.1317014694213867, "learning_rate": 3.3460478084556157e-06, "loss": 0.6636680364608765, "step": 1280 }, { "epoch": 2.7103594080338267, "grad_norm": 0.9098655581474304, "learning_rate": 3.33224634759839e-06, "loss": 0.9931256771087646, "step": 1282 }, { "epoch": 2.714587737843552, "grad_norm": 0.38242730498313904, "learning_rate": 3.318471388400476e-06, "loss": 0.6639761328697205, "step": 1284 }, { "epoch": 2.718816067653277, "grad_norm": 0.17166031897068024, "learning_rate": 3.3047230992662834e-06, "loss": 1.1374062299728394, "step": 1286 }, { "epoch": 2.723044397463002, "grad_norm": 0.6677655577659607, "learning_rate": 3.291001648274175e-06, "loss": 0.4790601134300232, "step": 1288 }, { "epoch": 2.7272727272727275, "grad_norm": 0.8687372803688049, "learning_rate": 3.277307203174395e-06, "loss": 0.8454591035842896, "step": 1290 }, { "epoch": 2.7315010570824523, "grad_norm": 1.537925124168396, "learning_rate": 3.263639931387039e-06, "loss": 0.941419780254364, "step": 1292 }, { "epoch": 2.7357293868921775, "grad_norm": 0.7092278599739075, "learning_rate": 3.2500000000000015e-06, "loss": 0.9132797122001648, "step": 1294 }, { "epoch": 2.7399577167019027, "grad_norm": 0.46952101588249207, "learning_rate": 3.236387575766916e-06, "loss": 0.28806474804878235, "step": 1296 }, { "epoch": 2.744186046511628, "grad_norm": 0.7009896039962769, "learning_rate": 3.222802825105138e-06, "loss": 0.5152756571769714, "step": 1298 }, { "epoch": 2.748414376321353, "grad_norm": 0.633802056312561, "learning_rate": 3.209245914093708e-06, "loss": 0.6203218698501587, "step": 1300 }, { "epoch": 2.7526427061310783, "grad_norm": 0.7175562381744385, "learning_rate": 3.1957170084713053e-06, "loss": 0.7376699447631836, "step": 1302 }, { "epoch": 2.7568710359408035, "grad_norm": 0.4519272744655609, "learning_rate": 3.182216273634235e-06, "loss": 0.5093539953231812, "step": 1304 }, { "epoch": 2.7610993657505283, "grad_norm": 15.518527030944824, "learning_rate": 3.1687438746344086e-06, "loss": 0.7812902927398682, "step": 1306 }, { "epoch": 2.765327695560254, "grad_norm": 1.0872677564620972, "learning_rate": 3.1552999761773166e-06, "loss": 0.8506465554237366, "step": 1308 }, { "epoch": 2.7695560253699787, "grad_norm": 0.6442310810089111, "learning_rate": 3.141884742620013e-06, "loss": 0.9239060282707214, "step": 1310 }, { "epoch": 2.773784355179704, "grad_norm": 0.6123709082603455, "learning_rate": 3.1284983379691247e-06, "loss": 0.7574492692947388, "step": 1312 }, { "epoch": 2.778012684989429, "grad_norm": 0.4088205099105835, "learning_rate": 3.1151409258788235e-06, "loss": 0.4660508334636688, "step": 1314 }, { "epoch": 2.7822410147991543, "grad_norm": 1.141333818435669, "learning_rate": 3.101812669648838e-06, "loss": 0.8330291509628296, "step": 1316 }, { "epoch": 2.7864693446088795, "grad_norm": 0.3151339590549469, "learning_rate": 3.0885137322224546e-06, "loss": 0.5428174734115601, "step": 1318 }, { "epoch": 2.7906976744186047, "grad_norm": 1.2727302312850952, "learning_rate": 3.075244276184529e-06, "loss": 0.831659734249115, "step": 1320 }, { "epoch": 2.79492600422833, "grad_norm": 2.281906843185425, "learning_rate": 3.0620044637594936e-06, "loss": 0.32405298948287964, "step": 1322 }, { "epoch": 2.7991543340380547, "grad_norm": 2.814282178878784, "learning_rate": 3.0487944568093685e-06, "loss": 0.9572070837020874, "step": 1324 }, { "epoch": 2.8033826638477803, "grad_norm": 1.5756009817123413, "learning_rate": 3.035614416831801e-06, "loss": 0.22164300084114075, "step": 1326 }, { "epoch": 2.807610993657505, "grad_norm": 2.000332832336426, "learning_rate": 3.0224645049580746e-06, "loss": 0.44347575306892395, "step": 1328 }, { "epoch": 2.8118393234672303, "grad_norm": 0.8483347296714783, "learning_rate": 3.0093448819511416e-06, "loss": 0.5184358954429626, "step": 1330 }, { "epoch": 2.8160676532769555, "grad_norm": 1.123403787612915, "learning_rate": 2.9962557082036677e-06, "loss": 0.8875306248664856, "step": 1332 }, { "epoch": 2.8202959830866807, "grad_norm": 0.6197065114974976, "learning_rate": 2.9831971437360606e-06, "loss": 0.6237058639526367, "step": 1334 }, { "epoch": 2.824524312896406, "grad_norm": 0.9332363605499268, "learning_rate": 2.9701693481945132e-06, "loss": 0.9639469385147095, "step": 1336 }, { "epoch": 2.828752642706131, "grad_norm": 0.7059350609779358, "learning_rate": 2.957172480849064e-06, "loss": 0.9761319756507874, "step": 1338 }, { "epoch": 2.8329809725158563, "grad_norm": 0.631553053855896, "learning_rate": 2.9442067005916375e-06, "loss": 0.7205939292907715, "step": 1340 }, { "epoch": 2.8372093023255816, "grad_norm": 3.6222476959228516, "learning_rate": 2.931272165934105e-06, "loss": 0.9150611758232117, "step": 1342 }, { "epoch": 2.8414376321353068, "grad_norm": 2.107342004776001, "learning_rate": 2.918369035006351e-06, "loss": 0.6306301355361938, "step": 1344 }, { "epoch": 2.8456659619450315, "grad_norm": 1.1300914287567139, "learning_rate": 2.9054974655543335e-06, "loss": 0.6678149700164795, "step": 1346 }, { "epoch": 2.8498942917547567, "grad_norm": 2.311150550842285, "learning_rate": 2.89265761493816e-06, "loss": 0.8838525414466858, "step": 1348 }, { "epoch": 2.854122621564482, "grad_norm": 1.4003689289093018, "learning_rate": 2.8798496401301644e-06, "loss": 0.5862592458724976, "step": 1350 }, { "epoch": 2.858350951374207, "grad_norm": 6.395923614501953, "learning_rate": 2.8670736977129843e-06, "loss": 0.8135141134262085, "step": 1352 }, { "epoch": 2.8625792811839323, "grad_norm": 0.6017135381698608, "learning_rate": 2.854329943877647e-06, "loss": 0.9131079912185669, "step": 1354 }, { "epoch": 2.8668076109936576, "grad_norm": 0.9853367209434509, "learning_rate": 2.841618534421664e-06, "loss": 0.4841229021549225, "step": 1356 }, { "epoch": 2.8710359408033828, "grad_norm": 0.6670907735824585, "learning_rate": 2.8289396247471227e-06, "loss": 0.9540837407112122, "step": 1358 }, { "epoch": 2.875264270613108, "grad_norm": 1.2367289066314697, "learning_rate": 2.816293369858788e-06, "loss": 0.6694561243057251, "step": 1360 }, { "epoch": 2.879492600422833, "grad_norm": 8.813061714172363, "learning_rate": 2.803679924362206e-06, "loss": 0.671470582485199, "step": 1362 }, { "epoch": 2.883720930232558, "grad_norm": 0.6193525195121765, "learning_rate": 2.7910994424618165e-06, "loss": 0.9682505130767822, "step": 1364 }, { "epoch": 2.887949260042283, "grad_norm": 1.3732298612594604, "learning_rate": 2.778552077959064e-06, "loss": 0.7805532813072205, "step": 1366 }, { "epoch": 2.8921775898520083, "grad_norm": 0.6943634748458862, "learning_rate": 2.766037984250521e-06, "loss": 0.9720330834388733, "step": 1368 }, { "epoch": 2.8964059196617336, "grad_norm": 0.6659116744995117, "learning_rate": 2.753557314326011e-06, "loss": 0.9326096773147583, "step": 1370 }, { "epoch": 2.9006342494714588, "grad_norm": 0.8604556322097778, "learning_rate": 2.7411102207667373e-06, "loss": 0.9358223676681519, "step": 1372 }, { "epoch": 2.904862579281184, "grad_norm": 0.5010468363761902, "learning_rate": 2.728696855743418e-06, "loss": 0.7417266368865967, "step": 1374 }, { "epoch": 2.909090909090909, "grad_norm": 1.059648871421814, "learning_rate": 2.7163173710144323e-06, "loss": 0.9080476760864258, "step": 1376 }, { "epoch": 2.9133192389006344, "grad_norm": 1.5313013792037964, "learning_rate": 2.703971917923951e-06, "loss": 0.5481768250465393, "step": 1378 }, { "epoch": 2.9175475687103596, "grad_norm": 1.3209562301635742, "learning_rate": 2.6916606474000965e-06, "loss": 0.6464402675628662, "step": 1380 }, { "epoch": 2.9217758985200843, "grad_norm": 0.9418007731437683, "learning_rate": 2.679383709953103e-06, "loss": 0.965014636516571, "step": 1382 }, { "epoch": 2.92600422832981, "grad_norm": 1.3891128301620483, "learning_rate": 2.6671412556734578e-06, "loss": 0.8594425916671753, "step": 1384 }, { "epoch": 2.9302325581395348, "grad_norm": 1.7596734762191772, "learning_rate": 2.6549334342300844e-06, "loss": 0.5994439125061035, "step": 1386 }, { "epoch": 2.93446088794926, "grad_norm": 0.9181379079818726, "learning_rate": 2.642760394868503e-06, "loss": 0.9260048866271973, "step": 1388 }, { "epoch": 2.938689217758985, "grad_norm": 0.23301850259304047, "learning_rate": 2.6306222864090157e-06, "loss": 0.727497935295105, "step": 1390 }, { "epoch": 2.9429175475687104, "grad_norm": 0.8787659406661987, "learning_rate": 2.61851925724487e-06, "loss": 0.9234793782234192, "step": 1392 }, { "epoch": 2.9471458773784356, "grad_norm": 0.20810967683792114, "learning_rate": 2.606451455340459e-06, "loss": 0.27765142917633057, "step": 1394 }, { "epoch": 2.951374207188161, "grad_norm": 2.010526418685913, "learning_rate": 2.5944190282295155e-06, "loss": 0.5208805799484253, "step": 1396 }, { "epoch": 2.955602536997886, "grad_norm": 1.2251652479171753, "learning_rate": 2.5824221230132895e-06, "loss": 0.895707905292511, "step": 1398 }, { "epoch": 2.9598308668076108, "grad_norm": 0.6847018599510193, "learning_rate": 2.5704608863587676e-06, "loss": 1.0490833520889282, "step": 1400 }, { "epoch": 2.9640591966173364, "grad_norm": 2.4751009941101074, "learning_rate": 2.558535464496877e-06, "loss": 0.7718542814254761, "step": 1402 }, { "epoch": 2.968287526427061, "grad_norm": 0.4144858419895172, "learning_rate": 2.5466460032206872e-06, "loss": 0.4790780544281006, "step": 1404 }, { "epoch": 2.9725158562367864, "grad_norm": 1.2547601461410522, "learning_rate": 2.53479264788364e-06, "loss": 0.7823005318641663, "step": 1406 }, { "epoch": 2.9767441860465116, "grad_norm": 4.610895156860352, "learning_rate": 2.522975543397769e-06, "loss": 0.7413574457168579, "step": 1408 }, { "epoch": 2.980972515856237, "grad_norm": 1.1200778484344482, "learning_rate": 2.511194834231922e-06, "loss": 0.596738874912262, "step": 1410 }, { "epoch": 2.985200845665962, "grad_norm": 0.8984434008598328, "learning_rate": 2.49945066441e-06, "loss": 0.8952209949493408, "step": 1412 }, { "epoch": 2.989429175475687, "grad_norm": 0.8357415795326233, "learning_rate": 2.4877431775092004e-06, "loss": 0.6842395663261414, "step": 1414 }, { "epoch": 2.9936575052854124, "grad_norm": 2.2530860900878906, "learning_rate": 2.4760725166582544e-06, "loss": 0.7452812194824219, "step": 1416 }, { "epoch": 2.997885835095137, "grad_norm": 0.4751785695552826, "learning_rate": 2.464438824535675e-06, "loss": 0.47679126262664795, "step": 1418 }, { "epoch": 3.0021141649048624, "grad_norm": 0.6052038073539734, "learning_rate": 2.452842243368028e-06, "loss": 0.8871709108352661, "step": 1420 }, { "epoch": 3.0063424947145876, "grad_norm": 0.8103311657905579, "learning_rate": 2.4412829149281735e-06, "loss": 0.48604846000671387, "step": 1422 }, { "epoch": 3.010570824524313, "grad_norm": 2.318795919418335, "learning_rate": 2.4297609805335472e-06, "loss": 0.8428451418876648, "step": 1424 }, { "epoch": 3.014799154334038, "grad_norm": 1.9729855060577393, "learning_rate": 2.4182765810444263e-06, "loss": 0.37439051270484924, "step": 1426 }, { "epoch": 3.019027484143763, "grad_norm": 0.5773168206214905, "learning_rate": 2.4068298568622083e-06, "loss": 0.46312323212623596, "step": 1428 }, { "epoch": 3.0232558139534884, "grad_norm": 0.5320132970809937, "learning_rate": 2.395420947927694e-06, "loss": 0.6929910182952881, "step": 1430 }, { "epoch": 3.0274841437632136, "grad_norm": 0.5879036784172058, "learning_rate": 2.3840499937193804e-06, "loss": 0.8313674926757812, "step": 1432 }, { "epoch": 3.031712473572939, "grad_norm": 1.1032063961029053, "learning_rate": 2.3727171332517496e-06, "loss": 0.752081036567688, "step": 1434 }, { "epoch": 3.035940803382664, "grad_norm": 1.4718198776245117, "learning_rate": 2.361422505073575e-06, "loss": 0.486899733543396, "step": 1436 }, { "epoch": 3.040169133192389, "grad_norm": 0.4620429277420044, "learning_rate": 2.3501662472662233e-06, "loss": 0.12096726894378662, "step": 1438 }, { "epoch": 3.044397463002114, "grad_norm": 1.0804848670959473, "learning_rate": 2.3389484974419685e-06, "loss": 0.7779964804649353, "step": 1440 }, { "epoch": 3.048625792811839, "grad_norm": 0.6782544255256653, "learning_rate": 2.327769392742309e-06, "loss": 0.5559878349304199, "step": 1442 }, { "epoch": 3.0528541226215644, "grad_norm": 3.0700762271881104, "learning_rate": 2.316629069836291e-06, "loss": 0.1795402467250824, "step": 1444 }, { "epoch": 3.0570824524312896, "grad_norm": 3.368241310119629, "learning_rate": 2.305527664918838e-06, "loss": 0.6382880210876465, "step": 1446 }, { "epoch": 3.061310782241015, "grad_norm": 1.2392091751098633, "learning_rate": 2.294465313709085e-06, "loss": 0.5487275719642639, "step": 1448 }, { "epoch": 3.06553911205074, "grad_norm": 0.6469317078590393, "learning_rate": 2.2834421514487205e-06, "loss": 0.5361343026161194, "step": 1450 }, { "epoch": 3.0697674418604652, "grad_norm": 2.480417013168335, "learning_rate": 2.27245831290033e-06, "loss": 0.6080769300460815, "step": 1452 }, { "epoch": 3.0739957716701904, "grad_norm": 1.1915767192840576, "learning_rate": 2.261513932345755e-06, "loss": 0.7330661416053772, "step": 1454 }, { "epoch": 3.0782241014799157, "grad_norm": 0.09113657474517822, "learning_rate": 2.250609143584443e-06, "loss": 0.1998719573020935, "step": 1456 }, { "epoch": 3.0824524312896404, "grad_norm": 0.705594539642334, "learning_rate": 2.239744079931818e-06, "loss": 0.5636231303215027, "step": 1458 }, { "epoch": 3.0866807610993656, "grad_norm": 1.154588222503662, "learning_rate": 2.228918874217649e-06, "loss": 0.6992950439453125, "step": 1460 }, { "epoch": 3.090909090909091, "grad_norm": 0.6058709621429443, "learning_rate": 2.2181336587844244e-06, "loss": 0.8395268321037292, "step": 1462 }, { "epoch": 3.095137420718816, "grad_norm": 0.5694272518157959, "learning_rate": 2.207388565485736e-06, "loss": 0.5642480850219727, "step": 1464 }, { "epoch": 3.0993657505285412, "grad_norm": 0.5902506709098816, "learning_rate": 2.196683725684666e-06, "loss": 0.6621085405349731, "step": 1466 }, { "epoch": 3.1035940803382664, "grad_norm": 0.5635288953781128, "learning_rate": 2.1860192702521826e-06, "loss": 0.911645770072937, "step": 1468 }, { "epoch": 3.1078224101479917, "grad_norm": 1.4576319456100464, "learning_rate": 2.1753953295655354e-06, "loss": 0.8580904006958008, "step": 1470 }, { "epoch": 3.112050739957717, "grad_norm": 2.070666790008545, "learning_rate": 2.164812033506673e-06, "loss": 0.5017863512039185, "step": 1472 }, { "epoch": 3.116279069767442, "grad_norm": 0.6993897557258606, "learning_rate": 2.1542695114606367e-06, "loss": 0.9207372665405273, "step": 1474 }, { "epoch": 3.120507399577167, "grad_norm": 0.7334129214286804, "learning_rate": 2.1437678923139944e-06, "loss": 0.7413107752799988, "step": 1476 }, { "epoch": 3.124735729386892, "grad_norm": 2.6316728591918945, "learning_rate": 2.1333073044532628e-06, "loss": 0.28628677129745483, "step": 1478 }, { "epoch": 3.1289640591966172, "grad_norm": 0.9278548359870911, "learning_rate": 2.122887875763327e-06, "loss": 0.804682731628418, "step": 1480 }, { "epoch": 3.1331923890063424, "grad_norm": 0.6053680181503296, "learning_rate": 2.1125097336258897e-06, "loss": 0.8053022623062134, "step": 1482 }, { "epoch": 3.1374207188160677, "grad_norm": 0.3366604745388031, "learning_rate": 2.1021730049179117e-06, "loss": 0.24735964834690094, "step": 1484 }, { "epoch": 3.141649048625793, "grad_norm": 1.4099671840667725, "learning_rate": 2.09187781601005e-06, "loss": 0.772537112236023, "step": 1486 }, { "epoch": 3.145877378435518, "grad_norm": 0.6000462174415588, "learning_rate": 2.0816242927651254e-06, "loss": 0.9057084321975708, "step": 1488 }, { "epoch": 3.1501057082452433, "grad_norm": 3.6962602138519287, "learning_rate": 2.071412560536581e-06, "loss": 0.6464021801948547, "step": 1490 }, { "epoch": 3.1543340380549685, "grad_norm": 1.7804287672042847, "learning_rate": 2.0612427441669475e-06, "loss": 0.564626932144165, "step": 1492 }, { "epoch": 3.1585623678646932, "grad_norm": 0.5757177472114563, "learning_rate": 2.051114967986311e-06, "loss": 0.3779014050960541, "step": 1494 }, { "epoch": 3.1627906976744184, "grad_norm": 0.24275517463684082, "learning_rate": 2.0410293558108074e-06, "loss": 0.5693655014038086, "step": 1496 }, { "epoch": 3.1670190274841437, "grad_norm": 0.6342794299125671, "learning_rate": 2.0309860309410986e-06, "loss": 0.7699047327041626, "step": 1498 }, { "epoch": 3.171247357293869, "grad_norm": 0.6351836919784546, "learning_rate": 2.0209851161608613e-06, "loss": 0.8631289005279541, "step": 1500 }, { "epoch": 3.175475687103594, "grad_norm": 1.7068089246749878, "learning_rate": 2.011026733735301e-06, "loss": 0.3002539873123169, "step": 1502 }, { "epoch": 3.1797040169133193, "grad_norm": 2.8718111515045166, "learning_rate": 2.001111005409643e-06, "loss": 0.42274966835975647, "step": 1504 }, { "epoch": 3.1839323467230445, "grad_norm": 0.7863564491271973, "learning_rate": 1.9912380524076503e-06, "loss": 0.64554363489151, "step": 1506 }, { "epoch": 3.1881606765327697, "grad_norm": 2.1150660514831543, "learning_rate": 1.981407995430136e-06, "loss": 0.30870649218559265, "step": 1508 }, { "epoch": 3.192389006342495, "grad_norm": 4.922764778137207, "learning_rate": 1.9716209546535e-06, "loss": 0.3047543168067932, "step": 1510 }, { "epoch": 3.1966173361522197, "grad_norm": 0.16690078377723694, "learning_rate": 1.9618770497282487e-06, "loss": 0.06573347002267838, "step": 1512 }, { "epoch": 3.200845665961945, "grad_norm": 1.664669156074524, "learning_rate": 1.9521763997775294e-06, "loss": 0.7595316767692566, "step": 1514 }, { "epoch": 3.20507399577167, "grad_norm": 1.4734818935394287, "learning_rate": 1.942519123395689e-06, "loss": 0.7761837244033813, "step": 1516 }, { "epoch": 3.2093023255813953, "grad_norm": 9.798881530761719, "learning_rate": 1.932905338646812e-06, "loss": 0.48673951625823975, "step": 1518 }, { "epoch": 3.2135306553911205, "grad_norm": 1.2953020334243774, "learning_rate": 1.9233351630632747e-06, "loss": 0.6937761306762695, "step": 1520 }, { "epoch": 3.2177589852008457, "grad_norm": 0.7194958329200745, "learning_rate": 1.9138087136443227e-06, "loss": 0.7490251660346985, "step": 1522 }, { "epoch": 3.221987315010571, "grad_norm": 3.53690505027771, "learning_rate": 1.904326106854626e-06, "loss": 0.9285955429077148, "step": 1524 }, { "epoch": 3.226215644820296, "grad_norm": 0.7734238505363464, "learning_rate": 1.8948874586228622e-06, "loss": 0.7260890007019043, "step": 1526 }, { "epoch": 3.2304439746300213, "grad_norm": 1.0451079607009888, "learning_rate": 1.8854928843402987e-06, "loss": 0.19621600210666656, "step": 1528 }, { "epoch": 3.234672304439746, "grad_norm": 1.009931206703186, "learning_rate": 1.8761424988593796e-06, "loss": 0.7605901956558228, "step": 1530 }, { "epoch": 3.2389006342494713, "grad_norm": 1.757731556892395, "learning_rate": 1.8668364164923248e-06, "loss": 0.7074478268623352, "step": 1532 }, { "epoch": 3.2431289640591965, "grad_norm": 1.9021389484405518, "learning_rate": 1.8575747510097294e-06, "loss": 0.795443058013916, "step": 1534 }, { "epoch": 3.2473572938689217, "grad_norm": 2.7139110565185547, "learning_rate": 1.8483576156391747e-06, "loss": 0.5726435780525208, "step": 1536 }, { "epoch": 3.251585623678647, "grad_norm": 0.7819252014160156, "learning_rate": 1.8391851230638443e-06, "loss": 0.5851442813873291, "step": 1538 }, { "epoch": 3.255813953488372, "grad_norm": 2.6603641510009766, "learning_rate": 1.8300573854211452e-06, "loss": 0.4966099262237549, "step": 1540 }, { "epoch": 3.2600422832980973, "grad_norm": 1.4432668685913086, "learning_rate": 1.8209745143013363e-06, "loss": 0.9058799743652344, "step": 1542 }, { "epoch": 3.2642706131078225, "grad_norm": 0.5591882467269897, "learning_rate": 1.811936620746167e-06, "loss": 0.8662747740745544, "step": 1544 }, { "epoch": 3.2684989429175477, "grad_norm": 1.4682643413543701, "learning_rate": 1.8029438152475159e-06, "loss": 0.6742696166038513, "step": 1546 }, { "epoch": 3.2727272727272725, "grad_norm": 0.5912283062934875, "learning_rate": 1.7939962077460448e-06, "loss": 0.19926191866397858, "step": 1548 }, { "epoch": 3.276955602536998, "grad_norm": 1.2033857107162476, "learning_rate": 1.785093907629849e-06, "loss": 0.626111626625061, "step": 1550 }, { "epoch": 3.281183932346723, "grad_norm": 0.7670483589172363, "learning_rate": 1.7762370237331233e-06, "loss": 0.7666741013526917, "step": 1552 }, { "epoch": 3.285412262156448, "grad_norm": 0.07503003627061844, "learning_rate": 1.7674256643348348e-06, "loss": 0.08163535594940186, "step": 1554 }, { "epoch": 3.2896405919661733, "grad_norm": 1.967747449874878, "learning_rate": 1.7586599371573887e-06, "loss": 0.7334260940551758, "step": 1556 }, { "epoch": 3.2938689217758985, "grad_norm": 0.8944741487503052, "learning_rate": 1.7499399493653225e-06, "loss": 0.43872132897377014, "step": 1558 }, { "epoch": 3.2980972515856237, "grad_norm": 4.230812072753906, "learning_rate": 1.7412658075639921e-06, "loss": 0.9002774953842163, "step": 1560 }, { "epoch": 3.302325581395349, "grad_norm": 2.6799612045288086, "learning_rate": 1.7326376177982635e-06, "loss": 0.5518818497657776, "step": 1562 }, { "epoch": 3.306553911205074, "grad_norm": 0.6690254807472229, "learning_rate": 1.7240554855512225e-06, "loss": 0.43848365545272827, "step": 1564 }, { "epoch": 3.3107822410147993, "grad_norm": 0.6490221619606018, "learning_rate": 1.7155195157428878e-06, "loss": 0.5805073976516724, "step": 1566 }, { "epoch": 3.3150105708245245, "grad_norm": 0.4233871400356293, "learning_rate": 1.707029812728916e-06, "loss": 0.12675338983535767, "step": 1568 }, { "epoch": 3.3192389006342493, "grad_norm": 2.227142095565796, "learning_rate": 1.6985864802993366e-06, "loss": 0.46591609716415405, "step": 1570 }, { "epoch": 3.3234672304439745, "grad_norm": 3.235050678253174, "learning_rate": 1.690189621677284e-06, "loss": 0.5820206999778748, "step": 1572 }, { "epoch": 3.3276955602536997, "grad_norm": 1.67011559009552, "learning_rate": 1.681839339517728e-06, "loss": 0.21307416260242462, "step": 1574 }, { "epoch": 3.331923890063425, "grad_norm": 3.0293209552764893, "learning_rate": 1.67353573590622e-06, "loss": 0.32746008038520813, "step": 1576 }, { "epoch": 3.33615221987315, "grad_norm": 2.043689489364624, "learning_rate": 1.6652789123576513e-06, "loss": 0.4417264461517334, "step": 1578 }, { "epoch": 3.3403805496828753, "grad_norm": 1.0741723775863647, "learning_rate": 1.6570689698150094e-06, "loss": 0.47951507568359375, "step": 1580 }, { "epoch": 3.3446088794926006, "grad_norm": 1.0110905170440674, "learning_rate": 1.6489060086481373e-06, "loss": 0.8221791386604309, "step": 1582 }, { "epoch": 3.3488372093023258, "grad_norm": 2.63273286819458, "learning_rate": 1.6407901286525152e-06, "loss": 0.55421382188797, "step": 1584 }, { "epoch": 3.353065539112051, "grad_norm": 0.7283967137336731, "learning_rate": 1.6327214290480382e-06, "loss": 0.5690028667449951, "step": 1586 }, { "epoch": 3.3572938689217757, "grad_norm": 3.24580454826355, "learning_rate": 1.6247000084778006e-06, "loss": 0.7003793716430664, "step": 1588 }, { "epoch": 3.361522198731501, "grad_norm": 0.8243573307991028, "learning_rate": 1.6167259650068887e-06, "loss": 0.28278282284736633, "step": 1590 }, { "epoch": 3.365750528541226, "grad_norm": 0.7466374635696411, "learning_rate": 1.6087993961211904e-06, "loss": 0.6998204588890076, "step": 1592 }, { "epoch": 3.3699788583509513, "grad_norm": 0.6926840543746948, "learning_rate": 1.6009203987261957e-06, "loss": 0.3137359321117401, "step": 1594 }, { "epoch": 3.3742071881606766, "grad_norm": 0.9338907599449158, "learning_rate": 1.593089069145809e-06, "loss": 0.7844272255897522, "step": 1596 }, { "epoch": 3.3784355179704018, "grad_norm": 10.693819999694824, "learning_rate": 1.5853055031211844e-06, "loss": 0.6243210434913635, "step": 1598 }, { "epoch": 3.382663847780127, "grad_norm": 1.5701663494110107, "learning_rate": 1.577569795809544e-06, "loss": 0.24767853319644928, "step": 1600 }, { "epoch": 3.386892177589852, "grad_norm": 0.8462756276130676, "learning_rate": 1.5698820417830137e-06, "loss": 0.49824339151382446, "step": 1602 }, { "epoch": 3.3911205073995774, "grad_norm": 0.9267445802688599, "learning_rate": 1.5622423350274784e-06, "loss": 0.8331782221794128, "step": 1604 }, { "epoch": 3.395348837209302, "grad_norm": 0.5655416250228882, "learning_rate": 1.5546507689414217e-06, "loss": 0.8436338305473328, "step": 1606 }, { "epoch": 3.3995771670190273, "grad_norm": 13.664563179016113, "learning_rate": 1.5471074363347894e-06, "loss": 0.4969770908355713, "step": 1608 }, { "epoch": 3.4038054968287526, "grad_norm": 0.5960814952850342, "learning_rate": 1.539612429427852e-06, "loss": 0.7964329123497009, "step": 1610 }, { "epoch": 3.4080338266384778, "grad_norm": 1.0011531114578247, "learning_rate": 1.5321658398500808e-06, "loss": 0.7183132767677307, "step": 1612 }, { "epoch": 3.412262156448203, "grad_norm": 1.0399303436279297, "learning_rate": 1.5247677586390255e-06, "loss": 0.61134272813797, "step": 1614 }, { "epoch": 3.416490486257928, "grad_norm": 0.7914999127388, "learning_rate": 1.5174182762392007e-06, "loss": 0.7869651317596436, "step": 1616 }, { "epoch": 3.4207188160676534, "grad_norm": 0.8571456670761108, "learning_rate": 1.5101174825009815e-06, "loss": 0.7777673006057739, "step": 1618 }, { "epoch": 3.4249471458773786, "grad_norm": 1.093721628189087, "learning_rate": 1.5028654666795042e-06, "loss": 0.7724699378013611, "step": 1620 }, { "epoch": 3.429175475687104, "grad_norm": 4.777921199798584, "learning_rate": 1.495662317433576e-06, "loss": 0.46792668104171753, "step": 1622 }, { "epoch": 3.4334038054968286, "grad_norm": 0.6687542200088501, "learning_rate": 1.4885081228245909e-06, "loss": 0.7230125665664673, "step": 1624 }, { "epoch": 3.4376321353065538, "grad_norm": 0.9153974056243896, "learning_rate": 1.4814029703154515e-06, "loss": 0.5965611338615417, "step": 1626 }, { "epoch": 3.441860465116279, "grad_norm": 0.8647253513336182, "learning_rate": 1.4743469467695017e-06, "loss": 0.8996585607528687, "step": 1628 }, { "epoch": 3.446088794926004, "grad_norm": 1.9691336154937744, "learning_rate": 1.4673401384494651e-06, "loss": 0.38864028453826904, "step": 1630 }, { "epoch": 3.4503171247357294, "grad_norm": 0.9358199238777161, "learning_rate": 1.4603826310163874e-06, "loss": 0.6906528472900391, "step": 1632 }, { "epoch": 3.4545454545454546, "grad_norm": 0.8819380402565002, "learning_rate": 1.453474509528593e-06, "loss": 0.5243771076202393, "step": 1634 }, { "epoch": 3.45877378435518, "grad_norm": 0.8172913789749146, "learning_rate": 1.446615858440642e-06, "loss": 0.6773174405097961, "step": 1636 }, { "epoch": 3.463002114164905, "grad_norm": 0.12850317358970642, "learning_rate": 1.4398067616022993e-06, "loss": 0.28421419858932495, "step": 1638 }, { "epoch": 3.46723044397463, "grad_norm": 0.887374222278595, "learning_rate": 1.43304730225751e-06, "loss": 0.46413639187812805, "step": 1640 }, { "epoch": 3.471458773784355, "grad_norm": 0.3610607981681824, "learning_rate": 1.4263375630433802e-06, "loss": 0.17972469329833984, "step": 1642 }, { "epoch": 3.47568710359408, "grad_norm": 0.6653920412063599, "learning_rate": 1.4196776259891665e-06, "loss": 0.8025823831558228, "step": 1644 }, { "epoch": 3.4799154334038054, "grad_norm": 0.9755842089653015, "learning_rate": 1.4130675725152762e-06, "loss": 0.7314320802688599, "step": 1646 }, { "epoch": 3.4841437632135306, "grad_norm": 0.13893330097198486, "learning_rate": 1.4065074834322677e-06, "loss": 0.4566381573677063, "step": 1648 }, { "epoch": 3.488372093023256, "grad_norm": 0.7628473043441772, "learning_rate": 1.3999974389398669e-06, "loss": 0.4339445233345032, "step": 1650 }, { "epoch": 3.492600422832981, "grad_norm": 2.7723426818847656, "learning_rate": 1.3935375186259817e-06, "loss": 0.45410311222076416, "step": 1652 }, { "epoch": 3.496828752642706, "grad_norm": 1.5761070251464844, "learning_rate": 1.3871278014657332e-06, "loss": 0.6341651678085327, "step": 1654 }, { "epoch": 3.5010570824524314, "grad_norm": 0.8093578815460205, "learning_rate": 1.3807683658204915e-06, "loss": 0.7561182379722595, "step": 1656 }, { "epoch": 3.5052854122621566, "grad_norm": 0.17710785567760468, "learning_rate": 1.3744592894369093e-06, "loss": 0.42824676632881165, "step": 1658 }, { "epoch": 3.5095137420718814, "grad_norm": 1.0580307245254517, "learning_rate": 1.3682006494459806e-06, "loss": 0.5228814482688904, "step": 1660 }, { "epoch": 3.513742071881607, "grad_norm": 1.6376277208328247, "learning_rate": 1.361992522362096e-06, "loss": 0.5424702167510986, "step": 1662 }, { "epoch": 3.517970401691332, "grad_norm": 1.5473077297210693, "learning_rate": 1.355834984082101e-06, "loss": 0.7882525324821472, "step": 1664 }, { "epoch": 3.522198731501057, "grad_norm": 5.682995796203613, "learning_rate": 1.3497281098843746e-06, "loss": 0.8401514291763306, "step": 1666 }, { "epoch": 3.526427061310782, "grad_norm": 0.17630316317081451, "learning_rate": 1.34367197442791e-06, "loss": 0.09405156224966049, "step": 1668 }, { "epoch": 3.5306553911205074, "grad_norm": 0.2291719913482666, "learning_rate": 1.3376666517513931e-06, "loss": 0.6272032856941223, "step": 1670 }, { "epoch": 3.5348837209302326, "grad_norm": 0.8694557547569275, "learning_rate": 1.3317122152723078e-06, "loss": 0.5084272027015686, "step": 1672 }, { "epoch": 3.539112050739958, "grad_norm": 0.8768728375434875, "learning_rate": 1.3258087377860323e-06, "loss": 0.7008619904518127, "step": 1674 }, { "epoch": 3.543340380549683, "grad_norm": 2.6604621410369873, "learning_rate": 1.3199562914649519e-06, "loss": 0.4144883453845978, "step": 1676 }, { "epoch": 3.547568710359408, "grad_norm": 0.699931800365448, "learning_rate": 1.314154947857571e-06, "loss": 0.7476627230644226, "step": 1678 }, { "epoch": 3.5517970401691334, "grad_norm": 0.7342777848243713, "learning_rate": 1.3084047778876487e-06, "loss": 0.43216150999069214, "step": 1680 }, { "epoch": 3.556025369978858, "grad_norm": 0.6512698531150818, "learning_rate": 1.3027058518533228e-06, "loss": 0.48497718572616577, "step": 1682 }, { "epoch": 3.5602536997885834, "grad_norm": 0.8440158367156982, "learning_rate": 1.2970582394262516e-06, "loss": 0.43415167927742004, "step": 1684 }, { "epoch": 3.5644820295983086, "grad_norm": 3.0011844635009766, "learning_rate": 1.291462009650768e-06, "loss": 0.13108518719673157, "step": 1686 }, { "epoch": 3.568710359408034, "grad_norm": 0.7657526135444641, "learning_rate": 1.2859172309430285e-06, "loss": 0.6375588178634644, "step": 1688 }, { "epoch": 3.572938689217759, "grad_norm": 0.07462926208972931, "learning_rate": 1.280423971090181e-06, "loss": 0.21131929755210876, "step": 1690 }, { "epoch": 3.5771670190274842, "grad_norm": 0.8213412165641785, "learning_rate": 1.2749822972495333e-06, "loss": 0.3477196991443634, "step": 1692 }, { "epoch": 3.5813953488372094, "grad_norm": 3.2954955101013184, "learning_rate": 1.2695922759477356e-06, "loss": 0.5371741056442261, "step": 1694 }, { "epoch": 3.585623678646934, "grad_norm": 0.981082558631897, "learning_rate": 1.2642539730799622e-06, "loss": 0.2583576738834381, "step": 1696 }, { "epoch": 3.58985200845666, "grad_norm": 0.8471117615699768, "learning_rate": 1.2589674539091115e-06, "loss": 0.7673356533050537, "step": 1698 }, { "epoch": 3.5940803382663846, "grad_norm": 0.8432892560958862, "learning_rate": 1.2537327830650042e-06, "loss": 1.037954330444336, "step": 1700 }, { "epoch": 3.59830866807611, "grad_norm": 1.5492260456085205, "learning_rate": 1.248550024543594e-06, "loss": 0.719721257686615, "step": 1702 }, { "epoch": 3.602536997885835, "grad_norm": 2.8111729621887207, "learning_rate": 1.2434192417061862e-06, "loss": 0.2542896270751953, "step": 1704 }, { "epoch": 3.6067653276955602, "grad_norm": 0.8572822213172913, "learning_rate": 1.2383404972786625e-06, "loss": 0.40817975997924805, "step": 1706 }, { "epoch": 3.6109936575052854, "grad_norm": 2.271526575088501, "learning_rate": 1.2333138533507139e-06, "loss": 0.6566154360771179, "step": 1708 }, { "epoch": 3.6152219873150107, "grad_norm": 0.8319665789604187, "learning_rate": 1.2283393713750816e-06, "loss": 0.5827223658561707, "step": 1710 }, { "epoch": 3.619450317124736, "grad_norm": 0.873588502407074, "learning_rate": 1.2234171121668069e-06, "loss": 0.4422128200531006, "step": 1712 }, { "epoch": 3.6236786469344606, "grad_norm": 0.247337207198143, "learning_rate": 1.2185471359024855e-06, "loss": 0.2833689749240875, "step": 1714 }, { "epoch": 3.6279069767441863, "grad_norm": 15.89297103881836, "learning_rate": 1.2137295021195341e-06, "loss": 0.6136111617088318, "step": 1716 }, { "epoch": 3.632135306553911, "grad_norm": 0.18936192989349365, "learning_rate": 1.2089642697154613e-06, "loss": 0.4236001670360565, "step": 1718 }, { "epoch": 3.6363636363636362, "grad_norm": 2.655916929244995, "learning_rate": 1.2042514969471475e-06, "loss": 0.3413780927658081, "step": 1720 }, { "epoch": 3.6405919661733614, "grad_norm": 0.62044757604599, "learning_rate": 1.1995912414301329e-06, "loss": 0.6521108150482178, "step": 1722 }, { "epoch": 3.6448202959830867, "grad_norm": 0.689145565032959, "learning_rate": 1.1949835601379144e-06, "loss": 0.6856220960617065, "step": 1724 }, { "epoch": 3.649048625792812, "grad_norm": 1.4508981704711914, "learning_rate": 1.1904285094012463e-06, "loss": 0.8365336656570435, "step": 1726 }, { "epoch": 3.653276955602537, "grad_norm": 0.8401748538017273, "learning_rate": 1.185926144907454e-06, "loss": 0.7526130676269531, "step": 1728 }, { "epoch": 3.6575052854122623, "grad_norm": 3.612522602081299, "learning_rate": 1.1814765216997522e-06, "loss": 0.811220109462738, "step": 1730 }, { "epoch": 3.6617336152219875, "grad_norm": 1.3352470397949219, "learning_rate": 1.1770796941765727e-06, "loss": 0.7842035889625549, "step": 1732 }, { "epoch": 3.6659619450317127, "grad_norm": 0.9922516942024231, "learning_rate": 1.1727357160908978e-06, "loss": 0.700925886631012, "step": 1734 }, { "epoch": 3.6701902748414374, "grad_norm": 1.2985800504684448, "learning_rate": 1.1684446405496052e-06, "loss": 0.7992870807647705, "step": 1736 }, { "epoch": 3.6744186046511627, "grad_norm": 1.934224247932434, "learning_rate": 1.1642065200128179e-06, "loss": 0.11340885609388351, "step": 1738 }, { "epoch": 3.678646934460888, "grad_norm": 3.2180862426757812, "learning_rate": 1.1600214062932613e-06, "loss": 0.48286184668540955, "step": 1740 }, { "epoch": 3.682875264270613, "grad_norm": 3.6676065921783447, "learning_rate": 1.1558893505556315e-06, "loss": 0.32635942101478577, "step": 1742 }, { "epoch": 3.6871035940803383, "grad_norm": 1.0813003778457642, "learning_rate": 1.1518104033159715e-06, "loss": 1.008674144744873, "step": 1744 }, { "epoch": 3.6913319238900635, "grad_norm": 0.12387872487306595, "learning_rate": 1.1477846144410493e-06, "loss": 0.3836336135864258, "step": 1746 }, { "epoch": 3.6955602536997887, "grad_norm": 1.8182772397994995, "learning_rate": 1.1438120331477506e-06, "loss": 0.2998937964439392, "step": 1748 }, { "epoch": 3.699788583509514, "grad_norm": 1.2452231645584106, "learning_rate": 1.1398927080024796e-06, "loss": 0.9126724004745483, "step": 1750 }, { "epoch": 3.704016913319239, "grad_norm": 1.444623351097107, "learning_rate": 1.1360266869205593e-06, "loss": 0.3185533583164215, "step": 1752 }, { "epoch": 3.708245243128964, "grad_norm": 2.635977029800415, "learning_rate": 1.1322140171656507e-06, "loss": 0.4931368827819824, "step": 1754 }, { "epoch": 3.712473572938689, "grad_norm": 0.9160709381103516, "learning_rate": 1.1284547453491734e-06, "loss": 0.5896167755126953, "step": 1756 }, { "epoch": 3.7167019027484143, "grad_norm": 1.665767788887024, "learning_rate": 1.1247489174297372e-06, "loss": 0.4484751224517822, "step": 1758 }, { "epoch": 3.7209302325581395, "grad_norm": 0.11082155257463455, "learning_rate": 1.1210965787125743e-06, "loss": 0.3725941777229309, "step": 1760 }, { "epoch": 3.7251585623678647, "grad_norm": 2.545762777328491, "learning_rate": 1.1174977738489955e-06, "loss": 0.7290308475494385, "step": 1762 }, { "epoch": 3.72938689217759, "grad_norm": 0.6581868529319763, "learning_rate": 1.113952546835835e-06, "loss": 0.45944976806640625, "step": 1764 }, { "epoch": 3.733615221987315, "grad_norm": 2.2127058506011963, "learning_rate": 1.1104609410149174e-06, "loss": 0.8505979776382446, "step": 1766 }, { "epoch": 3.7378435517970403, "grad_norm": 0.8868612051010132, "learning_rate": 1.1070229990725262e-06, "loss": 0.6368211507797241, "step": 1768 }, { "epoch": 3.7420718816067655, "grad_norm": 0.2171614021062851, "learning_rate": 1.1036387630388841e-06, "loss": 0.19001135230064392, "step": 1770 }, { "epoch": 3.7463002114164903, "grad_norm": 2.1844234466552734, "learning_rate": 1.100308274287636e-06, "loss": 0.4170336127281189, "step": 1772 }, { "epoch": 3.7505285412262155, "grad_norm": 1.5031449794769287, "learning_rate": 1.0970315735353434e-06, "loss": 0.8781365156173706, "step": 1774 }, { "epoch": 3.7547568710359407, "grad_norm": 0.7747744917869568, "learning_rate": 1.0938087008409909e-06, "loss": 0.8626254796981812, "step": 1776 }, { "epoch": 3.758985200845666, "grad_norm": 0.6465763449668884, "learning_rate": 1.0906396956054919e-06, "loss": 0.8508058786392212, "step": 1778 }, { "epoch": 3.763213530655391, "grad_norm": 1.0285508632659912, "learning_rate": 1.0875245965712077e-06, "loss": 0.8710418343544006, "step": 1780 }, { "epoch": 3.7674418604651163, "grad_norm": 1.3890773057937622, "learning_rate": 1.0844634418214763e-06, "loss": 0.6973411440849304, "step": 1782 }, { "epoch": 3.7716701902748415, "grad_norm": 1.9281103610992432, "learning_rate": 1.0814562687801448e-06, "loss": 0.08899842202663422, "step": 1784 }, { "epoch": 3.7758985200845667, "grad_norm": 1.2274760007858276, "learning_rate": 1.0785031142111103e-06, "loss": 0.5839956998825073, "step": 1786 }, { "epoch": 3.780126849894292, "grad_norm": 1.587509274482727, "learning_rate": 1.075604014217875e-06, "loss": 0.4758831858634949, "step": 1788 }, { "epoch": 3.7843551797040167, "grad_norm": 3.5664024353027344, "learning_rate": 1.0727590042431009e-06, "loss": 0.1844044029712677, "step": 1790 }, { "epoch": 3.7885835095137423, "grad_norm": 0.19450849294662476, "learning_rate": 1.0699681190681777e-06, "loss": 0.724148154258728, "step": 1792 }, { "epoch": 3.792811839323467, "grad_norm": 0.5447925925254822, "learning_rate": 1.067231392812798e-06, "loss": 0.7825165390968323, "step": 1794 }, { "epoch": 3.7970401691331923, "grad_norm": 0.8125079274177551, "learning_rate": 1.0645488589345396e-06, "loss": 0.42041015625, "step": 1796 }, { "epoch": 3.8012684989429175, "grad_norm": 2.1443631649017334, "learning_rate": 1.0619205502284574e-06, "loss": 0.7346239686012268, "step": 1798 }, { "epoch": 3.8054968287526427, "grad_norm": 1.0177946090698242, "learning_rate": 1.0593464988266811e-06, "loss": 0.801744818687439, "step": 1800 }, { "epoch": 3.809725158562368, "grad_norm": 0.8062474131584167, "learning_rate": 1.0568267361980225e-06, "loss": 0.5560252070426941, "step": 1802 }, { "epoch": 3.813953488372093, "grad_norm": 1.0575816631317139, "learning_rate": 1.0543612931475935e-06, "loss": 0.7360133528709412, "step": 1804 }, { "epoch": 3.8181818181818183, "grad_norm": 0.5269113183021545, "learning_rate": 1.0519501998164247e-06, "loss": 0.8456173539161682, "step": 1806 }, { "epoch": 3.822410147991543, "grad_norm": 3.8595588207244873, "learning_rate": 1.049593485681101e-06, "loss": 0.13375765085220337, "step": 1808 }, { "epoch": 3.8266384778012688, "grad_norm": 1.7326875925064087, "learning_rate": 1.0472911795533997e-06, "loss": 0.8030446767807007, "step": 1810 }, { "epoch": 3.8308668076109935, "grad_norm": 1.1177000999450684, "learning_rate": 1.045043309579938e-06, "loss": 0.9534491300582886, "step": 1812 }, { "epoch": 3.8350951374207187, "grad_norm": 1.0347278118133545, "learning_rate": 1.0428499032418297e-06, "loss": 0.6889645457267761, "step": 1814 }, { "epoch": 3.839323467230444, "grad_norm": 0.8279815912246704, "learning_rate": 1.0407109873543484e-06, "loss": 0.525916576385498, "step": 1816 }, { "epoch": 3.843551797040169, "grad_norm": 5.204910755157471, "learning_rate": 1.0386265880665996e-06, "loss": 0.49038824439048767, "step": 1818 }, { "epoch": 3.8477801268498943, "grad_norm": 1.2146579027175903, "learning_rate": 1.036596730861203e-06, "loss": 0.502511203289032, "step": 1820 }, { "epoch": 3.8520084566596196, "grad_norm": 0.49327629804611206, "learning_rate": 1.0346214405539783e-06, "loss": 0.563043475151062, "step": 1822 }, { "epoch": 3.8562367864693448, "grad_norm": 0.6168828010559082, "learning_rate": 1.0327007412936419e-06, "loss": 0.446968138217926, "step": 1824 }, { "epoch": 3.8604651162790695, "grad_norm": 3.70841121673584, "learning_rate": 1.0308346565615158e-06, "loss": 0.4755552411079407, "step": 1826 }, { "epoch": 3.864693446088795, "grad_norm": 0.8400986194610596, "learning_rate": 1.0290232091712337e-06, "loss": 0.8382009863853455, "step": 1828 }, { "epoch": 3.86892177589852, "grad_norm": 0.6075788140296936, "learning_rate": 1.0272664212684687e-06, "loss": 0.8633378744125366, "step": 1830 }, { "epoch": 3.873150105708245, "grad_norm": 0.8632439374923706, "learning_rate": 1.025564314330659e-06, "loss": 0.4257108271121979, "step": 1832 }, { "epoch": 3.8773784355179703, "grad_norm": 0.6881847381591797, "learning_rate": 1.0239169091667447e-06, "loss": 0.4178315997123718, "step": 1834 }, { "epoch": 3.8816067653276956, "grad_norm": 0.3449314534664154, "learning_rate": 1.022324225916917e-06, "loss": 0.41686826944351196, "step": 1836 }, { "epoch": 3.8858350951374208, "grad_norm": 0.12805426120758057, "learning_rate": 1.0207862840523672e-06, "loss": 0.4560801386833191, "step": 1838 }, { "epoch": 3.890063424947146, "grad_norm": 0.888679027557373, "learning_rate": 1.0193031023750534e-06, "loss": 0.7192030549049377, "step": 1840 }, { "epoch": 3.894291754756871, "grad_norm": 0.8274218440055847, "learning_rate": 1.017874699017468e-06, "loss": 0.7297270894050598, "step": 1842 }, { "epoch": 3.898520084566596, "grad_norm": 0.8374532461166382, "learning_rate": 1.0165010914424142e-06, "loss": 0.44513601064682007, "step": 1844 }, { "epoch": 3.9027484143763216, "grad_norm": 3.3731489181518555, "learning_rate": 1.015182296442798e-06, "loss": 0.4543711245059967, "step": 1846 }, { "epoch": 3.9069767441860463, "grad_norm": 2.6316797733306885, "learning_rate": 1.0139183301414176e-06, "loss": 0.08663269877433777, "step": 1848 }, { "epoch": 3.9112050739957716, "grad_norm": 2.804025888442993, "learning_rate": 1.0127092079907682e-06, "loss": 0.7571265697479248, "step": 1850 }, { "epoch": 3.9154334038054968, "grad_norm": 0.4946771562099457, "learning_rate": 1.0115549447728551e-06, "loss": 0.481839656829834, "step": 1852 }, { "epoch": 3.919661733615222, "grad_norm": 1.3148247003555298, "learning_rate": 1.0104555545990088e-06, "loss": 0.7280600666999817, "step": 1854 }, { "epoch": 3.923890063424947, "grad_norm": 0.5986359119415283, "learning_rate": 1.009411050909716e-06, "loss": 0.4173433482646942, "step": 1856 }, { "epoch": 3.9281183932346724, "grad_norm": 2.8993349075317383, "learning_rate": 1.008421446474455e-06, "loss": 0.6969733238220215, "step": 1858 }, { "epoch": 3.9323467230443976, "grad_norm": 2.2495806217193604, "learning_rate": 1.0074867533915367e-06, "loss": 0.3298008143901825, "step": 1860 }, { "epoch": 3.9365750528541223, "grad_norm": 2.097533941268921, "learning_rate": 1.0066069830879593e-06, "loss": 0.8229526281356812, "step": 1862 }, { "epoch": 3.940803382663848, "grad_norm": 0.7237894535064697, "learning_rate": 1.0057821463192687e-06, "loss": 0.7725432515144348, "step": 1864 }, { "epoch": 3.9450317124735728, "grad_norm": 0.6964863538742065, "learning_rate": 1.005012253169426e-06, "loss": 0.7440751791000366, "step": 1866 }, { "epoch": 3.949260042283298, "grad_norm": 0.1627444475889206, "learning_rate": 1.0042973130506839e-06, "loss": 0.002741903532296419, "step": 1868 }, { "epoch": 3.953488372093023, "grad_norm": 1.1003438234329224, "learning_rate": 1.003637334703472e-06, "loss": 0.8684495091438293, "step": 1870 }, { "epoch": 3.9577167019027484, "grad_norm": 0.9881070852279663, "learning_rate": 1.0030323261962922e-06, "loss": 0.5530273914337158, "step": 1872 }, { "epoch": 3.9619450317124736, "grad_norm": 0.962634801864624, "learning_rate": 1.002482294925615e-06, "loss": 0.5433282852172852, "step": 1874 }, { "epoch": 3.966173361522199, "grad_norm": 0.7757136821746826, "learning_rate": 1.0019872476157952e-06, "loss": 0.7751250267028809, "step": 1876 }, { "epoch": 3.970401691331924, "grad_norm": 12.38507080078125, "learning_rate": 1.0015471903189834e-06, "loss": 0.258527010679245, "step": 1878 }, { "epoch": 3.974630021141649, "grad_norm": 1.1273119449615479, "learning_rate": 1.0011621284150583e-06, "loss": 0.41534632444381714, "step": 1880 }, { "epoch": 3.9788583509513744, "grad_norm": 2.019026041030884, "learning_rate": 1.000832066611556e-06, "loss": 0.68313068151474, "step": 1882 }, { "epoch": 3.983086680761099, "grad_norm": 0.7554054856300354, "learning_rate": 1.0005570089436137e-06, "loss": 0.8781784772872925, "step": 1884 }, { "epoch": 3.9873150105708244, "grad_norm": 1.0642335414886475, "learning_rate": 1.0003369587739234e-06, "loss": 0.5445029735565186, "step": 1886 }, { "epoch": 3.9915433403805496, "grad_norm": 3.129509210586548, "learning_rate": 1.0001719187926854e-06, "loss": 0.7804299592971802, "step": 1888 }, { "epoch": 3.995771670190275, "grad_norm": 0.736476719379425, "learning_rate": 1.0000618910175811e-06, "loss": 0.7926643490791321, "step": 1890 }, { "epoch": 4.0, "grad_norm": 1.7702542543411255, "learning_rate": 1.000006876793743e-06, "loss": 0.4586936831474304, "step": 1892 }, { "epoch": 4.0, "step": 1892, "total_flos": 3.554237146892075e+18, "train_loss": 0.8450854239206619, "train_runtime": 19534.9003, "train_samples_per_second": 2.906, "train_steps_per_second": 0.097 } ], "logging_steps": 2, "max_steps": 1892, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 99999, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.554237146892075e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }