| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 288, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003472222222222222, | |
| "grad_norm": 0.6381791234016418, | |
| "learning_rate": 4e-05, | |
| "loss": 1.664, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006944444444444444, | |
| "grad_norm": 0.6412252187728882, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010416666666666666, | |
| "grad_norm": 0.6355312466621399, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6431, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013888888888888888, | |
| "grad_norm": 0.7827576994895935, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7554, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017361111111111112, | |
| "grad_norm": 0.7365180850028992, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6866, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020833333333333332, | |
| "grad_norm": 0.7607629299163818, | |
| "learning_rate": 0.00019929328621908128, | |
| "loss": 1.5447, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024305555555555556, | |
| "grad_norm": 0.7718775272369385, | |
| "learning_rate": 0.00019858657243816254, | |
| "loss": 1.5777, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": 0.7301136255264282, | |
| "learning_rate": 0.00019787985865724384, | |
| "loss": 1.3402, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 0.6953989863395691, | |
| "learning_rate": 0.0001971731448763251, | |
| "loss": 1.4443, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "grad_norm": 0.605755090713501, | |
| "learning_rate": 0.00019646643109540637, | |
| "loss": 1.3609, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03819444444444445, | |
| "grad_norm": 0.5867183804512024, | |
| "learning_rate": 0.00019575971731448764, | |
| "loss": 1.2765, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.041666666666666664, | |
| "grad_norm": 0.5973581075668335, | |
| "learning_rate": 0.00019505300353356894, | |
| "loss": 1.2585, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04513888888888889, | |
| "grad_norm": 0.7357228398323059, | |
| "learning_rate": 0.0001943462897526502, | |
| "loss": 1.2199, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04861111111111111, | |
| "grad_norm": 0.7804207801818848, | |
| "learning_rate": 0.00019363957597173144, | |
| "loss": 1.1996, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.052083333333333336, | |
| "grad_norm": 0.813244640827179, | |
| "learning_rate": 0.0001929328621908127, | |
| "loss": 1.1735, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.7277530431747437, | |
| "learning_rate": 0.00019222614840989398, | |
| "loss": 1.1094, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.059027777777777776, | |
| "grad_norm": 0.6414357423782349, | |
| "learning_rate": 0.00019151943462897527, | |
| "loss": 1.1786, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.5542577505111694, | |
| "learning_rate": 0.00019081272084805654, | |
| "loss": 0.9343, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06597222222222222, | |
| "grad_norm": 0.5263577699661255, | |
| "learning_rate": 0.0001901060070671378, | |
| "loss": 1.0607, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06944444444444445, | |
| "grad_norm": 0.49260228872299194, | |
| "learning_rate": 0.00018939929328621908, | |
| "loss": 0.9934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07291666666666667, | |
| "grad_norm": 0.5072307586669922, | |
| "learning_rate": 0.00018869257950530037, | |
| "loss": 1.0165, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0763888888888889, | |
| "grad_norm": 0.5154305696487427, | |
| "learning_rate": 0.00018798586572438164, | |
| "loss": 1.0159, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0798611111111111, | |
| "grad_norm": 0.5033209919929504, | |
| "learning_rate": 0.0001872791519434629, | |
| "loss": 1.0102, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 0.5032006502151489, | |
| "learning_rate": 0.00018657243816254417, | |
| "loss": 1.0215, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08680555555555555, | |
| "grad_norm": 0.4746347665786743, | |
| "learning_rate": 0.00018586572438162547, | |
| "loss": 0.867, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09027777777777778, | |
| "grad_norm": 0.4780479967594147, | |
| "learning_rate": 0.00018515901060070673, | |
| "loss": 0.951, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 0.45668691396713257, | |
| "learning_rate": 0.000184452296819788, | |
| "loss": 0.9464, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09722222222222222, | |
| "grad_norm": 0.43334755301475525, | |
| "learning_rate": 0.00018374558303886927, | |
| "loss": 0.8768, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10069444444444445, | |
| "grad_norm": 0.4458893835544586, | |
| "learning_rate": 0.00018303886925795054, | |
| "loss": 0.8553, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "grad_norm": 0.4605867564678192, | |
| "learning_rate": 0.00018233215547703183, | |
| "loss": 0.948, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1076388888888889, | |
| "grad_norm": 0.44694918394088745, | |
| "learning_rate": 0.0001816254416961131, | |
| "loss": 0.8755, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.45669859647750854, | |
| "learning_rate": 0.00018091872791519434, | |
| "loss": 0.8554, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11458333333333333, | |
| "grad_norm": 0.4380110502243042, | |
| "learning_rate": 0.0001802120141342756, | |
| "loss": 0.8699, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11805555555555555, | |
| "grad_norm": 0.4494687020778656, | |
| "learning_rate": 0.0001795053003533569, | |
| "loss": 0.8463, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12152777777777778, | |
| "grad_norm": 0.4385037422180176, | |
| "learning_rate": 0.00017879858657243817, | |
| "loss": 0.7964, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.42709654569625854, | |
| "learning_rate": 0.00017809187279151944, | |
| "loss": 0.8675, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1284722222222222, | |
| "grad_norm": 0.462563157081604, | |
| "learning_rate": 0.0001773851590106007, | |
| "loss": 0.9125, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13194444444444445, | |
| "grad_norm": 0.4372367560863495, | |
| "learning_rate": 0.00017667844522968197, | |
| "loss": 0.8352, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13541666666666666, | |
| "grad_norm": 0.4251866340637207, | |
| "learning_rate": 0.00017597173144876327, | |
| "loss": 0.8695, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": 0.43755847215652466, | |
| "learning_rate": 0.00017526501766784453, | |
| "loss": 0.8544, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1423611111111111, | |
| "grad_norm": 0.44858112931251526, | |
| "learning_rate": 0.0001745583038869258, | |
| "loss": 0.835, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14583333333333334, | |
| "grad_norm": 0.4447510838508606, | |
| "learning_rate": 0.00017385159010600707, | |
| "loss": 0.8537, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14930555555555555, | |
| "grad_norm": 0.42954930663108826, | |
| "learning_rate": 0.00017314487632508836, | |
| "loss": 0.7603, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1527777777777778, | |
| "grad_norm": 0.4357329308986664, | |
| "learning_rate": 0.00017243816254416963, | |
| "loss": 0.7315, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 0.4562698304653168, | |
| "learning_rate": 0.0001717314487632509, | |
| "loss": 0.9103, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1597222222222222, | |
| "grad_norm": 0.46614545583724976, | |
| "learning_rate": 0.00017102473498233216, | |
| "loss": 0.832, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16319444444444445, | |
| "grad_norm": 0.42011672258377075, | |
| "learning_rate": 0.00017031802120141343, | |
| "loss": 0.7172, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.40585461258888245, | |
| "learning_rate": 0.00016961130742049473, | |
| "loss": 0.7087, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1701388888888889, | |
| "grad_norm": 0.4490915834903717, | |
| "learning_rate": 0.000168904593639576, | |
| "loss": 0.7956, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1736111111111111, | |
| "grad_norm": 0.4251860976219177, | |
| "learning_rate": 0.00016819787985865723, | |
| "loss": 0.7763, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17708333333333334, | |
| "grad_norm": 0.4503968060016632, | |
| "learning_rate": 0.0001674911660777385, | |
| "loss": 0.833, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.18055555555555555, | |
| "grad_norm": 0.452923059463501, | |
| "learning_rate": 0.0001667844522968198, | |
| "loss": 0.729, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1840277777777778, | |
| "grad_norm": 0.45421820878982544, | |
| "learning_rate": 0.00016607773851590106, | |
| "loss": 0.8678, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 0.47255003452301025, | |
| "learning_rate": 0.00016537102473498233, | |
| "loss": 0.7856, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1909722222222222, | |
| "grad_norm": 0.49460238218307495, | |
| "learning_rate": 0.0001646643109540636, | |
| "loss": 0.8103, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.19444444444444445, | |
| "grad_norm": 0.47668716311454773, | |
| "learning_rate": 0.0001639575971731449, | |
| "loss": 0.6687, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.19791666666666666, | |
| "grad_norm": 0.4631917178630829, | |
| "learning_rate": 0.00016325088339222616, | |
| "loss": 0.7362, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2013888888888889, | |
| "grad_norm": 0.4908764064311981, | |
| "learning_rate": 0.00016254416961130743, | |
| "loss": 0.7734, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2048611111111111, | |
| "grad_norm": 0.47517484426498413, | |
| "learning_rate": 0.0001618374558303887, | |
| "loss": 0.8048, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 0.4693131744861603, | |
| "learning_rate": 0.00016113074204946996, | |
| "loss": 0.8148, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21180555555555555, | |
| "grad_norm": 0.48101750016212463, | |
| "learning_rate": 0.00016042402826855126, | |
| "loss": 0.7089, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2152777777777778, | |
| "grad_norm": 0.45942020416259766, | |
| "learning_rate": 0.00015971731448763253, | |
| "loss": 0.7649, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.21875, | |
| "grad_norm": 0.46566373109817505, | |
| "learning_rate": 0.0001590106007067138, | |
| "loss": 0.7081, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.4782656133174896, | |
| "learning_rate": 0.00015830388692579506, | |
| "loss": 0.6578, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.22569444444444445, | |
| "grad_norm": 0.4600412845611572, | |
| "learning_rate": 0.00015759717314487635, | |
| "loss": 0.6907, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.22916666666666666, | |
| "grad_norm": 0.47648143768310547, | |
| "learning_rate": 0.00015689045936395762, | |
| "loss": 0.7159, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2326388888888889, | |
| "grad_norm": 0.4845995008945465, | |
| "learning_rate": 0.00015618374558303886, | |
| "loss": 0.6186, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2361111111111111, | |
| "grad_norm": 0.5142258405685425, | |
| "learning_rate": 0.00015547703180212013, | |
| "loss": 0.7643, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.23958333333333334, | |
| "grad_norm": 0.5000512599945068, | |
| "learning_rate": 0.0001547703180212014, | |
| "loss": 0.734, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.24305555555555555, | |
| "grad_norm": 0.473004549741745, | |
| "learning_rate": 0.0001540636042402827, | |
| "loss": 0.689, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2465277777777778, | |
| "grad_norm": 0.49982285499572754, | |
| "learning_rate": 0.00015335689045936396, | |
| "loss": 0.7162, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.48723116517066956, | |
| "learning_rate": 0.00015265017667844523, | |
| "loss": 0.605, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2534722222222222, | |
| "grad_norm": 0.4668457508087158, | |
| "learning_rate": 0.0001519434628975265, | |
| "loss": 0.7956, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2569444444444444, | |
| "grad_norm": 0.5139826536178589, | |
| "learning_rate": 0.0001512367491166078, | |
| "loss": 0.6877, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2604166666666667, | |
| "grad_norm": 0.48903441429138184, | |
| "learning_rate": 0.00015053003533568906, | |
| "loss": 0.7341, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2638888888888889, | |
| "grad_norm": 0.4892962872982025, | |
| "learning_rate": 0.00014982332155477032, | |
| "loss": 0.6833, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2673611111111111, | |
| "grad_norm": 0.510981023311615, | |
| "learning_rate": 0.0001491166077738516, | |
| "loss": 0.6567, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.2708333333333333, | |
| "grad_norm": 0.48602378368377686, | |
| "learning_rate": 0.00014840989399293289, | |
| "loss": 0.6592, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2743055555555556, | |
| "grad_norm": 0.5149515271186829, | |
| "learning_rate": 0.00014770318021201415, | |
| "loss": 0.7435, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.4999159872531891, | |
| "learning_rate": 0.00014699646643109542, | |
| "loss": 0.7397, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 0.5036943554878235, | |
| "learning_rate": 0.0001462897526501767, | |
| "loss": 0.6791, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2847222222222222, | |
| "grad_norm": 0.4811699688434601, | |
| "learning_rate": 0.00014558303886925796, | |
| "loss": 0.6376, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2881944444444444, | |
| "grad_norm": 0.5215135812759399, | |
| "learning_rate": 0.00014487632508833925, | |
| "loss": 0.6547, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.2916666666666667, | |
| "grad_norm": 0.5180763006210327, | |
| "learning_rate": 0.00014416961130742052, | |
| "loss": 0.6667, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2951388888888889, | |
| "grad_norm": 0.5010943412780762, | |
| "learning_rate": 0.00014346289752650176, | |
| "loss": 0.6496, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2986111111111111, | |
| "grad_norm": 0.47832784056663513, | |
| "learning_rate": 0.00014275618374558303, | |
| "loss": 0.6516, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.3020833333333333, | |
| "grad_norm": 0.5183102488517761, | |
| "learning_rate": 0.00014204946996466432, | |
| "loss": 0.6822, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.3055555555555556, | |
| "grad_norm": 0.5250104069709778, | |
| "learning_rate": 0.0001413427561837456, | |
| "loss": 0.6837, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.3090277777777778, | |
| "grad_norm": 0.4821203052997589, | |
| "learning_rate": 0.00014063604240282686, | |
| "loss": 0.6734, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.5341935157775879, | |
| "learning_rate": 0.00013992932862190812, | |
| "loss": 0.7098, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3159722222222222, | |
| "grad_norm": 0.5351920127868652, | |
| "learning_rate": 0.0001392226148409894, | |
| "loss": 0.6806, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3194444444444444, | |
| "grad_norm": 0.5185657143592834, | |
| "learning_rate": 0.00013851590106007068, | |
| "loss": 0.6212, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3229166666666667, | |
| "grad_norm": 0.4946865439414978, | |
| "learning_rate": 0.00013780918727915195, | |
| "loss": 0.7244, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3263888888888889, | |
| "grad_norm": 0.51689213514328, | |
| "learning_rate": 0.00013710247349823322, | |
| "loss": 0.532, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3298611111111111, | |
| "grad_norm": 0.5387365221977234, | |
| "learning_rate": 0.0001363957597173145, | |
| "loss": 0.6225, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.5210251212120056, | |
| "learning_rate": 0.00013568904593639578, | |
| "loss": 0.6565, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3368055555555556, | |
| "grad_norm": 0.5470120310783386, | |
| "learning_rate": 0.00013498233215547705, | |
| "loss": 0.6181, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3402777777777778, | |
| "grad_norm": 0.5134613513946533, | |
| "learning_rate": 0.00013427561837455832, | |
| "loss": 0.5943, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.34375, | |
| "grad_norm": 0.5114628076553345, | |
| "learning_rate": 0.00013356890459363958, | |
| "loss": 0.7112, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3472222222222222, | |
| "grad_norm": 0.5393586158752441, | |
| "learning_rate": 0.00013286219081272085, | |
| "loss": 0.6513, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3506944444444444, | |
| "grad_norm": 0.5121696591377258, | |
| "learning_rate": 0.00013215547703180215, | |
| "loss": 0.6112, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3541666666666667, | |
| "grad_norm": 0.5529887676239014, | |
| "learning_rate": 0.0001314487632508834, | |
| "loss": 0.704, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.3576388888888889, | |
| "grad_norm": 0.5504875779151917, | |
| "learning_rate": 0.00013074204946996465, | |
| "loss": 0.6367, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.3611111111111111, | |
| "grad_norm": 0.5555490255355835, | |
| "learning_rate": 0.00013003533568904592, | |
| "loss": 0.6988, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.3645833333333333, | |
| "grad_norm": 0.5071545839309692, | |
| "learning_rate": 0.00012932862190812722, | |
| "loss": 0.6598, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3680555555555556, | |
| "grad_norm": 0.5332069396972656, | |
| "learning_rate": 0.00012862190812720848, | |
| "loss": 0.65, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.3715277777777778, | |
| "grad_norm": 0.5629200339317322, | |
| "learning_rate": 0.00012791519434628975, | |
| "loss": 0.699, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.5515280961990356, | |
| "learning_rate": 0.00012720848056537102, | |
| "loss": 0.6418, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.3784722222222222, | |
| "grad_norm": 0.527538001537323, | |
| "learning_rate": 0.0001265017667844523, | |
| "loss": 0.7302, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.3819444444444444, | |
| "grad_norm": 0.5716756582260132, | |
| "learning_rate": 0.00012579505300353358, | |
| "loss": 0.7443, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3854166666666667, | |
| "grad_norm": 0.5540614724159241, | |
| "learning_rate": 0.00012508833922261485, | |
| "loss": 0.6564, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.5193327069282532, | |
| "learning_rate": 0.00012438162544169612, | |
| "loss": 0.6783, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3923611111111111, | |
| "grad_norm": 0.5474222302436829, | |
| "learning_rate": 0.00012367491166077738, | |
| "loss": 0.6519, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.3958333333333333, | |
| "grad_norm": 0.5058162808418274, | |
| "learning_rate": 0.00012296819787985868, | |
| "loss": 0.5785, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.3993055555555556, | |
| "grad_norm": 0.5280646085739136, | |
| "learning_rate": 0.00012226148409893994, | |
| "loss": 0.6308, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.4027777777777778, | |
| "grad_norm": 0.536086916923523, | |
| "learning_rate": 0.0001215547703180212, | |
| "loss": 0.5696, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.40625, | |
| "grad_norm": 0.5223795771598816, | |
| "learning_rate": 0.00012084805653710247, | |
| "loss": 0.5861, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.4097222222222222, | |
| "grad_norm": 0.5218377113342285, | |
| "learning_rate": 0.00012014134275618376, | |
| "loss": 0.6151, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.4131944444444444, | |
| "grad_norm": 0.5461903214454651, | |
| "learning_rate": 0.00011943462897526503, | |
| "loss": 0.585, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 0.5451020002365112, | |
| "learning_rate": 0.0001187279151943463, | |
| "loss": 0.6571, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4201388888888889, | |
| "grad_norm": 0.5320534706115723, | |
| "learning_rate": 0.00011802120141342756, | |
| "loss": 0.6191, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.4236111111111111, | |
| "grad_norm": 0.5509814023971558, | |
| "learning_rate": 0.00011731448763250883, | |
| "loss": 0.542, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.4270833333333333, | |
| "grad_norm": 0.5494756102561951, | |
| "learning_rate": 0.00011660777385159012, | |
| "loss": 0.7145, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.4305555555555556, | |
| "grad_norm": 0.5778016448020935, | |
| "learning_rate": 0.00011590106007067139, | |
| "loss": 0.6787, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.4340277777777778, | |
| "grad_norm": 0.5546441674232483, | |
| "learning_rate": 0.00011519434628975265, | |
| "loss": 0.5897, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 0.5590822100639343, | |
| "learning_rate": 0.00011448763250883391, | |
| "loss": 0.6331, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.4409722222222222, | |
| "grad_norm": 0.5571174025535583, | |
| "learning_rate": 0.00011378091872791521, | |
| "loss": 0.6624, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.579007625579834, | |
| "learning_rate": 0.00011307420494699648, | |
| "loss": 0.6377, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.4479166666666667, | |
| "grad_norm": 0.5956988334655762, | |
| "learning_rate": 0.00011236749116607774, | |
| "loss": 0.6828, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.4513888888888889, | |
| "grad_norm": 0.5952633023262024, | |
| "learning_rate": 0.00011166077738515901, | |
| "loss": 0.5603, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4548611111111111, | |
| "grad_norm": 0.561600387096405, | |
| "learning_rate": 0.00011095406360424028, | |
| "loss": 0.6311, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4583333333333333, | |
| "grad_norm": 0.5515158772468567, | |
| "learning_rate": 0.00011024734982332157, | |
| "loss": 0.7293, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4618055555555556, | |
| "grad_norm": 0.5889860987663269, | |
| "learning_rate": 0.00010954063604240284, | |
| "loss": 0.6693, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.4652777777777778, | |
| "grad_norm": 0.5815720558166504, | |
| "learning_rate": 0.0001088339222614841, | |
| "loss": 0.6881, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 0.6205659508705139, | |
| "learning_rate": 0.00010812720848056536, | |
| "loss": 0.6732, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.4722222222222222, | |
| "grad_norm": 0.5689711570739746, | |
| "learning_rate": 0.00010742049469964666, | |
| "loss": 0.6206, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.4756944444444444, | |
| "grad_norm": 0.5453592538833618, | |
| "learning_rate": 0.00010671378091872792, | |
| "loss": 0.6257, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.4791666666666667, | |
| "grad_norm": 0.5330798625946045, | |
| "learning_rate": 0.00010600706713780919, | |
| "loss": 0.4674, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.4826388888888889, | |
| "grad_norm": 0.5798875093460083, | |
| "learning_rate": 0.00010530035335689046, | |
| "loss": 0.6017, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.4861111111111111, | |
| "grad_norm": 0.5574885010719299, | |
| "learning_rate": 0.00010459363957597175, | |
| "loss": 0.6087, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4895833333333333, | |
| "grad_norm": 0.5381941199302673, | |
| "learning_rate": 0.00010388692579505302, | |
| "loss": 0.6543, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.4930555555555556, | |
| "grad_norm": 0.5750802755355835, | |
| "learning_rate": 0.00010318021201413429, | |
| "loss": 0.6662, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.4965277777777778, | |
| "grad_norm": 0.6241365671157837, | |
| "learning_rate": 0.00010247349823321554, | |
| "loss": 0.5976, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.5461493134498596, | |
| "learning_rate": 0.00010176678445229681, | |
| "loss": 0.6796, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5034722222222222, | |
| "grad_norm": 0.5892328023910522, | |
| "learning_rate": 0.0001010600706713781, | |
| "loss": 0.6166, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5069444444444444, | |
| "grad_norm": 0.5670603513717651, | |
| "learning_rate": 0.00010035335689045937, | |
| "loss": 0.651, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.5104166666666666, | |
| "grad_norm": 0.5573473572731018, | |
| "learning_rate": 9.964664310954064e-05, | |
| "loss": 0.6268, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.5138888888888888, | |
| "grad_norm": 0.5641173720359802, | |
| "learning_rate": 9.893992932862192e-05, | |
| "loss": 0.6515, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.5173611111111112, | |
| "grad_norm": 0.5903286337852478, | |
| "learning_rate": 9.823321554770319e-05, | |
| "loss": 0.6705, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.5208333333333334, | |
| "grad_norm": 0.5907771587371826, | |
| "learning_rate": 9.752650176678447e-05, | |
| "loss": 0.6184, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5243055555555556, | |
| "grad_norm": 0.5515082478523254, | |
| "learning_rate": 9.681978798586572e-05, | |
| "loss": 0.661, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.5277777777777778, | |
| "grad_norm": 0.5268746614456177, | |
| "learning_rate": 9.611307420494699e-05, | |
| "loss": 0.6082, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.53125, | |
| "grad_norm": 0.5877247452735901, | |
| "learning_rate": 9.540636042402827e-05, | |
| "loss": 0.5856, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.5347222222222222, | |
| "grad_norm": 0.5402259826660156, | |
| "learning_rate": 9.469964664310954e-05, | |
| "loss": 0.574, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.5381944444444444, | |
| "grad_norm": 0.5235267281532288, | |
| "learning_rate": 9.399293286219082e-05, | |
| "loss": 0.5598, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5416666666666666, | |
| "grad_norm": 0.5417196750640869, | |
| "learning_rate": 9.328621908127209e-05, | |
| "loss": 0.6447, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.5451388888888888, | |
| "grad_norm": 0.6259889006614685, | |
| "learning_rate": 9.257950530035337e-05, | |
| "loss": 0.6227, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.5486111111111112, | |
| "grad_norm": 0.567189633846283, | |
| "learning_rate": 9.187279151943463e-05, | |
| "loss": 0.5788, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.5520833333333334, | |
| "grad_norm": 0.5860530138015747, | |
| "learning_rate": 9.116607773851592e-05, | |
| "loss": 0.5026, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.5970867872238159, | |
| "learning_rate": 9.045936395759717e-05, | |
| "loss": 0.65, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5590277777777778, | |
| "grad_norm": 0.5621108412742615, | |
| "learning_rate": 8.975265017667845e-05, | |
| "loss": 0.6118, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 0.5695009827613831, | |
| "learning_rate": 8.904593639575972e-05, | |
| "loss": 0.5119, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.5659722222222222, | |
| "grad_norm": 0.5741239786148071, | |
| "learning_rate": 8.833922261484099e-05, | |
| "loss": 0.5273, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.5694444444444444, | |
| "grad_norm": 0.5961455702781677, | |
| "learning_rate": 8.763250883392227e-05, | |
| "loss": 0.6197, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.5729166666666666, | |
| "grad_norm": 0.5358597636222839, | |
| "learning_rate": 8.692579505300353e-05, | |
| "loss": 0.5629, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.5763888888888888, | |
| "grad_norm": 0.5704313516616821, | |
| "learning_rate": 8.621908127208482e-05, | |
| "loss": 0.5838, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.5798611111111112, | |
| "grad_norm": 0.6421118378639221, | |
| "learning_rate": 8.551236749116608e-05, | |
| "loss": 0.5964, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.5833333333333334, | |
| "grad_norm": 0.5588890314102173, | |
| "learning_rate": 8.480565371024736e-05, | |
| "loss": 0.4957, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.5868055555555556, | |
| "grad_norm": 0.5954290628433228, | |
| "learning_rate": 8.409893992932862e-05, | |
| "loss": 0.6364, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.5902777777777778, | |
| "grad_norm": 0.5738086700439453, | |
| "learning_rate": 8.33922261484099e-05, | |
| "loss": 0.5661, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.59375, | |
| "grad_norm": 0.6033700704574585, | |
| "learning_rate": 8.268551236749117e-05, | |
| "loss": 0.6128, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.5972222222222222, | |
| "grad_norm": 0.6137632727622986, | |
| "learning_rate": 8.197879858657245e-05, | |
| "loss": 0.6271, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.6006944444444444, | |
| "grad_norm": 0.5929612517356873, | |
| "learning_rate": 8.127208480565371e-05, | |
| "loss": 0.6328, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.6041666666666666, | |
| "grad_norm": 0.5914517641067505, | |
| "learning_rate": 8.056537102473498e-05, | |
| "loss": 0.6406, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.6076388888888888, | |
| "grad_norm": 0.5911087989807129, | |
| "learning_rate": 7.985865724381626e-05, | |
| "loss": 0.5432, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.6051996350288391, | |
| "learning_rate": 7.915194346289753e-05, | |
| "loss": 0.576, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.6145833333333334, | |
| "grad_norm": 0.5913227200508118, | |
| "learning_rate": 7.844522968197881e-05, | |
| "loss": 0.6012, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.6180555555555556, | |
| "grad_norm": 0.5444892048835754, | |
| "learning_rate": 7.773851590106007e-05, | |
| "loss": 0.5324, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.6215277777777778, | |
| "grad_norm": 0.5951313972473145, | |
| "learning_rate": 7.703180212014135e-05, | |
| "loss": 0.6932, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.5791239142417908, | |
| "learning_rate": 7.632508833922261e-05, | |
| "loss": 0.6144, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6284722222222222, | |
| "grad_norm": 0.5847236514091492, | |
| "learning_rate": 7.56183745583039e-05, | |
| "loss": 0.5894, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.6319444444444444, | |
| "grad_norm": 0.6364589929580688, | |
| "learning_rate": 7.491166077738516e-05, | |
| "loss": 0.5187, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.6354166666666666, | |
| "grad_norm": 0.572428822517395, | |
| "learning_rate": 7.420494699646644e-05, | |
| "loss": 0.5653, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.6388888888888888, | |
| "grad_norm": 0.5649181008338928, | |
| "learning_rate": 7.349823321554771e-05, | |
| "loss": 0.5586, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.6423611111111112, | |
| "grad_norm": 0.5847340226173401, | |
| "learning_rate": 7.279151943462898e-05, | |
| "loss": 0.6389, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.6458333333333334, | |
| "grad_norm": 0.5655092597007751, | |
| "learning_rate": 7.208480565371026e-05, | |
| "loss": 0.5809, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.6493055555555556, | |
| "grad_norm": 0.5791696310043335, | |
| "learning_rate": 7.137809187279151e-05, | |
| "loss": 0.6295, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.6527777777777778, | |
| "grad_norm": 0.6031994223594666, | |
| "learning_rate": 7.06713780918728e-05, | |
| "loss": 0.5962, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 0.6025336980819702, | |
| "learning_rate": 6.996466431095406e-05, | |
| "loss": 0.6424, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.6597222222222222, | |
| "grad_norm": 0.6521866917610168, | |
| "learning_rate": 6.925795053003534e-05, | |
| "loss": 0.5857, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6631944444444444, | |
| "grad_norm": 0.5835008025169373, | |
| "learning_rate": 6.855123674911661e-05, | |
| "loss": 0.5807, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.5866998434066772, | |
| "learning_rate": 6.784452296819789e-05, | |
| "loss": 0.5653, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.6701388888888888, | |
| "grad_norm": 0.5725639462471008, | |
| "learning_rate": 6.713780918727916e-05, | |
| "loss": 0.4654, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.6736111111111112, | |
| "grad_norm": 0.6040775775909424, | |
| "learning_rate": 6.643109540636043e-05, | |
| "loss": 0.6563, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.6770833333333334, | |
| "grad_norm": 0.6573815941810608, | |
| "learning_rate": 6.57243816254417e-05, | |
| "loss": 0.5836, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6805555555555556, | |
| "grad_norm": 0.5753028392791748, | |
| "learning_rate": 6.501766784452296e-05, | |
| "loss": 0.6142, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.6840277777777778, | |
| "grad_norm": 0.6084535717964172, | |
| "learning_rate": 6.431095406360424e-05, | |
| "loss": 0.5592, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.6875, | |
| "grad_norm": 0.6668769717216492, | |
| "learning_rate": 6.360424028268551e-05, | |
| "loss": 0.563, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.6909722222222222, | |
| "grad_norm": 0.620083212852478, | |
| "learning_rate": 6.289752650176679e-05, | |
| "loss": 0.4906, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.6944444444444444, | |
| "grad_norm": 0.6372251510620117, | |
| "learning_rate": 6.219081272084806e-05, | |
| "loss": 0.5754, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6979166666666666, | |
| "grad_norm": 0.602571964263916, | |
| "learning_rate": 6.148409893992934e-05, | |
| "loss": 0.5631, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.7013888888888888, | |
| "grad_norm": 0.610701322555542, | |
| "learning_rate": 6.07773851590106e-05, | |
| "loss": 0.6417, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.7048611111111112, | |
| "grad_norm": 0.6244217753410339, | |
| "learning_rate": 6.007067137809188e-05, | |
| "loss": 0.6194, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.7083333333333334, | |
| "grad_norm": 0.6154200434684753, | |
| "learning_rate": 5.936395759717315e-05, | |
| "loss": 0.5724, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.7118055555555556, | |
| "grad_norm": 0.5975745916366577, | |
| "learning_rate": 5.8657243816254415e-05, | |
| "loss": 0.6117, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7152777777777778, | |
| "grad_norm": 0.6204216480255127, | |
| "learning_rate": 5.7950530035335696e-05, | |
| "loss": 0.6153, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.71875, | |
| "grad_norm": 0.5886074900627136, | |
| "learning_rate": 5.724381625441696e-05, | |
| "loss": 0.4968, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 0.5940162539482117, | |
| "learning_rate": 5.653710247349824e-05, | |
| "loss": 0.6544, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.7256944444444444, | |
| "grad_norm": 0.596792459487915, | |
| "learning_rate": 5.5830388692579505e-05, | |
| "loss": 0.5685, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.7291666666666666, | |
| "grad_norm": 0.5985198020935059, | |
| "learning_rate": 5.5123674911660786e-05, | |
| "loss": 0.5795, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7326388888888888, | |
| "grad_norm": 0.5998839735984802, | |
| "learning_rate": 5.441696113074205e-05, | |
| "loss": 0.5229, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.7361111111111112, | |
| "grad_norm": 0.5900275707244873, | |
| "learning_rate": 5.371024734982333e-05, | |
| "loss": 0.5882, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.7395833333333334, | |
| "grad_norm": 0.5826575756072998, | |
| "learning_rate": 5.3003533568904595e-05, | |
| "loss": 0.4709, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.7430555555555556, | |
| "grad_norm": 0.5909337997436523, | |
| "learning_rate": 5.2296819787985876e-05, | |
| "loss": 0.5528, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.7465277777777778, | |
| "grad_norm": 0.5588683485984802, | |
| "learning_rate": 5.1590106007067144e-05, | |
| "loss": 0.5373, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.5555421710014343, | |
| "learning_rate": 5.0883392226148405e-05, | |
| "loss": 0.5779, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.7534722222222222, | |
| "grad_norm": 0.5925477743148804, | |
| "learning_rate": 5.0176678445229686e-05, | |
| "loss": 0.5896, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.7569444444444444, | |
| "grad_norm": 0.6183862090110779, | |
| "learning_rate": 4.946996466431096e-05, | |
| "loss": 0.6245, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.7604166666666666, | |
| "grad_norm": 0.5807591080665588, | |
| "learning_rate": 4.8763250883392234e-05, | |
| "loss": 0.5509, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.7638888888888888, | |
| "grad_norm": 0.5723608136177063, | |
| "learning_rate": 4.8056537102473495e-05, | |
| "loss": 0.5927, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7673611111111112, | |
| "grad_norm": 0.5748648643493652, | |
| "learning_rate": 4.734982332155477e-05, | |
| "loss": 0.5009, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.7708333333333334, | |
| "grad_norm": 0.5595970749855042, | |
| "learning_rate": 4.664310954063604e-05, | |
| "loss": 0.5225, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.7743055555555556, | |
| "grad_norm": 0.5699341893196106, | |
| "learning_rate": 4.593639575971732e-05, | |
| "loss": 0.5945, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.5965125560760498, | |
| "learning_rate": 4.5229681978798585e-05, | |
| "loss": 0.6039, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 0.601673424243927, | |
| "learning_rate": 4.452296819787986e-05, | |
| "loss": 0.6116, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.7847222222222222, | |
| "grad_norm": 0.6311600804328918, | |
| "learning_rate": 4.381625441696113e-05, | |
| "loss": 0.6356, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.7881944444444444, | |
| "grad_norm": 0.6146146059036255, | |
| "learning_rate": 4.310954063604241e-05, | |
| "loss": 0.5925, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.7916666666666666, | |
| "grad_norm": 0.5608177781105042, | |
| "learning_rate": 4.240282685512368e-05, | |
| "loss": 0.4546, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.7951388888888888, | |
| "grad_norm": 0.6077985167503357, | |
| "learning_rate": 4.169611307420495e-05, | |
| "loss": 0.6111, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.7986111111111112, | |
| "grad_norm": 0.5868244171142578, | |
| "learning_rate": 4.0989399293286223e-05, | |
| "loss": 0.5945, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8020833333333334, | |
| "grad_norm": 0.587386965751648, | |
| "learning_rate": 4.028268551236749e-05, | |
| "loss": 0.5294, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.8055555555555556, | |
| "grad_norm": 0.5953108668327332, | |
| "learning_rate": 3.9575971731448765e-05, | |
| "loss": 0.5621, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.8090277777777778, | |
| "grad_norm": 0.6050392985343933, | |
| "learning_rate": 3.886925795053003e-05, | |
| "loss": 0.5374, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.8125, | |
| "grad_norm": 0.6083176732063293, | |
| "learning_rate": 3.816254416961131e-05, | |
| "loss": 0.5843, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.8159722222222222, | |
| "grad_norm": 0.5946184992790222, | |
| "learning_rate": 3.745583038869258e-05, | |
| "loss": 0.5049, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8194444444444444, | |
| "grad_norm": 0.5910969972610474, | |
| "learning_rate": 3.6749116607773855e-05, | |
| "loss": 0.5749, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.8229166666666666, | |
| "grad_norm": 0.5982712507247925, | |
| "learning_rate": 3.604240282685513e-05, | |
| "loss": 0.5882, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.8263888888888888, | |
| "grad_norm": 0.6084917783737183, | |
| "learning_rate": 3.53356890459364e-05, | |
| "loss": 0.5169, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.8298611111111112, | |
| "grad_norm": 0.6236574649810791, | |
| "learning_rate": 3.462897526501767e-05, | |
| "loss": 0.6085, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.592654824256897, | |
| "learning_rate": 3.3922261484098945e-05, | |
| "loss": 0.5525, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8368055555555556, | |
| "grad_norm": 0.6017850041389465, | |
| "learning_rate": 3.321554770318021e-05, | |
| "loss": 0.636, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.8402777777777778, | |
| "grad_norm": 0.5793926119804382, | |
| "learning_rate": 3.250883392226148e-05, | |
| "loss": 0.6003, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 0.5898053050041199, | |
| "learning_rate": 3.1802120141342755e-05, | |
| "loss": 0.6925, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.8472222222222222, | |
| "grad_norm": 0.6041194796562195, | |
| "learning_rate": 3.109540636042403e-05, | |
| "loss": 0.5509, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.8506944444444444, | |
| "grad_norm": 0.5889320373535156, | |
| "learning_rate": 3.03886925795053e-05, | |
| "loss": 0.5377, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.8541666666666666, | |
| "grad_norm": 0.65882408618927, | |
| "learning_rate": 2.9681978798586574e-05, | |
| "loss": 0.6909, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.8576388888888888, | |
| "grad_norm": 0.5652550458908081, | |
| "learning_rate": 2.8975265017667848e-05, | |
| "loss": 0.6553, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.8611111111111112, | |
| "grad_norm": 0.6159343123435974, | |
| "learning_rate": 2.826855123674912e-05, | |
| "loss": 0.4816, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.8645833333333334, | |
| "grad_norm": 0.5917626023292542, | |
| "learning_rate": 2.7561837455830393e-05, | |
| "loss": 0.6042, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.8680555555555556, | |
| "grad_norm": 0.5773218870162964, | |
| "learning_rate": 2.6855123674911664e-05, | |
| "loss": 0.5723, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8715277777777778, | |
| "grad_norm": 0.5936452150344849, | |
| "learning_rate": 2.6148409893992938e-05, | |
| "loss": 0.6071, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 0.6094207763671875, | |
| "learning_rate": 2.5441696113074202e-05, | |
| "loss": 0.5406, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.8784722222222222, | |
| "grad_norm": 0.6131781935691833, | |
| "learning_rate": 2.473498233215548e-05, | |
| "loss": 0.562, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.8819444444444444, | |
| "grad_norm": 0.5903745889663696, | |
| "learning_rate": 2.4028268551236747e-05, | |
| "loss": 0.5841, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.8854166666666666, | |
| "grad_norm": 0.5778252482414246, | |
| "learning_rate": 2.332155477031802e-05, | |
| "loss": 0.6071, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.6057181358337402, | |
| "learning_rate": 2.2614840989399292e-05, | |
| "loss": 0.5794, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.8923611111111112, | |
| "grad_norm": 0.5691949129104614, | |
| "learning_rate": 2.1908127208480567e-05, | |
| "loss": 0.5634, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.8958333333333334, | |
| "grad_norm": 0.6154379844665527, | |
| "learning_rate": 2.120141342756184e-05, | |
| "loss": 0.5389, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.8993055555555556, | |
| "grad_norm": 0.5671730637550354, | |
| "learning_rate": 2.0494699646643112e-05, | |
| "loss": 0.6045, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.9027777777777778, | |
| "grad_norm": 0.6344681978225708, | |
| "learning_rate": 1.9787985865724383e-05, | |
| "loss": 0.4922, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.90625, | |
| "grad_norm": 0.584071934223175, | |
| "learning_rate": 1.9081272084805653e-05, | |
| "loss": 0.5283, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.9097222222222222, | |
| "grad_norm": 0.5744527578353882, | |
| "learning_rate": 1.8374558303886928e-05, | |
| "loss": 0.51, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.9131944444444444, | |
| "grad_norm": 0.5983773469924927, | |
| "learning_rate": 1.76678445229682e-05, | |
| "loss": 0.619, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.9166666666666666, | |
| "grad_norm": 0.5973845720291138, | |
| "learning_rate": 1.6961130742049473e-05, | |
| "loss": 0.5131, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.9201388888888888, | |
| "grad_norm": 0.6193533539772034, | |
| "learning_rate": 1.625441696113074e-05, | |
| "loss": 0.577, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.9236111111111112, | |
| "grad_norm": 0.6047850251197815, | |
| "learning_rate": 1.5547703180212014e-05, | |
| "loss": 0.6277, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.9270833333333334, | |
| "grad_norm": 0.6007250547409058, | |
| "learning_rate": 1.4840989399293287e-05, | |
| "loss": 0.6026, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.9305555555555556, | |
| "grad_norm": 0.5738986730575562, | |
| "learning_rate": 1.413427561837456e-05, | |
| "loss": 0.5842, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.9340277777777778, | |
| "grad_norm": 0.5671294927597046, | |
| "learning_rate": 1.3427561837455832e-05, | |
| "loss": 0.4875, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.5837607383728027, | |
| "learning_rate": 1.2720848056537101e-05, | |
| "loss": 0.6032, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9409722222222222, | |
| "grad_norm": 0.6210164427757263, | |
| "learning_rate": 1.2014134275618374e-05, | |
| "loss": 0.6143, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.9444444444444444, | |
| "grad_norm": 0.5613874197006226, | |
| "learning_rate": 1.1307420494699646e-05, | |
| "loss": 0.5193, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.9479166666666666, | |
| "grad_norm": 0.5788601636886597, | |
| "learning_rate": 1.060070671378092e-05, | |
| "loss": 0.5993, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.9513888888888888, | |
| "grad_norm": 0.5956071615219116, | |
| "learning_rate": 9.893992932862191e-06, | |
| "loss": 0.6244, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.9548611111111112, | |
| "grad_norm": 0.5741413235664368, | |
| "learning_rate": 9.187279151943464e-06, | |
| "loss": 0.5912, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.9583333333333334, | |
| "grad_norm": 0.5746176242828369, | |
| "learning_rate": 8.480565371024736e-06, | |
| "loss": 0.4959, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.9618055555555556, | |
| "grad_norm": 0.6048396825790405, | |
| "learning_rate": 7.773851590106007e-06, | |
| "loss": 0.5358, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.9652777777777778, | |
| "grad_norm": 0.5789562463760376, | |
| "learning_rate": 7.06713780918728e-06, | |
| "loss": 0.526, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.96875, | |
| "grad_norm": 0.623224139213562, | |
| "learning_rate": 6.3604240282685506e-06, | |
| "loss": 0.6296, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.9722222222222222, | |
| "grad_norm": 0.5628058910369873, | |
| "learning_rate": 5.653710247349823e-06, | |
| "loss": 0.519, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9756944444444444, | |
| "grad_norm": 0.574334442615509, | |
| "learning_rate": 4.946996466431096e-06, | |
| "loss": 0.5241, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.9791666666666666, | |
| "grad_norm": 0.6212002038955688, | |
| "learning_rate": 4.240282685512368e-06, | |
| "loss": 0.6307, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.9826388888888888, | |
| "grad_norm": 0.6209303140640259, | |
| "learning_rate": 3.53356890459364e-06, | |
| "loss": 0.5419, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.9861111111111112, | |
| "grad_norm": 0.6056732535362244, | |
| "learning_rate": 2.8268551236749116e-06, | |
| "loss": 0.6091, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.9895833333333334, | |
| "grad_norm": 0.632924497127533, | |
| "learning_rate": 2.120141342756184e-06, | |
| "loss": 0.6159, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.9930555555555556, | |
| "grad_norm": 0.6058059334754944, | |
| "learning_rate": 1.4134275618374558e-06, | |
| "loss": 0.5805, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.9965277777777778, | |
| "grad_norm": 0.6084165573120117, | |
| "learning_rate": 7.067137809187279e-07, | |
| "loss": 0.6208, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.6049368977546692, | |
| "learning_rate": 0.0, | |
| "loss": 0.4819, | |
| "step": 288 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 288, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.5964978416533504e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |