{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.9411764705882355, "eval_steps": 500, "global_step": 558, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0106951871657754, "grad_norm": 2.3326733714545216, "learning_rate": 0.0, "loss": 2.2246, "step": 1 }, { "epoch": 0.0213903743315508, "grad_norm": 2.383068273995448, "learning_rate": 1.176470588235294e-08, "loss": 2.2524, "step": 2 }, { "epoch": 0.03208556149732621, "grad_norm": 2.346741099308723, "learning_rate": 2.352941176470588e-08, "loss": 2.2901, "step": 3 }, { "epoch": 0.0427807486631016, "grad_norm": 2.3195515052434774, "learning_rate": 3.5294117647058824e-08, "loss": 2.188, "step": 4 }, { "epoch": 0.053475935828877004, "grad_norm": 2.3930583380150647, "learning_rate": 4.705882352941176e-08, "loss": 2.3759, "step": 5 }, { "epoch": 0.06417112299465241, "grad_norm": 2.3702962178012346, "learning_rate": 5.88235294117647e-08, "loss": 2.2199, "step": 6 }, { "epoch": 0.0748663101604278, "grad_norm": 2.245916423471001, "learning_rate": 7.058823529411765e-08, "loss": 2.2146, "step": 7 }, { "epoch": 0.0855614973262032, "grad_norm": 2.41663882573251, "learning_rate": 8.235294117647059e-08, "loss": 2.2563, "step": 8 }, { "epoch": 0.0962566844919786, "grad_norm": 2.3987090250815117, "learning_rate": 9.411764705882353e-08, "loss": 2.265, "step": 9 }, { "epoch": 0.10695187165775401, "grad_norm": 2.4317750198267087, "learning_rate": 1.0588235294117647e-07, "loss": 2.2326, "step": 10 }, { "epoch": 0.11764705882352941, "grad_norm": 2.2502074348810797, "learning_rate": 1.176470588235294e-07, "loss": 2.2682, "step": 11 }, { "epoch": 0.12834224598930483, "grad_norm": 2.3396463833691086, "learning_rate": 1.2941176470588236e-07, "loss": 2.3054, "step": 12 }, { "epoch": 0.13903743315508021, "grad_norm": 2.2745883257040482, "learning_rate": 1.411764705882353e-07, "loss": 2.3155, "step": 13 }, { "epoch": 0.1497326203208556, "grad_norm": 2.252862417275673, "learning_rate": 1.529411764705882e-07, "loss": 2.2299, "step": 14 }, { "epoch": 0.16042780748663102, "grad_norm": 2.4840297553789084, "learning_rate": 1.6470588235294117e-07, "loss": 2.2689, "step": 15 }, { "epoch": 0.1711229946524064, "grad_norm": 2.3823729593084964, "learning_rate": 1.764705882352941e-07, "loss": 2.2657, "step": 16 }, { "epoch": 0.18181818181818182, "grad_norm": 2.3784768765909337, "learning_rate": 1.8823529411764705e-07, "loss": 2.4154, "step": 17 }, { "epoch": 0.1925133689839572, "grad_norm": 2.5799926908653994, "learning_rate": 2e-07, "loss": 2.1927, "step": 18 }, { "epoch": 0.20320855614973263, "grad_norm": 2.556016587859765, "learning_rate": 1.9999831393621957e-07, "loss": 2.2038, "step": 19 }, { "epoch": 0.21390374331550802, "grad_norm": 2.4625079082060704, "learning_rate": 1.999932558017345e-07, "loss": 2.198, "step": 20 }, { "epoch": 0.22459893048128343, "grad_norm": 2.342376776566097, "learning_rate": 1.999848257671115e-07, "loss": 2.1982, "step": 21 }, { "epoch": 0.23529411764705882, "grad_norm": 2.3597940311416545, "learning_rate": 1.999730241166222e-07, "loss": 2.2598, "step": 22 }, { "epoch": 0.24598930481283424, "grad_norm": 2.5731029459823365, "learning_rate": 1.9995785124823318e-07, "loss": 2.2165, "step": 23 }, { "epoch": 0.25668449197860965, "grad_norm": 2.439017240411731, "learning_rate": 1.99939307673593e-07, "loss": 2.1988, "step": 24 }, { "epoch": 0.26737967914438504, "grad_norm": 2.4757026852565547, "learning_rate": 1.9991739401801462e-07, "loss": 2.2609, "step": 25 }, { "epoch": 0.27807486631016043, "grad_norm": 2.2609181567151184, "learning_rate": 1.9989211102045448e-07, "loss": 2.2976, "step": 26 }, { "epoch": 0.2887700534759358, "grad_norm": 2.3746797901940226, "learning_rate": 1.9986345953348747e-07, "loss": 2.3904, "step": 27 }, { "epoch": 0.2994652406417112, "grad_norm": 2.5243054013882182, "learning_rate": 1.9983144052327829e-07, "loss": 2.272, "step": 28 }, { "epoch": 0.31016042780748665, "grad_norm": 2.6214531167132975, "learning_rate": 1.9979605506954883e-07, "loss": 2.3421, "step": 29 }, { "epoch": 0.32085561497326204, "grad_norm": 2.319467451607511, "learning_rate": 1.9975730436554175e-07, "loss": 2.2616, "step": 30 }, { "epoch": 0.3315508021390374, "grad_norm": 2.3011762850274966, "learning_rate": 1.9971518971798015e-07, "loss": 2.281, "step": 31 }, { "epoch": 0.3422459893048128, "grad_norm": 2.3833956949307824, "learning_rate": 1.9966971254702373e-07, "loss": 2.241, "step": 32 }, { "epoch": 0.35294117647058826, "grad_norm": 2.3979566222135222, "learning_rate": 1.9962087438622066e-07, "loss": 2.2686, "step": 33 }, { "epoch": 0.36363636363636365, "grad_norm": 2.367666395240584, "learning_rate": 1.9956867688245604e-07, "loss": 2.3193, "step": 34 }, { "epoch": 0.37433155080213903, "grad_norm": 2.3481007842322574, "learning_rate": 1.995131217958963e-07, "loss": 2.2987, "step": 35 }, { "epoch": 0.3850267379679144, "grad_norm": 2.325059035492084, "learning_rate": 1.9945421099992978e-07, "loss": 2.2611, "step": 36 }, { "epoch": 0.39572192513368987, "grad_norm": 2.4243466628904278, "learning_rate": 1.993919464811037e-07, "loss": 2.3346, "step": 37 }, { "epoch": 0.40641711229946526, "grad_norm": 2.388588771779077, "learning_rate": 1.9932633033905705e-07, "loss": 2.3664, "step": 38 }, { "epoch": 0.41711229946524064, "grad_norm": 2.4329366354312043, "learning_rate": 1.992573647864499e-07, "loss": 2.3358, "step": 39 }, { "epoch": 0.42780748663101603, "grad_norm": 2.3828846635370344, "learning_rate": 1.991850521488885e-07, "loss": 2.3046, "step": 40 }, { "epoch": 0.4385026737967914, "grad_norm": 2.422466010996084, "learning_rate": 1.991093948648474e-07, "loss": 2.2447, "step": 41 }, { "epoch": 0.44919786096256686, "grad_norm": 2.4257863974102993, "learning_rate": 1.9903039548558666e-07, "loss": 2.2242, "step": 42 }, { "epoch": 0.45989304812834225, "grad_norm": 2.459816598894942, "learning_rate": 1.9894805667506613e-07, "loss": 2.2538, "step": 43 }, { "epoch": 0.47058823529411764, "grad_norm": 2.285208230070572, "learning_rate": 1.988623812098555e-07, "loss": 2.3077, "step": 44 }, { "epoch": 0.48128342245989303, "grad_norm": 2.2685953405799384, "learning_rate": 1.9877337197904078e-07, "loss": 2.3158, "step": 45 }, { "epoch": 0.4919786096256685, "grad_norm": 2.416761236235903, "learning_rate": 1.9868103198412675e-07, "loss": 2.333, "step": 46 }, { "epoch": 0.5026737967914439, "grad_norm": 2.350542228223794, "learning_rate": 1.9858536433893584e-07, "loss": 2.2053, "step": 47 }, { "epoch": 0.5133689839572193, "grad_norm": 2.1785848820206373, "learning_rate": 1.9848637226950311e-07, "loss": 2.3158, "step": 48 }, { "epoch": 0.5240641711229946, "grad_norm": 2.185405529693909, "learning_rate": 1.9838405911396734e-07, "loss": 2.1461, "step": 49 }, { "epoch": 0.5347593582887701, "grad_norm": 2.215186649422488, "learning_rate": 1.9827842832245873e-07, "loss": 2.185, "step": 50 }, { "epoch": 0.5454545454545454, "grad_norm": 2.3270896330565054, "learning_rate": 1.9816948345698225e-07, "loss": 2.2417, "step": 51 }, { "epoch": 0.5561497326203209, "grad_norm": 2.1581766314900674, "learning_rate": 1.9805722819129778e-07, "loss": 2.1341, "step": 52 }, { "epoch": 0.5668449197860963, "grad_norm": 2.220228046154024, "learning_rate": 1.9794166631079605e-07, "loss": 2.2098, "step": 53 }, { "epoch": 0.5775401069518716, "grad_norm": 2.2382871743475303, "learning_rate": 1.978228017123711e-07, "loss": 2.2397, "step": 54 }, { "epoch": 0.5882352941176471, "grad_norm": 2.498458949528395, "learning_rate": 1.977006384042888e-07, "loss": 2.2127, "step": 55 }, { "epoch": 0.5989304812834224, "grad_norm": 2.420036444152971, "learning_rate": 1.9757518050605172e-07, "loss": 2.1451, "step": 56 }, { "epoch": 0.6096256684491979, "grad_norm": 2.2323849357463463, "learning_rate": 1.974464322482602e-07, "loss": 2.2212, "step": 57 }, { "epoch": 0.6203208556149733, "grad_norm": 2.2981710800271244, "learning_rate": 1.973143979724698e-07, "loss": 2.1737, "step": 58 }, { "epoch": 0.6310160427807486, "grad_norm": 2.28928522022645, "learning_rate": 1.971790821310447e-07, "loss": 2.2898, "step": 59 }, { "epoch": 0.6417112299465241, "grad_norm": 2.283401556024132, "learning_rate": 1.9704048928700763e-07, "loss": 2.2316, "step": 60 }, { "epoch": 0.6524064171122995, "grad_norm": 2.1214148922245744, "learning_rate": 1.9689862411388613e-07, "loss": 2.191, "step": 61 }, { "epoch": 0.6631016042780749, "grad_norm": 2.2747670704212473, "learning_rate": 1.9675349139555483e-07, "loss": 2.2126, "step": 62 }, { "epoch": 0.6737967914438503, "grad_norm": 2.261194454425025, "learning_rate": 1.9660509602607401e-07, "loss": 2.1511, "step": 63 }, { "epoch": 0.6844919786096256, "grad_norm": 2.092146529232135, "learning_rate": 1.9645344300952495e-07, "loss": 2.191, "step": 64 }, { "epoch": 0.6951871657754011, "grad_norm": 2.2009619848808186, "learning_rate": 1.9629853745984076e-07, "loss": 2.3149, "step": 65 }, { "epoch": 0.7058823529411765, "grad_norm": 2.1014895400052884, "learning_rate": 1.9614038460063416e-07, "loss": 2.2803, "step": 66 }, { "epoch": 0.7165775401069518, "grad_norm": 2.1767633273728775, "learning_rate": 1.9597898976502134e-07, "loss": 2.1756, "step": 67 }, { "epoch": 0.7272727272727273, "grad_norm": 2.218257357882039, "learning_rate": 1.95814358395442e-07, "loss": 2.3272, "step": 68 }, { "epoch": 0.7379679144385026, "grad_norm": 2.1697839813140205, "learning_rate": 1.9564649604347595e-07, "loss": 2.1906, "step": 69 }, { "epoch": 0.7486631016042781, "grad_norm": 2.230675420734239, "learning_rate": 1.9547540836965584e-07, "loss": 2.3508, "step": 70 }, { "epoch": 0.7593582887700535, "grad_norm": 2.1382651593643303, "learning_rate": 1.9530110114327624e-07, "loss": 2.2348, "step": 71 }, { "epoch": 0.7700534759358288, "grad_norm": 2.3279342085333576, "learning_rate": 1.951235802421992e-07, "loss": 2.1846, "step": 72 }, { "epoch": 0.7807486631016043, "grad_norm": 2.2619881853889927, "learning_rate": 1.949428516526559e-07, "loss": 2.1547, "step": 73 }, { "epoch": 0.7914438502673797, "grad_norm": 2.2132561395006154, "learning_rate": 1.9475892146904495e-07, "loss": 2.2588, "step": 74 }, { "epoch": 0.8021390374331551, "grad_norm": 2.2388056145192485, "learning_rate": 1.945717958937268e-07, "loss": 2.2958, "step": 75 }, { "epoch": 0.8128342245989305, "grad_norm": 2.063501174144287, "learning_rate": 1.943814812368145e-07, "loss": 2.2351, "step": 76 }, { "epoch": 0.8235294117647058, "grad_norm": 2.13517450471024, "learning_rate": 1.9418798391596108e-07, "loss": 2.1907, "step": 77 }, { "epoch": 0.8342245989304813, "grad_norm": 2.197441953376566, "learning_rate": 1.9399131045614298e-07, "loss": 2.2082, "step": 78 }, { "epoch": 0.8449197860962567, "grad_norm": 2.3801164641572576, "learning_rate": 1.937914674894402e-07, "loss": 2.2278, "step": 79 }, { "epoch": 0.8556149732620321, "grad_norm": 2.1856307034100864, "learning_rate": 1.9358846175481248e-07, "loss": 2.2563, "step": 80 }, { "epoch": 0.8663101604278075, "grad_norm": 2.1457251433851927, "learning_rate": 1.933823000978721e-07, "loss": 2.1317, "step": 81 }, { "epoch": 0.8770053475935828, "grad_norm": 2.2535981122464044, "learning_rate": 1.9317298947065316e-07, "loss": 2.1908, "step": 82 }, { "epoch": 0.8877005347593583, "grad_norm": 2.192723556995563, "learning_rate": 1.9296053693137703e-07, "loss": 2.2636, "step": 83 }, { "epoch": 0.8983957219251337, "grad_norm": 2.1836725834736046, "learning_rate": 1.927449496442143e-07, "loss": 2.2806, "step": 84 }, { "epoch": 0.9090909090909091, "grad_norm": 2.2458647554312337, "learning_rate": 1.9252623487904332e-07, "loss": 2.2044, "step": 85 }, { "epoch": 0.9197860962566845, "grad_norm": 2.1722372866447435, "learning_rate": 1.9230440001120494e-07, "loss": 2.2624, "step": 86 }, { "epoch": 0.93048128342246, "grad_norm": 2.2594112154874257, "learning_rate": 1.920794525212539e-07, "loss": 2.2259, "step": 87 }, { "epoch": 0.9411764705882353, "grad_norm": 2.235049013487852, "learning_rate": 1.918513999947065e-07, "loss": 2.1185, "step": 88 }, { "epoch": 0.9518716577540107, "grad_norm": 1.9873439930063803, "learning_rate": 1.9162025012178483e-07, "loss": 2.1832, "step": 89 }, { "epoch": 0.9625668449197861, "grad_norm": 2.05421858030192, "learning_rate": 1.913860106971575e-07, "loss": 2.13, "step": 90 }, { "epoch": 0.9732620320855615, "grad_norm": 2.168494886444294, "learning_rate": 1.9114868961967665e-07, "loss": 2.2074, "step": 91 }, { "epoch": 0.983957219251337, "grad_norm": 1.8342583305340783, "learning_rate": 1.909082948921118e-07, "loss": 1.9684, "step": 92 }, { "epoch": 0.9946524064171123, "grad_norm": 1.8252496033715673, "learning_rate": 1.9066483462087976e-07, "loss": 2.1233, "step": 93 }, { "epoch": 1.0, "grad_norm": 1.8252496033715673, "learning_rate": 1.9041831701577148e-07, "loss": 1.1198, "step": 94 }, { "epoch": 1.0106951871657754, "grad_norm": 1.8691680981114158, "learning_rate": 1.9016875038967503e-07, "loss": 2.1201, "step": 95 }, { "epoch": 1.0213903743315509, "grad_norm": 1.8502258064525274, "learning_rate": 1.899161431582954e-07, "loss": 2.0154, "step": 96 }, { "epoch": 1.032085561497326, "grad_norm": 1.7747332221223255, "learning_rate": 1.896605038398707e-07, "loss": 2.1209, "step": 97 }, { "epoch": 1.0427807486631016, "grad_norm": 1.7390901058397992, "learning_rate": 1.8940184105488477e-07, "loss": 2.1144, "step": 98 }, { "epoch": 1.053475935828877, "grad_norm": 1.724298907654552, "learning_rate": 1.8914016352577672e-07, "loss": 2.1626, "step": 99 }, { "epoch": 1.0641711229946524, "grad_norm": 1.7419133703338525, "learning_rate": 1.8887548007664663e-07, "loss": 2.0879, "step": 100 }, { "epoch": 1.0748663101604279, "grad_norm": 1.768435724184072, "learning_rate": 1.88607799632958e-07, "loss": 2.1311, "step": 101 }, { "epoch": 1.085561497326203, "grad_norm": 1.7137005612293372, "learning_rate": 1.883371312212369e-07, "loss": 2.0317, "step": 102 }, { "epoch": 1.0962566844919786, "grad_norm": 1.6405470049354822, "learning_rate": 1.8806348396876742e-07, "loss": 2.107, "step": 103 }, { "epoch": 1.106951871657754, "grad_norm": 1.7493534833078186, "learning_rate": 1.8778686710328395e-07, "loss": 2.1506, "step": 104 }, { "epoch": 1.1176470588235294, "grad_norm": 1.703455856407852, "learning_rate": 1.875072899526601e-07, "loss": 2.0856, "step": 105 }, { "epoch": 1.1283422459893049, "grad_norm": 1.7521981718015323, "learning_rate": 1.8722476194459395e-07, "loss": 2.1015, "step": 106 }, { "epoch": 1.1390374331550803, "grad_norm": 1.8175328159455935, "learning_rate": 1.869392926062904e-07, "loss": 2.0522, "step": 107 }, { "epoch": 1.1497326203208555, "grad_norm": 1.7494301211101768, "learning_rate": 1.8665089156413966e-07, "loss": 2.1142, "step": 108 }, { "epoch": 1.160427807486631, "grad_norm": 1.6732447167879811, "learning_rate": 1.8635956854339274e-07, "loss": 2.1077, "step": 109 }, { "epoch": 1.1711229946524064, "grad_norm": 1.8385904832517168, "learning_rate": 1.8606533336783357e-07, "loss": 2.2026, "step": 110 }, { "epoch": 1.1818181818181819, "grad_norm": 1.8110603990066274, "learning_rate": 1.857681959594475e-07, "loss": 2.032, "step": 111 }, { "epoch": 1.192513368983957, "grad_norm": 1.7695603471141617, "learning_rate": 1.8546816633808703e-07, "loss": 2.2146, "step": 112 }, { "epoch": 1.2032085561497325, "grad_norm": 1.8053785433240395, "learning_rate": 1.8516525462113376e-07, "loss": 2.1934, "step": 113 }, { "epoch": 1.213903743315508, "grad_norm": 1.6744855052025045, "learning_rate": 1.848594710231571e-07, "loss": 2.1834, "step": 114 }, { "epoch": 1.2245989304812834, "grad_norm": 1.7932054193144469, "learning_rate": 1.8455082585557006e-07, "loss": 2.0415, "step": 115 }, { "epoch": 1.2352941176470589, "grad_norm": 1.6428322261649346, "learning_rate": 1.8423932952628144e-07, "loss": 2.067, "step": 116 }, { "epoch": 1.2459893048128343, "grad_norm": 1.7382000300083023, "learning_rate": 1.8392499253934473e-07, "loss": 2.1724, "step": 117 }, { "epoch": 1.2566844919786098, "grad_norm": 1.8709019559433993, "learning_rate": 1.8360782549460418e-07, "loss": 2.0914, "step": 118 }, { "epoch": 1.267379679144385, "grad_norm": 1.6724119658449972, "learning_rate": 1.8328783908733708e-07, "loss": 2.1186, "step": 119 }, { "epoch": 1.2780748663101604, "grad_norm": 1.7835125551171003, "learning_rate": 1.8296504410789328e-07, "loss": 2.0482, "step": 120 }, { "epoch": 1.2887700534759359, "grad_norm": 1.6483657805365755, "learning_rate": 1.8263945144133124e-07, "loss": 2.0774, "step": 121 }, { "epoch": 1.299465240641711, "grad_norm": 1.6445372122410302, "learning_rate": 1.8231107206705102e-07, "loss": 2.0573, "step": 122 }, { "epoch": 1.3101604278074865, "grad_norm": 1.6844433896997877, "learning_rate": 1.8197991705842392e-07, "loss": 2.0911, "step": 123 }, { "epoch": 1.320855614973262, "grad_norm": 1.7477646676053702, "learning_rate": 1.8164599758241938e-07, "loss": 2.0409, "step": 124 }, { "epoch": 1.3315508021390374, "grad_norm": 1.8128634022890735, "learning_rate": 1.81309324899228e-07, "loss": 2.201, "step": 125 }, { "epoch": 1.3422459893048129, "grad_norm": 1.7216333338346883, "learning_rate": 1.8096991036188215e-07, "loss": 2.1659, "step": 126 }, { "epoch": 1.3529411764705883, "grad_norm": 1.7879340121787493, "learning_rate": 1.80627765415873e-07, "loss": 2.0892, "step": 127 }, { "epoch": 1.3636363636363638, "grad_norm": 1.6541027631644494, "learning_rate": 1.8028290159876453e-07, "loss": 1.9607, "step": 128 }, { "epoch": 1.374331550802139, "grad_norm": 1.679293552656214, "learning_rate": 1.7993533053980458e-07, "loss": 2.1868, "step": 129 }, { "epoch": 1.3850267379679144, "grad_norm": 1.8579543817143627, "learning_rate": 1.7958506395953265e-07, "loss": 2.1343, "step": 130 }, { "epoch": 1.3957219251336899, "grad_norm": 1.8636539235310083, "learning_rate": 1.7923211366938463e-07, "loss": 2.0674, "step": 131 }, { "epoch": 1.4064171122994653, "grad_norm": 1.7334184277035045, "learning_rate": 1.7887649157129445e-07, "loss": 2.1037, "step": 132 }, { "epoch": 1.4171122994652405, "grad_norm": 1.822849013764906, "learning_rate": 1.7851820965729302e-07, "loss": 2.0924, "step": 133 }, { "epoch": 1.427807486631016, "grad_norm": 1.7105008930519692, "learning_rate": 1.781572800091034e-07, "loss": 2.2073, "step": 134 }, { "epoch": 1.4385026737967914, "grad_norm": 1.749124781449127, "learning_rate": 1.777937147977338e-07, "loss": 2.159, "step": 135 }, { "epoch": 1.4491978609625669, "grad_norm": 1.817598510475392, "learning_rate": 1.7742752628306686e-07, "loss": 2.0806, "step": 136 }, { "epoch": 1.4598930481283423, "grad_norm": 1.6898545599804242, "learning_rate": 1.7705872681344646e-07, "loss": 2.0621, "step": 137 }, { "epoch": 1.4705882352941178, "grad_norm": 1.708524779494462, "learning_rate": 1.7668732882526113e-07, "loss": 2.0932, "step": 138 }, { "epoch": 1.481283422459893, "grad_norm": 1.6326058692899386, "learning_rate": 1.7631334484252478e-07, "loss": 1.9894, "step": 139 }, { "epoch": 1.4919786096256684, "grad_norm": 1.7668104108682112, "learning_rate": 1.759367874764544e-07, "loss": 2.03, "step": 140 }, { "epoch": 1.5026737967914439, "grad_norm": 1.742459692174338, "learning_rate": 1.7555766942504469e-07, "loss": 2.1366, "step": 141 }, { "epoch": 1.5133689839572193, "grad_norm": 1.626815988438644, "learning_rate": 1.7517600347263995e-07, "loss": 2.0893, "step": 142 }, { "epoch": 1.5240641711229945, "grad_norm": 1.6471938527920325, "learning_rate": 1.7479180248950293e-07, "loss": 2.1291, "step": 143 }, { "epoch": 1.53475935828877, "grad_norm": 1.750049700195507, "learning_rate": 1.744050794313809e-07, "loss": 2.137, "step": 144 }, { "epoch": 1.5454545454545454, "grad_norm": 1.7192190702489798, "learning_rate": 1.740158473390687e-07, "loss": 2.0149, "step": 145 }, { "epoch": 1.5561497326203209, "grad_norm": 1.6278331728210962, "learning_rate": 1.73624119337969e-07, "loss": 2.1269, "step": 146 }, { "epoch": 1.5668449197860963, "grad_norm": 1.7717325953894878, "learning_rate": 1.7322990863764964e-07, "loss": 2.059, "step": 147 }, { "epoch": 1.5775401069518717, "grad_norm": 1.647166848416035, "learning_rate": 1.728332285313983e-07, "loss": 2.0929, "step": 148 }, { "epoch": 1.5882352941176472, "grad_norm": 1.7617193268211082, "learning_rate": 1.724340923957742e-07, "loss": 2.1256, "step": 149 }, { "epoch": 1.5989304812834224, "grad_norm": 1.8528794452609483, "learning_rate": 1.72032513690157e-07, "loss": 1.9989, "step": 150 }, { "epoch": 1.6096256684491979, "grad_norm": 1.739301602599776, "learning_rate": 1.7162850595629282e-07, "loss": 2.0544, "step": 151 }, { "epoch": 1.6203208556149733, "grad_norm": 1.7484020503985405, "learning_rate": 1.7122208281783784e-07, "loss": 2.083, "step": 152 }, { "epoch": 1.6310160427807485, "grad_norm": 1.7558204718386419, "learning_rate": 1.708132579798988e-07, "loss": 2.0867, "step": 153 }, { "epoch": 1.641711229946524, "grad_norm": 1.823415289374815, "learning_rate": 1.7040204522857065e-07, "loss": 1.984, "step": 154 }, { "epoch": 1.6524064171122994, "grad_norm": 1.6620732687020978, "learning_rate": 1.699884584304719e-07, "loss": 2.0342, "step": 155 }, { "epoch": 1.6631016042780749, "grad_norm": 1.7491812472955983, "learning_rate": 1.6957251153227704e-07, "loss": 2.0562, "step": 156 }, { "epoch": 1.6737967914438503, "grad_norm": 1.790102048039344, "learning_rate": 1.6915421856024602e-07, "loss": 2.0468, "step": 157 }, { "epoch": 1.6844919786096257, "grad_norm": 1.8588607707775786, "learning_rate": 1.6873359361975142e-07, "loss": 2.073, "step": 158 }, { "epoch": 1.6951871657754012, "grad_norm": 1.9099382297562897, "learning_rate": 1.6831065089480278e-07, "loss": 2.1011, "step": 159 }, { "epoch": 1.7058823529411766, "grad_norm": 1.9156571559028355, "learning_rate": 1.6788540464756834e-07, "loss": 2.0902, "step": 160 }, { "epoch": 1.7165775401069518, "grad_norm": 1.7487683691532725, "learning_rate": 1.6745786921789398e-07, "loss": 2.0655, "step": 161 }, { "epoch": 1.7272727272727273, "grad_norm": 1.798922579729806, "learning_rate": 1.6702805902281974e-07, "loss": 2.0819, "step": 162 }, { "epoch": 1.7379679144385025, "grad_norm": 1.7516100546591455, "learning_rate": 1.6659598855609365e-07, "loss": 2.0015, "step": 163 }, { "epoch": 1.748663101604278, "grad_norm": 1.7598556009362833, "learning_rate": 1.661616723876831e-07, "loss": 1.9692, "step": 164 }, { "epoch": 1.7593582887700534, "grad_norm": 1.8518167267401615, "learning_rate": 1.6572512516328316e-07, "loss": 2.0501, "step": 165 }, { "epoch": 1.7700534759358288, "grad_norm": 1.9680098122752612, "learning_rate": 1.6528636160382324e-07, "loss": 2.068, "step": 166 }, { "epoch": 1.7807486631016043, "grad_norm": 1.7435746915577544, "learning_rate": 1.6484539650497015e-07, "loss": 2.0655, "step": 167 }, { "epoch": 1.7914438502673797, "grad_norm": 2.0163269938254897, "learning_rate": 1.644022447366296e-07, "loss": 2.1151, "step": 168 }, { "epoch": 1.8021390374331552, "grad_norm": 2.0397047851085475, "learning_rate": 1.6395692124244444e-07, "loss": 1.9838, "step": 169 }, { "epoch": 1.8128342245989306, "grad_norm": 1.8791425708108331, "learning_rate": 1.6350944103929102e-07, "loss": 2.0208, "step": 170 }, { "epoch": 1.8235294117647058, "grad_norm": 1.8524792892955046, "learning_rate": 1.6305981921677255e-07, "loss": 2.0714, "step": 171 }, { "epoch": 1.8342245989304813, "grad_norm": 2.1434113891517517, "learning_rate": 1.6260807093671043e-07, "loss": 1.9286, "step": 172 }, { "epoch": 1.8449197860962567, "grad_norm": 1.8668197245162237, "learning_rate": 1.6215421143263294e-07, "loss": 2.0335, "step": 173 }, { "epoch": 1.855614973262032, "grad_norm": 2.2307700413988756, "learning_rate": 1.616982560092615e-07, "loss": 2.0027, "step": 174 }, { "epoch": 1.8663101604278074, "grad_norm": 1.7759871927923943, "learning_rate": 1.6124022004199458e-07, "loss": 1.9088, "step": 175 }, { "epoch": 1.8770053475935828, "grad_norm": 2.002834449205516, "learning_rate": 1.6078011897638932e-07, "loss": 1.9709, "step": 176 }, { "epoch": 1.8877005347593583, "grad_norm": 1.9813445649823422, "learning_rate": 1.603179683276405e-07, "loss": 2.0326, "step": 177 }, { "epoch": 1.8983957219251337, "grad_norm": 2.1310400862958674, "learning_rate": 1.5985378368005758e-07, "loss": 2.1098, "step": 178 }, { "epoch": 1.9090909090909092, "grad_norm": 2.1055111936890896, "learning_rate": 1.5938758068653898e-07, "loss": 1.9046, "step": 179 }, { "epoch": 1.9197860962566846, "grad_norm": 2.001761438448876, "learning_rate": 1.5891937506804428e-07, "loss": 2.0031, "step": 180 }, { "epoch": 1.93048128342246, "grad_norm": 1.9854514227307951, "learning_rate": 1.5844918261306423e-07, "loss": 1.8822, "step": 181 }, { "epoch": 1.9411764705882353, "grad_norm": 2.0138722276092493, "learning_rate": 1.579770191770882e-07, "loss": 1.991, "step": 182 }, { "epoch": 1.9518716577540107, "grad_norm": 1.9822431627418198, "learning_rate": 1.5750290068206956e-07, "loss": 1.9941, "step": 183 }, { "epoch": 1.962566844919786, "grad_norm": 2.084618240884537, "learning_rate": 1.5702684311588867e-07, "loss": 1.9653, "step": 184 }, { "epoch": 1.9732620320855614, "grad_norm": 1.7089614667973392, "learning_rate": 1.5654886253181401e-07, "loss": 1.8998, "step": 185 }, { "epoch": 1.9839572192513368, "grad_norm": 2.1419061592120774, "learning_rate": 1.5606897504796058e-07, "loss": 1.9791, "step": 186 }, { "epoch": 1.9946524064171123, "grad_norm": 1.8168421557865153, "learning_rate": 1.555871968467464e-07, "loss": 1.8058, "step": 187 }, { "epoch": 2.0, "grad_norm": 1.91734849044011, "learning_rate": 1.5510354417434712e-07, "loss": 1.0229, "step": 188 }, { "epoch": 2.0106951871657754, "grad_norm": 1.8776996226642948, "learning_rate": 1.5461803334014768e-07, "loss": 1.8689, "step": 189 }, { "epoch": 2.021390374331551, "grad_norm": 2.0202302250974977, "learning_rate": 1.5413068071619277e-07, "loss": 1.9248, "step": 190 }, { "epoch": 2.0320855614973263, "grad_norm": 1.9107131755138838, "learning_rate": 1.5364150273663458e-07, "loss": 1.8459, "step": 191 }, { "epoch": 2.0427807486631018, "grad_norm": 1.8750367131155108, "learning_rate": 1.5315051589717852e-07, "loss": 1.9742, "step": 192 }, { "epoch": 2.053475935828877, "grad_norm": 2.0882288691076636, "learning_rate": 1.5265773675452717e-07, "loss": 1.9149, "step": 193 }, { "epoch": 2.064171122994652, "grad_norm": 1.9011219759565725, "learning_rate": 1.521631819258218e-07, "loss": 1.9256, "step": 194 }, { "epoch": 2.0748663101604277, "grad_norm": 1.9476978857090947, "learning_rate": 1.5166686808808206e-07, "loss": 1.9242, "step": 195 }, { "epoch": 2.085561497326203, "grad_norm": 1.9949087001080084, "learning_rate": 1.5116881197764368e-07, "loss": 1.8977, "step": 196 }, { "epoch": 2.0962566844919786, "grad_norm": 1.8896603268772247, "learning_rate": 1.5066903038959406e-07, "loss": 1.8176, "step": 197 }, { "epoch": 2.106951871657754, "grad_norm": 1.9319482581859762, "learning_rate": 1.5016754017720585e-07, "loss": 1.9653, "step": 198 }, { "epoch": 2.1176470588235294, "grad_norm": 1.7569523930673137, "learning_rate": 1.496643582513687e-07, "loss": 1.8301, "step": 199 }, { "epoch": 2.128342245989305, "grad_norm": 1.83472307789282, "learning_rate": 1.4915950158001906e-07, "loss": 1.9013, "step": 200 }, { "epoch": 2.1390374331550803, "grad_norm": 1.8411931902154157, "learning_rate": 1.4865298718756786e-07, "loss": 1.8867, "step": 201 }, { "epoch": 2.1497326203208558, "grad_norm": 2.007707841426601, "learning_rate": 1.4814483215432652e-07, "loss": 1.9634, "step": 202 }, { "epoch": 2.160427807486631, "grad_norm": 1.950219924953972, "learning_rate": 1.4763505361593093e-07, "loss": 1.8812, "step": 203 }, { "epoch": 2.171122994652406, "grad_norm": 1.997822009510831, "learning_rate": 1.4712366876276376e-07, "loss": 1.938, "step": 204 }, { "epoch": 2.1818181818181817, "grad_norm": 1.7761243562967859, "learning_rate": 1.4661069483937457e-07, "loss": 1.7846, "step": 205 }, { "epoch": 2.192513368983957, "grad_norm": 1.7646030167754145, "learning_rate": 1.4609614914389835e-07, "loss": 1.8128, "step": 206 }, { "epoch": 2.2032085561497325, "grad_norm": 2.013383482731404, "learning_rate": 1.4558004902747238e-07, "loss": 1.9804, "step": 207 }, { "epoch": 2.213903743315508, "grad_norm": 1.8188349668041328, "learning_rate": 1.4506241189365093e-07, "loss": 1.9228, "step": 208 }, { "epoch": 2.2245989304812834, "grad_norm": 1.59271102081584, "learning_rate": 1.4454325519781835e-07, "loss": 1.8434, "step": 209 }, { "epoch": 2.235294117647059, "grad_norm": 1.5659479150327449, "learning_rate": 1.440225964466008e-07, "loss": 1.7293, "step": 210 }, { "epoch": 2.2459893048128343, "grad_norm": 1.9706230149639103, "learning_rate": 1.4350045319727547e-07, "loss": 1.9061, "step": 211 }, { "epoch": 2.2566844919786098, "grad_norm": 1.9538098536813404, "learning_rate": 1.4297684305717873e-07, "loss": 1.9182, "step": 212 }, { "epoch": 2.267379679144385, "grad_norm": 1.8587869543475823, "learning_rate": 1.424517836831125e-07, "loss": 1.8547, "step": 213 }, { "epoch": 2.2780748663101607, "grad_norm": 2.0045513308335, "learning_rate": 1.4192529278074862e-07, "loss": 1.9467, "step": 214 }, { "epoch": 2.2887700534759357, "grad_norm": 1.6112672188222035, "learning_rate": 1.413973881040319e-07, "loss": 1.836, "step": 215 }, { "epoch": 2.299465240641711, "grad_norm": 2.137329904566206, "learning_rate": 1.4086808745458142e-07, "loss": 1.9221, "step": 216 }, { "epoch": 2.3101604278074865, "grad_norm": 1.7750991323465606, "learning_rate": 1.4033740868109032e-07, "loss": 1.8764, "step": 217 }, { "epoch": 2.320855614973262, "grad_norm": 1.696659194863298, "learning_rate": 1.3980536967872376e-07, "loss": 1.7564, "step": 218 }, { "epoch": 2.3315508021390374, "grad_norm": 1.8203438652025503, "learning_rate": 1.3927198838851552e-07, "loss": 1.8439, "step": 219 }, { "epoch": 2.342245989304813, "grad_norm": 1.9800710567556972, "learning_rate": 1.3873728279676315e-07, "loss": 1.8974, "step": 220 }, { "epoch": 2.3529411764705883, "grad_norm": 1.6338923753463463, "learning_rate": 1.3820127093442126e-07, "loss": 1.7486, "step": 221 }, { "epoch": 2.3636363636363638, "grad_norm": 1.722632870308358, "learning_rate": 1.376639708764936e-07, "loss": 1.8783, "step": 222 }, { "epoch": 2.374331550802139, "grad_norm": 1.9561833269011113, "learning_rate": 1.371254007414235e-07, "loss": 1.9165, "step": 223 }, { "epoch": 2.385026737967914, "grad_norm": 1.6064112149701273, "learning_rate": 1.365855786904829e-07, "loss": 1.8379, "step": 224 }, { "epoch": 2.3957219251336896, "grad_norm": 1.4931472703360875, "learning_rate": 1.3604452292716003e-07, "loss": 1.7287, "step": 225 }, { "epoch": 2.406417112299465, "grad_norm": 1.8268266382628995, "learning_rate": 1.355022516965453e-07, "loss": 1.9423, "step": 226 }, { "epoch": 2.4171122994652405, "grad_norm": 1.6679450062171188, "learning_rate": 1.3495878328471638e-07, "loss": 1.7914, "step": 227 }, { "epoch": 2.427807486631016, "grad_norm": 1.7955001612015629, "learning_rate": 1.344141360181214e-07, "loss": 1.8651, "step": 228 }, { "epoch": 2.4385026737967914, "grad_norm": 1.5079853464695963, "learning_rate": 1.3386832826296092e-07, "loss": 1.747, "step": 229 }, { "epoch": 2.449197860962567, "grad_norm": 1.774035108855846, "learning_rate": 1.3332137842456865e-07, "loss": 1.8224, "step": 230 }, { "epoch": 2.4598930481283423, "grad_norm": 1.859169247420952, "learning_rate": 1.3277330494679091e-07, "loss": 1.7962, "step": 231 }, { "epoch": 2.4705882352941178, "grad_norm": 1.7252805384966143, "learning_rate": 1.3222412631136443e-07, "loss": 1.843, "step": 232 }, { "epoch": 2.481283422459893, "grad_norm": 1.6684506315787555, "learning_rate": 1.3167386103729337e-07, "loss": 1.8126, "step": 233 }, { "epoch": 2.4919786096256686, "grad_norm": 1.6500782775923557, "learning_rate": 1.3112252768022464e-07, "loss": 1.7956, "step": 234 }, { "epoch": 2.502673796791444, "grad_norm": 1.6682685408009557, "learning_rate": 1.305701448318224e-07, "loss": 1.745, "step": 235 }, { "epoch": 2.5133689839572195, "grad_norm": 1.5946878676440053, "learning_rate": 1.300167311191409e-07, "loss": 1.7899, "step": 236 }, { "epoch": 2.5240641711229945, "grad_norm": 1.560578079266366, "learning_rate": 1.2946230520399647e-07, "loss": 1.888, "step": 237 }, { "epoch": 2.53475935828877, "grad_norm": 1.4760549883449223, "learning_rate": 1.2890688578233817e-07, "loss": 1.7398, "step": 238 }, { "epoch": 2.5454545454545454, "grad_norm": 1.498793769765859, "learning_rate": 1.2835049158361744e-07, "loss": 1.8217, "step": 239 }, { "epoch": 2.556149732620321, "grad_norm": 1.4568509017024076, "learning_rate": 1.2779314137015636e-07, "loss": 1.8265, "step": 240 }, { "epoch": 2.5668449197860963, "grad_norm": 1.6772171864469765, "learning_rate": 1.272348539365151e-07, "loss": 1.7811, "step": 241 }, { "epoch": 2.5775401069518717, "grad_norm": 1.8200935730938934, "learning_rate": 1.2667564810885806e-07, "loss": 1.8535, "step": 242 }, { "epoch": 2.588235294117647, "grad_norm": 1.4942945455847536, "learning_rate": 1.2611554274431919e-07, "loss": 1.7958, "step": 243 }, { "epoch": 2.598930481283422, "grad_norm": 1.677515885483504, "learning_rate": 1.255545567303657e-07, "loss": 1.8054, "step": 244 }, { "epoch": 2.6096256684491976, "grad_norm": 1.5019371775876145, "learning_rate": 1.2499270898416166e-07, "loss": 1.8354, "step": 245 }, { "epoch": 2.620320855614973, "grad_norm": 1.5035984972716776, "learning_rate": 1.2443001845192974e-07, "loss": 1.7432, "step": 246 }, { "epoch": 2.6310160427807485, "grad_norm": 1.4448270049593817, "learning_rate": 1.2386650410831257e-07, "loss": 1.7656, "step": 247 }, { "epoch": 2.641711229946524, "grad_norm": 1.8821467363740914, "learning_rate": 1.2330218495573245e-07, "loss": 1.7837, "step": 248 }, { "epoch": 2.6524064171122994, "grad_norm": 1.6140609004506175, "learning_rate": 1.227370800237512e-07, "loss": 1.8074, "step": 249 }, { "epoch": 2.663101604278075, "grad_norm": 1.5778751173081107, "learning_rate": 1.2217120836842794e-07, "loss": 1.8207, "step": 250 }, { "epoch": 2.6737967914438503, "grad_norm": 1.5462496099145762, "learning_rate": 1.2160458907167667e-07, "loss": 1.8321, "step": 251 }, { "epoch": 2.6844919786096257, "grad_norm": 1.5483799664470452, "learning_rate": 1.2103724124062292e-07, "loss": 1.7776, "step": 252 }, { "epoch": 2.695187165775401, "grad_norm": 1.4546045902761022, "learning_rate": 1.2046918400695927e-07, "loss": 1.7895, "step": 253 }, { "epoch": 2.7058823529411766, "grad_norm": 1.5661818236510652, "learning_rate": 1.1990043652630022e-07, "loss": 1.7656, "step": 254 }, { "epoch": 2.716577540106952, "grad_norm": 1.5592204536692256, "learning_rate": 1.1933101797753635e-07, "loss": 1.7647, "step": 255 }, { "epoch": 2.7272727272727275, "grad_norm": 1.5020128691019576, "learning_rate": 1.1876094756218745e-07, "loss": 1.8085, "step": 256 }, { "epoch": 2.7379679144385025, "grad_norm": 1.5418961057657317, "learning_rate": 1.1819024450375516e-07, "loss": 1.767, "step": 257 }, { "epoch": 2.748663101604278, "grad_norm": 1.6184096119952334, "learning_rate": 1.1761892804707451e-07, "loss": 1.7481, "step": 258 }, { "epoch": 2.7593582887700534, "grad_norm": 1.637911037192594, "learning_rate": 1.1704701745766532e-07, "loss": 1.8495, "step": 259 }, { "epoch": 2.770053475935829, "grad_norm": 1.4422095802965669, "learning_rate": 1.1647453202108208e-07, "loss": 1.7643, "step": 260 }, { "epoch": 2.7807486631016043, "grad_norm": 1.48789463277655, "learning_rate": 1.1590149104226408e-07, "loss": 1.6989, "step": 261 }, { "epoch": 2.7914438502673797, "grad_norm": 1.5323569508335757, "learning_rate": 1.1532791384488403e-07, "loss": 1.8489, "step": 262 }, { "epoch": 2.802139037433155, "grad_norm": 1.450131905952347, "learning_rate": 1.1475381977069671e-07, "loss": 1.7982, "step": 263 }, { "epoch": 2.8128342245989306, "grad_norm": 1.660853120722252, "learning_rate": 1.1417922817888666e-07, "loss": 1.8218, "step": 264 }, { "epoch": 2.8235294117647056, "grad_norm": 1.3859692711394558, "learning_rate": 1.1360415844541522e-07, "loss": 1.7648, "step": 265 }, { "epoch": 2.834224598930481, "grad_norm": 1.4948084649411704, "learning_rate": 1.1302862996236744e-07, "loss": 1.7943, "step": 266 }, { "epoch": 2.8449197860962565, "grad_norm": 1.5645545901296345, "learning_rate": 1.124526621372979e-07, "loss": 1.7092, "step": 267 }, { "epoch": 2.855614973262032, "grad_norm": 1.521845077946014, "learning_rate": 1.1187627439257636e-07, "loss": 1.7852, "step": 268 }, { "epoch": 2.8663101604278074, "grad_norm": 1.5209013355155485, "learning_rate": 1.1129948616473283e-07, "loss": 1.7674, "step": 269 }, { "epoch": 2.877005347593583, "grad_norm": 1.4764163127835195, "learning_rate": 1.107223169038021e-07, "loss": 1.7707, "step": 270 }, { "epoch": 2.8877005347593583, "grad_norm": 1.3568179061831744, "learning_rate": 1.1014478607266791e-07, "loss": 1.7085, "step": 271 }, { "epoch": 2.8983957219251337, "grad_norm": 1.5932701812482584, "learning_rate": 1.0956691314640655e-07, "loss": 1.8304, "step": 272 }, { "epoch": 2.909090909090909, "grad_norm": 1.5246313043450122, "learning_rate": 1.0898871761163024e-07, "loss": 1.8205, "step": 273 }, { "epoch": 2.9197860962566846, "grad_norm": 1.407517327392584, "learning_rate": 1.0841021896583002e-07, "loss": 1.7369, "step": 274 }, { "epoch": 2.93048128342246, "grad_norm": 1.4522126838670784, "learning_rate": 1.0783143671671812e-07, "loss": 1.767, "step": 275 }, { "epoch": 2.9411764705882355, "grad_norm": 1.432606400112954, "learning_rate": 1.0725239038157028e-07, "loss": 1.7491, "step": 276 }, { "epoch": 2.951871657754011, "grad_norm": 1.4873057134275895, "learning_rate": 1.0667309948656755e-07, "loss": 1.7425, "step": 277 }, { "epoch": 2.962566844919786, "grad_norm": 1.4706772073029357, "learning_rate": 1.0609358356613786e-07, "loss": 1.7667, "step": 278 }, { "epoch": 2.9732620320855614, "grad_norm": 1.2799714774907782, "learning_rate": 1.0551386216229734e-07, "loss": 1.7472, "step": 279 }, { "epoch": 2.983957219251337, "grad_norm": 1.3716417715799698, "learning_rate": 1.0493395482399112e-07, "loss": 1.7259, "step": 280 }, { "epoch": 2.9946524064171123, "grad_norm": 1.436193154440186, "learning_rate": 1.0435388110643448e-07, "loss": 1.7349, "step": 281 }, { "epoch": 3.0, "grad_norm": 1.436193154440186, "learning_rate": 1.0377366057045308e-07, "loss": 0.9011, "step": 282 }, { "epoch": 3.0106951871657754, "grad_norm": 1.3482977904549258, "learning_rate": 1.031933127818235e-07, "loss": 1.8296, "step": 283 }, { "epoch": 3.021390374331551, "grad_norm": 1.5989100956426507, "learning_rate": 1.0261285731061351e-07, "loss": 1.8202, "step": 284 }, { "epoch": 3.0320855614973263, "grad_norm": 1.4398640426605032, "learning_rate": 1.0203231373052204e-07, "loss": 1.7426, "step": 285 }, { "epoch": 3.0427807486631018, "grad_norm": 1.33703820692093, "learning_rate": 1.0145170161821915e-07, "loss": 1.7499, "step": 286 }, { "epoch": 3.053475935828877, "grad_norm": 1.5011360763108252, "learning_rate": 1.0087104055268585e-07, "loss": 1.8273, "step": 287 }, { "epoch": 3.064171122994652, "grad_norm": 1.2903788235296, "learning_rate": 1.0029035011455403e-07, "loss": 1.7058, "step": 288 }, { "epoch": 3.0748663101604277, "grad_norm": 1.3592525592535167, "learning_rate": 9.970964988544598e-08, "loss": 1.7881, "step": 289 }, { "epoch": 3.085561497326203, "grad_norm": 1.3917418493189146, "learning_rate": 9.912895944731414e-08, "loss": 1.7162, "step": 290 }, { "epoch": 3.0962566844919786, "grad_norm": 1.5583212522142622, "learning_rate": 9.85482983817809e-08, "loss": 1.8446, "step": 291 }, { "epoch": 3.106951871657754, "grad_norm": 1.5553950591003276, "learning_rate": 9.796768626947797e-08, "loss": 1.7906, "step": 292 }, { "epoch": 3.1176470588235294, "grad_norm": 1.3868064004214127, "learning_rate": 9.738714268938649e-08, "loss": 1.6799, "step": 293 }, { "epoch": 3.128342245989305, "grad_norm": 1.3715845604550376, "learning_rate": 9.68066872181765e-08, "loss": 1.7515, "step": 294 }, { "epoch": 3.1390374331550803, "grad_norm": 1.5310689280591294, "learning_rate": 9.622633942954691e-08, "loss": 1.8409, "step": 295 }, { "epoch": 3.1497326203208558, "grad_norm": 1.3855842615758482, "learning_rate": 9.564611889356554e-08, "loss": 1.7624, "step": 296 }, { "epoch": 3.160427807486631, "grad_norm": 1.3752292665194095, "learning_rate": 9.506604517600888e-08, "loss": 1.8053, "step": 297 }, { "epoch": 3.171122994652406, "grad_norm": 1.3206739769781466, "learning_rate": 9.448613783770268e-08, "loss": 1.7543, "step": 298 }, { "epoch": 3.1818181818181817, "grad_norm": 1.4055854649742987, "learning_rate": 9.390641643386213e-08, "loss": 1.6841, "step": 299 }, { "epoch": 3.192513368983957, "grad_norm": 1.2810506776795434, "learning_rate": 9.332690051343244e-08, "loss": 1.8271, "step": 300 }, { "epoch": 3.2032085561497325, "grad_norm": 1.3500223963543958, "learning_rate": 9.274760961842974e-08, "loss": 1.7186, "step": 301 }, { "epoch": 3.213903743315508, "grad_norm": 1.4938545965897436, "learning_rate": 9.216856328328188e-08, "loss": 1.701, "step": 302 }, { "epoch": 3.2245989304812834, "grad_norm": 1.239296679788258, "learning_rate": 9.158978103416997e-08, "loss": 1.748, "step": 303 }, { "epoch": 3.235294117647059, "grad_norm": 1.4849246325475256, "learning_rate": 9.101128238836973e-08, "loss": 1.8636, "step": 304 }, { "epoch": 3.2459893048128343, "grad_norm": 1.2082783737023335, "learning_rate": 9.043308685359344e-08, "loss": 1.737, "step": 305 }, { "epoch": 3.2566844919786098, "grad_norm": 1.2176724594339938, "learning_rate": 8.98552139273321e-08, "loss": 1.7951, "step": 306 }, { "epoch": 3.267379679144385, "grad_norm": 1.3010045094941596, "learning_rate": 8.92776830961979e-08, "loss": 1.6835, "step": 307 }, { "epoch": 3.2780748663101607, "grad_norm": 1.457630400842258, "learning_rate": 8.870051383526717e-08, "loss": 1.8205, "step": 308 }, { "epoch": 3.2887700534759357, "grad_norm": 1.436019893380362, "learning_rate": 8.812372560742362e-08, "loss": 1.7326, "step": 309 }, { "epoch": 3.299465240641711, "grad_norm": 1.3083741221362972, "learning_rate": 8.75473378627021e-08, "loss": 1.6797, "step": 310 }, { "epoch": 3.3101604278074865, "grad_norm": 1.3461233788596492, "learning_rate": 8.697137003763257e-08, "loss": 1.7474, "step": 311 }, { "epoch": 3.320855614973262, "grad_norm": 1.3268083676132274, "learning_rate": 8.639584155458478e-08, "loss": 1.7495, "step": 312 }, { "epoch": 3.3315508021390374, "grad_norm": 1.191737854993917, "learning_rate": 8.582077182111334e-08, "loss": 1.7327, "step": 313 }, { "epoch": 3.342245989304813, "grad_norm": 1.3873486562425863, "learning_rate": 8.524618022930328e-08, "loss": 1.774, "step": 314 }, { "epoch": 3.3529411764705883, "grad_norm": 1.267503500654065, "learning_rate": 8.467208615511598e-08, "loss": 1.8218, "step": 315 }, { "epoch": 3.3636363636363638, "grad_norm": 1.2310824627324275, "learning_rate": 8.409850895773594e-08, "loss": 1.7937, "step": 316 }, { "epoch": 3.374331550802139, "grad_norm": 1.4001475717116718, "learning_rate": 8.352546797891792e-08, "loss": 1.7684, "step": 317 }, { "epoch": 3.385026737967914, "grad_norm": 1.1789153845970866, "learning_rate": 8.29529825423347e-08, "loss": 1.6781, "step": 318 }, { "epoch": 3.3957219251336896, "grad_norm": 1.24396091907366, "learning_rate": 8.238107195292545e-08, "loss": 1.7719, "step": 319 }, { "epoch": 3.406417112299465, "grad_norm": 1.2292867117022759, "learning_rate": 8.180975549624487e-08, "loss": 1.7469, "step": 320 }, { "epoch": 3.4171122994652405, "grad_norm": 1.1717577870649791, "learning_rate": 8.123905243781254e-08, "loss": 1.6798, "step": 321 }, { "epoch": 3.427807486631016, "grad_norm": 1.2575938278398016, "learning_rate": 8.066898202246365e-08, "loss": 1.6889, "step": 322 }, { "epoch": 3.4385026737967914, "grad_norm": 1.1625293385087907, "learning_rate": 8.009956347369975e-08, "loss": 1.6975, "step": 323 }, { "epoch": 3.449197860962567, "grad_norm": 1.2690884645524694, "learning_rate": 7.953081599304072e-08, "loss": 1.7218, "step": 324 }, { "epoch": 3.4598930481283423, "grad_norm": 1.2419868432176155, "learning_rate": 7.896275875937708e-08, "loss": 1.7803, "step": 325 }, { "epoch": 3.4705882352941178, "grad_norm": 1.184099754729337, "learning_rate": 7.839541092832333e-08, "loss": 1.7156, "step": 326 }, { "epoch": 3.481283422459893, "grad_norm": 1.1862153909216864, "learning_rate": 7.782879163157208e-08, "loss": 1.7006, "step": 327 }, { "epoch": 3.4919786096256686, "grad_norm": 1.093851607116124, "learning_rate": 7.72629199762488e-08, "loss": 1.6786, "step": 328 }, { "epoch": 3.502673796791444, "grad_norm": 1.1282159418439401, "learning_rate": 7.669781504426756e-08, "loss": 1.7027, "step": 329 }, { "epoch": 3.5133689839572195, "grad_norm": 1.223168824958451, "learning_rate": 7.613349589168747e-08, "loss": 1.6564, "step": 330 }, { "epoch": 3.5240641711229945, "grad_norm": 1.1319623104240417, "learning_rate": 7.556998154807024e-08, "loss": 1.7227, "step": 331 }, { "epoch": 3.53475935828877, "grad_norm": 1.185091465957692, "learning_rate": 7.500729101583834e-08, "loss": 1.6848, "step": 332 }, { "epoch": 3.5454545454545454, "grad_norm": 1.0644230111184412, "learning_rate": 7.444544326963429e-08, "loss": 1.72, "step": 333 }, { "epoch": 3.556149732620321, "grad_norm": 1.21890226376482, "learning_rate": 7.388445725568084e-08, "loss": 1.8642, "step": 334 }, { "epoch": 3.5668449197860963, "grad_norm": 1.4445604734990471, "learning_rate": 7.332435189114193e-08, "loss": 1.7787, "step": 335 }, { "epoch": 3.5775401069518717, "grad_norm": 1.2105045461008825, "learning_rate": 7.276514606348491e-08, "loss": 1.6881, "step": 336 }, { "epoch": 3.588235294117647, "grad_norm": 1.102791736830715, "learning_rate": 7.220685862984363e-08, "loss": 1.7327, "step": 337 }, { "epoch": 3.598930481283422, "grad_norm": 1.1924084347760489, "learning_rate": 7.164950841638258e-08, "loss": 1.6902, "step": 338 }, { "epoch": 3.6096256684491976, "grad_norm": 1.1580958424661516, "learning_rate": 7.109311421766185e-08, "loss": 1.6331, "step": 339 }, { "epoch": 3.620320855614973, "grad_norm": 1.2916682833349695, "learning_rate": 7.053769479600353e-08, "loss": 1.6836, "step": 340 }, { "epoch": 3.6310160427807485, "grad_norm": 1.3469562641609119, "learning_rate": 6.998326888085908e-08, "loss": 1.7859, "step": 341 }, { "epoch": 3.641711229946524, "grad_norm": 1.0456519175667847, "learning_rate": 6.942985516817758e-08, "loss": 1.6976, "step": 342 }, { "epoch": 3.6524064171122994, "grad_norm": 1.2106511710270909, "learning_rate": 6.887747231977533e-08, "loss": 1.8105, "step": 343 }, { "epoch": 3.663101604278075, "grad_norm": 1.3109723902074921, "learning_rate": 6.832613896270666e-08, "loss": 1.7642, "step": 344 }, { "epoch": 3.6737967914438503, "grad_norm": 1.1136549809003966, "learning_rate": 6.777587368863558e-08, "loss": 1.7285, "step": 345 }, { "epoch": 3.6844919786096257, "grad_norm": 1.152042467158163, "learning_rate": 6.72266950532091e-08, "loss": 1.6912, "step": 346 }, { "epoch": 3.695187165775401, "grad_norm": 1.2594364070019213, "learning_rate": 6.667862157543133e-08, "loss": 1.687, "step": 347 }, { "epoch": 3.7058823529411766, "grad_norm": 1.215359320763271, "learning_rate": 6.613167173703911e-08, "loss": 1.735, "step": 348 }, { "epoch": 3.716577540106952, "grad_norm": 1.1425303492901393, "learning_rate": 6.558586398187862e-08, "loss": 1.7388, "step": 349 }, { "epoch": 3.7272727272727275, "grad_norm": 1.1589882610141018, "learning_rate": 6.504121671528363e-08, "loss": 1.7283, "step": 350 }, { "epoch": 3.7379679144385025, "grad_norm": 1.1920533294709206, "learning_rate": 6.44977483034547e-08, "loss": 1.6778, "step": 351 }, { "epoch": 3.748663101604278, "grad_norm": 1.1391863888328189, "learning_rate": 6.395547707283999e-08, "loss": 1.7453, "step": 352 }, { "epoch": 3.7593582887700534, "grad_norm": 1.2379984807700926, "learning_rate": 6.341442130951711e-08, "loss": 1.733, "step": 353 }, { "epoch": 3.770053475935829, "grad_norm": 1.0703234789118814, "learning_rate": 6.28745992585765e-08, "loss": 1.8132, "step": 354 }, { "epoch": 3.7807486631016043, "grad_norm": 1.219476162659901, "learning_rate": 6.233602912350639e-08, "loss": 1.6737, "step": 355 }, { "epoch": 3.7914438502673797, "grad_norm": 1.058057870241636, "learning_rate": 6.179872906557873e-08, "loss": 1.6902, "step": 356 }, { "epoch": 3.802139037433155, "grad_norm": 1.0205596002772725, "learning_rate": 6.126271720323682e-08, "loss": 1.6816, "step": 357 }, { "epoch": 3.8128342245989306, "grad_norm": 1.1288387982767425, "learning_rate": 6.072801161148449e-08, "loss": 1.6875, "step": 358 }, { "epoch": 3.8235294117647056, "grad_norm": 1.1972354864526025, "learning_rate": 6.019463032127625e-08, "loss": 1.7966, "step": 359 }, { "epoch": 3.834224598930481, "grad_norm": 1.0201467063278828, "learning_rate": 5.966259131890967e-08, "loss": 1.6446, "step": 360 }, { "epoch": 3.8449197860962565, "grad_norm": 1.089473679491638, "learning_rate": 5.913191254541856e-08, "loss": 1.7429, "step": 361 }, { "epoch": 3.855614973262032, "grad_norm": 1.1771812727242728, "learning_rate": 5.860261189596809e-08, "loss": 1.676, "step": 362 }, { "epoch": 3.8663101604278074, "grad_norm": 1.0206750210332003, "learning_rate": 5.8074707219251386e-08, "loss": 1.6714, "step": 363 }, { "epoch": 3.877005347593583, "grad_norm": 1.1184133152996911, "learning_rate": 5.754821631688751e-08, "loss": 1.7867, "step": 364 }, { "epoch": 3.8877005347593583, "grad_norm": 1.1145741640198596, "learning_rate": 5.7023156942821273e-08, "loss": 1.634, "step": 365 }, { "epoch": 3.8983957219251337, "grad_norm": 1.0359592137554388, "learning_rate": 5.649954680272453e-08, "loss": 1.7074, "step": 366 }, { "epoch": 3.909090909090909, "grad_norm": 1.1831471715225512, "learning_rate": 5.5977403553399214e-08, "loss": 1.741, "step": 367 }, { "epoch": 3.9197860962566846, "grad_norm": 1.0736413939749563, "learning_rate": 5.545674480218161e-08, "loss": 1.754, "step": 368 }, { "epoch": 3.93048128342246, "grad_norm": 1.1025910561917067, "learning_rate": 5.493758810634909e-08, "loss": 1.668, "step": 369 }, { "epoch": 3.9411764705882355, "grad_norm": 1.083360147948803, "learning_rate": 5.4419950972527606e-08, "loss": 1.6876, "step": 370 }, { "epoch": 3.951871657754011, "grad_norm": 1.0164021058465504, "learning_rate": 5.390385085610161e-08, "loss": 1.7347, "step": 371 }, { "epoch": 3.962566844919786, "grad_norm": 1.079427614315124, "learning_rate": 5.3389305160625456e-08, "loss": 1.6579, "step": 372 }, { "epoch": 3.9732620320855614, "grad_norm": 1.072485900134341, "learning_rate": 5.2876331237236246e-08, "loss": 1.777, "step": 373 }, { "epoch": 3.983957219251337, "grad_norm": 1.1092854935296532, "learning_rate": 5.236494638406904e-08, "loss": 1.7216, "step": 374 }, { "epoch": 3.9946524064171123, "grad_norm": 1.0290294918555363, "learning_rate": 5.18551678456735e-08, "loss": 1.7223, "step": 375 }, { "epoch": 4.0, "grad_norm": 0.9159150696404492, "learning_rate": 5.134701281243214e-08, "loss": 0.7722, "step": 376 }, { "epoch": 4.010695187165775, "grad_norm": 1.045160999252649, "learning_rate": 5.0840498419980936e-08, "loss": 1.6415, "step": 377 }, { "epoch": 4.021390374331551, "grad_norm": 1.0873773613372983, "learning_rate": 5.03356417486313e-08, "loss": 1.7117, "step": 378 }, { "epoch": 4.032085561497326, "grad_norm": 1.0625990917008519, "learning_rate": 4.9832459822794156e-08, "loss": 1.7381, "step": 379 }, { "epoch": 4.042780748663102, "grad_norm": 1.0544240961720956, "learning_rate": 4.9330969610405916e-08, "loss": 1.6628, "step": 380 }, { "epoch": 4.053475935828877, "grad_norm": 1.083022390800674, "learning_rate": 4.883118802235629e-08, "loss": 1.6743, "step": 381 }, { "epoch": 4.064171122994653, "grad_norm": 1.0072785770045913, "learning_rate": 4.8333131911917946e-08, "loss": 1.683, "step": 382 }, { "epoch": 4.074866310160428, "grad_norm": 1.1106839232668917, "learning_rate": 4.783681807417822e-08, "loss": 1.7179, "step": 383 }, { "epoch": 4.0855614973262036, "grad_norm": 1.159967527815892, "learning_rate": 4.7342263245472844e-08, "loss": 1.7814, "step": 384 }, { "epoch": 4.096256684491979, "grad_norm": 1.1751891288880876, "learning_rate": 4.6849484102821455e-08, "loss": 1.8497, "step": 385 }, { "epoch": 4.106951871657754, "grad_norm": 0.9737241398039365, "learning_rate": 4.6358497263365446e-08, "loss": 1.6612, "step": 386 }, { "epoch": 4.117647058823529, "grad_norm": 1.1500199588264601, "learning_rate": 4.586931928380724e-08, "loss": 1.7281, "step": 387 }, { "epoch": 4.128342245989304, "grad_norm": 1.0125990228815342, "learning_rate": 4.538196665985231e-08, "loss": 1.6853, "step": 388 }, { "epoch": 4.13903743315508, "grad_norm": 1.112547166514679, "learning_rate": 4.489645582565289e-08, "loss": 1.749, "step": 389 }, { "epoch": 4.149732620320855, "grad_norm": 0.9373796658534633, "learning_rate": 4.4412803153253574e-08, "loss": 1.6605, "step": 390 }, { "epoch": 4.160427807486631, "grad_norm": 1.1478427062702479, "learning_rate": 4.393102495203944e-08, "loss": 1.7992, "step": 391 }, { "epoch": 4.171122994652406, "grad_norm": 0.984316331367159, "learning_rate": 4.3451137468186e-08, "loss": 1.7312, "step": 392 }, { "epoch": 4.181818181818182, "grad_norm": 1.215361772202802, "learning_rate": 4.297315688411134e-08, "loss": 1.7271, "step": 393 }, { "epoch": 4.192513368983957, "grad_norm": 0.9519432895034219, "learning_rate": 4.2497099317930444e-08, "loss": 1.6531, "step": 394 }, { "epoch": 4.2032085561497325, "grad_norm": 0.9694859954136436, "learning_rate": 4.202298082291178e-08, "loss": 1.6931, "step": 395 }, { "epoch": 4.213903743315508, "grad_norm": 0.9915938419427395, "learning_rate": 4.155081738693575e-08, "loss": 1.7404, "step": 396 }, { "epoch": 4.224598930481283, "grad_norm": 1.0121466514102255, "learning_rate": 4.108062493195572e-08, "loss": 1.6925, "step": 397 }, { "epoch": 4.235294117647059, "grad_norm": 0.9877677414667453, "learning_rate": 4.0612419313461044e-08, "loss": 1.6788, "step": 398 }, { "epoch": 4.245989304812834, "grad_norm": 1.103944253925402, "learning_rate": 4.014621631994238e-08, "loss": 1.6785, "step": 399 }, { "epoch": 4.25668449197861, "grad_norm": 1.191241046676597, "learning_rate": 3.9682031672359465e-08, "loss": 1.7746, "step": 400 }, { "epoch": 4.267379679144385, "grad_norm": 0.9776512587883704, "learning_rate": 3.92198810236107e-08, "loss": 1.7673, "step": 401 }, { "epoch": 4.278074866310161, "grad_norm": 1.0727199447033928, "learning_rate": 3.8759779958005404e-08, "loss": 1.686, "step": 402 }, { "epoch": 4.288770053475936, "grad_norm": 1.02713175389167, "learning_rate": 3.83017439907385e-08, "loss": 1.7033, "step": 403 }, { "epoch": 4.2994652406417115, "grad_norm": 1.019828543693729, "learning_rate": 3.7845788567367065e-08, "loss": 1.6474, "step": 404 }, { "epoch": 4.310160427807487, "grad_norm": 1.186365894497435, "learning_rate": 3.7391929063289576e-08, "loss": 1.76, "step": 405 }, { "epoch": 4.320855614973262, "grad_norm": 0.9149309479166234, "learning_rate": 3.694018078322747e-08, "loss": 1.6247, "step": 406 }, { "epoch": 4.331550802139038, "grad_norm": 1.086461002242433, "learning_rate": 3.649055896070901e-08, "loss": 1.754, "step": 407 }, { "epoch": 4.342245989304812, "grad_norm": 1.041636492520959, "learning_rate": 3.6043078757555536e-08, "loss": 1.7195, "step": 408 }, { "epoch": 4.352941176470588, "grad_norm": 1.0528695022478751, "learning_rate": 3.55977552633704e-08, "loss": 1.7299, "step": 409 }, { "epoch": 4.363636363636363, "grad_norm": 0.9886087204978182, "learning_rate": 3.5154603495029846e-08, "loss": 1.7116, "step": 410 }, { "epoch": 4.374331550802139, "grad_norm": 1.051279876225997, "learning_rate": 3.4713638396176784e-08, "loss": 1.6781, "step": 411 }, { "epoch": 4.385026737967914, "grad_norm": 1.073747376196132, "learning_rate": 3.427487483671684e-08, "loss": 1.7091, "step": 412 }, { "epoch": 4.39572192513369, "grad_norm": 1.0073846498740464, "learning_rate": 3.383832761231691e-08, "loss": 1.6626, "step": 413 }, { "epoch": 4.406417112299465, "grad_norm": 0.9625216648433483, "learning_rate": 3.340401144390632e-08, "loss": 1.6789, "step": 414 }, { "epoch": 4.4171122994652405, "grad_norm": 0.9112659677354551, "learning_rate": 3.29719409771803e-08, "loss": 1.6958, "step": 415 }, { "epoch": 4.427807486631016, "grad_norm": 0.9811908769425028, "learning_rate": 3.254213078210603e-08, "loss": 1.6198, "step": 416 }, { "epoch": 4.438502673796791, "grad_norm": 0.9764765593601193, "learning_rate": 3.211459535243166e-08, "loss": 1.6625, "step": 417 }, { "epoch": 4.449197860962567, "grad_norm": 0.9923221460990236, "learning_rate": 3.168934910519722e-08, "loss": 1.7042, "step": 418 }, { "epoch": 4.459893048128342, "grad_norm": 1.0999249072613166, "learning_rate": 3.1266406380248556e-08, "loss": 1.7245, "step": 419 }, { "epoch": 4.470588235294118, "grad_norm": 1.051846878307153, "learning_rate": 3.084578143975399e-08, "loss": 1.7062, "step": 420 }, { "epoch": 4.481283422459893, "grad_norm": 0.967268221515666, "learning_rate": 3.0427488467722926e-08, "loss": 1.6732, "step": 421 }, { "epoch": 4.491978609625669, "grad_norm": 1.097020454537966, "learning_rate": 3.0011541569528066e-08, "loss": 1.7687, "step": 422 }, { "epoch": 4.502673796791444, "grad_norm": 1.0373715535055061, "learning_rate": 2.9597954771429357e-08, "loss": 1.6757, "step": 423 }, { "epoch": 4.5133689839572195, "grad_norm": 1.0559463184979518, "learning_rate": 2.9186742020101206e-08, "loss": 1.6872, "step": 424 }, { "epoch": 4.524064171122995, "grad_norm": 0.9585922909111559, "learning_rate": 2.8777917182162136e-08, "loss": 1.6987, "step": 425 }, { "epoch": 4.53475935828877, "grad_norm": 1.022452494959885, "learning_rate": 2.83714940437072e-08, "loss": 1.7271, "step": 426 }, { "epoch": 4.545454545454545, "grad_norm": 1.106707980068351, "learning_rate": 2.7967486309843002e-08, "loss": 1.752, "step": 427 }, { "epoch": 4.556149732620321, "grad_norm": 0.9765722083897883, "learning_rate": 2.756590760422578e-08, "loss": 1.6654, "step": 428 }, { "epoch": 4.566844919786096, "grad_norm": 0.9405887290280592, "learning_rate": 2.7166771468601712e-08, "loss": 1.6675, "step": 429 }, { "epoch": 4.577540106951871, "grad_norm": 1.0137005674417412, "learning_rate": 2.6770091362350355e-08, "loss": 1.7327, "step": 430 }, { "epoch": 4.588235294117647, "grad_norm": 0.9903908467216602, "learning_rate": 2.6375880662031e-08, "loss": 1.6886, "step": 431 }, { "epoch": 4.598930481283422, "grad_norm": 1.0333639492857196, "learning_rate": 2.598415266093128e-08, "loss": 1.6882, "step": 432 }, { "epoch": 4.609625668449198, "grad_norm": 1.011384599727104, "learning_rate": 2.559492056861906e-08, "loss": 1.7119, "step": 433 }, { "epoch": 4.620320855614973, "grad_norm": 0.9642911498735307, "learning_rate": 2.5208197510497076e-08, "loss": 1.6905, "step": 434 }, { "epoch": 4.6310160427807485, "grad_norm": 1.0418968810051497, "learning_rate": 2.482399652736006e-08, "loss": 1.6771, "step": 435 }, { "epoch": 4.641711229946524, "grad_norm": 1.028444493076486, "learning_rate": 2.4442330574955318e-08, "loss": 1.637, "step": 436 }, { "epoch": 4.652406417112299, "grad_norm": 1.1004647333050324, "learning_rate": 2.4063212523545605e-08, "loss": 1.7708, "step": 437 }, { "epoch": 4.663101604278075, "grad_norm": 0.9837960384009068, "learning_rate": 2.3686655157475222e-08, "loss": 1.6315, "step": 438 }, { "epoch": 4.67379679144385, "grad_norm": 1.010645283552132, "learning_rate": 2.3312671174738886e-08, "loss": 1.7004, "step": 439 }, { "epoch": 4.684491978609626, "grad_norm": 0.9870300226541476, "learning_rate": 2.2941273186553555e-08, "loss": 1.6602, "step": 440 }, { "epoch": 4.695187165775401, "grad_norm": 0.992869503429409, "learning_rate": 2.2572473716933117e-08, "loss": 1.6922, "step": 441 }, { "epoch": 4.705882352941177, "grad_norm": 0.9271004606468307, "learning_rate": 2.2206285202266196e-08, "loss": 1.6739, "step": 442 }, { "epoch": 4.716577540106952, "grad_norm": 0.9399426190307087, "learning_rate": 2.184271999089662e-08, "loss": 1.6714, "step": 443 }, { "epoch": 4.7272727272727275, "grad_norm": 0.9405470982909288, "learning_rate": 2.1481790342706985e-08, "loss": 1.6922, "step": 444 }, { "epoch": 4.737967914438503, "grad_norm": 0.9811133031262508, "learning_rate": 2.1123508428705526e-08, "loss": 1.7227, "step": 445 }, { "epoch": 4.748663101604278, "grad_norm": 0.9994183774525757, "learning_rate": 2.0767886330615393e-08, "loss": 1.6695, "step": 446 }, { "epoch": 4.759358288770054, "grad_norm": 0.8944615862810735, "learning_rate": 2.0414936040467324e-08, "loss": 1.6437, "step": 447 }, { "epoch": 4.770053475935828, "grad_norm": 0.9327486138997619, "learning_rate": 2.0064669460195427e-08, "loss": 1.6683, "step": 448 }, { "epoch": 4.780748663101605, "grad_norm": 1.0666867261313815, "learning_rate": 1.9717098401235466e-08, "loss": 1.6931, "step": 449 }, { "epoch": 4.791443850267379, "grad_norm": 0.9002639414061351, "learning_rate": 1.9372234584127e-08, "loss": 1.6548, "step": 450 }, { "epoch": 4.802139037433155, "grad_norm": 1.09999518872419, "learning_rate": 1.903008963811784e-08, "loss": 1.7297, "step": 451 }, { "epoch": 4.81283422459893, "grad_norm": 1.0114275537340787, "learning_rate": 1.869067510077197e-08, "loss": 1.7303, "step": 452 }, { "epoch": 4.823529411764706, "grad_norm": 0.9512765049240302, "learning_rate": 1.8354002417580616e-08, "loss": 1.6838, "step": 453 }, { "epoch": 4.834224598930481, "grad_norm": 1.050514450500839, "learning_rate": 1.8020082941576063e-08, "loss": 1.7167, "step": 454 }, { "epoch": 4.8449197860962565, "grad_norm": 1.094997909311891, "learning_rate": 1.7688927932948982e-08, "loss": 1.7323, "step": 455 }, { "epoch": 4.855614973262032, "grad_norm": 0.9111792597842645, "learning_rate": 1.736054855866874e-08, "loss": 1.6248, "step": 456 }, { "epoch": 4.866310160427807, "grad_norm": 1.1123177324598712, "learning_rate": 1.7034955892106706e-08, "loss": 1.7234, "step": 457 }, { "epoch": 4.877005347593583, "grad_norm": 1.0745839067449734, "learning_rate": 1.67121609126629e-08, "loss": 1.7122, "step": 458 }, { "epoch": 4.887700534759358, "grad_norm": 0.9529170195641278, "learning_rate": 1.6392174505395818e-08, "loss": 1.7174, "step": 459 }, { "epoch": 4.898395721925134, "grad_norm": 1.051414411800044, "learning_rate": 1.6075007460655264e-08, "loss": 1.723, "step": 460 }, { "epoch": 4.909090909090909, "grad_norm": 0.8961698608334864, "learning_rate": 1.5760670473718563e-08, "loss": 1.6516, "step": 461 }, { "epoch": 4.919786096256685, "grad_norm": 0.9750906247524822, "learning_rate": 1.5449174144429944e-08, "loss": 1.7271, "step": 462 }, { "epoch": 4.93048128342246, "grad_norm": 0.9320190655543753, "learning_rate": 1.5140528976842892e-08, "loss": 1.6043, "step": 463 }, { "epoch": 4.9411764705882355, "grad_norm": 0.897844088201777, "learning_rate": 1.4834745378866242e-08, "loss": 1.6956, "step": 464 }, { "epoch": 4.951871657754011, "grad_norm": 1.0633722675619555, "learning_rate": 1.453183366191294e-08, "loss": 1.6845, "step": 465 }, { "epoch": 4.962566844919786, "grad_norm": 0.9955108585955837, "learning_rate": 1.4231804040552475e-08, "loss": 1.734, "step": 466 }, { "epoch": 4.973262032085562, "grad_norm": 0.941749022002119, "learning_rate": 1.3934666632166447e-08, "loss": 1.6548, "step": 467 }, { "epoch": 4.983957219251337, "grad_norm": 1.1788580132926334, "learning_rate": 1.3640431456607249e-08, "loss": 1.7501, "step": 468 }, { "epoch": 4.994652406417112, "grad_norm": 0.9773320447474946, "learning_rate": 1.3349108435860323e-08, "loss": 1.7071, "step": 469 }, { "epoch": 5.0, "grad_norm": 0.9773320447474946, "learning_rate": 1.306070739370958e-08, "loss": 0.8559, "step": 470 }, { "epoch": 5.010695187165775, "grad_norm": 0.9188661754272343, "learning_rate": 1.2775238055406035e-08, "loss": 1.6589, "step": 471 }, { "epoch": 5.021390374331551, "grad_norm": 0.8901327328351276, "learning_rate": 1.2492710047339915e-08, "loss": 1.6933, "step": 472 }, { "epoch": 5.032085561497326, "grad_norm": 0.9246207493352062, "learning_rate": 1.221313289671605e-08, "loss": 1.6757, "step": 473 }, { "epoch": 5.042780748663102, "grad_norm": 0.9711328053669774, "learning_rate": 1.1936516031232579e-08, "loss": 1.6507, "step": 474 }, { "epoch": 5.053475935828877, "grad_norm": 0.885727686084371, "learning_rate": 1.166286877876309e-08, "loss": 1.6856, "step": 475 }, { "epoch": 5.064171122994653, "grad_norm": 0.9676248114351074, "learning_rate": 1.1392200367042004e-08, "loss": 1.6794, "step": 476 }, { "epoch": 5.074866310160428, "grad_norm": 1.0673039521382486, "learning_rate": 1.1124519923353381e-08, "loss": 1.6842, "step": 477 }, { "epoch": 5.0855614973262036, "grad_norm": 0.9009744016624704, "learning_rate": 1.0859836474223282e-08, "loss": 1.6965, "step": 478 }, { "epoch": 5.096256684491979, "grad_norm": 0.9455628262511884, "learning_rate": 1.0598158945115244e-08, "loss": 1.6861, "step": 479 }, { "epoch": 5.106951871657754, "grad_norm": 0.9077368959415236, "learning_rate": 1.0339496160129302e-08, "loss": 1.6267, "step": 480 }, { "epoch": 5.117647058823529, "grad_norm": 1.0415861040184733, "learning_rate": 1.0083856841704597e-08, "loss": 1.7341, "step": 481 }, { "epoch": 5.128342245989304, "grad_norm": 1.113520946442234, "learning_rate": 9.831249610324977e-09, "loss": 1.7696, "step": 482 }, { "epoch": 5.13903743315508, "grad_norm": 0.9585879130795013, "learning_rate": 9.581682984228512e-09, "loss": 1.7348, "step": 483 }, { "epoch": 5.149732620320855, "grad_norm": 0.9976079228700155, "learning_rate": 9.335165379120225e-09, "loss": 1.6163, "step": 484 }, { "epoch": 5.160427807486631, "grad_norm": 0.9592507411118638, "learning_rate": 9.091705107888203e-09, "loss": 1.7173, "step": 485 }, { "epoch": 5.171122994652406, "grad_norm": 0.9454912363881004, "learning_rate": 8.851310380323341e-09, "loss": 1.7292, "step": 486 }, { "epoch": 5.181818181818182, "grad_norm": 0.9961249864741337, "learning_rate": 8.613989302842505e-09, "loss": 1.6993, "step": 487 }, { "epoch": 5.192513368983957, "grad_norm": 0.9979318786464878, "learning_rate": 8.379749878215147e-09, "loss": 1.7191, "step": 488 }, { "epoch": 5.2032085561497325, "grad_norm": 1.1284315966256178, "learning_rate": 8.148600005293482e-09, "loss": 1.6809, "step": 489 }, { "epoch": 5.213903743315508, "grad_norm": 0.8828047682701857, "learning_rate": 7.920547478746087e-09, "loss": 1.5985, "step": 490 }, { "epoch": 5.224598930481283, "grad_norm": 0.9707982551103843, "learning_rate": 7.695599988795054e-09, "loss": 1.6298, "step": 491 }, { "epoch": 5.235294117647059, "grad_norm": 0.9771649057153118, "learning_rate": 7.473765120956676e-09, "loss": 1.6882, "step": 492 }, { "epoch": 5.245989304812834, "grad_norm": 0.9121736247147408, "learning_rate": 7.255050355785697e-09, "loss": 1.6989, "step": 493 }, { "epoch": 5.25668449197861, "grad_norm": 0.9797778068241166, "learning_rate": 7.039463068622941e-09, "loss": 1.6633, "step": 494 }, { "epoch": 5.267379679144385, "grad_norm": 0.9680218261730074, "learning_rate": 6.827010529346822e-09, "loss": 1.7067, "step": 495 }, { "epoch": 5.278074866310161, "grad_norm": 0.9489590503348215, "learning_rate": 6.617699902127904e-09, "loss": 1.6327, "step": 496 }, { "epoch": 5.288770053475936, "grad_norm": 0.8815268202238973, "learning_rate": 6.411538245187531e-09, "loss": 1.6435, "step": 497 }, { "epoch": 5.2994652406417115, "grad_norm": 0.9974336337092268, "learning_rate": 6.208532510559794e-09, "loss": 1.6332, "step": 498 }, { "epoch": 5.310160427807487, "grad_norm": 0.8933603401367466, "learning_rate": 6.008689543857004e-09, "loss": 1.6664, "step": 499 }, { "epoch": 5.320855614973262, "grad_norm": 0.9817436618753383, "learning_rate": 5.812016084038928e-09, "loss": 1.7075, "step": 500 }, { "epoch": 5.331550802139038, "grad_norm": 1.0161854159725459, "learning_rate": 5.618518763185498e-09, "loss": 1.7694, "step": 501 }, { "epoch": 5.342245989304812, "grad_norm": 0.937744754195074, "learning_rate": 5.428204106273182e-09, "loss": 1.7349, "step": 502 }, { "epoch": 5.352941176470588, "grad_norm": 0.9657660078838018, "learning_rate": 5.241078530955023e-09, "loss": 1.7279, "step": 503 }, { "epoch": 5.363636363636363, "grad_norm": 0.9907387527079021, "learning_rate": 5.057148347344098e-09, "loss": 1.6935, "step": 504 }, { "epoch": 5.374331550802139, "grad_norm": 0.9996821802022919, "learning_rate": 4.876419757800809e-09, "loss": 1.7443, "step": 505 }, { "epoch": 5.385026737967914, "grad_norm": 1.1041216412394943, "learning_rate": 4.698898856723755e-09, "loss": 1.7212, "step": 506 }, { "epoch": 5.39572192513369, "grad_norm": 0.9567425116064339, "learning_rate": 4.524591630344154e-09, "loss": 1.7302, "step": 507 }, { "epoch": 5.406417112299465, "grad_norm": 0.9139225110223402, "learning_rate": 4.3535039565240185e-09, "loss": 1.644, "step": 508 }, { "epoch": 5.4171122994652405, "grad_norm": 0.9557299419427362, "learning_rate": 4.185641604557988e-09, "loss": 1.776, "step": 509 }, { "epoch": 5.427807486631016, "grad_norm": 0.9891934448623068, "learning_rate": 4.021010234978672e-09, "loss": 1.621, "step": 510 }, { "epoch": 5.438502673796791, "grad_norm": 0.8523623141922965, "learning_rate": 3.859615399365834e-09, "loss": 1.6713, "step": 511 }, { "epoch": 5.449197860962567, "grad_norm": 1.0359319296166756, "learning_rate": 3.7014625401592504e-09, "loss": 1.7067, "step": 512 }, { "epoch": 5.459893048128342, "grad_norm": 0.9584687786262982, "learning_rate": 3.546556990475047e-09, "loss": 1.7035, "step": 513 }, { "epoch": 5.470588235294118, "grad_norm": 1.0397468854544867, "learning_rate": 3.394903973925978e-09, "loss": 1.6839, "step": 514 }, { "epoch": 5.481283422459893, "grad_norm": 0.9282319484076822, "learning_rate": 3.2465086044451972e-09, "loss": 1.6707, "step": 515 }, { "epoch": 5.491978609625669, "grad_norm": 1.0643511037463378, "learning_rate": 3.101375886113855e-09, "loss": 1.7574, "step": 516 }, { "epoch": 5.502673796791444, "grad_norm": 0.9249965346439781, "learning_rate": 2.9595107129923522e-09, "loss": 1.7454, "step": 517 }, { "epoch": 5.5133689839572195, "grad_norm": 1.1004989944852983, "learning_rate": 2.820917868955308e-09, "loss": 1.6926, "step": 518 }, { "epoch": 5.524064171122995, "grad_norm": 1.0097493072977206, "learning_rate": 2.6856020275301872e-09, "loss": 1.7823, "step": 519 }, { "epoch": 5.53475935828877, "grad_norm": 1.0308801410523392, "learning_rate": 2.5535677517397825e-09, "loss": 1.6779, "step": 520 }, { "epoch": 5.545454545454545, "grad_norm": 0.9699326714715057, "learning_rate": 2.4248194939482934e-09, "loss": 1.6935, "step": 521 }, { "epoch": 5.556149732620321, "grad_norm": 0.9609361738868017, "learning_rate": 2.2993615957112024e-09, "loss": 1.6996, "step": 522 }, { "epoch": 5.566844919786096, "grad_norm": 0.9767765231947246, "learning_rate": 2.1771982876288896e-09, "loss": 1.7514, "step": 523 }, { "epoch": 5.577540106951871, "grad_norm": 1.0183380125591044, "learning_rate": 2.0583336892039284e-09, "loss": 1.724, "step": 524 }, { "epoch": 5.588235294117647, "grad_norm": 0.9309198688472802, "learning_rate": 1.942771808702204e-09, "loss": 1.6802, "step": 525 }, { "epoch": 5.598930481283422, "grad_norm": 0.9888708909033831, "learning_rate": 1.8305165430177349e-09, "loss": 1.7302, "step": 526 }, { "epoch": 5.609625668449198, "grad_norm": 0.9634253477947875, "learning_rate": 1.721571677541267e-09, "loss": 1.6462, "step": 527 }, { "epoch": 5.620320855614973, "grad_norm": 0.8931832430877537, "learning_rate": 1.6159408860326407e-09, "loss": 1.6759, "step": 528 }, { "epoch": 5.6310160427807485, "grad_norm": 1.0398451908071025, "learning_rate": 1.5136277304969026e-09, "loss": 1.7388, "step": 529 }, { "epoch": 5.641711229946524, "grad_norm": 0.9718661959054758, "learning_rate": 1.4146356610641452e-09, "loss": 1.7415, "step": 530 }, { "epoch": 5.652406417112299, "grad_norm": 1.020355689324263, "learning_rate": 1.318968015873234e-09, "loss": 1.6606, "step": 531 }, { "epoch": 5.663101604278075, "grad_norm": 0.9385275215082548, "learning_rate": 1.2266280209592195e-09, "loss": 1.7019, "step": 532 }, { "epoch": 5.67379679144385, "grad_norm": 0.9140476987794279, "learning_rate": 1.13761879014449e-09, "loss": 1.6577, "step": 533 }, { "epoch": 5.684491978609626, "grad_norm": 0.9571683238609927, "learning_rate": 1.0519433249338684e-09, "loss": 1.8192, "step": 534 }, { "epoch": 5.695187165775401, "grad_norm": 0.995812738831554, "learning_rate": 9.696045144133137e-10, "loss": 1.6624, "step": 535 }, { "epoch": 5.705882352941177, "grad_norm": 0.9979630006008087, "learning_rate": 8.906051351525668e-10, "loss": 1.7615, "step": 536 }, { "epoch": 5.716577540106952, "grad_norm": 1.1020069060561395, "learning_rate": 8.149478511114583e-10, "loss": 1.7092, "step": 537 }, { "epoch": 5.7272727272727275, "grad_norm": 0.96304384040326, "learning_rate": 7.426352135501135e-10, "loss": 1.7152, "step": 538 }, { "epoch": 5.737967914438503, "grad_norm": 1.0636369337963125, "learning_rate": 6.736696609429215e-10, "loss": 1.7183, "step": 539 }, { "epoch": 5.748663101604278, "grad_norm": 0.8943816455569424, "learning_rate": 6.080535188962899e-10, "loss": 1.6725, "step": 540 }, { "epoch": 5.759358288770054, "grad_norm": 0.9147076914165057, "learning_rate": 5.45789000070207e-10, "loss": 1.6266, "step": 541 }, { "epoch": 5.770053475935828, "grad_norm": 0.9259441954861048, "learning_rate": 4.868782041037023e-10, "loss": 1.714, "step": 542 }, { "epoch": 5.780748663101605, "grad_norm": 1.0050666366612744, "learning_rate": 4.3132311754395803e-10, "loss": 1.681, "step": 543 }, { "epoch": 5.791443850267379, "grad_norm": 1.0015006260910468, "learning_rate": 3.791256137793408e-10, "loss": 1.7501, "step": 544 }, { "epoch": 5.802139037433155, "grad_norm": 0.9735042106859433, "learning_rate": 3.302874529762745e-10, "loss": 1.7039, "step": 545 }, { "epoch": 5.81283422459893, "grad_norm": 0.8663801231432109, "learning_rate": 2.848102820198428e-10, "loss": 1.7333, "step": 546 }, { "epoch": 5.823529411764706, "grad_norm": 0.9724868452239626, "learning_rate": 2.4269563445825646e-10, "loss": 1.6686, "step": 547 }, { "epoch": 5.834224598930481, "grad_norm": 0.9405244140826245, "learning_rate": 2.039449304511498e-10, "loss": 1.6336, "step": 548 }, { "epoch": 5.8449197860962565, "grad_norm": 1.0463056589093365, "learning_rate": 1.685594767216969e-10, "loss": 1.6941, "step": 549 }, { "epoch": 5.855614973262032, "grad_norm": 0.9973891857547772, "learning_rate": 1.365404665125247e-10, "loss": 1.6165, "step": 550 }, { "epoch": 5.866310160427807, "grad_norm": 0.9212864575228166, "learning_rate": 1.078889795455229e-10, "loss": 1.7158, "step": 551 }, { "epoch": 5.877005347593583, "grad_norm": 0.9558079062751006, "learning_rate": 8.260598198537305e-11, "loss": 1.7074, "step": 552 }, { "epoch": 5.887700534759358, "grad_norm": 1.047243790928667, "learning_rate": 6.069232640698585e-11, "loss": 1.7006, "step": 553 }, { "epoch": 5.898395721925134, "grad_norm": 1.0050896260076372, "learning_rate": 4.214875176680177e-11, "loss": 1.7195, "step": 554 }, { "epoch": 5.909090909090909, "grad_norm": 0.9001691362483673, "learning_rate": 2.697588337779999e-11, "loss": 1.669, "step": 555 }, { "epoch": 5.919786096256685, "grad_norm": 0.9164142508936975, "learning_rate": 1.5174232888470752e-11, "loss": 1.7238, "step": 556 }, { "epoch": 5.93048128342246, "grad_norm": 0.9516118267040808, "learning_rate": 6.744198265506984e-12, "loss": 1.7005, "step": 557 }, { "epoch": 5.9411764705882355, "grad_norm": 0.9866304863791698, "learning_rate": 1.686063780426128e-12, "loss": 1.6486, "step": 558 }, { "epoch": 5.9411764705882355, "step": 558, "total_flos": 348615437615104.0, "train_loss": 1.8701536655426025, "train_runtime": 9233.6332, "train_samples_per_second": 48.562, "train_steps_per_second": 0.06 } ], "logging_steps": 1.0, "max_steps": 558, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 348615437615104.0, "train_batch_size": 50, "trial_name": null, "trial_params": null }