{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.7094017094017095, "eval_steps": 500, "global_step": 3600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004748338081671415, "grad_norm": 19.59556146139992, "learning_rate": 8.547008547008548e-07, "loss": 8.2567, "step": 10 }, { "epoch": 0.00949667616334283, "grad_norm": 18.470526689140495, "learning_rate": 1.8043684710351376e-06, "loss": 8.1368, "step": 20 }, { "epoch": 0.014245014245014245, "grad_norm": 9.516482160543532, "learning_rate": 2.7540360873694207e-06, "loss": 7.4974, "step": 30 }, { "epoch": 0.01899335232668566, "grad_norm": 4.9847966260626215, "learning_rate": 3.7037037037037037e-06, "loss": 6.7488, "step": 40 }, { "epoch": 0.023741690408357077, "grad_norm": 3.2443480486318945, "learning_rate": 4.653371320037987e-06, "loss": 6.2614, "step": 50 }, { "epoch": 0.02849002849002849, "grad_norm": 3.038128638423009, "learning_rate": 5.60303893637227e-06, "loss": 5.9181, "step": 60 }, { "epoch": 0.03323836657169991, "grad_norm": 3.7165566072111664, "learning_rate": 6.5527065527065525e-06, "loss": 5.5221, "step": 70 }, { "epoch": 0.03798670465337132, "grad_norm": 3.8807466365954384, "learning_rate": 7.5023741690408365e-06, "loss": 4.9324, "step": 80 }, { "epoch": 0.042735042735042736, "grad_norm": 4.403564124821985, "learning_rate": 8.452041785375119e-06, "loss": 4.2636, "step": 90 }, { "epoch": 0.04748338081671415, "grad_norm": 4.690397199283881, "learning_rate": 9.401709401709402e-06, "loss": 3.6723, "step": 100 }, { "epoch": 0.052231718898385564, "grad_norm": 4.093575668273963, "learning_rate": 1.0351377018043685e-05, "loss": 3.2591, "step": 110 }, { "epoch": 0.05698005698005698, "grad_norm": 2.8440866604729447, "learning_rate": 1.1301044634377968e-05, "loss": 3.0232, "step": 120 }, { "epoch": 0.06172839506172839, "grad_norm": 2.3787189109612714, "learning_rate": 1.2250712250712251e-05, "loss": 2.8761, "step": 130 }, { "epoch": 0.06647673314339982, "grad_norm": 5.294760512204114, "learning_rate": 1.3200379867046534e-05, "loss": 2.7696, "step": 140 }, { "epoch": 0.07122507122507123, "grad_norm": 7.938750274935964, "learning_rate": 1.4150047483380819e-05, "loss": 2.6909, "step": 150 }, { "epoch": 0.07597340930674264, "grad_norm": 4.651664460732956, "learning_rate": 1.50997150997151e-05, "loss": 2.6095, "step": 160 }, { "epoch": 0.08072174738841406, "grad_norm": 9.256919687252832, "learning_rate": 1.604938271604938e-05, "loss": 2.5501, "step": 170 }, { "epoch": 0.08547008547008547, "grad_norm": 12.064856380603368, "learning_rate": 1.6999050332383668e-05, "loss": 2.4904, "step": 180 }, { "epoch": 0.09021842355175688, "grad_norm": 12.087773624352351, "learning_rate": 1.794871794871795e-05, "loss": 2.433, "step": 190 }, { "epoch": 0.0949667616334283, "grad_norm": 15.164867794392874, "learning_rate": 1.889838556505223e-05, "loss": 2.3694, "step": 200 }, { "epoch": 0.09971509971509972, "grad_norm": 13.822253776356119, "learning_rate": 1.9848053181386517e-05, "loss": 2.3272, "step": 210 }, { "epoch": 0.10446343779677113, "grad_norm": 16.631555759707965, "learning_rate": 2.07977207977208e-05, "loss": 2.2625, "step": 220 }, { "epoch": 0.10921177587844255, "grad_norm": 16.016081398374507, "learning_rate": 2.174738841405508e-05, "loss": 2.1999, "step": 230 }, { "epoch": 0.11396011396011396, "grad_norm": 22.615931913843276, "learning_rate": 2.2697056030389367e-05, "loss": 2.1498, "step": 240 }, { "epoch": 0.11870845204178537, "grad_norm": 19.23627606954933, "learning_rate": 2.364672364672365e-05, "loss": 2.0798, "step": 250 }, { "epoch": 0.12345679012345678, "grad_norm": 17.696013693555628, "learning_rate": 2.459639126305793e-05, "loss": 1.9921, "step": 260 }, { "epoch": 0.1282051282051282, "grad_norm": 16.807227837452878, "learning_rate": 2.5546058879392216e-05, "loss": 1.9044, "step": 270 }, { "epoch": 0.13295346628679963, "grad_norm": 11.41571060893682, "learning_rate": 2.64957264957265e-05, "loss": 1.8066, "step": 280 }, { "epoch": 0.13770180436847104, "grad_norm": 6.5123968942805135, "learning_rate": 2.744539411206078e-05, "loss": 1.7012, "step": 290 }, { "epoch": 0.14245014245014245, "grad_norm": 6.283214265860335, "learning_rate": 2.839506172839506e-05, "loss": 1.6008, "step": 300 }, { "epoch": 0.14719848053181386, "grad_norm": 9.079823119870198, "learning_rate": 2.9344729344729345e-05, "loss": 1.5131, "step": 310 }, { "epoch": 0.15194681861348527, "grad_norm": 6.449231111194866, "learning_rate": 3.029439696106363e-05, "loss": 1.4408, "step": 320 }, { "epoch": 0.15669515669515668, "grad_norm": 7.974966858082437, "learning_rate": 3.1244064577397914e-05, "loss": 1.3754, "step": 330 }, { "epoch": 0.16144349477682812, "grad_norm": 4.822536153428492, "learning_rate": 3.2193732193732194e-05, "loss": 1.328, "step": 340 }, { "epoch": 0.16619183285849953, "grad_norm": 5.432798377694006, "learning_rate": 3.314339981006648e-05, "loss": 1.2678, "step": 350 }, { "epoch": 0.17094017094017094, "grad_norm": 5.187313579614613, "learning_rate": 3.409306742640076e-05, "loss": 1.2157, "step": 360 }, { "epoch": 0.17568850902184235, "grad_norm": 5.499195508916456, "learning_rate": 3.504273504273504e-05, "loss": 1.1706, "step": 370 }, { "epoch": 0.18043684710351376, "grad_norm": 4.926464577040076, "learning_rate": 3.599240265906933e-05, "loss": 1.1311, "step": 380 }, { "epoch": 0.18518518518518517, "grad_norm": 5.042820415005092, "learning_rate": 3.694207027540361e-05, "loss": 1.1026, "step": 390 }, { "epoch": 0.1899335232668566, "grad_norm": 5.458949172817995, "learning_rate": 3.789173789173789e-05, "loss": 1.0523, "step": 400 }, { "epoch": 0.19468186134852802, "grad_norm": 5.673599382737787, "learning_rate": 3.884140550807218e-05, "loss": 1.0205, "step": 410 }, { "epoch": 0.19943019943019943, "grad_norm": 3.4632351646502926, "learning_rate": 3.979107312440646e-05, "loss": 0.9893, "step": 420 }, { "epoch": 0.20417853751187084, "grad_norm": 6.070644448266208, "learning_rate": 4.074074074074074e-05, "loss": 0.9638, "step": 430 }, { "epoch": 0.20892687559354226, "grad_norm": 4.854679094572386, "learning_rate": 4.169040835707503e-05, "loss": 0.9357, "step": 440 }, { "epoch": 0.21367521367521367, "grad_norm": 4.529619524145627, "learning_rate": 4.264007597340931e-05, "loss": 0.9076, "step": 450 }, { "epoch": 0.2184235517568851, "grad_norm": 4.157674076266944, "learning_rate": 4.358974358974359e-05, "loss": 0.8933, "step": 460 }, { "epoch": 0.22317188983855651, "grad_norm": 6.4050560210455165, "learning_rate": 4.453941120607788e-05, "loss": 0.868, "step": 470 }, { "epoch": 0.22792022792022792, "grad_norm": 5.032943336700719, "learning_rate": 4.548907882241216e-05, "loss": 0.842, "step": 480 }, { "epoch": 0.23266856600189934, "grad_norm": 6.013522469421973, "learning_rate": 4.643874643874644e-05, "loss": 0.8071, "step": 490 }, { "epoch": 0.23741690408357075, "grad_norm": 5.110412155585145, "learning_rate": 4.738841405508073e-05, "loss": 0.7809, "step": 500 }, { "epoch": 0.24216524216524216, "grad_norm": 5.7836833567564305, "learning_rate": 4.833808167141501e-05, "loss": 0.7605, "step": 510 }, { "epoch": 0.24691358024691357, "grad_norm": 4.319290309225294, "learning_rate": 4.928774928774929e-05, "loss": 0.7286, "step": 520 }, { "epoch": 0.251661918328585, "grad_norm": 5.40178280723504, "learning_rate": 5.0237416904083576e-05, "loss": 0.7105, "step": 530 }, { "epoch": 0.2564102564102564, "grad_norm": 4.71777919695988, "learning_rate": 5.118708452041786e-05, "loss": 0.6931, "step": 540 }, { "epoch": 0.2611585944919278, "grad_norm": 5.6291823771994665, "learning_rate": 5.213675213675214e-05, "loss": 0.6759, "step": 550 }, { "epoch": 0.26590693257359926, "grad_norm": 5.5347321476291835, "learning_rate": 5.308641975308642e-05, "loss": 0.6491, "step": 560 }, { "epoch": 0.2706552706552707, "grad_norm": 5.257360790177073, "learning_rate": 5.403608736942071e-05, "loss": 0.6285, "step": 570 }, { "epoch": 0.2754036087369421, "grad_norm": 5.511202010659421, "learning_rate": 5.498575498575499e-05, "loss": 0.6012, "step": 580 }, { "epoch": 0.2801519468186135, "grad_norm": 5.380510479349013, "learning_rate": 5.5935422602089274e-05, "loss": 0.5852, "step": 590 }, { "epoch": 0.2849002849002849, "grad_norm": 3.6898979087460755, "learning_rate": 5.6885090218423554e-05, "loss": 0.5671, "step": 600 }, { "epoch": 0.2896486229819563, "grad_norm": 4.727348568866969, "learning_rate": 5.7834757834757834e-05, "loss": 0.5514, "step": 610 }, { "epoch": 0.2943969610636277, "grad_norm": 4.668206154804636, "learning_rate": 5.878442545109212e-05, "loss": 0.5278, "step": 620 }, { "epoch": 0.29914529914529914, "grad_norm": 3.5726965671314566, "learning_rate": 5.97340930674264e-05, "loss": 0.5064, "step": 630 }, { "epoch": 0.30389363722697055, "grad_norm": 4.046849737286265, "learning_rate": 6.068376068376068e-05, "loss": 0.4812, "step": 640 }, { "epoch": 0.30864197530864196, "grad_norm": 4.042224830358077, "learning_rate": 6.163342830009497e-05, "loss": 0.4733, "step": 650 }, { "epoch": 0.31339031339031337, "grad_norm": 2.7104179759082787, "learning_rate": 6.258309591642925e-05, "loss": 0.4485, "step": 660 }, { "epoch": 0.3181386514719848, "grad_norm": 3.530227033382703, "learning_rate": 6.353276353276355e-05, "loss": 0.436, "step": 670 }, { "epoch": 0.32288698955365625, "grad_norm": 4.347310302223748, "learning_rate": 6.448243114909783e-05, "loss": 0.4151, "step": 680 }, { "epoch": 0.32763532763532766, "grad_norm": 2.522321016680872, "learning_rate": 6.54320987654321e-05, "loss": 0.4114, "step": 690 }, { "epoch": 0.33238366571699907, "grad_norm": 3.7746726650422113, "learning_rate": 6.638176638176638e-05, "loss": 0.3887, "step": 700 }, { "epoch": 0.3371320037986705, "grad_norm": 2.907400275302209, "learning_rate": 6.733143399810066e-05, "loss": 0.3768, "step": 710 }, { "epoch": 0.3418803418803419, "grad_norm": 2.109887545655247, "learning_rate": 6.828110161443494e-05, "loss": 0.3621, "step": 720 }, { "epoch": 0.3466286799620133, "grad_norm": 2.597481793691592, "learning_rate": 6.923076923076924e-05, "loss": 0.3516, "step": 730 }, { "epoch": 0.3513770180436847, "grad_norm": 2.6365690488571807, "learning_rate": 7.018043684710352e-05, "loss": 0.3339, "step": 740 }, { "epoch": 0.3561253561253561, "grad_norm": 2.8201086376128943, "learning_rate": 7.11301044634378e-05, "loss": 0.3198, "step": 750 }, { "epoch": 0.36087369420702753, "grad_norm": 2.396568559036651, "learning_rate": 7.207977207977208e-05, "loss": 0.3114, "step": 760 }, { "epoch": 0.36562203228869894, "grad_norm": 1.9490881875653105, "learning_rate": 7.302943969610636e-05, "loss": 0.295, "step": 770 }, { "epoch": 0.37037037037037035, "grad_norm": 3.0763488368388328, "learning_rate": 7.397910731244065e-05, "loss": 0.2809, "step": 780 }, { "epoch": 0.37511870845204176, "grad_norm": 2.094402852150148, "learning_rate": 7.492877492877494e-05, "loss": 0.2701, "step": 790 }, { "epoch": 0.3798670465337132, "grad_norm": 2.274287566601407, "learning_rate": 7.587844254510922e-05, "loss": 0.2568, "step": 800 }, { "epoch": 0.38461538461538464, "grad_norm": 1.9068766015691088, "learning_rate": 7.68281101614435e-05, "loss": 0.2463, "step": 810 }, { "epoch": 0.38936372269705605, "grad_norm": 1.9600446391982316, "learning_rate": 7.777777777777778e-05, "loss": 0.2363, "step": 820 }, { "epoch": 0.39411206077872746, "grad_norm": 1.6629965521131573, "learning_rate": 7.872744539411206e-05, "loss": 0.2234, "step": 830 }, { "epoch": 0.39886039886039887, "grad_norm": 2.875635682058353, "learning_rate": 7.967711301044634e-05, "loss": 0.2145, "step": 840 }, { "epoch": 0.4036087369420703, "grad_norm": 1.7911106686775673, "learning_rate": 8.062678062678063e-05, "loss": 0.2081, "step": 850 }, { "epoch": 0.4083570750237417, "grad_norm": 1.8738797366152795, "learning_rate": 8.157644824311491e-05, "loss": 0.1934, "step": 860 }, { "epoch": 0.4131054131054131, "grad_norm": 1.6699636137939626, "learning_rate": 8.25261158594492e-05, "loss": 0.1845, "step": 870 }, { "epoch": 0.4178537511870845, "grad_norm": 2.1263011843663304, "learning_rate": 8.347578347578347e-05, "loss": 0.1815, "step": 880 }, { "epoch": 0.4226020892687559, "grad_norm": 1.637253223509006, "learning_rate": 8.442545109211775e-05, "loss": 0.1677, "step": 890 }, { "epoch": 0.42735042735042733, "grad_norm": 1.6085444053060045, "learning_rate": 8.537511870845205e-05, "loss": 0.1617, "step": 900 }, { "epoch": 0.43209876543209874, "grad_norm": 1.3811533428380767, "learning_rate": 8.632478632478634e-05, "loss": 0.1536, "step": 910 }, { "epoch": 0.4368471035137702, "grad_norm": 1.5957142791343428, "learning_rate": 8.727445394112062e-05, "loss": 0.1471, "step": 920 }, { "epoch": 0.4415954415954416, "grad_norm": 2.077322656782395, "learning_rate": 8.82241215574549e-05, "loss": 0.1367, "step": 930 }, { "epoch": 0.44634377967711303, "grad_norm": 1.3863777124344219, "learning_rate": 8.917378917378918e-05, "loss": 0.1305, "step": 940 }, { "epoch": 0.45109211775878444, "grad_norm": 1.379373447849942, "learning_rate": 9.012345679012346e-05, "loss": 0.1254, "step": 950 }, { "epoch": 0.45584045584045585, "grad_norm": 1.0225553190768473, "learning_rate": 9.107312440645774e-05, "loss": 0.1184, "step": 960 }, { "epoch": 0.46058879392212726, "grad_norm": 1.4701065784223963, "learning_rate": 9.202279202279203e-05, "loss": 0.1142, "step": 970 }, { "epoch": 0.46533713200379867, "grad_norm": 1.1083829513415684, "learning_rate": 9.297245963912631e-05, "loss": 0.1083, "step": 980 }, { "epoch": 0.4700854700854701, "grad_norm": 0.9116224133866325, "learning_rate": 9.392212725546059e-05, "loss": 0.1015, "step": 990 }, { "epoch": 0.4748338081671415, "grad_norm": 1.0732215966409744, "learning_rate": 9.487179487179487e-05, "loss": 0.0981, "step": 1000 }, { "epoch": 0.4795821462488129, "grad_norm": 1.4448532002931684, "learning_rate": 9.582146248812915e-05, "loss": 0.0955, "step": 1010 }, { "epoch": 0.4843304843304843, "grad_norm": 0.9727037977093907, "learning_rate": 9.677113010446344e-05, "loss": 0.0919, "step": 1020 }, { "epoch": 0.4890788224121557, "grad_norm": 0.6538136654859616, "learning_rate": 9.772079772079774e-05, "loss": 0.0843, "step": 1030 }, { "epoch": 0.49382716049382713, "grad_norm": 0.5485567949471478, "learning_rate": 9.867046533713202e-05, "loss": 0.0787, "step": 1040 }, { "epoch": 0.4985754985754986, "grad_norm": 0.8261306762820796, "learning_rate": 9.96201329534663e-05, "loss": 0.0767, "step": 1050 }, { "epoch": 0.50332383665717, "grad_norm": 0.639974727003365, "learning_rate": 9.999990109907572e-05, "loss": 0.0716, "step": 1060 }, { "epoch": 0.5080721747388414, "grad_norm": 0.5475316216026064, "learning_rate": 9.999929670595522e-05, "loss": 0.0686, "step": 1070 }, { "epoch": 0.5128205128205128, "grad_norm": 0.5409377296081475, "learning_rate": 9.99981428713058e-05, "loss": 0.0652, "step": 1080 }, { "epoch": 0.5175688509021842, "grad_norm": 0.7449946627107062, "learning_rate": 9.999643960780693e-05, "loss": 0.0612, "step": 1090 }, { "epoch": 0.5223171889838556, "grad_norm": 0.5311754725201671, "learning_rate": 9.999418693417573e-05, "loss": 0.059, "step": 1100 }, { "epoch": 0.5270655270655271, "grad_norm": 0.4708957925911922, "learning_rate": 9.999138487516681e-05, "loss": 0.0566, "step": 1110 }, { "epoch": 0.5318138651471985, "grad_norm": 0.5784265250336279, "learning_rate": 9.998803346157195e-05, "loss": 0.0564, "step": 1120 }, { "epoch": 0.5365622032288699, "grad_norm": 0.5168678159856918, "learning_rate": 9.99841327302198e-05, "loss": 0.0546, "step": 1130 }, { "epoch": 0.5413105413105413, "grad_norm": 0.32193609799540956, "learning_rate": 9.997968272397542e-05, "loss": 0.0512, "step": 1140 }, { "epoch": 0.5460588793922128, "grad_norm": 0.44104880195699325, "learning_rate": 9.997468349173985e-05, "loss": 0.0487, "step": 1150 }, { "epoch": 0.5508072174738842, "grad_norm": 0.4133398175893821, "learning_rate": 9.99691350884496e-05, "loss": 0.0477, "step": 1160 }, { "epoch": 0.5555555555555556, "grad_norm": 0.37749172837304285, "learning_rate": 9.996303757507602e-05, "loss": 0.0462, "step": 1170 }, { "epoch": 0.560303893637227, "grad_norm": 0.4428973313011144, "learning_rate": 9.995639101862453e-05, "loss": 0.0458, "step": 1180 }, { "epoch": 0.5650522317188984, "grad_norm": 0.3162890941987217, "learning_rate": 9.994919549213408e-05, "loss": 0.0441, "step": 1190 }, { "epoch": 0.5698005698005698, "grad_norm": 0.3125288250812194, "learning_rate": 9.99414510746762e-05, "loss": 0.0425, "step": 1200 }, { "epoch": 0.5745489078822412, "grad_norm": 0.3703137658941141, "learning_rate": 9.993315785135416e-05, "loss": 0.0419, "step": 1210 }, { "epoch": 0.5792972459639126, "grad_norm": 0.31262957519265083, "learning_rate": 9.99243159133021e-05, "loss": 0.0406, "step": 1220 }, { "epoch": 0.584045584045584, "grad_norm": 0.29796796936840436, "learning_rate": 9.991492535768392e-05, "loss": 0.0392, "step": 1230 }, { "epoch": 0.5887939221272555, "grad_norm": 0.3318213355802759, "learning_rate": 9.99049862876923e-05, "loss": 0.0386, "step": 1240 }, { "epoch": 0.5935422602089269, "grad_norm": 0.34217083103520574, "learning_rate": 9.989449881254754e-05, "loss": 0.0382, "step": 1250 }, { "epoch": 0.5982905982905983, "grad_norm": 0.283802792484964, "learning_rate": 9.988346304749635e-05, "loss": 0.0366, "step": 1260 }, { "epoch": 0.6030389363722697, "grad_norm": 0.29414736488607734, "learning_rate": 9.987187911381059e-05, "loss": 0.0359, "step": 1270 }, { "epoch": 0.6077872744539411, "grad_norm": 0.2751603131267791, "learning_rate": 9.985974713878592e-05, "loss": 0.0347, "step": 1280 }, { "epoch": 0.6125356125356125, "grad_norm": 0.2925423079705012, "learning_rate": 9.984706725574044e-05, "loss": 0.0347, "step": 1290 }, { "epoch": 0.6172839506172839, "grad_norm": 0.27725866932297377, "learning_rate": 9.983383960401319e-05, "loss": 0.0336, "step": 1300 }, { "epoch": 0.6220322886989553, "grad_norm": 0.7941618027767806, "learning_rate": 9.982006432896266e-05, "loss": 0.035, "step": 1310 }, { "epoch": 0.6267806267806267, "grad_norm": 1.6840351403640696, "learning_rate": 9.980574158196512e-05, "loss": 0.0524, "step": 1320 }, { "epoch": 0.6315289648622981, "grad_norm": 1.3554091307998244, "learning_rate": 9.979087152041304e-05, "loss": 0.0713, "step": 1330 }, { "epoch": 0.6362773029439696, "grad_norm": 0.36897356801036785, "learning_rate": 9.977545430771332e-05, "loss": 0.0417, "step": 1340 }, { "epoch": 0.6410256410256411, "grad_norm": 0.2904292474002773, "learning_rate": 9.975949011328542e-05, "loss": 0.0347, "step": 1350 }, { "epoch": 0.6457739791073125, "grad_norm": 0.2776192308462496, "learning_rate": 9.97429791125597e-05, "loss": 0.0322, "step": 1360 }, { "epoch": 0.6505223171889839, "grad_norm": 0.2598684841997891, "learning_rate": 9.972592148697528e-05, "loss": 0.0311, "step": 1370 }, { "epoch": 0.6552706552706553, "grad_norm": 0.23868060621698645, "learning_rate": 9.970831742397815e-05, "loss": 0.0302, "step": 1380 }, { "epoch": 0.6600189933523267, "grad_norm": 0.22695749001395263, "learning_rate": 9.969016711701908e-05, "loss": 0.0295, "step": 1390 }, { "epoch": 0.6647673314339981, "grad_norm": 0.23540766289324025, "learning_rate": 9.967147076555157e-05, "loss": 0.0289, "step": 1400 }, { "epoch": 0.6695156695156695, "grad_norm": 0.22325211499568143, "learning_rate": 9.965222857502951e-05, "loss": 0.0277, "step": 1410 }, { "epoch": 0.674264007597341, "grad_norm": 0.20341994994410992, "learning_rate": 9.963244075690505e-05, "loss": 0.0267, "step": 1420 }, { "epoch": 0.6790123456790124, "grad_norm": 0.2082789878363781, "learning_rate": 9.961210752862626e-05, "loss": 0.0266, "step": 1430 }, { "epoch": 0.6837606837606838, "grad_norm": 0.1834817910047751, "learning_rate": 9.959122911363463e-05, "loss": 0.0258, "step": 1440 }, { "epoch": 0.6885090218423552, "grad_norm": 0.20370040107298587, "learning_rate": 9.956980574136281e-05, "loss": 0.0249, "step": 1450 }, { "epoch": 0.6932573599240266, "grad_norm": 0.20761457959687116, "learning_rate": 9.954783764723188e-05, "loss": 0.0245, "step": 1460 }, { "epoch": 0.698005698005698, "grad_norm": 0.19324113426502953, "learning_rate": 9.952532507264891e-05, "loss": 0.0235, "step": 1470 }, { "epoch": 0.7027540360873694, "grad_norm": 0.22152991183679277, "learning_rate": 9.950226826500426e-05, "loss": 0.0235, "step": 1480 }, { "epoch": 0.7075023741690408, "grad_norm": 0.18291746764808686, "learning_rate": 9.947866747766882e-05, "loss": 0.0225, "step": 1490 }, { "epoch": 0.7122507122507122, "grad_norm": 0.18692740414379616, "learning_rate": 9.945452296999131e-05, "loss": 0.0221, "step": 1500 }, { "epoch": 0.7169990503323836, "grad_norm": 0.20635010095393333, "learning_rate": 9.942983500729536e-05, "loss": 0.0215, "step": 1510 }, { "epoch": 0.7217473884140551, "grad_norm": 0.22328566441681175, "learning_rate": 9.940460386087667e-05, "loss": 0.0238, "step": 1520 }, { "epoch": 0.7264957264957265, "grad_norm": 0.22969926818749956, "learning_rate": 9.937882980799986e-05, "loss": 0.0238, "step": 1530 }, { "epoch": 0.7312440645773979, "grad_norm": 0.1891326951743918, "learning_rate": 9.935251313189564e-05, "loss": 0.0212, "step": 1540 }, { "epoch": 0.7359924026590693, "grad_norm": 0.18894118096050505, "learning_rate": 9.93256541217576e-05, "loss": 0.0201, "step": 1550 }, { "epoch": 0.7407407407407407, "grad_norm": 0.16839965478347466, "learning_rate": 9.929825307273898e-05, "loss": 0.0194, "step": 1560 }, { "epoch": 0.7454890788224121, "grad_norm": 0.1651031818463282, "learning_rate": 9.927031028594951e-05, "loss": 0.0188, "step": 1570 }, { "epoch": 0.7502374169040835, "grad_norm": 0.17864976798516016, "learning_rate": 9.924182606845204e-05, "loss": 0.0183, "step": 1580 }, { "epoch": 0.7549857549857549, "grad_norm": 0.15081354129337066, "learning_rate": 9.921280073325922e-05, "loss": 0.0177, "step": 1590 }, { "epoch": 0.7597340930674265, "grad_norm": 0.1492823322050948, "learning_rate": 9.918323459933005e-05, "loss": 0.0171, "step": 1600 }, { "epoch": 0.7644824311490979, "grad_norm": 0.19617624499767475, "learning_rate": 9.915312799156632e-05, "loss": 0.0168, "step": 1610 }, { "epoch": 0.7692307692307693, "grad_norm": 0.19442787986064758, "learning_rate": 9.91224812408091e-05, "loss": 0.0166, "step": 1620 }, { "epoch": 0.7739791073124407, "grad_norm": 0.15196414738372457, "learning_rate": 9.909129468383506e-05, "loss": 0.0161, "step": 1630 }, { "epoch": 0.7787274453941121, "grad_norm": 0.15107912995719286, "learning_rate": 9.905956866335286e-05, "loss": 0.0156, "step": 1640 }, { "epoch": 0.7834757834757835, "grad_norm": 0.18162048926922258, "learning_rate": 9.90273035279992e-05, "loss": 0.0153, "step": 1650 }, { "epoch": 0.7882241215574549, "grad_norm": 0.17872639214115862, "learning_rate": 9.899449963233523e-05, "loss": 0.015, "step": 1660 }, { "epoch": 0.7929724596391263, "grad_norm": 0.15227646692118818, "learning_rate": 9.896115733684244e-05, "loss": 0.0141, "step": 1670 }, { "epoch": 0.7977207977207977, "grad_norm": 0.14676815381097183, "learning_rate": 9.892727700791881e-05, "loss": 0.0143, "step": 1680 }, { "epoch": 0.8024691358024691, "grad_norm": 0.1461341101081371, "learning_rate": 9.889285901787482e-05, "loss": 0.0139, "step": 1690 }, { "epoch": 0.8072174738841406, "grad_norm": 0.144084266582809, "learning_rate": 9.885790374492921e-05, "loss": 0.0133, "step": 1700 }, { "epoch": 0.811965811965812, "grad_norm": 0.1524301640273114, "learning_rate": 9.882241157320497e-05, "loss": 0.0136, "step": 1710 }, { "epoch": 0.8167141500474834, "grad_norm": 0.142713391750164, "learning_rate": 9.878638289272507e-05, "loss": 0.013, "step": 1720 }, { "epoch": 0.8214624881291548, "grad_norm": 0.1684868465091661, "learning_rate": 9.874981809940808e-05, "loss": 0.0133, "step": 1730 }, { "epoch": 0.8262108262108262, "grad_norm": 0.1495843385262352, "learning_rate": 9.871271759506404e-05, "loss": 0.013, "step": 1740 }, { "epoch": 0.8309591642924976, "grad_norm": 0.16249545483594732, "learning_rate": 9.86750817873898e-05, "loss": 0.0123, "step": 1750 }, { "epoch": 0.835707502374169, "grad_norm": 0.1484440363408758, "learning_rate": 9.863691108996471e-05, "loss": 0.0123, "step": 1760 }, { "epoch": 0.8404558404558404, "grad_norm": 0.13923187737177664, "learning_rate": 9.859820592224599e-05, "loss": 0.0118, "step": 1770 }, { "epoch": 0.8452041785375118, "grad_norm": 0.13420351938535, "learning_rate": 9.855896670956415e-05, "loss": 0.0115, "step": 1780 }, { "epoch": 0.8499525166191833, "grad_norm": 0.13630062969945986, "learning_rate": 9.851919388311832e-05, "loss": 0.0114, "step": 1790 }, { "epoch": 0.8547008547008547, "grad_norm": 0.1246353289517896, "learning_rate": 9.84788878799715e-05, "loss": 0.0112, "step": 1800 }, { "epoch": 0.8594491927825261, "grad_norm": 0.14345803685459527, "learning_rate": 9.843804914304577e-05, "loss": 0.011, "step": 1810 }, { "epoch": 0.8641975308641975, "grad_norm": 0.14506693260435694, "learning_rate": 9.839667812111739e-05, "loss": 0.0109, "step": 1820 }, { "epoch": 0.8689458689458689, "grad_norm": 0.12722790203829418, "learning_rate": 9.835477526881189e-05, "loss": 0.0107, "step": 1830 }, { "epoch": 0.8736942070275404, "grad_norm": 0.1163438224056889, "learning_rate": 9.831234104659913e-05, "loss": 0.0101, "step": 1840 }, { "epoch": 0.8784425451092118, "grad_norm": 0.14002925358695015, "learning_rate": 9.826937592078811e-05, "loss": 0.01, "step": 1850 }, { "epoch": 0.8831908831908832, "grad_norm": 0.12645139122469412, "learning_rate": 9.822588036352201e-05, "loss": 0.01, "step": 1860 }, { "epoch": 0.8879392212725546, "grad_norm": 0.1279116230540049, "learning_rate": 9.81818548527728e-05, "loss": 0.01, "step": 1870 }, { "epoch": 0.8926875593542261, "grad_norm": 0.11747423324191776, "learning_rate": 9.81372998723362e-05, "loss": 0.0095, "step": 1880 }, { "epoch": 0.8974358974358975, "grad_norm": 0.1211527355018785, "learning_rate": 9.809221591182623e-05, "loss": 0.0092, "step": 1890 }, { "epoch": 0.9021842355175689, "grad_norm": 0.12293904643959307, "learning_rate": 9.804660346666984e-05, "loss": 0.0091, "step": 1900 }, { "epoch": 0.9069325735992403, "grad_norm": 0.1482409803141583, "learning_rate": 9.800046303810154e-05, "loss": 0.0092, "step": 1910 }, { "epoch": 0.9116809116809117, "grad_norm": 0.11674273639492025, "learning_rate": 9.795379513315779e-05, "loss": 0.009, "step": 1920 }, { "epoch": 0.9164292497625831, "grad_norm": 0.11934587390529006, "learning_rate": 9.790660026467153e-05, "loss": 0.0086, "step": 1930 }, { "epoch": 0.9211775878442545, "grad_norm": 0.14900042200916447, "learning_rate": 9.785887895126644e-05, "loss": 0.0086, "step": 1940 }, { "epoch": 0.9259259259259259, "grad_norm": 0.13568773436282386, "learning_rate": 9.781063171735134e-05, "loss": 0.0088, "step": 1950 }, { "epoch": 0.9306742640075973, "grad_norm": 0.1328365053259777, "learning_rate": 9.776185909311437e-05, "loss": 0.0086, "step": 1960 }, { "epoch": 0.9354226020892688, "grad_norm": 0.13003758649459962, "learning_rate": 9.771256161451716e-05, "loss": 0.0087, "step": 1970 }, { "epoch": 0.9401709401709402, "grad_norm": 0.11812702500699346, "learning_rate": 9.766273982328899e-05, "loss": 0.0082, "step": 1980 }, { "epoch": 0.9449192782526116, "grad_norm": 0.13165164753737524, "learning_rate": 9.761239426692077e-05, "loss": 0.0081, "step": 1990 }, { "epoch": 0.949667616334283, "grad_norm": 0.13407300149292833, "learning_rate": 9.756152549865907e-05, "loss": 0.0082, "step": 2000 }, { "epoch": 0.9544159544159544, "grad_norm": 0.12762091779181864, "learning_rate": 9.751013407750004e-05, "loss": 0.0079, "step": 2010 }, { "epoch": 0.9591642924976258, "grad_norm": 0.12456491400989496, "learning_rate": 9.745822056818324e-05, "loss": 0.008, "step": 2020 }, { "epoch": 0.9639126305792972, "grad_norm": 0.12223601838894273, "learning_rate": 9.740578554118545e-05, "loss": 0.0077, "step": 2030 }, { "epoch": 0.9686609686609686, "grad_norm": 0.10941058482154375, "learning_rate": 9.735282957271438e-05, "loss": 0.0075, "step": 2040 }, { "epoch": 0.97340930674264, "grad_norm": 0.10280049040448914, "learning_rate": 9.729935324470243e-05, "loss": 0.0074, "step": 2050 }, { "epoch": 0.9781576448243114, "grad_norm": 0.11721819495852459, "learning_rate": 9.724535714480012e-05, "loss": 0.0072, "step": 2060 }, { "epoch": 0.9829059829059829, "grad_norm": 0.12854328456395978, "learning_rate": 9.719084186636984e-05, "loss": 0.0072, "step": 2070 }, { "epoch": 0.9876543209876543, "grad_norm": 0.11608851834126488, "learning_rate": 9.713580800847916e-05, "loss": 0.0071, "step": 2080 }, { "epoch": 0.9924026590693258, "grad_norm": 0.11446727537621004, "learning_rate": 9.708025617589431e-05, "loss": 0.0071, "step": 2090 }, { "epoch": 0.9971509971509972, "grad_norm": 0.13203067710053076, "learning_rate": 9.702418697907357e-05, "loss": 0.007, "step": 2100 }, { "epoch": 1.0018993352326686, "grad_norm": 0.1181182954370442, "learning_rate": 9.696760103416049e-05, "loss": 0.0066, "step": 2110 }, { "epoch": 1.00664767331434, "grad_norm": 0.11408210884452168, "learning_rate": 9.69104989629772e-05, "loss": 0.0063, "step": 2120 }, { "epoch": 1.0113960113960114, "grad_norm": 0.13157429410214536, "learning_rate": 9.685288139301749e-05, "loss": 0.0062, "step": 2130 }, { "epoch": 1.0161443494776827, "grad_norm": 0.11970089437493539, "learning_rate": 9.679474895744002e-05, "loss": 0.0063, "step": 2140 }, { "epoch": 1.0208926875593543, "grad_norm": 0.11388191798417464, "learning_rate": 9.673610229506123e-05, "loss": 0.0059, "step": 2150 }, { "epoch": 1.0256410256410255, "grad_norm": 0.08441090681599825, "learning_rate": 9.667694205034842e-05, "loss": 0.0057, "step": 2160 }, { "epoch": 1.030389363722697, "grad_norm": 0.11689750221829001, "learning_rate": 9.661726887341264e-05, "loss": 0.006, "step": 2170 }, { "epoch": 1.0351377018043684, "grad_norm": 0.11274428393327461, "learning_rate": 9.655708342000158e-05, "loss": 0.0059, "step": 2180 }, { "epoch": 1.03988603988604, "grad_norm": 0.10098582123991313, "learning_rate": 9.649638635149225e-05, "loss": 0.0056, "step": 2190 }, { "epoch": 1.0446343779677112, "grad_norm": 0.1033996217337553, "learning_rate": 9.643517833488387e-05, "loss": 0.0058, "step": 2200 }, { "epoch": 1.0493827160493827, "grad_norm": 0.12602732630184946, "learning_rate": 9.637346004279038e-05, "loss": 0.0062, "step": 2210 }, { "epoch": 1.0541310541310542, "grad_norm": 0.1608507502875564, "learning_rate": 9.631123215343323e-05, "loss": 0.0056, "step": 2220 }, { "epoch": 1.0588793922127255, "grad_norm": 0.11475788599163383, "learning_rate": 9.624849535063373e-05, "loss": 0.0057, "step": 2230 }, { "epoch": 1.063627730294397, "grad_norm": 0.10081600705293761, "learning_rate": 9.61852503238057e-05, "loss": 0.0056, "step": 2240 }, { "epoch": 1.0683760683760684, "grad_norm": 0.09109365869270909, "learning_rate": 9.612149776794776e-05, "loss": 0.0057, "step": 2250 }, { "epoch": 1.0731244064577399, "grad_norm": 0.09152185491210062, "learning_rate": 9.605723838363586e-05, "loss": 0.0055, "step": 2260 }, { "epoch": 1.0778727445394112, "grad_norm": 0.10304657297255751, "learning_rate": 9.599247287701539e-05, "loss": 0.0053, "step": 2270 }, { "epoch": 1.0826210826210827, "grad_norm": 0.1120323110613297, "learning_rate": 9.592720195979353e-05, "loss": 0.0054, "step": 2280 }, { "epoch": 1.087369420702754, "grad_norm": 0.12251903528255756, "learning_rate": 9.586142634923141e-05, "loss": 0.0052, "step": 2290 }, { "epoch": 1.0921177587844255, "grad_norm": 0.10412028931581724, "learning_rate": 9.579514676813627e-05, "loss": 0.0052, "step": 2300 }, { "epoch": 1.0968660968660968, "grad_norm": 0.09996891892419266, "learning_rate": 9.572836394485345e-05, "loss": 0.005, "step": 2310 }, { "epoch": 1.1016144349477683, "grad_norm": 0.09706126483807406, "learning_rate": 9.566107861325836e-05, "loss": 0.0052, "step": 2320 }, { "epoch": 1.1063627730294396, "grad_norm": 0.09276552171641933, "learning_rate": 9.559329151274854e-05, "loss": 0.005, "step": 2330 }, { "epoch": 1.1111111111111112, "grad_norm": 0.09136162436626215, "learning_rate": 9.552500338823543e-05, "loss": 0.0048, "step": 2340 }, { "epoch": 1.1158594491927825, "grad_norm": 0.1058965116466736, "learning_rate": 9.54562149901362e-05, "loss": 0.0048, "step": 2350 }, { "epoch": 1.120607787274454, "grad_norm": 0.0852597845490393, "learning_rate": 9.538692707436554e-05, "loss": 0.0047, "step": 2360 }, { "epoch": 1.1253561253561253, "grad_norm": 0.11391418801796557, "learning_rate": 9.531714040232733e-05, "loss": 0.0047, "step": 2370 }, { "epoch": 1.1301044634377968, "grad_norm": 0.10315295981745898, "learning_rate": 9.524685574090627e-05, "loss": 0.0047, "step": 2380 }, { "epoch": 1.134852801519468, "grad_norm": 0.1056230183532422, "learning_rate": 9.517607386245948e-05, "loss": 0.0047, "step": 2390 }, { "epoch": 1.1396011396011396, "grad_norm": 0.10469277147682136, "learning_rate": 9.510479554480793e-05, "loss": 0.0047, "step": 2400 }, { "epoch": 1.144349477682811, "grad_norm": 0.0946041447007643, "learning_rate": 9.503302157122804e-05, "loss": 0.0045, "step": 2410 }, { "epoch": 1.1490978157644824, "grad_norm": 0.08630800421431441, "learning_rate": 9.496075273044293e-05, "loss": 0.0045, "step": 2420 }, { "epoch": 1.1538461538461537, "grad_norm": 0.08863274697939626, "learning_rate": 9.488798981661379e-05, "loss": 0.0045, "step": 2430 }, { "epoch": 1.1585944919278253, "grad_norm": 0.09077160610736557, "learning_rate": 9.481473362933122e-05, "loss": 0.0048, "step": 2440 }, { "epoch": 1.1633428300094968, "grad_norm": 0.09665070075222562, "learning_rate": 9.474098497360637e-05, "loss": 0.0046, "step": 2450 }, { "epoch": 1.168091168091168, "grad_norm": 0.09391971124218054, "learning_rate": 9.466674465986211e-05, "loss": 0.0045, "step": 2460 }, { "epoch": 1.1728395061728394, "grad_norm": 0.08789599761967867, "learning_rate": 9.459201350392418e-05, "loss": 0.0044, "step": 2470 }, { "epoch": 1.177587844254511, "grad_norm": 0.0872699522223815, "learning_rate": 9.451679232701212e-05, "loss": 0.0045, "step": 2480 }, { "epoch": 1.1823361823361824, "grad_norm": 0.22001860863117792, "learning_rate": 9.444108195573031e-05, "loss": 0.0047, "step": 2490 }, { "epoch": 1.1870845204178537, "grad_norm": 0.140562428680801, "learning_rate": 9.436488322205892e-05, "loss": 0.0056, "step": 2500 }, { "epoch": 1.1918328584995252, "grad_norm": 0.10025358944697903, "learning_rate": 9.42881969633447e-05, "loss": 0.0049, "step": 2510 }, { "epoch": 1.1965811965811965, "grad_norm": 0.11417005189788736, "learning_rate": 9.42110240222918e-05, "loss": 0.0045, "step": 2520 }, { "epoch": 1.201329534662868, "grad_norm": 0.10016368862810253, "learning_rate": 9.413336524695253e-05, "loss": 0.0044, "step": 2530 }, { "epoch": 1.2060778727445394, "grad_norm": 0.1054090147272164, "learning_rate": 9.405522149071801e-05, "loss": 0.0045, "step": 2540 }, { "epoch": 1.210826210826211, "grad_norm": 0.08462731008500991, "learning_rate": 9.397659361230883e-05, "loss": 0.0043, "step": 2550 }, { "epoch": 1.2155745489078822, "grad_norm": 0.07544323769645477, "learning_rate": 9.389748247576557e-05, "loss": 0.0042, "step": 2560 }, { "epoch": 1.2203228869895537, "grad_norm": 0.09247962241535229, "learning_rate": 9.381788895043933e-05, "loss": 0.0043, "step": 2570 }, { "epoch": 1.225071225071225, "grad_norm": 0.09760578731093097, "learning_rate": 9.373781391098218e-05, "loss": 0.0044, "step": 2580 }, { "epoch": 1.2298195631528965, "grad_norm": 0.08261862930810554, "learning_rate": 9.365725823733753e-05, "loss": 0.0042, "step": 2590 }, { "epoch": 1.2345679012345678, "grad_norm": 0.09531812579252252, "learning_rate": 9.35762228147305e-05, "loss": 0.0042, "step": 2600 }, { "epoch": 1.2393162393162394, "grad_norm": 0.1174538965335085, "learning_rate": 9.349470853365815e-05, "loss": 0.0042, "step": 2610 }, { "epoch": 1.2440645773979107, "grad_norm": 0.08548743992987816, "learning_rate": 9.341271628987968e-05, "loss": 0.0043, "step": 2620 }, { "epoch": 1.2488129154795822, "grad_norm": 0.09576582546053228, "learning_rate": 9.333024698440667e-05, "loss": 0.0042, "step": 2630 }, { "epoch": 1.2535612535612537, "grad_norm": 0.09559728611442127, "learning_rate": 9.324730152349306e-05, "loss": 0.0041, "step": 2640 }, { "epoch": 1.258309591642925, "grad_norm": 0.1007238852682294, "learning_rate": 9.31638808186253e-05, "loss": 0.0048, "step": 2650 }, { "epoch": 1.2630579297245963, "grad_norm": 0.11616087329471156, "learning_rate": 9.307998578651228e-05, "loss": 0.0042, "step": 2660 }, { "epoch": 1.2678062678062678, "grad_norm": 0.09621091341632317, "learning_rate": 9.299561734907528e-05, "loss": 0.0042, "step": 2670 }, { "epoch": 1.2725546058879393, "grad_norm": 0.08108310161966806, "learning_rate": 9.291077643343776e-05, "loss": 0.004, "step": 2680 }, { "epoch": 1.2773029439696106, "grad_norm": 0.08260063413069021, "learning_rate": 9.282546397191531e-05, "loss": 0.0038, "step": 2690 }, { "epoch": 1.282051282051282, "grad_norm": 0.08841115374830935, "learning_rate": 9.273968090200533e-05, "loss": 0.0039, "step": 2700 }, { "epoch": 1.2867996201329535, "grad_norm": 0.09066775737012889, "learning_rate": 9.265342816637666e-05, "loss": 0.0039, "step": 2710 }, { "epoch": 1.291547958214625, "grad_norm": 0.07987204818425336, "learning_rate": 9.256670671285934e-05, "loss": 0.004, "step": 2720 }, { "epoch": 1.2962962962962963, "grad_norm": 0.06944382614619178, "learning_rate": 9.247951749443413e-05, "loss": 0.0037, "step": 2730 }, { "epoch": 1.3010446343779676, "grad_norm": 0.0780297931194837, "learning_rate": 9.239186146922208e-05, "loss": 0.0037, "step": 2740 }, { "epoch": 1.305792972459639, "grad_norm": 0.07741505632615943, "learning_rate": 9.230373960047394e-05, "loss": 0.0037, "step": 2750 }, { "epoch": 1.3105413105413106, "grad_norm": 0.07774491429364261, "learning_rate": 9.22151528565596e-05, "loss": 0.0035, "step": 2760 }, { "epoch": 1.315289648622982, "grad_norm": 0.08974337782810247, "learning_rate": 9.212610221095748e-05, "loss": 0.0036, "step": 2770 }, { "epoch": 1.3200379867046534, "grad_norm": 0.07048073853858783, "learning_rate": 9.203658864224382e-05, "loss": 0.0036, "step": 2780 }, { "epoch": 1.3247863247863247, "grad_norm": 0.09888847833471957, "learning_rate": 9.194661313408187e-05, "loss": 0.0035, "step": 2790 }, { "epoch": 1.3295346628679963, "grad_norm": 0.0788598184186524, "learning_rate": 9.185617667521117e-05, "loss": 0.0036, "step": 2800 }, { "epoch": 1.3342830009496676, "grad_norm": 0.06913587027701612, "learning_rate": 9.176528025943663e-05, "loss": 0.0035, "step": 2810 }, { "epoch": 1.339031339031339, "grad_norm": 0.10829516653874842, "learning_rate": 9.167392488561758e-05, "loss": 0.0037, "step": 2820 }, { "epoch": 1.3437796771130104, "grad_norm": 0.07407529609882196, "learning_rate": 9.158211155765692e-05, "loss": 0.0034, "step": 2830 }, { "epoch": 1.348528015194682, "grad_norm": 0.0738892487380136, "learning_rate": 9.14898412844899e-05, "loss": 0.0035, "step": 2840 }, { "epoch": 1.3532763532763532, "grad_norm": 0.09083788378231447, "learning_rate": 9.13971150800732e-05, "loss": 0.0034, "step": 2850 }, { "epoch": 1.3580246913580247, "grad_norm": 0.06748049777692004, "learning_rate": 9.130393396337368e-05, "loss": 0.0035, "step": 2860 }, { "epoch": 1.362773029439696, "grad_norm": 0.06931027153606457, "learning_rate": 9.121029895835731e-05, "loss": 0.0034, "step": 2870 }, { "epoch": 1.3675213675213675, "grad_norm": 0.07142662712039213, "learning_rate": 9.111621109397769e-05, "loss": 0.0033, "step": 2880 }, { "epoch": 1.3722697056030388, "grad_norm": 0.07754467744413668, "learning_rate": 9.102167140416503e-05, "loss": 0.0032, "step": 2890 }, { "epoch": 1.3770180436847104, "grad_norm": 0.07290606205834894, "learning_rate": 9.092668092781454e-05, "loss": 0.0032, "step": 2900 }, { "epoch": 1.381766381766382, "grad_norm": 0.08139374143245391, "learning_rate": 9.083124070877516e-05, "loss": 0.0033, "step": 2910 }, { "epoch": 1.3865147198480532, "grad_norm": 0.0704151002522339, "learning_rate": 9.073535179583806e-05, "loss": 0.0033, "step": 2920 }, { "epoch": 1.3912630579297245, "grad_norm": 0.07284709978462862, "learning_rate": 9.063901524272505e-05, "loss": 0.0032, "step": 2930 }, { "epoch": 1.396011396011396, "grad_norm": 0.08035026789508909, "learning_rate": 9.054223210807709e-05, "loss": 0.0032, "step": 2940 }, { "epoch": 1.4007597340930675, "grad_norm": 0.07416292784019261, "learning_rate": 9.044500345544262e-05, "loss": 0.0031, "step": 2950 }, { "epoch": 1.4055080721747388, "grad_norm": 0.059128318497472195, "learning_rate": 9.034733035326584e-05, "loss": 0.0032, "step": 2960 }, { "epoch": 1.4102564102564101, "grad_norm": 0.08358939462158771, "learning_rate": 9.024921387487504e-05, "loss": 0.0031, "step": 2970 }, { "epoch": 1.4150047483380817, "grad_norm": 0.0794870565834276, "learning_rate": 9.015065509847075e-05, "loss": 0.0031, "step": 2980 }, { "epoch": 1.4197530864197532, "grad_norm": 0.07762466294912042, "learning_rate": 9.005165510711387e-05, "loss": 0.0032, "step": 2990 }, { "epoch": 1.4245014245014245, "grad_norm": 0.08039569280537912, "learning_rate": 8.995221498871387e-05, "loss": 0.0031, "step": 3000 }, { "epoch": 1.429249762583096, "grad_norm": 0.06991816186417003, "learning_rate": 8.98523358360167e-05, "loss": 0.003, "step": 3010 }, { "epoch": 1.4339981006647673, "grad_norm": 0.07192860262939446, "learning_rate": 8.975201874659292e-05, "loss": 0.0031, "step": 3020 }, { "epoch": 1.4387464387464388, "grad_norm": 0.1463170468469212, "learning_rate": 8.965126482282549e-05, "loss": 0.0032, "step": 3030 }, { "epoch": 1.4434947768281101, "grad_norm": 1.3520752077854254, "learning_rate": 8.955007517189784e-05, "loss": 0.0194, "step": 3040 }, { "epoch": 1.4482431149097816, "grad_norm": 0.7948815643934889, "learning_rate": 8.944845090578149e-05, "loss": 0.0598, "step": 3050 }, { "epoch": 1.452991452991453, "grad_norm": 0.2516141865538996, "learning_rate": 8.934639314122401e-05, "loss": 0.0162, "step": 3060 }, { "epoch": 1.4577397910731245, "grad_norm": 1.168314858024135, "learning_rate": 8.924390299973666e-05, "loss": 0.0254, "step": 3070 }, { "epoch": 1.4624881291547958, "grad_norm": 0.602695086469322, "learning_rate": 8.91409816075821e-05, "loss": 0.0417, "step": 3080 }, { "epoch": 1.4672364672364673, "grad_norm": 0.15485966185215264, "learning_rate": 8.903763009576195e-05, "loss": 0.0126, "step": 3090 }, { "epoch": 1.4719848053181386, "grad_norm": 0.10127339560973059, "learning_rate": 8.893384960000445e-05, "loss": 0.007, "step": 3100 }, { "epoch": 1.47673314339981, "grad_norm": 0.09215853276110185, "learning_rate": 8.882964126075192e-05, "loss": 0.0049, "step": 3110 }, { "epoch": 1.4814814814814814, "grad_norm": 0.08598358901178002, "learning_rate": 8.872500622314829e-05, "loss": 0.0046, "step": 3120 }, { "epoch": 1.486229819563153, "grad_norm": 0.06802382656872473, "learning_rate": 8.861994563702638e-05, "loss": 0.004, "step": 3130 }, { "epoch": 1.4909781576448244, "grad_norm": 0.07530694013806413, "learning_rate": 8.851446065689544e-05, "loss": 0.0038, "step": 3140 }, { "epoch": 1.4957264957264957, "grad_norm": 0.06332501409410973, "learning_rate": 8.840855244192836e-05, "loss": 0.0034, "step": 3150 }, { "epoch": 1.500474833808167, "grad_norm": 0.073015791882403, "learning_rate": 8.83022221559489e-05, "loss": 0.0034, "step": 3160 }, { "epoch": 1.5052231718898386, "grad_norm": 0.0670117459789316, "learning_rate": 8.819547096741904e-05, "loss": 0.0032, "step": 3170 }, { "epoch": 1.50997150997151, "grad_norm": 0.0717273519967652, "learning_rate": 8.8088300049426e-05, "loss": 0.003, "step": 3180 }, { "epoch": 1.5147198480531814, "grad_norm": 0.07039799018841889, "learning_rate": 8.798071057966935e-05, "loss": 0.003, "step": 3190 }, { "epoch": 1.5194681861348527, "grad_norm": 0.061310355995191274, "learning_rate": 8.787270374044824e-05, "loss": 0.003, "step": 3200 }, { "epoch": 1.5242165242165242, "grad_norm": 0.06607257587428796, "learning_rate": 8.776428071864819e-05, "loss": 0.0029, "step": 3210 }, { "epoch": 1.5289648622981957, "grad_norm": 0.05639906637179054, "learning_rate": 8.76554427057282e-05, "loss": 0.0028, "step": 3220 }, { "epoch": 1.533713200379867, "grad_norm": 0.05845008796172244, "learning_rate": 8.754619089770755e-05, "loss": 0.0029, "step": 3230 }, { "epoch": 1.5384615384615383, "grad_norm": 0.06413076337172967, "learning_rate": 8.743652649515275e-05, "loss": 0.0028, "step": 3240 }, { "epoch": 1.5432098765432098, "grad_norm": 0.06214647290342327, "learning_rate": 8.73264507031643e-05, "loss": 0.0028, "step": 3250 }, { "epoch": 1.5479582146248814, "grad_norm": 0.06005110260846312, "learning_rate": 8.721596473136342e-05, "loss": 0.0027, "step": 3260 }, { "epoch": 1.5527065527065527, "grad_norm": 0.06833817241779995, "learning_rate": 8.710506979387882e-05, "loss": 0.0028, "step": 3270 }, { "epoch": 1.557454890788224, "grad_norm": 0.06021939597837059, "learning_rate": 8.699376710933336e-05, "loss": 0.0027, "step": 3280 }, { "epoch": 1.5622032288698955, "grad_norm": 0.06009888288480629, "learning_rate": 8.688205790083053e-05, "loss": 0.0026, "step": 3290 }, { "epoch": 1.566951566951567, "grad_norm": 0.056310989938336484, "learning_rate": 8.676994339594118e-05, "loss": 0.0025, "step": 3300 }, { "epoch": 1.5716999050332383, "grad_norm": 0.05386134868136637, "learning_rate": 8.665742482668996e-05, "loss": 0.0025, "step": 3310 }, { "epoch": 1.5764482431149098, "grad_norm": 0.06851904227000911, "learning_rate": 8.654450342954175e-05, "loss": 0.0025, "step": 3320 }, { "epoch": 1.5811965811965814, "grad_norm": 0.06066123206668021, "learning_rate": 8.643118044538808e-05, "loss": 0.0026, "step": 3330 }, { "epoch": 1.5859449192782527, "grad_norm": 0.06233337795455967, "learning_rate": 8.631745711953357e-05, "loss": 0.0026, "step": 3340 }, { "epoch": 1.590693257359924, "grad_norm": 0.05857550402071415, "learning_rate": 8.620333470168214e-05, "loss": 0.0025, "step": 3350 }, { "epoch": 1.5954415954415955, "grad_norm": 0.054472718028662076, "learning_rate": 8.608881444592337e-05, "loss": 0.0024, "step": 3360 }, { "epoch": 1.600189933523267, "grad_norm": 0.061338037134372705, "learning_rate": 8.597389761071862e-05, "loss": 0.0024, "step": 3370 }, { "epoch": 1.6049382716049383, "grad_norm": 0.06126455979483316, "learning_rate": 8.58585854588873e-05, "loss": 0.0024, "step": 3380 }, { "epoch": 1.6096866096866096, "grad_norm": 0.04904972384151903, "learning_rate": 8.574287925759294e-05, "loss": 0.0025, "step": 3390 }, { "epoch": 1.6144349477682811, "grad_norm": 0.06535964315699233, "learning_rate": 8.562678027832925e-05, "loss": 0.0026, "step": 3400 }, { "epoch": 1.6191832858499526, "grad_norm": 0.0566749828887955, "learning_rate": 8.551028979690621e-05, "loss": 0.0024, "step": 3410 }, { "epoch": 1.623931623931624, "grad_norm": 0.05349963580946675, "learning_rate": 8.539340909343597e-05, "loss": 0.0024, "step": 3420 }, { "epoch": 1.6286799620132952, "grad_norm": 0.062200638926613656, "learning_rate": 8.527613945231885e-05, "loss": 0.0024, "step": 3430 }, { "epoch": 1.6334283000949668, "grad_norm": 0.06769370276522023, "learning_rate": 8.51584821622292e-05, "loss": 0.0024, "step": 3440 }, { "epoch": 1.6381766381766383, "grad_norm": 0.06723030988054225, "learning_rate": 8.504043851610122e-05, "loss": 0.0022, "step": 3450 }, { "epoch": 1.6429249762583096, "grad_norm": 0.06327028018982928, "learning_rate": 8.492200981111482e-05, "loss": 0.0023, "step": 3460 }, { "epoch": 1.6476733143399809, "grad_norm": 0.06622292060619561, "learning_rate": 8.480319734868124e-05, "loss": 0.0023, "step": 3470 }, { "epoch": 1.6524216524216524, "grad_norm": 0.058077310337942605, "learning_rate": 8.468400243442888e-05, "loss": 0.0023, "step": 3480 }, { "epoch": 1.657169990503324, "grad_norm": 0.052519164823119004, "learning_rate": 8.456442637818889e-05, "loss": 0.0022, "step": 3490 }, { "epoch": 1.6619183285849952, "grad_norm": 0.06416308701543828, "learning_rate": 8.444447049398076e-05, "loss": 0.0022, "step": 3500 }, { "epoch": 1.6666666666666665, "grad_norm": 0.05176049997293671, "learning_rate": 8.432413609999794e-05, "loss": 0.0023, "step": 3510 }, { "epoch": 1.671415004748338, "grad_norm": 0.054921230364693076, "learning_rate": 8.420342451859329e-05, "loss": 0.0023, "step": 3520 }, { "epoch": 1.6761633428300096, "grad_norm": 0.05169385443721526, "learning_rate": 8.408233707626458e-05, "loss": 0.0021, "step": 3530 }, { "epoch": 1.6809116809116809, "grad_norm": 0.06081669303085387, "learning_rate": 8.39608751036399e-05, "loss": 0.0023, "step": 3540 }, { "epoch": 1.6856600189933522, "grad_norm": 0.06271425983547295, "learning_rate": 8.383903993546311e-05, "loss": 0.0023, "step": 3550 }, { "epoch": 1.690408357075024, "grad_norm": 0.06661746950466081, "learning_rate": 8.371683291057902e-05, "loss": 0.0022, "step": 3560 }, { "epoch": 1.6951566951566952, "grad_norm": 0.054041560782742026, "learning_rate": 8.359425537191883e-05, "loss": 0.0023, "step": 3570 }, { "epoch": 1.6999050332383665, "grad_norm": 0.05355240517739856, "learning_rate": 8.347130866648528e-05, "loss": 0.0022, "step": 3580 }, { "epoch": 1.704653371320038, "grad_norm": 0.05632475914741002, "learning_rate": 8.334799414533791e-05, "loss": 0.0022, "step": 3590 }, { "epoch": 1.7094017094017095, "grad_norm": 0.058940934906551334, "learning_rate": 8.322431316357815e-05, "loss": 0.0022, "step": 3600 } ], "logging_steps": 10, "max_steps": 10530, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 1800, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 332520438104064.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }